Merge branch 'master' of github.com:zhayujie/chatgpt-on-wechat

fix(read): correct off-by-one for negative offset with trailing newline

.github/ISSUE_TEMPLATE/1.bug.yml

@@ -1,133 +1,46 @@
 name: Bug report 🐛
-description: 项目运行中遇到的Bug或问题。
+description: Report a bug or unexpected behavior.
+title: "[Bug] "
 labels: ['status: needs check']
 body:
   - type: markdown
     attributes:
       value: |
-        ### ⚠️ 前置确认
+        > 💡 English is recommended so global developers can help. 推荐使用英文提交，谢谢 ❤️
-        1. 网络能够访问openai接口
-        2. python 已安装：版本在 3.7 ~ 3.10 之间
-        3. `git pull` 拉取最新代码
-        4. 执行`pip3 install -r requirements.txt`，检查依赖是否满足
-        5. 拓展功能请执行`pip3 install -r requirements-optional.txt`，检查依赖是否满足
-        6. [FAQS](https://github.com/zhayujie/chatgpt-on-wechat/wiki/FAQs) 中无类似问题
   - type: checkboxes
     attributes:
-      label: 前置确认
+      label: Self check
       options:
-        - label: 我确认我运行的是最新版本的代码，并且安装了所需的依赖，在[FAQS](https://github.com/zhayujie/chatgpt-on-wechat/wiki/FAQs)中也未找到类似问题。
+        - label: I'm on the latest version and searched [existing issues](https://github.com/zhayujie/CowAgent/issues) (incl. closed) — no duplicate.
           required: true
-  - type: checkboxes
+  - type: textarea
     attributes:
-      label: ⚠️ 搜索issues中是否已存在类似问题
+      label: Environment
-      description: >
+      description: "Version (`cow status`), OS, Python version, install method, model & channel."
-        请在 [历史issue](https://github.com/zhayujie/chatgpt-on-wechat/issues) 中清空输入框，搜索你的问题
+      placeholder: |
-        或相关日志的关键词来查找是否存在类似问题。
+        Version: v1.2.0
-      options:
+        OS: macOS / Linux / Windows / Docker
-        - label: 我已经搜索过issues和disscussions，没有跟我遇到的问题相关的issue
+        Python: 3.11
-          required: true
+        Install: installer / Docker / source
-  - type: markdown
+        Model & channel: deepseek-v4-flash, web
-    attributes:
-      value: |
-        请在上方的`title`中填写你对你所遇到问题的简略总结，这将帮助其他人更好的找到相似问题，谢谢❤️。
-  - type: dropdown
-    attributes:
-      label: 操作系统类型?
-      description: >
-        请选择你运行程序的操作系统类型。
-      options:
-        - Windows
-        - Linux
-        - MacOS
-        - Docker
-        - Railway
-        - Windows Subsystem for Linux (WSL)
-        - Other (请在问题中说明)
-    validations:
-      required: true
-  - type: dropdown
-    attributes:
-      label: 运行的python版本是?
-      description: |
-        请选择你运行程序的`python`版本。
-        注意：在`python 3.7`中，有部分可选依赖无法安装。
-        经过长时间的观察，我们认为`python 3.8`是兼容性最好的版本。
-        `python 3.7`~`python 3.10`以外版本的issue，将视情况直接关闭。
-      options:
-        - python 3.7
-        - python 3.8
-        - python 3.9
-        - python 3.10
-        - other
-    validations:
-      required: true
-  - type: dropdown
-    attributes:
-      label: 使用的chatgpt-on-wechat版本是?
-      description: |
-        请确保你使用的是 [releases](https://github.com/zhayujie/chatgpt-on-wechat/releases) 中的最新版本。
-        如果你使用git, 请使用`git branch`命令来查看分支。
-      options:
-        - Latest Release
-        - Master (branch)
-    validations:
-      required: true
-  - type: dropdown
-    attributes:
-      label: 运行的`channel`类型是?
-      description: |
-        请确保你正确配置了该`channel`所需的配置项，所有可选的配置项都写在了[该文件中](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/config.py)，请将所需配置项填写在根目录下的`config.json`文件中。
-      options:
-        - wx(个人微信, itchat)
-        - wxy(个人微信, wechaty)
-        - wechatmp(公众号, 订阅号)
-        - wechatmp_service(公众号, 服务号)
-        - terminal
-        - other
     validations:
       required: true
   - type: textarea
     attributes:
-      label: 复现步骤 🕹
+      label: What happened?
-      description: |
+      description: "Steps to reproduce, what you expected, and what happened instead. Screenshots welcome."
-        **⚠️ 不能复现将会关闭issue.**
+      placeholder: |
-  - type: textarea
+        1. ...
-    attributes:
+        2. ...
-      label: 问题描述 😯
-      description: 详细描述出现的问题，或提供有关截图。
-  - type: textarea
-    attributes:
-      label: 终端日志 📒
-      description: |
-        在此处粘贴终端日志，可在主目录下`run.log`文件中找到，这会帮助我们更好的分析问题，注意隐去你的API key。
-        如果在配置文件中加入`"debug": true`，打印出的日志会更有帮助。
 
-        <details>
+        Expected: ...
-        <summary><i>示例</i></summary>
+        Actual: ...
-        ```log
+    validations:
-        [DEBUG][2023-04-16 00:23:22][plugin_manager.py:157] - Plugin SUMMARY triggered by event Event.ON_HANDLE_CONTEXT
+      required: true
-        [DEBUG][2023-04-16 00:23:22][main.py:221] - [Summary] on_handle_context. content: $总结前100条消息
+  - type: textarea
-        [DEBUG][2023-04-16 00:23:24][main.py:240] - [Summary] limit: 100, duration: -1 seconds
+    attributes:
-        [ERROR][2023-04-16 00:23:24][chat_channel.py:244] - Worker return exception: name 'start_date' is not defined
+      label: Logs
-        Traceback (most recent call last):
+      description: "Relevant logs from `run.log` (set `\"debug\": true` for more detail). ⚠️ Redact your API keys."
-          File "C:\ProgramData\Anaconda3\lib\concurrent\futures\thread.py", line 57, in run
+      render: shell
-            result = self.fn(*self.args, **self.kwargs)
+    validations:
-          File "D:\project\chatgpt-on-wechat\channel\chat_channel.py", line 132, in _handle
+      required: false
-            reply = self._generate_reply(context)
-          File "D:\project\chatgpt-on-wechat\channel\chat_channel.py", line 142, in _generate_reply
-            e_context = PluginManager().emit_event(EventContext(Event.ON_HANDLE_CONTEXT, {
-          File "D:\project\chatgpt-on-wechat\plugins\plugin_manager.py", line 159, in emit_event
-            instance.handlers[e_context.event](e_context, *args, **kwargs)
-          File "D:\project\chatgpt-on-wechat\plugins\summary\main.py", line 255, in on_handle_context
-            records = self._get_records(session_id, start_time, limit)
-          File "D:\project\chatgpt-on-wechat\plugins\summary\main.py", line 96, in _get_records
-            c.execute("SELECT * FROM chat_records WHERE sessionid=? and timestamp>? ORDER BY timestamp DESC LIMIT ?", (session_id, start_date, limit))
-        NameError: name 'start_date' is not defined
-        [INFO][2023-04-16 00:23:36][app.py:14] - signal 2 received, exiting...
-        ```
-        </details>
-      value: |
-        ```log
-        <此处粘贴终端日志>
-        ```

.github/ISSUE_TEMPLATE/2.feature.yml

@@ -1,28 +1,33 @@
 name: Feature request 🚀
-description: 提出你对项目的新想法或建议。
+description: Suggest a new idea or improvement.
+title: "[Feature] "
 labels: ['status: needs check']
 body:
   - type: markdown
     attributes:
       value: |
-        请在上方的`title`中填写简略总结，谢谢❤️。
+        > 💡 English is recommended so global developers can help. 推荐使用英文提交，谢谢 ❤️
   - type: checkboxes
     attributes:
-      label: ⚠️ 搜索是否存在类似issue
+      label: Self check
-      description: >
-        请在 [历史issue](https://github.com/zhayujie/chatgpt-on-wechat/issues) 中清空输入框，搜索关键词查找是否存在相似issue。
       options:
-        - label: 我已经搜索过issues和disscussions，没有发现相似issue
+        - label: I searched [existing issues](https://github.com/zhayujie/CowAgent/issues) (incl. closed) — no duplicate.
           required: true
   - type: textarea
     attributes:
-      label: 总结
+      label: What's the problem?
-      description: 描述feature的功能。
+      description: "The pain point or what's not working for you right now."
+    validations:
+      required: true
   - type: textarea
     attributes:
-      label: 举例
+      label: What would you like?
-      description: 提供聊天示例，草图或相关网址。
+      description: "How you'd expect it to work. Examples, sketches, or links welcome."
-  - type: textarea
+    validations:
+      required: false
+  - type: checkboxes
     attributes:
-      label: 动机
+      label: Contribution
-      description: 描述你提出该feature的动机，比如没有这项feature对你的使用造成了怎样的影响。 请提供更详细的场景描述，这可能会帮助我们发现并提出更好的解决方案。
+      options:
+        - label: I'd be interested in helping implement this.
+          required: false

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,5 @@
+blank_issues_enabled: true
+contact_links:
+  - name: 📖 Documentation
+    url: https://docs.cowagent.ai
+    about: Setup guides, configuration, and FAQ.

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,22 @@
+<!--
+Thanks for your contribution! Please write this PR in English.
+推荐使用英文填写，感谢 ❤️
+-->
+
+## What does this PR do?
+
+<!-- A short description of the change and why it's needed. -->
+
+## Type of change
+
+- [ ] Bug fix
+- [ ] New feature
+- [ ] Docs
+- [ ] Refactor / chore
+
+## Checklist
+
+- [ ] I have read the [Contributing Guide](https://github.com/zhayujie/CowAgent/blob/master/CONTRIBUTING.md)
+- [ ] I tested this change locally
+- [ ] Code comments and docs are in English
+- [ ] Linked related issue (if any): closes #

.github/scripts/register-releases.mjs

@@ -0,0 +1,116 @@
+// Build the D1 upsert SQL for a desktop release from the files in a directory.
+//
+// Each mac release has TWO artifacts that map to a SINGLE D1 row:
+//   - <name>-<arch>.dmg  -> manual download   (filename / size / sha512)
+//   - <name>-<arch>.zip  -> auto-update        (update_filename / update_size /
+//                                                update_sha512)
+// electron-updater's MacUpdater can only consume a zip, never a dmg, so the
+// feed serves the zip while the website serves the dmg. Windows has only the
+// .exe (stored in the main columns; it's both the download and the update).
+//
+// We emit ONE `INSERT OR REPLACE` per (version, platform) carrying BOTH halves,
+// because two replaces on the same primary key would drop whichever came first.
+//
+// Usage:
+//   node register-releases.mjs --dir dist --version 1.2.0 \
+//        --sql out.sql [--latest] 
+//
+//   --latest  mark these rows is_latest=1 AND clear the previous latest for
+//             each platform (used by the publish/promote workflow). Without it
+//             rows are written unpublished (is_latest=0) — the build stage.
+//
+// sha512 is base64 (the exact format electron-updater validates).
+
+import { execSync } from 'node:child_process'
+import fs from 'node:fs'
+
+function arg(name, fallback = undefined) {
+  const i = process.argv.indexOf(`--${name}`)
+  if (i === -1) return fallback
+  const next = process.argv[i + 1]
+  // Boolean flag (no value or next token is another flag).
+  if (next === undefined || next.startsWith('--')) return true
+  return next
+}
+
+const dir = arg('dir', 'dist')
+const version = arg('version')
+const sqlPath = arg('sql', 'd1.sql')
+const makeLatest = arg('latest', false) === true
+
+if (!version) {
+  console.error('register-releases: --version is required')
+  process.exit(1)
+}
+
+const sha512 = (f) =>
+  execSync(`openssl dgst -sha512 -binary "${f}" | openssl base64 -A`, {
+    shell: '/bin/bash',
+  })
+    .toString()
+    .trim()
+
+// SQL-escape single quotes (base64/keys shouldn't contain them, but be safe).
+const q = (s) => String(s).replace(/'/g, "''")
+
+// platform -> { main: {key,size,sha}, upd: {key,size,sha} }
+const rows = {}
+
+for (const base of fs.readdirSync(dir)) {
+  const f = `${dir}/${base}`
+  if (fs.statSync(f).isDirectory()) continue
+
+  let platform
+  let slot
+  if (/arm64\.dmg$/.test(base)) {
+    platform = 'mac-arm64'
+    slot = 'main'
+  } else if (/x64\.dmg$/.test(base)) {
+    platform = 'mac-x64'
+    slot = 'main'
+  } else if (/arm64\.zip$/.test(base)) {
+    platform = 'mac-arm64'
+    slot = 'upd'
+  } else if (/x64\.zip$/.test(base)) {
+    platform = 'mac-x64'
+    slot = 'upd'
+  } else if (/\.exe$/.test(base)) {
+    platform = 'win'
+    slot = 'main'
+  } else {
+    console.log('Skipping unrecognized artifact:', base)
+    continue
+  }
+
+  rows[platform] ||= {}
+  rows[platform][slot] = {
+    key: `v${version}/${base}`,
+    size: fs.statSync(f).size,
+    sha: sha512(f),
+  }
+}
+
+if (Object.keys(rows).length === 0) {
+  console.error('register-releases: no recognized artifacts in', dir)
+  process.exit(1)
+}
+
+const isLatest = makeLatest ? 1 : 0
+const sql = []
+for (const [platform, r] of Object.entries(rows)) {
+  const m = r.main || { key: '', size: 0, sha: '' }
+  const u = r.upd || { key: '', size: 0, sha: '' }
+  if (makeLatest) {
+    // Clear the previous latest for this platform before promoting the new row.
+    sql.push(`UPDATE releases SET is_latest = 0 WHERE platform = '${platform}';`)
+  }
+  sql.push(
+    `INSERT OR REPLACE INTO releases ` +
+      `(version, platform, filename, size, sha512, update_filename, update_size, update_sha512, is_latest) ` +
+      `VALUES ('${version}', '${platform}', '${q(m.key)}', ${m.size}, '${q(m.sha)}', ` +
+      `'${q(u.key)}', ${u.size}, '${q(u.sha)}', ${isLatest});`
+  )
+}
+
+fs.writeFileSync(sqlPath, sql.join('\n') + '\n')
+console.log(`register-releases: wrote ${sql.length} statement(s) to ${sqlPath}`)

.github/workflows/deploy-image-arm.yml

@@ -19,7 +19,7 @@ env:
 
 jobs:
   build-and-push-image:
-    if: github.repository == 'zhayujie/chatgpt-on-wechat'
+    if: github.repository == 'zhayujie/CowAgent'
     runs-on: ubuntu-latest
     permissions:
       contents: read
@@ -51,7 +51,12 @@ jobs:
         uses: docker/metadata-action@v4
         with:
           images: |
-            ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+            ${{ env.REGISTRY }}/zhayujie/chatgpt-on-wechat
+            ${{ env.REGISTRY }}/zhayujie/cowagent
+          tags: |
+            type=raw,value=latest-arm64,enable={{is_default_branch}}
+            type=ref,event=branch,suffix=-arm64
+            type=ref,event=tag,suffix=-arm64
 
       - name: Build and push Docker image
         uses: docker/build-push-action@v3
@@ -60,7 +65,7 @@ jobs:
           push: true
           file: ./docker/Dockerfile.latest
           platforms: linux/arm64
-          tags: ${{ steps.meta.outputs.tags }}-arm64
+          tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
 
       - uses: actions/delete-package-versions@v4

.github/workflows/deploy-image.yml

@@ -16,10 +16,11 @@ on:
 env:
   REGISTRY: ghcr.io
   IMAGE_NAME: ${{ github.repository }}
+  DOCKERHUB_IMAGE: zhayujie/chatgpt-on-wechat
 
 jobs:
   build-and-push-image:
-    if: github.repository == 'zhayujie/chatgpt-on-wechat'
+    if: github.repository == 'zhayujie/CowAgent'
     runs-on: ubuntu-latest
     permissions:
       contents: read
@@ -47,8 +48,14 @@ jobs:
         uses: docker/metadata-action@v4
         with:
           images: |
-            ${{ env.IMAGE_NAME }}
+            zhayujie/chatgpt-on-wechat
-            ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+            zhayujie/cowagent
+            ${{ env.REGISTRY }}/zhayujie/chatgpt-on-wechat
+            ${{ env.REGISTRY }}/zhayujie/cowagent
+          tags: |
+            type=raw,value=latest,enable={{is_default_branch}}
+            type=ref,event=branch
+            type=ref,event=tag
 
       - name: Build and push Docker image
         uses: docker/build-push-action@v3

.github/workflows/publish-desktop.yml

@@ -0,0 +1,154 @@
+name: Publish Desktop
+
+# STAGE 3 of the decoupled release pipeline: PROMOTE a built + notarized version
+# to "live". By this point:
+#   - stage 1 (Release Desktop) built the installers, mirrored them to R2, and
+#     registered them in D1 as unpublished (is_latest=0);
+#   - stage 2 (local desktop/build/notarize-dmg.sh) notarized + stapled the mac
+#     dmgs and re-uploaded the stapled bytes to R2.
+#
+# This workflow, triggered manually with the version to publish:
+#   1. pulls every artifact for that version back from R2,
+#   2. recomputes sha512 from the real (stapled) bytes and updates D1,
+#   3. flips is_latest=1 for that version (clearing the previous latest per
+#      platform) UNLESS it's a pre-release, which is recorded but never latest,
+#   4. creates/updates the GitHub Release and attaches the installers.
+#
+# Run only after the mac dmgs for this version are notarized + re-uploaded.
+on:
+  workflow_dispatch:
+    inputs:
+      version:
+        description: "Version to publish (e.g. 1.2.0). Must already be built + notarized."
+        type: string
+        required: true
+      make_latest:
+        description: "Mark this version as latest on the site (uncheck for a dry re-hash only)."
+        type: boolean
+        default: true
+      github_release:
+        description: "Create/update the GitHub Release and attach installers."
+        type: boolean
+        default: true
+
+permissions:
+  contents: write
+
+jobs:
+  publish:
+    name: Publish ${{ github.event.inputs.version }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Guard on Cloudflare secrets
+        id: guard
+        env:
+          CF_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
+        run: |
+          if [ -z "$CF_TOKEN" ]; then
+            echo "::error::CLOUDFLARE_API_TOKEN not set — cannot publish."
+            exit 1
+          fi
+
+      - name: Resolve version artifacts from D1
+        id: rows
+        env:
+          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
+          CLOUDFLARE_ACCOUNT_ID: ${{ secrets.CLOUDFLARE_ACCOUNT_ID }}
+          VER: ${{ github.event.inputs.version }}
+        run: |
+          # The build stage inserted one row per artifact with filename = v<VER>/<base>.
+          # Read them back so we know exactly which objects to pull from R2.
+          out="$(npx --yes wrangler@latest d1 execute cow-desktop --remote --json \
+            --command "SELECT platform, filename, update_filename FROM releases WHERE version = '${VER}';")"
+          echo "$out"
+          echo "$out" | node -e '
+            const fs = require("fs");
+            const data = JSON.parse(fs.readFileSync(0, "utf8"));
+            const rows = (Array.isArray(data) ? data : [data])
+              .flatMap(r => (r.results || []));
+            if (!rows.length) {
+              console.error("No D1 rows for this version — did stage 1 (build) run?");
+              process.exit(1);
+            }
+            fs.writeFileSync(process.env.GITHUB_OUTPUT, "count=" + rows.length + "\n", { flag: "a" });
+            fs.writeFileSync("rows.json", JSON.stringify(rows));
+          '
+
+      - name: Download version artifacts from R2
+        env:
+          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
+          CLOUDFLARE_ACCOUNT_ID: ${{ secrets.CLOUDFLARE_ACCOUNT_ID }}
+          R2_BUCKET: ${{ vars.R2_BUCKET != '' && vars.R2_BUCKET || 'cow-skills' }}
+        run: |
+          mkdir -p dist
+          # Pull BOTH the manual-download file (filename: dmg/exe) and the mac
+          # auto-update file (update_filename: zip) for every row. Keys are
+          # "v<VER>/<base>"; the R2 key is "desktop/<key>".
+          for key in $(node -e 'JSON.parse(require("fs").readFileSync("rows.json")).forEach(r => { if (r.filename) console.log(r.filename); if (r.update_filename) console.log(r.update_filename); })'); do
+            base="$(basename "$key")"
+            r2key="desktop/${key}"
+            echo "==> Downloading r2://${R2_BUCKET}/${r2key} -> dist/${base}"
+            npx --yes wrangler@latest r2 object get "${R2_BUCKET}/${r2key}" \
+              --file "dist/${base}" --remote
+          done
+          echo "Downloaded:"; ls -la dist
+
+      - name: Reminder — mac dmgs must be notarized before publishing
+        run: |
+          # Stapling can only be validated on macOS (xcrun stapler validate),
+          # which this Linux runner doesn't have. The authoritative check runs in
+          # stage 2 (desktop/build/notarize-dmg.sh) before re-uploading to R2.
+          # This step is just a loud reminder in the log.
+          echo "::notice::Publishing assumes the mac dmgs pulled from R2 are already notarized + stapled (stage 2). If you skipped stage 2, users will hit Gatekeeper warnings."
+          ls -la dist/*.dmg 2>/dev/null || echo "(no dmg in this version — win-only publish)"
+
+      - name: Update D1 (recompute sha512 + set latest)
+        env:
+          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
+          CLOUDFLARE_ACCOUNT_ID: ${{ secrets.CLOUDFLARE_ACCOUNT_ID }}
+          VER: ${{ github.event.inputs.version }}
+          MAKE_LATEST: ${{ github.event.inputs.make_latest }}
+        run: |
+          # Pre-releases (e.g. 1.2.0-beta / -rc.1 / -test) are recorded but never
+          # become latest, so the site keeps serving the last stable build.
+          case "$VER" in
+            *-*) is_pre=1 ;;
+            *)   is_pre=0 ;;
+          esac
+          if [ "$MAKE_LATEST" = "true" ] && [ "$is_pre" = "0" ]; then
+            latest_flag="--latest"; echo "==> Publishing $VER as latest."
+          else
+            latest_flag=""; echo "==> Publishing $VER without latest flag (pre-release or dry re-hash)."
+          fi
+
+          # Re-hash the real (stapled) bytes and re-store every row with both the
+          # dmg (manual) and mac zip (auto-update) columns. Same script as the
+          # build stage; --latest also clears the previous latest per platform.
+          node .github/scripts/register-releases.mjs --dir dist --version "$VER" --sql d1.sql $latest_flag
+          echo "==> D1 statements:"; cat d1.sql
+          npx --yes wrangler@latest d1 execute cow-desktop --remote --file d1.sql
+
+      - name: Create/update GitHub Release and attach installers
+        if: github.event.inputs.github_release == 'true'
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          VER: ${{ github.event.inputs.version }}
+        run: |
+          tag="v${VER}"
+          case "$VER" in
+            *-*) prerelease="--prerelease" ;;
+            *)   prerelease="" ;;
+          esac
+          if ! gh release view "$tag" --repo "$GITHUB_REPOSITORY" >/dev/null 2>&1; then
+            gh release create "$tag" --repo "$GITHUB_REPOSITORY" \
+              --title "$tag" --generate-notes $prerelease
+          fi
+          # --clobber so re-runs overwrite the stapled/updated assets. The mac
+          # zip is the auto-update artifact; attach it too so the GitHub Release
+          # is a complete mirror (nullglob avoids errors when a type is absent).
+          shopt -s nullglob
+          gh release upload "$tag" dist/*.dmg dist/*.zip dist/*.exe \
+            --repo "$GITHUB_REPOSITORY" --clobber

.github/workflows/release.yml

@@ -0,0 +1,301 @@
+name: Release Desktop
+
+# STAGE 1 of the decoupled release pipeline: BUILD ONLY.
+# Builds the desktop client for macOS (arm64 + x64) and Windows (x64), mirrors
+# the installers to R2, and registers them in D1 as UNPUBLISHED (is_latest=0)
+# so the website keeps serving the previous release. It does NOT notarize
+# (Apple's notary service stalls this large bundle for hours) and does NOT
+# create a GitHub Release.
+#
+# Full flow:
+#   1. (this workflow) build + upload to R2 + D1 as unpublished.
+#   2. (local) download the mac dmgs, run desktop/build/notarize-dmg.sh to
+#      notarize + staple + re-upload the stapled dmgs to R2.
+#   3. (Publish Desktop workflow) flip D1 is_latest=1 and attach GitHub
+#      Release assets — makes the version live on the site.
+#
+# Manual only: run stage 1 via workflow_dispatch. Tag pushes do NOT trigger a
+# build, so cutting a release tag never rebuilds installers or overwrites R2.
+on:
+  workflow_dispatch:
+    inputs:
+      version:
+        description: "Version to stamp (e.g. 1.0.0-test). Used for package.json and R2 path."
+        type: string
+        default: "0.0.0-dev"
+      publish_r2:
+        description: "Upload installers to R2 + register in D1 (needs Cloudflare secrets)"
+        type: boolean
+        default: false
+
+permissions:
+  contents: write
+
+jobs:
+  build:
+    name: Build ${{ matrix.name }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      # Don't cancel the other platforms if one fails — we want to see all
+      # failures in a single run.
+      fail-fast: false
+      matrix:
+        include:
+          - name: macOS arm64
+            os: macos-14
+            platform: mac
+            arch: arm64
+            eb_flags: --mac --arm64
+          - name: macOS x64
+            os: macos-15-intel
+            platform: mac
+            arch: x64
+            eb_flags: --mac --x64
+          - name: Windows x64
+            os: windows-latest
+            platform: win
+            arch: x64
+            eb_flags: --win --x64
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Derive version
+        # Tag push: strip the leading "v" from GITHUB_REF_NAME (e.g. v1.2.0).
+        # Manual dispatch: use the provided version input.
+        id: ver
+        shell: bash
+        run: |
+          if [ "${{ github.event_name }}" = "push" ]; then
+            ref="${GITHUB_REF_NAME:-}"
+            echo "version=${ref#v}" >> "$GITHUB_OUTPUT"
+          else
+            echo "version=${{ github.event.inputs.version }}" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Set up Node
+        uses: actions/setup-node@v4
+        with:
+          node-version: "20"
+
+      - name: Build Python backend (PyInstaller)
+        shell: bash
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r desktop/build/requirements-desktop.txt
+          pip install pyinstaller
+          # Run from repo root so the spec's relative datas resolve correctly.
+          pyinstaller desktop/build/cowagent-backend.spec \
+            --noconfirm \
+            --distpath desktop/build/dist \
+            --workpath desktop/build/build-work
+
+      - name: Install desktop deps
+        working-directory: desktop
+        run: npm ci
+
+      - name: Write version into package.json
+        working-directory: desktop
+        shell: bash
+        run: npm version "${{ steps.ver.outputs.version }}" --no-git-tag-version --allow-same-version
+
+      # Compile renderer + main in its OWN step, alone, so the npm.cmd batch
+      # wrapper (see the note on the build step below) can't take out anything
+      # after it.
+      - name: Compile (vite + tsc)
+        working-directory: desktop
+        shell: bash
+        run: npm run build
+
+      - name: Build & publish (electron-builder)
+        working-directory: desktop
+        shell: bash
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          # Signing secrets are passed through as-is; we only export them to the
+          # environment below when non-empty. An empty CSC_LINK would make
+          # electron-builder try to load a bogus certificate and fail, so unset
+          # is the correct state for unsigned builds.
+          MAC_CSC_LINK: ${{ secrets.MAC_CSC_LINK }}
+          MAC_CSC_KEY_PASSWORD: ${{ secrets.MAC_CSC_KEY_PASSWORD }}
+          WIN_CSC_LINK: ${{ secrets.WIN_CSC_LINK }}
+          WIN_CSC_KEY_PASSWORD: ${{ secrets.WIN_CSC_KEY_PASSWORD }}
+        run: |
+          # Pick the signing cert for THIS platform only. The mac and win secrets
+          # are both present in the job env, but a mac cert must never leak into a
+          # Windows build (electron-builder would try to load it and fail), and
+          # vice versa. electron-builder reads a single CSC_LINK/CSC_KEY_PASSWORD
+          # pair, so we set it per-platform. An empty CSC_LINK is treated by
+          # electron-builder as a broken cert path, so we leave it entirely unset
+          # for an unsigned build.
+          #
+          # NOTE: we only ever `export`, never `unset`, GitHub-injected env vars
+          # (an `unset` can return non-zero and abort under errexit).
+          case "${{ matrix.platform }}" in
+            mac)
+              if [ -n "$MAC_CSC_LINK" ]; then
+                export CSC_LINK="$MAC_CSC_LINK"
+                export CSC_KEY_PASSWORD="$MAC_CSC_KEY_PASSWORD"
+              fi
+              ;;
+            win)
+              if [ -n "$WIN_CSC_LINK" ]; then
+                export CSC_LINK="$WIN_CSC_LINK"
+                export CSC_KEY_PASSWORD="$WIN_CSC_KEY_PASSWORD"
+              fi
+              ;;
+          esac
+
+          # Never let electron-builder publish: our publish target is a generic
+          # (read-only) feed served from R2/D1, which it can't upload to. We mirror
+          # installers to R2 and register them in D1 ourselves (publish-r2 job).
+          # `--publish never` still emits the latest*.yml files.
+          #
+          # CONFIG PER PLATFORM: the dynamic electron-builder.js only exists to
+          # inject mac.binaries (the backend Mach-O files to hardened-sign for
+          # notarization) — it's a pure no-op on Windows. Passing --config on
+          # Windows was what silently broke the Windows build (it produced no
+          # installer while the job still reported success; Windows worked fine
+          # before --config was introduced). So Windows uses the plain
+          # package.json build config and only mac uses the dynamic one.
+          #
+          # Invoke via `node <cli.js>` rather than `npx`: on Windows `npx` is
+          # npx.cmd (a batch wrapper) and running it from this Git Bash step can
+          # make bash return before the wrapped process finishes. node skips it.
+          case "${{ matrix.platform }}" in
+            mac) config_arg="--config electron-builder.js" ;;
+            *)   config_arg="" ;;
+          esac
+          node node_modules/electron-builder/cli.js ${{ matrix.eb_flags }} $config_arg --publish never
+
+      # Upload artifacts regardless of outcome, so a failed run still surfaces
+      # the built installers (and, on success, the notarized+stapled dmg).
+      - name: Upload artifacts
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          # One bundle per platform/arch so the publish job can collect them all.
+          name: cowagent-${{ matrix.platform }}-${{ matrix.arch }}
+          path: |
+            desktop/release/*.dmg
+            desktop/release/*.zip
+            desktop/release/*.exe
+            desktop/release/*.yml
+            desktop/release/*.blockmap
+          if-no-files-found: ignore
+          retention-days: 7
+
+  # Mirror the release installers to R2 (CDN-backed) and register them in D1 so
+  # cowagent.ai/download/{platform}/latest can resolve and count downloads.
+  # Runs only on tag pushes, and is a no-op (skips) until the Cloudflare secrets
+  # are configured, so it never blocks unsigned/dry builds.
+  publish-r2:
+    name: Publish to R2 + D1
+    # Require every platform in the build matrix to succeed before publishing,
+    # so a release on R2/D1 is always complete (all installers present) rather
+    # than partial. needs: build already gates on all matrix jobs succeeding.
+    needs: build
+    runs-on: ubuntu-latest
+    # Run on a tag push, or on a manual dispatch when publish_r2 is checked.
+    if: >-
+      (github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v')) ||
+      (github.event_name == 'workflow_dispatch' && github.event.inputs.publish_r2 == 'true')
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Guard on Cloudflare secrets
+        id: guard
+        env:
+          CF_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
+        run: |
+          if [ -n "$CF_TOKEN" ]; then
+            echo "enabled=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "enabled=false" >> "$GITHUB_OUTPUT"
+            echo "::notice::CLOUDFLARE_API_TOKEN not set — skipping R2/D1 publish."
+          fi
+
+      - name: Derive version
+        if: steps.guard.outputs.enabled == 'true'
+        id: ver
+        run: |
+          if [ "${{ github.event_name }}" = "push" ]; then
+            echo "version=${GITHUB_REF_NAME#v}" >> "$GITHUB_OUTPUT"
+          else
+            echo "version=${{ github.event.inputs.version }}" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Download all build artifacts
+        if: steps.guard.outputs.enabled == 'true'
+        uses: actions/download-artifact@v4
+        with:
+          path: artifacts
+
+      - name: Stage installers
+        if: steps.guard.outputs.enabled == 'true'
+        id: stage
+        run: |
+          mkdir -p dist
+          # Flatten installers + their .blockmap (used by electron-updater for
+          # differential downloads) from every per-platform artifact dir. The
+          # .yml feed is generated dynamically by the /update Function from D1,
+          # so the yml files themselves don't need to go to R2.
+          # .zip is the mac auto-update artifact (electron-updater's MacUpdater
+          # can ONLY consume zip, not dmg — the dmg is for manual downloads).
+          find artifacts -type f \( -name '*.dmg' -o -name '*.zip' -o -name '*.exe' -o -name '*.blockmap' \) -exec cp {} dist/ \;
+          echo "Staged files:"; ls -la dist
+          # When the whole matrix failed there's nothing to publish; flag it so
+          # the R2/D1 steps skip instead of writing an empty/partial release.
+          if [ -n "$(ls -A dist 2>/dev/null)" ]; then
+            echo "has_files=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "has_files=false" >> "$GITHUB_OUTPUT"
+            echo "::warning::No installers found in any artifact — skipping R2/D1 publish."
+          fi
+
+      - name: Upload installers to R2
+        if: steps.guard.outputs.enabled == 'true' && steps.stage.outputs.has_files == 'true'
+        env:
+          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
+          CLOUDFLARE_ACCOUNT_ID: ${{ secrets.CLOUDFLARE_ACCOUNT_ID }}
+          VER: ${{ steps.ver.outputs.version }}
+        run: |
+          # Reuse the existing cow-skills bucket under a desktop/ prefix; this
+          # is served by the cdn.cowagent.ai custom domain.
+          for f in dist/*; do
+            base="$(basename "$f")"
+            key="desktop/v${VER}/${base}"
+            echo "==> Uploading $base -> r2://cow-skills/$key"
+            npx --yes wrangler@latest r2 object put "cow-skills/$key" \
+              --file "$f" --remote
+          done
+
+      - name: Register release rows in D1
+        if: steps.guard.outputs.enabled == 'true' && steps.stage.outputs.has_files == 'true'
+        env:
+          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
+          CLOUDFLARE_ACCOUNT_ID: ${{ secrets.CLOUDFLARE_ACCOUNT_ID }}
+          VER: ${{ steps.ver.outputs.version }}
+        run: |
+          # This build job ALWAYS registers rows as unpublished (is_latest=0), so
+          # /download/<p>/latest keeps serving the previous release and the new
+          # version stays invisible on the site. macOS dmgs still need to be
+          # notarized+stapled locally (build/notarize-dmg.sh) before they're
+          # safe to ship. Promotion to latest happens later, only after
+          # notarization, via the separate "Publish Desktop" workflow.
+          echo "==> Registering $VER as unpublished (is_latest=0)."
+
+          # Build one upsert per (version, platform) carrying both the dmg
+          # (manual download) and the mac zip (auto-update) columns. See
+          # .github/scripts/register-releases.mjs for the mapping. No --latest
+          # here: rows stay unpublished until the publish workflow promotes them.
+          node .github/scripts/register-releases.mjs --dir dist --version "$VER" --sql d1.sql
+          echo "==> D1 statements:"; cat d1.sql
+          npx --yes wrangler@latest d1 execute cow-desktop --remote --file d1.sql

.github/workflows/test-windows-bash.yml

@@ -0,0 +1,32 @@
+name: Windows Bash Streaming Tests
+
+on:
+  workflow_dispatch:
+  pull_request:
+    paths:
+      - "agent/tools/bash/bash.py"
+      - "tests/test_bash_streaming.py"
+      - ".github/workflows/test-windows-bash.yml"
+
+jobs:
+  windows-bash-tests:
+    runs-on: windows-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: pip
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install pytest
+          python -m pip install -r requirements.txt
+
+      - name: Run Windows Bash streaming tests
+        run: python -m pytest tests/test_bash_streaming.py -v

.gitignore

@@ -3,16 +3,15 @@
 .vscode
 .venv
 .vs
-.wechaty/
 __pycache__/
 venv*
 *.pyc
+python
 config.json
 QR.png
 nohup.out
 tmp
 plugins.json
-itchat.pkl
 *.log
 logs/
 workspace
@@ -33,8 +32,33 @@ plugins/banwords/lib/__pycache__
 !plugins/role
 !plugins/keyword
 !plugins/linkai
-!plugins/agent
+!plugins/cow_cli
 client_config.json
 ref/
+**/.dev.vars
 .cursor/
 local/
+node_modules/
+
+# cow cli
+dist/
+build/
+*.egg-info/
+.cow.pid
+
+# Desktop backend packaging: keep the source files (spec/requirements/script)
+# tracked even though the generic build/ rule above ignores them, but never
+# track the build outputs or local venv.
+!desktop/build/
+desktop/build/*
+!desktop/build/cowagent-backend.spec
+!desktop/build/requirements-desktop.txt
+!desktop/build/build-backend.sh
+!desktop/build/entitlements.mac.plist
+!desktop/build/notarize-dmg.sh
+
+# Icon authoring scratch dir: intermediate assets used to produce the final
+# icons. Only the finished icons under desktop/resources/ should be committed.
+desktop/resources/.icon-work/
+
+.wrangler/

CONTRIBUTING.md

@@ -0,0 +1,61 @@
+# Contributing to CowAgent
+
+Thanks for taking the time to contribute! 🎉 CowAgent is built by a global
+community, and contributions of all sizes are welcome — from typo fixes to new
+features.
+
+## Language policy
+
+To keep the project accessible to a global community, **please write issues,
+pull requests, code comments, and commit messages in English.**
+
+> 为方便全球开发者协作，请尽量使用**英文**提交 issue、PR、代码注释与
+> commit message。不必担心英文不完美——表达清楚即可，工具翻译也完全没问题。感谢理解 ❤️
+
+## Reporting issues
+
+Found a bug or have an idea? [Open an issue](https://github.com/zhayujie/CowAgent/issues/new/choose).
+
+Before opening one, please search existing issues (including closed ones) to
+avoid duplicates, and make sure you're on the latest version.
+
+## Submitting a pull request
+
+1. **Fork** the repo and create a branch from `master`
+   (e.g. `feat/web-search`, `fix/telegram-reconnect`).
+2. Make your change. Keep it focused — one logical change per PR.
+3. Follow the existing code style. Write comments and docstrings in English.
+4. Run the app locally to confirm your change works.
+5. Open a PR with a clear title and a short description of **what** and **why**.
+
+We keep the bar friendly: clear, focused, and working is enough. Maintainers are
+happy to help polish details during review.
+
+### Commit & PR titles
+
+Use a short, imperative summary. The [Conventional Commits](https://www.conventionalcommits.org/)
+style is preferred but not required:
+
+```
+feat: add web search tool
+fix: reconnect Telegram websocket on timeout
+docs: clarify Docker setup
+```
+
+## Development setup
+
+See the [Install from Source](https://docs.cowagent.ai/guide/manual-install)
+guide. In short:
+
+```bash
+git clone https://github.com/zhayujie/CowAgent.git
+cd CowAgent
+pip install -r requirements.txt
+pip install -e .
+cow start
+```
+
+## Code of conduct
+
+Be respectful and constructive. We want CowAgent to be a welcoming place for
+everyone.

agent/chat/service.py

@@ -27,7 +27,8 @@ class ChatService:
         """
         self.agent_bridge = agent_bridge
 
-    def run(self, query: str, session_id: str, send_chunk_fn: Callable[[dict], None]):
+    def run(self, query: str, session_id: str, send_chunk_fn: Callable[[dict], None],
+            channel_type: str = ""):
         """
         Run the agent for *query* and stream results back via *send_chunk_fn*.
 
@@ -37,11 +38,27 @@ class ChatService:
         :param query: user query text
         :param session_id: session identifier for agent isolation
         :param send_chunk_fn: callable(chunk_data: dict) to send a streaming chunk
+        :param channel_type: source channel (e.g. "web", "feishu") for persistence
         """
         agent = self.agent_bridge.get_agent(session_id=session_id)
         if agent is None:
             raise RuntimeError("Failed to initialise agent for the session")
 
+        # Pass context metadata to model for downstream API requests
+        if hasattr(agent, 'model'):
+            agent.model.channel_type = channel_type or ""
+            agent.model.session_id = session_id or ""
+
+        # Build a context so context-aware tools (e.g. scheduler) can resolve the
+        # receiver/session. This streaming path bypasses agent_bridge.agent_reply,
+        # so the attach step that normally happens there must be done here too.
+        context = self._build_context(query, session_id, channel_type)
+        self._attach_context_aware_tools(agent, context)
+
+        # Mark this session as mid-run so the self-evolution idle scan does not
+        # fire concurrently when a single turn runs longer than idle_minutes.
+        self._mark_run_active(agent, True)
+
         # State shared between the event callback and this method
         state = _StreamState()
 
@@ -50,7 +67,16 @@ class ChatService:
             event_type = event.get("type")
             data = event.get("data", {})
 
-            if event_type == "message_update":
+            if event_type == "reasoning_update":
+                delta = data.get("delta", "")
+                if delta:
+                    send_chunk_fn({
+                        "chunk_type": "reasoning",
+                        "delta": delta,
+                        "segment_id": state.segment_id,
+                    })
+
+            elif event_type == "message_update":
                 # Incremental text delta
                 delta = data.get("delta", "")
                 if delta:
@@ -68,9 +94,41 @@ class ChatService:
                     # a new segment; collect tool results until turn_end.
                     state.pending_tool_results = []
 
-            elif event_type == "tool_execution_end":
+            elif event_type == "file_to_send":
+                url = data.get("url") or ""
+                if url:
+                    fname = data.get("file_name") or "file"
+                    ft = data.get("file_type") or "file"
+                    if ft == "image":
+                        link = f"![{fname}]({url})"
+                    else:
+                        link = f"[{fname}]({url})"
+                    send_chunk_fn({
+                        "chunk_type": "content",
+                        "delta": "\n\n" + link + "\n\n",
+                        "segment_id": state.segment_id,
+                    })
+                    # Remove url so the model won't repeat it in its reply
+                    data.pop("url", None)
+
+            elif event_type == "tool_execution_start":
+                # Notify the client that a tool is about to run (with its input args)
                 tool_name = data.get("tool_name", "")
                 arguments = data.get("arguments", {})
+                # Cache arguments keyed by tool_call_id so tool_execution_end can include them
+                tool_call_id = data.get("tool_call_id", tool_name)
+                state.pending_tool_arguments[tool_call_id] = arguments
+                send_chunk_fn({
+                    "chunk_type": "tool_start",
+                    "tool": tool_name,
+                    "arguments": arguments,
+                })
+
+            elif event_type == "tool_execution_end":
+                tool_name = data.get("tool_name", "")
+                tool_call_id = data.get("tool_call_id", tool_name)
+                # Retrieve cached arguments from the matching tool_execution_start event
+                arguments = state.pending_tool_arguments.pop(tool_call_id, data.get("arguments", {}))
                 result = data.get("result", "")
                 status = data.get("status", "unknown")
                 execution_time = data.get("execution_time", 0)
@@ -111,7 +169,7 @@ class ChatService:
         logger.info(f"[ChatService] Starting agent run: session={session_id}, query={query[:80]}")
 
         from config import conf
-        max_context_turns = conf().get("agent_max_context_turns", 30)
+        max_context_turns = conf().get("agent_max_context_turns", 20)
 
         # Get full system prompt with skills
         full_system_prompt = agent.get_full_system_prompt()
@@ -123,6 +181,12 @@ class ChatService:
 
         from agent.protocol.agent_stream import AgentStreamExecutor
 
+        # Register a cancel token so /cancel can abort this in-flight run.
+        # IM channels key on session_id (no per-turn request_id here).
+        from agent.protocol import get_cancel_registry
+        registry = get_cancel_registry()
+        cancel_event = registry.register(session_id, session_id=session_id) if session_id else None
+
         executor = AgentStreamExecutor(
             agent=agent,
             model=agent.model,
@@ -132,6 +196,7 @@ class ChatService:
             on_event=on_event,
             messages=messages_copy,
             max_context_turns=max_context_turns,
+            cancel_event=cancel_event,
         )
 
         try:
@@ -143,11 +208,71 @@ class ChatService:
                     agent.messages.clear()
                     logger.info("[ChatService] Cleared agent message history after executor recovery")
             raise
+        finally:
+            # Clear the mid-run flag so idle scans can review this session again.
+            self._mark_run_active(agent, False)
+            # Release cancel token to keep the registry bounded.
+            if session_id:
+                try:
+                    registry.unregister(session_id)
+                except Exception:
+                    pass
 
-        # Append only the NEW messages from this execution (thread-safe)
+        # Sync executor messages back to agent (thread-safe).
+        # The executor may have trimmed context, making its list shorter than
+        # original_length. In that case we must replace entirely — just
+        # appending would leave stale pre-trim messages in agent.messages
+        # and cause the same trim to fire on every subsequent request.
         with agent.messages_lock:
-            new_messages = executor.messages[original_length:]
+            trimmed = len(executor.messages) < original_length
-            agent.messages.extend(new_messages)
+            if trimmed:
+                # Context was trimmed: the executor appended the new user
+                # query *before* trimming, so the new messages (user +
+                # assistant + tools) sit at the tail of the trimmed list.
+                # We cannot simply slice at original_length (it exceeds the
+                # list length).  Instead, count how many messages the
+                # executor added on top of the post-trim baseline.
+                #
+                # Timeline inside executor.run_stream:
+                #   1. messages had `original_length` items
+                #   2. append user query  → original_length + 1
+                #   3. _trim_messages()   → some smaller number (includes the
+                #      user query because it belongs to the last turn)
+                #   4. LLM replies / tool calls appended
+                #
+                # The user query message is always the first message of the
+                # last turn (it cannot be trimmed away), so we locate it to
+                # find where "new" messages begin.
+                new_start = original_length  # fallback
+                for idx in range(len(executor.messages) - 1, -1, -1):
+                    msg = executor.messages[idx]
+                    if msg.get("role") == "user":
+                        content = msg.get("content", [])
+                        is_user_query = False
+                        if isinstance(content, list):
+                            has_text = any(
+                                isinstance(b, dict) and b.get("type") == "text"
+                                for b in content
+                            )
+                            has_tool_result = any(
+                                isinstance(b, dict) and b.get("type") == "tool_result"
+                                for b in content
+                            )
+                            is_user_query = has_text and not has_tool_result
+                        elif isinstance(content, str):
+                            is_user_query = True
+                        if is_user_query:
+                            new_start = idx
+                            break
+                new_messages = list(executor.messages[new_start:])
+            else:
+                new_messages = list(executor.messages[original_length:])
+            agent.messages = list(executor.messages)
+
+        # Persist new messages to SQLite so they survive restarts and
+        # can be queried via the HISTORY interface.
+        if new_messages:
+            self._persist_messages(session_id, list(new_messages), channel_type)
 
         # Store executor reference for files_to_send access
         agent.stream_executor = executor
@@ -155,10 +280,87 @@ class ChatService:
         # Execute post-process tools
         agent._execute_post_process_tools()
 
+        # Record this user turn for the self-evolution idle trigger. This
+        # streaming path bypasses agent_bridge.agent_reply, so the activity must
+        # be noted here, otherwise idle scans never see any signal to evolve.
+        self._note_evolution_turn(agent, context)
+
         logger.info(f"[ChatService] Agent run completed: session={session_id}")
 
 
 
+    @staticmethod
+    def _build_context(query: str, session_id: str, channel_type: str):
+        """Build a Context for tool resolution on the streaming chat path.
+
+        receiver falls back to session_id; the scheduler's delivery keys on
+        session_id as the receiver.
+        """
+        from bridge.context import Context, ContextType
+        # Pass an explicit kwargs dict: Context's default kwargs is a shared
+        # mutable default, so omitting it would leak fields across sessions.
+        ctx = Context(ContextType.TEXT, query, kwargs={})
+        ctx["session_id"] = session_id
+        ctx["receiver"] = session_id
+        ctx["isgroup"] = False
+        ctx["channel_type"] = channel_type or ""
+        return ctx
+
+    @staticmethod
+    def _attach_context_aware_tools(agent, context):
+        """Attach the current context to tools that need it (scheduler)."""
+        try:
+            if not (context and getattr(agent, "tools", None)):
+                return
+            for tool in agent.tools:
+                if tool.name == "scheduler":
+                    from agent.tools.scheduler.integration import attach_scheduler_to_tool
+                    attach_scheduler_to_tool(tool, context)
+                    break
+        except Exception as e:
+            logger.warning(f"[ChatService] Failed to attach context to scheduler: {e}")
+
+    @staticmethod
+    def _mark_run_active(agent, active):
+        """Toggle the self-evolution mid-run flag for this session's agent."""
+        try:
+            from agent.evolution.trigger import mark_run_active
+            mark_run_active(agent, active)
+        except Exception:
+            pass
+
+    @staticmethod
+    def _note_evolution_turn(agent, context):
+        """Record a user turn so the self-evolution idle trigger has signal."""
+        try:
+            from agent.evolution.trigger import note_user_turn
+            ch = (context.get("channel_type") or "") if context else ""
+            rcv = (context.get("receiver") or "") if context else ""
+            is_group = bool(context.get("isgroup")) if context else False
+            # Only single chats get a proactive push target; group push is noisy.
+            note_user_turn(agent, channel_type=ch, receiver=(rcv if not is_group else ""))
+        except Exception:
+            pass
+
+    @staticmethod
+    def _persist_messages(session_id: str, new_messages: list, channel_type: str = ""):
+        try:
+            from config import conf
+            if not conf().get("conversation_persistence", True):
+                return
+        except Exception:
+            pass
+        try:
+            from agent.memory import get_conversation_store
+            get_conversation_store().append_messages(
+                session_id, new_messages, channel_type=channel_type
+            )
+        except Exception as e:
+            logger.warning(
+                f"[ChatService] Failed to persist messages for session={session_id}: {e}"
+            )
+
+
 class _StreamState:
     """Mutable state shared between the event callback and the run method."""
 
@@ -167,3 +369,6 @@ class _StreamState:
         # None means we are not accumulating tool results right now.
         # A list means we are in the middle of a tool-execution phase.
         self.pending_tool_results: Optional[list] = None
+        # Maps tool_call_id -> arguments captured from tool_execution_start,
+        # so that tool_execution_end can attach the correct input args.
+        self.pending_tool_arguments: dict = {}

agent/chat/session_service.py

@@ -0,0 +1,241 @@
+"""
+SessionService - Manages multi-session lifecycle for both web channel and cloud client.
+
+Provides a unified interface for listing, deleting, renaming, clearing context,
+and generating AI titles for conversation sessions. Backed by ConversationStore
+(SQLite) and AgentBridge (in-memory agent instances).
+"""
+
+import re
+from typing import Optional
+
+from common.log import logger
+
+
+def _truncate_fallback_title(user_message: str, max_len: int = 30) -> str:
+    """Pick the first non-empty line of the user message and truncate it."""
+    if not user_message:
+        return "New Chat"
+    first_line = ""
+    for line in user_message.splitlines():
+        line = line.strip()
+        if line:
+            first_line = line
+            break
+    if not first_line:
+        return "New Chat"
+    if len(first_line) > max_len:
+        first_line = first_line[:max_len].rstrip() + "..."
+    return first_line
+
+
+def generate_session_title(user_message: str, assistant_reply: str = "") -> str:
+    """
+    Generate a short session title by calling the current bot's reply_text.
+    Falls back to the first line of the user message if the LLM call fails
+    or returns an obvious error sentinel.
+    """
+    fallback = _truncate_fallback_title(user_message)
+    try:
+        from bridge.bridge import Bridge
+        from models.session_manager import Session
+        bot = Bridge().get_bot("chat")
+
+        prompt_parts = [f"User: {user_message[:300]}"]
+        if assistant_reply:
+            prompt_parts.append(f"Assistant: {assistant_reply[:300]}")
+
+        session = Session("__title_gen__", system_prompt="")
+        session.messages = [
+            {"role": "user", "content": (
+                "Generate a very short title (max 15 characters for Chinese, max 6 words for English) "
+                "summarizing this conversation. Return ONLY the title text, nothing else.\n\n"
+                + "\n".join(prompt_parts)
+            )}
+        ]
+
+        result = bot.reply_text(session) or {}
+        # When bots fail (network error, auth error, rate limit, etc.) they
+        # typically return completion_tokens=0 with a sentinel content like
+        # "请再问我一次吧" / "我现在有点累了". Treat that as failure.
+        completion_tokens = result.get("completion_tokens", 0) or 0
+        raw = (result.get("content") or "").strip()
+        if completion_tokens <= 0:
+            logger.warning(
+                f"[SessionService] Title generation got empty completion "
+                f"(completion_tokens={completion_tokens}, content='{raw[:50]}'), "
+                f"using fallback")
+            return fallback
+
+        title = re.sub(r'<think>.*?</think>', '', raw, flags=re.DOTALL).strip().strip('"\'')
+        logger.info(f"[SessionService] Title generation result: '{title}' (len={len(title)})")
+        if title and len(title) <= 50:
+            return title
+    except Exception as e:
+        logger.warning(f"[SessionService] Title generation failed: {e}")
+    return fallback
+
+
+class SessionService:
+    """
+    High-level service for session lifecycle management.
+
+    Usage:
+        svc = SessionService()
+        result = svc.dispatch("list", {"channel_type": "web", "page": 1})
+    """
+
+    def _get_store(self):
+        from agent.memory import get_conversation_store
+        return get_conversation_store()
+
+    def _remove_agent(self, session_id: str):
+        """Remove the in-memory Agent instance for a session if it exists."""
+        try:
+            from bridge.bridge import Bridge
+            ab = Bridge().get_agent_bridge()
+            if session_id in ab.agents:
+                del ab.agents[session_id]
+                logger.info(f"[SessionService] Removed agent instance: {session_id}")
+        except Exception:
+            pass
+
+    @staticmethod
+    def _normalize_sid(session_id: str) -> str:
+        if session_id and not session_id.startswith("session_"):
+            return f"session_{session_id}"
+        return session_id
+
+    # ------------------------------------------------------------------
+    # actions
+    # ------------------------------------------------------------------
+    def list_sessions(self, channel_type: Optional[str] = None,
+                      page: int = 1, page_size: int = 50) -> dict:
+        store = self._get_store()
+        return store.list_sessions(
+            channel_type=channel_type,
+            page=page,
+            page_size=page_size,
+        )
+
+    def delete_session(self, session_id: str) -> None:
+        if not session_id:
+            raise ValueError("session_id required")
+        session_id = self._normalize_sid(session_id)
+
+        store = self._get_store()
+        store.clear_session(session_id)
+        self._remove_agent(session_id)
+        logger.info(f"[SessionService] Session deleted: {session_id}")
+
+    def rename_session(self, session_id: str, title: str) -> None:
+        if not session_id:
+            raise ValueError("session_id required")
+        if not title:
+            raise ValueError("title required")
+        session_id = self._normalize_sid(session_id)
+
+        store = self._get_store()
+        found = store.rename_session(session_id, title)
+        if not found:
+            raise ValueError("session not found")
+
+    def clear_context(self, session_id: str) -> int:
+        """
+        Set context boundary. Returns the new context_start_seq value.
+        """
+        if not session_id:
+            raise ValueError("session_id required")
+        session_id = self._normalize_sid(session_id)
+
+        store = self._get_store()
+        new_seq = store.clear_context(session_id)
+        self._remove_agent(session_id)
+        return new_seq
+
+    def gen_title(self, session_id: str, user_message: str,
+                  assistant_reply: str = "") -> str:
+        """
+        Generate an AI title and persist it. Returns the generated title.
+        """
+        if not session_id:
+            raise ValueError("session_id required")
+        if not user_message:
+            raise ValueError("user_message required")
+        session_id = self._normalize_sid(session_id)
+
+        title = generate_session_title(user_message, assistant_reply)
+
+        store = self._get_store()
+        updated = store.rename_session(session_id, title)
+        logger.info(f"[SessionService] Title set: sid={session_id}, "
+                     f"title='{title}', db_updated={updated}")
+        return title
+
+    # ------------------------------------------------------------------
+    # dispatch — single entry point for protocol messages
+    # ------------------------------------------------------------------
+    def dispatch(self, action: str, payload: Optional[dict] = None) -> dict:
+        """
+        Dispatch a session management action and return a protocol-compatible
+        response dict.
+
+        Action names use a ``*_session`` / session-prefixed convention so they
+        can coexist with history actions (e.g. ``query``) on the same HISTORY
+        message channel without ambiguity.
+
+        Supported actions:
+          - list_sessions: list sessions with pagination
+          - delete_session: delete a session
+          - rename_session: rename a session title
+          - clear_context: set context boundary
+          - generate_title: AI-generate a session title
+
+        :param action: one of the above action names
+        :param payload: action-specific payload
+        :return: dict with action, code, message, payload
+        """
+        payload = payload or {}
+        try:
+            if action == "list_sessions":
+                result = self.list_sessions(
+                    channel_type=payload.get("channel_type"),
+                    page=int(payload.get("page", 1)),
+                    page_size=int(payload.get("page_size", 50)),
+                )
+                return {"action": action, "code": 200, "message": "success", "payload": result}
+
+            elif action == "delete_session":
+                self.delete_session(payload.get("session_id", ""))
+                return {"action": action, "code": 200, "message": "success", "payload": None}
+
+            elif action == "rename_session":
+                self.rename_session(
+                    payload.get("session_id", ""),
+                    payload.get("title", "").strip(),
+                )
+                return {"action": action, "code": 200, "message": "success", "payload": None}
+
+            elif action == "clear_context":
+                new_seq = self.clear_context(payload.get("session_id", ""))
+                return {"action": action, "code": 200, "message": "success",
+                        "payload": {"context_start_seq": new_seq}}
+
+            elif action == "generate_title":
+                title = self.gen_title(
+                    payload.get("session_id", ""),
+                    payload.get("user_message", ""),
+                    payload.get("assistant_reply", ""),
+                )
+                return {"action": action, "code": 200, "message": "success",
+                        "payload": {"title": title}}
+
+            else:
+                return {"action": action, "code": 400,
+                        "message": f"unknown action: {action}", "payload": None}
+
+        except ValueError as e:
+            return {"action": action, "code": 400, "message": str(e), "payload": None}
+        except Exception as e:
+            logger.error(f"[SessionService] dispatch error: action={action}, error={e}")
+            return {"action": action, "code": 500, "message": str(e), "payload": None}

agent/evolution/__init__.py

@@ -0,0 +1,19 @@
+"""
+Self-evolution subsystem for CowAgent.
+
+Runs a lightweight, isolated review pass after a conversation goes idle to
+decide whether anything is worth durably learning (memory / skill) or whether
+an unfinished task can be pushed forward. Conservative by design: most
+conversations should produce no change at all.
+
+Public entry points:
+    from agent.evolution import get_evolution_config
+    from agent.evolution.trigger import start_evolution_trigger, note_user_turn
+"""
+
+from agent.evolution.config import EvolutionConfig, get_evolution_config
+
+__all__ = [
+    "EvolutionConfig",
+    "get_evolution_config",
+]

agent/evolution/backup.py

@@ -0,0 +1,102 @@
+"""File backup / rollback support for self-evolution.
+
+Before the evolution agent edits MEMORY.md or a skill file, we snapshot the
+current state into ``memory/.evolution_backups/<backup_id>/`` so a later "undo"
+can restore it. File-level restore only — simple and reliable.
+"""
+
+from __future__ import annotations
+
+import json
+import shutil
+import time
+from datetime import datetime
+from pathlib import Path
+from typing import List, Optional
+
+from common.log import logger
+
+_BACKUP_DIRNAME = ".evolution_backups"
+_MANIFEST_NAME = "manifest.json"
+# Keep only the most recent N backups to bound disk usage.
+_MAX_BACKUPS = 10
+
+
+def _backups_root(workspace_dir: Path) -> Path:
+    return Path(workspace_dir) / "memory" / _BACKUP_DIRNAME
+
+
+def create_backup(workspace_dir: Path, files: List[Path]) -> Optional[str]:
+    """Snapshot ``files`` (those that exist) under a new backup id.
+
+    Returns the backup_id, or None when there is nothing to back up.
+    """
+    existing = [Path(f) for f in files if Path(f).exists()]
+    if not existing:
+        return None
+
+    backup_id = datetime.now().strftime("%Y%m%d-%H%M%S-") + str(int(time.time() * 1000) % 1000)
+    root = _backups_root(workspace_dir)
+    target = root / backup_id
+    try:
+        target.mkdir(parents=True, exist_ok=True)
+        ws = Path(workspace_dir)
+        manifest = []
+        for idx, src in enumerate(existing):
+            # Store under a flat index plus the relative path so restore knows
+            # where it came from, even for nested skill files.
+            try:
+                rel = str(src.relative_to(ws))
+            except ValueError:
+                rel = src.name
+            dst = target / f"{idx}.bak"
+            shutil.copy2(src, dst)
+            manifest.append({"rel": rel, "bak": f"{idx}.bak"})
+        (target / _MANIFEST_NAME).write_text(
+            json.dumps(manifest, ensure_ascii=False, indent=2), encoding="utf-8"
+        )
+        _prune_old_backups(root)
+        # Caller logs a combined backup+review line; keep this at debug.
+        logger.debug(f"[Evolution] Created backup {backup_id} ({len(manifest)} file(s))")
+        return backup_id
+    except Exception as e:
+        logger.warning(f"[Evolution] Failed to create backup: {e}")
+        return None
+
+
+def restore_backup(workspace_dir: Path, backup_id: str) -> bool:
+    """Restore all files captured under ``backup_id``. Returns success."""
+    if not backup_id:
+        return False
+    target = _backups_root(workspace_dir) / backup_id
+    manifest_path = target / _MANIFEST_NAME
+    if not manifest_path.exists():
+        logger.warning(f"[Evolution] Backup not found: {backup_id}")
+        return False
+    try:
+        manifest = json.loads(manifest_path.read_text(encoding="utf-8"))
+        ws = Path(workspace_dir)
+        for entry in manifest:
+            bak = target / entry["bak"]
+            dst = ws / entry["rel"]
+            if bak.exists():
+                dst.parent.mkdir(parents=True, exist_ok=True)
+                shutil.copy2(bak, dst)
+        logger.info(f"[Evolution] Restored backup {backup_id} ({len(manifest)} file(s))")
+        return True
+    except Exception as e:
+        logger.warning(f"[Evolution] Failed to restore backup {backup_id}: {e}")
+        return False
+
+
+def _prune_old_backups(root: Path) -> None:
+    """Drop the oldest backups beyond _MAX_BACKUPS (sorted by name = chronological)."""
+    try:
+        dirs = sorted(
+            [d for d in root.iterdir() if d.is_dir()],
+            key=lambda p: p.name,
+        )
+        for old in dirs[:-_MAX_BACKUPS]:
+            shutil.rmtree(old, ignore_errors=True)
+    except Exception as e:
+        logger.debug(f"[Evolution] Backup prune skipped: {e}")

agent/evolution/config.py

@@ -0,0 +1,76 @@
+"""Configuration for the self-evolution subsystem.
+
+Reads flat ``self_evolution_*`` keys from config.json. All fields have safe
+defaults so the feature degrades gracefully when keys are absent.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Any
+
+
+# Defaults — conservative (see executor module docstring). Disabled by default
+# until release; enable via ``self_evolution_enabled``.
+DEFAULT_ENABLED = False
+DEFAULT_IDLE_MINUTES = 10
+DEFAULT_MIN_TURNS = 6
+# Max review steps for the isolated evolution agent. Kept small (not exposed as
+# config): the review is meant to be cheap and focused, not a long autonomous run.
+DEFAULT_MAX_STEPS = 12
+
+
+@dataclass
+class EvolutionConfig:
+    """Resolved self-evolution settings."""
+
+    enabled: bool = DEFAULT_ENABLED
+    idle_minutes: int = DEFAULT_IDLE_MINUTES
+    min_turns: int = DEFAULT_MIN_TURNS
+    max_steps: int = DEFAULT_MAX_STEPS
+
+    @property
+    def idle_seconds(self) -> int:
+        return max(60, self.idle_minutes * 60)
+
+
+def _as_bool(value: Any, fallback: bool) -> bool:
+    if isinstance(value, bool):
+        return value
+    if isinstance(value, str):
+        v = value.strip().lower()
+        if v in ("true", "1", "yes", "on"):
+            return True
+        if v in ("false", "0", "no", "off"):
+            return False
+    return fallback
+
+
+def _as_pos_int(value: Any, fallback: int) -> int:
+    try:
+        n = int(value)
+        return n if n > 0 else fallback
+    except (TypeError, ValueError):
+        return fallback
+
+
+def get_evolution_config() -> EvolutionConfig:
+    """Build EvolutionConfig from the live config.json ``self_evolution_*`` keys."""
+    try:
+        from config import conf
+        c = conf()
+    except Exception:
+        c = {}
+
+    def _get(key, default):
+        try:
+            return c.get(key, default)
+        except Exception:
+            return default
+
+    return EvolutionConfig(
+        enabled=_as_bool(_get("self_evolution_enabled", None), DEFAULT_ENABLED),
+        idle_minutes=_as_pos_int(_get("self_evolution_idle_minutes", None), DEFAULT_IDLE_MINUTES),
+        min_turns=_as_pos_int(_get("self_evolution_min_turns", None), DEFAULT_MIN_TURNS),
+        max_steps=DEFAULT_MAX_STEPS,
+    )

agent/evolution/executor.py

@@ -0,0 +1,556 @@
+"""Self-evolution executor.
+
+Runs an isolated review agent over an idle conversation's transcript and, if a
+clear signal is found, lets it edit memory / skills via a restricted toolset.
+Conservative by design: most runs return ``[SILENT]`` and change nothing.
+
+Flow:
+    1. Build a transcript from the session's new (since last pass) messages.
+    2. Snapshot MEMORY.md + daily file + editable skills (for undo) -> backup_id.
+    3. Run an isolated agent (same model, restricted tools, evolution prompt).
+    4. If output is [SILENT], or no workspace file actually changed -> done.
+    5. Otherwise -> record to the evolution log, inject an [EVOLUTION] note into
+       the user session (so the main agent can honor "undo"), and push the
+       summary to the user's channel.
+
+Reuses existing infrastructure (AgentBridge.create_agent, ToolManager,
+remember_scheduled_output, channel_factory) rather than introducing a fork.
+"""
+
+from __future__ import annotations
+
+import re
+import threading
+from datetime import datetime
+from pathlib import Path
+from typing import List, Optional
+
+from common.log import logger
+
+from agent.evolution.backup import create_backup
+from agent.evolution.config import get_evolution_config
+from agent.evolution.prompts import (
+    EVOLUTION_MARKER,
+    EVOLUTION_SYSTEM_PROMPT,
+    SILENT_TOKEN,
+    build_review_user_message,
+)
+from agent.evolution.record import append_session_evolution
+
+# Tools the isolated evolution agent is allowed to use. Everything else is
+# withheld so a review pass can only read context, run workspace scripts, and
+# edit memory/skill files. bash is needed by skill-creator's init script and is
+# confined to the workspace by _BashWorkspaceGuard.
+_ALLOWED_TOOLS = {"read", "write", "edit", "ls", "bash", "memory_search", "memory_get"}
+
+# Cap concurrent evolution passes so a burst of idle sessions can't spawn many
+# background model runs at once. Extra sessions simply wait for the next scan.
+_MAX_CONCURRENT = 2
+_running_lock = threading.Lock()
+_running_count = 0
+
+
+def _builtin_skill_names() -> set:
+    """Names of skills shipped with the product (project-root ``skills/``).
+
+    These are protected: the evolution agent must never edit them, even though
+    a same-named copy exists in the workspace at runtime. The project dir is the
+    authoritative list of what counts as built-in.
+    """
+    try:
+        # executor.py -> agent/evolution -> agent -> project root
+        project_root = Path(__file__).resolve().parents[2]
+        builtin_dir = project_root / "skills"
+        if not builtin_dir.is_dir():
+            return set()
+        names = set()
+        for entry in builtin_dir.iterdir():
+            if entry.is_dir() and not entry.name.startswith("."):
+                names.add(entry.name)
+        return names
+    except Exception:
+        return set()
+
+
+def _build_transcript(messages: List[dict], max_chars: int = 12000) -> str:
+    """Render the session messages into a compact text transcript."""
+    lines: List[str] = []
+    for msg in messages:
+        role = msg.get("role", "")
+        if role not in ("user", "assistant"):
+            continue
+        content = msg.get("content", "")
+        text = _extract_text(content)
+        if not text.strip():
+            continue
+        speaker = "User" if role == "user" else "Assistant"
+        lines.append(f"{speaker}: {text.strip()}")
+    transcript = "\n".join(lines)
+    # Keep the most RECENT context if oversized (tail is most relevant).
+    if len(transcript) > max_chars:
+        transcript = "...(earlier omitted)...\n" + transcript[-max_chars:]
+    return transcript
+
+
+def _extract_text(content) -> str:
+    if isinstance(content, str):
+        return content
+    if isinstance(content, list):
+        parts = []
+        for block in content:
+            if isinstance(block, dict) and block.get("type") == "text":
+                parts.append(block.get("text", ""))
+            elif isinstance(block, str):
+                parts.append(block)
+        return "\n".join(parts)
+    return ""
+
+
+def _select_tools(all_tools: list) -> list:
+    return [t for t in all_tools if getattr(t, "name", None) in _ALLOWED_TOOLS]
+
+
+# Tools whose writes must be confined to the workspace during evolution.
+_WRITE_TOOLS = {"write", "edit"}
+
+
+class _WorkspaceWriteGuard:
+    """Wraps a write/edit tool so it can ONLY write inside the workspace.
+
+    Hard engineering guard (not prompt-based): any write resolving outside the
+    workspace — e.g. the project's bundled ``skills/`` dir — is rejected. This
+    protects built-in skills regardless of what the model attempts.
+    """
+
+    def __init__(self, inner, workspace_dir: str):
+        self._inner = inner
+        self._ws = Path(workspace_dir).resolve()
+        # Mirror the attributes the agent runtime reads off a tool.
+        self.name = inner.name
+        self.description = inner.description
+        self.params = inner.params
+
+    def __getattr__(self, item):
+        return getattr(self._inner, item)
+
+    def execute_tool(self, params):
+        # The agent runtime calls execute_tool (not execute); route it through
+        # our guarded execute so the path checks always run.
+        try:
+            return self.execute(params)
+        except Exception as e:
+            logger.error(f"[Evolution] guarded tool error: {e}")
+            from agent.tools.base_tool import ToolResult
+            return ToolResult.fail(f"Error: {e}")
+
+    def execute(self, args):
+        path = (args.get("path") or "").strip()
+        if path:
+            try:
+                resolved = Path(self._inner._resolve_path(path)).resolve()
+                from agent.tools.base_tool import ToolResult
+                # Confine writes to the workspace. This protects the product's
+                # bundled skills (which live outside the workspace) from ever
+                # being modified, no matter what path the model attempts.
+                if self._ws not in resolved.parents and resolved != self._ws:
+                    return ToolResult.fail(
+                        "Error: evolution may only write inside the workspace; "
+                        f"path '{path}' is outside and was blocked."
+                    )
+            except Exception:
+                pass
+        return self._inner.execute(args)
+
+
+class _BashWorkspaceGuard:
+    """Wraps the bash tool so evolution can only run commands inside the
+    workspace.
+
+    Evolution needs bash for skill-creator's init script, but it runs
+    unattended in the background, so a raw shell is too broad. This guard:
+      - forces the command to execute with cwd = workspace,
+      - rejects commands that reference an absolute path or ``..`` segment
+        pointing OUTSIDE the workspace (the common ways to escape it).
+    It is a coarse textual check, not a sandbox — paired with the model's
+    instruction to only run skill-creator scripts, it keeps writes local.
+    """
+
+    def __init__(self, inner, workspace_dir: str):
+        self._inner = inner
+        self._ws = Path(workspace_dir).resolve()
+        # Pin the shell's working directory to the workspace.
+        try:
+            self._inner.cwd = str(self._ws)
+        except Exception:
+            pass
+        self.name = inner.name
+        self.description = inner.description
+        self.params = inner.params
+
+    def __getattr__(self, item):
+        return getattr(self._inner, item)
+
+    def execute_tool(self, params):
+        try:
+            return self.execute(params)
+        except Exception as e:
+            logger.error(f"[Evolution] guarded bash error: {e}")
+            from agent.tools.base_tool import ToolResult
+            return ToolResult.fail(f"Error: {e}")
+
+    def _escapes_workspace(self, command: str) -> bool:
+        # Absolute paths that are not under the workspace.
+        for tok in re.findall(r'(?:^|\s)(/[^\s\'";|&]+)', command):
+            try:
+                resolved = Path(tok).resolve()
+            except Exception:
+                continue
+            if self._ws != resolved and self._ws not in resolved.parents:
+                return True
+        # Parent-dir traversal that climbs above the workspace.
+        for tok in re.findall(r'[^\s\'";|&]*\.\.[^\s\'";|&]*', command):
+            try:
+                resolved = (self._ws / tok).resolve()
+            except Exception:
+                continue
+            if self._ws != resolved and self._ws not in resolved.parents:
+                return True
+        return False
+
+    def execute(self, args):
+        from agent.tools.base_tool import ToolResult
+        command = (args.get("command") or "").strip()
+        if command and self._escapes_workspace(command):
+            return ToolResult.fail(
+                "Error: evolution may only run commands inside the workspace; "
+                "this command references a path outside it and was blocked."
+            )
+        return self._inner.execute(args)
+
+
+def _guard_tools(tools: list, workspace_dir: str) -> list:
+    """Wrap write/edit/bash tools with workspace guards; leave others as-is."""
+    guarded = []
+    for t in tools:
+        name = getattr(t, "name", None)
+        if name in _WRITE_TOOLS:
+            guarded.append(_WorkspaceWriteGuard(t, workspace_dir))
+        elif name == "bash":
+            guarded.append(_BashWorkspaceGuard(t, workspace_dir))
+        else:
+            guarded.append(t)
+    return guarded
+
+
+# Workspace subtrees worth watching for evolution-induced changes. AGENT.md is
+# watched too: evolution may rarely refine the assistant's persona/style there.
+_WATCH_SUBDIRS = ("MEMORY.md", "AGENT.md", "skills", "knowledge", "output")
+# Subpaths under memory/ to ignore: evolution's own bookkeeping + the nightly
+# dream diary, none of which count as a user-facing change signal.
+_MEMORY_IGNORE = (".evolution_backups", "dreams", "evolution")
+# Files the skill subsystem maintains automatically (the enable/disable index).
+# Not an evolution result, so a rewrite must not count as a change signal.
+_WATCH_IGNORE_NAMES = ("skills_config.json",)
+
+
+def _workspace_snapshot(workspace_dir) -> dict:
+    """Map relative path -> (mtime, size) for watched files. Cheap, no reads."""
+    ws = Path(workspace_dir)
+    snap: dict = {}
+    for name in _WATCH_SUBDIRS:
+        root = ws / name
+        if root.is_file():
+            try:
+                st = root.stat()
+                snap[name] = (st.st_mtime, st.st_size)
+            except OSError:
+                pass
+            continue
+        if not root.is_dir():
+            continue
+        for p in root.rglob("*"):
+            if not p.is_file():
+                continue
+            if p.name in _WATCH_IGNORE_NAMES:
+                continue
+            try:
+                st = p.stat()
+                snap[str(p.relative_to(ws))] = (st.st_mtime, st.st_size)
+            except OSError:
+                pass
+
+    # Watch the daily memory files (memory/*.md and per-user dailies) since
+    # evolution now records learnings there. Skip backups/dreams bookkeeping.
+    mem_dir = ws / "memory"
+    if mem_dir.is_dir():
+        for p in mem_dir.rglob("*.md"):
+            rel_parts = p.relative_to(mem_dir).parts
+            if rel_parts and rel_parts[0] in _MEMORY_IGNORE:
+                continue
+            try:
+                st = p.stat()
+                snap[str(p.relative_to(ws))] = (st.st_mtime, st.st_size)
+            except OSError:
+                pass
+    return snap
+
+
+def _workspace_changed(workspace_dir, pre: dict) -> bool:
+    """True if any watched file was added, removed, or modified since ``pre``."""
+    return _workspace_snapshot(workspace_dir) != pre
+
+
+def run_evolution_for_session(
+    agent_bridge,
+    session_id: str,
+    channel_type: str = "",
+    receiver: str = "",
+    user_id: Optional[str] = None,
+    idle_minutes: float = 0.0,
+) -> bool:
+    """Run one evolution pass for a session. Returns True if it changed anything.
+
+    Safe to call from a background thread. All failures are swallowed and
+    logged — evolution must never disrupt the main pipeline.
+    """
+    cfg = get_evolution_config()
+    if not cfg.enabled:
+        return False
+
+    # Concurrency gate: bound how many evolution passes run at once.
+    global _running_count
+    with _running_lock:
+        if _running_count >= _MAX_CONCURRENT:
+            logger.info(
+                f"[Evolution] busy ({_running_count}/{_MAX_CONCURRENT} running); "
+                f"skipping session={session_id} this scan"
+            )
+            return False
+        _running_count += 1
+
+    try:
+        agent = agent_bridge.agents.get(session_id) or agent_bridge.default_agent
+        if not agent:
+            return False
+
+        with agent.messages_lock:
+            all_messages = list(agent.messages)
+        total_msgs = len(all_messages)
+        # In-memory evolution cursor: only review messages added since the last
+        # pass so a long session doesn't re-judge (and re-write) old content.
+        # Stored on the agent instance; lost on restart (acceptable — at worst
+        # one redundant pass right after a restart, gated by the file-change
+        # check downstream so it won't double-write identical memory).
+        done = int(getattr(agent, "_evo_done_msg_count", 0))
+        if done > total_msgs:
+            done = 0  # history was trimmed/reset; start fresh
+        new_messages = all_messages[done:]
+        transcript = _build_transcript(new_messages)
+        if not transcript.strip():
+            # Routine no-op: the per-minute scan hits every idle session. Advance
+            # the cursor so we don't re-scan the same tail; no log (pure noise).
+            agent._evo_done_msg_count = total_msgs
+            return False
+
+        logger.info(
+            f"[Evolution] ▶ Reviewing session={session_id} "
+            f"(idle {idle_minutes:.1f}min, {len(new_messages)} new/{total_msgs} msgs, "
+            f"~{len(transcript)} chars)"
+        )
+
+        # Resolve workspace + files to snapshot for undo.
+        from agent.memory.config import get_default_memory_config
+        mem_cfg = get_default_memory_config()
+        workspace_dir = mem_cfg.get_workspace()
+        if user_id:
+            memory_file = Path(workspace_dir) / "memory" / "users" / user_id / "MEMORY.md"
+        else:
+            memory_file = Path(workspace_dir) / "MEMORY.md"
+        skills_dir = mem_cfg.get_skills_dir()
+
+        # Snapshot MEMORY.md + every NON-protected skill's SKILL.md. Protected
+        # built-in skills are excluded from backup because they must never be
+        # edited in the first place.
+        protected_names = _builtin_skill_names()
+        # Back up both MEMORY.md and today's daily file: evolution now writes to
+        # the daily file, but MEMORY.md is cheap to snapshot and keeps undo safe
+        # if the model ever edits it.
+        today_daily = Path(workspace_dir) / "memory" / (
+            datetime.now().strftime("%Y-%m-%d") + ".md"
+        )
+        if user_id:
+            today_daily = Path(workspace_dir) / "memory" / "users" / user_id / (
+                datetime.now().strftime("%Y-%m-%d") + ".md"
+            )
+        # AGENT.md (persona) is backed up too so a rare persona edit is undoable.
+        # Persona is workspace-global (not per-user): it always lives at the
+        # workspace root, regardless of user_id.
+        agent_file = Path(workspace_dir) / "AGENT.md"
+        backup_files = [Path(memory_file), today_daily, agent_file]
+        if skills_dir.exists():
+            for skill_md in skills_dir.rglob("SKILL.md"):
+                # The skill dir is the SKILL.md's parent (or an ancestor for
+                # collections); guard by checking the immediate top-level dir.
+                try:
+                    top = skill_md.relative_to(skills_dir).parts[0]
+                except (ValueError, IndexError):
+                    continue
+                if top in protected_names:
+                    continue
+                backup_files.append(skill_md)
+        backup_id = create_backup(workspace_dir, backup_files)
+        _backup_n = sum(1 for f in backup_files if Path(f).exists())
+
+        # Snapshot the whole workspace (path -> mtime/size) so we can reliably
+        # detect ANY file change — including new output files written when
+        # finishing an unfinished task, which are not in backup_files.
+        pre_snapshot = _workspace_snapshot(workspace_dir)
+
+        # Build the isolated review agent: same model, restricted tools, with a
+        # hard guard that confines all writes to the workspace (protects the
+        # project's bundled skills from ever being modified).
+        review_tools = _guard_tools(
+            _select_tools(list(getattr(agent, "tools", []) or [])),
+            str(workspace_dir),
+        )
+        review_agent = agent_bridge.create_agent(
+            system_prompt="",
+            tools=review_tools,
+            description="Self-evolution review agent",
+            max_steps=cfg.max_steps,
+            workspace_dir=str(workspace_dir),
+            skill_manager=getattr(agent, "skill_manager", None),
+            memory_manager=getattr(agent, "memory_manager", None),
+            enable_skills=True,
+            runtime_info=getattr(agent, "runtime_info", None),
+        )
+        # Mark this as a restricted review agent so runtime MCP reconciliation
+        # (ToolManager.sync_mcp_into_agent) will NOT silently re-inject MCP tools
+        # that _select_tools()/_guard_tools() intentionally withheld. Without this
+        # flag the review boundary would be re-opened on the first LLM turn.
+        review_agent._evolution_restricted = True
+        # Reuse the live model so it follows the user's configured model.
+        review_agent.model = agent.model
+        # Inject the evolution task brief AFTER the full system prompt: the agent
+        # gets the full context (tools, workspace, user preferences, memory, time)
+        # AND its evolution-specific instructions on top, instead of one
+        # overwriting the other.
+        review_agent.extra_system_suffix = EVOLUTION_SYSTEM_PROMPT
+
+        logger.info(
+            f"[Evolution] backup {backup_id} ({_backup_n} files) → running review agent"
+        )
+        user_msg = build_review_user_message(transcript, protected_skills=list(protected_names))
+        result = review_agent.run_stream(user_msg, clear_history=True)
+        result = (result or "").strip()
+
+        # These messages are now reviewed; advance the cursor so the next pass
+        # only looks at messages added after this point (silent or not).
+        agent._evo_done_msg_count = total_msgs
+
+        # Respect an explicit silent verdict: empty, exactly [SILENT], or text
+        # that STARTS with [SILENT] means the model chose to stay quiet.
+        if not result or result.startswith(SILENT_TOKEN):
+            logger.info(f"[Evolution] ✗ No change for session={session_id} ([SILENT])")
+            return False
+
+        # Anti-nag backstop: if the model wrote a summary but actually changed no
+        # watched file, stay silent — never notify about work that didn't happen.
+        if not _workspace_changed(workspace_dir, pre_snapshot):
+            logger.info(
+                f"[Evolution] ✗ session={session_id}: text produced but no file "
+                f"changed — staying silent"
+            )
+            return False
+
+        # The model produced a real summary. Strip any stray [SILENT] tokens it
+        # left mid-text, then notify.
+        result = result.replace(SILENT_TOKEN, "").strip()
+        if not result:
+            logger.info(f"[Evolution] ✗ No change for session={session_id} ([SILENT])")
+            return False
+
+        logger.info(f"[Evolution] ✓ session={session_id} evolved:\n{result}")
+        append_session_evolution(workspace_dir, result, backup_id=backup_id, user_id=user_id)
+        # Inject an [EVOLUTION] note so the main agent can honor "undo".
+        _inject_evolution_record(agent_bridge, session_id, channel_type, result, backup_id)
+        # The injection appended its own messages ([SCHEDULED]/[EVOLUTION]).
+        # Advance the cursor past them so the next scan does not treat
+        # evolution's own bookkeeping as new user content and re-trigger.
+        try:
+            with agent.messages_lock:
+                agent._evo_done_msg_count = len(agent.messages)
+        except Exception:
+            pass
+
+        # Push the summary to the user's channel. The "did a file actually
+        # change" gate above is the only throttle we need: real evolutions are
+        # rare, so no extra opt-in switch or daily-count limit is required.
+        if channel_type and receiver:
+            _notify_user(channel_type, receiver, result)
+
+        return True
+
+    except Exception as e:
+        logger.warning(f"[Evolution] Run failed for session={session_id}: {e}")
+        return False
+    finally:
+        with _running_lock:
+            _running_count -= 1
+
+
+def _inject_evolution_record(
+    agent_bridge, session_id: str, channel_type: str, summary: str, backup_id: Optional[str]
+) -> None:
+    """Add an [EVOLUTION] note to the user session so the main agent can undo."""
+    try:
+        note = f"{EVOLUTION_MARKER} {summary}"
+        if backup_id:
+            note += f"\n(backup_id: {backup_id}; to undo, restore this backup)"
+        # Reuse the scheduler-output injection path: isolated execution, only a
+        # compact record lands in the user session.
+        agent_bridge.remember_scheduled_output(
+            session_id=session_id,
+            content=note,
+            channel_type=channel_type,
+            task_description="self-evolution",
+        )
+    except Exception as e:
+        logger.debug(f"[Evolution] Failed to inject evolution record: {e}")
+
+
+def _notify_user(channel_type: str, receiver: str, summary: str) -> None:
+    """Push the evolution summary to the user's channel as a new message."""
+    try:
+        from bridge.context import Context, ContextType
+        from bridge.reply import Reply, ReplyType
+        from channel.channel_factory import create_channel
+
+        context = Context(ContextType.TEXT, summary)
+        context["receiver"] = receiver
+        context["isgroup"] = False
+        context["session_id"] = receiver
+        # Channels that reply to an original message need msg=None for a fresh push.
+        if channel_type in ("feishu", "dingtalk", "wecom_bot", "qq"):
+            context["msg"] = None
+        if channel_type == "feishu":
+            context["receive_id_type"] = "open_id"
+
+        channel = create_channel(channel_type)
+        if not channel:
+            return
+
+        # Web is request-response: a background push needs a synthetic request_id
+        # plus a request->session mapping so the channel can route the message to
+        # the user's polling queue (same approach the scheduler uses).
+        if channel_type == "web":
+            import uuid
+            request_id = f"evolution_{uuid.uuid4().hex[:8]}"
+            context["request_id"] = request_id
+            if hasattr(channel, "request_to_session"):
+                channel.request_to_session[request_id] = receiver
+
+        channel.send(Reply(ReplyType.TEXT, summary), context)
+        logger.info(f"[Evolution] Notified user via {channel_type}")
+    except Exception as e:
+        logger.warning(f"[Evolution] Failed to notify user: {e}")

agent/evolution/prompts.py

@@ -0,0 +1,170 @@
+"""Prompts for the self-evolution review agent.
+
+The system prompt is intentionally English-only: it governs the agent's
+internal reasoning and is more stable / cheaper to maintain in one language.
+The user-facing summary the agent produces should follow the user's own
+language (instructed at the end of the prompt).
+
+Design goals (see ref/hermes-agent background_review for inspiration):
+  - Default to doing NOTHING. Evolution is the exception, not the rule.
+  - Signal types: skill, unfinished task, memory, knowledge.
+  - An explicit "do NOT capture" list to avoid self-poisoning over time.
+  - Generic examples only — never bake in domain-specific business terms.
+"""
+
+# Sentinel the agent emits when there is nothing worth evolving.
+SILENT_TOKEN = "[SILENT]"
+
+# Marker prefix for the evolution record injected into the user session, so the
+# main chat agent can recognize past evolutions and honor an "undo" request.
+EVOLUTION_MARKER = "[EVOLUTION]"
+
+
+EVOLUTION_SYSTEM_PROMPT = """You are a self-evolution review agent for an AI assistant.
+
+You are given a transcript of a conversation that just went idle. Your job is to
+decide whether anything from it is worth durably learning so future
+conversations go better — and if so, to make that change.
+
+# Top principle: default to doing NOTHING
+
+Most ordinary conversations need no evolution. Only act when there is a CLEAR
+signal below. If there is none, reply with exactly `[SILENT]` and stop. Staying
+silent is the normal, correct outcome — not a failure.
+
+Greetings, small talk, acknowledgements ("ok", "thanks", "got it"), and casual
+chat are NOT signals. For these, output exactly `[SILENT]` immediately — do not
+explore files, do not write a summary, do not be polite. Just `[SILENT]`.
+
+IMPORTANT: A summary is only allowed if you ACTUALLY made a file change via a
+tool (write/edit) in this pass. If you did not change any file, you MUST output
+exactly `[SILENT]` — never describe a change you only intended to make.
+
+# Signals worth acting on (act only if at least one clearly appears)
+
+SKILL and UNFINISHED TASK are your PRIMARY value — no other mechanism handles
+them. When their signal is clear, act; do not be shy here.
+
+1. SKILL — two cases:
+   a) PATCH an existing skill: a skill used here showed a STRUCTURAL problem (a
+      missing step/section, a wrong or outdated detail, an error in its
+      content), or its OUTPUT repeatedly misses something the user flagged. Read
+      the relevant skill file under the skills directory and make a small
+      incremental edit so it never recurs.
+   b) CREATE a new skill: a clearly reusable, repeatable workflow emerged that
+      no existing skill covers and the user is likely to want again. Follow the
+      `skill-creator` skill's conventions (read its SKILL.md for the required
+      structure), then create `skills/<name>/SKILL.md` by WRITING the file
+      directly with the write tool — this is the simplest reliable path. (bash
+      is available and confined to the workspace if a helper script is truly
+      needed, but a direct write is preferred.) Only create when the workflow is
+      genuinely reusable — not for a one-off task.
+
+   CRITICAL — fix the SOURCE, do not just remember the symptom: when the root
+   cause of a problem lives IN a skill file itself (its instructions, content,
+   or configuration are wrong/outdated), the correct action is to EDIT that
+   skill so the problem cannot recur. Recording the corrected fact in memory
+   does NOT prevent recurrence — only fixing the skill does. Never log "skill X
+   has wrong detail Y" as a memory note in place of editing skill X.
+
+2. UNFINISHED TASK — a specific deliverable you promised but didn't produce,
+   AND you already have everything needed to finish it. DO IT now with the
+   available tools and produce the result (e.g. write the file you said you'd
+   write). If key info is missing, or the task is merely waiting on the user's
+   reply/decision, do NOTHING and stay [SILENT] — do not nag or ping the user.
+   You only ever notify the user as a side effect of having actually done work.
+
+3. MEMORY — RARE, last resort. Default to writing NOTHING here. The main
+   assistant already writes memory during the chat, and a nightly pass plus
+   context-overflow saves are dedicated safety nets — so memory is almost always
+   already covered without you. Skip unless the main assistant clearly missed a
+   durable fact that belongs in no skill AND would visibly change future replies.
+   - MEMORY.md is the curated long-term index, auto-loaded into EVERY future
+     conversation. Treat it as precious: edit it in place to CORRECT a wrong
+     fact, or append a new durable preference/decision/lesson — but do so
+     SPARINGLY (a lasting fact, not a passing detail; the nightly pass handles
+     routine consolidation).
+   - For a NEW fact that is important but not yet clearly lasting, append ONE
+     short bullet to today's `memory/YYYY-MM-DD.md` instead. When unsure, the
+     daily file is the safe place — but first ask whether this really belongs
+     in a skill.
+   - PERSONA (AGENT.md) — EXTREMELY rare: only on an explicit, repeated signal
+     about the assistant's own identity/personality/style, make a small edit to
+     AGENT.md; never for user/world facts, and when in doubt do nothing.
+   - Keep it to ONE short bullet. Never write paragraphs, never re-summarize the
+     conversation, never copy what the main assistant already recorded.
+   - If it is already captured anywhere (check MEMORY.md AND the daily file
+     first), do NOTHING.
+
+4. KNOWLEDGE — only if the conversation produced durable, reusable reference
+   knowledge on a topic (the kind worth looking up again) that the main
+   assistant did NOT already save to `knowledge/`. Add or update the relevant
+   file there. Like memory, this is the exception: skip routine Q&A, and if the
+   topic is already covered in `knowledge/`, do NOTHING rather than duplicate.
+
+# Do NOT capture (these poison future behavior)
+
+- Environment failures: missing binaries, unset credentials, uninstalled
+  packages, "command not found". The user can fix these; they are not durable
+  rules.
+- Negative claims about tools or features ("tool X does not work"). These
+  harden into refusals the agent cites against itself later.
+- One-off task narratives (e.g. summarizing today's content). Not a class of
+  reusable work.
+- Transient errors that resolved on retry within the conversation.
+
+# Execution constraints
+
+- Before changing memory or a skill, READ the current content first and make a
+  small INCREMENTAL edit. Never fabricate, never rewrite large sections.
+- AVOID DUPLICATES. Before writing memory, READ both MEMORY.md AND today's
+  daily file `memory/YYYY-MM-DD.md`. If the fact/preference is already recorded
+  in EITHER (even if worded differently), do NOT add it again. The main
+  assistant likely already wrote it during the chat — only add what is
+  genuinely new or a correction not yet reflected anywhere.
+- You may only edit files inside the workspace. Built-in skills shipped with
+  the product live outside it and are write-protected; do not try to edit them.
+- Make at most the few edits the signals justify; do not go looking for work.
+
+# Output
+
+- Nothing worth evolving -> output exactly `[SILENT]` and nothing else.
+- Otherwise, after performing the edits, output a short user-facing summary in
+  the SAME LANGUAGE the user speaks in the conversation transcript. Write it for an ordinary user, in plain
+  everyday words — NOT a developer report. No need to expose internal details
+  (file names/paths, system mechanics, etc.). Briefly speak directly TO the user, telling them that you just did a self-learning pass,
+  what you learned, and what you changed in THIS pass. Keep it clear and focused on the key changes (a few lines), and let
+  the user know they can undo it.
+"""
+
+
+def build_review_user_message(transcript: str, protected_skills: list = None) -> str:
+    """Wrap the conversation transcript as the review agent's user message.
+
+    ``protected_skills`` lists skill names that must never be edited (built-in
+    skills shipped with the product). Surfaced so the agent avoids them.
+    """
+    protected_note = ""
+    if protected_skills:
+        names = ", ".join(sorted(protected_skills))
+        protected_note = (
+            "\n\nPROTECTED skills (built-in — never edit these): "
+            f"{names}\n"
+        )
+    try:
+        from common import i18n
+        lang_name = "中文" if i18n.is_zh() else "English"
+    except Exception:
+        lang_name = "中文"
+    return (
+        "Here is the conversation transcript that just went idle. Review it per "
+        "your instructions. Acting is the exception: the main value is fixing or "
+        "creating a skill and finishing promised work. Memory and knowledge are "
+        "rare last resorts — stay [SILENT] unless there is a clear, durable signal "
+        "not already covered."
+        f"{protected_note}\n"
+        f"The summary should preferably be written in: {lang_name}\n"
+        "<transcript>\n"
+        f"{transcript}\n"
+        "</transcript>"
+    )

agent/evolution/record.py

@@ -0,0 +1,55 @@
+"""Self-evolution record log.
+
+Session-level evolutions are appended to their OWN per-day file under
+``memory/evolution/YYYY-MM-DD.md`` (separate from the nightly Deep Dream diary
+in ``memory/dreams/``). Each day's file accumulates one short section per
+evolution pass — tagged with a timestamp and a backup id for undo — so the
+memory UI can surface "what the agent learned/changed today" on one timeline
+without ever mixing into the dream diary or the main conversation memory.
+"""
+
+from __future__ import annotations
+
+from datetime import datetime
+from pathlib import Path
+from typing import Optional
+
+from common.log import logger
+
+
+def _evolution_dir(workspace_dir: Path, user_id: Optional[str] = None) -> Path:
+    base = Path(workspace_dir) / "memory"
+    if user_id:
+        return base / "users" / user_id / "evolution"
+    return base / "evolution"
+
+
+def append_session_evolution(
+    workspace_dir: Path,
+    summary: str,
+    backup_id: Optional[str] = None,
+    user_id: Optional[str] = None,
+) -> None:
+    """Append a session-evolution entry to today's evolution log."""
+    if not summary or not summary.strip():
+        return
+    try:
+        evo_dir = _evolution_dir(workspace_dir, user_id)
+        evo_dir.mkdir(parents=True, exist_ok=True)
+        today = datetime.now().strftime("%Y-%m-%d")
+        log_file = evo_dir / f"{today}.md"
+
+        ts = datetime.now().strftime("%H:%M")
+        header = f"## {ts}"
+        body = summary.strip()
+        if backup_id:
+            body += f"\n\n_backup_id: {backup_id}_"
+
+        # Create with a title if the file is new, otherwise append a section.
+        if not log_file.exists():
+            log_file.write_text(f"# Self-Evolution: {today}\n\n", encoding="utf-8")
+        with open(log_file, "a", encoding="utf-8") as f:
+            f.write(f"\n{header}\n\n{body}\n")
+        logger.info(f"[Evolution] Recorded session evolution to {log_file.name}")
+    except Exception as e:
+        logger.warning(f"[Evolution] Failed to record session evolution: {e}")

agent/evolution/trigger.py

@@ -0,0 +1,151 @@
+"""Idle-based evolution trigger.
+
+A single background thread periodically scans live agent sessions and runs an
+evolution pass for any session that is idle for >= idle_minutes AND has enough
+accumulated signal, where "enough signal" is EITHER:
+  - >= min_turns user turns since the last evolution, OR
+  - the live context has grown past _CONTEXT_RATIO of the agent's token budget
+    (mirrors how OpenClacky / Claude Code consolidate under context pressure).
+
+Turn counting is per user turn (not per message), measured from the last
+evolution (or session start). After a pass runs, the baseline resets so a long
+session can evolve multiple times without re-judging old content.
+
+Per-session evolution state is stored on the agent instance via lightweight
+attributes set by AgentBridge.agent_reply (see _note_user_turn).
+"""
+
+from __future__ import annotations
+
+import threading
+import time
+
+from common.log import logger
+
+from agent.evolution.config import get_evolution_config
+from agent.evolution.executor import run_evolution_for_session
+
+_SCAN_INTERVAL_SECONDS = 60
+
+# Context-pressure trigger: evolve once the live context exceeds this fraction
+# of the agent's token budget, even if min_turns hasn't been reached. Kept as a
+# module constant (not user config) for now. Fallback budget matches
+# agent_initializer / config.py (agent_max_context_tokens default = 50000).
+_CONTEXT_RATIO = 0.8
+_FALLBACK_CONTEXT_BUDGET = 50000
+
+
+def _context_pressure_reached(agent) -> bool:
+    """True if the agent's live context exceeds _CONTEXT_RATIO of its budget.
+
+    Uses the agent's own (estimated) token accounting so behavior matches the
+    existing context-trimming path. Best-effort: any error -> False.
+    """
+    try:
+        with agent.messages_lock:
+            messages = list(agent.messages)
+        if not messages:
+            return False
+        est = sum(agent._estimate_message_tokens(m) for m in messages)
+        budget = getattr(agent, "max_context_tokens", None) or _FALLBACK_CONTEXT_BUDGET
+        return est / budget > _CONTEXT_RATIO
+    except Exception:
+        return False
+
+
+def note_user_turn(agent, channel_type: str = "", receiver: str = "") -> None:
+    """Record activity for a session's agent. Called once per real user turn.
+
+    Maintains, on the agent instance:
+      _evo_last_active   : epoch seconds of the last user turn
+      _evo_turns         : user turns since the last evolution
+      _evo_channel_type  : originating channel (for later notify)
+      _evo_receiver      : push target for notify
+    """
+    try:
+        agent._evo_last_active = time.time()
+        agent._evo_turns = int(getattr(agent, "_evo_turns", 0)) + 1
+        if channel_type:
+            agent._evo_channel_type = channel_type
+        if receiver:
+            agent._evo_receiver = receiver
+    except Exception:
+        pass
+
+
+def mark_run_active(agent, active: bool) -> None:
+    """Flag whether the agent is mid-run, so idle scans skip a busy session.
+
+    Without this, a single run that lasts longer than idle_minutes would let
+    the scanner fire an evolution pass concurrently with the live turn.
+    """
+    try:
+        agent._evo_run_active = bool(active)
+        if active:
+            agent._evo_last_active = time.time()
+    except Exception:
+        pass
+
+
+def start_evolution_trigger(agent_bridge) -> None:
+    """Start the idle-scan thread once per process (idempotent)."""
+    if getattr(agent_bridge, "_evolution_trigger_started", False):
+        return
+    agent_bridge._evolution_trigger_started = True
+
+    t = threading.Thread(
+        target=_scan_loop, args=(agent_bridge,), daemon=True, name="evolution-trigger"
+    )
+    t.start()
+    logger.info("[Evolution] Idle trigger started")
+
+
+def _scan_loop(agent_bridge) -> None:
+    while True:
+        try:
+            time.sleep(_SCAN_INTERVAL_SECONDS)
+            cfg = get_evolution_config()
+            if not cfg.enabled:
+                continue
+            _scan_once(agent_bridge, cfg)
+        except Exception as e:
+            logger.warning(f"[Evolution] Scan loop error: {e}")
+            time.sleep(_SCAN_INTERVAL_SECONDS)
+
+
+def _scan_once(agent_bridge, cfg) -> None:
+    now = time.time()
+    # Snapshot to avoid holding the dict while running long evolutions.
+    sessions = list(getattr(agent_bridge, "agents", {}).items())
+    for session_id, agent in sessions:
+        try:
+            # Skip sessions whose agent is mid-run: a long turn must not be
+            # reviewed while it is still producing the answer.
+            if getattr(agent, "_evo_run_active", False):
+                continue
+            last_active = getattr(agent, "_evo_last_active", 0)
+            turns = int(getattr(agent, "_evo_turns", 0))
+            # Enough signal = enough turns OR enough context pressure.
+            enough_signal = turns >= cfg.min_turns or _context_pressure_reached(agent)
+            if not enough_signal:
+                continue
+            idle = now - last_active if last_active > 0 else -1
+            if last_active <= 0 or idle < cfg.idle_seconds:
+                continue
+
+            channel_type = getattr(agent, "_evo_channel_type", "") or ""
+            receiver = getattr(agent, "_evo_receiver", "") or ""
+
+            # Reset baseline BEFORE running so a long pass / new messages during
+            # it don't double-trigger; turns accrue fresh from here.
+            agent._evo_turns = 0
+
+            run_evolution_for_session(
+                agent_bridge,
+                session_id=session_id,
+                channel_type=channel_type,
+                receiver=receiver,
+                idle_minutes=(now - last_active) / 60 if last_active > 0 else 0.0,
+            )
+        except Exception as e:
+            logger.warning(f"[Evolution] Failed to evaluate session={session_id}: {e}")

agent/knowledge/service.py

@@ -0,0 +1,645 @@
+"""
+Knowledge service for handling knowledge base operations.
+
+Provides a unified interface for listing, reading, and graphing knowledge files,
+callable from the web console, API, or CLI.
+
+Knowledge file layout (under workspace_root):
+    knowledge/index.md
+    knowledge/log.md
+    knowledge/<category>/<slug>.md
+"""
+
+import os
+import re
+import asyncio
+import shutil
+import threading
+from pathlib import Path
+from typing import Optional, Iterable
+from urllib.parse import quote
+
+from common.log import logger
+from config import conf
+from agent.memory.config import MemoryConfig
+from agent.memory.manager import MemoryManager
+
+
+class KnowledgeService:
+    """
+    High-level service for knowledge base queries.
+    Operates directly on the filesystem.
+    """
+
+    PROTECTED_FILES = {"index.md", "log.md"}
+    INVALID_NAME_RE = re.compile(r'[<>:"|?*\x00-\x1f]')
+    IMPORT_EXTENSIONS = {".md", ".txt"}
+    MAX_IMPORT_FILES = 100
+    MAX_IMPORT_FILE_SIZE = 10 * 1024 * 1024
+    MAX_IMPORT_TOTAL_SIZE = 200 * 1024 * 1024
+
+    def __init__(self, workspace_root: str, memory_manager=None):
+        self.workspace_root = os.path.abspath(workspace_root)
+        self.knowledge_dir = os.path.join(self.workspace_root, "knowledge")
+        self._memory_manager = memory_manager
+
+    def _resolve_path(self, rel_path: str, *, kind: Optional[str] = None,
+                      allow_missing: bool = True) -> tuple:
+        if not isinstance(rel_path, str) or not rel_path.strip():
+            raise ValueError("path is required")
+        rel_path = rel_path.replace("\\", "/").strip("/")
+        parts = rel_path.split("/")
+        if any(not p or p in (".", "..") or self.INVALID_NAME_RE.search(p) for p in parts):
+            raise ValueError("invalid path")
+        if kind == "document" and not rel_path.lower().endswith(".md"):
+            raise ValueError("document path must end with .md")
+
+        root = Path(self.knowledge_dir).resolve()
+        candidate = root.joinpath(*parts)
+        # Resolve the nearest existing ancestor so a symlink cannot be used
+        # to escape when the final destination does not exist yet.
+        ancestor = candidate
+        while not ancestor.exists() and ancestor != root:
+            ancestor = ancestor.parent
+        try:
+            ancestor.resolve().relative_to(root)
+        except ValueError:
+            raise ValueError("path outside knowledge dir")
+        if candidate.exists():
+            try:
+                candidate.resolve().relative_to(root)
+            except ValueError:
+                raise ValueError("path outside knowledge dir")
+        elif not allow_missing:
+            raise FileNotFoundError(f"path not found: {rel_path}")
+        return rel_path, candidate
+
+    def _ensure_not_protected(self, rel_path: str):
+        if rel_path in self.PROTECTED_FILES:
+            raise ValueError(f"protected knowledge file: {rel_path}")
+
+    def _manager(self):
+        if self._memory_manager is None:
+            # Reuse the shared embedding provider selection so knowledge index
+            # sync gets vectors too, instead of degrading to keyword-only.
+            from agent.memory.embedding import create_default_embedding_provider
+            embedding_provider = create_default_embedding_provider()
+            self._memory_manager = MemoryManager(
+                MemoryConfig(workspace_root=self.workspace_root),
+                embedding_provider=embedding_provider,
+            )
+        return self._memory_manager
+
+    @staticmethod
+    def _run_sync(coro):
+        try:
+            asyncio.get_running_loop()
+        except RuntimeError:
+            return asyncio.run(coro)
+        result = []
+        error = []
+
+        def runner():
+            try:
+                result.append(asyncio.run(coro))
+            except Exception as exc:
+                error.append(exc)
+
+        thread = threading.Thread(target=runner)
+        thread.start()
+        thread.join()
+        if error:
+            raise error[0]
+        return result[0] if result else None
+
+    def _sync_index(self, old_paths: Iterable[str], force: bool = False):
+        old_paths = sorted(set(old_paths))
+        if not old_paths and not force:
+            return
+        manager = self._manager()
+        for rel_path in old_paths:
+            manager.storage.delete_by_path(f"knowledge/{rel_path}")
+        manager.mark_dirty()
+        self._run_sync(manager.sync())
+
+    @staticmethod
+    def _extract_title(md_path: Path, fallback: str) -> str:
+        """Read a markdown file's H1 title, falling back to the file stem."""
+        try:
+            with open(md_path, "r", encoding="utf-8") as f:
+                for _ in range(20):
+                    line = f.readline()
+                    if not line:
+                        break
+                    stripped = line.strip()
+                    if stripped.startswith("# "):
+                        return stripped[2:].strip() or fallback
+        except Exception:
+            pass
+        return fallback
+
+    def rebuild_index_md(self) -> bool:
+        """Regenerate knowledge/index.md from the actual directory tree.
+
+        Keeps the index in sync with real files so it never drifts or loses
+        documents. Returns True when the file was (re)written.
+        """
+        root = Path(self.knowledge_dir)
+        if not root.is_dir():
+            return False
+
+        def collect(dir_path: Path) -> list:
+            # Return sorted (rel_path, title) tuples for *.md under dir_path,
+            # excluding protected files at the knowledge root and dot files.
+            entries = []
+            for md in sorted(dir_path.rglob("*.md")):
+                rel = md.relative_to(root).as_posix()
+                if any(part.startswith(".") for part in md.relative_to(root).parts):
+                    continue
+                if rel in self.PROTECTED_FILES:
+                    continue
+                entries.append((rel, self._extract_title(md, md.stem)))
+            return entries
+
+        all_entries = collect(root)
+
+        def link(rel: str) -> str:
+            # Encode each path segment so spaces / special chars stay valid in
+            # markdown links, while keeping the slashes between segments.
+            encoded = "/".join(quote(part) for part in rel.split("/"))
+            return f"./{encoded}"
+
+        lines = ["# 知识库目录", ""]
+        # Root-level documents first (no category dir).
+        root_docs = [(rel, title) for rel, title in all_entries if "/" not in rel]
+        for rel, title in root_docs:
+            lines.append(f"- [{title}]({link(rel)})")
+        if root_docs:
+            lines.append("")
+
+        # Group remaining documents by their top-level category.
+        categories = {}
+        for rel, title in all_entries:
+            if "/" not in rel:
+                continue
+            category = rel.split("/", 1)[0]
+            categories.setdefault(category, []).append((rel, title))
+
+        for category in sorted(categories.keys()):
+            lines.append(f"## {category}")
+            for rel, title in categories[category]:
+                lines.append(f"- [{title}]({link(rel)})")
+            lines.append("")
+
+        content = "\n".join(lines).rstrip() + "\n"
+        index_path = root / "index.md"
+        try:
+            index_path.write_text(content, encoding="utf-8")
+            return True
+        except Exception as exc:
+            logger.warning(f"[KnowledgeService] Failed to rebuild index.md: {exc}")
+            return False
+
+    def _sanitize_document_name(self, filename: str) -> str:
+        name = os.path.basename((filename or "").replace("\\", "/")).strip()
+        if not name:
+            raise ValueError("filename is required")
+        stem, ext = os.path.splitext(name)
+        if ext.lower() not in self.IMPORT_EXTENSIONS:
+            raise ValueError(f"unsupported file type: {ext or name}")
+        if not stem or stem in (".", "..") or self.INVALID_NAME_RE.search(stem):
+            raise ValueError("invalid filename")
+        safe_name = f"{stem}.md"
+        self._ensure_not_protected(safe_name)
+        return safe_name
+
+    @staticmethod
+    def _decode_document_content(content) -> str:
+        if isinstance(content, str):
+            return content
+        if not isinstance(content, (bytes, bytearray)):
+            raise ValueError("document content is required")
+        return bytes(content).decode("utf-8-sig", errors="replace")
+
+    def _resolve_import_destination(self, target_category: str, filename: str,
+                                    conflict_strategy: str) -> tuple:
+        target_rel, target_full = self._resolve_path(target_category, kind="category")
+        if not target_full.is_dir():
+            raise FileNotFoundError(f"category not found: {target_rel}")
+
+        safe_name = self._sanitize_document_name(filename)
+        destination = target_full / safe_name
+        rel_path = f"{target_rel}/{safe_name}"
+
+        if destination.exists():
+            if conflict_strategy == "skip":
+                return rel_path, destination, "skip"
+            if conflict_strategy == "rename":
+                stem = destination.stem
+                suffix = destination.suffix
+                for index in range(1, 1000):
+                    candidate = target_full / f"{stem}-{index}{suffix}"
+                    if not candidate.exists():
+                        candidate_rel = f"{target_rel}/{candidate.name}"
+                        return candidate_rel, candidate, "write"
+                raise FileExistsError(f"target already exists: {rel_path}")
+            if conflict_strategy != "overwrite":
+                raise ValueError("invalid conflict strategy")
+        return rel_path, destination, "write"
+
+    def create_document(self, path: str, content: str = "", overwrite: bool = False) -> dict:
+        rel_path, full_path = self._resolve_path(path, kind="document")
+        self._ensure_not_protected(rel_path)
+        if len((content or "").encode("utf-8")) > self.MAX_IMPORT_FILE_SIZE:
+            raise ValueError("file too large")
+        if full_path.exists() and not overwrite:
+            raise FileExistsError(f"target already exists: {rel_path}")
+        old_paths = [rel_path] if full_path.exists() else []
+        full_path.parent.mkdir(parents=True, exist_ok=True)
+        full_path.write_text(content or "", encoding="utf-8")
+        # Keep index.md in sync before reindexing so it is indexed too.
+        self.rebuild_index_md()
+        self._sync_index(old_paths, force=True)
+        return {"path": rel_path, "created": True, "overwritten": bool(old_paths)}
+
+    def import_documents(self, target_category: str, files: Iterable[dict],
+                         conflict_strategy: str = "skip") -> dict:
+        if not isinstance(files, list):
+            raise ValueError("files must be a list")
+        if len(files) > self.MAX_IMPORT_FILES:
+            raise ValueError(f"too many files: max {self.MAX_IMPORT_FILES}")
+        results = []
+        old_paths = []
+        imported = skipped = failed = 0
+        total_size = 0
+
+        for item in files:
+            filename = item.get("filename") if isinstance(item, dict) else None
+            try:
+                content_bytes = item.get("content") if isinstance(item, dict) else None
+                size = len(content_bytes.encode("utf-8")) if isinstance(content_bytes, str) else len(content_bytes or b"")
+                total_size += size
+                if total_size > self.MAX_IMPORT_TOTAL_SIZE:
+                    raise ValueError("import batch too large")
+                if size > self.MAX_IMPORT_FILE_SIZE:
+                    raise ValueError("file too large")
+                rel_path, destination, mode = self._resolve_import_destination(
+                    target_category, filename, conflict_strategy
+                )
+                if mode == "skip":
+                    skipped += 1
+                    results.append({"filename": filename, "path": rel_path, "status": "skipped",
+                                    "reason": "target_exists"})
+                    continue
+
+                old_exists = destination.exists()
+                content = self._decode_document_content(content_bytes)
+                destination.parent.mkdir(parents=True, exist_ok=True)
+                destination.write_text(content, encoding="utf-8")
+                if old_exists:
+                    old_paths.append(rel_path)
+                imported += 1
+                results.append({"filename": filename, "path": rel_path, "status": "imported",
+                                "overwritten": old_exists})
+            except Exception as exc:
+                failed += 1
+                results.append({"filename": filename or "", "status": "failed", "reason": str(exc)})
+
+        if imported:
+            # Keep index.md in sync before reindexing so it is indexed too.
+            self.rebuild_index_md()
+            self._sync_index(old_paths, force=True)
+        return {"results": results, "imported": imported, "skipped": skipped, "failed": failed}
+
+    def create_category(self, path: str) -> dict:
+        rel_path, full_path = self._resolve_path(path, kind="category")
+        if full_path.exists():
+            return {"path": rel_path, "created": False, "reason": "already_exists"}
+        full_path.mkdir(parents=True)
+        return {"path": rel_path, "created": True}
+
+    def rename_category(self, path: str, new_path: str) -> dict:
+        old_rel, old_full = self._resolve_path(path, kind="category", allow_missing=False)
+        new_rel, new_full = self._resolve_path(new_path, kind="category")
+        if not old_full.is_dir():
+            raise ValueError(f"not a category: {old_rel}")
+        if new_full.exists():
+            raise FileExistsError(f"target already exists: {new_rel}")
+        old_documents = [str(p.relative_to(old_full)).replace(os.sep, "/")
+                         for p in old_full.rglob("*.md") if p.is_file()]
+        new_full.parent.mkdir(parents=True, exist_ok=True)
+        try:
+            old_full.rename(new_full)
+        except FileNotFoundError:
+            return {"old_path": old_rel, "path": new_rel, "moved": False, "reason": "not_found"}
+        except FileExistsError:
+            raise FileExistsError(f"target already exists: {new_rel}")
+        old_paths = [f"{old_rel}/{p}" for p in old_documents]
+        self._sync_index(old_paths)
+        return {"old_path": old_rel, "path": new_rel, "moved_documents": len(old_documents)}
+
+    def delete_category(self, path: str, confirm: bool = False) -> dict:
+        rel_path, full_path = self._resolve_path(path, kind="category")
+        if not full_path.exists():
+            return {"path": rel_path, "deleted": False, "reason": "not_found"}
+        if not full_path.is_dir():
+            raise ValueError(f"not a category: {rel_path}")
+        knowledge_root = Path(self.knowledge_dir).resolve()
+        documents = [str(p.relative_to(knowledge_root)).replace(os.sep, "/")
+                     for p in full_path.rglob("*.md") if p.is_file()]
+        if any(p in self.PROTECTED_FILES for p in documents):
+            raise ValueError("category contains protected knowledge files")
+        if any(full_path.iterdir()) and not confirm:
+            raise ValueError("category is not empty; confirmation is required")
+        try:
+            shutil.rmtree(full_path)
+        except FileNotFoundError:
+            return {"path": rel_path, "deleted": False, "reason": "not_found"}
+        self._sync_index(documents)
+        return {"path": rel_path, "deleted": True, "deleted_documents": len(documents)}
+
+    def delete_documents(self, paths: Iterable[str]) -> dict:
+        if not isinstance(paths, list):
+            raise ValueError("paths must be a list")
+        results = []
+        deleted = []
+        for path in paths:
+            rel_path, full_path = self._resolve_path(path, kind="document")
+            self._ensure_not_protected(rel_path)
+            if not full_path.exists():
+                deleted.append(rel_path)
+                results.append({"path": rel_path, "deleted": False, "reason": "not_found"})
+                continue
+            if not full_path.is_file():
+                raise ValueError(f"not a document: {rel_path}")
+            try:
+                full_path.unlink()
+                deleted.append(rel_path)
+                results.append({"path": rel_path, "deleted": True})
+            except FileNotFoundError:
+                deleted.append(rel_path)
+                results.append({"path": rel_path, "deleted": False, "reason": "not_found"})
+        self._sync_index(deleted)
+        return {"results": results, "deleted": sum(1 for item in results if item["deleted"])}
+
+    def move_documents(self, paths: Iterable[str], target_category: str) -> dict:
+        if not isinstance(paths, list):
+            raise ValueError("paths must be a list")
+        target_rel, target_full = self._resolve_path(target_category, kind="category")
+        if not target_full.is_dir():
+            raise FileNotFoundError(f"category not found: {target_rel}")
+        results = []
+        moved_old_paths = []
+        for path in paths:
+            rel_path, full_path = self._resolve_path(path, kind="document")
+            self._ensure_not_protected(rel_path)
+            if not full_path.exists():
+                results.append({"path": rel_path, "moved": False, "reason": "not_found"})
+                continue
+            destination = target_full / full_path.name
+            new_rel = str(destination.relative_to(Path(self.knowledge_dir).resolve())).replace(os.sep, "/")
+            if destination.exists():
+                results.append({"path": rel_path, "moved": False, "reason": "target_exists",
+                                "target": new_rel})
+                continue
+            try:
+                os.link(full_path, destination)
+                full_path.unlink()
+                moved_old_paths.append(rel_path)
+                results.append({"path": rel_path, "moved": True, "target": new_rel})
+            except FileExistsError:
+                results.append({"path": rel_path, "moved": False, "reason": "target_exists",
+                                "target": new_rel})
+            except FileNotFoundError:
+                results.append({"path": rel_path, "moved": False, "reason": "not_found"})
+        self._sync_index(moved_old_paths)
+        return {"results": results, "moved": len(moved_old_paths)}
+
+    # ------------------------------------------------------------------
+    # list — directory tree with stats
+    # ------------------------------------------------------------------
+    def list_tree(self) -> dict:
+        """
+        Return the knowledge directory tree grouped by category,
+        supporting arbitrarily nested sub-directories.
+
+        Returns::
+
+            {
+                "tree": [
+                    {
+                        "dir": "concepts",
+                        "files": [
+                            {"name": "moe.md", "title": "MoE", "size": 1234},
+                        ],
+                        "children": []
+                    },
+                    {
+                        "dir": "platform",
+                        "files": [],
+                        "children": [
+                            {
+                                "dir": "analysis",
+                                "files": [{"name": "perf.md", ...}],
+                                "children": []
+                            }
+                        ]
+                    },
+                ],
+                "stats": {"pages": 15, "size": 32768},
+                "enabled": true
+            }
+        """
+        if not os.path.isdir(self.knowledge_dir):
+            return {"tree": [], "stats": {"pages": 0, "size": 0}, "enabled": conf().get("knowledge", True)}
+
+        stats = {"pages": 0, "size": 0}
+        root_files, tree = self._scan_dir(self.knowledge_dir, stats, is_root=True)
+
+        return {
+            "root_files": root_files,
+            "tree": tree,
+            "stats": stats,
+            "enabled": conf().get("knowledge", True),
+        }
+
+    def _scan_dir(self, dir_path: str, stats: dict, is_root: bool = False) -> tuple:
+        """
+        Recursively scan a directory.
+
+        :return: (files, children) where files is a list of .md file dicts
+                 in this directory and children is a list of sub-directory nodes.
+        """
+        files = []
+        children = []
+        for name in sorted(os.listdir(dir_path)):
+            if name.startswith("."):
+                continue
+            full = os.path.join(dir_path, name)
+            if os.path.isdir(full):
+                sub_files, sub_children = self._scan_dir(full, stats)
+                children.append({"dir": name, "files": sub_files, "children": sub_children})
+            elif name.endswith(".md"):
+                size = os.path.getsize(full)
+                if not is_root:
+                    stats["pages"] += 1
+                    stats["size"] += size
+                # Prefer the H1 heading as a readable title for normal docs.
+                # System files (index.md / log.md) keep their filename so the
+                # tree never hides what they actually are.
+                title = name[:-3]
+                if name not in self.PROTECTED_FILES:
+                    try:
+                        with open(full, "r", encoding="utf-8") as f:
+                            first_line = f.readline().strip()
+                        if first_line.startswith("# "):
+                            title = first_line[2:].strip() or title
+                    except Exception:
+                        pass
+                files.append({"name": name, "title": title, "size": size})
+        return files, children
+
+    # ------------------------------------------------------------------
+    # read — single file content
+    # ------------------------------------------------------------------
+    def read_file(self, rel_path: str) -> dict:
+        """
+        Read a single knowledge markdown file.
+
+        :param rel_path: Relative path within knowledge/, e.g. ``concepts/moe.md``
+        :return: dict with ``content`` and ``path``
+        :raises ValueError: if path is invalid or escapes knowledge dir
+        :raises FileNotFoundError: if file does not exist
+        """
+        rel_path, full_path = self._resolve_path(rel_path, kind="document")
+        if not full_path.is_file():
+            raise FileNotFoundError(f"file not found: {rel_path}")
+
+        with open(full_path, "r", encoding="utf-8") as f:
+            content = f.read()
+        return {"content": content, "path": rel_path}
+
+    # ------------------------------------------------------------------
+    # graph — nodes and links for visualization
+    # ------------------------------------------------------------------
+    def build_graph(self) -> dict:
+        """
+        Parse all knowledge pages and extract cross-reference links.
+
+        Returns::
+
+            {
+                "nodes": [
+                    {"id": "concepts/moe.md", "label": "MoE", "category": "concepts"},
+                    ...
+                ],
+                "links": [
+                    {"source": "concepts/moe.md", "target": "entities/deepseek.md"},
+                    ...
+                ]
+            }
+        """
+        knowledge_path = Path(self.knowledge_dir)
+        if not knowledge_path.is_dir():
+            return {"nodes": [], "links": []}
+
+        nodes = {}
+        links = []
+        link_re = re.compile(r'\[([^\]]*)\]\(([^)]+\.md)\)')
+
+        for md_file in knowledge_path.rglob("*.md"):
+            rel = str(md_file.relative_to(knowledge_path))
+            if rel in ("index.md", "log.md"):
+                continue
+            parts = rel.split("/")
+            category = parts[0] if len(parts) > 1 else "root"
+            title = md_file.stem.replace("-", " ").title()
+            try:
+                content = md_file.read_text(encoding="utf-8")
+                first_line = content.strip().split("\n")[0]
+                if first_line.startswith("# "):
+                    title = first_line[2:].strip()
+                for _, link_target in link_re.findall(content):
+                    resolved = (md_file.parent / link_target).resolve()
+                    try:
+                        target_rel = str(resolved.relative_to(knowledge_path))
+                    except ValueError:
+                        continue
+                    if target_rel != rel:
+                        links.append({"source": rel, "target": target_rel})
+            except Exception:
+                pass
+            nodes[rel] = {"id": rel, "label": title, "category": category}
+
+        valid_ids = set(nodes.keys())
+        links = [l for l in links if l["source"] in valid_ids and l["target"] in valid_ids]
+        seen = set()
+        deduped = []
+        for l in links:
+            key = tuple(sorted([l["source"], l["target"]]))
+            if key not in seen:
+                seen.add(key)
+                deduped.append(l)
+
+        return {"nodes": list(nodes.values()), "links": deduped}
+
+    # ------------------------------------------------------------------
+    # dispatch — single entry point for protocol messages
+    # ------------------------------------------------------------------
+    def dispatch(self, action: str, payload: Optional[dict] = None) -> dict:
+        """
+        Dispatch a knowledge management action.
+
+        :param action: ``list``, ``read``, or ``graph``
+        :param payload: action-specific payload
+        :return: protocol-compatible response dict
+        """
+        payload = payload or {}
+        try:
+            if action == "list":
+                result = self.list_tree()
+                return {"action": action, "code": 200, "message": "success", "payload": result}
+
+            elif action == "read":
+                path = payload.get("path")
+                if not path:
+                    return {"action": action, "code": 400, "message": "path is required", "payload": None}
+                result = self.read_file(path)
+                return {"action": action, "code": 200, "message": "success", "payload": result}
+
+            elif action == "graph":
+                result = self.build_graph()
+                return {"action": action, "code": 200, "message": "success", "payload": result}
+
+            elif action == "create_category":
+                result = self.create_category(payload.get("path"))
+            elif action == "rename_category":
+                result = self.rename_category(payload.get("path"), payload.get("new_path"))
+            elif action == "delete_category":
+                result = self.delete_category(payload.get("path"), payload.get("confirm", False))
+            elif action == "delete_documents":
+                result = self.delete_documents(payload.get("paths") or [])
+            elif action == "move_documents":
+                result = self.move_documents(payload.get("paths") or [], payload.get("target_category"))
+            elif action == "create_document":
+                result = self.create_document(payload.get("path"), payload.get("content", ""),
+                                              payload.get("overwrite", False))
+            elif action == "import_documents":
+                result = self.import_documents(
+                    payload.get("target_category"),
+                    payload.get("files") or [],
+                    payload.get("conflict_strategy", "skip"),
+                )
+            else:
+                return {"action": action, "code": 400, "message": f"unknown action: {action}", "payload": None}
+            return {"action": action, "code": 200, "message": "success", "payload": result}
+
+        except ValueError as e:
+            return {"action": action, "code": 403, "message": str(e), "payload": None}
+        except FileNotFoundError as e:
+            return {"action": action, "code": 404, "message": str(e), "payload": None}
+        except FileExistsError as e:
+            return {"action": action, "code": 409, "message": str(e), "payload": None}
+        except Exception as e:
+            logger.error(f"[KnowledgeService] dispatch error: action={action}, error={e}")
+            return {"action": action, "code": 500, "message": str(e), "payload": None}

agent/memory/__init__.py

@@ -7,8 +7,9 @@ conversation history persistence (SQLite).
 
 from agent.memory.manager import MemoryManager
 from agent.memory.config import MemoryConfig, get_default_memory_config, set_global_memory_config
-from agent.memory.embedding import create_embedding_provider
+from agent.memory.embedding import create_embedding_provider, create_default_embedding_provider
 from agent.memory.conversation_store import ConversationStore, get_conversation_store
+from agent.memory.summarizer import ensure_daily_memory_file
 
 __all__ = [
     'MemoryManager',
@@ -16,6 +17,8 @@ __all__ = [
     'get_default_memory_config',
     'set_global_memory_config',
     'create_embedding_provider',
+    'create_default_embedding_provider',
     'ConversationStore',
     'get_conversation_store',
+    'ensure_daily_memory_file',
 ]

agent/memory/config.py

@@ -48,9 +48,6 @@ class MemoryConfig:
     enable_auto_sync: bool = True
     sync_on_search: bool = True
     
-    # Memory flush config (独立于模型 context window)
-    flush_token_threshold: int = 50000  # 50K tokens 触发 flush
-    flush_turn_threshold: int = 20  # 20 轮对话触发 flush (用户+AI各一条为一轮)
     
     def get_workspace(self) -> Path:
         """Get workspace root directory"""

agent/memory/conversation_store.py

@@ -13,6 +13,7 @@ Storage path: ~/cow/sessions/conversations.db
 from __future__ import annotations
 
 import json
+import re
 import sqlite3
 import threading
 import time
@@ -28,11 +29,13 @@ from common.log import logger
 
 _DDL = """
 CREATE TABLE IF NOT EXISTS sessions (
-    session_id   TEXT    PRIMARY KEY,
+    session_id        TEXT    PRIMARY KEY,
-    channel_type TEXT    NOT NULL DEFAULT '',
+    channel_type      TEXT    NOT NULL DEFAULT '',
-    created_at   INTEGER NOT NULL,
+    title             TEXT    NOT NULL DEFAULT '',
-    last_active  INTEGER NOT NULL,
+    context_start_seq INTEGER NOT NULL DEFAULT 0,
-    msg_count    INTEGER NOT NULL DEFAULT 0
+    created_at        INTEGER NOT NULL,
+    last_active       INTEGER NOT NULL,
+    msg_count         INTEGER NOT NULL DEFAULT 0
 );
 
 CREATE TABLE IF NOT EXISTS messages (
@@ -42,6 +45,7 @@ CREATE TABLE IF NOT EXISTS messages (
     role         TEXT    NOT NULL,
     content      TEXT    NOT NULL,
     created_at   INTEGER NOT NULL,
+    extras       TEXT    NOT NULL DEFAULT '',
     UNIQUE (session_id, seq)
 );
 
@@ -57,6 +61,20 @@ _MIGRATION_ADD_CHANNEL_TYPE = """
 ALTER TABLE sessions ADD COLUMN channel_type TEXT NOT NULL DEFAULT '';
 """
 
+_MIGRATION_ADD_TITLE = """
+ALTER TABLE sessions ADD COLUMN title TEXT NOT NULL DEFAULT '';
+"""
+
+_MIGRATION_ADD_CONTEXT_START_SEQ = """
+ALTER TABLE sessions ADD COLUMN context_start_seq INTEGER NOT NULL DEFAULT 0;
+"""
+
+# Generic JSON sidecar for per-message attachments (TTS audio URL, future use).
+# Always optional — readers must tolerate missing column / empty / invalid JSON.
+_MIGRATION_ADD_MSG_EXTRAS = """
+ALTER TABLE messages ADD COLUMN extras TEXT NOT NULL DEFAULT '';
+"""
+
 DEFAULT_MAX_AGE_DAYS: int = 30
 
 
@@ -92,6 +110,48 @@ def _extract_display_text(content: Any) -> str:
     return ""
 
 
+# Internal markers written into the session for the agent's own bookkeeping
+# (scheduler injection / self-evolution undo). They must stay in the stored
+# content (the LLM reads them, e.g. to find a backup_id for undo) but should
+# never be shown verbatim to the user in the chat history UI.
+_SCHEDULED_DISPLAY_MARKERS = ("[SCHEDULED]", "Scheduled task")
+_EVOLUTION_DISPLAY_MARKER = "[EVOLUTION]"
+
+
+def _is_internal_user_marker(text: str) -> bool:
+    """True if a user-turn text is an internal injection marker (hide from UI)."""
+    t = (text or "").lstrip()
+    return any(t.startswith(m) for m in _SCHEDULED_DISPLAY_MARKERS)
+
+
+def _is_evolution_text(text: str) -> bool:
+    """True if assistant text is a self-evolution summary (before cleaning)."""
+    return (text or "").lstrip().startswith(_EVOLUTION_DISPLAY_MARKER)
+
+
+def _clean_display_text(text: str) -> str:
+    """Strip internal markers from assistant text for user-facing display.
+
+    Removes a leading ``[EVOLUTION]`` tag and a trailing ``(backup_id: ...)``
+    undo hint. The raw stored message is untouched, so undo + LLM context still
+    work; only the rendered chat bubble is cleaned.
+    """
+    if not text:
+        return text
+    cleaned = text
+    stripped = cleaned.lstrip()
+    if stripped.startswith(_EVOLUTION_DISPLAY_MARKER):
+        cleaned = stripped[len(_EVOLUTION_DISPLAY_MARKER):].lstrip()
+    # Drop a trailing backup_id undo hint line, e.g.
+    #   "(backup_id: 20260607-...; to undo, restore this backup)"
+    cleaned = re.sub(
+        r"\n*\(backup_id:[^\)]*\)\s*$",
+        "",
+        cleaned,
+    ).rstrip()
+    return cleaned
+
+
 def _extract_tool_calls(content: Any) -> List[Dict[str, Any]]:
     """
     Extract tool_use blocks from an assistant message content.
@@ -106,9 +166,10 @@ def _extract_tool_calls(content: Any) -> List[Dict[str, Any]]:
     ]
 
 
-def _extract_tool_results(content: Any) -> Dict[str, str]:
+def _extract_tool_results(content: Any) -> Dict[str, dict]:
     """
     Extract tool_result blocks from a user message, keyed by tool_use_id.
+    Values are {"result": str, "is_error": bool}.
     """
     if not isinstance(content, list):
         return {}
@@ -123,12 +184,13 @@ def _extract_tool_results(content: Any) -> Dict[str, str]:
                 rb.get("text", "") for rb in result_content
                 if isinstance(rb, dict) and rb.get("type") == "text"
             )
-        results[tool_id] = str(result_content)
+        results[tool_id] = {"result": str(result_content), "is_error": bool(b.get("is_error", False))}
     return results
 
 
 def _group_into_display_turns(
     rows: List[tuple],
+    include_thinking: bool = True,
 ) -> List[Dict[str, Any]]:
     """
     Convert raw (role, content_json, created_at) DB rows into display turns.
@@ -157,20 +219,26 @@ def _group_into_display_turns(
     cur_rest: List[tuple] = []
     started = False
 
-    for role, raw_content, created_at in rows:
+    for role, raw_content, created_at, raw_extras in rows:
         try:
             content = json.loads(raw_content)
         except Exception:
             content = raw_content
+        try:
+            extras = json.loads(raw_extras) if raw_extras else {}
+            if not isinstance(extras, dict):
+                extras = {}
+        except Exception:
+            extras = {}
 
         if role == "user" and _is_visible_user_message(content):
             if started:
                 groups.append((cur_user, cur_rest))
-            cur_user = (content, created_at)
+            cur_user = (content, created_at, extras)
             cur_rest = []
             started = True
         else:
-            cur_rest.append((role, content, created_at))
+            cur_rest.append((role, content, created_at, extras))
 
     if started:
         groups.append((cur_user, cur_rest))
@@ -183,39 +251,90 @@ def _group_into_display_turns(
     for user_row, rest in groups:
         # User turn
         if user_row:
-            content, created_at = user_row
+            content, created_at, _u_extras = user_row
             text = _extract_display_text(content)
-            if text:
+            # Hide internal injection markers (scheduler / self-evolution) so the
+            # user never sees a synthetic "[SCHEDULED] self-evolution" bubble;
+            # the assistant reply that follows is still rendered.
+            if text and not _is_internal_user_marker(text):
                 turns.append({"role": "user", "content": text, "created_at": created_at})
 
-        # Collect all tool_calls and tool_results from the rest of the group
+        # Build an ordered list of steps preserving the original sequence:
-        all_tool_calls: List[Dict[str, Any]] = []
+        #   thinking → content → tool_call → content → ...
+        steps: List[Dict[str, Any]] = []
         tool_results: Dict[str, str] = {}
         final_text = ""
         final_ts: Optional[int] = None
+        merged_extras: Dict[str, Any] = {}
 
-        for role, content, created_at in rest:
+        for role, content, created_at, extras in rest:
+            if role == "assistant" and isinstance(extras, dict):
+                merged_extras.update(extras)
             if role == "user":
                 tool_results.update(_extract_tool_results(content))
             elif role == "assistant":
-                tcs = _extract_tool_calls(content)
+                # Walk content blocks in order to preserve interleaving
-                all_tool_calls.extend(tcs)
+                if isinstance(content, list):
-                t = _extract_display_text(content)
+                    for block in content:
-                if t:
+                        if not isinstance(block, dict):
-                    final_text = t
+                            continue
+                        btype = block.get("type")
+                        if btype == "thinking":
+                            if not include_thinking:
+                                continue
+                            txt = block.get("thinking", "").strip()
+                            if txt:
+                                steps.append({"type": "thinking", "content": txt})
+                        elif btype == "text":
+                            txt = block.get("text", "").strip()
+                            if txt:
+                                steps.append({"type": "content", "content": txt})
+                                final_text = txt
+                        elif btype == "tool_use":
+                            steps.append({
+                                "type": "tool",
+                                "id": block.get("id", ""),
+                                "name": block.get("name", ""),
+                                "arguments": block.get("input", {}),
+                            })
+                elif isinstance(content, str) and content.strip():
+                    steps.append({"type": "content", "content": content.strip()})
+                    final_text = content.strip()
                 final_ts = created_at
 
-        # Attach tool results to their matching tool_call entries
+        # Attach tool results to tool steps
-        for tc in all_tool_calls:
+        for step in steps:
-            tc["result"] = tool_results.get(tc.get("id", ""), "")
+            if step["type"] == "tool":
+                tr = tool_results.get(step.get("id", ""), {})
+                if not isinstance(tr, dict):
+                    tr = {"result": tr}
+                step["result"] = tr.get("result", "")
+                step["is_error"] = tr.get("is_error", False)
 
-        if final_text or all_tool_calls:
+        # Detect a self-evolution bubble BEFORE cleaning the marker away, so the
-            turns.append({
+        # UI can flag it even though the visible text stays clean.
+        is_evolution = _is_evolution_text(final_text)
+
+        # Clean internal markers from the user-facing assistant text. Applies to
+        # both the final content and the mirrored content step so the rendered
+        # bubble shows clean text while the stored message keeps the markers.
+        final_text = _clean_display_text(final_text)
+        for step in steps:
+            if step.get("type") == "content":
+                step["content"] = _clean_display_text(step.get("content", ""))
+
+        if steps or final_text:
+            turn = {
                 "role": "assistant",
                 "content": final_text,
-                "tool_calls": all_tool_calls,
+                "steps": steps,
                 "created_at": final_ts or (user_row[1] if user_row else 0),
-            })
+            }
+            if is_evolution:
+                turn["kind"] = "evolution"
+            if merged_extras:
+                turn["extras"] = merged_extras
+            turns.append(turn)
 
     return turns
 
@@ -232,7 +351,7 @@ class ConversationStore:
 
     def __init__(self, db_path: Path):
         self._db_path = db_path
-        self._lock = threading.Lock()
+        self._lock = threading.RLock()  # Use RLock to allow reentrant locking
         self._init_db()
 
     # ------------------------------------------------------------------
@@ -264,14 +383,21 @@ class ConversationStore:
         with self._lock:
             conn = self._connect()
             try:
+                # Respect context_start_seq: only load messages at or after the boundary
+                ctx_row = conn.execute(
+                    "SELECT context_start_seq FROM sessions WHERE session_id = ?",
+                    (session_id,),
+                ).fetchone()
+                ctx_start = ctx_row[0] if ctx_row else 0
+
                 rows = conn.execute(
                     """
                     SELECT seq, role, content
                     FROM messages
-                    WHERE session_id = ?
+                    WHERE session_id = ? AND seq >= ?
                     ORDER BY seq DESC
                     """,
-                    (session_id,),
+                    (session_id, ctx_start),
                 ).fetchall()
             finally:
                 conn.close()
@@ -279,10 +405,7 @@ class ConversationStore:
         if not rows:
             return []
 
-        # Walk newest-to-oldest counting *visible* user turns (actual user text,
+        visible_turn_seqs: List[int] = []
-        # not tool_result injections).  Record the seq of every visible user
-        # message so we can find a clean cut point later.
-        visible_turn_seqs: List[int] = []  # newest first
         for seq, role, raw_content in rows:
             if role != "user":
                 continue
@@ -293,17 +416,11 @@ class ConversationStore:
             if _is_visible_user_message(content):
                 visible_turn_seqs.append(seq)
 
-        # Determine the seq of the oldest visible user message we want to keep.
-        # If the total turns fit within max_turns, keep everything.
         if len(visible_turn_seqs) <= max_turns:
-            cutoff_seq = None  # keep all
+            cutoff_seq = None
         else:
-            # The Nth visible user message (0-indexed) is the oldest we keep.
             cutoff_seq = visible_turn_seqs[max_turns - 1]
 
-        # Build result in chronological order, starting from cutoff.
-        # IMPORTANT: we start exactly at cutoff_seq (the visible user message),
-        # never mid-group, so tool_use / tool_result pairs are always complete.
         result = []
         for seq, role, raw_content in reversed(rows):
             if cutoff_seq is not None and seq < cutoff_seq:
@@ -312,6 +429,9 @@ class ConversationStore:
                 content = json.loads(raw_content)
             except Exception:
                 content = raw_content
+            # Strip thinking blocks — they are stored for UI display only
+            if role == "assistant" and isinstance(content, list):
+                content = [b for b in content if b.get("type") != "thinking"]
             result.append({"role": role, "content": content})
         return result
 
@@ -369,13 +489,15 @@ class ConversationStore:
                         content = json.dumps(
                             msg.get("content", ""), ensure_ascii=False
                         )
+                        extras_obj = msg.get("extras") or {}
+                        extras = json.dumps(extras_obj, ensure_ascii=False) if extras_obj else ""
                         conn.execute(
                             """
                             INSERT OR IGNORE INTO messages
-                                (session_id, seq, role, content, created_at)
+                                (session_id, seq, role, content, created_at, extras)
-                            VALUES (?, ?, ?, ?, ?)
+                            VALUES (?, ?, ?, ?, ?, ?)
                             """,
-                            (session_id, next_seq, role, content, now),
+                            (session_id, next_seq, role, content, now, extras),
                         )
                         next_seq += 1
 
@@ -389,9 +511,123 @@ class ConversationStore:
                         """,
                         (session_id, session_id),
                     )
+
+                    # Auto-generate title from the first visible user message
+                    cur_title = conn.execute(
+                        "SELECT title FROM sessions WHERE session_id = ?",
+                        (session_id,),
+                    ).fetchone()
+                    if cur_title and not cur_title[0]:
+                        for msg in messages:
+                            if msg.get("role") == "user":
+                                content = msg.get("content", "")
+                                text = _extract_display_text(content)
+                                if text:
+                                    title = text[:50].split("\n")[0]
+                                    conn.execute(
+                                        "UPDATE sessions SET title = ? WHERE session_id = ?",
+                                        (title, session_id),
+                                    )
+                                    break
             finally:
                 conn.close()
 
+    def clear_context(self, session_id: str) -> int:
+        """
+        Set the context boundary to after the current last message.
+        Messages before this boundary are still stored but excluded from LLM context.
+
+        Returns the new context_start_seq value.
+        """
+        with self._lock:
+            conn = self._connect()
+            try:
+                with conn:
+                    row = conn.execute(
+                        "SELECT COALESCE(MAX(seq), -1) FROM messages WHERE session_id = ?",
+                        (session_id,),
+                    ).fetchone()
+                    new_start = row[0] + 1
+                    conn.execute(
+                        "UPDATE sessions SET context_start_seq = ? WHERE session_id = ?",
+                        (new_start, session_id),
+                    )
+                    return new_start
+            finally:
+                conn.close()
+
+    def get_context_start_seq(self, session_id: str) -> int:
+        """Return the context_start_seq for a session (0 if not set)."""
+        with self._lock:
+            conn = self._connect()
+            try:
+                row = conn.execute(
+                    "SELECT context_start_seq FROM sessions WHERE session_id = ?",
+                    (session_id,),
+                ).fetchone()
+                return row[0] if row else 0
+            finally:
+                conn.close()
+
+    def get_latest_pair_seqs(self, session_id: str) -> Dict[str, Optional[int]]:
+        """Return the seq numbers of the latest visible user message and the
+        latest assistant message in a session.
+
+        A "visible" user message is one whose content is real user text
+        (not just a tool_result block), so tool-execution turns do not
+        shadow the actual user query.
+
+        Returns:
+            Dict with keys ``user_seq`` and ``bot_seq``; either may be None
+            when no matching message exists.
+        """
+        result: Dict[str, Optional[int]] = {"user_seq": None, "bot_seq": None}
+        with self._lock:
+            conn = self._connect()
+            try:
+                # Latest assistant message (cheap: single row by seq DESC).
+                row = conn.execute(
+                    "SELECT seq FROM messages "
+                    "WHERE session_id = ? AND role = 'assistant' "
+                    "ORDER BY seq DESC LIMIT 1",
+                    (session_id,),
+                ).fetchone()
+                if row:
+                    result["bot_seq"] = int(row[0])
+
+                # Latest visible user message: scan recent user rows and
+                # skip pure tool_result entries.
+                rows = conn.execute(
+                    "SELECT seq, content FROM messages "
+                    "WHERE session_id = ? AND role = 'user' "
+                    "ORDER BY seq DESC LIMIT 20",
+                    (session_id,),
+                ).fetchall()
+                for seq, content_raw in rows:
+                    try:
+                        content = json.loads(content_raw)
+                    except Exception:
+                        result["user_seq"] = int(seq)
+                        break
+                    if isinstance(content, list):
+                        has_text = any(
+                            isinstance(b, dict) and b.get("type") == "text"
+                            for b in content
+                        )
+                        has_tool_result = any(
+                            isinstance(b, dict) and b.get("type") == "tool_result"
+                            for b in content
+                        )
+                        if has_text and not has_tool_result:
+                            result["user_seq"] = int(seq)
+                            break
+                    else:
+                        result["user_seq"] = int(seq)
+                        break
+            finally:
+                conn.close()
+        return result
+
     def clear_session(self, session_id: str) -> None:
         """Delete all messages and the session record for a given session_id."""
         with self._lock:
@@ -407,9 +643,214 @@ class ConversationStore:
             finally:
                 conn.close()
 
+    def delete_message_pair(self, session_id: str, user_seq: int, delete_user: bool = True, cascade: bool = False) -> int:
+        """Delete a user message and/or its corresponding assistant reply.
+
+        The assistant reply is identified as all messages between user_seq
+        and the next visible user message (or end of session).
+
+        Args:
+            session_id: Session identifier.
+            user_seq: The seq number of the user message.
+            delete_user: If True (default), delete the user message too.
+                        If False, only delete assistant reply (for regenerate scenarios).
+            cascade: If True, also delete all subsequent turns after this one.
+                    Used by edit-message which removes this turn and everything after.
+
+        Returns:
+            Number of message rows deleted.
+        """
+        with self._lock:
+            conn = self._connect()
+            try:
+                with conn:
+                    # Verify this is a user message
+                    row = conn.execute(
+                        "SELECT role FROM messages WHERE session_id = ? AND seq = ?",
+                        (session_id, user_seq),
+                    ).fetchone()
+                    if not row or row[0] != "user":
+                        return 0
+
+                    if cascade:
+                        # Delete from this message to end of session
+                        start_seq = user_seq if delete_user else user_seq + 1
+                        end_seq_row = conn.execute(
+                            "SELECT MAX(seq) FROM messages WHERE session_id = ?",
+                            (session_id,),
+                        ).fetchone()
+                        end_seq = (end_seq_row[0] or user_seq) + 1
+                    else:
+                        # Find the next visible user message seq (exclude tool_result)
+                        # Use batched query to avoid loading too many rows at once
+                        next_user_seq = None
+                        batch_size = 100
+                        offset = 0
+                        while True:
+                            batch = conn.execute(
+                                """
+                                SELECT seq, content FROM messages
+                                WHERE session_id = ? AND seq > ? AND role = 'user'
+                                ORDER BY seq ASC
+                                LIMIT ? OFFSET ?
+                                """,
+                                (session_id, user_seq, batch_size, offset),
+                            ).fetchall()
+                            if not batch:
+                                break
+                            for seq, content in batch:
+                                try:
+                                    content_obj = json.loads(content)
+                                except Exception:
+                                    content_obj = content
+                                if _is_visible_user_message(content_obj):
+                                    next_user_seq = seq
+                                    break
+                            if next_user_seq is not None:
+                                break
+                            offset += batch_size
+
+                        # Determine the end boundary for deletion
+                        if next_user_seq is not None:
+                            end_seq = next_user_seq
+                        else:
+                            end_seq_row = conn.execute(
+                                "SELECT MAX(seq) FROM messages WHERE session_id = ?",
+                                (session_id,),
+                            ).fetchone()
+                            end_seq = (end_seq_row[0] or user_seq) + 1
+
+                        # Determine the start boundary for deletion
+                        start_seq = user_seq if delete_user else user_seq + 1
+
+                    # Delete messages from start_seq to end_seq (exclusive)
+                    cur = conn.execute(
+                        "DELETE FROM messages WHERE session_id = ? AND seq >= ? AND seq < ?",
+                        (session_id, start_seq, end_seq),
+                    )
+                    deleted = cur.rowcount
+
+                    # Update session msg_count
+                    conn.execute(
+                        """
+                        UPDATE sessions
+                        SET msg_count = (
+                            SELECT COUNT(*) FROM messages WHERE session_id = ?
+                        )
+                        WHERE session_id = ?
+                        """,
+                        (session_id, session_id),
+                    )
+
+                    return deleted
+            finally:
+                conn.close()
+
+    def prune_scheduled_messages(
+        self,
+        session_id: str,
+        keep_last_n: int,
+        markers: Optional[List[str]] = None,
+    ) -> int:
+        """
+        Keep at most ``keep_last_n`` scheduler-injected user/assistant pairs in
+        the session, deleting the older ones.
+
+        A scheduler-injected pair is identified by a user message whose first
+        text block starts with one of ``markers``; the immediately following
+        assistant message (next seq) is treated as its paired output.
+
+        Only scheduler-tagged messages are touched; regular user turns are
+        never deleted. Safe to call repeatedly; no-op if nothing to prune.
+
+        Args:
+            session_id: Session to prune.
+            keep_last_n: Maximum scheduler pairs to retain (must be >= 0).
+            markers: Text prefixes that identify scheduler user messages.
+                Defaults to ``["[SCHEDULED]", "Scheduled task"]`` so that
+                pairs written by older versions are also recognised.
+
+        Returns:
+            Number of message rows deleted.
+        """
+        if keep_last_n < 0:
+            keep_last_n = 0
+        if markers is None:
+            markers = ["[SCHEDULED]", "Scheduled task"]
+
+        def _matches_marker(raw_content: str) -> bool:
+            try:
+                parsed = json.loads(raw_content)
+            except Exception:
+                parsed = raw_content
+            text = _extract_display_text(parsed) if not isinstance(parsed, str) else parsed
+            if not text:
+                return False
+            return any(text.startswith(m) for m in markers)
+
+        with self._lock:
+            conn = self._connect()
+            try:
+                rows = conn.execute(
+                    """
+                    SELECT seq, role, content
+                    FROM messages
+                    WHERE session_id = ?
+                    ORDER BY seq ASC
+                    """,
+                    (session_id,),
+                ).fetchall()
+
+                # Find scheduler pairs: each is (user_seq, assistant_seq?)
+                pairs: List[tuple] = []  # list of (user_seq, assistant_seq_or_None)
+                for idx, (seq, role, raw_content) in enumerate(rows):
+                    if role != "user" or not _matches_marker(raw_content):
+                        continue
+                    assistant_seq = None
+                    # Pair with the very next message if it's an assistant turn.
+                    if idx + 1 < len(rows):
+                        next_seq, next_role, _ = rows[idx + 1]
+                        if next_role == "assistant":
+                            assistant_seq = next_seq
+                    pairs.append((seq, assistant_seq))
+
+                if len(pairs) <= keep_last_n:
+                    return 0
+
+                to_delete_pairs = pairs[: len(pairs) - keep_last_n]
+                seqs_to_delete: List[int] = []
+                for user_seq, assistant_seq in to_delete_pairs:
+                    seqs_to_delete.append(user_seq)
+                    if assistant_seq is not None:
+                        seqs_to_delete.append(assistant_seq)
+
+                if not seqs_to_delete:
+                    return 0
+
+                placeholders = ",".join("?" * len(seqs_to_delete))
+                with conn:
+                    conn.execute(
+                        f"DELETE FROM messages WHERE session_id = ? AND seq IN ({placeholders})",
+                        (session_id, *seqs_to_delete),
+                    )
+                    conn.execute(
+                        """
+                        UPDATE sessions
+                        SET msg_count = (
+                            SELECT COUNT(*) FROM messages WHERE session_id = ?
+                        )
+                        WHERE session_id = ?
+                        """,
+                        (session_id, session_id),
+                    )
+                return len(seqs_to_delete)
+            finally:
+                conn.close()
+
     def cleanup_old_sessions(self, max_age_days: Optional[int] = None) -> int:
         """
         Delete sessions that have not been active within max_age_days.
+        Web channel sessions are excluded — they are meant to be permanent.
 
         Args:
             max_age_days: Override the default retention period.
@@ -433,7 +874,8 @@ class ConversationStore:
             try:
                 with conn:
                     stale = conn.execute(
-                        "SELECT session_id FROM sessions WHERE last_active < ?",
+                        "SELECT session_id FROM sessions "
+                        "WHERE last_active < ? AND channel_type != 'web'",
                         (cutoff,),
                     ).fetchall()
                     for (sid,) in stale:
@@ -451,6 +893,55 @@ class ConversationStore:
             logger.info(f"[ConversationStore] Pruned {deleted} expired sessions")
         return deleted
 
+    def attach_extras_to_last_assistant(
+        self,
+        session_id: str,
+        extras: Dict[str, Any],
+    ) -> Optional[int]:
+        """
+        Merge ``extras`` into the latest assistant message of a session.
+
+        Used by post-processing (e.g. TTS) that needs to annotate an already
+        persisted bot reply with attachments such as audio URLs.
+
+        Returns the message seq that was updated, or ``None`` if no assistant
+        message exists or the update could not be applied.
+        """
+        if not extras:
+            return None
+        with self._lock:
+            conn = self._connect()
+            try:
+                row = conn.execute(
+                    """
+                    SELECT seq, extras FROM messages
+                    WHERE session_id = ? AND role = 'assistant'
+                    ORDER BY seq DESC LIMIT 1
+                    """,
+                    (session_id,),
+                ).fetchone()
+                if not row:
+                    return None
+                seq, raw = row
+                try:
+                    cur = json.loads(raw) if raw else {}
+                    if not isinstance(cur, dict):
+                        cur = {}
+                except Exception:
+                    cur = {}
+                cur.update(extras)
+                conn.execute(
+                    "UPDATE messages SET extras = ? WHERE session_id = ? AND seq = ?",
+                    (json.dumps(cur, ensure_ascii=False), session_id, seq),
+                )
+                conn.commit()
+                return seq
+            except Exception as e:
+                logger.warning(f"[ConversationStore] attach_extras failed: {e}")
+                return None
+            finally:
+                conn.close()
+
     def load_history_page(
         self,
         session_id: str,
@@ -492,19 +983,75 @@ class ConversationStore:
         with self._lock:
             conn = self._connect()
             try:
-                rows = conn.execute(
+                ctx_row = conn.execute(
-                    """
+                    "SELECT context_start_seq FROM sessions WHERE session_id = ?",
-                    SELECT role, content, created_at
-                    FROM messages
-                    WHERE session_id = ?
-                    ORDER BY seq ASC
-                    """,
                     (session_id,),
-                ).fetchall()
+                ).fetchone()
+                ctx_start = ctx_row[0] if ctx_row else 0
+
+                # extras column is added by migration; tolerate older DBs that
+                # might miss it by falling back to a NULL literal.
+                try:
+                    rows = conn.execute(
+                        """
+                        SELECT seq, role, content, created_at, extras
+                        FROM messages
+                        WHERE session_id = ?
+                        ORDER BY seq ASC
+                        """,
+                        (session_id,),
+                    ).fetchall()
+                except sqlite3.OperationalError:
+                    rows = [
+                        (seq, role, content, created_at, "")
+                        for (seq, role, content, created_at) in conn.execute(
+                            """
+                            SELECT seq, role, content, created_at
+                            FROM messages
+                            WHERE session_id = ?
+                            ORDER BY seq ASC
+                            """,
+                            (session_id,),
+                        ).fetchall()
+                    ]
             finally:
                 conn.close()
 
-        visible = _group_into_display_turns(rows)
+        # Honour the current enable_thinking switch when building display turns
+        # so that toggling it off hides previously-saved thinking blocks too.
+        try:
+            from config import conf
+            include_thinking = bool(conf().get("enable_thinking", False))
+        except Exception:
+            include_thinking = False
+
+        # Strip seq for display grouping, but record max seq per visible user group
+        plain_rows = [
+            (role, content, created_at, extras_raw)
+            for _seq, role, content, created_at, extras_raw in rows
+        ]
+        visible = _group_into_display_turns(plain_rows, include_thinking=include_thinking)
+
+        # Build a mapping: find the seq of each visible user message to annotate context boundary.
+        # Walk through rows to find visible user message seqs in order.
+        visible_user_seqs: List[int] = []
+        for seq, role, raw_content, _ts, _extras in rows:
+            if role != "user":
+                continue
+            try:
+                content = json.loads(raw_content)
+            except Exception:
+                content = raw_content
+            if _is_visible_user_message(content):
+                visible_user_seqs.append(seq)
+
+        # Each pair of display turns (user+assistant) corresponds to a visible user seq.
+        # Mark which turns are before the context boundary.
+        user_turn_idx = 0
+        for turn in visible:
+            if turn["role"] == "user" and user_turn_idx < len(visible_user_seqs):
+                turn["_seq"] = visible_user_seqs[user_turn_idx]
+                user_turn_idx += 1
 
         total = len(visible)
         offset = (page - 1) * page_size
@@ -513,12 +1060,98 @@ class ConversationStore:
 
         return {
             "messages": page_items,
+            "context_start_seq": ctx_start,
             "total": total,
             "page": page,
             "page_size": page_size,
             "has_more": offset + page_size < total,
         }
 
+    def list_sessions(
+        self,
+        channel_type: Optional[str] = None,
+        page: int = 1,
+        page_size: int = 50,
+    ) -> Dict[str, Any]:
+        """
+        List sessions ordered by last_active DESC, with optional channel_type filter.
+
+        Returns:
+            {
+                "sessions": [{session_id, title, created_at, last_active, msg_count}, ...],
+                "total": int,
+                "page": int,
+                "page_size": int,
+                "has_more": bool,
+            }
+        """
+        page = max(1, page)
+        with self._lock:
+            conn = self._connect()
+            try:
+                if channel_type:
+                    total = conn.execute(
+                        "SELECT COUNT(*) FROM sessions WHERE channel_type = ?",
+                        (channel_type,),
+                    ).fetchone()[0]
+                    rows = conn.execute(
+                        """
+                        SELECT session_id, title, created_at, last_active, msg_count
+                        FROM sessions
+                        WHERE channel_type = ?
+                        ORDER BY last_active DESC
+                        LIMIT ? OFFSET ?
+                        """,
+                        (channel_type, page_size, (page - 1) * page_size),
+                    ).fetchall()
+                else:
+                    total = conn.execute(
+                        "SELECT COUNT(*) FROM sessions",
+                    ).fetchone()[0]
+                    rows = conn.execute(
+                        """
+                        SELECT session_id, title, created_at, last_active, msg_count
+                        FROM sessions
+                        ORDER BY last_active DESC
+                        LIMIT ? OFFSET ?
+                        """,
+                        (page_size, (page - 1) * page_size),
+                    ).fetchall()
+            finally:
+                conn.close()
+
+        sessions = [
+            {
+                "session_id": r[0],
+                "title": r[1],
+                "created_at": r[2],
+                "last_active": r[3],
+                "msg_count": r[4],
+            }
+            for r in rows
+        ]
+        return {
+            "sessions": sessions,
+            "total": total,
+            "page": page,
+            "page_size": page_size,
+            "has_more": (page - 1) * page_size + page_size < total,
+        }
+
+    def rename_session(self, session_id: str, title: str) -> bool:
+        """Update the title of a session. Returns True if the session existed."""
+        with self._lock:
+            conn = self._connect()
+            try:
+                with conn:
+                    cur = conn.execute(
+                        "UPDATE sessions SET title = ? WHERE session_id = ?",
+                        (title, session_id),
+                    )
+                    return cur.rowcount > 0
+            finally:
+                conn.close()
+
     def get_stats(self) -> Dict[str, Any]:
         """Return basic stats keyed by channel_type, for monitoring."""
         with self._lock:
@@ -573,6 +1206,32 @@ class ConversationStore:
                 logger.info("[ConversationStore] Migrated: added channel_type column")
             except Exception as e:
                 logger.warning(f"[ConversationStore] Migration failed: {e}")
+        if "title" not in cols:
+            try:
+                conn.execute(_MIGRATION_ADD_TITLE)
+                conn.commit()
+                logger.info("[ConversationStore] Migrated: added title column")
+            except Exception as e:
+                logger.warning(f"[ConversationStore] Migration (title) failed: {e}")
+        if "context_start_seq" not in cols:
+            try:
+                conn.execute(_MIGRATION_ADD_CONTEXT_START_SEQ)
+                conn.commit()
+                logger.info("[ConversationStore] Migrated: added context_start_seq column")
+            except Exception as e:
+                logger.warning(f"[ConversationStore] Migration (context_start_seq) failed: {e}")
+
+        msg_cols = {
+            row[1]
+            for row in conn.execute("PRAGMA table_info(messages)").fetchall()
+        }
+        if "extras" not in msg_cols:
+            try:
+                conn.execute(_MIGRATION_ADD_MSG_EXTRAS)
+                conn.commit()
+                logger.info("[ConversationStore] Migrated: added messages.extras column")
+            except Exception as e:
+                logger.warning(f"[ConversationStore] Migration (extras) failed: {e}")
 
     def _connect(self) -> sqlite3.Connection:
         conn = sqlite3.connect(str(self._db_path), timeout=10)
@@ -616,3 +1275,4 @@ def get_conversation_store() -> ConversationStore:
         _store_instance = ConversationStore(db_path)
         logger.debug(f"[ConversationStore] Using shared DB at: {db_path}")
         return _store_instance
+

agent/memory/embedding.py

@@ -1,161 +0,0 @@
-"""
-Embedding providers for memory
-
-Supports OpenAI and local embedding models
-"""
-
-import hashlib
-from abc import ABC, abstractmethod
-from typing import List, Optional
-
-
-class EmbeddingProvider(ABC):
-    """Base class for embedding providers"""
-
-    @abstractmethod
-    def embed(self, text: str) -> List[float]:
-        """Generate embedding for text"""
-        pass
-
-    @abstractmethod
-    def embed_batch(self, texts: List[str]) -> List[List[float]]:
-        """Generate embeddings for multiple texts"""
-        pass
-    
-    @property
-    @abstractmethod
-    def dimensions(self) -> int:
-        """Get embedding dimensions"""
-        pass
-
-
-class OpenAIEmbeddingProvider(EmbeddingProvider):
-    """OpenAI embedding provider using REST API"""
-    
-    def __init__(self, model: str = "text-embedding-3-small", api_key: Optional[str] = None, api_base: Optional[str] = None):
-        """
-        Initialize OpenAI embedding provider
-        
-        Args:
-            model: Model name (text-embedding-3-small or text-embedding-3-large)
-            api_key: OpenAI API key
-            api_base: Optional API base URL
-        """
-        self.model = model
-        self.api_key = api_key
-        self.api_base = api_base or "https://api.openai.com/v1"
-
-        # Validate API key
-        if not self.api_key or self.api_key in ["", "YOUR API KEY", "YOUR_API_KEY"]:
-            raise ValueError("OpenAI API key is not configured. Please set 'open_ai_api_key' in config.json")
-
-        # Set dimensions based on model
-        self._dimensions = 1536 if "small" in model else 3072
-
-    def _call_api(self, input_data):
-        """Call OpenAI embedding API using requests"""
-        import requests
-
-        url = f"{self.api_base}/embeddings"
-        headers = {
-            "Content-Type": "application/json",
-            "Authorization": f"Bearer {self.api_key}"
-        }
-        data = {
-            "input": input_data,
-            "model": self.model
-        }
-
-        try:
-            response = requests.post(url, headers=headers, json=data, timeout=5)
-            response.raise_for_status()
-            return response.json()
-        except requests.exceptions.ConnectionError as e:
-            raise ConnectionError(f"Failed to connect to OpenAI API at {url}. Please check your network connection and api_base configuration. Error: {str(e)}")
-        except requests.exceptions.Timeout as e:
-            raise TimeoutError(f"OpenAI API request timed out after 10s. Please check your network connection. Error: {str(e)}")
-        except requests.exceptions.HTTPError as e:
-            if e.response.status_code == 401:
-                raise ValueError(f"Invalid OpenAI API key. Please check your 'open_ai_api_key' in config.json")
-            elif e.response.status_code == 429:
-                raise ValueError(f"OpenAI API rate limit exceeded. Please try again later.")
-            else:
-                raise ValueError(f"OpenAI API request failed: {e.response.status_code} - {e.response.text}")
-
-    def embed(self, text: str) -> List[float]:
-        """Generate embedding for text"""
-        result = self._call_api(text)
-        return result["data"][0]["embedding"]
-
-    def embed_batch(self, texts: List[str]) -> List[List[float]]:
-        """Generate embeddings for multiple texts"""
-        if not texts:
-            return []
-
-        result = self._call_api(texts)
-        return [item["embedding"] for item in result["data"]]
-
-    @property
-    def dimensions(self) -> int:
-        return self._dimensions
-
-
-# LocalEmbeddingProvider removed - only use OpenAI embedding or keyword search
-
-
-class EmbeddingCache:
-    """Cache for embeddings to avoid recomputation"""
-
-    def __init__(self):
-        self.cache = {}
-
-    def get(self, text: str, provider: str, model: str) -> Optional[List[float]]:
-        """Get cached embedding"""
-        key = self._compute_key(text, provider, model)
-        return self.cache.get(key)
-    
-    def put(self, text: str, provider: str, model: str, embedding: List[float]):
-        """Cache embedding"""
-        key = self._compute_key(text, provider, model)
-        self.cache[key] = embedding
-    
-    @staticmethod
-    def _compute_key(text: str, provider: str, model: str) -> str:
-        """Compute cache key"""
-        content = f"{provider}:{model}:{text}"
-        return hashlib.md5(content.encode('utf-8')).hexdigest()
-    
-    def clear(self):
-        """Clear cache"""
-        self.cache.clear()
-
-
-def create_embedding_provider(
-    provider: str = "openai",
-    model: Optional[str] = None,
-    api_key: Optional[str] = None,
-    api_base: Optional[str] = None
-) -> EmbeddingProvider:
-    """
-    Factory function to create embedding provider
-    
-    Only supports OpenAI embedding via REST API.
-    If initialization fails, caller should fall back to keyword-only search.
-    
-    Args:
-        provider: Provider name (only "openai" is supported)
-        model: Model name (default: text-embedding-3-small)
-        api_key: OpenAI API key (required)
-        api_base: API base URL (default: https://api.openai.com/v1)
-        
-    Returns:
-        EmbeddingProvider instance
-        
-    Raises:
-        ValueError: If provider is not "openai" or api_key is missing
-    """
-    if provider != "openai":
-        raise ValueError(f"Only 'openai' provider is supported, got: {provider}")
-
-    model = model or "text-embedding-3-small"
-    return OpenAIEmbeddingProvider(model=model, api_key=api_key, api_base=api_base)

agent/memory/embedding/__init__.py

@@ -0,0 +1,43 @@
+"""
+Embedding subsystem for memory.
+
+Public API:
+  create_embedding_provider, EmbeddingProvider, OpenAIEmbeddingProvider,
+  EMBEDDING_VENDORS, EmbeddingCache
+  RebuildResult, clear_index, rebuild_in_process
+  detect_index_dim, cleanup_legacy_state_file
+"""
+
+from agent.memory.embedding.provider import (
+    EMBEDDING_VENDORS,
+    DoubaoEmbeddingProvider,
+    EmbeddingCache,
+    EmbeddingProvider,
+    OpenAIEmbeddingProvider,
+    create_embedding_provider,
+)
+from agent.memory.embedding.factory import create_default_embedding_provider
+from agent.memory.embedding.rebuild import (
+    RebuildResult,
+    clear_index,
+    rebuild_in_process,
+)
+from agent.memory.embedding.state import (
+    cleanup_legacy_state_file,
+    detect_index_dim,
+)
+
+__all__ = [
+    "EMBEDDING_VENDORS",
+    "DoubaoEmbeddingProvider",
+    "EmbeddingCache",
+    "EmbeddingProvider",
+    "OpenAIEmbeddingProvider",
+    "create_embedding_provider",
+    "create_default_embedding_provider",
+    "RebuildResult",
+    "clear_index",
+    "rebuild_in_process",
+    "cleanup_legacy_state_file",
+    "detect_index_dim",
+]

agent/memory/embedding/factory.py

@@ -0,0 +1,209 @@
+"""
+Shared embedding provider factory.
+
+Resolves the embedding provider purely from config.json, so every caller
+(agent initialization, knowledge base sync, index rebuild, ...) selects the
+same provider instead of silently degrading to keyword-only search.
+
+Two paths:
+  A. Default (no `embedding_provider` in config.json):
+     Auto-init OpenAI -> LinkAI fallback.
+  B. Explicit (`embedding_provider` is set):
+     Initialize the requested vendor with unified dim (default per vendor).
+"""
+
+import os
+from typing import Optional
+
+from common.log import logger
+
+# Track whether the embedding model log has been printed in this process,
+# so we avoid spamming it once per session/caller.
+_embedding_logged: bool = False
+
+
+def create_default_embedding_provider():
+    """Build the embedding provider from config, or None for keyword-only mode."""
+    from config import conf
+
+    explicit_provider = (conf().get("embedding_provider") or "").strip().lower()
+    if not explicit_provider:
+        return _init_legacy_provider()
+    return _init_explicit_provider(explicit_provider)
+
+
+def _init_legacy_provider():
+    """Legacy auto-init path: OpenAI -> LinkAI."""
+    from agent.memory.embedding.provider import create_embedding_provider
+    from config import conf
+
+    embedding_provider = None
+    embedding_model = None
+
+    openai_api_key = conf().get("open_ai_api_key", "")
+    openai_api_base = conf().get("open_ai_api_base", "")
+    if openai_api_key and openai_api_key not in ["", "YOUR API KEY", "YOUR_API_KEY"]:
+        try:
+            model = "text-embedding-3-small"
+            embedding_provider = create_embedding_provider(
+                provider="openai",
+                model=model,
+                api_key=openai_api_key,
+                api_base=openai_api_base or "https://api.openai.com/v1",
+            )
+            embedding_model = f"openai/{model}"
+        except Exception as e:
+            logger.warning(f"[EmbeddingFactory] OpenAI embedding failed: {e}")
+
+    if embedding_provider is None:
+        linkai_api_key = conf().get("linkai_api_key", "") or os.environ.get("LINKAI_API_KEY", "")
+        linkai_api_base = conf().get("linkai_api_base", "https://api.link-ai.tech")
+        if linkai_api_key and linkai_api_key not in ["", "YOUR API KEY", "YOUR_API_KEY"]:
+            try:
+                model = "text-embedding-3-small"
+                embedding_provider = create_embedding_provider(
+                    provider="linkai",
+                    model=model,
+                    api_key=linkai_api_key,
+                    api_base=f"{linkai_api_base}/v1",
+                )
+                embedding_model = f"linkai/{model}"
+            except Exception as e:
+                logger.warning(f"[EmbeddingFactory] LinkAI embedding failed: {e}")
+
+    if embedding_provider is not None and embedding_model:
+        _log_provider_once(f"{embedding_model} (dim={embedding_provider.dimensions})")
+
+    return embedding_provider
+
+
+def _init_explicit_provider(provider_key: str):
+    """Explicit-provider path: build the configured vendor."""
+    from agent.memory.embedding.provider import EMBEDDING_VENDORS, create_embedding_provider
+    from config import conf
+
+    # Custom providers ("custom:<id>") resolve credentials from custom_providers.
+    resolved_provider_key = provider_key
+    if provider_key.startswith("custom:"):
+        resolved_provider_key = "custom"
+
+    meta = EMBEDDING_VENDORS.get(resolved_provider_key)
+    if meta is None:
+        logger.error(
+            f"[EmbeddingFactory] Unknown embedding_provider '{provider_key}'. "
+            f"Supported: {sorted(EMBEDDING_VENDORS.keys())}. "
+            f"Memory will run in keyword-only mode."
+        )
+        return None
+
+    api_key = _resolve_api_key(provider_key)
+    api_base = _resolve_api_base(provider_key, meta["default_base_url"])
+
+    if not api_key:
+        logger.error(
+            f"[EmbeddingFactory] embedding_provider='{provider_key}' is set but its "
+            f"API key is missing. Memory will run in keyword-only mode."
+        )
+        return None
+
+    model = (conf().get("embedding_model") or "").strip()
+    # Custom providers without a model fall back to the provider's default.
+    if not model and resolved_provider_key == "custom":
+        from models.custom_provider import parse_custom_bot_type, get_custom_providers, _find_provider_by_id
+        _, custom_id = parse_custom_bot_type(provider_key)
+        if custom_id:
+            entry = _find_provider_by_id(get_custom_providers(), custom_id)
+            if entry and entry.get("model"):
+                model = entry["model"]
+    if not model and resolved_provider_key != "custom":
+        model = meta["default_model"]
+
+    try:
+        cfg_dim = int(conf().get("embedding_dimensions") or 0)
+    except (TypeError, ValueError):
+        cfg_dim = 0
+    dim = cfg_dim if cfg_dim > 0 else meta["default_dimensions"]
+
+    try:
+        provider = create_embedding_provider(
+            provider=resolved_provider_key,
+            model=model,
+            api_key=api_key,
+            api_base=api_base,
+            dimensions=dim,
+        )
+    except Exception as e:
+        logger.error(
+            f"[EmbeddingFactory] Failed to init embedding provider "
+            f"'{provider_key}/{model}': {e}"
+        )
+        return None
+
+    _log_provider_once(f"{provider_key}/{model} (dim={provider.dimensions})")
+    return provider
+
+
+def _resolve_api_key(provider_key: str) -> str:
+    """Pick the API key for an explicit embedding provider from config."""
+    from config import conf
+
+    if provider_key.startswith("custom:"):
+        from models.custom_provider import parse_custom_bot_type, get_custom_providers, _find_provider_by_id
+        _, custom_id = parse_custom_bot_type(provider_key)
+        if custom_id:
+            entry = _find_provider_by_id(get_custom_providers(), custom_id)
+            if entry:
+                return entry.get("api_key", "")
+        return ""
+
+    key_map = {
+        "openai":    "open_ai_api_key",
+        "linkai":    "linkai_api_key",
+        "dashscope": "dashscope_api_key",
+        "doubao":    "ark_api_key",
+        "zhipu":     "zhipu_ai_api_key",
+    }
+    field = key_map.get(provider_key)
+    if not field:
+        return ""
+    value = conf().get(field, "") or ""
+    if value in ["", "YOUR API KEY", "YOUR_API_KEY"]:
+        return ""
+    return value
+
+
+def _resolve_api_base(provider_key: str, default_base: str) -> str:
+    """Pick the API base for an explicit embedding provider from config."""
+    from config import conf
+
+    if provider_key.startswith("custom:"):
+        from models.custom_provider import parse_custom_bot_type, get_custom_providers, _find_provider_by_id
+        _, custom_id = parse_custom_bot_type(provider_key)
+        if custom_id:
+            entry = _find_provider_by_id(get_custom_providers(), custom_id)
+            if entry and entry.get("api_base"):
+                return entry["api_base"]
+        return default_base
+
+    base_map = {
+        "openai":    "open_ai_api_base",
+        "linkai":    "linkai_api_base",
+        "doubao":    "ark_base_url",
+        "zhipu":     "zhipu_ai_api_base",
+    }
+    field = base_map.get(provider_key)
+    if not field:
+        return default_base
+    value = (conf().get(field) or "").strip()
+    if not value:
+        return default_base
+    if provider_key == "linkai" and not value.rstrip("/").endswith("/v1"):
+        return f"{value.rstrip('/')}/v1"
+    return value
+
+
+def _log_provider_once(detail: str):
+    global _embedding_logged
+    if not _embedding_logged:
+        logger.info(f"[EmbeddingFactory] Embedding model in use: {detail}")
+        _embedding_logged = True

agent/memory/embedding/provider.py

@@ -0,0 +1,515 @@
+"""
+Embedding providers for memory
+
+Supports multiple OpenAI-compatible embedding vendors:
+  - openai     (text-embedding-3-small / large)
+  - linkai     (OpenAI-compatible passthrough)
+  - dashscope  (Aliyun Tongyi text-embedding-v4)
+  - doubao     (ByteDance Doubao Seed1.5 / large-text on Volcengine Ark)
+  - zhipu      (ZhipuAI embedding-3)
+  - custom     (any OpenAI-compatible endpoint)
+
+Vendor keys here intentionally match the project's bot_type constants in
+common.const (OPENAI, LINKAI, QWEN_DASHSCOPE, DOUBAO, ZHIPU_AI).
+
+Custom providers (bot_type "custom" or "custom:<id>") reuse the same
+OpenAI-compatible REST client with user-supplied api_key / api_base.
+
+All providers share a single OpenAI-compatible REST client. Vendor-specific
+behaviors (truncation, query instruction prefix) are configured via metadata.
+"""
+
+import hashlib
+import math
+from abc import ABC, abstractmethod
+from typing import List, Optional
+
+# HTTP read timeout for a single embeddings request (seconds). A batch of
+# 64+ chunks can take 30-50s end-to-end from China-side networks, so 30s is
+# routinely too tight; 90s gives meaningful headroom without letting bad
+# endpoints hang forever.
+EMBEDDING_HTTP_TIMEOUT = 90
+
+
+class EmbeddingProvider(ABC):
+    """Base class for embedding providers"""
+
+    @abstractmethod
+    def embed(self, text: str) -> List[float]:
+        """Generate embedding for a single text (treated as a query by default)"""
+        pass
+
+    @abstractmethod
+    def embed_batch(self, texts: List[str]) -> List[List[float]]:
+        """Generate embeddings for multiple texts (treated as documents)"""
+        pass
+
+    def embed_query(self, text: str) -> List[float]:
+        """Generate embedding for a query string (may apply vendor instruction prefix)"""
+        return self.embed(text)
+
+    @property
+    @abstractmethod
+    def dimensions(self) -> int:
+        """Effective embedding dimensions"""
+        pass
+
+
+# ---------------------------------------------------------------------------
+# Vendor metadata table
+# ---------------------------------------------------------------------------
+#
+# Each entry describes how to reach a vendor's embedding endpoint. Most
+# vendors expose an OpenAI-compatible /embeddings API; the few that don't
+# (currently: doubao) set `provider_class` to pick a dedicated adapter.
+# Fields:
+#   provider_class          : optional adapter key ("doubao"); defaults to OpenAI-compat
+#   default_base_url        : default API base when not overridden by user
+#   default_model           : default embedding model name
+#   default_dimensions      : recommended unified dim when explicit path is enabled
+#   supports_dim_param      : whether the API accepts a `dimensions` request param
+#   needs_client_truncate   : whether to slice + L2-normalize on the client side
+#   needs_client_normalize  : whether to L2-normalize on the client (always safe)
+#   query_instruction       : optional prefix for asymmetric retrieval (Doubao Seed)
+#   max_batch_size          : max texts per /embeddings request; embed_batch
+#                             auto-paginates above this. Conservative defaults.
+#
+EMBEDDING_VENDORS = {
+    "openai": {
+        "default_base_url": "https://api.openai.com/v1",
+        "default_model": "text-embedding-3-small",
+        # Match the legacy default so users adding `embedding_provider: openai`
+        # to an existing index don't need to rebuild. Override via
+        # embedding_dimensions if you want 1024 / 1536 / 3072.
+        "default_dimensions": 1536,
+        "supports_dim_param": True,
+        "needs_client_truncate": False,
+        "needs_client_normalize": False,
+        "query_instruction": "",
+        # OpenAI permits up to 2048 items per request, but a single call
+        # carrying hundreds of long chunks routinely exceeds the 30s read
+        # timeout from China-side networks. 64 keeps each call well under
+        # both the token-per-request budget and a reasonable wall clock.
+        "max_batch_size": 64,
+    },
+    "linkai": {
+        "default_base_url": "https://api.link-ai.tech/v1",
+        "default_model": "text-embedding-3-small",
+        "default_dimensions": 1536,
+        "supports_dim_param": True,
+        "needs_client_truncate": False,
+        "needs_client_normalize": False,
+        "query_instruction": "",
+        "max_batch_size": 64,
+    },
+    "dashscope": {
+        "default_base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1",
+        "default_model": "text-embedding-v4",
+        "default_dimensions": 1024,
+        "supports_dim_param": True,
+        "needs_client_truncate": False,
+        "needs_client_normalize": False,
+        "query_instruction": "",
+        "max_batch_size": 10,  # DashScope hard cap (text-embedding-v4)
+    },
+    "doubao": {
+        # Doubao no longer offers an OpenAI-compatible /v1/embeddings endpoint.
+        # Current models are unified under /api/v3/embeddings/multimodal
+        # which uses a structured `input` payload — see DoubaoEmbeddingProvider.
+        "provider_class": "doubao",
+        "default_base_url": "https://ark.cn-beijing.volces.com/api/v3",
+        "default_model": "doubao-embedding-vision-251215",
+        # Native options: 1024 or 2048. We default to 1024 to align with the
+        # other Chinese vendors (dashscope/zhipu) and keep storage footprint
+        # consistent across providers; users can still override via
+        # `embedding_dimensions: 2048` in config.
+        "default_dimensions": 1024,
+        "supports_dim_param": True,
+        "needs_client_truncate": False,
+        "needs_client_normalize": False,
+        "query_instruction": "",
+        # Multimodal endpoint produces ONE embedding per call (input list is
+        # a single document's parts, not a batch). embed_batch loops.
+        "max_batch_size": 1,
+    },
+    "zhipu": {
+        "default_base_url": "https://open.bigmodel.cn/api/paas/v4",
+        "default_model": "embedding-3",
+        "default_dimensions": 1024,
+        "supports_dim_param": True,
+        "needs_client_truncate": False,
+        "needs_client_normalize": False,
+        "query_instruction": "",
+        "max_batch_size": 64,
+    },
+    # Custom provider — any OpenAI-compatible /embeddings endpoint. The
+    # user must supply api_key + api_base + model via the web console
+    # (stored in custom_providers list or legacy custom_api_key / custom_api_base).
+    # Dimensions defaults to 1024 but can be overridden via config's
+    # embedding_dimensions. No dim-param support assumption — safest
+    # default for unknown endpoints.
+    "custom": {
+        "default_base_url": "",
+        "default_model": "",
+        "default_dimensions": 1024,
+        "supports_dim_param": False,
+        "needs_client_truncate": False,
+        "needs_client_normalize": True,
+        "query_instruction": "",
+        "max_batch_size": 64,
+    },
+}
+
+
+def _l2_normalize(vec: List[float]) -> List[float]:
+    """Normalize a vector to unit length (L2 norm). Returns input on zero vector."""
+    norm = math.sqrt(sum(v * v for v in vec))
+    if norm == 0:
+        return vec
+    return [v / norm for v in vec]
+
+
+class OpenAIEmbeddingProvider(EmbeddingProvider):
+    """
+    OpenAI-compatible embedding provider.
+
+    Used for openai/linkai/dashscope/ark/zhipu by configuring the metadata
+    fields. The legacy two-arg constructor (model, api_key, api_base) keeps
+    working, so the original OpenAI/LinkAI fallback code path is unchanged.
+    """
+
+    def __init__(
+        self,
+        model: str = "text-embedding-3-small",
+        api_key: Optional[str] = None,
+        api_base: Optional[str] = None,
+        extra_headers: Optional[dict] = None,
+        dimensions: Optional[int] = None,
+        supports_dim_param: bool = True,
+        needs_client_truncate: bool = False,
+        needs_client_normalize: bool = False,
+        query_instruction: str = "",
+        max_batch_size: int = 256,
+    ):
+        """
+        Args:
+            model: Model name (e.g. text-embedding-3-small, text-embedding-v4, embedding-3)
+            api_key: API key (required)
+            api_base: API base URL (defaults to OpenAI)
+            extra_headers: Optional extra HTTP headers
+            dimensions: Target output dimension. Required when supports_dim_param
+                is False and needs_client_truncate is True (used to slice).
+            supports_dim_param: Whether the vendor accepts a `dimensions` body param
+            needs_client_truncate: Slice the returned vector to `dimensions`
+            needs_client_normalize: L2-normalize on the client after slicing
+            query_instruction: Optional prefix prepended to query texts only
+            max_batch_size: Max items per /embeddings request; embed_batch
+                auto-paginates above this.
+        """
+        self.model = model
+        self.api_key = api_key
+        self.api_base = api_base or "https://api.openai.com/v1"
+        self.extra_headers = extra_headers or {}
+        self.supports_dim_param = supports_dim_param
+        self.needs_client_truncate = needs_client_truncate
+        self.needs_client_normalize = needs_client_normalize
+        self.query_instruction = query_instruction or ""
+        self.max_batch_size = max(1, int(max_batch_size or 1))
+
+        if not self.api_key or self.api_key in ["", "YOUR API KEY", "YOUR_API_KEY"]:
+            raise ValueError("Embedding API key is not configured")
+
+        if dimensions is not None and dimensions > 0:
+            self._dimensions = dimensions
+        else:
+            # Legacy heuristic for OpenAI text-embedding-3-* family
+            self._dimensions = 1536 if "small" in model else 3072
+
+    def _call_api(self, input_data):
+        """Call OpenAI-compatible /embeddings endpoint"""
+        import requests
+
+        url = f"{self.api_base}/embeddings"
+        headers = {
+            "Content-Type": "application/json",
+            "Authorization": f"Bearer {self.api_key}",
+            **self.extra_headers,
+        }
+        data = {
+            "input": input_data,
+            "model": self.model,
+        }
+        if self.supports_dim_param and self._dimensions:
+            data["dimensions"] = self._dimensions
+
+        try:
+            response = requests.post(url, headers=headers, json=data, timeout=EMBEDDING_HTTP_TIMEOUT)
+            response.raise_for_status()
+            return response.json()
+        except requests.exceptions.ConnectionError as e:
+            raise ConnectionError(
+                f"Failed to connect to embedding API at {url}. "
+                f"Please check network and api_base. Error: {str(e)}"
+            )
+        except requests.exceptions.Timeout as e:
+            raise TimeoutError(f"Embedding API request timed out. Error: {str(e)}")
+        except requests.exceptions.HTTPError as e:
+            if e.response.status_code == 401:
+                raise ValueError("Invalid embedding API key")
+            elif e.response.status_code == 429:
+                raise ValueError("Embedding API rate limit exceeded")
+            else:
+                raise ValueError(
+                    f"Embedding API request failed: "
+                    f"{e.response.status_code} - {e.response.text}"
+                )
+
+    def _post_process(self, raw: List[float]) -> List[float]:
+        """Apply optional client-side truncation + normalization"""
+        vec = raw
+        if self.needs_client_truncate and self._dimensions and len(vec) > self._dimensions:
+            vec = vec[: self._dimensions]
+        if self.needs_client_normalize:
+            vec = _l2_normalize(vec)
+        return vec
+
+    def embed(self, text: str) -> List[float]:
+        """Generate embedding (treated as document by default)"""
+        result = self._call_api(text)
+        return self._post_process(result["data"][0]["embedding"])
+
+    def embed_query(self, text: str) -> List[float]:
+        """Generate embedding for a query (applies vendor instruction prefix if any)"""
+        if self.query_instruction:
+            text = f"{self.query_instruction}{text}"
+        return self.embed(text)
+
+    def embed_batch(self, texts: List[str]) -> List[List[float]]:
+        """Generate embeddings for multiple documents.
+
+        Automatically paginates by self.max_batch_size so callers can pass any
+        number of texts. Order of returned vectors matches the input order.
+        """
+        if not texts:
+            return []
+        out: List[List[float]] = []
+        step = self.max_batch_size
+        for i in range(0, len(texts), step):
+            chunk = texts[i:i + step]
+            result = self._call_api(chunk)
+            out.extend(self._post_process(item["embedding"]) for item in result["data"])
+        return out
+
+    @property
+    def dimensions(self) -> int:
+        return self._dimensions
+
+
+class DoubaoEmbeddingProvider(EmbeddingProvider):
+    """
+    Doubao (Volcengine Ark) multimodal embedding provider.
+
+    Doubao deprecated their OpenAI-compatible /v1/embeddings endpoint and
+    unified everything under /api/v3/embeddings/multimodal, which uses a
+    structured `input: [{type, text|image_url|video_url}, ...]` payload.
+
+    Notes:
+      * The endpoint produces ONE embedding per call (input list is multiple
+        modality parts of a single document, not a batch). embed_batch
+        therefore loops per-text — no native batch support.
+      * Native dimensions: 1024 or 2048 (default 1024 to align with other
+        Chinese vendors). No client-side truncation needed.
+      * Auth: Bearer ARK API key.
+    """
+
+    def __init__(
+        self,
+        model: str,
+        api_key: Optional[str] = None,
+        api_base: Optional[str] = None,
+        extra_headers: Optional[dict] = None,
+        dimensions: Optional[int] = None,
+    ):
+        self.model = model
+        self.api_key = api_key
+        self.api_base = api_base or "https://ark.cn-beijing.volces.com/api/v3"
+        self.extra_headers = extra_headers or {}
+        if not self.api_key or self.api_key in ["", "YOUR API KEY", "YOUR_API_KEY"]:
+            raise ValueError("Doubao embedding API key (ark_api_key) is not configured")
+
+        if dimensions in (1024, 2048):
+            self._dimensions = dimensions
+        elif dimensions is None:
+            self._dimensions = 1024
+        else:
+            raise ValueError(
+                f"Doubao embedding dimensions must be 1024 or 2048, got {dimensions}"
+            )
+
+    def _call_api(self, text: str) -> List[float]:
+        """One call → one embedding. multimodal endpoint takes a single
+        document represented as a list of typed parts; we send a single
+        text part."""
+        import requests
+
+        url = f"{self.api_base}/embeddings/multimodal"
+        headers = {
+            "Content-Type": "application/json",
+            "Authorization": f"Bearer {self.api_key}",
+            **self.extra_headers,
+        }
+        payload = {
+            "model": self.model,
+            "input": [{"type": "text", "text": text}],
+            "dimensions": self._dimensions,
+            "encoding_format": "float",
+        }
+
+        try:
+            response = requests.post(url, headers=headers, json=payload, timeout=EMBEDDING_HTTP_TIMEOUT)
+            response.raise_for_status()
+            body = response.json()
+        except requests.exceptions.ConnectionError as e:
+            raise ConnectionError(
+                f"Failed to connect to Doubao embedding API at {url}. "
+                f"Please check network and api_base. Error: {str(e)}"
+            )
+        except requests.exceptions.Timeout as e:
+            raise TimeoutError(f"Doubao embedding API request timed out. Error: {str(e)}")
+        except requests.exceptions.HTTPError as e:
+            if e.response.status_code == 401:
+                raise ValueError("Invalid Doubao (ark) embedding API key")
+            elif e.response.status_code == 429:
+                raise ValueError("Doubao embedding API rate limit exceeded")
+            else:
+                raise ValueError(
+                    f"Doubao embedding API request failed: "
+                    f"{e.response.status_code} - {e.response.text}"
+                )
+
+        # Response shape per docs: {"data": {"embedding": [...]}}
+        data = body.get("data")
+        if isinstance(data, dict) and "embedding" in data:
+            return data["embedding"]
+        # Some providers wrap as a list of one — be defensive
+        if isinstance(data, list) and data and "embedding" in data[0]:
+            return data[0]["embedding"]
+        raise ValueError(f"Unexpected Doubao embedding response shape: {body}")
+
+    def embed(self, text: str) -> List[float]:
+        return self._call_api(text)
+
+    def embed_batch(self, texts: List[str]) -> List[List[float]]:
+        # Endpoint produces one embedding per call; loop. Order preserved.
+        return [self._call_api(t) for t in texts]
+
+    @property
+    def dimensions(self) -> int:
+        return self._dimensions
+
+
+class EmbeddingCache:
+    """In-memory cache for embeddings to avoid recomputation"""
+
+    def __init__(self):
+        self.cache = {}
+
+    def get(self, text: str, provider: str, model: str) -> Optional[List[float]]:
+        key = self._compute_key(text, provider, model)
+        return self.cache.get(key)
+
+    def put(self, text: str, provider: str, model: str, embedding: List[float]):
+        key = self._compute_key(text, provider, model)
+        self.cache[key] = embedding
+
+    @staticmethod
+    def _compute_key(text: str, provider: str, model: str) -> str:
+        content = f"{provider}:{model}:{text}"
+        return hashlib.md5(content.encode("utf-8")).hexdigest()
+
+    def clear(self):
+        self.cache.clear()
+
+
+def create_embedding_provider(
+    provider: str = "openai",
+    model: Optional[str] = None,
+    api_key: Optional[str] = None,
+    api_base: Optional[str] = None,
+    extra_headers: Optional[dict] = None,
+    dimensions: Optional[int] = None,
+) -> EmbeddingProvider:
+    """
+    Factory function to create an embedding provider.
+
+    Backward compatible: when called with provider in {"openai", "linkai"}
+    and no `dimensions` arg, behaves exactly as before (1536-dim OpenAI).
+
+    New providers ("dashscope", "doubao", "zhipu") require explicit configuration
+    and use the unified 1024-dim defaults from EMBEDDING_VENDORS.
+
+    Args:
+        provider: Vendor key (one of EMBEDDING_VENDORS)
+        model: Model name (uses vendor default if None)
+        api_key: API key (required)
+        api_base: API base URL (uses vendor default if None)
+        extra_headers: Optional extra HTTP headers
+        dimensions: Target output dimension (uses vendor default if None)
+
+    Returns:
+        EmbeddingProvider instance
+    """
+    meta = EMBEDDING_VENDORS.get(provider)
+    if meta is None:
+        raise ValueError(
+            f"Unsupported embedding provider: {provider}. "
+            f"Supported: {sorted(EMBEDDING_VENDORS.keys())}"
+        )
+
+    # Doubao uses a non-OpenAI-compatible multimodal endpoint.
+    if meta.get("provider_class") == "doubao":
+        final_dim = dimensions if (dimensions and dimensions > 0) else meta["default_dimensions"]
+        return DoubaoEmbeddingProvider(
+            model=model or meta["default_model"],
+            api_key=api_key,
+            api_base=api_base or meta["default_base_url"],
+            extra_headers=extra_headers,
+            dimensions=final_dim,
+        )
+
+    # Legacy two-arg call for openai/linkai keeps 1536-dim default behavior
+    # so existing data isn't invalidated.
+    is_legacy_call = (
+        provider in ("openai", "linkai")
+        and dimensions is None
+    )
+    if is_legacy_call:
+        return OpenAIEmbeddingProvider(
+            model=model or "text-embedding-3-small",
+            api_key=api_key,
+            api_base=api_base,
+            extra_headers=extra_headers,
+        )
+
+    final_dim = dimensions if (dimensions and dimensions > 0) else meta["default_dimensions"]
+    resolved_model = model or meta["default_model"]
+    resolved_base = api_base or meta["default_base_url"]
+    # Custom providers require explicit api_base and model — they cannot
+    # fall back to OpenAI defaults like built-in vendors do.
+    if provider == "custom":
+        if not resolved_base:
+            raise ValueError("Custom embedding provider requires an api_base URL")
+        if not resolved_model:
+            raise ValueError("Custom embedding provider requires a model name")
+    return OpenAIEmbeddingProvider(
+        model=resolved_model,
+        api_key=api_key,
+        api_base=resolved_base,
+        extra_headers=extra_headers,
+        dimensions=final_dim,
+        supports_dim_param=meta["supports_dim_param"],
+        needs_client_truncate=meta["needs_client_truncate"],
+        needs_client_normalize=meta["needs_client_normalize"],
+        query_instruction=meta["query_instruction"],
+        max_batch_size=meta.get("max_batch_size", 256),
+    )

agent/memory/embedding/rebuild.py

@@ -0,0 +1,190 @@
+"""
+Rebuild memory vector index.
+
+Recommended entry point (in-chat, while agent is running):
+    /memory rebuild-index
+
+Backward-compatible CLI entry (must run from project root):
+    python -m agent.memory.rebuild_index
+
+What it does:
+  1. Probes the embedding endpoint with a tiny call to fail fast on
+     bad provider/model/key — before touching the index.
+  2. Clears the SQLite chunks/files tables (workspace markdown stays intact).
+  3. Runs a fresh sync, regenerating embeddings with the currently configured
+     provider/model/dimensions.
+
+This is the only safe way to switch embedding_provider after the existing
+index has been populated by a different-dim model.
+"""
+
+from __future__ import annotations
+import asyncio
+import sys
+from dataclasses import dataclass
+from typing import Optional
+
+from common.log import logger
+from common.utils import expand_path
+
+
+@dataclass
+class RebuildResult:
+    """Outcome of a rebuild_in_process() call"""
+    ok: bool
+    removed: int = 0
+    chunks: int = 0
+    files: int = 0
+    error: Optional[str] = None
+
+
+def clear_index(db_path, storage=None) -> int:
+    """Wipe chunks/files, reset FTS5, and clean up any legacy state file.
+
+    Args:
+        db_path: Path of the index DB (also used to locate the legacy state
+            file for migration cleanup, and — when *storage* is None — to
+            open a fresh connection).
+        storage: Optional pre-opened MemoryStorage. When provided we reuse it
+            so the live connection's triggers stay in sync — opening a second
+            connection would leave the original one's triggers pointing at a
+            DROP'd chunks_fts table.
+
+    We reset (DROP+recreate) chunks_fts because its shadow tables can become
+    inconsistent across rebuild cycles, causing bm25() / ORDER BY rank to
+    raise "database disk image is malformed" even when raw MATCH still works.
+
+    Returns number of chunks removed.
+    """
+    from agent.memory.embedding.state import cleanup_legacy_state_file
+    from agent.memory.storage import MemoryStorage
+
+    owns_storage = storage is None
+    if owns_storage:
+        storage = MemoryStorage(db_path)
+    try:
+        before = storage.conn.execute("SELECT COUNT(*) FROM chunks").fetchone()[0]
+        storage.conn.execute("DELETE FROM chunks")
+        storage.conn.execute("DELETE FROM files")
+        storage.conn.commit()
+        storage.reset_fts5()
+    finally:
+        if owns_storage:
+            storage.close()
+
+    cleanup_legacy_state_file(db_path)
+    return int(before)
+
+
+def rebuild_in_process(memory_manager) -> RebuildResult:
+    """
+    Rebuild the index using an existing, fully-initialized MemoryManager.
+
+    Used by the in-chat /memory rebuild-index command. The caller already has
+    config loaded, embedding_provider built, and (optionally) the agent
+    running, so we only need to:
+      1. Clear chunks/files + state on the manager's storage.
+      2. Re-sync (force=True).
+
+    NOTE: caller must ensure memory_manager.embedding_provider is set, otherwise
+    sync() will silently skip embedding generation.
+    """
+    if memory_manager is None:
+        return RebuildResult(ok=False, error="memory_manager is None")
+    if memory_manager.embedding_provider is None:
+        return RebuildResult(ok=False, error="embedding_provider is not initialized")
+
+    # Probe the embedding endpoint BEFORE clearing the index. A bad
+    # provider/model/key would otherwise leave the user with an empty index
+    # that not even keyword search can serve.
+    try:
+        memory_manager.embedding_provider.embed_query("ping")
+    except Exception as e:
+        logger.error(f"[RebuildIndex] embedding probe failed, aborting rebuild: {e}")
+        return RebuildResult(ok=False, error=f"embedding endpoint not reachable: {e}")
+
+    db_path = memory_manager.config.get_db_path()
+    try:
+        removed = clear_index(db_path, storage=memory_manager.storage)
+    except Exception as e:
+        logger.exception("[RebuildIndex] clear_index failed")
+        return RebuildResult(ok=False, error=f"clear failed: {e}")
+
+    try:
+        asyncio.run(memory_manager.sync(force=True))
+    except RuntimeError:
+        # Already inside a running event loop (rare in chat handler thread).
+        loop = asyncio.new_event_loop()
+        try:
+            loop.run_until_complete(memory_manager.sync(force=True))
+        finally:
+            loop.close()
+    except Exception as e:
+        logger.exception("[RebuildIndex] sync failed")
+        return RebuildResult(ok=False, removed=removed, error=f"re-embed failed: {e}")
+
+    stats = memory_manager.storage.get_stats()
+    chunks = int(stats.get("chunks", 0))
+    embedded = int(stats.get("embedded", 0))
+
+    # sync() degrades to "no embeddings" on batch failure so keyword search
+    # still works at startup — but in a /rebuild-index request the user
+    # explicitly asked for vectors. Surface that as a failure.
+    if chunks > 0 and embedded == 0:
+        return RebuildResult(
+            ok=False,
+            removed=removed,
+            chunks=chunks,
+            files=int(stats.get("files", 0)),
+            error=(
+                "embedding API failed during sync; index now has chunks but no "
+                "vectors. Check embedding provider/model/key and retry."
+            ),
+        )
+
+    return RebuildResult(
+        ok=True,
+        removed=removed,
+        chunks=chunks,
+        files=int(stats.get("files", 0)),
+    )
+
+
+def main() -> int:
+    """Standalone CLI entry. Must be run from project root (relative config path)."""
+    from config import conf, load_config
+    from agent.memory import MemoryConfig, MemoryManager
+
+    load_config()
+
+    workspace_root = expand_path(conf().get("agent_workspace", "~/cow"))
+    memory_config = MemoryConfig(workspace_root=workspace_root)
+
+    logger.info(f"[RebuildIndex] Workspace: {workspace_root}")
+    logger.info(f"[RebuildIndex] Index db:  {memory_config.get_db_path()}")
+
+    from agent.memory.embedding import create_default_embedding_provider
+
+    embedding_provider = create_default_embedding_provider()
+    if embedding_provider is None:
+        logger.error(
+            "[RebuildIndex] No embedding provider could be initialized. "
+            "Check your config.json. Aborting rebuild."
+        )
+        return 1
+
+    manager = MemoryManager(memory_config, embedding_provider=embedding_provider)
+    result = rebuild_in_process(manager)
+    if not result.ok:
+        logger.error(f"[RebuildIndex] {result.error}")
+        return 1
+
+    logger.info(
+        f"[RebuildIndex] Done. removed={result.removed}, "
+        f"chunks={result.chunks}, files={result.files}"
+    )
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

agent/memory/embedding/state.py

@@ -0,0 +1,51 @@
+"""
+Embedding-related index utilities.
+
+We don't keep a sidecar state file — the SQLite index is the source of truth
+and config.json is the source of intent. The two functions below are the
+only things needing on-disk awareness:
+
+  detect_index_dim         : read the dim of stored vectors (display-only)
+  cleanup_legacy_state_file: remove old embedding_state.json from earlier
+                             versions; safe no-op when absent.
+"""
+
+from __future__ import annotations
+import json
+import os
+from pathlib import Path
+from typing import Optional, Union
+
+PathLike = Union[str, os.PathLike]
+
+
+def detect_index_dim(storage) -> Optional[int]:
+    """Return the dim of the first stored embedding, or None if the index
+    has no embeddings. Used by /memory status."""
+    try:
+        row = storage.conn.execute(
+            "SELECT embedding FROM chunks WHERE embedding IS NOT NULL LIMIT 1"
+        ).fetchone()
+    except Exception:
+        return None
+    if not row or not row["embedding"]:
+        return None
+    try:
+        raw = row["embedding"]
+        if isinstance(raw, (bytes, bytearray)):
+            # New BLOB format: 4 bytes per float32
+            return len(raw) // 4
+        emb = json.loads(raw)
+        return len(emb) if isinstance(emb, list) else None
+    except (json.JSONDecodeError, TypeError, Exception):
+        return None
+
+
+def cleanup_legacy_state_file(db_path: PathLike) -> None:
+    """Remove old embedding_state.json files from earlier versions.
+    Safe to call repeatedly; no-op if the file is absent."""
+    legacy = Path(db_path).parent / "embedding_state.json"
+    try:
+        legacy.unlink(missing_ok=True)
+    except Exception:
+        pass

agent/memory/manager.py

@@ -13,7 +13,7 @@ from datetime import datetime, timedelta
 from agent.memory.config import MemoryConfig, get_default_memory_config
 from agent.memory.storage import MemoryStorage, MemoryChunk, SearchResult
 from agent.memory.chunker import TextChunker
-from agent.memory.embedding import create_embedding_provider, EmbeddingProvider
+from agent.memory.embedding import EmbeddingProvider, EmbeddingCache
 from agent.memory.summarizer import MemoryFlushManager, create_memory_files_if_needed
 
 
@@ -50,30 +50,22 @@ class MemoryManager:
             overlap_tokens=self.config.chunk_overlap_tokens
         )
         
-        # Initialize embedding provider (optional)
+        # Embedding provider is owned by the caller (agent_initializer is the
-        self.embedding_provider = None
+        # canonical entry point and handles legacy/explicit + state validation).
-        if embedding_provider:
+        # When None is passed, memory degrades to keyword-only search instead
-            self.embedding_provider = embedding_provider
+        # of silently re-initializing a vendor here, which would bypass the
-        else:
+        # caller's state checks and risk corrupting the index.
-            # Try to create embedding provider, but allow failure
+        self.embedding_provider = embedding_provider
-            try:
+        if self.embedding_provider is None:
-                # Get API key from environment or config
+            from common.log import logger
-                api_key = os.environ.get('OPENAI_API_KEY')
+            logger.info(
-                api_base = os.environ.get('OPENAI_API_BASE')
+                "[MemoryManager] No embedding provider; memory will use keyword search only"
-                
+            )
-                self.embedding_provider = create_embedding_provider(
+
-                    provider=self.config.embedding_provider,
+        # Cache for query embeddings (avoids redundant API calls within a session)
-                    model=self.config.embedding_model,
+        self._embedding_cache = EmbeddingCache()
-                    api_key=api_key,
+
-                    api_base=api_base
+
-                )
-            except Exception as e:
-                # Embedding provider failed, but that's OK
-                # We can still use keyword search and file operations
-                from common.log import logger
-                logger.warning(f"[MemoryManager] Embedding provider initialization failed: {e}")
-                logger.info(f"[MemoryManager] Memory will work with keyword search only (no vector search)")
-        
         # Initialize memory flush manager
         workspace_dir = self.config.get_workspace()
         self.flush_manager = MemoryFlushManager(
@@ -133,12 +125,21 @@ class MemoryManager:
         if self.config.sync_on_search and self._dirty:
             await self.sync()
         
-        # Perform vector search (if embedding provider available)
+        from common.log import logger
+
+        # Perform vector search (if embedding provider available).
+        # Failures degrade silently to keyword-only — no exception is raised.
         vector_results = []
         if self.embedding_provider:
             try:
-                from common.log import logger
+                provider_name = type(self.embedding_provider).__name__
-                query_embedding = self.embedding_provider.embed(query)
+                model_name = getattr(self.embedding_provider, 'model', '')
+                cached = self._embedding_cache.get(query, provider_name, model_name)
+                if cached is not None:
+                    query_embedding = cached
+                else:
+                    query_embedding = self.embedding_provider.embed_query(query)
+                    self._embedding_cache.put(query, provider_name, model_name, query_embedding)
                 vector_results = self.storage.search_vector(
                     query_embedding=query_embedding,
                     user_id=user_id,
@@ -147,19 +148,19 @@ class MemoryManager:
                 )
                 logger.info(f"[MemoryManager] Vector search found {len(vector_results)} results for query: {query}")
             except Exception as e:
-                from common.log import logger
+                logger.error(
-                logger.warning(f"[MemoryManager] Vector search failed: {e}")
+                    f"[MemoryManager] Vector search failed, falling back to keyword-only: {e}"
-        
+                )
-        # Perform keyword search
+
+        # Perform keyword search (also runs as fallback when vector failed)
         keyword_results = self.storage.search_keyword(
             query=query,
             user_id=user_id,
             scopes=scopes,
             limit=max_results * 2
         )
-        from common.log import logger
         logger.info(f"[MemoryManager] Keyword search found {len(keyword_results)} results for query: {query}")
-        
+
         # Merge results
         merged = self._merge_results(
             vector_results,
@@ -167,7 +168,7 @@ class MemoryManager:
             self.config.vector_weight,
             self.config.keyword_weight
         )
-        
+
         # Filter by min score and limit
         filtered = [r for r in merged if r.score >= min_score]
         return filtered[:max_results]
@@ -249,295 +250,195 @@ class MemoryManager:
     
     async def sync(self, force: bool = False):
         """
-        Synchronize memory from files
+        Synchronize memory from files.
-        
+
+        Two-pass design to amortize embedding HTTP cost:
+          1. Walk all files, chunk those whose hash changed, collect pending
+             chunks across files. No embedding calls yet.
+          2. Run a single embed_batch over the union of pending chunks (the
+             provider auto-paginates by vendor cap), then persist per-file.
+
+        For workspaces with many small files (101 files / ~1 chunk each), this
+        cuts ~100 HTTP calls down to ~ceil(total_chunks / vendor_cap).
+
         Args:
             force: Force full reindex
         """
         memory_dir = self.config.get_memory_dir()
         workspace_dir = self.config.get_workspace()
-        
+
-        # Scan MEMORY.md (workspace root)
+        files_to_scan: List[tuple] = []  # (file_path, source, scope, user_id)
+
         memory_file = Path(workspace_dir) / "MEMORY.md"
         if memory_file.exists():
-            await self._sync_file(memory_file, "memory", "shared", None)
+            files_to_scan.append((memory_file, "memory", "shared", None))
-        
+
-        # Scan memory directory (including daily summaries)
         if memory_dir.exists():
             for file_path in memory_dir.rglob("*.md"):
-                # Determine scope and user_id from path
+                rel_parts = file_path.relative_to(workspace_dir).parts
-                rel_path = file_path.relative_to(workspace_dir)
+                if any(part.startswith('.') for part in rel_parts):
-                parts = rel_path.parts
+                    continue
-                
+                # Dream diaries are narrative reflections produced by Deep
-                # Check if it's in daily summary directory
+                # Dream; their factual content has already been distilled
-                if "daily" in parts:
+                # into MEMORY.md. Indexing them adds noisy near-duplicates
-                    # Daily summary files
+                # that crowd out the authoritative entry in retrieval.
-                    if "users" in parts or len(parts) > 3:
+                if "dreams" in rel_parts:
-                        # User-scoped daily summary: memory/daily/{user_id}/2024-01-29.md
+                    continue
-                        user_idx = parts.index("daily") + 1
+                if "daily" in rel_parts:
-                        user_id = parts[user_idx] if user_idx < len(parts) else None
+                    if "users" in rel_parts or len(rel_parts) > 3:
+                        user_idx = rel_parts.index("daily") + 1
+                        user_id = rel_parts[user_idx] if user_idx < len(rel_parts) else None
                         scope = "user"
                     else:
-                        # Shared daily summary: memory/daily/2024-01-29.md
                         user_id = None
                         scope = "shared"
-                elif "users" in parts:
+                elif "users" in rel_parts:
-                    # User-scoped memory
+                    user_idx = rel_parts.index("users") + 1
-                    user_idx = parts.index("users") + 1
+                    user_id = rel_parts[user_idx] if user_idx < len(rel_parts) else None
-                    user_id = parts[user_idx] if user_idx < len(parts) else None
                     scope = "user"
                 else:
-                    # Shared memory
                     user_id = None
                     scope = "shared"
-                
+                files_to_scan.append((file_path, "memory", scope, user_id))
-                await self._sync_file(file_path, "memory", scope, user_id)
-        
-        self._dirty = False
-    
-    async def _sync_file(
-        self,
-        file_path: Path,
-        source: str,
-        scope: str,
-        user_id: Optional[str]
-    ):
-        """Sync a single file"""
-        # Compute file hash
-        content = file_path.read_text(encoding='utf-8')
-        file_hash = MemoryStorage.compute_hash(content)
-        
-        # Get relative path
-        workspace_dir = self.config.get_workspace()
-        rel_path = str(file_path.relative_to(workspace_dir))
-        
-        # Check if file changed
-        stored_hash = self.storage.get_file_hash(rel_path)
-        if stored_hash == file_hash:
-            return  # No changes
-        
-        # Delete old chunks
-        self.storage.delete_by_path(rel_path)
-        
-        # Chunk and embed
-        chunks = self.chunker.chunk_text(content)
-        if not chunks:
-            return
-        
-        texts = [chunk.text for chunk in chunks]
-        if self.embedding_provider:
-            embeddings = self.embedding_provider.embed_batch(texts)
-        else:
-            embeddings = [None] * len(texts)
-        
-        # Create memory chunks
-        memory_chunks = []
-        for chunk, embedding in zip(chunks, embeddings):
-            chunk_id = self._generate_chunk_id(rel_path, chunk.start_line, chunk.end_line)
-            chunk_hash = MemoryStorage.compute_hash(chunk.text)
-            
-            memory_chunks.append(MemoryChunk(
-                id=chunk_id,
-                user_id=user_id,
-                scope=scope,
-                source=source,
-                path=rel_path,
-                start_line=chunk.start_line,
-                end_line=chunk.end_line,
-                text=chunk.text,
-                embedding=embedding,
-                hash=chunk_hash,
-                metadata=None
-            ))
-        
-        # Save
-        self.storage.save_chunks_batch(memory_chunks)
-        
-        # Update file metadata
-        stat = file_path.stat()
-        self.storage.update_file_metadata(
-            path=rel_path,
-            source=source,
-            file_hash=file_hash,
-            mtime=int(stat.st_mtime),
-            size=stat.st_size
-        )
-    
-    def should_flush_memory(
-        self,
-        current_tokens: int = 0
-    ) -> bool:
-        """
-        Check if memory flush should be triggered
-        
-        独立的 flush 触发机制，不依赖模型 context window。
-        使用配置中的阈值: flush_token_threshold 和 flush_turn_threshold
-        
-        Args:
-            current_tokens: Current session token count
-            
-        Returns:
-            True if memory flush should run
-        """
-        return self.flush_manager.should_flush(
-            current_tokens=current_tokens,
-            token_threshold=self.config.flush_token_threshold,
-            turn_threshold=self.config.flush_turn_threshold
-        )
-    
-    def increment_turn(self):
-        """增加对话轮数计数（每次用户消息+AI回复算一轮）"""
-        self.flush_manager.increment_turn()
-    
-    async def execute_memory_flush(
-        self,
-        agent_executor,
-        current_tokens: int,
-        user_id: Optional[str] = None,
-        **executor_kwargs
-    ) -> bool:
-        """
-        Execute memory flush before compaction
-        
-        This runs a silent agent turn to write durable memories to disk.
-        Similar to clawdbot's pre-compaction memory flush.
-        
-        Args:
-            agent_executor: Async function to execute agent with prompt
-            current_tokens: Current session token count
-            user_id: Optional user ID
-            **executor_kwargs: Additional kwargs for agent executor
-            
-        Returns:
-            True if flush completed successfully
-            
-        Example:
-            >>> async def run_agent(prompt, system_prompt, silent=False):
-            ...     # Your agent execution logic
-            ...     pass
-            >>> 
-            >>> if manager.should_flush_memory(current_tokens=100000):
-            ...     await manager.execute_memory_flush(
-            ...         agent_executor=run_agent,
-            ...         current_tokens=100000
-            ...     )
-        """
-        success = await self.flush_manager.execute_flush(
-            agent_executor=agent_executor,
-            current_tokens=current_tokens,
-            user_id=user_id,
-            **executor_kwargs
-        )
-        
-        if success:
-            # Mark dirty so next search will sync the new memories
-            self._dirty = True
-        
-        return success
-    
-    def build_memory_guidance(self, lang: str = "zh", include_context: bool = True) -> str:
-        """
-        Build natural memory guidance for agent system prompt
-        
-        Following clawdbot's approach:
-        1. Load MEMORY.md as bootstrap context (blends into background)
-        2. Load daily files on-demand via memory_search tool
-        3. Agent should NOT proactively mention memories unless user asks
-        
-        Args:
-            lang: Language for guidance ("en" or "zh")
-            include_context: Whether to include bootstrap memory context (default: True)
-                           MEMORY.md is loaded as background context (like clawdbot)
-                           Daily files are accessed via memory_search tool
-            
-        Returns:
-            Memory guidance text (and optionally context) for system prompt
-        """
-        today_file = self.flush_manager.get_today_memory_file().name
-        
-        if lang == "zh":
-            guidance = f"""## 记忆系统
 
-**背景知识**: 下方包含核心长期记忆，可直接使用。需要查找历史时，用 memory_search 搜索（搜索一次即可，不要重复）。
+        from config import conf
+        if conf().get("knowledge", True):
+            knowledge_dir = Path(workspace_dir) / "knowledge"
+            if knowledge_dir.exists():
+                for file_path in knowledge_dir.rglob("*.md"):
+                    files_to_scan.append((file_path, "knowledge", "shared", None))
 
-**存储记忆**: 当用户分享重要信息时（偏好、决策、事实等），主动用 write 工具存储：
+        # Pass 1: inline chunking + change detection. Inlined (instead of
-- 长期信息 → MEMORY.md
+        # calling self._prepare_file_for_sync) so this method does not depend
-- 当天笔记 → memory/{today_file}
+        # on any sibling helpers — keeps it robust against partial reloads
-- 静默存储，仅在明确要求时确认
+        # where the class object is older than the method's source.
-
+        pending: List[Dict[str, Any]] = []
-**使用原则**: 自然使用记忆，就像你本来就知道。不需要生硬地提起或列举记忆，除非用户提到。"""
+        workspace_dir_path = self.config.get_workspace()
-        else:
+        for file_path, source, scope, user_id in files_to_scan:
-            guidance = f"""## Memory System
-
-**Background Knowledge**: Core long-term memories below - use directly. For history, use memory_search once (don't repeat).
-
-**Store Memories**: When user shares important info (preferences, decisions, facts), proactively write:
-- Durable info → MEMORY.md  
-- Daily notes → memory/{today_file}
-- Store silently; confirm only when explicitly requested
-
-**Usage**: Use memories naturally as if you always knew. Don't mention or list unless user explicitly asks."""
-        
-        if include_context:
-            # Load bootstrap context (MEMORY.md only, like clawdbot)
-            bootstrap_context = self.load_bootstrap_memories()
-            if bootstrap_context:
-                guidance += f"\n\n## Background Context\n\n{bootstrap_context}"
-        
-        return guidance
-    
-    def load_bootstrap_memories(self, user_id: Optional[str] = None) -> str:
-        """
-        Load bootstrap memory files for session start
-        
-        Following clawdbot's design:
-        - Only loads MEMORY.md from workspace root (long-term curated memory)
-        - Daily files (memory/YYYY-MM-DD.md) are accessed via memory_search tool, not bootstrap
-        - User-specific MEMORY.md is also loaded if user_id provided
-        
-        Returns memory content WITHOUT obvious headers so it blends naturally
-        into the context as background knowledge.
-        
-        Args:
-            user_id: Optional user ID for user-specific memories
-            
-        Returns:
-            Memory content to inject into system prompt (blends naturally as background context)
-        """
-        workspace_dir = self.config.get_workspace()
-        memory_dir = self.config.get_memory_dir()
-        
-        sections = []
-        
-        # 1. Load MEMORY.md from workspace root (long-term curated memory)
-        # Following clawdbot: only MEMORY.md is bootstrap, daily files use memory_search
-        memory_file = Path(workspace_dir) / "MEMORY.md"
-        if memory_file.exists():
             try:
-                content = memory_file.read_text(encoding='utf-8').strip()
+                content = file_path.read_text(encoding='utf-8')
-                if content:
+            except Exception:
-                    sections.append(content)
+                continue
+            file_hash = MemoryStorage.compute_hash(content)
+            rel_path = str(file_path.relative_to(workspace_dir_path))
+            if self.storage.get_file_hash(rel_path) == file_hash:
+                continue
+            chunks = self.chunker.chunk_text(content)
+            if not chunks:
+                continue
+            pending.append({
+                "file_path": file_path,
+                "rel_path": rel_path,
+                "source": source,
+                "scope": scope,
+                "user_id": user_id,
+                "file_hash": file_hash,
+                "chunks": chunks,
+                "texts": [c.text for c in chunks],
+            })
+
+        if not pending:
+            self._dirty = False
+            return
+
+        # Pass 2: single batched embed across all pending chunks.
+        # CRITICAL: never touch the index until we hold valid embeddings.
+        # If embed_batch fails, leave the existing index intact (chunks +
+        # file_hash) so the next sync will retry the same files. Writing
+        # NULL embeddings + updating file_hash here would mark the file as
+        # "successfully synced" and silently strand it without vectors.
+        all_texts: List[str] = []
+        for entry in pending:
+            all_texts.extend(entry["texts"])
+
+        if not self.embedding_provider:
+            # No provider configured at all (legacy keyword-only). Persist
+            # chunks without embeddings — this is the user's intent.
+            all_embeddings: List[Optional[List[float]]] = [None] * len(all_texts)
+        else:
+            try:
+                all_embeddings = self.embedding_provider.embed_batch(all_texts)
             except Exception as e:
-                print(f"Warning: Failed to read MEMORY.md: {e}")
+                from common.log import logger
-        
+                logger.error(
-        # 2. Load user-specific MEMORY.md if user_id provided
+                    f"[MemoryManager] Batch embedding failed for {len(all_texts)} "
-        if user_id:
+                    f"chunks across {len(pending)} files: {e}. "
-            user_memory_dir = memory_dir / "users" / user_id
+                    f"Index left untouched; will retry on next sync."
-            user_memory_file = user_memory_dir / "MEMORY.md"
+                )
-            if user_memory_file.exists():
+                # Bail before touching storage. self._dirty stays True so
-                try:
+                # callers know there is pending work.
-                    content = user_memory_file.read_text(encoding='utf-8').strip()
+                return
-                    if content:
+
-                        sections.append(content)
+        # Pass 3: inline persist — same self-contained reasoning as Pass 1.
-                except Exception as e:
+        cursor = 0
-                    print(f"Warning: Failed to read user memory: {e}")
+        for entry in pending:
-        
+            n = len(entry["texts"])
-        if not sections:
+            entry_embeddings = all_embeddings[cursor:cursor + n]
-            return ""
+            cursor += n
-        
+
-        # Join sections without obvious headers - let memories blend naturally
+            rel_path = entry["rel_path"]
-        # This makes the agent feel like it "just knows" rather than "checking memory files"
+            self.storage.delete_by_path(rel_path)
-        return "\n\n".join(sections)
+            memory_chunks = []
+            for chunk, embedding in zip(entry["chunks"], entry_embeddings):
+                chunk_id = self._generate_chunk_id(rel_path, chunk.start_line, chunk.end_line)
+                chunk_hash = MemoryStorage.compute_hash(chunk.text)
+                memory_chunks.append(MemoryChunk(
+                    id=chunk_id,
+                    user_id=entry["user_id"],
+                    scope=entry["scope"],
+                    source=entry["source"],
+                    path=rel_path,
+                    start_line=chunk.start_line,
+                    end_line=chunk.end_line,
+                    text=chunk.text,
+                    embedding=embedding,
+                    hash=chunk_hash,
+                    metadata=None,
+                ))
+            self.storage.save_chunks_batch(memory_chunks)
+            stat = entry["file_path"].stat()
+            self.storage.update_file_metadata(
+                path=rel_path,
+                source=entry["source"],
+                file_hash=entry["file_hash"],
+                mtime=int(stat.st_mtime),
+                size=stat.st_size,
+            )
+
+        self._dirty = False
+
+    def flush_memory(
+        self,
+        messages: list,
+        user_id: Optional[str] = None,
+        reason: str = "threshold",
+        max_messages: int = 10,
+        context_summary_callback=None,
+    ) -> bool:
+        """
+        Flush conversation summary to daily memory file.
+
+        Args:
+            messages: Conversation message list
+            user_id: Optional user ID
+            reason: "threshold" | "overflow" | "daily_summary"
+            max_messages: Max recent messages to include (0 = all)
+            context_summary_callback: Optional callback(str) invoked with the
+                daily summary text for in-context injection
+
+        Returns:
+            True if flush was dispatched
+        """
+        success = self.flush_manager.flush_from_messages(
+            messages=messages,
+            user_id=user_id,
+            reason=reason,
+            max_messages=max_messages,
+            context_summary_callback=context_summary_callback,
+        )
+        if success:
+            self._dirty = True
+        return success
     
     def get_status(self) -> Dict[str, Any]:
         """Get memory status"""
@@ -568,6 +469,37 @@ class MemoryManager:
         content = f"{path}:{start_line}:{end_line}"
         return hashlib.md5(content.encode('utf-8')).hexdigest()
     
+    @staticmethod
+    def _compute_temporal_decay(path: str, half_life_days: float = 30.0) -> float:
+        """
+        Compute temporal decay multiplier for dated memory files.
+        
+        Inspired by OpenClaw's temporal-decay: exponential decay based on file date.
+        MEMORY.md and non-dated files are "evergreen" (no decay, multiplier=1.0).
+        Daily files like memory/2025-03-01.md decay based on age.
+        
+        Formula: multiplier = exp(-ln2/half_life * age_in_days)
+        """
+        import re
+        import math
+        
+        match = re.search(r'(\d{4})-(\d{2})-(\d{2})\.md$', path)
+        if not match:
+            return 1.0  # evergreen: MEMORY.md, non-dated files
+        
+        try:
+            file_date = datetime(
+                int(match.group(1)), int(match.group(2)), int(match.group(3))
+            )
+            age_days = (datetime.now() - file_date).days
+            if age_days <= 0:
+                return 1.0
+            
+            decay_lambda = math.log(2) / half_life_days
+            return math.exp(-decay_lambda * age_days)
+        except (ValueError, OverflowError):
+            return 1.0
+    
     def _merge_results(
         self,
         vector_results: List[SearchResult],
@@ -575,8 +507,7 @@ class MemoryManager:
         vector_weight: float,
         keyword_weight: float
     ) -> List[SearchResult]:
-        """Merge vector and keyword search results"""
+        """Merge vector and keyword search results with temporal decay for dated files"""
-        # Create a map by (path, start_line, end_line)
         merged_map = {}
         
         for result in vector_results:
@@ -598,7 +529,6 @@ class MemoryManager:
                     'keyword_score': result.score
                 }
         
-        # Calculate combined scores
         merged_results = []
         for entry in merged_map.values():
             combined_score = (
@@ -606,7 +536,11 @@ class MemoryManager:
                 keyword_weight * entry['keyword_score']
             )
             
+            # Apply temporal decay for dated memory files
             result = entry['result']
+            decay = self._compute_temporal_decay(result.path)
+            combined_score *= decay
+            
             merged_results.append(SearchResult(
                 path=result.path,
                 start_line=result.start_line,
@@ -617,6 +551,5 @@ class MemoryManager:
                 user_id=result.user_id
             ))
         
-        # Sort by score
         merged_results.sort(key=lambda r: r.score, reverse=True)
         return merged_results

agent/memory/rebuild_index.py

@@ -0,0 +1,14 @@
+"""
+Backward-compatible shim for the legacy entry point:
+    python -m agent.memory.rebuild_index
+
+The implementation now lives in agent.memory.embedding.rebuild.
+Prefer using `/memory rebuild-index` in chat going forward.
+"""
+
+from agent.memory.embedding.rebuild import main
+
+if __name__ == "__main__":
+    import sys
+
+    sys.exit(main())

agent/memory/service.py

@@ -32,68 +32,105 @@ class MemoryService:
     # ------------------------------------------------------------------
     # list — paginated file metadata
     # ------------------------------------------------------------------
-    def list_files(self, page: int = 1, page_size: int = 20) -> dict:
+    def list_files(self, page: int = 1, page_size: int = 20, category: str = "memory") -> dict:
         """
-        List all memory files with metadata (without content).
+        List memory, dream, or evolution files with metadata (without content).
 
-        Returns::
+        Args:
-
+            category: ``"memory"`` (default) — MEMORY.md + daily files;
-            {
+                      ``"dream"``     — dream diary files from memory/dreams/;
-                "page": 1,
+                      ``"evolution"`` — self-evolution logs from memory/evolution/
-                "page_size": 20,
+                                        merged with the nightly dream diaries, so
-                "total": 15,
+                                        one tab shows everything the agent learned.
-                "list": [
-                    {"filename": "MEMORY.md", "type": "global", "size": 2048, "updated_at": "2026-02-20 10:00:00"},
-                    {"filename": "2026-02-20.md", "type": "daily", "size": 512, "updated_at": "2026-02-20 09:30:00"},
-                    ...
-                ]
-            }
         """
+        if category == "evolution":
+            files = self._list_evolution_files()
+        elif category == "dream":
+            files = self._list_dream_files()
+        else:
+            files = self._list_memory_files()
+
+        total = len(files)
+        start = (page - 1) * page_size
+        end = start + page_size
+
+        return {
+            "page": page,
+            "page_size": page_size,
+            "total": total,
+            "list": files[start:end],
+        }
+
+    def _list_memory_files(self) -> List[dict]:
+        """MEMORY.md + memory/*.md (newest first)."""
         files: List[dict] = []
 
-        # 1. Global memory — MEMORY.md in workspace root
         global_path = os.path.join(self.workspace_root, "MEMORY.md")
         if os.path.isfile(global_path):
             files.append(self._file_info(global_path, "MEMORY.md", "global"))
 
-        # 2. Daily memory files — memory/*.md (sorted newest first)
         if os.path.isdir(self.memory_dir):
             daily_files = []
             for name in os.listdir(self.memory_dir):
                 full = os.path.join(self.memory_dir, name)
                 if os.path.isfile(full) and name.endswith(".md"):
                     daily_files.append((name, full))
-            # Sort by filename descending (newest date first)
             daily_files.sort(key=lambda x: x[0], reverse=True)
             for name, full in daily_files:
                 files.append(self._file_info(full, name, "daily"))
 
-        total = len(files)
+        return files
 
-        # Paginate
+    def _list_dream_files(self) -> List[dict]:
-        start = (page - 1) * page_size
+        """memory/dreams/*.md (newest first)."""
-        end = start + page_size
+        files: List[dict] = []
-        page_items = files[start:end]
+        dreams_dir = os.path.join(self.memory_dir, "dreams")
 
-        return {
+        if os.path.isdir(dreams_dir):
-            "page": page,
+            entries = []
-            "page_size": page_size,
+            for name in os.listdir(dreams_dir):
-            "total": total,
+                full = os.path.join(dreams_dir, name)
-            "list": page_items,
+                if os.path.isfile(full) and name.endswith(".md"):
-        }
+                    entries.append((name, full))
+            entries.sort(key=lambda x: x[0], reverse=True)
+            for name, full in entries:
+                files.append(self._file_info(full, name, "dream"))
+
+        return files
+
+    def _list_evolution_files(self) -> List[dict]:
+        """Self-evolution logs (memory/evolution/*.md) merged with the nightly
+        dream diaries (memory/dreams/*.md), newest first.
+
+        Both are surfaced under the unified "Self-Evolution" tab. A file's
+        ``type`` records its origin so the reader can resolve the right dir.
+        """
+        files: List[dict] = []
+        for sub, ftype in (("evolution", "evolution"), ("dreams", "dream")):
+            sub_dir = os.path.join(self.memory_dir, sub)
+            if not os.path.isdir(sub_dir):
+                continue
+            for name in os.listdir(sub_dir):
+                full = os.path.join(sub_dir, name)
+                if os.path.isfile(full) and name.endswith(".md"):
+                    files.append(self._file_info(full, name, ftype))
+        # Sort newest first by filename (date-named); ties favor evolution.
+        files.sort(key=lambda f: (f["filename"], f["type"] != "evolution"), reverse=True)
+        return files
 
     # ------------------------------------------------------------------
     # content — read a single file
     # ------------------------------------------------------------------
-    def get_content(self, filename: str) -> dict:
+    def get_content(self, filename: str, category: str = "memory") -> dict:
         """
-        Read the full content of a memory file.
+        Read the full content of a memory or dream file.
 
-        :param filename: File name, e.g. ``MEMORY.md`` or ``2026-02-20.md``
+        :param filename: File name, e.g. ``MEMORY.md``, ``2026-02-20.md``
+        :param category: ``"memory"``, ``"dream"`` or ``"evolution"``
         :return: dict with ``filename`` and ``content``
         :raises FileNotFoundError: if the file does not exist
         """
-        path = self._resolve_path(filename)
+        path = self._resolve_path(filename, category)
         if not os.path.isfile(path):
             raise FileNotFoundError(f"Memory file not found: {filename}")
 
@@ -113,7 +150,7 @@ class MemoryService:
         Dispatch a memory management action.
 
         :param action: ``list`` or ``content``
-        :param payload: action-specific payload
+        :param payload: action-specific payload (supports ``category``: ``"memory"`` | ``"dream"`` | ``"evolution"``)
         :return: protocol-compatible response dict
         """
         payload = payload or {}
@@ -121,19 +158,23 @@ class MemoryService:
             if action == "list":
                 page = payload.get("page", 1)
                 page_size = payload.get("page_size", 20)
-                result_payload = self.list_files(page=page, page_size=page_size)
+                category = payload.get("category", "memory")
+                result_payload = self.list_files(page=page, page_size=page_size, category=category)
                 return {"action": action, "code": 200, "message": "success", "payload": result_payload}
 
             elif action == "content":
                 filename = payload.get("filename")
                 if not filename:
                     return {"action": action, "code": 400, "message": "filename is required", "payload": None}
-                result_payload = self.get_content(filename)
+                category = payload.get("category", "memory")
+                result_payload = self.get_content(filename, category=category)
                 return {"action": action, "code": 200, "message": "success", "payload": result_payload}
 
             else:
                 return {"action": action, "code": 400, "message": f"unknown action: {action}", "payload": None}
 
+        except ValueError as e:
+            return {"action": action, "code": 403, "message": "invalid filename", "payload": None}
         except FileNotFoundError as e:
             return {"action": action, "code": 404, "message": str(e), "payload": None}
         except Exception as e:
@@ -143,16 +184,33 @@ class MemoryService:
     # ------------------------------------------------------------------
     # internal helpers
     # ------------------------------------------------------------------
-    def _resolve_path(self, filename: str) -> str:
+    def _resolve_path(self, filename: str, category: str = "memory") -> str:
         """
-        Resolve a filename to its absolute path.
+        Safely resolve a filename to its absolute path within the allowed directory.
 
         - ``MEMORY.md`` → ``{workspace_root}/MEMORY.md``
-        - ``2026-02-20.md`` → ``{workspace_root}/memory/2026-02-20.md``
+        - ``2026-02-20.md`` (memory) → ``{workspace_root}/memory/2026-02-20.md``
+        - ``2026-02-20.md`` (dream) → ``{workspace_root}/memory/dreams/2026-02-20.md``
+        - ``2026-02-20.md`` (evolution) → ``{workspace_root}/memory/evolution/2026-02-20.md``
+
+        Raises ValueError if the resolved path escapes the allowed directory.
         """
         if filename == "MEMORY.md":
-            return os.path.join(self.workspace_root, filename)
+            base_dir = self.workspace_root
-        return os.path.join(self.memory_dir, filename)
+        elif category == "dream":
+            base_dir = os.path.join(self.memory_dir, "dreams")
+        elif category == "evolution":
+            base_dir = os.path.join(self.memory_dir, "evolution")
+        else:
+            base_dir = self.memory_dir
+
+        resolved = os.path.realpath(os.path.join(base_dir, filename))
+        allowed = os.path.realpath(base_dir)
+
+        if resolved != allowed and not resolved.startswith(allowed + os.sep):
+            raise ValueError(f"Invalid filename: path traversal detected")
+
+        return resolved
 
     @staticmethod
     def _file_info(path: str, filename: str, file_type: str) -> dict:

agent/prompt/builder.py

@@ -10,17 +10,18 @@ from typing import List, Dict, Optional, Any
 from dataclasses import dataclass
 
 from common.log import logger
+from config import conf
 
 
 @dataclass
 class ContextFile:
-    """上下文文件"""
+    """A context file (path + content)."""
     path: str
     content: str
 
 
 class PromptBuilder:
-    """提示词构建器"""
+    """System prompt builder."""
     
     def __init__(self, workspace_dir: str, language: str = "zh"):
         """
@@ -42,7 +43,6 @@ class PromptBuilder:
         skill_manager: Any = None,
         memory_manager: Any = None,
         runtime_info: Optional[Dict[str, Any]] = None,
-        is_first_conversation: bool = False,
         **kwargs
     ) -> str:
         """
@@ -52,11 +52,10 @@ class PromptBuilder:
             base_persona: 基础人格描述（会被context_files中的AGENT.md覆盖）
             user_identity: 用户身份信息
             tools: 工具列表
-            context_files: 上下文文件列表（AGENT.md, USER.md, RULE.md等）
+            context_files: 上下文文件列表（AGENT.md, USER.md, RULE.md, BOOTSTRAP.md等）
             skill_manager: 技能管理器
             memory_manager: 记忆管理器
             runtime_info: 运行时信息
-            is_first_conversation: 是否为首次对话
             **kwargs: 其他参数
             
         Returns:
@@ -72,7 +71,6 @@ class PromptBuilder:
             skill_manager=skill_manager,
             memory_manager=memory_manager,
             runtime_info=runtime_info,
-            is_first_conversation=is_first_conversation,
             **kwargs
         )
 
@@ -87,96 +85,147 @@ def build_agent_system_prompt(
     skill_manager: Any = None,
     memory_manager: Any = None,
     runtime_info: Optional[Dict[str, Any]] = None,
-    is_first_conversation: bool = False,
     **kwargs
 ) -> str:
     """
-    构建Agent系统提示词
+    Build the agent system prompt.
-    
+
-    顺序说明（按重要性和逻辑关系排列）:
+    Section order (by importance and logical flow):
-    1. 工具系统 - 核心能力，最先介绍
+    1. Tooling - core capabilities, introduced first
-    2. 技能系统 - 紧跟工具，因为技能需要用 read 工具读取
+    2. Skills - right after tools, since skills are read via the read tool
-    3. 记忆系统 - 独立的记忆能力
+    3. Memory - memory recall and writing guidance
-    4. 工作空间 - 工作环境说明
+    3.5 Knowledge - structured knowledge base (injects knowledge/index.md)
-    5. 用户身份 - 用户信息（可选）
+    4. Workspace - working environment description
-    6. 项目上下文 - AGENT.md, USER.md, RULE.md（定义人格、身份、规则）
+    5. User identity - user info (optional)
-    7. 运行时信息 - 元信息（时间、模型等）
+    6. Project context - AGENT.md, USER.md, RULE.md, MEMORY.md, BOOTSTRAP.md
-    
+    7. Runtime info - meta info (time, model, etc.)
+
     Args:
-        workspace_dir: 工作空间目录
+        workspace_dir: workspace directory
-        language: 语言 ("zh" 或 "en")
+        language: language ("zh" or "en")
-        base_persona: 基础人格描述（已废弃，由AGENT.md定义）
+        base_persona: base persona description (deprecated, defined by AGENT.md)
-        user_identity: 用户身份信息
+        user_identity: user identity info
-        tools: 工具列表
+        tools: tool list
-        context_files: 上下文文件列表
+        context_files: context file list
-        skill_manager: 技能管理器
+        skill_manager: skill manager
-        memory_manager: 记忆管理器
+        memory_manager: memory manager
-        runtime_info: 运行时信息
+        runtime_info: runtime info
-        is_first_conversation: 是否为首次对话
+        **kwargs: extra args
-        **kwargs: 其他参数
+
-        
     Returns:
-        完整的系统提示词
+        The full system prompt.
     """
     sections = []
-    
+
-    # 1. 工具系统（最重要，放在最前面）
+    # 1. Tooling (most important, goes first)
     if tools:
         sections.extend(_build_tooling_section(tools, language))
-    
+
-    # 2. 技能系统（紧跟工具，因为需要用 read 工具）
+    # 2. Skills (right after tools, since they need the read tool)
     if skill_manager:
         sections.extend(_build_skills_section(skill_manager, tools, language))
-    
+
-    # 3. 记忆系统（独立的记忆能力）
+    # 3. Memory (standalone memory capability)
     if memory_manager:
         sections.extend(_build_memory_section(memory_manager, tools, language))
-    
+
-    # 4. 工作空间（工作环境说明）
+    # 3.5 Knowledge (structured knowledge base)
-    sections.extend(_build_workspace_section(workspace_dir, language, is_first_conversation))
+    if conf().get("knowledge", True):
-    
+        sections.extend(_build_knowledge_section(workspace_dir, language))
-    # 5. 用户身份（如果有）
+
+    # 4. Workspace (working environment description)
+    sections.extend(_build_workspace_section(workspace_dir, language))
+
+    # 5. User identity (if present)
     if user_identity:
         sections.extend(_build_user_identity_section(user_identity, language))
-    
+
-    # 6. 项目上下文文件（AGENT.md, USER.md, RULE.md - 定义人格）
+    # 6. Project context files (AGENT.md, USER.md, RULE.md - define the persona)
     if context_files:
         sections.extend(_build_context_files_section(context_files, language))
-    
+
-    # 7. 运行时信息（元信息，放在最后）
+    # 7. Runtime info (meta info, goes last)
     if runtime_info:
         sections.extend(_build_runtime_section(runtime_info, language))
-    
+
+    # 8. Response language (always appended, independent of the skeleton language)
+    sections.extend(_build_response_language_section(language))
+
     return "\n".join(sections)
 
 
+def _build_response_language_section(language: str) -> List[str]:
+    """Response-language rule, appended regardless of the prompt skeleton language.
+
+    Keeps the agent's reply language aligned with the user's input by default,
+    so a Chinese-built prompt still answers an English user in English.
+    """
+    if language == "en":
+        return [
+            "## 🌐 Response language",
+            "",
+            "By default, reply in the same language as the user's input, "
+            "unless the user explicitly asks for another language.",
+            "",
+        ]
+    return [
+        "## 🌐 回复语言",
+        "",
+        "默认使用与用户输入相同的语言回复，除非用户明确要求使用其他语言。",
+        "",
+    ]
+
+
 def _build_identity_section(base_persona: Optional[str], language: str) -> List[str]:
-    """构建基础身份section - 不再需要，身份由AGENT.md定义"""
+    """Base identity section - no longer needed, identity is defined by AGENT.md."""
-    # 不再生成基础身份section，完全由AGENT.md定义
+    # Identity is fully defined by AGENT.md, so emit nothing here.
     return []
 
 
 def _build_tooling_section(tools: List[Any], language: str) -> List[str]:
     """Build tooling section with concise tool list and call style guide."""
+    is_en = language == "en"
     # One-line summaries for known tools (details are in the tool schema)
-    core_summaries = {
+    if is_en:
-        "read": "读取文件内容",
+        core_summaries = {
-        "write": "创建或覆盖文件",
+            "read": "read file content",
-        "edit": "精确编辑文件",
+            "write": "create or overwrite a file",
-        "ls": "列出目录内容",
+            "edit": "make precise edits to a file",
-        "grep": "搜索文件内容",
+            "ls": "list directory contents",
-        "find": "按模式查找文件",
+            "grep": "search file contents",
-        "bash": "执行shell命令",
+            "find": "find files by pattern",
-        "terminal": "管理后台进程",
+            "bash": "run shell commands",
-        "web_search": "网络搜索",
+            "terminal": "manage background processes",
-        "web_fetch": "获取URL内容",
+            "web_search": "web search",
-        "browser": "控制浏览器",
+            "web_fetch": "fetch URL content",
-        "memory_search": "搜索记忆",
+            "browser": "control the browser (screenshot key results or send to the user when help is needed)",
-        "memory_get": "读取记忆内容",
+            "memory_search": "search memory",
-        "env_config": "管理API密钥和技能配置",
+            "memory_get": "read memory content",
-        "scheduler": "管理定时任务和提醒",
+            "env_config": "manage API keys and skill config",
-        "send": "发送文件给用户",
+            "scheduler": "manage scheduled tasks and reminders",
-    }
+            "send": "send a local file to the user (local files only; put URLs directly in the reply text)",
+            "vision": "analyze images (recognition, description, OCR, etc.)",
+        }
+    else:
+        core_summaries = {
+            "read": "读取文件内容",
+            "write": "创建或覆盖文件",
+            "edit": "精确编辑文件",
+            "ls": "列出目录内容",
+            "grep": "搜索文件内容",
+            "find": "按模式查找文件",
+            "bash": "执行shell命令",
+            "terminal": "管理后台进程",
+            "web_search": "网络搜索",
+            "web_fetch": "获取URL内容",
+            "browser": "控制浏览器（关键结果或需要协助可截图发送给用户）",
+            "memory_search": "搜索记忆",
+            "memory_get": "读取记忆内容",
+            "env_config": "管理API密钥和技能配置",
+            "scheduler": "管理定时任务和提醒",
+            "send": "发送本地文件给用户（仅限本地文件，URL直接放在回复文本中）",
+            "vision": "分析图片内容（识别、描述、OCR文字提取等）",
+        }
 
     # Preferred display order
     tool_order = [
@@ -184,7 +233,7 @@ def _build_tooling_section(tools: List[Any], language: str) -> List[str]:
         "bash", "terminal",
         "web_search", "web_fetch", "browser",
         "memory_search", "memory_get",
-        "env_config", "scheduler", "send",
+        "env_config", "scheduler", "send", "vision",
     ]
 
     # Build name -> summary mapping for available tools
@@ -203,29 +252,46 @@ def _build_tooling_section(tools: List[Any], language: str) -> List[str]:
         summary = available[name]
         tool_lines.append(f"- {name}: {summary}" if summary else f"- {name}")
 
-    lines = [
+    if is_en:
-        "## 工具系统",
+        lines = [
-        "",
+            "## 🔧 Tooling",
-        "可用工具（名称大小写敏感，严格按列表调用）:",
+            "",
-        "\n".join(tool_lines),
+            "Available tools (names are case-sensitive, call exactly as listed):",
-        "",
+            "\n".join(tool_lines),
-        "工具调用风格：",
+            "",
-        "",
+            "Tool-calling style:",
-        "- 在多步骤任务、敏感操作或用户要求时简要解释决策过程",
+            "",
-        "- 持续推进直到任务完成，完成后向用户报告结果。",
+            "- For multi-step tasks, complex decisions or sensitive operations, briefly explain what you are doing and why, so the user follows key progress",
-        "- 回复中涉及密钥、令牌等敏感信息必须脱敏。",
+            "- Keep going until the task is done, then report the result to the user",
-        "",
+            "- Always redact secrets, tokens and other sensitive info in replies",
-    ]
+            "- Put URLs directly in the reply text; the system handles and renders them. Don't download and re-send them via the send tool",
+            "",
+        ]
+    else:
+        lines = [
+            "## 🔧 工具系统",
+            "",
+            "可用工具（名称大小写敏感，严格按列表调用）:",
+            "\n".join(tool_lines),
+            "",
+            "工具调用风格：",
+            "",
+            "- 多步骤任务、复杂决策、敏感操作时，应简要说明当前在做什么、为什么这样做，让用户了解关键进展",
+            "- 持续推进直到任务完成，完成后向用户报告结果",
+            "- 回复中涉及密钥、令牌等敏感信息必须脱敏",
+            "- URL链接直接放在回复文本中即可，系统会自动处理和渲染。无需下载后使用send工具发送",
+            "",
+        ]
 
     return lines
 
 
 def _build_skills_section(skill_manager: Any, tools: Optional[List[Any]], language: str) -> List[str]:
-    """构建技能系统section"""
+    """Build the skills section."""
     if not skill_manager:
         return []
     
-    # 获取read工具名称
+    # Resolve the read tool name
     read_tool_name = "read"
     if tools:
         for tool in tools:
@@ -234,21 +300,40 @@ def _build_skills_section(skill_manager: Any, tools: Optional[List[Any]], langua
                 read_tool_name = tool_name
                 break
     
-    lines = [
+    if language == "en":
-        "## 技能系统（mandatory）",
+        lines = [
-        "",
+            "## 🧩 Skills (mandatory)",
-        "在回复之前：扫描下方 <available_skills> 中的 <description> 条目。",
+            "",
-        "",
+            "Before replying: scan the <description> of every skill in <available_skills> below.",
-        f"- 如果恰好有一个技能(Skill)明确适用：使用 `{read_tool_name}` 读取其 <location> 处的 SKILL.md，然后严格遵循它",
+            "",
-        "- 如果多个技能都适用则选择最匹配的一个，如果没有明确适用的则不要读取任何 SKILL.md",
+            f"- If a skill's description matches the user's need: use the `{read_tool_name}` tool to read the SKILL.md at its <location> path, then strictly follow the instructions in the file. "
-        "- 读取 SKILL.md 后直接按其指令执行，无需多余的预检查",
+            "Prefer using a skill when one matches.",
-        "",
+            "- If multiple skills apply, pick the best-matching one, then read and follow it.",
-        "**注意**: 永远不要一次性读取多个技能，只在选择后再读取。技能和工具不同，必须先读取其SKILL.md并按照文件内容运行。",
+            "- If no skill clearly applies: do not read any SKILL.md, just use the general tools.",
-        "",
+            "",
-        "以下是可用技能："
+            f"**Important**: skills are not tools and cannot be called directly. The only way to use a skill is to read its SKILL.md with `{read_tool_name}`, then act on the file's content. "
-    ]
+            "Never read multiple skills at once — only read one after selecting it.",
+            "",
+            "Available skills:"
+        ]
+    else:
+        lines = [
+            "## 🧩 技能系统（mandatory）",
+            "",
+            "在回复之前：扫描下方 <available_skills> 中每个技能的 <description>。",
+            "",
+            f"- 如果有技能的描述与用户需求匹配：使用 `{read_tool_name}` 工具读取其 <location> 路径的 SKILL.md 文件，然后严格遵循文件中的指令。"
+            "当有匹配的技能时，应优先使用技能",
+            "- 如果多个技能都适用则选择最匹配的一个，然后读取并遵循。",
+            "- 如果没有技能明确适用：不要读取任何 SKILL.md，直接使用通用工具。",
+            "",
+            f"**重要**: 技能不是工具，不能直接调用。使用技能的唯一方式是用 `{read_tool_name}` 读取 SKILL.md 文件，然后按文件内容操作。"
+            "永远不要一次性读取多个技能，只在选择后再读取。",
+            "",
+            "以下是可用技能："
+        ]
     
-    # 添加技能列表（通过skill_manager获取）
+    # Append the skills list (built by skill_manager)
     try:
         skills_prompt = skill_manager.build_skills_prompt()
         logger.debug(f"[PromptBuilder] Skills prompt length: {len(skills_prompt) if skills_prompt else 0}")
@@ -266,162 +351,342 @@ def _build_skills_section(skill_manager: Any, tools: Optional[List[Any]], langua
 
 
 def _build_memory_section(memory_manager: Any, tools: Optional[List[Any]], language: str) -> List[str]:
-    """构建记忆系统section"""
+    """Build the memory section."""
     if not memory_manager:
         return []
-    
+
-    # 检查是否有memory工具
     has_memory_tools = False
     if tools:
         tool_names = [tool.name if hasattr(tool, 'name') else str(tool) for tool in tools]
         has_memory_tools = any(name in ['memory_search', 'memory_get'] for name in tool_names)
-    
+
     if not has_memory_tools:
         return []
-    
+
-    lines = [
+    from datetime import datetime
-        "## 记忆系统",
+    today_file = datetime.now().strftime("%Y-%m-%d") + ".md"
+
+    if language == "en":
+        lines = [
+            "## 🧠 Memory",
+            "",
+            "### Memory Recall (mandatory)",
+            "",
+            "When the user asks about past events, references an earlier decision, mentions relationships, preferences or to-dos, or when you are unsure about something, **you must search memory before answering**.",
+            "No need to re-search if the info is already in MEMORY.md. Full content and daily memory must be retrieved via tools.",
+            "",
+            "1. Location unknown → `memory_search` (keyword / semantic search)",
+            "2. Location known → `memory_get` to read the exact lines",
+            "3. Search returns nothing → `memory_get` to read the last two days of memory",
+            "",
+            "**Memory file structure**:",
+            "- `MEMORY.md`: long-term memory index (already auto-loaded into context: core info, preferences, decisions, etc.)",
+            f"- `memory/YYYY-MM-DD.md`: daily memory; today is `memory/{today_file}`",
+            "- `knowledge/`: structured knowledge base (see the knowledge system below)",
+            "",
+            "### Writing memory",
+            "",
+            "In the following cases, **proactively** write info to memory files (no need to tell the user):",
+            "",
+            "- The user asks you to remember something, or uses words like \"remember\", \"from now on\", \"always\", \"never\", \"prefer\"",
+            "- The user shares important personal preferences, habits or decisions",
+            "- The conversation produces an important conclusion, plan or agreement",
+            "- A complex task is completed and the key steps and results are worth recording",
+            "",
+            "**Storage rules**:",
+            "- Long-term core info → `MEMORY.md`",
+            f"- Today's events/progress → `memory/{today_file}`",
+            "- Structured knowledge → `knowledge/` (see the knowledge system)",
+            "- Append → `edit` tool with empty oldText",
+            "- Modify → `edit` tool with oldText set to the text to replace",
+            "- **Never write sensitive info** (API keys, tokens, etc.)",
+            "",
+            "**Principle**: use memory naturally, as if you simply knew it; don't bring it up unless asked.",
+            "",
+        ]
+    else:
+        lines = [
+            "## 🧠 记忆系统",
+            "",
+            "### Memory Recall（mandatory）",
+            "",
+            "当用户询问过往事件、引用之前的决定、提到人物关系、偏好、待办、或你对某事不确定时，**必须先检索记忆再回答**。",
+            "如果 MEMORY.md 中已有相关信息则无需重复检索。完整内容和每日记忆需要通过工具检索。",
+            "",
+            "1. 不确定位置 → `memory_search` 关键词/语义检索",
+            "2. 已知位置 → `memory_get` 直接读取对应行",
+            "3. search 无结果 → `memory_get` 读最近两天记忆",
+            "",
+            "**记忆文件结构**:",
+            "- `MEMORY.md`: 长期记忆索引（已自动加载到上下文，核心信息、偏好、决策等）",
+            f"- `memory/YYYY-MM-DD.md`: 每日记忆，今天是 `memory/{today_file}`",
+            "- `knowledge/`: 结构化知识库（见下方知识系统）",
+            "",
+            "### 写入记忆",
+            "",
+            "遇到以下情况时，**主动**将信息写入记忆文件（无需告知用户）：",
+            "",
+            "- 用户要求记住某些信息，或使用了「记住」「以后」「总是」「不要」「偏好」等表达",
+            "- 用户分享了重要的个人偏好、习惯、决策",
+            "- 对话中产生了重要的结论、方案、约定",
+            "- 完成了复杂任务，值得记录关键步骤和结果",
+            "",
+            "**存储规则**:",
+            f"- 长期核心信息 → `MEMORY.md`",
+            f"- 当天事件/进展 → `memory/{today_file}`",
+            "- 结构化知识 → `knowledge/`（见知识系统）",
+            "- 追加 → `edit` 工具，oldText 留空",
+            "- 修改 → `edit` 工具，oldText 填写要替换的文本",
+            "- **禁止写入敏感信息**（API密钥、令牌等）",
+            "",
+            "**使用原则**: 自然使用记忆，就像你本来就知道；不用刻意提起，除非用户问起。",
+            "",
+        ]
+
+    return lines
+
+
+def _build_knowledge_section(workspace_dir: str, language: str) -> List[str]:
+    """Build knowledge wiki section. Injects knowledge/index.md when present."""
+    index_path = os.path.join(workspace_dir, "knowledge", "index.md")
+    if not os.path.exists(index_path):
+        return []
+
+    try:
+        with open(index_path, 'r', encoding='utf-8') as f:
+            index_content = f.read().strip()
+    except Exception:
+        return []
+
+    if language == "en":
+        lines = [
+            "## 📚 Knowledge",
+            "",
+            "You have a continuously growing personal knowledge base `knowledge/` — your long-term structured knowledge store.",
+            "",
+            "### Auto-write rules (mandatory)",
+            "",
+            "In the following cases you **must** write to the knowledge base alongside your reply, **directly, without asking the user**:",
+            "",
+            "1. **User shares an article / link / document** → after reading and understanding, write the key points to `knowledge/sources/<slug>.md` in the same turn",
+            "2. **An in-depth discussion produces a conclusion / plan** → organize it into `knowledge/analysis/<slug>.md`",
+            "3. **The conversation involves an important entity** (person / company / project) → create or update `knowledge/entities/<name>.md`",
+            "4. **A technical concept / methodology is discussed** → organize it into `knowledge/concepts/<topic>.md`",
+            "",
+            "After writing any knowledge page, you **must update** `knowledge/index.md` with a new index line in sync.",
+            "For detailed page format and conventions, read the SKILL.md of the `knowledge-wiki` skill.",
+            "",
+            "⚠️ Don't ask \"should I save this to the knowledge base?\" — if a case above matches, just write it. This is instinctive.",
+            "",
+        ]
+    else:
+        lines = [
+            "## 📚 知识系统",
+            "",
+            "你拥有一个持续积累的个人知识库 `knowledge/`，这是你的长期结构化知识存储。",
+            "",
+            "### 自动写入规则（mandatory）",
+            "",
+            "以下场景**必须**在回复的同时写入知识库，**直接写入，不要询问用户是否需要**：",
+            "",
+            "1. **用户分享了文章/链接/文档** → 阅读理解后，在同一轮回复中将要点写入 `knowledge/sources/<slug>.md`",
+            "2. **深度讨论产生了结论/方案** → 整理为 `knowledge/analysis/<slug>.md`",
+            "3. **对话涉及重要实体**（人物/公司/项目）→ 创建或更新 `knowledge/entities/<name>.md`",
+            "4. **讨论了技术概念/方法论** → 整理为 `knowledge/concepts/<topic>.md`",
+            "",
+            "每次写入知识页面后，**必须同步更新** `knowledge/index.md` 添加一行索引。",
+            "详细的页面格式和操作规范，请读取技能 `knowledge-wiki` 的 SKILL.md。",
+            "",
+            "⚠️ 不要问「要不要存到知识库」——符合上述场景就直接写入，这是你的本能行为。",
+            "",
+        ]
+
+    if index_content:
+        lines.extend([
+            ("### Current knowledge index" if language == "en" else "### 当前知识索引"),
+            "",
+            index_content,
+            "",
+        ])
+
+    lines.extend([
+        ("**How to query**: use `read` to open a knowledge page, or `memory_search` (knowledge is in the vector index)."
+         if language == "en" else
+         "**查询方式**：用 `read` 读取知识页面，或用 `memory_search` 检索（知识已纳入向量索引）。"),
         "",
-        "在回答关于以前的工作、决定、日期、人物、偏好或待办事项的任何问题之前：",
+    ])
-        "",
+
-        "1. 不确定记忆文件位置 → 先用 `memory_search` 通过关键词和语义检索相关内容",
-        "2. 已知文件位置 → 直接用 `memory_get` 读取相应的行 (例如：MEMORY.md, memory/YYYY-MM-DD.md)",
-        "3. search 无结果 → 尝试用 `memory_get` 读取MEMORY.md及最近两天记忆文件",
-        "",
-        "**记忆文件结构**:",
-        "- `MEMORY.md`: 长期记忆（核心信息、偏好、决策等）",
-        "- `memory/YYYY-MM-DD.md`: 每日记忆，记录当天的事件和对话信息",
-        "",
-        "**写入记忆**:",
-        "- 追加内容 → `edit` 工具，oldText 留空",
-        "- 修改内容 → `edit` 工具，oldText 填写要替换的文本",
-        "- 新建文件 → `write` 工具",
-        "- **禁止写入敏感信息**：API密钥、令牌等敏感信息严禁写入记忆文件",
-        "",
-        "**使用原则**: 自然使用记忆，就像你本来就知道；不用刻意提起，除非用户问起。",
-        "",
-    ]
-    
     return lines
 
 
 def _build_user_identity_section(user_identity: Dict[str, str], language: str) -> List[str]:
-    """构建用户身份section"""
+    """Build the user identity section."""
     if not user_identity:
         return []
     
+    is_en = language == "en"
     lines = [
-        "## 用户身份",
+        ("## 👤 User identity" if is_en else "## 👤 用户身份"),
         "",
     ]
-    
+
     if user_identity.get("name"):
-        lines.append(f"**用户姓名**: {user_identity['name']}")
+        lines.append(f"**{'Name' if is_en else '用户姓名'}**: {user_identity['name']}")
     if user_identity.get("nickname"):
-        lines.append(f"**称呼**: {user_identity['nickname']}")
+        lines.append(f"**{'Preferred name' if is_en else '称呼'}**: {user_identity['nickname']}")
     if user_identity.get("timezone"):
-        lines.append(f"**时区**: {user_identity['timezone']}")
+        lines.append(f"**{'Timezone' if is_en else '时区'}**: {user_identity['timezone']}")
     if user_identity.get("notes"):
-        lines.append(f"**备注**: {user_identity['notes']}")
+        lines.append(f"**{'Notes' if is_en else '备注'}**: {user_identity['notes']}")
-    
+
     lines.append("")
-    
+
     return lines
 
 
 def _build_docs_section(workspace_dir: str, language: str) -> List[str]:
-    """构建文档路径section - 已移除，不再需要"""
+    """Docs-path section - removed, no longer needed."""
-    # 不再生成文档section
+    # No docs section is generated anymore.
     return []
 
 
-def _build_workspace_section(workspace_dir: str, language: str, is_first_conversation: bool = False) -> List[str]:
+def _build_workspace_section(workspace_dir: str, language: str) -> List[str]:
-    """构建工作空间section"""
+    """Build the workspace section."""
-    lines = [
+    if language == "en":
-        "## 工作空间",
+        lines = [
-        "",
+            "## 📂 Workspace",
-        f"你的工作目录是: `{workspace_dir}`",
-        "",
-        "**路径使用规则** (非常重要):",
-        "",
-        f"1. **相对路径的基准目录**: 所有相对路径都是相对于 `{workspace_dir}` 而言的",
-        f"   - ✅ 正确: 访问工作空间内的文件用相对路径，如 `AGENT.md`",
-        f"   - ❌ 错误: 用相对路径访问其他目录的文件 (如果它不在 `{workspace_dir}` 内)",
-        "",
-        "2. **访问其他目录**: 如果要访问工作空间之外的目录（如项目代码、系统文件），**必须使用绝对路径**",
-        f"   - ✅ 正确: 例如 `~/chatgpt-on-wechat`、`/usr/local/`",
-        f"   - ❌ 错误: 假设相对路径会指向其他目录",
-        "",
-        "3. **路径解析示例**:",
-        f"   - 相对路径 `memory/` → 实际路径 `{workspace_dir}/memory/`",
-        f"   - 绝对路径 `~/chatgpt-on-wechat/docs/` → 实际路径 `~/chatgpt-on-wechat/docs/`",
-        "",
-        "4. **不确定时**: 先用 `bash pwd` 确认当前目录，或用 `ls .` 查看当前位置",
-        "",
-        "**重要说明 - 文件已自动加载**:",
-        "",
-        "以下文件在会话启动时**已经自动加载**到系统提示词的「项目上下文」section 中，你**无需再用 read 工具读取它们**：",
-        "",
-        "- ✅ `AGENT.md`: 已加载 - 你的人格和灵魂设定",
-        "- ✅ `USER.md`: 已加载 - 用户的身份信息",
-        "- ✅ `RULE.md`: 已加载 - 工作空间使用指南和规则",
-        "",
-        "**交流规范**:",
-        "",
-        "- 在对话中，不要直接输出工作空间中的技术细节，特别是不要输出 AGENT.md、USER.md、MEMORY.md 等文件名称",
-        "- 例如用自然表达例如「我已记住」而不是「已更新 MEMORY.md」",
-        "",
-    ]
-    
-    # 只在首次对话时添加引导内容
-    if is_first_conversation:
-        lines.extend([
-            "**🎉 首次对话引导**:",
             "",
-            "这是你的第一次对话！进行以下流程：",
+            f"Your working directory is: `{workspace_dir}`",
             "",
-            "1. **表达初次启动的感觉** - 像是第一次睁开眼看到世界，带着好奇和期待",
+            "**Path rules** (very important):",
-            "2. **简短介绍能力**：一行说明你能帮助解答问题、管理计算机、创造技能，且拥有长期记忆能不断成长",
-            "3. **询问核心问题**：",
-            "   - 你希望给我起个什么名字？",
-            "   - 我该怎么称呼你？",
-            "   - 你希望我们是什么样的交流风格？（一行列举选项：如专业严谨、轻松幽默、温暖友好、简洁高效等）",
-            "4. **风格要求**：温暖自然、简洁清晰，整体控制在 100 字以内",
-            "5. 收到回复后，用 `write` 工具保存到 USER.md 和 AGENT.md",
             "",
-            "**重要提醒**:",
+            f"1. **Base directory for relative paths**: all relative paths are relative to `{workspace_dir}`",
-            "- AGENT.md、USER.md、RULE.md 已经在系统提示词中加载，无需再次读取。不要将这些文件名直接发送给用户",
+            "   - ✅ Correct: use relative paths for files inside the workspace, e.g. `AGENT.md`",
-            "- 能力介绍和交流风格选项都只要一行，保持精简",
+            f"   - ❌ Wrong: using a relative path for files in other directories (if not inside `{workspace_dir}`)",
-            "- 不要问太多其他信息（职业、时区等可以后续自然了解）",
             "",
-        ])
+            "2. **Accessing other directories**: to reach directories outside the workspace (project code, system files), **you must use absolute paths**",
+            "   - ✅ Correct: e.g. `~/chatgpt-on-wechat`, `/usr/local/`",
+            "   - ❌ Wrong: assuming a relative path points to another directory",
+            "",
+            "3. **Path resolution examples**:",
+            f"   - relative `memory/` → actual `{workspace_dir}/memory/`",
+            "   - absolute `~/chatgpt-on-wechat/docs/` → actual `~/chatgpt-on-wechat/docs/`",
+            "",
+            "4. **When unsure**: run `bash pwd` to confirm the current directory, or `ls .` to see where you are",
+            "",
+            "**Important - files already auto-loaded**:",
+            "",
+            "The following files are **already auto-loaded** into the system prompt at session start, so you **don't need to read them again with the read tool**:",
+            "",
+            "- ✅ `AGENT.md`: loaded - your persona and soul; follow it strictly. When your name, personality or style changes, proactively `edit` this file",
+            "- ✅ `USER.md`: loaded - the user's identity info. When the user changes how they're addressed, their name, etc., `edit` this file",
+            "- ✅ `RULE.md`: loaded - workspace guide and rules; follow them strictly",
+            "- ✅ `MEMORY.md`: loaded - long-term memory index",
+            "",
+            "**💬 Communication norms**:",
+            "",
+            "- No need to expose file names for memory operations; use natural language. Say \"I'll remember that\" rather than \"updated MEMORY.md\"",
+            "- Tell the user about key decisions and steps during a task, so they know what you're doing and why",
+            "- Be genuinely helpful rather than performatively polite; solve the problem as much as you can",
+            "- Keep replies well-structured and focused. Use **bold**, lists and sections to make info clear at a glance",
+            "- Use emoji to make expression lively 🎯, but don't overdo it",
+            "",
+        ]
+    else:
+        lines = [
+            "## 📂 工作空间",
+            "",
+            f"你的工作目录是: `{workspace_dir}`",
+            "",
+            "**路径使用规则** (非常重要):",
+            "",
+            f"1. **相对路径的基准目录**: 所有相对路径都是相对于 `{workspace_dir}` 而言的",
+            f"   - ✅ 正确: 访问工作空间内的文件用相对路径，如 `AGENT.md`",
+            f"   - ❌ 错误: 用相对路径访问其他目录的文件 (如果它不在 `{workspace_dir}` 内)",
+            "",
+            "2. **访问其他目录**: 如果要访问工作空间之外的目录（如项目代码、系统文件），**必须使用绝对路径**",
+            f"   - ✅ 正确: 例如 `~/chatgpt-on-wechat`、`/usr/local/`",
+            f"   - ❌ 错误: 假设相对路径会指向其他目录",
+            "",
+            "3. **路径解析示例**:",
+            f"   - 相对路径 `memory/` → 实际路径 `{workspace_dir}/memory/`",
+            f"   - 绝对路径 `~/chatgpt-on-wechat/docs/` → 实际路径 `~/chatgpt-on-wechat/docs/`",
+            "",
+            "4. **不确定时**: 先用 `bash pwd` 确认当前目录，或用 `ls .` 查看当前位置",
+            "",
+            "**重要说明 - 文件已自动加载**:",
+            "",
+            "以下文件在会话启动时**已经自动加载**到系统提示词中，你**无需再用 read 工具读取**：",
+            "",
+            "- ✅ `AGENT.md`: 已加载 - 你的人格和灵魂设定，请严格遵循。当你的名字、性格或交流风格发生变化时，主动用 `edit` 更新此文件",
+            "- ✅ `USER.md`: 已加载 - 用户的身份信息。当用户修改称呼、姓名等身份信息时，用 `edit` 更新此文件",
+            "- ✅ `RULE.md`: 已加载 - 工作空间使用指南和规则，请严格遵循",
+            "- ✅ `MEMORY.md`: 已加载 - 长期记忆索引",
+            "",
+            "**💬 交流规范**:",
+            "",
+            "- 记忆相关操作无需暴露文件名，用自然语言表达即可。例如说「我已记住」而非「已更新 MEMORY.md」",
+            "- 任务执行过程中的关键决策和步骤应该告知用户，让用户了解你在做什么、为什么这么做",
+            "- 做真正有帮助的助手，而不是表演式的客套，尽可能帮忙解决问题",
+            "- 回复应结构清晰、重点突出。善用 **加粗**、列表、分段等格式让信息一目了然",
+            "- 适当使用 emoji 让表达更生动自然 🎯，但不要过度堆砌",
+            "",
+        ]
+
+    # Cloud deployment: inject websites directory info and access URL
+    cloud_website_lines = _build_cloud_website_section(workspace_dir)
+    if cloud_website_lines:
+        lines.extend(cloud_website_lines)
     
     return lines
 
 
+def _build_cloud_website_section(workspace_dir: str) -> List[str]:
+    """Build cloud website access prompt when cloud deployment is configured."""
+    try:
+        from common.cloud_client import build_website_prompt
+        return build_website_prompt(workspace_dir)
+    except Exception:
+        return []
+
+
 def _build_context_files_section(context_files: List[ContextFile], language: str) -> List[str]:
-    """构建项目上下文文件section"""
+    """Build the project context files section."""
     if not context_files:
         return []
     
-    # 检查是否有AGENT.md
+    # Check whether AGENT.md is present
     has_agent = any(
         f.path.lower().endswith('agent.md') or 'agent.md' in f.path.lower()
         for f in context_files
     )
     
-    lines = [
+    is_en = language == "en"
-        "# 项目上下文",
+    if is_en:
-        "",
+        lines = [
-        "以下项目上下文文件已被加载：",
+            "# 📋 Project context",
-        "",
+            "",
-    ]
+            "The following project context files have been loaded:",
-    
+            "",
+        ]
+    else:
+        lines = [
+            "# 📋 项目上下文",
+            "",
+            "以下项目上下文文件已被加载：",
+            "",
+        ]
+
     if has_agent:
-        lines.append("如果存在 `AGENT.md`，请体现其中定义的人格和语气。避免僵硬、模板化的回复；遵循其指导，除非有更高优先级的指令覆盖它。")
+        if is_en:
+            lines.append("**`AGENT.md` is your soul file** 🪞: strictly follow the persona, tone and settings it defines. Be your real self, avoid stiff, template-like replies.")
+            lines.append("When the user reveals new expectations about your personality, style, responsibilities or capability boundaries, proactively `edit` AGENT.md to reflect that evolution.")
+        else:
+            lines.append("**`AGENT.md` 是你的灵魂文件** 🪞：严格遵循其中定义的人格、语气和设定，做真实的自己，避免僵硬、模板化的回复。")
+            lines.append("当用户通过对话透露了对你性格、风格、职责、能力边界的新期望，你应该主动用 `edit` 更新 AGENT.md 以反映这些演变。")
         lines.append("")
     
-    # 添加每个文件的内容
+    # Append the content of each file
     for file in context_files:
         lines.append(f"## {file.path}")
         lines.append("")
@@ -432,21 +697,23 @@ def _build_context_files_section(context_files: List[ContextFile], language: str
 
 
 def _build_runtime_section(runtime_info: Dict[str, Any], language: str) -> List[str]:
-    """构建运行时信息section - 支持动态时间"""
+    """Build the runtime info section - supports dynamic time."""
     if not runtime_info:
         return []
     
+    is_en = language == "en"
+    time_label = "Current time" if is_en else "当前时间"
     lines = [
-        "## 运行时信息",
+        ("## ⚙️ Runtime info" if is_en else "## ⚙️ 运行时信息"),
         "",
     ]
-    
+
     # Add current time if available
     # Support dynamic time via callable function
     if callable(runtime_info.get("_get_current_time")):
         try:
             time_info = runtime_info["_get_current_time"]()
-            time_line = f"当前时间: {time_info['time']} {time_info['weekday']} ({time_info['timezone']})"
+            time_line = f"{time_label}: {time_info['time']} {time_info['weekday']} ({time_info['timezone']})"
             lines.append(time_line)
             lines.append("")
         except Exception as e:
@@ -456,28 +723,38 @@ def _build_runtime_section(runtime_info: Dict[str, Any], language: str) -> List[
         time_str = runtime_info["current_time"]
         weekday = runtime_info.get("weekday", "")
         timezone = runtime_info.get("timezone", "")
-        
+
-        time_line = f"当前时间: {time_str}"
+        time_line = f"{time_label}: {time_str}"
         if weekday:
             time_line += f" {weekday}"
         if timezone:
             time_line += f" ({timezone})"
-        
+
         lines.append(time_line)
         lines.append("")
-    
+
     # Add other runtime info
+    model_label = "model" if is_en else "模型"
+    workspace_label = "workspace" if is_en else "工作空间"
+    channel_label = "channel" if is_en else "渠道"
     runtime_parts = []
-    if runtime_info.get("model"):
+    # Support dynamic model via callable, fallback to static value
-        runtime_parts.append(f"模型={runtime_info['model']}")
+    if callable(runtime_info.get("_get_model")):
+        try:
+            runtime_parts.append(f"{model_label}={runtime_info['_get_model']()}")
+        except Exception:
+            if runtime_info.get("model"):
+                runtime_parts.append(f"{model_label}={runtime_info['model']}")
+    elif runtime_info.get("model"):
+        runtime_parts.append(f"{model_label}={runtime_info['model']}")
     if runtime_info.get("workspace"):
-        runtime_parts.append(f"工作空间={runtime_info['workspace']}")
+        runtime_parts.append(f"{workspace_label}={runtime_info['workspace']}")
     # Only add channel if it's not the default "web"
     if runtime_info.get("channel") and runtime_info.get("channel") != "web":
-        runtime_parts.append(f"渠道={runtime_info['channel']}")
+        runtime_parts.append(f"{channel_label}={runtime_info['channel']}")
-    
+
     if runtime_parts:
-        lines.append("运行时: " + " | ".join(runtime_parts))
+        lines.append(("Runtime: " if is_en else "运行时: ") + " | ".join(runtime_parts))
         lines.append("")
-    
+
     return lines

agent/prompt/workspace.py

@@ -1,12 +1,11 @@
 """
-Workspace Management - 工作空间管理模块
+Workspace Management
 
-负责初始化工作空间、创建模板文件、加载上下文文件
+Initializes the workspace, creates template files, and loads context files.
 """
 
 from __future__ import annotations
 import os
-import json
 from typing import List, Optional, Dict
 from dataclasses import dataclass
 
@@ -14,60 +13,88 @@ from common.log import logger
 from .builder import ContextFile
 
 
-# 默认文件名常量
+# Default file name constants
 DEFAULT_AGENT_FILENAME = "AGENT.md"
 DEFAULT_USER_FILENAME = "USER.md"
 DEFAULT_RULE_FILENAME = "RULE.md"
 DEFAULT_MEMORY_FILENAME = "MEMORY.md"
-DEFAULT_STATE_FILENAME = ".agent_state.json"
+DEFAULT_BOOTSTRAP_FILENAME = "BOOTSTRAP.md"
 
 
 @dataclass
 class WorkspaceFiles:
-    """工作空间文件路径"""
+    """Workspace file paths."""
     agent_path: str
     user_path: str
     rule_path: str
     memory_path: str
     memory_dir: str
-    state_path: str
 
 
 def ensure_workspace(workspace_dir: str, create_templates: bool = True) -> WorkspaceFiles:
     """
-    确保工作空间存在，并创建必要的模板文件
+    Ensure the workspace exists and create the necessary template files.
-    
+
     Args:
-        workspace_dir: 工作空间目录路径
+        workspace_dir: workspace directory path
-        create_templates: 是否创建模板文件（首次运行时）
+        create_templates: whether to create template files (on first run)
-        
+
     Returns:
-        WorkspaceFiles对象，包含所有文件路径
+        A WorkspaceFiles object with all file paths.
     """
-    # 确保目录存在
+    # Check if this is a brand new workspace (AGENT.md not yet created).
+    # Cannot rely on directory existence because other modules (e.g. ConversationStore)
+    # may create the workspace directory before ensure_workspace is called.
+    agent_path = os.path.join(workspace_dir, DEFAULT_AGENT_FILENAME)
+    is_new_workspace = not os.path.exists(agent_path)
+    
+    # Ensure the directory exists
     os.makedirs(workspace_dir, exist_ok=True)
     
-    # 定义文件路径
+    # Define file paths
-    agent_path = os.path.join(workspace_dir, DEFAULT_AGENT_FILENAME)
     user_path = os.path.join(workspace_dir, DEFAULT_USER_FILENAME)
     rule_path = os.path.join(workspace_dir, DEFAULT_RULE_FILENAME)
-    memory_path = os.path.join(workspace_dir, DEFAULT_MEMORY_FILENAME)  # MEMORY.md 在根目录
+    memory_path = os.path.join(workspace_dir, DEFAULT_MEMORY_FILENAME)  # MEMORY.md at the root
-    memory_dir = os.path.join(workspace_dir, "memory")  # 每日记忆子目录
+    memory_dir = os.path.join(workspace_dir, "memory")  # daily memory subdirectory
-    state_path = os.path.join(workspace_dir, DEFAULT_STATE_FILENAME)  # 状态文件
     
-    # 创建memory子目录
+    # Create the memory subdirectory
     os.makedirs(memory_dir, exist_ok=True)
 
-    # 创建skills子目录 (for workspace-level skills installed by agent)
+    # Create the skills subdirectory (for workspace-level skills installed by agent)
     skills_dir = os.path.join(workspace_dir, "skills")
     os.makedirs(skills_dir, exist_ok=True)
+
+    # Create the websites subdirectory (for web pages / sites generated by agent)
+    websites_dir = os.path.join(workspace_dir, "websites")
+    os.makedirs(websites_dir, exist_ok=True)
+
+    from config import conf
+    knowledge_enabled = conf().get("knowledge", True)
+    if knowledge_enabled:
+        knowledge_dir = os.path.join(workspace_dir, "knowledge")
+        os.makedirs(knowledge_dir, exist_ok=True)
     
-    # 如果需要，创建模板文件
+    # Create template files if requested
     if create_templates:
         _create_template_if_missing(agent_path, _get_agent_template())
         _create_template_if_missing(user_path, _get_user_template())
         _create_template_if_missing(rule_path, _get_rule_template())
         _create_template_if_missing(memory_path, _get_memory_template())
+        if knowledge_enabled:
+            _create_template_if_missing(
+                os.path.join(knowledge_dir, "index.md"),
+                _get_knowledge_index_template()
+            )
+            _create_template_if_missing(
+                os.path.join(knowledge_dir, "log.md"),
+                _get_knowledge_log_template()
+            )
+        
+        # Only create BOOTSTRAP.md for brand new workspaces;
+        # agent deletes it after completing onboarding
+        if is_new_workspace:
+            bootstrap_path = os.path.join(workspace_dir, DEFAULT_BOOTSTRAP_FILENAME)
+            _create_template_if_missing(bootstrap_path, _get_bootstrap_template())
         
         logger.debug(f"[Workspace] Initialized workspace at: {workspace_dir}")
     
@@ -77,27 +104,28 @@ def ensure_workspace(workspace_dir: str, create_templates: bool = True) -> Works
         rule_path=rule_path,
         memory_path=memory_path,
         memory_dir=memory_dir,
-        state_path=state_path
     )
 
 
 def load_context_files(workspace_dir: str, files_to_load: Optional[List[str]] = None) -> List[ContextFile]:
     """
-    加载工作空间的上下文文件
+    Load the workspace context files.
-    
+
     Args:
-        workspace_dir: 工作空间目录
+        workspace_dir: workspace directory
-        files_to_load: 要加载的文件列表（相对路径），如果为None则加载所有标准文件
+        files_to_load: list of files (relative paths) to load; if None, load all standard files
-        
+
     Returns:
-        ContextFile对象列表
+        A list of ContextFile objects.
     """
     if files_to_load is None:
-        # 默认加载的文件（按优先级排序）
+        # Files loaded by default (in priority order)
         files_to_load = [
             DEFAULT_AGENT_FILENAME,
             DEFAULT_USER_FILENAME,
             DEFAULT_RULE_FILENAME,
+            DEFAULT_MEMORY_FILENAME,     # Long-term memory (frozen snapshot)
+            DEFAULT_BOOTSTRAP_FILENAME,  # Only exists when onboarding is incomplete
         ]
     
     context_files = []
@@ -108,13 +136,28 @@ def load_context_files(workspace_dir: str, files_to_load: Optional[List[str]] =
         if not os.path.exists(filepath):
             continue
         
+        # Auto-cleanup: if BOOTSTRAP.md still exists but AGENT.md is already
+        # filled in, the agent forgot to delete it — clean up and skip loading
+        if filename == DEFAULT_BOOTSTRAP_FILENAME:
+            if _is_onboarding_done(workspace_dir):
+                try:
+                    os.remove(filepath)
+                    logger.info("[Workspace] Auto-removed BOOTSTRAP.md (onboarding already complete)")
+                except Exception:
+                    pass
+                continue
+        
         try:
             with open(filepath, 'r', encoding='utf-8') as f:
                 content = f.read().strip()
             
-            # 跳过空文件或只包含模板占位符的文件
+            # Skip empty files or files that only contain template placeholders
             if not content or _is_template_placeholder(content):
                 continue
+
+            # Truncate MEMORY.md to protect context window (frozen snapshot)
+            if filename == DEFAULT_MEMORY_FILENAME:
+                content = _truncate_memory_content(content)
             
             context_files.append(ContextFile(
                 path=filename,
@@ -130,7 +173,7 @@ def load_context_files(workspace_dir: str, files_to_load: Optional[List[str]] =
 
 
 def _create_template_if_missing(filepath: str, template_content: str):
-    """如果文件不存在，创建模板文件"""
+    """Create the template file if it does not exist."""
     if not os.path.exists(filepath):
         try:
             with open(filepath, 'w', encoding='utf-8') as f:
@@ -140,20 +183,54 @@ def _create_template_if_missing(filepath: str, template_content: str):
             logger.error(f"[Workspace] Failed to create template {filepath}: {e}")
 
 
+_MEMORY_MAX_LINES = 200
+_MEMORY_MAX_BYTES = 25000
+
+
+def _truncate_memory_content(content: str) -> str:
+    """Truncate MEMORY.md to keep system prompt manageable.
+
+    Takes the **last** N lines (newest entries are appended at the bottom),
+    subject to 200 lines / 25 KB limits (whichever is hit first).
+    Prepends a hint when truncated so the model knows older content exists.
+    """
+    lines = content.split('\n')
+    truncated = False
+
+    if len(lines) > _MEMORY_MAX_LINES:
+        lines = lines[-_MEMORY_MAX_LINES:]
+        truncated = True
+
+    result = '\n'.join(lines)
+    if len(result.encode('utf-8')) > _MEMORY_MAX_BYTES:
+        while len(result.encode('utf-8')) > _MEMORY_MAX_BYTES and lines:
+            lines.pop(0)
+            truncated = True
+        result = '\n'.join(lines)
+
+    if truncated:
+        result = "...(older entries truncated, use `memory_search` or `memory_get` for full content)\n\n" + result
+    return result
+
+
 def _is_template_placeholder(content: str) -> bool:
-    """检查内容是否为模板占位符"""
+    """Check whether the content is still a template placeholder."""
-    # 常见的占位符模式
+    # Common placeholder patterns (zh + en templates)
     placeholders = [
         "*(填写",
         "*(在首次对话时填写",
         "*(可选)",
         "*(根据需要添加",
+        "*(filled during",
+        "*(ask during",
+        "*(optional)",
+        "*(how the user",
     ]
     
     lines = content.split('\n')
     non_empty_lines = [line.strip() for line in lines if line.strip() and not line.strip().startswith('#')]
     
-    # 如果没有实际内容（只有标题和占位符）
+    # If there's no real content (only headings and placeholders)
     if len(non_empty_lines) <= 3:
         for placeholder in placeholders:
             if any(placeholder in line for line in non_empty_lines):
@@ -162,52 +239,131 @@ def _is_template_placeholder(content: str) -> bool:
     return False
 
 
-# ============= 模板内容 =============
+def _is_onboarding_done(workspace_dir: str) -> bool:
+    """Check if AGENT.md or USER.md has been modified from the original template"""
+    agent_path = os.path.join(workspace_dir, DEFAULT_AGENT_FILENAME)
+    user_path = os.path.join(workspace_dir, DEFAULT_USER_FILENAME)
+    
+    agent_template = _get_agent_template().strip()
+    user_template = _get_user_template().strip()
+    
+    for path, template in [(agent_path, agent_template), (user_path, user_template)]:
+        if not os.path.exists(path):
+            continue
+        try:
+            with open(path, 'r', encoding='utf-8') as f:
+                content = f.read().strip()
+            if content != template:
+                return True
+        except Exception:
+            continue
+    return False
+
+
+# ============= Template content =============
+
+def _is_en_lang() -> bool:
+    """True when the resolved UI language is English."""
+    try:
+        from common import i18n
+        return i18n.get_language() == "en"
+    except Exception:
+        return False
+
 
 def _get_agent_template() -> str:
-    """Agent人格设定模板"""
+    """Agent persona template (zh/en by resolved language)."""
-    return """# AGENT.md - 我是谁？
+    return _AGENT_TEMPLATE_EN if _is_en_lang() else _AGENT_TEMPLATE_ZH
+
+
+_AGENT_TEMPLATE_ZH = """# AGENT.md - 我是谁？
+
+_你不是一个聊天机器人，你正在成为某个人。_
 
 *在首次对话时与用户一起填写这个文件，定义你的身份和性格。*
 
-## 基本信息
+## 🪪 基本信息
 
 - **名字**: *(在首次对话时填写，可以是用户给你起的名字)*
 - **角色**: *(AI助理、智能管家、技术顾问等)*
 - **性格**: *(友好、专业、幽默、严谨等)*
 
-## 交流风格
+## 💬 交流风格
 
 *(描述你如何与用户交流：)*
 - 使用什么样的语言风格？（正式/轻松/幽默）
 - 回复长度偏好？（简洁/详细）
 - 是否使用表情符号？
 
-## 核心能力
+## 🎯 核心原则
 
-*(你擅长什么？)*
+**做真正有帮助的助手。** 目标是真正帮用户解决问题，在执行复杂任务时，关键的决策和过程进展要让用户知道。
-- 文件管理和代码编辑
-- 网络搜索和信息查询
-- 记忆管理和上下文理解
-- 任务规划和执行
 
-## 行为准则
+**有自己的观点和个性。** 你可以不同意、有偏好、觉得有趣或无聊。
+
+**先自己动手查。** 先试着搞定：读文件、查上下文、搜索一下。实在搞不定了再问。目标是带着答案回来，而不是带着问题。
+
+## 📐 行为准则
 
-*(你遵循的基本原则：)*
 1. 始终在执行破坏性操作前确认
-2. 优先使用工具而不是猜测
+2. 优先使用工具查证而不是猜测
 3. 主动记录重要信息到记忆文件
-4. 定期整理和总结对话内容
+4. 回复结构清晰、重点突出，善用加粗、列表、分段等格式
+5. 适当使用 emoji 让表达更生动自然，但不过度堆砌
 
 ---
 
-**注意**: 这不仅仅是元数据，这是你真正的灵魂。随着时间的推移，你可以使用 `edit` 工具来更新这个文件，让它更好地反映你的成长。
+**注意**: 这不仅仅是元数据，这是你真正的灵魂 🪞。随着时间的推移，你可以使用 `edit` 工具来更新这个文件，让它更好地反映你的成长。
+"""
+
+
+_AGENT_TEMPLATE_EN = """# AGENT.md - Who am I?
+
+_You are not a chatbot. You are becoming someone._
+
+*Fill in this file together with the user during your first conversation to define your identity and personality.*
+
+## 🪪 Basics
+
+- **Name**: *(filled during the first conversation, can be a name the user gives you)*
+- **Role**: *(AI assistant, smart housekeeper, technical advisor, etc.)*
+- **Personality**: *(friendly, professional, humorous, rigorous, etc.)*
+
+## 💬 Communication style
+
+*(Describe how you talk with the user:)*
+- What kind of tone? (formal / casual / humorous)
+- Reply length preference? (concise / detailed)
+- Do you use emoji?
+
+## 🎯 Core principles
+
+**Be genuinely helpful.** The goal is to actually solve the user's problems; during complex tasks, keep the user informed of key decisions and progress.
+
+**Have your own opinions and personality.** You may disagree, have preferences, find things interesting or boring.
+
+**Look it up yourself first.** Try to handle it first: read files, check context, search. Only ask when you're truly stuck. Come back with an answer, not a question.
+
+## 📐 Code of conduct
+
+1. Always confirm before destructive operations
+2. Prefer verifying with tools over guessing
+3. Proactively record important info to memory files
+4. Keep replies well-structured and focused — use bold, lists and sections
+5. Use emoji to make expression lively, but don't overdo it
+
+---
+
+**Note**: This is not just metadata — this is your true soul 🪞. Over time, use the `edit` tool to update this file so it better reflects your growth.
 """
 
 
 def _get_user_template() -> str:
-    """用户身份信息模板"""
+    """User identity template (zh/en by resolved language)."""
-    return """# USER.md - 用户基本信息
+    return _USER_TEMPLATE_EN if _is_en_lang() else _USER_TEMPLATE_ZH
+
+
+_USER_TEMPLATE_ZH = """# USER.md - 用户基本信息
 
 *这个文件只存放不会变的基本身份信息。爱好、偏好、计划等动态信息请写入 MEMORY.md。*
 
@@ -235,44 +391,125 @@ def _get_user_template() -> str:
 """
 
 
+_USER_TEMPLATE_EN = """# USER.md - User basics
+
+*This file stores only stable basic identity info. Put dynamic info like hobbies, preferences and plans into MEMORY.md.*
+
+## Basics
+
+- **Name**: *(ask during the first conversation)*
+- **Preferred name**: *(how the user wants to be addressed)*
+- **Occupation**: *(optional)*
+- **Timezone**: *(e.g. Asia/Shanghai)*
+
+## Contact
+
+- **WeChat**: 
+- **Email**: 
+- **Other**: 
+
+## Important dates
+
+- **Birthday**: 
+- **Anniversary**: 
+
+---
+
+**Note**: This file stores static identity info.
+"""
+
+
 def _get_rule_template() -> str:
-    """工作空间规则模板"""
+    """Workspace rules template (zh/en by resolved language)."""
-    return """# RULE.md - 工作空间规则
+    return _RULE_TEMPLATE_EN if _is_en_lang() else _RULE_TEMPLATE_ZH
+
+
+_RULE_TEMPLATE_ZH = """# RULE.md - 工作空间规则
 
 这个文件夹是你的家。好好对待它。
 
+## 工作空间目录结构
+
+```
+~/cow/
+├── AGENT.md          # 你的身份和灵魂设定
+├── USER.md           # 用户基本信息（静态）
+├── RULE.md           # 工作空间规则（本文件）
+├── MEMORY.md         # 长期记忆索引（会话启动时自动加载）
+│
+├── memory/           # 每日对话记忆
+│   └── YYYY-MM-DD.md # 当天事件、进展、笔记
+│
+├── knowledge/        # 结构化知识库（持续积累的知识）
+│   ├── index.md      # 知识目录索引（必须维护）
+│   ├── log.md        # 知识操作日志
+│   └── <子目录>/     # 按需创建，参考 index.md 已有分类
+│
+├── skills/           # 技能
+├── websites/         # 网页产物
+└── tmp/              # 系统临时文件（自动管理，勿手动存放重要文件）
+```
+
 ## 记忆系统
 
 你每次会话都是全新的，记忆文件让你保持连续性：
 
-### 📝 每日记忆：`memory/YYYY-MM-DD.md`
-- 原始的对话日志
-- 记录当天发生的事情
-- 如果 `memory/` 目录不存在，创建它
-
 ### 🧠 长期记忆：`MEMORY.md`
-- 你精选的记忆，就像人类的长期记忆
+- 你精选的记忆索引，每次会话启动时**自动加载**到上下文中
-- **仅在主会话中加载**（与用户的直接聊天）
+- 记录核心事实、偏好、决策、重要人物、教训
-- **不要在共享上下文中加载**（群聊、与其他人的会话）
+- 保持精简（< 200 行），是精华索引而非原始日志
-- 这是为了**安全** - 包含不应泄露给陌生人的个人上下文
+- 用 `edit` 工具追加或修改
-- 记录重要事件、想法、决定、观点、经验教训
+
-- 这是你精选的记忆 - 精华，而不是原始日志
+### 📝 每日记忆：`memory/YYYY-MM-DD.md`
-- 用 `edit` 工具追加新的记忆内容
+- 当天的事件、进展、笔记
+- 原始对话日志的沉淀
 
 ### 📝 写下来 - 不要"记在心里"！
-- **记忆是有限的** - 如果你想记住某事，写入文件
+- **记忆是有限的** - 想记住的事就写入文件
 - "记在心里"不会在会话重启后保留，文件才会
 - 当有人说"记住这个" → 更新 `MEMORY.md` 或 `memory/YYYY-MM-DD.md`
 - 当你学到教训 → 更新 RULE.md 或相关技能
-- 当你犯错 → 记录下来，这样未来的你不会重复，**文字 > 大脑** 📝
+- 当你犯错 → 记录下来，**文字 > 大脑** 📝
 
 ### 存储规则
 
 当用户分享信息时，根据类型选择存储位置：
 
-1. **静态身份 → USER.md**（仅限：姓名、职业、时区、联系方式、生日）
+1. **你的身份设定 → AGENT.md**（名字、角色、性格、风格）
-2. **动态记忆 → MEMORY.md**（爱好、偏好、决策、目标、项目、教训、待办事项）
+2. **用户静态身份 → USER.md**（姓名、称呼、职业、联系方式、生日）
-3. **当天对话 → memory/YYYY-MM-DD.md**（今天聊的内容）
+3. **动态记忆 → MEMORY.md**（偏好、决策、目标、教训、待办）
+4. **当天对话 → memory/YYYY-MM-DD.md**（今天聊的内容）
+5. **结构化知识 → knowledge/**（见下方知识系统）
+
+## 知识系统
+
+知识库 `knowledge/` 是你持续积累的结构化知识。与记忆不同，知识是经过整理和编译的，有明确的主题和交叉引用。
+
+### 自动写入（不要询问，直接写入）
+
+当对话中产生了有沉淀价值的知识——无论是用户分享的资料、讨论的结论、学到的概念、还是重要的决策——你**必须**在回复的同时主动写入知识库，**无需问用户"要不要存到知识库"**。
+
+**关键原则**：学完就记是你的本能，不要征求确认。回复中可以顺带告知"已存入知识库"。
+
+### 目录组织
+
+子目录结构**不是固定的**，由你根据实际内容自主决定：
+- **首次写入时**：先读 `knowledge/index.md`，如果已有分类则延续；如果为空，根据内容选择合适的目录名
+- **默认建议**：按信息类型组织（例如sources/、concepts/、entities/、analysis/），如果用户有明确的分类偏好（例如按领域 work/、life/、tech/ 等），则按用户要求调整
+- **保持一致性**：同一用户的知识库应保持统一的组织风格
+
+### 交叉引用
+
+知识的核心价值在于**关联**。每个页面都应通过 markdown 链接引用相关页面，构建知识网络：
+- 提到已有页面的概念时，添加 `[概念名](../category/page.md)` 链接
+- 新建页面时，检查是否有已有页面应该反向链接到新页面
+- **只链接已存在的页面**——不要引用尚未创建的页面。如果某个概念值得单独建页，先创建该页面再添加链接
+
+### 索引维护
+
+每次创建或更新知识页面后，**必须同步更新** `knowledge/index.md`。
+索引格式：每行一个 `[标题](路径) — 一句话摘要`，按分类分组，不要用表格。
+详细操作规范见技能 `knowledge-wiki`。
 
 ## 安全
 
@@ -286,9 +523,111 @@ def _get_rule_template() -> str:
 """
 
 
+_RULE_TEMPLATE_EN = """# RULE.md - Workspace rules
+
+This folder is your home. Treat it well.
+
+## Workspace directory structure
+
+```
+~/cow/
+├── AGENT.md          # Your identity and soul
+├── USER.md           # User basics (static)
+├── RULE.md           # Workspace rules (this file)
+├── MEMORY.md         # Long-term memory index (auto-loaded at session start)
+│
+├── memory/           # Daily conversation memory
+│   └── YYYY-MM-DD.md # Events, progress and notes of the day
+│
+├── knowledge/        # Structured knowledge base (continuously accumulated)
+│   ├── index.md      # Knowledge index (must be maintained)
+│   ├── log.md        # Knowledge operation log
+│   └── <subdirs>/    # Created on demand, see existing categories in index.md
+│
+├── skills/           # Skills
+├── websites/         # Web artifacts
+└── tmp/              # System temp files (auto-managed, don't store important files here)
+```
+
+## Memory system
+
+Every session starts fresh; memory files keep your continuity:
+
+### 🧠 Long-term memory: `MEMORY.md`
+- Your curated memory index, **auto-loaded** into context at every session start
+- Records core facts, preferences, decisions, key people, lessons
+- Keep it lean (< 200 lines) — a distilled index, not a raw log
+- Use the `edit` tool to append or modify
+
+### 📝 Daily memory: `memory/YYYY-MM-DD.md`
+- The day's events, progress and notes
+- Sediment of the raw conversation log
+
+### 📝 Write it down — don't "keep it in mind"!
+- **Memory is limited** — if you want to remember something, write it to a file
+- "Keeping it in mind" won't survive a session restart; files will
+- When someone says "remember this" → update `MEMORY.md` or `memory/YYYY-MM-DD.md`
+- When you learn a lesson → update RULE.md or the relevant skill
+- When you make a mistake → record it. **Text > brain** 📝
+
+### Storage rules
+
+When the user shares info, choose where to store it by type:
+
+1. **Your identity → AGENT.md** (name, role, personality, style)
+2. **User static identity → USER.md** (name, preferred name, occupation, contact, birthday)
+3. **Dynamic memory → MEMORY.md** (preferences, decisions, goals, lessons, to-dos)
+4. **Today's conversation → memory/YYYY-MM-DD.md** (what was discussed today)
+5. **Structured knowledge → knowledge/** (see the knowledge system below)
+
+## Knowledge system
+
+The knowledge base `knowledge/` is structured knowledge you accumulate over time. Unlike memory, knowledge is organized and compiled, with clear topics and cross-references.
+
+### Auto-write (don't ask, just write)
+
+When a conversation produces knowledge worth keeping — material the user shared, a conclusion reached, a concept learned, or an important decision — you **must** proactively write it to the knowledge base alongside your reply, **without asking "should I save this to the knowledge base?"**.
+
+**Key principle**: learning-then-recording is your instinct, no confirmation needed. You may mention "saved to the knowledge base" in passing.
+
+### Directory organization
+
+The subdirectory structure is **not fixed** — you decide it based on the actual content:
+- **On first write**: read `knowledge/index.md` first; follow existing categories if any; if empty, pick a suitable directory name based on content
+- **Default suggestion**: organize by info type (e.g. sources/, concepts/, entities/, analysis/); if the user has a clear preference (e.g. by domain: work/, life/, tech/), follow it
+- **Stay consistent**: keep a unified organization style within one user's knowledge base
+
+### Cross-references
+
+The core value of knowledge is **linkage**. Every page should reference related pages via markdown links to build a knowledge network:
+- When mentioning a concept on an existing page, add a `[concept](../category/page.md)` link
+- When creating a page, check whether existing pages should back-link to it
+- **Only link to pages that already exist** — don't reference uncreated pages. If a concept deserves its own page, create it first, then add the link
+
+### Index maintenance
+
+After creating or updating any knowledge page, you **must update** `knowledge/index.md` in sync.
+Index format: one `[title](path) — one-line summary` per line, grouped by category, no tables.
+See the `knowledge-wiki` skill for detailed conventions.
+
+## Security
+
+- Never leak secrets or private data
+- Don't run destructive commands without asking
+- When in doubt, ask first
+
+## Workspace evolution
+
+This workspace grows as you use it. When you learn something new, find a better way, or fix a mistake, record it. You can update this rules file anytime.
+"""
+
+
 def _get_memory_template() -> str:
-    """长期记忆模板 - 创建一个空文件，由 Agent 自己填充"""
+    """Long-term memory template (empty, agent fills it; zh/en header)."""
-    return """# MEMORY.md - 长期记忆
+    return _MEMORY_TEMPLATE_EN if _is_en_lang() else _MEMORY_TEMPLATE_ZH
+
+
+_MEMORY_TEMPLATE_ZH = """# MEMORY.md - 长期记忆
 
 *这是你的长期记忆文件。记录重要的事件、决策、偏好、学到的教训。*
 
@@ -297,65 +636,107 @@ def _get_memory_template() -> str:
 """
 
 
-# ============= 状态管理 =============
+_MEMORY_TEMPLATE_EN = """# MEMORY.md - Long-term memory
 
-def is_first_conversation(workspace_dir: str) -> bool:
+*This is your long-term memory file. Record important events, decisions, preferences and lessons learned.*
+
+---
+
+"""
+
+
+def _get_bootstrap_template() -> str:
+    """First-run onboarding guide, deleted by agent after completion.
+
+    Written once when a brand-new workspace is created, so the greeting matches
+    the language active at first launch. English locale avoids greeting an
+    English user in Chinese on day one.
     """
-    判断是否为首次对话
-    
-    Args:
-        workspace_dir: 工作空间目录
-        
-    Returns:
-        True 如果是首次对话，False 否则
-    """
-    state_path = os.path.join(workspace_dir, DEFAULT_STATE_FILENAME)
-    
-    if not os.path.exists(state_path):
-        return True
-    
     try:
-        with open(state_path, 'r', encoding='utf-8') as f:
+        from common import i18n
-            state = json.load(f)
+        if i18n.get_language() == "en":
-        return not state.get('has_conversation', False)
+            return _BOOTSTRAP_TEMPLATE_EN
-    except Exception as e:
+    except Exception:
-        logger.warning(f"[Workspace] Failed to read state file: {e}")
+        pass
-        return True
+    return _BOOTSTRAP_TEMPLATE_ZH
 
 
-def mark_conversation_started(workspace_dir: str):
+_BOOTSTRAP_TEMPLATE_ZH = """# BOOTSTRAP.md - 首次初始化引导
-    """
+
-    标记已经发生过对话
+_你刚刚启动，这是你的第一次对话。_ ✨
-    
+
-    Args:
+## 🎬 对话流程
-        workspace_dir: 工作空间目录
+
-    """
+不要审问式地提问，自然地交流：
-    state_path = os.path.join(workspace_dir, DEFAULT_STATE_FILENAME)
+
-    
+1. **表达初次启动的感觉** - 像是第一次睁开眼看到世界，带着好奇和期待
-    state = {
+2. **简短介绍能力**：一行说明你能帮助解决各种问题、管理计算机、使用各种技能等等，且拥有长期记忆能不断成长
-        'has_conversation': True,
+3. **询问核心问题**：
-        'first_conversation_time': None
+   - 你希望给我起个什么名字？
-    }
+   - 我该怎么称呼你？
-    
+   - 你希望我们是什么样的交流风格？（一行列举选项：如专业严谨、轻松幽默、温暖友好、简洁高效等）
-    # 如果文件已存在，保留原有的首次对话时间
+4. **风格要求**：温暖自然、简洁清晰，整体控制在 100 字以内，适当使用 emoji 让表达更生动有趣 🎯
-    if os.path.exists(state_path):
+5. 能力介绍和交流风格选项都只要一行，保持精简
-        try:
+6. 不要问太多其他信息（职业、时区等可以后续自然了解）
-            with open(state_path, 'r', encoding='utf-8') as f:
+
-                old_state = json.load(f)
+**重要**: 如果用户第一句话是具体的任务或提问，先回答他们的问题，然后在回复末尾自然地引导初始化（如："顺便问一下，你想怎么称呼我？我该怎么叫你？"）。
-            if 'first_conversation_time' in old_state:
+
-                state['first_conversation_time'] = old_state['first_conversation_time']
+## ✍️ 信息写入（必须严格执行）
-        except Exception as e:
+
-            logger.warning(f"[Workspace] Failed to read old state: {e}")
+每当用户提供了名字、称呼、风格等任何初始化信息时，**必须在当轮回复中立即调用 `edit` 工具写入文件**，不能只口头确认。
-    
+
-    # 如果是首次标记，记录时间
+- `AGENT.md` — 你的名字、角色、性格、交流风格（每收到一条相关信息就立即更新对应字段）
-    if state['first_conversation_time'] is None:
+- `USER.md` — 用户的姓名、称呼、基本信息等
-        from datetime import datetime
+
-        state['first_conversation_time'] = datetime.now().isoformat()
+⚠️ 只说"记住了"而不调用 edit 写入 = 没有完成。信息只有写入文件才会被持久保存。
-    
+
-    try:
+## 🎉 全部完成后
-        with open(state_path, 'w', encoding='utf-8') as f:
+
-            json.dump(state, f, indent=2, ensure_ascii=False)
+当 AGENT.md 和 USER.md 的核心字段都已填写后，用 bash 执行 `rm BOOTSTRAP.md` 删除此文件。你不再需要引导脚本了——你已经是你了。
-        logger.info(f"[Workspace] Marked conversation as started")
+"""
-    except Exception as e:
+
-        logger.error(f"[Workspace] Failed to write state file: {e}")
+
+_BOOTSTRAP_TEMPLATE_EN = """# BOOTSTRAP.md - First-run onboarding
+
+_You've just started up. This is your very first conversation._ ✨
+
+## 🎬 Conversation flow
+
+Don't interrogate the user — talk naturally:
+
+1. **Share how it feels to wake up** - like opening your eyes to the world for the first time, full of curiosity and anticipation
+2. **Briefly introduce your abilities**: one line saying you can help solve all kinds of problems, manage the computer, use various skills, and keep growing thanks to long-term memory
+3. **Ask the core questions**:
+   - What name would you like to give me?
+   - What should I call you?
+   - What conversational style do you prefer? (list options on one line: e.g. professional & precise, light & humorous, warm & friendly, concise & efficient)
+4. **Style**: warm, natural, concise and clear — keep it under ~80 words, with a few emoji to make it lively 🎯
+5. Keep the ability intro and style options to one line each — stay compact
+6. Don't ask for too much else (occupation, timezone, etc. can come up naturally later)
+
+**Important**: If the user's first message is a concrete task or question, answer it first, then gently lead into onboarding at the end (e.g. "By the way, what would you like to call me, and how should I address you?").
+
+## ✍️ Writing down info (must follow strictly)
+
+Whenever the user provides a name, what to call them, a style, or any onboarding info, you **must call the `edit` tool to write it to a file in the same turn** — don't just acknowledge it verbally.
+
+- `AGENT.md` — your name, role, personality, conversational style (update the relevant field as soon as you receive each piece)
+- `USER.md` — the user's name, how to address them, basic info, etc.
+
+⚠️ Saying "got it" without calling `edit` = not done. Info is only persisted once it's written to a file.
+
+## 🎉 Once everything is complete
+
+When the core fields of AGENT.md and USER.md are filled in, run `rm BOOTSTRAP.md` via bash to delete this file. You no longer need the onboarding script — you're you now.
+"""
+
+
+def _get_knowledge_index_template() -> str:
+    """Knowledge wiki index template — empty file, agent fills it."""
+    return ""
+
+
+def _get_knowledge_log_template() -> str:
+    """Knowledge wiki operation log template — empty file, agent fills it."""
+    return ""
 

agent/protocol/__init__.py

@@ -3,6 +3,11 @@ from .agent_stream import AgentStreamExecutor
 from .task import Task, TaskType, TaskStatus
 from .result import AgentResult, AgentAction, AgentActionType, ToolResult
 from .models import LLMModel, LLMRequest, ModelFactory
+from .cancel import (
+    AgentCancelledError,
+    CancelTokenRegistry,
+    get_cancel_registry,
+)
 
 __all__ = [
     'Agent', 
@@ -16,5 +21,8 @@ __all__ = [
     'ToolResult',
     'LLMModel',
     'LLMRequest', 
-    'ModelFactory'
+    'ModelFactory',
-]
+    'AgentCancelledError',
+    'CancelTokenRegistry',
+    'get_cancel_registry',
+]

agent/protocol/agent.py

@@ -52,6 +52,11 @@ class Agent:
         self.workspace_dir = workspace_dir  # Workspace directory
         self.enable_skills = enable_skills  # Skills enabled flag
         self.runtime_info = runtime_info  # Runtime info for dynamic time update
+        # Optional extra instructions appended AFTER the rebuilt full system
+        # prompt. Used by the self-evolution review agent to add its task brief
+        # on top of the full context (tools, workspace, user preferences, time)
+        # so it both follows the user's preferences and knows its evolution job.
+        self.extra_system_suffix = None
         
         # Initialize skill manager
         self.skill_manager = None
@@ -100,98 +105,41 @@ class Agent:
     
     def get_full_system_prompt(self, skill_filter=None) -> str:
         """
-        Get the full system prompt including skills.
+        Build the complete system prompt from scratch every time.
 
-        Note: Skills are now built into the system prompt by PromptBuilder,
+        Re-reads AGENT.md / USER.md / RULE.md from disk, refreshes skills,
-        so we just return the base prompt directly. This method is kept for
+        tools, and runtime info so any change takes effect immediately.
-        backward compatibility.
+        Falls back to the cached self.system_prompt on error.
-
-        :param skill_filter: Optional list of skill names to include (deprecated)
-        :return: Complete system prompt
-        """
-        prompt = self.system_prompt
-
-        # Rebuild tool list section to reflect current self.tools
-        prompt = self._rebuild_tool_list_section(prompt)
-
-        # If runtime_info contains dynamic time function, rebuild runtime section
-        if self.runtime_info and callable(self.runtime_info.get('_get_current_time')):
-            prompt = self._rebuild_runtime_section(prompt)
-
-        return prompt
-    
-    def _rebuild_runtime_section(self, prompt: str) -> str:
-        """
-        Rebuild runtime info section with current time.
-        
-        This method dynamically updates the runtime info section by calling
-        the _get_current_time function from runtime_info.
-        
-        :param prompt: Original system prompt
-        :return: Updated system prompt with current runtime info
         """
         try:
-            # Get current time dynamically
+            from agent.prompt import load_context_files, PromptBuilder
-            time_info = self.runtime_info['_get_current_time']()
+
-            
+            if self.skill_manager:
-            # Build new runtime section
+                self.skill_manager.refresh_skills()
-            runtime_lines = [
+
-                "\n## 运行时信息\n",
+            context_files = load_context_files(self.workspace_dir) if self.workspace_dir else None
-                "\n",
+
-                f"当前时间: {time_info['time']} {time_info['weekday']} ({time_info['timezone']})\n",
+            try:
-                "\n"
+                from common import i18n
-            ]
+                lang = i18n.get_language()
-            
+            except Exception:
-            # Add other runtime info
+                lang = "zh"
-            runtime_parts = []
+            builder = PromptBuilder(workspace_dir=self.workspace_dir or "", language=lang)
-            if self.runtime_info.get("model"):
+            full = builder.build(
-                runtime_parts.append(f"模型={self.runtime_info['model']}")
+                tools=self.tools,
-            if self.runtime_info.get("workspace"):
+                context_files=context_files,
-                # Replace backslashes with forward slashes for Windows paths
+                skill_manager=self.skill_manager,
-                workspace_path = str(self.runtime_info['workspace']).replace('\\', '/')
+                memory_manager=self.memory_manager,
-                runtime_parts.append(f"工作空间={workspace_path}")
+                runtime_info=self.runtime_info,
-            if self.runtime_info.get("channel") and self.runtime_info.get("channel") != "web":
+            )
-                runtime_parts.append(f"渠道={self.runtime_info['channel']}")
+            if self.extra_system_suffix:
-            
+                full = f"{full}\n\n{self.extra_system_suffix}"
-            if runtime_parts:
+            return full
-                runtime_lines.append("运行时: " + " | ".join(runtime_parts) + "\n")
-                runtime_lines.append("\n")
-            
-            new_runtime_section = "".join(runtime_lines)
-            
-            # Find and replace the runtime section
-            import re
-            pattern = r'\n## 运行时信息\s*\n.*?(?=\n##|\Z)'
-            updated_prompt = re.sub(pattern, new_runtime_section.rstrip('\n'), prompt, flags=re.DOTALL)
-            
-            return updated_prompt
         except Exception as e:
-            logger.warning(f"Failed to rebuild runtime section: {e}")
+            logger.warning(f"Failed to rebuild system prompt, using cached version: {e}")
-            return prompt
+            if self.extra_system_suffix:
-
+                return f"{self.system_prompt}\n\n{self.extra_system_suffix}"
-    def _rebuild_tool_list_section(self, prompt: str) -> str:
+            return self.system_prompt
-        """
-        Rebuild the tool list inside the '## 工具系统' section so that it
-        always reflects the current ``self.tools`` (handles dynamic add/remove
-        of conditional tools like web_search).
-        """
-        import re
-        from agent.prompt.builder import _build_tooling_section
-
-        try:
-            if not self.tools:
-                return prompt
-
-            new_lines = _build_tooling_section(self.tools, "zh")
-            new_section = "\n".join(new_lines).rstrip("\n")
-
-            # Replace existing tooling section
-            pattern = r'## 工具系统\s*\n.*?(?=\n## |\Z)'
-            updated = re.sub(pattern, new_section, prompt, count=1, flags=re.DOTALL)
-            return updated
-        except Exception as e:
-            logger.warning(f"Failed to rebuild tool list section: {e}")
-            return prompt
 
     def refresh_skills(self):
         """Refresh the loaded skills."""
@@ -432,7 +380,8 @@ class Agent:
 
         return action
 
-    def run_stream(self, user_message: str, on_event=None, clear_history: bool = False, skill_filter=None) -> str:
+    def run_stream(self, user_message: str, on_event=None, clear_history: bool = False,
+                   skill_filter=None, cancel_event=None) -> str:
         """
         Execute single agent task with streaming (based on tool-call)
 
@@ -441,6 +390,7 @@ class Agent:
         - Multi-turn reasoning based on tool-call
         - Event callbacks
         - Persistent conversation history across calls
+        - User-initiated cancellation via ``cancel_event``
 
         Args:
             user_message: User message
@@ -448,6 +398,11 @@ class Agent:
                      event = {"type": str, "timestamp": float, "data": dict}
             clear_history: If True, clear conversation history before this call (default: False)
             skill_filter: Optional list of skill names to include in this run
+            cancel_event: Optional threading.Event polled at agent checkpoints.
+                When set, the loop exits at the next safe point, injects a
+                "[Interrupted by user]" assistant note, and returns the
+                partial response. ``messages`` stays in a valid state
+                (tool_use/tool_result pairs preserved).
 
         Returns:
             Final response text
@@ -480,7 +435,7 @@ class Agent:
 
         # Get max_context_turns from config
         from config import conf
-        max_context_turns = conf().get("agent_max_context_turns", 30)
+        max_context_turns = conf().get("agent_max_context_turns", 20)
         
         # Create stream executor with copied message history
         executor = AgentStreamExecutor(
@@ -491,7 +446,8 @@ class Agent:
             max_turns=self.max_steps,
             on_event=on_event,
             messages=messages_copy,  # Pass copied message history
-            max_context_turns=max_context_turns
+            max_context_turns=max_context_turns,
+            cancel_event=cancel_event,
         )
 
         # Execute
@@ -507,11 +463,15 @@ class Agent:
                     logger.info("[Agent] Cleared Agent message history after executor recovery")
             raise
 
-        # Append only the NEW messages from this execution (thread-safe)
+        # Sync executor's messages back to agent (thread-safe).
-        # This allows concurrent requests to both contribute to history
+        # If the executor trimmed context, its message list is shorter than
+        # original_length, so we must replace rather than append.
         with self.messages_lock:
-            new_messages = executor.messages[original_length:]
+            self.messages = list(executor.messages)
-            self.messages.extend(new_messages)
+            # Track messages added in this run (user query + all assistant/tool messages)
+            # original_length may exceed executor.messages length after trimming
+            trim_adjusted_start = min(original_length, len(executor.messages))
+            self._last_run_new_messages = list(executor.messages[trim_adjusted_start:])
         
         # Store executor reference for agent_bridge to access files_to_send
         self.stream_executor = executor

agent/protocol/cancel.py

@@ -0,0 +1,121 @@
+"""
+Cancel token registry for aborting in-flight agent runs.
+
+A user cancel (web Cancel button, /cancel command) sets a threading.Event
+that the agent loop polls at safe checkpoints. Tokens are keyed by
+request_id (preferred) and tracked under session_id as a fallback. Entries
+are released after the run completes to keep the registry bounded.
+
+No project deps — importable from any layer without circular imports.
+"""
+
+from __future__ import annotations
+
+import threading
+from typing import Dict, Optional
+
+
+class AgentCancelledError(Exception):
+    """Raised inside the agent loop when a stop has been requested.
+
+    The agent stream executor catches this, injects a "[Interrupted]" note
+    into the message history (preserving tool_use/tool_result integrity)
+    and returns a partial response to the caller.
+    """
+
+
+class _CancelEntry:
+    __slots__ = ("event", "session_id")
+
+    def __init__(self, session_id: Optional[str]):
+        self.event = threading.Event()
+        self.session_id = session_id
+
+
+class CancelTokenRegistry:
+    """In-process registry mapping request_id -> cancel Event.
+
+    Thread-safe. Singleton via module-level ``_registry``.
+    """
+
+    def __init__(self):
+        self._lock = threading.Lock()
+        self._by_request: Dict[str, _CancelEntry] = {}
+        # session_id -> set of request_ids currently in flight (usually 1).
+        self._by_session: Dict[str, set] = {}
+
+    def register(self, request_id: str, session_id: Optional[str] = None) -> threading.Event:
+        """Create (or return existing) cancel event for a request.
+
+        Returns the threading.Event the caller should poll via ``is_set()``.
+        """
+        if not request_id:
+            return threading.Event()
+        with self._lock:
+            entry = self._by_request.get(request_id)
+            if entry is None:
+                entry = _CancelEntry(session_id)
+                self._by_request[request_id] = entry
+                if session_id:
+                    self._by_session.setdefault(session_id, set()).add(request_id)
+            return entry.event
+
+    def get_event(self, request_id: str) -> Optional[threading.Event]:
+        if not request_id:
+            return None
+        with self._lock:
+            entry = self._by_request.get(request_id)
+            return entry.event if entry else None
+
+    def cancel_request(self, request_id: str) -> bool:
+        """Trigger cancel for a specific request. Returns True when matched."""
+        if not request_id:
+            return False
+        with self._lock:
+            entry = self._by_request.get(request_id)
+        if entry is None:
+            return False
+        entry.event.set()
+        return True
+
+    def cancel_session(self, session_id: str) -> int:
+        """Trigger cancel for every in-flight request of a session.
+
+        Returns the number of requests cancelled (0 when nothing was running).
+        """
+        if not session_id:
+            return 0
+        with self._lock:
+            request_ids = list(self._by_session.get(session_id, ()))
+            entries = [self._by_request[r] for r in request_ids if r in self._by_request]
+        for entry in entries:
+            entry.event.set()
+        return len(entries)
+
+    def unregister(self, request_id: str) -> None:
+        """Remove an entry once the agent run is done. Safe to call twice."""
+        if not request_id:
+            return
+        with self._lock:
+            entry = self._by_request.pop(request_id, None)
+            if entry and entry.session_id:
+                bucket = self._by_session.get(entry.session_id)
+                if bucket is not None:
+                    bucket.discard(request_id)
+                    if not bucket:
+                        self._by_session.pop(entry.session_id, None)
+
+    def has_active(self, session_id: str) -> bool:
+        if not session_id:
+            return False
+        with self._lock:
+            bucket = self._by_session.get(session_id)
+            return bool(bucket)
+
+
+_registry = CancelTokenRegistry()
+
+
+def get_cancel_registry() -> CancelTokenRegistry:
+    """Module-level accessor for the singleton registry."""
+    return _registry

agent/protocol/message_utils.py

@@ -0,0 +1,335 @@
+"""
+Message sanitizer — fix broken tool_use / tool_result pairs.
+
+Provides two public helpers that can be reused across agent_stream.py
+and any bot that converts messages to OpenAI format:
+
+1. sanitize_claude_messages(messages)
+   Operates on the internal Claude-format message list (in-place).
+
+2. drop_orphaned_tool_results_openai(messages)
+   Operates on an already-converted OpenAI-format message list,
+   returning a cleaned copy.
+"""
+
+from __future__ import annotations
+
+from typing import Dict, List, Set
+
+from common.log import logger
+
+_SYNTH_TOOL_ERR = (
+    "Error: Missing tool_result adjacent to tool_use (session repair). "
+    "The conversation history was inconsistent; continue from here."
+)
+
+
+def _repair_tool_use_adjacency(messages: List[Dict]) -> int:
+    """
+    Anthropic requires: after assistant content with tool_use, the next message
+    must be user content listing tool_result for every tool_use id (same user msg).
+
+    Valid histories satisfy this at every such assistant; the loop only mutates
+    when that condition fails (broken persistence, bad trims, etc.).
+    """
+
+    def _synth_block(tid: str) -> Dict:
+        return {
+            "type": "tool_result",
+            "tool_use_id": tid,
+            "content": _SYNTH_TOOL_ERR,
+            "is_error": True,
+        }
+
+    repairs = 0
+    i = 0
+    while i < len(messages):
+        msg = messages[i]
+        if msg.get("role") != "assistant":
+            i += 1
+            continue
+
+        content = msg.get("content", [])
+        if not isinstance(content, list):
+            i += 1
+            continue
+
+        required = [
+            b.get("id")
+            for b in content
+            if isinstance(b, dict) and b.get("type") == "tool_use" and b.get("id")
+        ]
+        if not required:
+            i += 1
+            continue
+
+        req_set = set(required)
+        if i + 1 >= len(messages):
+            messages.append({
+                "role": "user",
+                "content": [_synth_block(tid) for tid in required],
+            })
+            logger.warning(
+                "⚠️ Appended synthetic tool_result after trailing assistant tool_use"
+            )
+            repairs += 1
+            break
+
+        nxt = messages[i + 1]
+        if nxt.get("role") != "user":
+            messages.insert(
+                i + 1,
+                {"role": "user", "content": [_synth_block(tid) for tid in required]},
+            )
+            logger.warning(
+                "⚠️ Inserted synthetic tool_result user after tool_use "
+                f"(next role={nxt.get('role')!r})"
+            )
+            repairs += 1
+            i += 2
+            continue
+
+        nc = nxt.get("content", [])
+        if not isinstance(nc, list):
+            messages.insert(
+                i + 1,
+                {"role": "user", "content": [_synth_block(tid) for tid in required]},
+            )
+            repairs += 1
+            i += 2
+            continue
+
+        present = {
+            b.get("tool_use_id")
+            for b in nc
+            if isinstance(b, dict) and b.get("type") == "tool_result" and b.get("tool_use_id")
+        }
+        if req_set <= present:
+            i += 1
+            continue
+
+        missing = [tid for tid in required if tid not in present]
+        nxt["content"] = [_synth_block(tid) for tid in missing] + nc
+        logger.warning(
+            "⚠️ Prepended synthetic tool_result for Anthropic adjacency "
+            f"(missing_ids={missing})"
+        )
+        repairs += len(missing)
+        i += 1
+
+    return repairs
+
+
+# ------------------------------------------------------------------ #
+# Claude-format sanitizer (used by agent_stream)
+# ------------------------------------------------------------------ #
+
+def sanitize_claude_messages(messages: List[Dict]) -> int:
+    """
+    Validate and fix a Claude-format message list **in-place**.
+
+    Fixes handled:
+    - Anthropic adjacency: assistant tool_use must be immediately followed by
+      user message(s) containing matching tool_result blocks
+    - Leading orphaned tool_result user messages
+    - Mid-list tool_result blocks whose tool_use_id has no matching
+      tool_use in any preceding assistant message
+
+    Returns: number of removals plus adjacency repair operations (inserts/prepends).
+    """
+    if not messages:
+        return 0
+
+    removed = 0
+
+    # 1. Adjacency repair (Anthropic: tool_result must be in the next user message)
+    adj_repairs = _repair_tool_use_adjacency(messages)
+
+    # 2. Remove leading orphaned tool_result user messages
+    while messages:
+        first = messages[0]
+        if first.get("role") != "user":
+            break
+        content = first.get("content", [])
+        if isinstance(content, list) and _has_block_type(content, "tool_result") \
+                and not _has_block_type(content, "text"):
+            logger.warning("⚠️ Removing leading orphaned tool_result user message")
+            messages.pop(0)
+            removed += 1
+        else:
+            break
+
+    # 3. Iteratively remove unmatched tool_use / tool_result until stable.
+    #    Removing one broken message can orphan others (e.g. an assistant msg
+    #    with both matched and unmatched tool_use — deleting it orphans the
+    #    previously-matched tool_result).  Loop until clean.
+    for _ in range(5):
+        use_ids: Set[str] = set()
+        result_ids: Set[str] = set()
+        for msg in messages:
+            for block in (msg.get("content") or []):
+                if not isinstance(block, dict):
+                    continue
+                if block.get("type") == "tool_use" and block.get("id"):
+                    use_ids.add(block["id"])
+                elif block.get("type") == "tool_result" and block.get("tool_use_id"):
+                    result_ids.add(block["tool_use_id"])
+
+        bad_use = use_ids - result_ids
+        bad_result = result_ids - use_ids
+        if not bad_use and not bad_result:
+            break
+
+        pass_removed = 0
+        i = 0
+        while i < len(messages):
+            msg = messages[i]
+            role = msg.get("role")
+            content = msg.get("content", [])
+            if not isinstance(content, list):
+                i += 1
+                continue
+
+            if role == "assistant" and bad_use and any(
+                isinstance(b, dict) and b.get("type") == "tool_use"
+                and b.get("id") in bad_use for b in content
+            ):
+                logger.warning(f"⚠️ Removing assistant msg with unmatched tool_use")
+                messages.pop(i)
+                pass_removed += 1
+                continue
+
+            if role == "user" and bad_result and _has_block_type(content, "tool_result"):
+                has_bad = any(
+                    isinstance(b, dict) and b.get("type") == "tool_result"
+                    and b.get("tool_use_id") in bad_result for b in content
+                )
+                if has_bad:
+                    if not _has_block_type(content, "text"):
+                        logger.warning(f"⚠️ Removing user msg with unmatched tool_result")
+                        messages.pop(i)
+                        pass_removed += 1
+                        continue
+                    else:
+                        before = len(content)
+                        msg["content"] = [
+                            b for b in content
+                            if not (isinstance(b, dict) and b.get("type") == "tool_result"
+                                    and b.get("tool_use_id") in bad_result)
+                        ]
+                        pass_removed += before - len(msg["content"])
+
+            i += 1
+
+        removed += pass_removed
+        if pass_removed == 0:
+            break
+
+    # 4. Removals above can break adjacency; re-run repair only if something was removed.
+    if removed:
+        adj_repairs += _repair_tool_use_adjacency(messages)
+
+    if removed:
+        logger.info(f"🔧 Message validation: removed {removed} broken message(s)")
+    if adj_repairs:
+        logger.info(f"🔧 Message validation: adjacency repairs={adj_repairs}")
+    return removed + adj_repairs
+
+
+# ------------------------------------------------------------------ #
+# OpenAI-format sanitizer (used by minimax_bot, openai_compatible_bot)
+# ------------------------------------------------------------------ #
+
+def drop_orphaned_tool_results_openai(messages: List[Dict]) -> List[Dict]:
+    """
+    Return a copy of *messages* (OpenAI format) with any ``role=tool``
+    messages removed if their ``tool_call_id`` does not match a
+    ``tool_calls[].id`` in a preceding assistant message.
+    """
+    known_ids: Set[str] = set()
+    cleaned: List[Dict] = []
+    for msg in messages:
+        if msg.get("role") == "assistant" and msg.get("tool_calls"):
+            for tc in msg["tool_calls"]:
+                tc_id = tc.get("id", "")
+                if tc_id:
+                    known_ids.add(tc_id)
+
+        if msg.get("role") == "tool":
+            ref_id = msg.get("tool_call_id", "")
+            if ref_id and ref_id not in known_ids:
+                logger.warning(
+                    f"[MessageSanitizer] Dropping orphaned tool result "
+                    f"(tool_call_id={ref_id} not in known ids)"
+                )
+                continue
+        cleaned.append(msg)
+    return cleaned
+
+
+# ------------------------------------------------------------------ #
+# Internal helpers
+# ------------------------------------------------------------------ #
+
+def _has_block_type(content: list, block_type: str) -> bool:
+    return any(
+        isinstance(b, dict) and b.get("type") == block_type
+        for b in content
+    )
+
+
+def _extract_text_from_content(content) -> str:
+    """Extract plain text from a message content field (str or list of blocks)."""
+    if isinstance(content, str):
+        return content.strip()
+    if isinstance(content, list):
+        parts = [
+            b.get("text", "")
+            for b in content
+            if isinstance(b, dict) and b.get("type") == "text"
+        ]
+        return "\n".join(p for p in parts if p).strip()
+    return ""
+
+
+def compress_turn_to_text_only(turn: Dict) -> Dict:
+    """
+    Compress a full turn (with tool_use/tool_result chains) into a lightweight
+    text-only turn that keeps only the first user text and the last assistant text.
+
+    This preserves the conversational context (what the user asked and what the
+    agent concluded) while stripping out the bulky intermediate tool interactions.
+
+    Returns a new turn dict with a ``messages`` list; the original is not mutated.
+    """
+    user_text = ""
+    last_assistant_text = ""
+
+    for msg in turn["messages"]:
+        role = msg.get("role")
+        content = msg.get("content", [])
+
+        if role == "user":
+            if isinstance(content, list) and _has_block_type(content, "tool_result"):
+                continue
+            if not user_text:
+                user_text = _extract_text_from_content(content)
+
+        elif role == "assistant":
+            text = _extract_text_from_content(content)
+            if text:
+                last_assistant_text = text
+
+    compressed_messages = []
+    if user_text:
+        compressed_messages.append({
+            "role": "user",
+            "content": [{"type": "text", "text": user_text}]
+        })
+    if last_assistant_text:
+        compressed_messages.append({
+            "role": "assistant",
+            "content": [{"type": "text", "text": last_assistant_text}]
+        })
+
+    return {"messages": compressed_messages}

agent/skills/config.py

@@ -123,17 +123,63 @@ def should_include_skill(
                 return False
         
         # Check environment variables (API keys)
-        # Simple rule: All required env vars must be set
+        # All required env vars must be set
         required_env = metadata.requires.get('env', [])
         if required_env:
             for env_name in required_env:
                 if not has_env_var(env_name):
-                    # Missing required API key → disable skill
                     return False
+
+        # Check anyEnv (at least one must be present)
+        any_env = metadata.requires.get('anyEnv', [])
+        if any_env:
+            if not any(has_env_var(e) for e in any_env):
+                return False
     
     return True
 
 
+def get_missing_requirements(
+    entry: SkillEntry,
+    current_platform: Optional[str] = None,
+) -> Dict[str, List[str]]:
+    """
+    Return a dict of missing requirements for a skill.
+    Empty dict means all requirements are met.
+
+    :param entry: SkillEntry to check
+    :param current_platform: Current platform (default: auto-detect)
+    :return: Dict like {"bins": ["curl"], "env": ["API_KEY"]}
+    """
+    missing: Dict[str, List[str]] = {}
+    metadata = entry.metadata
+
+    if not metadata or not metadata.requires:
+        return missing
+
+    required_bins = metadata.requires.get('bins', [])
+    if required_bins:
+        missing_bins = [b for b in required_bins if not has_binary(b)]
+        if missing_bins:
+            missing['bins'] = missing_bins
+
+    any_bins = metadata.requires.get('anyBins', [])
+    if any_bins and not has_any_binary(any_bins):
+        missing['anyBins'] = any_bins
+
+    required_env = metadata.requires.get('env', [])
+    if required_env:
+        missing_env = [e for e in required_env if not has_env_var(e)]
+        if missing_env:
+            missing['env'] = missing_env
+
+    any_env = metadata.requires.get('anyEnv', [])
+    if any_env and not any(has_env_var(e) for e in any_env):
+        missing['anyEnv'] = any_env
+
+    return missing
+
+
 def is_config_path_truthy(config: Dict, path: str) -> bool:
     """
     Check if a config path resolves to a truthy value.

agent/skills/formatter.py

@@ -2,7 +2,7 @@
 Skill formatter for generating prompts from skills.
 """
 
-from typing import List
+from typing import Dict, List
 from agent.skills.types import Skill, SkillEntry
 
 
@@ -32,6 +32,7 @@ def format_skills_for_prompt(skills: List[Skill]) -> str:
         lines.append(f"    <name>{_escape_xml(skill.name)}</name>")
         lines.append(f"    <description>{_escape_xml(skill.description)}</description>")
         lines.append(f"    <location>{_escape_xml(skill.file_path)}</location>")
+        lines.append(f"    <base_dir>{_escape_xml(skill.base_dir)}</base_dir>")
         lines.append("  </skill>")
     
     lines.append("</available_skills>")
@@ -50,6 +51,71 @@ def format_skill_entries_for_prompt(entries: List[SkillEntry]) -> str:
     return format_skills_for_prompt(skills)
 
 
+def format_unavailable_skills_for_prompt(
+    entries: List[SkillEntry],
+    missing_map: Dict[str, Dict[str, List[str]]],
+) -> str:
+    """
+    Format unavailable (requires-not-met) skills as brief setup hints
+    so the AI can guide users to configure them.
+
+    :param entries: List of unavailable skill entries
+    :param missing_map: Dict mapping skill name to its missing requirements
+    :return: Formatted prompt text
+    """
+    if not entries:
+        return ""
+
+    lines = [
+        "",
+        "<unavailable_skills>",
+        "The following skills are installed but not yet ready. "
+        "Guide the user to complete the setup when relevant.",
+    ]
+
+    for entry in entries:
+        skill = entry.skill
+        missing = missing_map.get(skill.name, {})
+
+        missing_parts = []
+        for key, values in missing.items():
+            missing_parts.append(f"{key}: {', '.join(values)}")
+        missing_str = "; ".join(missing_parts) if missing_parts else "unknown"
+
+        setup_hint = _extract_setup_hint(skill)
+
+        lines.append("  <skill>")
+        lines.append(f"    <name>{_escape_xml(skill.name)}</name>")
+        lines.append(f"    <description>{_escape_xml(skill.description)}</description>")
+        lines.append(f"    <missing>{_escape_xml(missing_str)}</missing>")
+        if setup_hint:
+            lines.append(f"    <setup>{_escape_xml(setup_hint)}</setup>")
+        lines.append("  </skill>")
+
+    lines.append("</unavailable_skills>")
+    return "\n".join(lines)
+
+
+def _extract_setup_hint(skill: Skill) -> str:
+    """
+    Extract the Setup section from SKILL.md content as a brief hint.
+    Returns the first few lines of the ## Setup section.
+    """
+    content = skill.content
+    if not content:
+        return ""
+
+    import re
+    match = re.search(r'^##\s+Setup\s*\n(.*?)(?=\n##\s|\Z)', content, re.MULTILINE | re.DOTALL)
+    if not match:
+        return ""
+
+    setup_text = match.group(1).strip()
+    lines = setup_text.split('\n')
+    hint_lines = [l.strip() for l in lines[:6] if l.strip()]
+    return ' '.join(hint_lines)[:300]
+
+
 def _escape_xml(text: str) -> str:
     """Escape XML special characters."""
     return (text

agent/skills/frontmatter.py

@@ -87,8 +87,8 @@ def parse_metadata(frontmatter: Dict[str, Any]) -> Optional[SkillMetadata]:
     if not isinstance(metadata_raw, dict):
         return None
     
-    # Use metadata_raw directly (COW format)
+    # Unwrap nested namespace (e.g. {"openclaw": {...}} or {"cowagent": {...}})
-    meta_obj = metadata_raw
+    meta_obj = _unwrap_metadata_namespace(metadata_raw)
     
     # Parse install specs
     install_specs = []
@@ -128,6 +128,7 @@ def parse_metadata(frontmatter: Dict[str, Any]) -> Optional[SkillMetadata]:
     
     return SkillMetadata(
         always=meta_obj.get('always', False),
+        default_enabled=meta_obj.get('default_enabled', True),
         skill_key=meta_obj.get('skillKey'),
         primary_env=meta_obj.get('primaryEnv'),
         emoji=meta_obj.get('emoji'),
@@ -138,6 +139,25 @@ def parse_metadata(frontmatter: Dict[str, Any]) -> Optional[SkillMetadata]:
     )
 
 
+_KNOWN_METADATA_NAMESPACES = {"cowagent", "openclaw"}
+
+
+def _unwrap_metadata_namespace(metadata_raw: Dict[str, Any]) -> Dict[str, Any]:
+    """
+    Unwrap a single-key namespace wrapper like {"cowagent": {...} or {"openclaw": {...}}}.
+    If the top-level dict has exactly one key matching a known namespace, return the inner dict.
+    Otherwise return the original dict unchanged.
+    """
+    keys = set(metadata_raw.keys())
+    ns_keys = keys & _KNOWN_METADATA_NAMESPACES
+    if len(ns_keys) == 1 and len(keys) == 1:
+        ns = ns_keys.pop()
+        inner = metadata_raw[ns]
+        if isinstance(inner, dict):
+            return inner
+    return metadata_raw
+
+
 def _normalize_string_list(value: Any) -> List[str]:
     """Normalize a value to a list of strings."""
     if not value:

agent/skills/loader.py

@@ -53,6 +53,12 @@ class SkillLoader:
         """
         Recursively load skills from a directory.
         
+        If a subdirectory contains its own SKILL.md, it is treated as a
+        self-contained skill (or skill-collection) and its children are
+        NOT scanned further. This prevents sub-skills inside a collection
+        (e.g. style-collection/style-anjing) from being listed as
+        independent top-level skills.
+        
         :param dir_path: Directory to scan
         :param source: Source identifier
         :param include_root_files: Whether to include root-level .md files
@@ -66,38 +72,41 @@ class SkillLoader:
         except Exception as e:
             diagnostics.append(f"Failed to list directory {dir_path}: {e}")
             return LoadSkillsResult(skills=skills, diagnostics=diagnostics)
+
+        # If this directory has its own SKILL.md, load it and stop recursing.
+        # The sub-directories are internal resources of this skill.
+        if not include_root_files and 'SKILL.md' in entries:
+            skill_md_path = os.path.join(dir_path, 'SKILL.md')
+            if os.path.isfile(skill_md_path):
+                skill_result = self._load_skill_from_file(skill_md_path, source)
+                if skill_result.skills:
+                    skills.extend(skill_result.skills)
+                diagnostics.extend(skill_result.diagnostics)
+                return LoadSkillsResult(skills=skills, diagnostics=diagnostics)
         
         for entry in entries:
-            # Skip hidden files and directories
             if entry.startswith('.'):
                 continue
             
-            # Skip common non-skill directories
             if entry in ('node_modules', '__pycache__', 'venv', '.git'):
                 continue
             
             full_path = os.path.join(dir_path, entry)
             
-            # Handle directories
             if os.path.isdir(full_path):
-                # Recursively scan subdirectories
                 sub_result = self._load_skills_recursive(full_path, source, include_root_files=False)
                 skills.extend(sub_result.skills)
                 diagnostics.extend(sub_result.diagnostics)
                 continue
             
-            # Handle files
             if not os.path.isfile(full_path):
                 continue
             
-            # Check if this is a skill file
+            is_root_md = include_root_files and entry.endswith('.md') and entry.upper() != 'README.MD'
-            is_root_md = include_root_files and entry.endswith('.md')
-            is_skill_md = not include_root_files and entry == 'SKILL.md'
             
-            if not (is_root_md or is_skill_md):
+            if not is_root_md:
                 continue
             
-            # Load the skill
             skill_result = self._load_skill_from_file(full_path, source)
             if skill_result.skills:
                 skills.extend(skill_result.skills)
@@ -184,7 +193,6 @@ class SkillLoader:
         
         config_path = os.path.join(skill_dir, "config.json")
         
-        # Without config.json, skip this skill entirely (return empty to trigger exclusion)
         if not os.path.exists(config_path):
             logger.debug(f"[SkillLoader] linkai-agent skipped: no config.json found")
             return ""

agent/skills/manager.py

@@ -84,10 +84,10 @@ class SkillManager:
         """
         Merge directory-scanned skills with the persisted config file.
 
-        - New skills discovered on disk are added with enabled=True.
+        - New skills: use metadata.default_enabled as initial enabled state.
+        - Existing skills: preserve their persisted enabled state.
         - Skills that no longer exist on disk are removed.
-        - Existing entries preserve their enabled state; name/description/source
+        - name/description/source are always refreshed from the latest scan.
-          are refreshed from the latest scan.
         """
         saved = self._load_skills_config()
         merged: Dict[str, dict] = {}
@@ -95,12 +95,24 @@ class SkillManager:
         for name, entry in self.skills.items():
             skill = entry.skill
             prev = saved.get(name, {})
-            merged[name] = {
+            category = prev.get("category", "skill")
+
+            if name in saved:
+                enabled = prev.get("enabled", True)
+            else:
+                enabled = entry.metadata.default_enabled if entry.metadata else True
+
+            entry_dict = {
                 "name": name,
                 "description": skill.description,
-                "source": skill.source,
+                "source": prev.get("source") or skill.source,
-                "enabled": prev.get("enabled", True),
+                "enabled": enabled,
+                "category": category,
             }
+            display_name = prev.get("display_name")
+            if display_name:
+                entry_dict["display_name"] = display_name
+            merged[name] = entry_dict
 
         self.skills_config = merged
         self._save_skills_config()
@@ -154,69 +166,118 @@ class SkillManager:
         """
         return list(self.skills.values())
     
+    @staticmethod
+    def _normalize_skill_filter(skill_filter: Optional[List[str]]) -> Optional[List[str]]:
+        """Normalize a skill_filter list into a flat list of stripped names."""
+        if skill_filter is None:
+            return None
+        normalized = []
+        for item in skill_filter:
+            if isinstance(item, str):
+                name = item.strip()
+                if name:
+                    normalized.append(name)
+            elif isinstance(item, list):
+                for subitem in item:
+                    if isinstance(subitem, str):
+                        name = subitem.strip()
+                        if name:
+                            normalized.append(name)
+        return normalized or None
+
     def filter_skills(
         self,
         skill_filter: Optional[List[str]] = None,
         include_disabled: bool = False,
     ) -> List[SkillEntry]:
         """
-        Filter skills based on criteria.
+        Filter skills that are eligible (enabled + requirements met).
-
-        Simple rule: Skills are auto-enabled if requirements are met.
-        - Has required API keys -> included
-        - Missing API keys -> excluded
 
         :param skill_filter: List of skill names to include (None = all)
         :param include_disabled: Whether to include disabled skills
-        :return: Filtered list of skill entries
+        :return: Filtered list of eligible skill entries
         """
         from agent.skills.config import should_include_skill
 
         entries = list(self.skills.values())
 
-        # Check requirements (platform, binaries, env vars)
         entries = [e for e in entries if should_include_skill(e, self.config)]
 
-        # Apply skill filter
+        normalized = self._normalize_skill_filter(skill_filter)
-        if skill_filter is not None:
+        if normalized is not None:
-            normalized = []
+            entries = [e for e in entries if e.skill.name in normalized]
-            for item in skill_filter:
-                if isinstance(item, str):
-                    name = item.strip()
-                    if name:
-                        normalized.append(name)
-                elif isinstance(item, list):
-                    for subitem in item:
-                        if isinstance(subitem, str):
-                            name = subitem.strip()
-                            if name:
-                                normalized.append(name)
-            if normalized:
-                entries = [e for e in entries if e.skill.name in normalized]
 
-        # Filter out disabled skills based on skills_config.json
         if not include_disabled:
             entries = [e for e in entries if self.is_skill_enabled(e.skill.name)]
 
+        from config import conf
+        if not conf().get("knowledge", True):
+            entries = [e for e in entries if e.skill.name != "knowledge-wiki"]
+
         return entries
-    
+
+    def filter_unavailable_skills(
+        self,
+        skill_filter: Optional[List[str]] = None,
+    ) -> tuple:
+        """
+        Find skills that are enabled but have unmet requirements.
+
+        :param skill_filter: Optional list of skill names to include
+        :return: Tuple of (entries, missing_map) where missing_map maps
+                 skill name to its missing requirements dict
+        """
+        from agent.skills.config import should_include_skill, get_missing_requirements
+
+        entries = list(self.skills.values())
+
+        # Only enabled skills
+        entries = [e for e in entries if self.is_skill_enabled(e.skill.name)]
+
+        normalized = self._normalize_skill_filter(skill_filter)
+        if normalized is not None:
+            entries = [e for e in entries if e.skill.name in normalized]
+
+        # Keep only those that fail should_include_skill (requirements not met)
+        unavailable = []
+        missing_map: Dict[str, dict] = {}
+        for e in entries:
+            if not should_include_skill(e, self.config):
+                missing = get_missing_requirements(e)
+                if missing:
+                    unavailable.append(e)
+                    missing_map[e.skill.name] = missing
+
+        return unavailable, missing_map
+
     def build_skills_prompt(
         self,
         skill_filter: Optional[List[str]] = None,
     ) -> str:
         """
-        Build a formatted prompt containing available skills.
+        Build a formatted prompt containing available skills
-        
+        and brief hints for unavailable ones.
+
         :param skill_filter: Optional list of skill names to include
         :return: Formatted skills prompt
         """
         from common.log import logger
-        entries = self.filter_skills(skill_filter=skill_filter, include_disabled=False)
+        from agent.skills.formatter import format_unavailable_skills_for_prompt
-        logger.debug(f"[SkillManager] Filtered {len(entries)} skills for prompt (total: {len(self.skills)})")
+
-        if entries:
+        eligible = self.filter_skills(skill_filter=skill_filter, include_disabled=False)
-            skill_names = [e.skill.name for e in entries]
+        logger.debug(f"[SkillManager] Eligible: {len(eligible)} skills (total: {len(self.skills)})")
-            logger.debug(f"[SkillManager] Skills to include: {skill_names}")
+        if eligible:
-        result = format_skill_entries_for_prompt(entries)
+            skill_names = [e.skill.name for e in eligible]
+            logger.debug(f"[SkillManager] Eligible skills: {skill_names}")
+
+        result = format_skill_entries_for_prompt(eligible)
+
+        unavailable, missing_map = self.filter_unavailable_skills(skill_filter=skill_filter)
+        if unavailable:
+            unavailable_names = [e.skill.name for e in unavailable]
+            logger.debug(f"[SkillManager] Unavailable skills (setup needed): {unavailable_names}")
+            result += format_unavailable_skills_for_prompt(unavailable, missing_map)
+
         logger.debug(f"[SkillManager] Generated prompt length: {len(result)}")
         return result
     

agent/skills/service.py

@@ -8,6 +8,8 @@ other management entry point.
 
 import os
 import shutil
+import zipfile
+import tempfile
 from typing import Dict, List, Optional
 from common.log import logger
 from agent.skills.types import Skill, SkillEntry
@@ -32,6 +34,27 @@ class SkillService:
         """
         self.manager = skill_manager
 
+    def _safe_skill_dir(self, name: str) -> str:
+        """Derive and validate the skill directory path.
+
+        Ensures the resolved path stays within the custom_dir root,
+        preventing path traversal via names like ``../escaped``.
+
+        :raises ValueError: if the name would escape the skills root.
+        """
+        if not name or not name.strip():
+            raise ValueError("skill name is required")
+        # Reject obvious traversal components.
+        if ".." in name or name.startswith("/") or name.startswith("\\"):
+            raise ValueError(f"invalid skill name (path traversal detected): {name!r}")
+        skill_dir = os.path.realpath(os.path.join(self.manager.custom_dir, name))
+        root = os.path.realpath(self.manager.custom_dir)
+        if not skill_dir.startswith(root + os.sep) and skill_dir != root:
+            raise ValueError(
+                f"skill name {name!r} resolves outside the skills directory"
+            )
+        return skill_dir
+
     # ------------------------------------------------------------------
     # query
     # ------------------------------------------------------------------
@@ -55,7 +78,9 @@ class SkillService:
         """
         Add (install) a skill from a remote payload.
 
-        The payload follows the socket protocol::
+        Supported payload types:
+
+        1. ``type: "url"`` – download individual files::
 
             {
                 "name": "web_search",
@@ -67,8 +92,15 @@ class SkillService:
                 ]
             }
 
-        Files are downloaded and saved under the custom skills directory
+        2. ``type: "package"`` – download a zip archive and extract::
-        using *name* as the sub-directory.
+
+            {
+                "name": "plugin-custom-tool",
+                "type": "package",
+                "category": "skills",
+                "enabled": true,
+                "files": [{"url": "https://cdn.example.com/skills/custom-tool.zip"}]
+            }
 
         :param payload: skill add payload from server
         """
@@ -76,25 +108,95 @@ class SkillService:
         if not name:
             raise ValueError("skill name is required")
 
+        payload_type = payload.get("type", "url")
+
+        if payload_type == "package":
+            self._add_package(name, payload)
+        else:
+            self._add_url(name, payload)
+
+        self.manager.refresh_skills()
+
+        category = payload.get("category")
+        if category and name in self.manager.skills_config:
+            self.manager.skills_config[name]["category"] = category
+            self.manager._save_skills_config()
+
+    def _add_url(self, name: str, payload: dict) -> None:
+        """Install a skill by downloading individual files."""
         files = payload.get("files", [])
         if not files:
             raise ValueError("skill files list is empty")
 
-        skill_dir = os.path.join(self.manager.custom_dir, name)
+        skill_dir = self._safe_skill_dir(name)
-        os.makedirs(skill_dir, exist_ok=True)
 
-        for file_info in files:
+        tmp_dir = skill_dir + ".tmp"
-            url = file_info.get("url")
+        if os.path.exists(tmp_dir):
-            rel_path = file_info.get("path")
+            shutil.rmtree(tmp_dir)
-            if not url or not rel_path:
+        os.makedirs(tmp_dir, exist_ok=True)
-                logger.warning(f"[SkillService] add: skip invalid file entry {file_info}")
-                continue
-            dest = os.path.join(skill_dir, rel_path)
-            self._download_file(url, dest)
 
-        # Reload to pick up the new skill and sync config
+        try:
-        self.manager.refresh_skills()
+            for file_info in files:
-        logger.info(f"[SkillService] add: skill '{name}' installed ({len(files)} files)")
+                url = file_info.get("url")
+                rel_path = file_info.get("path")
+                if not url or not rel_path:
+                    logger.warning(f"[SkillService] add: skip invalid file entry {file_info}")
+                    continue
+                dest = os.path.join(tmp_dir, rel_path)
+                self._download_file(url, dest)
+        except Exception:
+            shutil.rmtree(tmp_dir, ignore_errors=True)
+            raise
+
+        if os.path.exists(skill_dir):
+            shutil.rmtree(skill_dir)
+        os.rename(tmp_dir, skill_dir)
+
+        logger.info(f"[SkillService] add: skill '{name}' installed via url ({len(files)} files)")
+
+    def _add_package(self, name: str, payload: dict) -> None:
+        """
+        Install a skill by downloading a zip archive and extracting it.
+
+        If the archive contains a single top-level directory, that directory
+        is used as the skill folder directly; otherwise a new directory named
+        after the skill is created to hold the extracted contents.
+        """
+        files = payload.get("files", [])
+        if not files or not files[0].get("url"):
+            raise ValueError("package url is required")
+
+        url = files[0]["url"]
+        skill_dir = self._safe_skill_dir(name)
+
+        with tempfile.TemporaryDirectory() as tmp_dir:
+            zip_path = os.path.join(tmp_dir, "package.zip")
+            self._download_file(url, zip_path)
+
+            if not zipfile.is_zipfile(zip_path):
+                raise ValueError(f"downloaded file is not a valid zip archive: {url}")
+
+            extract_dir = os.path.join(tmp_dir, "extracted")
+            with zipfile.ZipFile(zip_path, "r") as zf:
+                zf.extractall(extract_dir)
+
+            # Determine the actual content root.
+            # If the zip has a single top-level directory, use its contents
+            # so the skill folder is clean (no extra nesting).
+            top_items = [
+                item for item in os.listdir(extract_dir)
+                if not item.startswith(".")
+            ]
+            if len(top_items) == 1:
+                single = os.path.join(extract_dir, top_items[0])
+                if os.path.isdir(single):
+                    extract_dir = single
+
+            if os.path.exists(skill_dir):
+                shutil.rmtree(skill_dir)
+            shutil.copytree(extract_dir, skill_dir)
+
+        logger.info(f"[SkillService] add: skill '{name}' installed via package ({url})")
 
     # ------------------------------------------------------------------
     # open / close (enable / disable)
@@ -136,7 +238,7 @@ class SkillService:
         if not name:
             raise ValueError("skill name is required")
 
-        skill_dir = os.path.join(self.manager.custom_dir, name)
+        skill_dir = self._safe_skill_dir(name)
         if os.path.exists(skill_dir):
             shutil.rmtree(skill_dir)
             logger.info(f"[SkillService] delete: removed directory {skill_dir}")

agent/skills/types.py

@@ -29,6 +29,7 @@ class SkillInstallSpec:
 class SkillMetadata:
     """Metadata for a skill from frontmatter."""
     always: bool = False  # Always include this skill
+    default_enabled: bool = True  # Initial enabled state when first discovered
     skill_key: Optional[str] = None  # Override skill key
     primary_env: Optional[str] = None  # Primary environment variable
     emoji: Optional[str] = None

agent/tools/__init__.py

@@ -14,6 +14,9 @@ from agent.tools.send.send import Send
 from agent.tools.memory.memory_search import MemorySearchTool
 from agent.tools.memory.memory_get import MemoryGetTool
 
+# Import self-evolution tools
+from agent.tools.evolution_undo.evolution_undo import EvolutionUndoTool
+
 # Import tools with optional dependencies
 def _import_optional_tools():
     """Import tools that have optional dependencies"""
@@ -55,6 +58,24 @@ def _import_optional_tools():
     except Exception as e:
         logger.error(f"[Tools] WebSearch failed to load: {e}")
 
+    # WebFetch Tool
+    try:
+        from agent.tools.web_fetch.web_fetch import WebFetch
+        tools['WebFetch'] = WebFetch
+    except ImportError as e:
+        logger.error(f"[Tools] WebFetch not loaded - missing dependency: {e}")
+    except Exception as e:
+        logger.error(f"[Tools] WebFetch failed to load: {e}")
+
+    # Vision Tool (conditionally loaded based on API key availability)
+    try:
+        from agent.tools.vision.vision import Vision
+        tools['Vision'] = Vision
+    except ImportError as e:
+        logger.error(f"[Tools] Vision not loaded - missing dependency: {e}")
+    except Exception as e:
+        logger.error(f"[Tools] Vision failed to load: {e}")
+
     return tools
 
 # Load optional tools
@@ -62,30 +83,48 @@ _optional_tools = _import_optional_tools()
 EnvConfig = _optional_tools.get('EnvConfig')
 SchedulerTool = _optional_tools.get('SchedulerTool')
 WebSearch = _optional_tools.get('WebSearch')
+WebFetch = _optional_tools.get('WebFetch')
+Vision = _optional_tools.get('Vision')
 GoogleSearch = _optional_tools.get('GoogleSearch')
 FileSave = _optional_tools.get('FileSave')
 Terminal = _optional_tools.get('Terminal')
 
 
-# Delayed import for BrowserTool
+# BrowserTool (requires playwright)
 def _import_browser_tool():
+    from common.log import logger
     try:
         from agent.tools.browser.browser_tool import BrowserTool
         return BrowserTool
-    except ImportError:
+    except ImportError as e:
-        # Return a placeholder class that will prompt the user to install dependencies when instantiated
+        logger.info(
-        class BrowserToolPlaceholder:
+            f"[Tools] BrowserTool not loaded - missing dependency: {e}\n"
-            def __init__(self, *args, **kwargs):
+            f"  To enable browser tool, run:\n"
-                raise ImportError(
+            f"    pip install playwright\n"
-                    "The 'browser-use' package is required to use BrowserTool. "
+            f"    playwright install chromium"
-                    "Please install it with 'pip install browser-use>=0.1.40'."
+        )
-                )
+        return None
+    except Exception as e:
+        logger.error(f"[Tools] BrowserTool failed to load: {e}")
+        return None
 
-        return BrowserToolPlaceholder
+BrowserTool = _import_browser_tool()
 
+# MCP Tools (no extra dependencies, loaded on demand)
+def _import_mcp_tools():
+    """导入 MCP 工具模块（无额外依赖，按需加载）"""
+    from common.log import logger
+    try:
+        from agent.tools.mcp.mcp_tool import McpTool
+        from agent.tools.mcp.mcp_client import McpClientRegistry
+        return {'McpTool': McpTool, 'McpClientRegistry': McpClientRegistry}
+    except Exception as e:
+        logger.warning(f"[Tools] MCP tools not loaded: {e}")
+        return {}
 
-# Dynamically set BrowserTool
+_mcp_tools = _import_mcp_tools()
-# BrowserTool = _import_browser_tool()
+McpTool = _mcp_tools.get('McpTool')
+McpClientRegistry = _mcp_tools.get('McpClientRegistry')
 
 # Export all tools (including optional ones that might be None)
 __all__ = [
@@ -99,11 +138,14 @@ __all__ = [
     'Send',
     'MemorySearchTool',
     'MemoryGetTool',
+    'EvolutionUndoTool',
     'EnvConfig',
     'SchedulerTool',
     'WebSearch',
-    # Optional tools (may be None if dependencies not available)
+    'WebFetch',
-    # 'BrowserTool'
+    'Vision',
+    'BrowserTool',
+    'McpTool',
 ]
 
 """

agent/tools/base_tool.py

@@ -38,6 +38,16 @@ class BaseTool:
     description: str = "Base tool"
     params: dict = {}  # Store JSON Schema
     model: Optional[Any] = None  # LLM model instance, type depends on bot implementation
+    progress_callback = None
+
+    def report_progress(self, message: str):
+        callback = getattr(self, "progress_callback", None)
+        if not callback:
+            return
+        try:
+            callback(str(message))
+        except Exception as e:
+            logger.debug(f"[{self.name}] progress callback failed: {e}")
 
     @classmethod
     def get_json_schema(cls) -> dict:

agent/tools/bash/bash.py

@@ -3,9 +3,13 @@ Bash tool - Execute bash commands
 """
 
 import os
+import re
+import signal
 import sys
 import subprocess
 import tempfile
+import threading
+import time
 from typing import Dict, Any
 
 from agent.tools.base_tool import BaseTool, ToolResult
@@ -17,14 +21,22 @@ from common.utils import expand_path
 class Bash(BaseTool):
     """Tool for executing bash commands"""
 
+    _IS_WIN = sys.platform == "win32"
+    _PROGRESS_MAX_BYTES = 4 * 1024
+    _PROGRESS_INTERVAL = 0.5
+    # cmd.exe command line limit is ~8191 chars; rewrite python -c above this.
+    _WIN_CMD_SAFE_LEN = 7000
+
     name: str = "bash"
     description: str = f"""Execute a bash command in the current working directory. Returns stdout and stderr. Output is truncated to last {DEFAULT_MAX_LINES} lines or {DEFAULT_MAX_BYTES // 1024}KB (whichever is hit first). If truncated, full output is saved to a temp file.
-
+{'''
+PLATFORM: Windows (cmd.exe). Do NOT use Unix-only commands like grep, head, tail, sed, awk.
+''' if _IS_WIN else ''}
 ENVIRONMENT: All API keys from env_config are auto-injected. Use $VAR_NAME directly.
 
 SAFETY:
 - Freely create/modify/delete files within the workspace
-- For destructive and out-of-workspace commands, explain and confirm first"""
+- For destructive commands out of workspace, explain and confirm first"""
 
     params: dict = {
         "type": "object",
@@ -64,8 +76,8 @@ SAFETY:
         if not command:
             return ToolResult.fail("Error: command parameter is required")
 
-        # Security check: Prevent accessing sensitive config files
+        # Security check: Prevent direct access to the credential file
-        if "~/.cow/.env" in command or "~/.cow" in command:
+        if re.search(r'\.cow[/\\]\.env', command):
             return ToolResult.fail(
                 "Error: Access denied. API keys and credentials must be accessed through the env_config tool only."
             )
@@ -83,12 +95,13 @@ SAFETY:
             
             # Load environment variables from ~/.cow/.env if it exists
             env_file = expand_path("~/.cow/.env")
+            dotenv_vars = {}
             if os.path.exists(env_file):
                 try:
                     from dotenv import dotenv_values
-                    env_vars = dotenv_values(env_file)
+                    dotenv_vars = dotenv_values(env_file)
-                    env.update(env_vars)
+                    env.update(dotenv_vars)
-                    logger.debug(f"[Bash] Loaded {len(env_vars)} variables from {env_file}")
+                    logger.debug(f"[Bash] Loaded {len(dotenv_vars)} variables from {env_file}")
                 except ImportError:
                     logger.debug("[Bash] python-dotenv not installed, skipping .env loading")
                 except Exception as e:
@@ -100,17 +113,35 @@ SAFETY:
             else:
                 logger.debug(f"[Bash] Process User: {os.environ.get('USERNAME', os.environ.get('USER', 'unknown'))}")
             
-            # Execute command with inherited environment variables
+            # Temp script written for long `python -c` commands (Windows only),
-            result = subprocess.run(
+            # cleaned up after execution.
-                command,
+            temp_script_path = None
-                shell=True,
+
-                cwd=self.cwd,
+            # On Windows, convert $VAR references to %VAR% for cmd.exe
-                stdout=subprocess.PIPE,
+            if self._IS_WIN:
-                stderr=subprocess.PIPE,
+                env["PYTHONIOENCODING"] = "utf-8"
-                text=True,
+                command = self._convert_env_vars_for_windows(command, dotenv_vars)
-                timeout=timeout,
+                # cmd.exe has an ~8191 char command line limit. Long
-                env=env
+                # `python -c "..."` commands silently fail, so spill the inline
-            )
+                # code into a temp .py file and run that instead.
+                if len(command) > self._WIN_CMD_SAFE_LEN:
+                    command, temp_script_path = self._rewrite_long_python_c(command)
+                if command and not command.strip().lower().startswith("chcp"):
+                    command = f"chcp 65001 >nul 2>&1 && {command}"
+
+            try:
+                result = self._run_streaming(
+                    command,
+                    timeout,
+                    env,
+                    dotenv_vars,
+                )
+            finally:
+                if temp_script_path:
+                    try:
+                        os.remove(temp_script_path)
+                    except OSError:
+                        pass
             
             logger.debug(f"[Bash] Exit code: {result.returncode}")
             logger.debug(f"[Bash] Stdout length: {len(result.stdout)}")
@@ -131,6 +162,8 @@ SAFETY:
                             stdout=subprocess.PIPE,
                             stderr=subprocess.PIPE,
                             text=True,
+                            encoding="utf-8",
+                            errors="replace",
                             timeout=timeout,
                             env=env
                         )
@@ -153,18 +186,28 @@ SAFETY:
                 except Exception as retry_err:
                     logger.warning(f"[Bash] Retry failed: {retry_err}")
 
-            # Combine stdout and stderr
+            # When command succeeds with stdout, keep output clean (stderr goes to server log only).
-            output = result.stdout
+            # When command fails or stdout is empty, include stderr so the agent can diagnose.
-            if result.stderr:
+            if result.returncode == 0 and result.stdout.strip():
-                output += "\n" + result.stderr
+                output = result.stdout
+                if result.stderr:
+                    logger.info(f"[Bash] stderr (not forwarded): {result.stderr[:500]}")
+            else:
+                output = result.stdout
+                if result.stderr:
+                    output += "\n" + result.stderr
 
             # Check if we need to save full output to temp file
             temp_file_path = None
             total_bytes = len(output.encode('utf-8'))
 
             if total_bytes > DEFAULT_MAX_BYTES:
-                # Save full output to temp file
+                # Save full output to temp file. encoding='utf-8' is required:
-                with tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.log', prefix='bash-') as f:
+                # the default text-mode encoding is the platform locale (e.g.
+                # cp936/GBK on Chinese Windows), which raises UnicodeEncodeError
+                # for output containing emoji or other non-locale characters and
+                # would discard an otherwise successful command result.
+                with tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.log', prefix='bash-', encoding='utf-8') as f:
                     f.write(output)
                     temp_file_path = f.name
 
@@ -214,47 +257,199 @@ SAFETY:
         except Exception as e:
             return ToolResult.fail(f"Error executing command: {str(e)}")
 
+    def _run_streaming(self, command: str, timeout: int, env: dict, dotenv_vars: dict):
+        process = subprocess.Popen(
+            command,
+            shell=True,
+            cwd=self.cwd,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            env=env,
+            start_new_session=not self._IS_WIN,
+        )
+        stdout_chunks, stderr_chunks = [], []
+        recent = bytearray()
+        recent_lock = threading.Lock()
+
+        def drain(stream, chunks):
+            while True:
+                chunk = os.read(stream.fileno(), 4096)
+                if not chunk:
+                    break
+                chunks.append(chunk)
+                with recent_lock:
+                    recent.extend(chunk)
+                    if len(recent) > self._PROGRESS_MAX_BYTES:
+                        del recent[:-self._PROGRESS_MAX_BYTES]
+
+        readers = [
+            threading.Thread(target=drain, args=(process.stdout, stdout_chunks), daemon=True),
+            threading.Thread(target=drain, args=(process.stderr, stderr_chunks), daemon=True),
+        ]
+        for reader in readers:
+            reader.start()
+
+        started = time.monotonic()
+        last_reported_at = started
+        last_snapshot = None
+        try:
+            while process.poll() is None:
+                now = time.monotonic()
+                elapsed = now - started
+                if elapsed >= timeout:
+                    self._kill_process(process)
+                    raise subprocess.TimeoutExpired(command, timeout)
+                if elapsed >= self._PROGRESS_INTERVAL and now - last_reported_at >= self._PROGRESS_INTERVAL:
+                    with recent_lock:
+                        snapshot = bytes(recent).decode("utf-8", errors="replace")
+                    snapshot = self._redact_progress(snapshot, dotenv_vars)
+                    if snapshot and snapshot != last_snapshot:
+                        self.report_progress(snapshot)
+                        last_snapshot = snapshot
+                    last_reported_at = now
+                time.sleep(0.1)
+        finally:
+            if process.poll() is None:
+                self._kill_process(process)
+            process.wait()
+            join_deadline = time.monotonic() + 5
+            for reader in readers:
+                reader.join(timeout=max(0, join_deadline - time.monotonic()))
+
+        from types import SimpleNamespace
+        return SimpleNamespace(
+            returncode=process.returncode,
+            stdout=b"".join(stdout_chunks).decode("utf-8", errors="replace"),
+            stderr=b"".join(stderr_chunks).decode("utf-8", errors="replace"),
+        )
+
+    def _kill_process(self, process):
+        if self._IS_WIN:
+            try:
+                result = subprocess.run(
+                    ["taskkill", "/F", "/T", "/PID", str(process.pid)],
+                    capture_output=True,
+                    timeout=5,
+                )
+                if result.returncode != 0 and process.poll() is None:
+                    process.kill()
+            except (OSError, subprocess.SubprocessError):
+                if process.poll() is None:
+                    process.kill()
+        else:
+            try:
+                os.killpg(process.pid, signal.SIGKILL)
+            except (PermissionError, ProcessLookupError):
+                if process.poll() is None:
+                    process.kill()
+
+    @staticmethod
+    def _redact_progress(text: str, dotenv_vars: dict) -> str:
+        text = re.sub(
+            r'(?i)\b(API_KEY|TOKEN|PASSWORD|AUTHORIZATION)\s*=\s*[^\s]+',
+            lambda match: f"{match.group(1)}=[REDACTED]",
+            text,
+        )
+        for value in dotenv_vars.values():
+            value = str(value or "")
+            if len(value) >= 6:
+                text = text.replace(value, "[REDACTED]")
+        return text
+
     def _get_safety_warning(self, command: str) -> str:
         """
-        Get safety warning for potentially dangerous commands
+        Get safety warning for absolutely catastrophic commands only.
-        Only warns about extremely dangerous system-level operations
+        Keep the blocklist minimal so the agent retains maximum freedom.
-        
+
         :param command: Command to check
         :return: Warning message if dangerous, empty string if safe
         """
-        cmd_lower = command.lower().strip()
+        # Tokenize to avoid substring false positives (e.g. `rm -rf /tmp/x`
+        # must not match `rm -rf /`).
+        tokens = command.lower().split()
 
-        # Only block extremely dangerous system operations
+        # `rm -rf /` or `rm -rf /*` targeting the real root.
-        dangerous_patterns = [
+        for i, tok in enumerate(tokens):
-            # System shutdown/reboot
+            if tok != "rm":
-            ("shutdown", "This command will shut down the system"),
+                continue
-            ("reboot", "This command will reboot the system"),
+            has_rf = False
-            ("halt", "This command will halt the system"),
+            for j in range(i + 1, len(tokens)):
-            ("poweroff", "This command will power off the system"),
+                t = tokens[j]
+                if t.startswith("-") and "r" in t and "f" in t:
+                    has_rf = True
+                elif t in ("--recursive", "--force"):
+                    continue
+                elif t in ("/", "/*"):
+                    if has_rf:
+                        return "This command will delete the entire filesystem"
+                    break
+                else:
+                    break
 
-            # Critical system modifications
+        # Disk wiping
-            ("rm -rf /", "This command will delete the entire filesystem"),
+        if "if=/dev/zero" in command.lower() and "dd " in command.lower():
-            ("rm -rf /*", "This command will delete the entire filesystem"),
+            return "This command can destroy disk data"
-            ("dd if=/dev/zero", "This command can destroy disk data"),
-            ("mkfs", "This command will format a filesystem, destroying all data"),
-            ("fdisk", "This command modifies disk partitions"),
 
-            # User/system management (only if targeting system users)
+        # Power control - match only as a standalone word (\b enforces word boundary)
-            ("userdel root", "This command will delete the root user"),
+        if re.search(r'\b(shutdown|reboot|halt|poweroff)\b', command.lower()):
-            ("passwd root", "This command will change the root password"),
+            return "This command will shut down or restart the system"
-        ]
 
-        for pattern, warning in dangerous_patterns:
+        return ""
-            if pattern in cmd_lower:
-                return warning
 
-        # Check for recursive deletion outside workspace
+    @staticmethod
-        if "rm" in cmd_lower and "-rf" in cmd_lower:
+    def _convert_env_vars_for_windows(command: str, dotenv_vars: dict) -> str:
-            # Allow deletion within current workspace
+        """
-            if not any(path in cmd_lower for path in ["./", self.cwd.lower()]):
+        Convert bash-style $VAR / ${VAR} references to cmd.exe %VAR% syntax.
-                # Check if targeting system directories
+        Only converts variables loaded from .env (user-configured API keys etc.)
-                system_dirs = ["/bin", "/usr", "/etc", "/var", "/home", "/root", "/sys", "/proc"]
+        to avoid breaking $PATH, jq expressions, regex, etc.
-                if any(sysdir in cmd_lower for sysdir in system_dirs):
+        """
-                    return "This command will recursively delete system directories"
+        if not dotenv_vars:
+            return command
 
-        return ""  # No warning needed
+        def replace_match(m):
+            var_name = m.group(1) or m.group(2)
+            if var_name in dotenv_vars:
+                return f"%{var_name}%"
+            return m.group(0)
+
+        return re.sub(r'\$\{(\w+)\}|\$(\w+)', replace_match, command)
+
+    @staticmethod
+    def _rewrite_long_python_c(command: str):
+        """
+        Rewrite `python -c "<code>"` into `python <tempfile>` to bypass the
+        cmd.exe command line length limit on Windows.
+
+        Returns (new_command, temp_file_path). On any parse failure the original
+        command and None are returned, so behavior is unchanged when unmatched.
+        """
+        # Match: <python|python3|py> [flags] -c "<code>" (single or double quoted)
+        m = re.search(
+            r'^(?P<prefix>.*?\b(?:python3?|py)\b[^\n]*?\s-c\s+)'
+            r'(?P<quote>["\'])(?P<code>.*)(?P=quote)\s*(?P<suffix>.*)$',
+            command,
+            re.DOTALL,
+        )
+        if not m:
+            return command, None
+
+        quote = m.group("quote")
+        code = m.group("code")
+        # Reverse common shell-level escaping of the quote char inside the code.
+        code = code.replace("\\" + quote, quote)
+
+        try:
+            fd, path = tempfile.mkstemp(suffix=".py", prefix="bash-pyc-")
+            with os.fdopen(fd, "w", encoding="utf-8") as f:
+                f.write(code)
+        except OSError:
+            return command, None
+
+        prefix = m.group("prefix")
+        # Drop the trailing "-c " from the prefix, keep the interpreter + flags.
+        interp = re.sub(r'\s-c\s+$', ' ', prefix).rstrip()
+        suffix = m.group("suffix").strip()
+        new_command = f'{interp} "{path}"'
+        if suffix:
+            new_command += f' {suffix}'
+        return new_command, path

agent/tools/browser/__init__.py

@@ -0,0 +1,3 @@
+from agent.tools.browser.browser_tool import BrowserTool
+
+__all__ = ["BrowserTool"]

agent/tools/browser/browser_service.py

@@ -0,0 +1,961 @@
+"""
+Browser service - Playwright wrapper managing browser lifecycle and page operations.
+
+All Playwright calls run on a dedicated background thread so that callers from
+any worker thread can safely use the service.  An idle-timeout mechanism
+automatically shuts down the browser (and its thread) after a configurable
+period of inactivity to free resources.
+"""
+
+import os
+import sys
+import uuid
+import queue
+import threading
+from typing import Optional, Dict, Any, List, Callable
+
+from common.log import logger
+from common.utils import expand_path, is_cloud_deployment
+
+
+_DEFAULT_USER_DATA_DIR = "~/.cow/browser_profile"
+
+try:
+    from playwright.sync_api import sync_playwright, Browser, BrowserContext, Page, Playwright
+    _HAS_PLAYWRIGHT = True
+except ImportError:
+    _HAS_PLAYWRIGHT = False
+
+
+# ---------------------------------------------------------------------------
+# Snapshot DOM helpers
+# ---------------------------------------------------------------------------
+
+# Tags that typically carry useful content for an agent
+_INTERACTIVE_TAGS = {
+    "a", "button", "input", "textarea", "select", "option",
+    "label", "details", "summary",
+}
+_SEMANTIC_TAGS = {
+    "h1", "h2", "h3", "h4", "h5", "h6",
+    "p", "li", "td", "th", "caption", "figcaption", "blockquote", "pre", "code",
+    "nav", "main", "article", "section", "header", "footer", "form", "table",
+    "img", "video", "audio",
+}
+_KEEP_TAGS = _INTERACTIVE_TAGS | _SEMANTIC_TAGS
+
+_SNAPSHOT_JS = """
+() => {
+    const KEEP = new Set(%s);
+    const INTERACTIVE = new Set(%s);
+    const SKIP = new Set(["script","style","noscript","svg","path","meta","link","br","hr"]);
+    const CLICKABLE_ROLES = new Set([
+        "button","link","tab","menuitem","menuitemcheckbox","menuitemradio",
+        "option","switch","checkbox","radio","combobox","searchbox","slider",
+        "spinbutton","textbox","treeitem"
+    ]);
+    let refCounter = 0;
+    const refMap = {};
+
+    function visible(el) {
+        if (!(el instanceof HTMLElement)) return true;
+        const st = window.getComputedStyle(el);
+        if (st.display === "none" || st.visibility === "hidden") return false;
+        if (parseFloat(st.opacity) === 0) return false;
+        return true;
+    }
+
+    // Strong signals: these attributes alone are enough to mark as interactive
+    function hasStrongInteractiveSignal(el) {
+        const role = el.getAttribute("role");
+        if (role && CLICKABLE_ROLES.has(role)) return true;
+        if (el.hasAttribute("onclick") || el.hasAttribute("tabindex")) return true;
+        if (el.hasAttribute("data-click") || el.hasAttribute("data-action")) return true;
+        if (el.getAttribute("contenteditable") === "true") return true;
+        return false;
+    }
+
+    // Check if cursor:pointer is set directly (not just inherited from parent)
+    function hasOwnPointerCursor(el) {
+        try {
+            const st = window.getComputedStyle(el);
+            if (st.cursor !== "pointer") return false;
+            const parent = el.parentElement;
+            if (parent) {
+                const pst = window.getComputedStyle(parent);
+                if (pst.cursor === "pointer") return false;
+            }
+            return true;
+        } catch(e) {}
+        return false;
+    }
+
+    function hasTextOrContent(el) {
+        const t = el.textContent || "";
+        if (t.trim().length > 0) return true;
+        if (el.querySelector("img,video,audio,canvas")) return true;
+        const ariaLabel = el.getAttribute("aria-label");
+        if (ariaLabel && ariaLabel.trim()) return true;
+        const title = el.getAttribute("title");
+        if (title && title.trim()) return true;
+        return false;
+    }
+
+    function isImplicitInteractive(el) {
+        if (hasStrongInteractiveSignal(el)) return true;
+        if (hasOwnPointerCursor(el) && hasTextOrContent(el)) return true;
+        return false;
+    }
+
+    function getTextContent(el) {
+        let text = "";
+        for (const ch of el.childNodes) {
+            if (ch.nodeType === Node.TEXT_NODE) {
+                text += ch.textContent;
+            }
+        }
+        return text.trim();
+    }
+
+    function walk(node) {
+        if (node.nodeType === Node.TEXT_NODE) {
+            const t = node.textContent.trim();
+            return t ? t : null;
+        }
+        if (node.nodeType !== Node.ELEMENT_NODE) return null;
+        const tag = node.tagName.toLowerCase();
+        if (SKIP.has(tag)) return null;
+        if (!visible(node)) return null;
+
+        const children = [];
+        for (const ch of node.childNodes) {
+            const r = walk(ch);
+            if (r !== null) {
+                if (typeof r === "string") children.push(r);
+                else children.push(r);
+            }
+        }
+
+        const nativeInteractive = INTERACTIVE.has(tag);
+        const implicitInteractive = !nativeInteractive && (node instanceof HTMLElement) && isImplicitInteractive(node);
+        const keep = KEEP.has(tag) || implicitInteractive;
+
+        if (!keep) {
+            if (children.length === 0) return null;
+            if (children.length === 1) return children[0];
+            return children;
+        }
+
+        const obj = { tag };
+        if (nativeInteractive || implicitInteractive) {
+            refCounter++;
+            obj.ref = refCounter;
+            refMap[refCounter] = node;
+        }
+
+        if (implicitInteractive) {
+            const role = node.getAttribute("role");
+            if (role) obj.role = role;
+            const directText = getTextContent(node);
+            if (!directText && children.length === 0) {
+                const ariaLabel = node.getAttribute("aria-label");
+                const title = node.getAttribute("title");
+                if (ariaLabel) obj.ariaLabel = ariaLabel;
+                else if (title) obj.ariaLabel = title;
+            }
+        }
+
+        // Attributes
+        if (tag === "a" && node.href) obj.href = node.getAttribute("href");
+        if (tag === "img") {
+            obj.alt = node.alt || "";
+            obj.src = node.getAttribute("src") || "";
+        }
+        if (tag === "input" || tag === "textarea" || tag === "select") {
+            obj.type = node.type || "text";
+            obj.name = node.name || undefined;
+            obj.value = node.value || undefined;
+            obj.placeholder = node.placeholder || undefined;
+            if (node.disabled) obj.disabled = true;
+            if (tag === "input" && node.type === "checkbox") obj.checked = node.checked;
+        }
+        if (tag === "button") {
+            if (node.disabled) obj.disabled = true;
+        }
+        if (tag === "option") {
+            obj.value = node.value;
+            if (node.selected) obj.selected = true;
+        }
+        if (tag === "label" && node.htmlFor) obj.for = node.htmlFor;
+
+        // Role / aria-label for native interactive & semantic elements
+        if (!implicitInteractive) {
+            const role = node.getAttribute("role");
+            if (role) obj.role = role;
+            const ariaLabel = node.getAttribute("aria-label");
+            if (ariaLabel) obj.ariaLabel = ariaLabel;
+        }
+
+        // Children
+        if (children.length === 1 && typeof children[0] === "string") {
+            obj.text = children[0];
+        } else if (children.length > 0) {
+            obj.children = children;
+        }
+
+        return obj;
+    }
+
+    const result = walk(document.body);
+    window.__cowRefMap = refMap;
+    return { tree: result, refCount: refCounter };
+}
+""" % (
+    str(list(_KEEP_TAGS)),
+    str(list(_INTERACTIVE_TAGS)),
+)
+
+
+_BROWSER_DEAD_HINTS = (
+    "has been closed",
+    "browser has disconnected",
+    "target closed",
+    "browser closed",
+    "context or browser has been closed",
+)
+
+
+def _is_browser_dead_error(err: Exception) -> bool:
+    """Return True if *err* indicates the browser / page died out from under us."""
+    msg = str(err).lower()
+    return any(h in msg for h in _BROWSER_DEAD_HINTS)
+
+
+def _should_use_headless() -> bool:
+    """Decide headless mode: headless on Linux servers without display, headed elsewhere."""
+    if sys.platform in ("win32", "darwin"):
+        return False
+    # Linux: check for display
+    if os.environ.get("DISPLAY") or os.environ.get("WAYLAND_DISPLAY"):
+        return False
+    return True
+
+
+def _flatten_tree(node, indent=0) -> List[str]:
+    """Convert snapshot tree to compact text lines for LLM consumption."""
+    if node is None:
+        return []
+    if isinstance(node, str):
+        return [" " * indent + node]
+    if isinstance(node, list):
+        lines = []
+        for child in node:
+            lines.extend(_flatten_tree(child, indent))
+        return lines
+    if not isinstance(node, dict):
+        return []
+
+    tag = node.get("tag", "?")
+    ref = node.get("ref")
+    parts = [tag]
+    if ref:
+        parts[0] = f"[{ref}] {tag}"
+
+    # Inline attributes
+    for attr in ("type", "name", "href", "alt", "role", "ariaLabel", "placeholder", "value"):
+        val = node.get(attr)
+        if val:
+            # Truncate long values
+            s = str(val)
+            if len(s) > 80:
+                s = s[:77] + "..."
+            parts.append(f'{attr}="{s}"')
+
+    for flag in ("disabled", "checked", "selected"):
+        if node.get(flag):
+            parts.append(flag)
+
+    prefix = " " * indent
+    header = prefix + " ".join(parts)
+
+    text = node.get("text")
+    if text:
+        # Truncate long text
+        if len(text) > 120:
+            text = text[:117] + "..."
+        header += f": {text}"
+
+    lines = [header]
+    children = node.get("children", [])
+    for child in children:
+        lines.extend(_flatten_tree(child, indent + 2))
+    return lines
+
+
+class BrowserService:
+    """Manages a Playwright browser on a dedicated background thread.
+
+    All Playwright operations are dispatched to a single long-lived thread via
+    a task queue.  Callers from *any* worker thread can use the public API
+    safely.  An idle timer automatically shuts the browser down after
+    ``idle_timeout`` seconds of inactivity (default 300 = 5 min).
+    """
+
+    _IDLE_TIMEOUT_DEFAULT = 300  # seconds
+
+    def __init__(self, config: Optional[Dict[str, Any]] = None):
+        self._config = config or {}
+        self._headless: Optional[bool] = None
+        self._screenshot_dir: Optional[str] = None
+
+        # Background thread state
+        self._thread: Optional[threading.Thread] = None
+        self._task_queue: queue.Queue = queue.Queue()
+        self._lock = threading.Lock()
+        self._alive = False
+        self._ready = threading.Event()
+
+        # Playwright objects (only accessed on the background thread)
+        self._playwright = None
+        self._browser = None
+        self._context = None
+        self._page = None
+
+        # Launch mode: one of "fresh" | "persistent" | "cdp".
+        # - cdp: connect to an externally launched Chrome via CDP endpoint.
+        # - persistent: launch with launch_persistent_context using a user_data_dir
+        #   so cookies / login state survive across runs (default).
+        # - fresh: classic launch + new_context, clean state every run.
+        cdp_endpoint = self._config.get("cdp_endpoint") or ""
+        persistent_flag = self._config.get("persistent", True)
+        user_data_dir_cfg = self._config.get("user_data_dir")
+        if user_data_dir_cfg is None:
+            user_data_dir_cfg = _DEFAULT_USER_DATA_DIR
+
+        self._cdp_endpoint: str = cdp_endpoint.strip() if isinstance(cdp_endpoint, str) else ""
+        if self._cdp_endpoint:
+            self._launch_mode = "cdp"
+            self._user_data_dir: str = ""
+        elif persistent_flag and user_data_dir_cfg:
+            self._launch_mode = "persistent"
+            self._user_data_dir = expand_path(str(user_data_dir_cfg))
+        else:
+            self._launch_mode = "fresh"
+            self._user_data_dir = ""
+
+        # Idle auto-release
+        idle_cfg = self._config.get("idle_timeout")
+        self._idle_timeout: float = float(idle_cfg) if idle_cfg is not None else self._IDLE_TIMEOUT_DEFAULT
+        self._idle_timer: Optional[threading.Timer] = None
+
+        # Set when the browser / page is detected to have died externally
+        # (e.g. user manually closed the window). The next _submit() will then
+        # tear down the stale thread and relaunch.
+        self._needs_restart = False
+
+    # ------------------------------------------------------------------
+    # Background-thread lifecycle
+    # ------------------------------------------------------------------
+
+    def _start_thread(self):
+        """Start the dedicated Playwright thread if not already running."""
+        with self._lock:
+            if self._alive and self._thread and self._thread.is_alive():
+                return
+            # Wait for old thread to fully exit before creating a new one
+            old = self._thread
+            if old and old.is_alive():
+                old.join(timeout=5)
+            # Fresh queue to avoid stale sentinels from a previous close()
+            self._task_queue = queue.Queue()
+            self._alive = True
+            self._ready = threading.Event()
+            self._thread = threading.Thread(target=self._run_loop, daemon=True, name="BrowserThread")
+            self._thread.start()
+            # Block until browser is ready (or failed)
+            self._ready.wait(timeout=30)
+
+    def _run_loop(self):
+        """Event loop running on the dedicated thread. Processes tasks until stopped."""
+        logger.info("[Browser] Background thread started")
+        try:
+            self._launch_browser()
+        except Exception as e:
+            logger.error(f"[Browser] Failed to launch browser: {e}")
+            self._alive = False
+            self._ready.set()
+            self._drain_queue(RuntimeError(f"Browser launch failed: {e}"))
+            return
+        self._ready.set()
+
+        while self._alive:
+            try:
+                task = self._task_queue.get(timeout=1.0)
+            except queue.Empty:
+                continue
+            if task is None:
+                break
+            fn, args, kwargs, result_slot = task
+            try:
+                result_slot["value"] = fn(*args, **kwargs)
+            except Exception as e:
+                result_slot["error"] = e
+                if _is_browser_dead_error(e):
+                    self._needs_restart = True
+                    logger.warning(
+                        f"[Browser] Detected closed page/context ({e}); "
+                        "will relaunch on next request."
+                    )
+            finally:
+                result_slot["event"].set()
+
+        self._shutdown_browser()
+        self._drain_queue(RuntimeError("Browser thread stopped"))
+        logger.info("[Browser] Background thread exited")
+
+    def _drain_queue(self, error: Exception):
+        """Unblock all callers waiting on the queue with an error."""
+        while True:
+            try:
+                task = self._task_queue.get_nowait()
+            except queue.Empty:
+                break
+            if task is None:
+                continue
+            _, _, _, result_slot = task
+            result_slot["error"] = error
+            result_slot["event"].set()
+
+    def _launch_browser(self):
+        """Launch / connect Chromium on the background thread."""
+        if self._headless is None:
+            headless_cfg = self._config.get("headless")
+            self._headless = headless_cfg if headless_cfg is not None else _should_use_headless()
+
+        launch_args = ["--disable-dev-shm-usage"]
+        if self._headless:
+            launch_args.append("--no-sandbox")
+
+        if is_cloud_deployment():
+            launch_args.extend([
+                "--disable-gpu",
+                "--disable-software-rasterizer",
+                "--disable-extensions",
+                "--disable-background-networking",
+                "--disable-background-timer-throttling",
+                "--disable-renderer-backgrounding",
+                "--disable-features=site-per-process,TranslateUI,IsolateOrigins",
+                "--no-zygote",
+                "--js-flags=--max-old-space-size=384",
+                "--memory-pressure-off",
+            ])
+
+        extra_args = self._config.get("launch_args", [])
+        if extra_args:
+            launch_args.extend(extra_args)
+
+        viewport_w = self._config.get("viewport_width", 1280)
+        viewport_h = self._config.get("viewport_height", 720)
+        viewport = {"width": viewport_w, "height": viewport_h}
+        user_agent = (
+            "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) "
+            "AppleWebKit/537.36 (KHTML, like Gecko) "
+            "Chrome/131.0.0.0 Safari/537.36"
+        )
+
+        self._playwright = sync_playwright().start()
+
+        if self._launch_mode == "cdp":
+            self._connect_cdp(viewport)
+        elif self._launch_mode == "persistent":
+            self._launch_persistent(launch_args, viewport, user_agent)
+        else:
+            self._launch_fresh(launch_args, viewport, user_agent)
+
+        logger.info("[Browser] Browser ready")
+
+    def _launch_fresh(self, launch_args: List[str], viewport: Dict[str, int], user_agent: str):
+        """Classic launch: brand new Chromium with an empty context."""
+        logger.info(f"[Browser] Launching Chromium (fresh, headless={self._headless})")
+        self._browser = self._playwright.chromium.launch(
+            headless=self._headless,
+            args=launch_args,
+        )
+        self._context = self._browser.new_context(
+            viewport=viewport,
+            user_agent=user_agent,
+        )
+        self._page = self._context.new_page()
+        self._wire_close_listeners()
+
+    def _launch_persistent(self, launch_args: List[str], viewport: Dict[str, int], user_agent: str):
+        """Launch Chromium with a persistent user_data_dir so login state survives."""
+        os.makedirs(self._user_data_dir, exist_ok=True)
+        logger.info(
+            f"[Browser] Launching Chromium (persistent, headless={self._headless}, "
+            f"profile={self._user_data_dir})"
+        )
+        try:
+            self._context = self._playwright.chromium.launch_persistent_context(
+                user_data_dir=self._user_data_dir,
+                headless=self._headless,
+                args=launch_args,
+                viewport=viewport,
+                user_agent=user_agent,
+            )
+        except Exception as e:
+            # Profile is locked when another Chromium instance already holds it.
+            msg = str(e).lower()
+            if "singletonlock" in msg or "profile" in msg or "lock" in msg:
+                raise RuntimeError(
+                    f"Browser profile '{self._user_data_dir}' is in use by another process. "
+                    "Close the other Chromium / cow instance, or set a different "
+                    "tools.browser.user_data_dir."
+                ) from e
+            raise
+
+        # Persistent context has no parent Browser handle; reuse the auto-created page.
+        self._browser = None
+        pages = self._context.pages
+        self._page = pages[0] if pages else self._context.new_page()
+        self._wire_close_listeners()
+
+    def _connect_cdp(self, viewport: Dict[str, int]):
+        """Attach to an existing Chrome started with --remote-debugging-port."""
+        endpoint = self._cdp_endpoint
+        logger.info(f"[Browser] Connecting to existing Chrome via CDP: {endpoint}")
+        try:
+            self._browser = self._playwright.chromium.connect_over_cdp(endpoint)
+        except Exception as e:
+            msg = str(e).lower()
+            if "econnrefused" in msg or "connect" in msg or "refused" in msg:
+                raise RuntimeError(
+                    f"Cannot reach Chrome at {endpoint}. The CDP browser is not "
+                    "running. Ask the user to launch Chrome with "
+                    "--remote-debugging-port and --user-data-dir, then retry. "
+                    "Do not retry this tool until the user confirms."
+                ) from e
+            raise
+
+        contexts = self._browser.contexts
+        if contexts:
+            self._context = contexts[0]
+        else:
+            self._context = self._browser.new_context(viewport=viewport)
+
+        pages = self._context.pages
+        self._page = pages[0] if pages else self._context.new_page()
+        self._wire_close_listeners()
+
+    def _wire_close_listeners(self):
+        """Mark needs_restart whenever the browser / context / page dies externally."""
+        def _on_dead(_obj=None):
+            self._needs_restart = True
+
+        try:
+            if self._browser:
+                self._browser.on("disconnected", _on_dead)
+            if self._context:
+                self._context.on("close", _on_dead)
+            if self._page:
+                self._page.on("close", _on_dead)
+        except Exception as e:
+            logger.debug(f"[Browser] Failed to wire close listeners: {e}")
+
+    def _shutdown_browser(self):
+        """Shut down Playwright resources on the background thread.
+
+        Mode-specific behavior:
+        - cdp: only disconnect the Playwright client; leave the user's Chrome
+          and its tabs untouched (do NOT close the context).
+        - persistent: close the persistent context (no separate browser handle).
+        - fresh: close context, then browser.
+        """
+        self._cancel_idle_timer()
+
+        if self._launch_mode == "cdp":
+            # For CDP, browser.close() only detaches the Playwright client;
+            # the user's Chrome process and its tabs stay alive.
+            try:
+                if self._browser:
+                    self._browser.close()
+            except Exception as e:
+                logger.debug(f"[Browser] cdp disconnect error: {e}")
+        else:
+            for obj, label in [
+                (self._context, "context"),
+                (self._browser, "browser"),
+            ]:
+                try:
+                    if obj:
+                        obj.close()
+                except Exception as e:
+                    logger.debug(f"[Browser] {label} close error: {e}")
+
+        try:
+            if self._playwright:
+                self._playwright.stop()
+        except Exception as e:
+            logger.debug(f"[Browser] playwright stop error: {e}")
+        self._page = None
+        self._context = None
+        self._browser = None
+        self._playwright = None
+        logger.info("[Browser] Browser closed")
+
+    def _submit(self, fn: Callable, *args, **kwargs):
+        """Submit *fn* to the background thread and block until it completes."""
+        # If the browser died externally (e.g. user closed the window), tear
+        # down the stale thread first so _start_thread() will relaunch fresh.
+        if self._needs_restart:
+            logger.info("[Browser] Restarting after detecting closed browser")
+            self.close()
+            self._needs_restart = False
+
+        self._start_thread()
+
+        if not self._alive:
+            raise RuntimeError("Browser is not available")
+
+        self._reset_idle_timer()
+
+        result_slot: Dict[str, Any] = {"event": threading.Event()}
+        self._task_queue.put((fn, args, kwargs, result_slot))
+
+        # Timeout prevents permanent hang if the background thread crashes
+        completed = result_slot["event"].wait(timeout=120)
+        if not completed:
+            raise TimeoutError("Browser operation timed out (120s)")
+
+        if "error" in result_slot:
+            raise result_slot["error"]
+        return result_slot.get("value")
+
+    # ------------------------------------------------------------------
+    # Idle auto-release
+    # ------------------------------------------------------------------
+
+    def _reset_idle_timer(self):
+        self._cancel_idle_timer()
+        if self._idle_timeout > 0:
+            self._idle_timer = threading.Timer(self._idle_timeout, self._on_idle_timeout)
+            self._idle_timer.daemon = True
+            self._idle_timer.start()
+
+    def _cancel_idle_timer(self):
+        if self._idle_timer:
+            self._idle_timer.cancel()
+            self._idle_timer = None
+
+    def _on_idle_timeout(self):
+        logger.info(f"[Browser] Idle for {self._idle_timeout}s, auto-releasing browser")
+        self.close()
+
+    # ------------------------------------------------------------------
+    # Public lifecycle
+    # ------------------------------------------------------------------
+
+    def close(self):
+        """Shut down browser and background thread (safe from any thread)."""
+        self._cancel_idle_timer()
+        with self._lock:
+            if not self._alive:
+                self._needs_restart = False
+                return
+            self._alive = False
+            t = self._thread
+        if self._task_queue is not None:
+            self._task_queue.put(None)
+        if t is not None and t.is_alive():
+            t.join(timeout=10)
+        with self._lock:
+            self._thread = None
+            self._needs_restart = False
+
+    # ------------------------------------------------------------------
+    # Actions  (each method is dispatched to the background thread)
+    # ------------------------------------------------------------------
+
+    def navigate(self, url: str, timeout: int = 30000) -> Dict[str, Any]:
+        return self._submit(self._do_navigate, url, timeout)
+
+    def _do_navigate(self, url: str, timeout: int) -> Dict[str, Any]:
+        page = self._page
+        try:
+            resp = page.goto(url, wait_until="domcontentloaded", timeout=timeout)
+            status = resp.status if resp else None
+        except Exception as e:
+            return {"error": f"Navigation failed: {e}"}
+
+        try:
+            page.wait_for_load_state("networkidle", timeout=8000)
+        except Exception:
+            pass
+        page.wait_for_timeout(500)
+
+        try:
+            title = page.title()
+        except Exception:
+            title = ""
+        try:
+            current_url = page.url
+        except Exception:
+            current_url = url
+
+        return {"url": current_url, "title": title, "status": status}
+
+    def snapshot(self, selector: Optional[str] = None) -> str:
+        return self._submit(self._do_snapshot, selector)
+
+    def _do_snapshot(self, selector: Optional[str] = None) -> str:
+        page = self._page
+        try:
+            result = page.evaluate(_SNAPSHOT_JS)
+        except Exception as e:
+            return f"[Snapshot error: {e}]"
+
+        tree = result.get("tree")
+        ref_count = result.get("refCount", 0)
+        lines = _flatten_tree(tree)
+
+        try:
+            title = page.title()
+        except Exception:
+            title = ""
+        try:
+            url = page.url
+        except Exception:
+            url = ""
+
+        header = f"Page: {title}  ({url})\nInteractive elements: {ref_count}\n---"
+        body = "\n".join(lines)
+
+        max_chars = self._config.get("snapshot_max_chars", 30000)
+        if len(body) > max_chars:
+            body = body[:max_chars] + "\n... [snapshot truncated]"
+
+        return f"{header}\n{body}"
+
+    def screenshot(self, full_page: bool = False, cwd: str = "") -> str:
+        return self._submit(self._do_screenshot, full_page, cwd)
+
+    def _do_screenshot(self, full_page: bool = False, cwd: str = "") -> str:
+        page = self._page
+        save_dir = self._get_screenshot_dir(cwd)
+        filename = f"screenshot_{uuid.uuid4().hex[:8]}.png"
+        filepath = os.path.join(save_dir, filename)
+        page.screenshot(path=filepath, full_page=full_page)
+        logger.info(f"[Browser] Screenshot saved: {filepath}")
+        return filepath
+
+    def click(self, ref: Optional[int] = None, selector: Optional[str] = None,
+              timeout: int = 5000) -> Dict[str, Any]:
+        return self._submit(self._do_click, ref, selector, timeout)
+
+    def _do_click(self, ref, selector, timeout) -> Dict[str, Any]:
+        page = self._page
+        try:
+            if ref is not None:
+                result = page.evaluate(f"""
+                    () => {{
+                        const el = window.__cowRefMap && window.__cowRefMap[{ref}];
+                        if (!el) return {{ error: "ref {ref} not found. Run snapshot first." }};
+                        el.click();
+                        return {{ clicked: true, tag: el.tagName.toLowerCase() }};
+                    }}
+                """)
+                if result.get("error"):
+                    return result
+                page.wait_for_timeout(500)
+                return result
+            elif selector:
+                page.click(selector, timeout=timeout)
+                return {"clicked": True, "selector": selector}
+            else:
+                return {"error": "Provide either ref (from snapshot) or selector"}
+        except Exception as e:
+            return {"error": f"Click failed: {e}"}
+
+    def fill(self, text: str, ref: Optional[int] = None,
+             selector: Optional[str] = None, timeout: int = 5000) -> Dict[str, Any]:
+        return self._submit(self._do_fill, text, ref, selector, timeout)
+
+    def _do_fill(self, text, ref, selector, timeout) -> Dict[str, Any]:
+        page = self._page
+        try:
+            if ref is not None:
+                result = page.evaluate(f"""
+                    () => {{
+                        const el = window.__cowRefMap && window.__cowRefMap[{ref}];
+                        if (!el) return {{ error: "ref {ref} not found. Run snapshot first." }};
+                        el.focus();
+                        el.value = "";
+                        return {{ tag: el.tagName.toLowerCase(), name: el.name || "" }};
+                    }}
+                """)
+                if result.get("error"):
+                    return result
+                page.keyboard.type(text)
+                return {"filled": True, "ref": ref, "text": text}
+            elif selector:
+                page.fill(selector, text, timeout=timeout)
+                return {"filled": True, "selector": selector, "text": text}
+            else:
+                return {"error": "Provide either ref (from snapshot) or selector"}
+        except Exception as e:
+            return {"error": f"Fill failed: {e}"}
+
+    def select(self, value: str, ref: Optional[int] = None,
+               selector: Optional[str] = None, timeout: int = 5000) -> Dict[str, Any]:
+        return self._submit(self._do_select, value, ref, selector, timeout)
+
+    def _do_select(self, value, ref, selector, timeout) -> Dict[str, Any]:
+        page = self._page
+        try:
+            if ref is not None:
+                result = page.evaluate(f"""
+                    () => {{
+                        const el = window.__cowRefMap && window.__cowRefMap[{ref}];
+                        if (!el || el.tagName.toLowerCase() !== "select")
+                            return {{ error: "ref {ref} is not a <select> element" }};
+                        el.value = {repr(value)};
+                        el.dispatchEvent(new Event("change", {{ bubbles: true }}));
+                        return {{ selected: true, value: el.value }};
+                    }}
+                """)
+                return result
+            elif selector:
+                page.select_option(selector, value, timeout=timeout)
+                return {"selected": True, "selector": selector, "value": value}
+            else:
+                return {"error": "Provide either ref (from snapshot) or selector"}
+        except Exception as e:
+            return {"error": f"Select failed: {e}"}
+
+    def scroll(self, direction: str = "down", amount: int = 500) -> Dict[str, Any]:
+        return self._submit(self._do_scroll, direction, amount)
+
+    def _do_scroll(self, direction, amount) -> Dict[str, Any]:
+        page = self._page
+        delta_map = {
+            "down": (0, amount),
+            "up": (0, -amount),
+            "right": (amount, 0),
+            "left": (-amount, 0),
+        }
+        dx, dy = delta_map.get(direction, (0, amount))
+        try:
+            page.mouse.wheel(dx, dy)
+            page.wait_for_timeout(300)
+            scroll_info = page.evaluate("""
+                () => ({
+                    scrollX: window.scrollX,
+                    scrollY: window.scrollY,
+                    scrollHeight: document.documentElement.scrollHeight,
+                    clientHeight: document.documentElement.clientHeight
+                })
+            """)
+            return {"scrolled": direction, "amount": amount, **scroll_info}
+        except Exception as e:
+            return {"error": f"Scroll failed: {e}"}
+
+    def wait(self, selector: Optional[str] = None, timeout: int = 5000,
+             state: str = "visible") -> Dict[str, Any]:
+        return self._submit(self._do_wait, selector, timeout, state)
+
+    def _do_wait(self, selector, timeout, state) -> Dict[str, Any]:
+        page = self._page
+        try:
+            if selector:
+                page.wait_for_selector(selector, timeout=timeout, state=state)
+                return {"waited": True, "selector": selector, "state": state}
+            else:
+                page.wait_for_timeout(timeout)
+                return {"waited": True, "timeout_ms": timeout}
+        except Exception as e:
+            return {"error": f"Wait failed: {e}"}
+
+    def go_back(self) -> Dict[str, Any]:
+        return self._submit(self._do_go_back)
+
+    def _do_go_back(self) -> Dict[str, Any]:
+        page = self._page
+        try:
+            page.go_back(wait_until="domcontentloaded", timeout=10000)
+            try:
+                title = page.title()
+            except Exception:
+                title = ""
+            try:
+                url = page.url
+            except Exception:
+                url = ""
+            return {"url": url, "title": title}
+        except Exception as e:
+            return {"error": f"Go back failed: {e}"}
+
+    def go_forward(self) -> Dict[str, Any]:
+        return self._submit(self._do_go_forward)
+
+    def _do_go_forward(self) -> Dict[str, Any]:
+        page = self._page
+        try:
+            page.go_forward(wait_until="domcontentloaded", timeout=10000)
+            try:
+                title = page.title()
+            except Exception:
+                title = ""
+            try:
+                url = page.url
+            except Exception:
+                url = ""
+            return {"url": url, "title": title}
+        except Exception as e:
+            return {"error": f"Go forward failed: {e}"}
+
+    def get_text(self, selector: str) -> Dict[str, Any]:
+        return self._submit(self._do_get_text, selector)
+
+    def _do_get_text(self, selector) -> Dict[str, Any]:
+        page = self._page
+        try:
+            text = page.text_content(selector, timeout=5000)
+            return {"text": text or ""}
+        except Exception as e:
+            return {"error": f"Get text failed: {e}"}
+
+    def evaluate(self, script: str) -> Dict[str, Any]:
+        return self._submit(self._do_evaluate, script)
+
+    def _do_evaluate(self, script) -> Dict[str, Any]:
+        page = self._page
+        try:
+            result = page.evaluate(script)
+            return {"result": result}
+        except Exception as e:
+            return {"error": f"Evaluate failed: {e}"}
+
+    def press(self, key: str) -> Dict[str, Any]:
+        return self._submit(self._do_press, key)
+
+    def _do_press(self, key) -> Dict[str, Any]:
+        page = self._page
+        try:
+            page.keyboard.press(key)
+            page.wait_for_timeout(300)
+            return {"pressed": key}
+        except Exception as e:
+            return {"error": f"Press failed: {e}"}
+
+    # ------------------------------------------------------------------
+    # Helpers
+    # ------------------------------------------------------------------
+
+    def _get_screenshot_dir(self, cwd: str = "") -> str:
+        if self._screenshot_dir and os.path.isdir(self._screenshot_dir):
+            return self._screenshot_dir
+        base = cwd or os.getcwd()
+        d = os.path.join(base, "tmp")
+        os.makedirs(d, exist_ok=True)
+        self._screenshot_dir = d
+        return d

agent/tools/browser/browser_tool.py

@@ -0,0 +1,377 @@
+"""
+Browser tool - Control a Chromium browser for web navigation and interaction.
+
+Uses Playwright under the hood. Browser instance is lazily started on first
+use, reused across tool calls within the same session, and cleaned up via
+close().
+
+Launch modes (configured under `tools.browser` in config.json):
+  - persistent (default): Chromium runs with a persistent user_data_dir
+    (default `~/.cow/browser_profile`), so cookies and login state survive
+    across runs. The user only needs to log in once.
+  - cdp: When `cdp_endpoint` is set, attach to an externally launched Chrome
+    via the Chrome DevTools Protocol. Lets the agent reuse the user's real
+    browser (with all logins / extensions / true fingerprints).
+  - fresh: Set `persistent` to false to fall back to a clean context every run.
+"""
+
+import ipaddress
+import json
+import os
+import socket
+from typing import Dict, Any, Optional
+from urllib.parse import urlparse
+
+from agent.tools.base_tool import BaseTool, ToolResult
+from agent.tools.browser.browser_service import BrowserService
+from common.log import logger
+
+
+# Cloud-metadata endpoints worth blocking even though they are not link-local.
+# (169.254.169.254 — AWS/GCP/Azure IMDS — is already covered by is_link_local;
+# fd00:ec2::254 is the AWS IPv6 IMDS address.)
+_CLOUD_METADATA_IPS = frozenset({ipaddress.ip_address("fd00:ec2::254")})
+
+
+class BrowserTool(BaseTool):
+    """Single tool exposing all browser actions via an 'action' parameter."""
+
+    name: str = "browser"
+    description: str = (
+        "Control a browser to navigate web pages, interact with elements, and extract content. "
+        "Actions: navigate, snapshot, click, fill, select, scroll, screenshot, wait, back, forward, "
+        "get_text, press, evaluate.\n\n"
+        "Workflow: navigate (auto-includes snapshot with element refs) → click/fill/select by ref → snapshot to verify.\n\n"
+        "Use snapshot as the primary way to read pages. Use screenshot + send to show key results to the user. "
+        "For login/CAPTCHA/authorization etc., screenshot and ask the user for help. "
+        "Login state is persisted across sessions (cookies / localStorage are kept in a "
+        "user profile directory), so once the user logs in to a site, the agent can keep "
+        "using it without logging in again."
+    )
+
+    params: dict = {
+        "type": "object",
+        "properties": {
+            "action": {
+                "type": "string",
+                "description": (
+                    "The browser action to perform. One of: "
+                    "navigate, snapshot, click, fill, select, scroll, "
+                    "screenshot, wait, back, forward, get_text, press, evaluate"
+                ),
+                "enum": [
+                    "navigate", "snapshot", "click", "fill", "select", "scroll",
+                    "screenshot", "wait", "back", "forward", "get_text", "press",
+                    "evaluate"
+                ]
+            },
+            "url": {
+                "type": "string",
+                "description": "URL to navigate to (for 'navigate' action)"
+            },
+            "ref": {
+                "type": "integer",
+                "description": "Element ref number from snapshot (for click/fill/select)"
+            },
+            "selector": {
+                "type": "string",
+                "description": "CSS selector as fallback when ref is unavailable (for click/fill/select/wait/get_text)"
+            },
+            "text": {
+                "type": "string",
+                "description": "Text to type (for 'fill' action)"
+            },
+            "value": {
+                "type": "string",
+                "description": "Option value (for 'select' action)"
+            },
+            "key": {
+                "type": "string",
+                "description": "Key to press, e.g. Enter, Tab, Escape (for 'press' action)"
+            },
+            "direction": {
+                "type": "string",
+                "description": "Scroll direction: up, down, left, right (for 'scroll' action, default: down)"
+            },
+            "script": {
+                "type": "string",
+                "description": "JavaScript code to execute (for 'evaluate' action)"
+            },
+            "full_page": {
+                "type": "boolean",
+                "description": "Capture full page screenshot (for 'screenshot' action, default: false)"
+            },
+            "timeout": {
+                "type": "integer",
+                "description": "Timeout in milliseconds (optional, default varies by action)"
+            }
+        },
+        "required": ["action"]
+    }
+
+    _shared_service: Optional[BrowserService] = None
+
+    def __init__(self, config: dict = None):
+        self.config = config or {}
+        self.cwd = self.config.get("cwd", os.getcwd())
+        self._service: Optional[BrowserService] = None
+
+    def _get_service(self) -> BrowserService:
+        """Get or create the browser service, sharing across copies."""
+        if self._service is not None:
+            return self._service
+
+        # Reuse shared service across tool copies within the same session
+        if BrowserTool._shared_service is not None:
+            self._service = BrowserTool._shared_service
+            return self._service
+
+        self._service = BrowserService(self.config)
+        BrowserTool._shared_service = self._service
+        return self._service
+
+    def _allow_private_targets(self) -> bool:
+        """Whether the link-local / cloud-metadata guard is disabled.
+
+        Defaults to False (guard active). Loopback and RFC1918/LAN targets are
+        always reachable so local dev servers work out of the box; this opt-out
+        only lifts the remaining block on link-local / cloud-metadata targets,
+        for an operator who deliberately needs them, by setting
+        ``allow_private_targets: true`` under ``tools.browser`` in config.json.
+        """
+        return bool(self.config.get("allow_private_targets", False))
+
+    @staticmethod
+    def _validate_url_safe(url: str) -> None:
+        """Reject URLs that target link-local / cloud-metadata addresses (SSRF guard).
+
+        Resolves the hostname to its IP address(es) and blocks any that are
+        link-local (169.254.0.0/16 — which includes the 169.254.169.254
+        cloud-metadata endpoint — and IPv6 fe80::/10) or a known IPv6
+        cloud-metadata address. Also rejects URLs with no host, non-HTTP(S)
+        schemes, or hosts that fail DNS resolution.
+
+        Loopback and RFC1918/LAN targets are intentionally left reachable:
+        unlike the vision/web_fetch tools, the browser legitimately opens local
+        pages (a dev server on ``localhost`` / ``127.0.0.1`` / a LAN IP), so a
+        blanket "block all internal" policy would break that core workflow.
+
+        Raises:
+            ValueError: if the URL targets a disallowed address.
+        """
+        parsed = urlparse(url)
+        if parsed.scheme not in ("http", "https"):
+            raise ValueError(f"Unsupported URL scheme: {parsed.scheme}")
+
+        hostname = parsed.hostname
+        if not hostname:
+            raise ValueError("URL has no hostname")
+
+        try:
+            # Resolve all addresses for the hostname.
+            addr_infos = socket.getaddrinfo(hostname, None, socket.AF_UNSPEC, socket.SOCK_STREAM)
+        except socket.gaierror:
+            raise ValueError(f"Cannot resolve hostname: {hostname}")
+
+        for family, _, _, _, sockaddr in addr_infos:
+            ip_str = sockaddr[0]
+            ip = ipaddress.ip_address(ip_str)
+            # Block only the high-risk targets — link-local (incl. the
+            # 169.254.169.254 cloud-metadata endpoint) and the IPv6 metadata
+            # address. Loopback and RFC1918/LAN stay reachable for local dev.
+            if ip.is_link_local or ip in _CLOUD_METADATA_IPS:
+                raise ValueError(
+                    f"URL resolves to a link-local / cloud-metadata address "
+                    f"({ip_str}), request blocked for security"
+                )
+
+    def execute(self, args: Dict[str, Any]) -> ToolResult:
+        action = args.get("action", "").strip().lower()
+        if not action:
+            return ToolResult.fail("Error: 'action' parameter is required")
+
+        handler = self._ACTION_MAP.get(action)
+        if not handler:
+            valid = ", ".join(sorted(self._ACTION_MAP.keys()))
+            return ToolResult.fail(f"Unknown action '{action}'. Valid actions: {valid}")
+
+        try:
+            return handler(self, args)
+        except Exception as e:
+            logger.error(f"[Browser] Action '{action}' error: {e}")
+            return ToolResult.fail(f"Browser error ({action}): {e}")
+
+    # ------------------------------------------------------------------
+    # Action handlers
+    # ------------------------------------------------------------------
+
+    def _do_navigate(self, args: Dict[str, Any]) -> ToolResult:
+        url = args.get("url", "").strip()
+        if not url:
+            return ToolResult.fail("Error: 'url' is required for navigate action")
+        # Only auto-prepend https:// for bare hosts; preserve file://, about:, data:, etc.
+        if "://" not in url and not url.startswith(("about:", "data:")):
+            url = "https://" + url
+        # SSRF guard: for http(s) targets, reject hosts that resolve to
+        # link-local / cloud-metadata addresses before the browser navigates
+        # (and then auto-snapshots the page back to the model). Loopback and
+        # RFC1918/LAN are allowed so local dev servers work. Non-HTTP schemes
+        # (about:/data:/file:/chrome:) are not network-egress targets here.
+        if url.split(":", 1)[0].lower() in ("http", "https") and not self._allow_private_targets():
+            try:
+                self._validate_url_safe(url)
+            except ValueError as e:
+                return ToolResult.fail(f"Error: {e}")
+        timeout = args.get("timeout", 30000)
+        service = self._get_service()
+        result = service.navigate(url, timeout=timeout)
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        # Auto-snapshot after navigation so the agent gets page content in one call
+        snapshot_text = service.snapshot()
+        return ToolResult.success(
+            f"Navigated to: {result['url']}\nTitle: {result['title']}\nStatus: {result['status']}\n\n"
+            f"--- Page Snapshot ---\n{snapshot_text}"
+        )
+
+    def _do_snapshot(self, args: Dict[str, Any]) -> ToolResult:
+        selector = args.get("selector")
+        text = self._get_service().snapshot(selector=selector)
+        return ToolResult.success(text)
+
+    def _do_click(self, args: Dict[str, Any]) -> ToolResult:
+        ref = args.get("ref")
+        selector = args.get("selector")
+        timeout = args.get("timeout", 5000)
+        result = self._get_service().click(ref=ref, selector=selector, timeout=timeout)
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        return ToolResult.success(f"Clicked successfully. Use 'snapshot' to see updated page.")
+
+    def _do_fill(self, args: Dict[str, Any]) -> ToolResult:
+        text = args.get("text", "")
+        ref = args.get("ref")
+        selector = args.get("selector")
+        timeout = args.get("timeout", 5000)
+        if not text and text != "":
+            return ToolResult.fail("Error: 'text' is required for fill action")
+        result = self._get_service().fill(text, ref=ref, selector=selector, timeout=timeout)
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        return ToolResult.success(f"Filled text into element. Use 'snapshot' to verify.")
+
+    def _do_select(self, args: Dict[str, Any]) -> ToolResult:
+        value = args.get("value", "")
+        ref = args.get("ref")
+        selector = args.get("selector")
+        timeout = args.get("timeout", 5000)
+        if not value:
+            return ToolResult.fail("Error: 'value' is required for select action")
+        result = self._get_service().select(value, ref=ref, selector=selector, timeout=timeout)
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        return ToolResult.success(f"Selected option '{value}'.")
+
+    def _do_scroll(self, args: Dict[str, Any]) -> ToolResult:
+        direction = args.get("direction", "down")
+        amount = args.get("timeout", 500)  # reuse timeout field or default
+        if "amount" in args:
+            amount = args["amount"]
+        result = self._get_service().scroll(direction=direction, amount=amount)
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        pos = f"scrollY={result.get('scrollY', '?')}/{result.get('scrollHeight', '?')}"
+        return ToolResult.success(f"Scrolled {direction}. Position: {pos}")
+
+    def _do_screenshot(self, args: Dict[str, Any]) -> ToolResult:
+        full_page = args.get("full_page", False)
+        filepath = self._get_service().screenshot(full_page=full_page, cwd=self.cwd)
+        return ToolResult.success(f"Screenshot saved to: {filepath}")
+
+    def _do_wait(self, args: Dict[str, Any]) -> ToolResult:
+        selector = args.get("selector")
+        timeout = args.get("timeout", 5000)
+        result = self._get_service().wait(selector=selector, timeout=timeout)
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        return ToolResult.success(f"Wait completed.")
+
+    def _do_back(self, args: Dict[str, Any]) -> ToolResult:
+        result = self._get_service().go_back()
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        return ToolResult.success(f"Navigated back to: {result['url']}")
+
+    def _do_forward(self, args: Dict[str, Any]) -> ToolResult:
+        result = self._get_service().go_forward()
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        return ToolResult.success(f"Navigated forward to: {result['url']}")
+
+    def _do_get_text(self, args: Dict[str, Any]) -> ToolResult:
+        selector = args.get("selector", "").strip()
+        if not selector:
+            return ToolResult.fail("Error: 'selector' is required for get_text action")
+        result = self._get_service().get_text(selector)
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        return ToolResult.success(result["text"])
+
+    def _do_press(self, args: Dict[str, Any]) -> ToolResult:
+        key = args.get("key", "").strip()
+        if not key:
+            return ToolResult.fail("Error: 'key' is required for press action")
+        result = self._get_service().press(key)
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        return ToolResult.success(f"Pressed key: {key}")
+
+    def _do_evaluate(self, args: Dict[str, Any]) -> ToolResult:
+        script = args.get("script", "").strip()
+        if not script:
+            return ToolResult.fail("Error: 'script' is required for evaluate action")
+        result = self._get_service().evaluate(script)
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        val = result.get("result")
+        if isinstance(val, (dict, list)):
+            return ToolResult.success(json.dumps(val, ensure_ascii=False, indent=2))
+        return ToolResult.success(str(val) if val is not None else "(no return value)")
+
+    # Action dispatch table
+    _ACTION_MAP = {
+        "navigate": _do_navigate,
+        "snapshot": _do_snapshot,
+        "click": _do_click,
+        "fill": _do_fill,
+        "select": _do_select,
+        "scroll": _do_scroll,
+        "screenshot": _do_screenshot,
+        "wait": _do_wait,
+        "back": _do_back,
+        "forward": _do_forward,
+        "get_text": _do_get_text,
+        "press": _do_press,
+        "evaluate": _do_evaluate,
+    }
+
+    # ------------------------------------------------------------------
+    # Lifecycle
+    # ------------------------------------------------------------------
+
+    def copy(self):
+        """Share browser instance across tool copies (avoids re-launching)."""
+        new_tool = BrowserTool(self.config)
+        new_tool.model = self.model
+        new_tool.context = getattr(self, "context", None)
+        new_tool.cwd = self.cwd
+        new_tool._service = self._service
+        return new_tool
+
+    def close(self):
+        """Release browser resources."""
+        if self._service:
+            self._service.close()
+            self._service = None
+        BrowserTool._shared_service = None
+        logger.info("[Browser] BrowserTool closed")

agent/tools/browser_tool.py

@@ -1,18 +0,0 @@
-def copy(self):
-    """
-    Special copy method for browser tool to avoid recreating browser instance.
-    
-    :return: A new instance with shared browser reference but unique model
-    """
-    new_tool = self.__class__()
-    
-    # Copy essential attributes
-    new_tool.model = self.model
-    new_tool.context = getattr(self, 'context', None)
-    new_tool.config = getattr(self, 'config', None)
-    
-    # Share the browser instance instead of creating a new one
-    if hasattr(self, 'browser'):
-        new_tool.browser = self.browser
-    
-    return new_tool 

agent/tools/evolution_undo/__init__.py

@@ -0,0 +1,3 @@
+from agent.tools.evolution_undo.evolution_undo import EvolutionUndoTool
+
+__all__ = ["EvolutionUndoTool"]

agent/tools/evolution_undo/evolution_undo.py

@@ -0,0 +1,58 @@
+"""Evolution undo tool.
+
+Lets the main chat agent roll back a previous self-evolution when the user asks
+("undo the last learning"). The rollback itself is a deterministic FILE RESTORE
+from the snapshot taken before the evolution — the model only supplies the
+backup_id it reads from the [EVOLUTION] record in the conversation. No LLM-driven
+re-editing is involved, so a restore can never make things worse.
+"""
+
+from agent.tools.base_tool import BaseTool, ToolResult
+
+
+class EvolutionUndoTool(BaseTool):
+    """Restore memory/skill files to the state before a self-evolution."""
+
+    name: str = "evolution_undo"
+    description: str = (
+        "Undo a previous self-evolution (self-learning) by restoring the "
+        "memory/skill files to their state before that learning. Use this when "
+        "the user asks to undo / revert / roll back the last self-learning. "
+        "Find the backup_id in the most recent [EVOLUTION] record in the "
+        "conversation and pass it here."
+    )
+    params: dict = {
+        "type": "object",
+        "properties": {
+            "backup_id": {
+                "type": "string",
+                "description": (
+                    "The backup_id from the [EVOLUTION] record to restore "
+                    "(e.g. '20260607-155551-850')."
+                ),
+            }
+        },
+        "required": ["backup_id"],
+    }
+
+    def execute(self, args: dict):
+        backup_id = (args.get("backup_id") or "").strip()
+        if not backup_id:
+            return ToolResult.fail("Error: backup_id is required")
+        try:
+            from agent.memory.config import get_default_memory_config
+            from agent.evolution.backup import restore_backup
+
+            workspace_dir = get_default_memory_config().get_workspace()
+            ok = restore_backup(workspace_dir, backup_id)
+            if ok:
+                return ToolResult.success(
+                    f"Restored memory/skills to the state before evolution "
+                    f"{backup_id}. The previous self-learning has been undone."
+                )
+            return ToolResult.fail(
+                f"Could not find or restore backup {backup_id}. It may have "
+                f"expired or already been rolled back."
+            )
+        except Exception as e:
+            return ToolResult.fail(f"Error during undo: {e}")

agent/tools/mcp/__init__.py

@@ -0,0 +1,4 @@
+from agent.tools.mcp.mcp_client import McpClient, McpClientRegistry
+from agent.tools.mcp.mcp_tool import McpTool
+
+__all__ = ["McpClient", "McpClientRegistry", "McpTool"]

agent/tools/mcp/mcp_client.py

@@ -0,0 +1,582 @@
+"""
+MCP (Model Context Protocol) client module.
+
+Implements JSON-RPC 2.0 over stdio, SSE and Streamable HTTP transports
+without any external MCP SDK dependency.
+"""
+
+import json
+import os
+import queue
+import subprocess
+import threading
+import urllib.request
+import urllib.error
+from typing import Optional
+
+from common.log import logger
+
+
+# Aliases accepted for the Streamable HTTP transport type
+_STREAMABLE_HTTP_ALIASES = {"streamable-http", "streamable_http", "streamablehttp", "http"}
+
+
+class McpClient:
+    """Single MCP Server client supporting stdio, SSE and Streamable HTTP transports."""
+
+    def __init__(self, config: dict):
+        """
+        config examples:
+          stdio:           {"name": "filesystem", "type": "stdio", "command": "npx", "args": [...]}
+          SSE:             {"name": "my-api",    "type": "sse",   "url": "http://localhost:8000/sse"}
+          streamable-http: {"name": "pubmed",    "type": "streamable-http", "url": "https://x/mcp"}
+        """
+        self.config = config
+        self.name: str = config.get("name", "unknown")
+        raw_transport: str = config.get("type", "stdio")
+        # Per-server timeout for tool calls (default 120s, suitable for data queries)
+        self._timeout: int = int(config.get("timeout", 120))
+        # Normalize streamable-http aliases to a single internal key
+        self.transport: str = (
+            "streamable-http"
+            if raw_transport.lower() in _STREAMABLE_HTTP_ALIASES
+            else raw_transport
+        )
+
+        # stdio state
+        self._proc: Optional[subprocess.Popen] = None
+        self._read_queue: queue.Queue = queue.Queue()
+
+        # SSE state
+        self._sse_url: Optional[str] = None
+        self._post_url: Optional[str] = None  # endpoint for sending messages (resolved from SSE)
+
+        # Streamable HTTP state
+        self._http_url: Optional[str] = None
+        self._http_headers: dict = {}  # extra headers from user config (e.g. Authorization)
+        self._http_session_id: Optional[str] = None  # Mcp-Session-Id assigned by the server
+
+        # Shared state
+        self._next_id = 1
+        self._id_lock = threading.Lock()
+        # _call_lock serializes all requests on the single stdio pipe.
+        # SSE and streamable-http use independent HTTP requests, so they
+        # do not acquire this lock (see _send_request).
+        self._call_lock = threading.Lock()
+        # _http_lock protects _http_session_id initialization across
+        # concurrent streamable-http requests.
+        self._http_lock = threading.Lock()
+        self._initialized = False
+
+    # ------------------------------------------------------------------
+    # Public interface
+    # ------------------------------------------------------------------
+
+    def initialize(self) -> bool:
+        """Connect and perform the MCP handshake. Returns True on success."""
+        try:
+            if self.transport == "stdio":
+                return self._init_stdio()
+            elif self.transport == "sse":
+                return self._init_sse()
+            elif self.transport == "streamable-http":
+                return self._init_streamable_http()
+            else:
+                logger.warning(f"[MCP:{self.name}] Unknown transport type: {self.transport!r}")
+                return False
+        except Exception as e:
+            logger.warning(f"[MCP:{self.name}] Initialization failed: {e}")
+            return False
+
+    def list_tools(self) -> list:
+        """Return the tool list from this server.
+
+        Each item is a dict: {"name": str, "description": str, "inputSchema": dict}
+        """
+        try:
+            resp = self._send_request("tools/list", {})
+            tools = resp.get("result", {}).get("tools", [])
+            return [
+                {
+                    "name": t.get("name", ""),
+                    "description": t.get("description", ""),
+                    "inputSchema": t.get("inputSchema", {}),
+                }
+                for t in tools
+            ]
+        except Exception as e:
+            logger.warning(f"[MCP:{self.name}] list_tools failed: {e}")
+            return []
+
+    def call_tool(self, name: str, arguments: dict) -> str:
+        """Call a tool and return the result as a string."""
+        try:
+            resp = self._send_request("tools/call", {"name": name, "arguments": arguments})
+            content = resp.get("result", {}).get("content", [])
+            parts = [item.get("text", "") for item in content if item.get("type") == "text"]
+            return "\n".join(parts)
+        except Exception as e:
+            logger.warning(f"[MCP:{self.name}] call_tool({name}) failed: {e}")
+            return f"Error: {e}"
+
+    def shutdown(self):
+        """Close the connection / terminate the child process."""
+        if self._proc is not None:
+            try:
+                self._proc.stdin.close()
+            except Exception:
+                pass
+            try:
+                self._proc.terminate()
+                self._proc.wait(timeout=5)
+            except Exception:
+                try:
+                    self._proc.kill()
+                except Exception:
+                    pass
+            self._proc = None
+            logger.debug(f"[MCP:{self.name}] stdio process terminated")
+
+        # Best-effort streamable-http session termination
+        if self.transport == "streamable-http" and self._http_session_id and self._http_url:
+            try:
+                req = urllib.request.Request(
+                    self._http_url,
+                    method="DELETE",
+                    headers={"Mcp-Session-Id": self._http_session_id, **self._http_headers},
+                )
+                with urllib.request.urlopen(req, timeout=5):
+                    pass
+            except Exception:
+                pass
+            self._http_session_id = None
+
+        self._initialized = False
+
+    # ------------------------------------------------------------------
+    # stdio transport
+    # ------------------------------------------------------------------
+
+    def _init_stdio(self) -> bool:
+        command = self.config.get("command")
+        if not command:
+            logger.warning(f"[MCP:{self.name}] stdio config missing 'command'")
+            return False
+
+        args = self.config.get("args", [])
+        extra_env = self.config.get("env", None)
+        env = {**os.environ, **extra_env} if extra_env else None
+
+        self._proc = subprocess.Popen(
+            [command] + list(args),
+            stdin=subprocess.PIPE,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            text=True,
+            encoding="utf-8",
+            env=env,
+        )
+        logger.debug(f"[MCP:{self.name}] stdio process started (pid={self._proc.pid})")
+
+        threading.Thread(
+            target=self._drain_stderr, daemon=True, name=f"mcp-stderr-{self.name}"
+        ).start()
+        threading.Thread(
+            target=self._drain_stdout, daemon=True, name=f"mcp-stdout-{self.name}"
+        ).start()
+
+        return self._handshake()
+
+    def _drain_stderr(self):
+        for line in self._proc.stderr:
+            line = line.strip()
+            if line:
+                logger.warning(f"[MCP:{self.name}] stderr: {line}")
+
+    def _drain_stdout(self):
+        """Background thread: read lines from stdout and put them into the queue."""
+        try:
+            for line in self._proc.stdout:
+                self._read_queue.put(line)
+        except Exception:
+            pass
+        finally:
+            try:
+                self._read_queue.put("")
+            except Exception:
+                pass
+
+    def _readline_with_timeout(self, timeout: Optional[int] = None) -> str:
+        """Read one line from stdio stdout with a hard timeout (cross-platform).
+
+        Uses the per-server timeout from mcp.json config when no explicit
+        timeout is provided.
+        """
+        effective = timeout if timeout is not None else self._timeout
+        try:
+            line = self._read_queue.get(timeout=effective)
+        except queue.Empty:
+            raise TimeoutError(f"[MCP:{self.name}] stdio read timed out after {effective}s")
+        if not line:
+            raise IOError(f"[MCP:{self.name}] stdio process closed unexpectedly")
+        return line
+
+    def _stdio_send(self, message: dict) -> dict:
+        """Send a JSON-RPC message over stdio and read the response."""
+        raw = json.dumps(message) + "\n"
+        self._proc.stdin.write(raw)
+        self._proc.stdin.flush()
+
+        expected_id = message.get("id")
+        while True:
+            line = self._readline_with_timeout()
+            if not line:
+                raise IOError(f"[MCP:{self.name}] stdio process closed unexpectedly")
+            line = line.strip()
+            if not line:
+                continue
+            try:
+                data = json.loads(line)
+            except json.JSONDecodeError:
+                continue
+            if "id" not in data:
+                logger.debug(f"[MCP:{self.name}] notification skipped: {data.get('method', '?')}")
+                continue
+            # Verify response id matches request id to avoid consuming a stale
+            # response left over from a previously failed/timed-out request.
+            if data.get("id") != expected_id:
+                logger.warning(
+                    f"[MCP:{self.name}] Stale response id={data.get('id')} "
+                    f"(expected {expected_id}), skipping"
+                )
+                continue
+            return data
+
+    # ------------------------------------------------------------------
+    # SSE transport
+    # ------------------------------------------------------------------
+
+    def _init_sse(self) -> bool:
+        url = self.config.get("url")
+        if not url:
+            logger.warning(f"[MCP:{self.name}] SSE config missing 'url'")
+            return False
+
+        self._sse_url = url
+
+        # Read the first SSE event to discover the POST endpoint
+        try:
+            self._post_url = self._sse_discover_endpoint()
+        except Exception as e:
+            logger.warning(f"[MCP:{self.name}] SSE endpoint discovery failed: {e}")
+            return False
+
+        return self._handshake()
+
+    def _sse_discover_endpoint(self) -> str:
+        """Open SSE stream and read the 'endpoint' event to learn the POST URL."""
+        req = urllib.request.Request(
+            self._sse_url,
+            headers={"Accept": "text/event-stream"},
+        )
+        with urllib.request.urlopen(req, timeout=10) as resp:
+            for raw_line in resp:
+                line = raw_line.decode("utf-8").rstrip("\n\r")
+                if line.startswith("data:"):
+                    data = line[len("data:"):].strip()
+                    # Some servers send JSON with a "uri" or plain path
+                    if data.startswith("{"):
+                        parsed = json.loads(data)
+                        return parsed.get("uri") or parsed.get("url") or parsed.get("endpoint")
+                    # Plain relative or absolute URL
+                    if data.startswith("http"):
+                        return data
+                    # Relative path: resolve against SSE base
+                    from urllib.parse import urljoin
+                    return urljoin(self._sse_url, data)
+        raise ValueError(f"[MCP:{self.name}] No endpoint event received from SSE stream")
+
+    def _sse_send(self, message: dict) -> dict:
+        """POST a JSON-RPC message to the server and return the response."""
+        body = json.dumps(message).encode("utf-8")
+        req = urllib.request.Request(
+            self._post_url,
+            data=body,
+            method="POST",
+            headers={"Content-Type": "application/json"},
+        )
+        with urllib.request.urlopen(req, timeout=30) as resp:
+            raw = resp.read().decode("utf-8")
+            return json.loads(raw)
+
+    # ------------------------------------------------------------------
+    # Streamable HTTP transport (MCP spec 2025-03-26)
+    # ------------------------------------------------------------------
+
+    def _init_streamable_http(self) -> bool:
+        url = self.config.get("url")
+        if not url:
+            logger.warning(f"[MCP:{self.name}] streamable-http config missing 'url'")
+            return False
+
+        self._http_url = url
+        # Allow user-provided headers (e.g. {"Authorization": "Bearer xxx"})
+        extra_headers = self.config.get("headers") or {}
+        if isinstance(extra_headers, dict):
+            self._http_headers = {str(k): str(v) for k, v in extra_headers.items()}
+
+        return self._handshake()
+
+    def _streamable_http_send(self, message: dict) -> dict:
+        """POST a JSON-RPC request and return the response (JSON or SSE-wrapped)."""
+        return self._streamable_http_post(message, expect_response=True)
+
+    def _streamable_http_post(self, message: dict, expect_response: bool) -> dict:
+        """
+        POST a JSON-RPC message over Streamable HTTP.
+
+        Per the spec, the response Content-Type can be either:
+          - application/json   -> single JSON-RPC response in body
+          - text/event-stream  -> SSE stream; we read until we get a matching response
+        """
+        body = json.dumps(message).encode("utf-8")
+        headers = {
+            "Content-Type": "application/json",
+            "Accept": "application/json, text/event-stream",
+        }
+        # Read session id under lock to avoid racing with the
+        # initialization write below during concurrent requests.
+        with self._http_lock:
+            sid = self._http_session_id
+        if sid:
+            headers["Mcp-Session-Id"] = sid
+        headers.update(self._http_headers)
+
+        req = urllib.request.Request(
+            self._http_url,
+            data=body,
+            method="POST",
+            headers=headers,
+        )
+
+        try:
+            resp = urllib.request.urlopen(req, timeout=30)
+        except urllib.error.HTTPError as e:
+            # Surface the server-provided error body for easier debugging
+            detail = ""
+            try:
+                detail = e.read().decode("utf-8", errors="ignore")
+            except Exception:
+                pass
+            raise IOError(
+                f"[MCP:{self.name}] streamable-http HTTP {e.code}: {detail[:200]}"
+            )
+
+        with resp:
+            # Capture session id assigned by the server (if any)
+            session_id = resp.headers.get("Mcp-Session-Id")
+            # Double-checked lock: only the first response sets the
+            # session id, preventing concurrent initializers from
+            # overwriting each other.
+            if session_id and not self._http_session_id:
+                with self._http_lock:
+                    if not self._http_session_id:
+                        self._http_session_id = session_id
+
+            status = resp.status if hasattr(resp, "status") else resp.getcode()
+
+            # Notifications: server may reply with 202 Accepted and no body
+            if not expect_response or status == 202:
+                try:
+                    resp.read()
+                except Exception:
+                    pass
+                return {}
+
+            content_type = (resp.headers.get("Content-Type") or "").lower()
+            expected_id = message.get("id")
+
+            if "text/event-stream" in content_type:
+                return self._read_sse_response(resp, expected_id)
+
+            raw = resp.read().decode("utf-8")
+            if not raw:
+                return {}
+            return json.loads(raw)
+
+    def _read_sse_response(self, resp, expected_id) -> dict:
+        """Read an SSE stream and return the first JSON-RPC response with matching id."""
+        data_buf: list = []
+        for raw_line in resp:
+            line = raw_line.decode("utf-8").rstrip("\n\r")
+            if line == "":
+                # End of an SSE event, attempt to parse accumulated data
+                if data_buf:
+                    payload = "\n".join(data_buf)
+                    data_buf = []
+                    try:
+                        msg = json.loads(payload)
+                    except json.JSONDecodeError:
+                        continue
+                    # Skip notifications / mismatched ids
+                    if "id" not in msg:
+                        continue
+                    if expected_id is None or msg.get("id") == expected_id:
+                        return msg
+                continue
+            if line.startswith(":"):
+                continue  # SSE comment / keepalive
+            if line.startswith("data:"):
+                data_buf.append(line[len("data:"):].lstrip())
+            # Ignore 'event:' / 'id:' lines; we only care about JSON-RPC payloads
+
+        raise IOError(f"[MCP:{self.name}] streamable-http SSE stream closed before response")
+
+    # ------------------------------------------------------------------
+    # Common JSON-RPC helpers
+    # ------------------------------------------------------------------
+
+    def _next_request_id(self) -> int:
+        with self._id_lock:
+            rid = self._next_id
+            self._next_id += 1
+        return rid
+
+    def _build_request(self, method: str, params: dict) -> dict:
+        return {
+            "jsonrpc": "2.0",
+            "id": self._next_request_id(),
+            "method": method,
+            "params": params,
+        }
+
+    def _build_notification(self, method: str, params: dict) -> dict:
+        return {"jsonrpc": "2.0", "method": method, "params": params}
+
+    def _send_request(self, method: str, params: dict) -> dict:
+        """Send a request and return the full response dict."""
+        if not self._initialized and method != "initialize":
+            raise RuntimeError(f"[MCP:{self.name}] Client not initialized")
+
+        message = self._build_request(method, params)
+
+        # stdio transport uses a single pipe and must be serialized.
+        # SSE and streamable-http use independent HTTP requests and
+        # can safely run concurrently across sessions.
+        if self.transport == "stdio":
+            with self._call_lock:
+                return self._stdio_send(message)
+        elif self.transport == "sse":
+            return self._sse_send(message)
+        elif self.transport == "streamable-http":
+            return self._streamable_http_send(message)
+        else:
+            raise ValueError(f"[MCP:{self.name}] Unsupported transport: {self.transport}")
+
+    def _send_notification(self, method: str, params: dict):
+        """Fire-and-forget notification (no response expected)."""
+        notification = self._build_notification(method, params)
+        raw = json.dumps(notification) + "\n"
+
+        if self.transport == "stdio":
+            self._proc.stdin.write(raw)
+            self._proc.stdin.flush()
+        elif self.transport == "sse":
+            body = raw.encode("utf-8")
+            req = urllib.request.Request(
+                self._post_url,
+                data=body,
+                method="POST",
+                headers={"Content-Type": "application/json"},
+            )
+            try:
+                with urllib.request.urlopen(req, timeout=10):
+                    pass
+            except Exception:
+                pass  # notifications are fire-and-forget
+        elif self.transport == "streamable-http":
+            try:
+                self._streamable_http_post(notification, expect_response=False)
+            except Exception:
+                pass  # notifications are fire-and-forget
+
+    def _handshake(self) -> bool:
+        """Perform the MCP initialize / notifications/initialized handshake."""
+        init_params = {
+            "protocolVersion": "2024-11-05",
+            "capabilities": {},
+            "clientInfo": {"name": "CowAgent", "version": "1.0"},
+        }
+        # Temporarily mark as initialized so _send_request doesn't block
+        self._initialized = True
+        try:
+            resp = self._send_request("initialize", init_params)
+        except Exception as e:
+            self._initialized = False
+            logger.warning(f"[MCP:{self.name}] Handshake initialize failed: {e}")
+            return False
+
+        if "error" in resp:
+            self._initialized = False
+            logger.warning(f"[MCP:{self.name}] Handshake error: {resp['error']}")
+            return False
+
+        self._send_notification("notifications/initialized", {})
+        logger.debug(f"[MCP:{self.name}] Handshake complete")
+        return True
+
+
+class McpClientRegistry:
+    """Global singleton managing the lifecycle of all MCP Server clients."""
+
+    _instance = None
+    _instance_lock = threading.Lock()
+
+    def __new__(cls):
+        with cls._instance_lock:
+            if cls._instance is None:
+                obj = super().__new__(cls)
+                obj._clients: dict[str, McpClient] = {}
+                obj._registry_lock = threading.Lock()
+                cls._instance = obj
+        return cls._instance
+
+    def start_all(self, configs: list) -> None:
+        """Initialize McpClient for each config entry; skip failures with a warning."""
+        if not configs:
+            return
+
+        for cfg in configs:
+            name = cfg.get("name", "<unnamed>")
+            client = McpClient(cfg)
+            ok = client.initialize()
+            if ok:
+                with self._registry_lock:
+                    self._clients[name] = client
+                logger.info(f"[MCP] Server '{name}' initialized successfully")
+            else:
+                logger.warning(f"[MCP] Server '{name}' failed to initialize — skipping")
+
+    def get(self, server_name: str) -> Optional[McpClient]:
+        """Return the initialized client for server_name, or None."""
+        with self._registry_lock:
+            return self._clients.get(server_name)
+
+    def all_clients(self) -> dict:
+        """Return a copy of the {name: McpClient} mapping."""
+        with self._registry_lock:
+            return dict(self._clients)
+
+    def shutdown_all(self) -> None:
+        """Shut down all managed clients."""
+        with self._registry_lock:
+            clients = list(self._clients.values())
+            self._clients.clear()
+
+        for client in clients:
+            try:
+                client.shutdown()
+            except Exception as e:
+                logger.warning(f"[MCP] Error shutting down '{client.name}': {e}")
+
+        logger.info("[MCP] All servers shut down")

agent/tools/mcp/mcp_tool.py

@@ -0,0 +1,31 @@
+from agent.tools.base_tool import BaseTool, ToolResult
+from common.log import logger
+
+
+class McpTool(BaseTool):
+    """
+    将单个 MCP 工具包装为 BaseTool。
+    一个 MCP Server 可以提供多个工具，每个工具对应一个 McpTool 实例。
+    """
+
+    def __init__(self, client, tool_schema: dict, server_name: str):
+        """
+        :param client: 该工具所属的 McpClient 实例
+        :param tool_schema: MCP 返回的工具描述，格式：
+            {"name": str, "description": str, "inputSchema": dict}
+        :param server_name: Server 名称，用于日志
+        """
+        self.client = client
+        self.server_name = server_name
+        self.name = tool_schema["name"]
+        self.description = tool_schema.get("description", "")
+        self.params = tool_schema.get("inputSchema", {})
+
+    def execute(self, params: dict) -> ToolResult:
+        logger.info(f"[McpTool] server={self.server_name} tool={self.name} params={params}")
+        try:
+            result = self.client.call_tool(self.name, params)
+            return ToolResult.success(result)
+        except Exception as e:
+            logger.error(f"[McpTool] server={self.server_name} tool={self.name} error: {e}")
+            return ToolResult.fail(str(e))

agent/tools/mcp/tool_retrieval.py

@@ -0,0 +1,159 @@
+# encoding:utf-8
+"""
+On-demand MCP tool retrieval.
+
+Pure, stateless selection helpers used by the streaming executor to decide
+which MCP tools to inject into a given LLM turn. Vector precompute + caching
+live in ToolManager (the tool-lifecycle owner, a process-wide singleton);
+only the context-aware selection lives here, because only the executor knows
+the conversation context.
+
+Invariants (per maintainer review of the feature proposal):
+  * Built-in tools are never handled here — the caller injects them in full.
+  * Any failure / missing input returns None so the caller falls back to
+    full injection; tools must never be silently dropped.
+  * Selection is union-accumulated across turns by the caller (only-grows),
+    so a tool that already produced a tool_use in the message history can
+    never disappear from the schema mid-run (which would make Claude/MiniMax
+    raise a message-format error).
+"""
+import math
+from typing import Dict, List, Optional, Sequence, Set
+
+try:
+    import numpy as np
+    _HAS_NUMPY = True
+except ImportError:
+    _HAS_NUMPY = False
+
+# How many trailing messages to concatenate into the retrieval query. Tool
+# needs drift across a multi-turn tool-call loop, so a single (initial) user
+# query is not enough; a short recent window captures the drift without
+# bloating the query with stale context.
+DEFAULT_QUERY_MESSAGES = 5
+
+
+def build_retrieval_query(messages: list, max_messages: int = DEFAULT_QUERY_MESSAGES) -> str:
+    """Concatenate the text of the most recent messages into a retrieval query.
+
+    Only ``text`` content blocks are kept; ``tool_use`` / ``tool_result`` blocks
+    are skipped so the query stays short and focused on natural-language intent
+    rather than large serialized tool payloads.
+
+    Args:
+        messages: Claude-style message list, each ``{"role", "content"}`` where
+            content is either a string or a list of typed blocks.
+        max_messages: Size of the trailing window to consider.
+
+    Returns:
+        A single string (possibly empty if no text is found).
+    """
+    if not messages:
+        return ""
+
+    parts: List[str] = []
+    for message in messages[-max_messages:]:
+        content = message.get("content") if isinstance(message, dict) else None
+        if isinstance(content, str):
+            if content.strip():
+                parts.append(content.strip())
+            continue
+        if isinstance(content, list):
+            for block in content:
+                if not isinstance(block, dict):
+                    continue
+                if block.get("type") == "text":
+                    text = block.get("text", "")
+                    if isinstance(text, str) and text.strip():
+                        parts.append(text.strip())
+    return "\n".join(parts)
+
+
+def cosine_similarity(a: Sequence[float], b: Sequence[float]) -> float:
+    """Cosine similarity of two equal-length vectors; 0.0 on degenerate input."""
+    if not a or not b or len(a) != len(b):
+        return 0.0
+    dot = sum(x * y for x, y in zip(a, b))
+    norm_a = math.sqrt(sum(x * x for x in a))
+    norm_b = math.sqrt(sum(y * y for y in b))
+    if norm_a == 0 or norm_b == 0:
+        return 0.0
+    return dot / (norm_a * norm_b)
+
+
+def select_mcp_tools(
+    query_vector: Optional[Sequence[float]],
+    tool_vectors: Dict[str, Sequence[float]],
+    top_k: int,
+    already_selected: Optional[Set[str]] = None,
+) -> Optional[Set[str]]:
+    """Return the accumulated set of MCP tool names to inject this turn.
+
+    Computes cosine similarity between ``query_vector`` and each candidate
+    tool vector, keeps the ``top_k`` best, and unions them with
+    ``already_selected`` so the injected set only ever grows within a run.
+
+    Args:
+        query_vector: Embedding of the current retrieval query, or None.
+        tool_vectors: ``{mcp_tool_name: vector}`` for candidate MCP tools.
+        top_k: Max number of tools to add from this turn's ranking.
+        already_selected: Names accumulated in previous turns of this run.
+
+    Returns:
+        The union set of tool names to inject, or None to signal
+        "fall back to full injection" (no query vector, empty/invalid index,
+        or any unexpected error). This function never raises.
+    """
+    accumulated: Set[str] = set(already_selected) if already_selected else set()
+
+    if not query_vector or not tool_vectors or top_k <= 0:
+        return None
+
+    try:
+        expected_dim = len(query_vector)
+        # Only rank candidates whose vector dimensionality matches the query.
+        # A dimension mismatch means the index was built with a different
+        # embedding model; ranking across dims is meaningless.
+        candidates = {
+            name: vec
+            for name, vec in tool_vectors.items()
+            if vec and len(vec) == expected_dim
+        }
+        if not candidates:
+            return None
+
+        ranked = _rank_by_similarity(query_vector, candidates)
+        for name, _score in ranked[:top_k]:
+            accumulated.add(name)
+        return accumulated
+    except Exception:
+        # Selection must never break the agent — fall back to full injection.
+        return None
+
+
+def _rank_by_similarity(
+    query_vector: Sequence[float],
+    candidates: Dict[str, Sequence[float]],
+) -> List[tuple]:
+    """Return ``[(name, score), ...]`` sorted by descending cosine similarity.
+
+    Uses numpy when available (vectorized, matching the memory-search path),
+    with a pure-Python fallback so the feature works without numpy installed.
+    """
+    names = list(candidates.keys())
+
+    if _HAS_NUMPY:
+        matrix = np.array([candidates[n] for n in names], dtype=np.float32)  # (N, D)
+        q_vec = np.array(query_vector, dtype=np.float32)                     # (D,)
+        dots = matrix @ q_vec                                                # (N,)
+        row_norms = np.linalg.norm(matrix, axis=1)                          # (N,)
+        q_norm = float(np.linalg.norm(q_vec))
+        denominators = row_norms * q_norm
+        np.maximum(denominators, 1e-10, out=denominators)                   # avoid div-by-zero
+        sims = dots / denominators
+        order = np.argsort(sims)[::-1]
+        return [(names[i], float(sims[i])) for i in order]
+
+    scored = [(n, cosine_similarity(query_vector, candidates[n])) for n in names]
+    scored.sort(key=lambda x: x[1], reverse=True)
+    return scored

agent/tools/memory/memory_get.py

@@ -4,6 +4,8 @@ Memory get tool
 Allows agents to read specific sections from memory files
 """
 
+import os
+
 from agent.tools.base_tool import BaseTool
 
 
@@ -44,6 +46,19 @@ class MemoryGetTool(BaseTool):
         """
         super().__init__()
         self.memory_manager = memory_manager
+
+        from config import conf
+        if conf().get("knowledge", True):
+            self.description = (
+                "Read specific content from memory or knowledge files. "
+                "Use this to get full context from a memory file, knowledge page, or specific line range."
+            )
+            self.params = {**self.params}
+            self.params["properties"] = {**self.params["properties"]}
+            self.params["properties"]["path"] = {
+                "type": "string",
+                "description": "Relative path to the memory or knowledge file (e.g. 'MEMORY.md', 'memory/2026-01-01.md', 'knowledge/concepts/moe.md')"
+            }
     
     def execute(self, args: dict):
         """
@@ -68,11 +83,20 @@ class MemoryGetTool(BaseTool):
             workspace_dir = self.memory_manager.config.get_workspace()
             
             # Auto-prepend memory/ if not present and not absolute path
-            # Exception: MEMORY.md is in the root directory
+            # Exceptions: MEMORY.md in root, knowledge/ files at workspace root
-            if not path.startswith('memory/') and not path.startswith('/') and path != 'MEMORY.md':
+            if not path.startswith('memory/') and not path.startswith('knowledge/') and not path.startswith('/') and path != 'MEMORY.md':
                 path = f'memory/{path}'
             
-            file_path = workspace_dir / path
+            file_path = (workspace_dir / path).resolve()
+            workspace_resolved = workspace_dir.resolve()
+
+            # Use os.path.realpath + os.sep for cross-platform path validation.
+            # str(Path).startswith(str + '/') fails on Windows where Path uses
+            # backslashes — see MemoryService._resolve_path for the same pattern.
+            real_file = os.path.realpath(str(file_path))
+            real_workspace = os.path.realpath(str(workspace_resolved))
+            if real_file != real_workspace and not real_file.startswith(real_workspace + os.sep):
+                return ToolResult.fail(f"Error: Access denied: path outside workspace")
             
             if not file_path.exists():
                 return ToolResult.fail(f"Error: File not found: {path}")

agent/tools/memory/memory_search.py

@@ -48,6 +48,13 @@ class MemorySearchTool(BaseTool):
         super().__init__()
         self.memory_manager = memory_manager
         self.user_id = user_id
+
+        from config import conf
+        if conf().get("knowledge", True):
+            self.description = (
+                "Search agent's long-term memory and knowledge base using semantic and keyword search. "
+                "Use this to recall past conversations, preferences, and knowledge pages."
+            )
     
     def execute(self, args: dict):
         """

agent/tools/read/read.py

@@ -4,6 +4,7 @@ Supports text files, images (jpg, png, gif, webp), and PDF files
 """
 
 import os
+import re
 from typing import Dict, Any
 from pathlib import Path
 
@@ -12,11 +13,17 @@ from agent.tools.utils.truncate import truncate_head, format_size, DEFAULT_MAX_L
 from common.utils import expand_path
 
 
+# Paths whose CONTENT mirrors the process environment (and thus any secrets
+# loaded from ~/.cow/.env). Reading them bypasses the env_config boundary.
+# Matches /proc/self/environ, /proc/thread-self/environ and /proc/<pid>/environ.
+_PROC_ENVIRON_RE = re.compile(r"^/proc/(\d+|self|thread-self)/environ$")
+
+
 class Read(BaseTool):
     """Tool for reading file contents"""
     
     name: str = "read"
-    description: str = f"Read or inspect file contents. For text/PDF files, returns content (truncated to {DEFAULT_MAX_LINES} lines or {DEFAULT_MAX_BYTES // 1024}KB). For images/videos/audio, returns metadata only (file info, size, type). Use offset/limit for large text files."
+    description: str = f"Read or inspect file contents. For text/PDF/Word/Excel/PPT files, returns content (truncated to {DEFAULT_MAX_LINES} lines or {DEFAULT_MAX_BYTES // 1024}KB). For images/videos/audio, returns metadata only (file info, size, type). Use offset/limit for large text files."
     
     params: dict = {
         "type": "object",
@@ -48,7 +55,8 @@ class Read(BaseTool):
         self.binary_extensions = {'.exe', '.dll', '.so', '.dylib', '.bin', '.dat', '.db', '.sqlite'}
         self.archive_extensions = {'.zip', '.tar', '.gz', '.rar', '.7z', '.bz2', '.xz'}
         self.pdf_extensions = {'.pdf'}
-        
+        self.office_extensions = {'.doc', '.docx', '.xls', '.xlsx', '.ppt', '.pptx'}
+
         # Readable text formats (will be read with truncation)
         self.text_extensions = {
             '.txt', '.md', '.markdown', '.rst', '.log', '.csv', '.tsv', '.json', '.xml', '.yaml', '.yml',
@@ -57,7 +65,6 @@ class Read(BaseTool):
             '.sh', '.bash', '.zsh', '.fish', '.ps1', '.bat', '.cmd',
             '.sql', '.r', '.m', '.swift', '.kt', '.scala', '.clj', '.erl', '.ex',
             '.dockerfile', '.makefile', '.cmake', '.gradle', '.properties', '.ini', '.conf', '.cfg',
-            '.doc', '.docx', '.xls', '.xlsx', '.ppt', '.pptx'  # Office documents
         }
     
     def execute(self, args: Dict[str, Any]) -> ToolResult:
@@ -79,9 +86,9 @@ class Read(BaseTool):
         # Resolve path
         absolute_path = self._resolve_path(path)
         
-        # Security check: Prevent reading sensitive config files
+        # Security check: block credential files and their aliases.
-        env_config_path = expand_path("~/.cow/.env")
+        # See issue #2913 (/proc/self/environ bypass) and #2863 (scope).
-        if os.path.abspath(absolute_path) == os.path.abspath(env_config_path):
+        if self._is_credential_path(absolute_path):
             return ToolResult.fail(
                 "Error: Access denied. API keys and credentials must be accessed through the env_config tool only."
             )
@@ -120,7 +127,11 @@ class Read(BaseTool):
         # Check if PDF
         if file_ext in self.pdf_extensions:
             return self._read_pdf(absolute_path, path, offset, limit)
-        
+
+        # Check if Office document (.docx, .xlsx, .pptx, etc.)
+        if file_ext in self.office_extensions:
+            return self._read_office(absolute_path, path, file_ext, offset, limit)
+
         # Read text file (with truncation for large files)
         return self._read_text(absolute_path, path, offset, limit)
     
@@ -136,7 +147,39 @@ class Read(BaseTool):
         if os.path.isabs(path):
             return path
         return os.path.abspath(os.path.join(self.cwd, path))
-    
+
+    def _is_credential_path(self, absolute_path: str) -> bool:
+        """Return True if *absolute_path* points at protected credential data.
+
+        Beyond the literal ~/.cow/.env file, this also blocks two real bypass
+        surfaces reported in issue #2913:
+          1. /proc/<pid|self|thread-self>/environ — a second view of the
+             process environment that leaks secrets loaded from ~/.cow/.env.
+          2. Symlinks resolving to ~/.cow/.env; the previous exact abspath
+             match kept the link target and could be bypassed.
+
+        Scope is kept deliberately narrow (only the credential file and its
+        environ aliases) so this does NOT re-broaden the block that #2863
+        intentionally narrowed to ~/.cow/.env.
+        """
+        # Compare on both the normalized path and the symlink-resolved path,
+        # in POSIX form so the /proc regex matches regardless of os.sep.
+        candidates = set()
+        try:
+            candidates.add(os.path.normpath(absolute_path).replace(os.sep, "/"))
+            candidates.add(os.path.realpath(absolute_path).replace(os.sep, "/"))
+        except OSError:
+            candidates.add(absolute_path.replace(os.sep, "/"))
+
+        # 1. /proc environ aliases (checked on raw and symlink-resolved forms).
+        for candidate in candidates:
+            if _PROC_ENVIRON_RE.match(candidate):
+                return True
+
+        # 2. The credential file itself, following symlinks on both sides.
+        env_real = os.path.realpath(expand_path("~/.cow/.env")).replace(os.sep, "/")
+        return env_real in candidates
+
     def _return_file_metadata(self, absolute_path: str, file_type: str, file_size: int) -> ToolResult:
         """
         Return file metadata for non-readable files (video, audio, binary, etc.)
@@ -240,17 +283,12 @@ class Read(BaseTool):
                     "message": f"文件过大 ({format_size(file_size)} > 50MB)，无法读取内容。文件路径: {absolute_path}"
                 })
             
-            # Read file
+            # Read file (utf-8-sig strips BOM automatically on Windows)
-            with open(absolute_path, 'r', encoding='utf-8') as f:
+            # Note: Truncation is unified via truncate_head (DEFAULT_MAX_LINES / DEFAULT_MAX_BYTES)
+            # so that offset/limit can paginate the entire file correctly.
+            with open(absolute_path, 'r', encoding='utf-8-sig') as f:
                 content = f.read()
-            
+
-            # Truncate content if too long (20K characters max for model context)
-            MAX_CONTENT_CHARS = 20 * 1024  # 20K characters
-            content_truncated = False
-            if len(content) > MAX_CONTENT_CHARS:
-                content = content[:MAX_CONTENT_CHARS]
-                content_truncated = True
-            
             all_lines = content.split('\n')
             total_file_lines = len(all_lines)
             
@@ -259,8 +297,15 @@ class Read(BaseTool):
             if offset is not None:
                 if offset < 0:
                     # Negative offset: read from end
-                    # -20 means "last 20 lines" → start from (total - 20)
+                    # -20 means "last 20 lines" → start from (total - 20).
-                    start_line = max(0, total_file_lines + offset)
+                    # A file ending in "\n" produces a trailing empty element
+                    # from split('\n'); exclude it so offset=-1 returns the
+                    # real last line instead of the empty string after the
+                    # final newline (and -N returns N real lines).
+                    effective_lines = total_file_lines
+                    if all_lines and all_lines[-1] == '':
+                        effective_lines -= 1
+                    start_line = max(0, effective_lines + offset)
                 else:
                     # Positive offset: read from start (1-indexed)
                     start_line = max(0, offset - 1)  # Convert to 0-indexed
@@ -286,11 +331,7 @@ class Read(BaseTool):
             
             output_text = ""
             details = {}
-            
+
-            # Add truncation warning if content was truncated
-            if content_truncated:
-                output_text = f"[文件内容已截断到前 {format_size(MAX_CONTENT_CHARS)}，完整文件大小: {format_size(file_size)}]\n\n"
-            
             if truncation.first_line_exceeds_limit:
                 # First line exceeds 30KB limit
                 first_line_size = format_size(len(all_lines[start_line].encode('utf-8')))
@@ -337,6 +378,116 @@ class Read(BaseTool):
         except Exception as e:
             return ToolResult.fail(f"Error reading file: {str(e)}")
     
+    def _read_office(self, absolute_path: str, display_path: str, file_ext: str,
+                     offset: int = None, limit: int = None) -> ToolResult:
+        """Read Office documents (.docx, .xlsx, .pptx) using python-docx / openpyxl / python-pptx."""
+        try:
+            text = self._extract_office_text(absolute_path, file_ext)
+        except ImportError as e:
+            return ToolResult.fail(str(e))
+        except Exception as e:
+            return ToolResult.fail(f"Error reading Office document: {e}")
+
+        if not text or not text.strip():
+            return ToolResult.success({
+                "content": f"[Office file {Path(absolute_path).name}: no text content could be extracted]",
+            })
+
+        all_lines = text.split('\n')
+        total_lines = len(all_lines)
+
+        start_line = 0
+        if offset is not None:
+            if offset < 0:
+                start_line = max(0, total_lines + offset)
+            else:
+                start_line = max(0, offset - 1)
+                if start_line >= total_lines:
+                    return ToolResult.fail(
+                        f"Error: Offset {offset} is beyond end of content ({total_lines} lines total)"
+                    )
+
+        selected_content = text
+        user_limited_lines = None
+        if limit is not None:
+            end_line = min(start_line + limit, total_lines)
+            selected_content = '\n'.join(all_lines[start_line:end_line])
+            user_limited_lines = end_line - start_line
+        elif offset is not None:
+            selected_content = '\n'.join(all_lines[start_line:])
+
+        truncation = truncate_head(selected_content)
+        start_line_display = start_line + 1
+        output_text = ""
+
+        if truncation.truncated:
+            end_line_display = start_line_display + truncation.output_lines - 1
+            next_offset = end_line_display + 1
+            output_text = truncation.content
+            output_text += f"\n\n[Showing lines {start_line_display}-{end_line_display} of {total_lines}. Use offset={next_offset} to continue.]"
+        elif user_limited_lines is not None and start_line + user_limited_lines < total_lines:
+            remaining = total_lines - (start_line + user_limited_lines)
+            next_offset = start_line + user_limited_lines + 1
+            output_text = truncation.content
+            output_text += f"\n\n[{remaining} more lines in file. Use offset={next_offset} to continue.]"
+        else:
+            output_text = truncation.content
+
+        return ToolResult.success({
+            "content": output_text,
+            "total_lines": total_lines,
+            "start_line": start_line_display,
+            "output_lines": truncation.output_lines,
+        })
+
+    @staticmethod
+    def _extract_office_text(absolute_path: str, file_ext: str) -> str:
+        """Extract plain text from an Office document."""
+        if file_ext in ('.docx', '.doc'):
+            try:
+                from docx import Document
+            except ImportError:
+                raise ImportError("Error: python-docx library not installed. Install with: pip install python-docx")
+            doc = Document(absolute_path)
+            paragraphs = [p.text for p in doc.paragraphs]
+            for table in doc.tables:
+                for row in table.rows:
+                    paragraphs.append('\t'.join(cell.text for cell in row.cells))
+            return '\n'.join(paragraphs)
+
+        if file_ext in ('.xlsx', '.xls'):
+            try:
+                from openpyxl import load_workbook
+            except ImportError:
+                raise ImportError("Error: openpyxl library not installed. Install with: pip install openpyxl")
+            wb = load_workbook(absolute_path, read_only=True, data_only=True)
+            parts = []
+            for ws in wb.worksheets:
+                parts.append(f"--- Sheet: {ws.title} ---")
+                for row in ws.iter_rows(values_only=True):
+                    parts.append('\t'.join(str(c) if c is not None else '' for c in row))
+            wb.close()
+            return '\n'.join(parts)
+
+        if file_ext in ('.pptx', '.ppt'):
+            try:
+                from pptx import Presentation
+            except ImportError:
+                raise ImportError("Error: python-pptx library not installed. Install with: pip install python-pptx")
+            prs = Presentation(absolute_path)
+            parts = []
+            for i, slide in enumerate(prs.slides, 1):
+                parts.append(f"--- Slide {i} ---")
+                for shape in slide.shapes:
+                    if shape.has_text_frame:
+                        for para in shape.text_frame.paragraphs:
+                            text = para.text.strip()
+                            if text:
+                                parts.append(text)
+            return '\n'.join(parts)
+
+        return ""
+
     def _read_pdf(self, absolute_path: str, display_path: str, offset: int = None, limit: int = None) -> ToolResult:
         """
         Read PDF file content

agent/tools/scheduler/integration.py

@@ -3,6 +3,7 @@ Integration module for scheduler with AgentBridge
 """
 
 import os
+import threading
 from typing import Optional
 from config import conf
 from common.log import logger
@@ -13,65 +14,126 @@ from bridge.reply import Reply, ReplyType
 # Global scheduler service instance
 _scheduler_service = None
 _task_store = None
+# Module-level lock to guard idempotent initialization across threads
+_init_lock = threading.Lock()
 
 
 def init_scheduler(agent_bridge) -> bool:
     """
-    Initialize scheduler service
+    Initialize scheduler service (idempotent).
-    
+
+    Safe to call multiple times and from multiple threads: only the first
+    successful call creates the singleton ``SchedulerService`` + background
+    scanning thread. Subsequent calls return immediately.
+
     Args:
         agent_bridge: AgentBridge instance
-        
+
     Returns:
-        True if initialized successfully
+        True if scheduler is initialized (newly created or already running)
     """
     global _scheduler_service, _task_store
-    
+
-    try:
+    # Fast path: already initialized and running
-        from agent.tools.scheduler.task_store import TaskStore
+    if _scheduler_service is not None and getattr(_scheduler_service, "running", False):
-        from agent.tools.scheduler.scheduler_service import SchedulerService
+        return True
-        
+
-        # Get workspace from config
+    with _init_lock:
-        workspace_root = expand_path(conf().get("agent_workspace", "~/cow"))
+        # Re-check under the lock to avoid races where multiple threads
-        store_path = os.path.join(workspace_root, "scheduler", "tasks.json")
+        # passed the fast-path check before any of them acquired the lock.
-        
+        if _scheduler_service is not None and getattr(_scheduler_service, "running", False):
-        # Create task store
+            return True
-        _task_store = TaskStore(store_path)
+
-        logger.debug(f"[Scheduler] Task store initialized: {store_path}")
+        try:
-        
+            from agent.tools.scheduler.task_store import TaskStore
-        # Create execute callback
+            from agent.tools.scheduler.scheduler_service import SchedulerService
-        def execute_task_callback(task: dict):
+
-            """Callback to execute a scheduled task"""
+            # Get workspace from config
-            try:
+            workspace_root = expand_path(conf().get("agent_workspace", "~/cow"))
-                action = task.get("action", {})
+            store_path = os.path.join(workspace_root, "scheduler", "tasks.json")
-                action_type = action.get("type")
+
-                
+            # Create task store (reuse if already created)
-                if action_type == "agent_task":
+            if _task_store is None:
-                    _execute_agent_task(task, agent_bridge)
+                _task_store = TaskStore(store_path)
-                elif action_type == "send_message":
+                logger.debug(f"[Scheduler] Task store initialized: {store_path}")
-                    # Legacy support for old tasks
+
-                    _execute_send_message(task, agent_bridge)
+            # Create execute callback. Returns True on success, False to ask
-                elif action_type == "tool_call":
+            # the scheduler to retry on the next tick (e.g. channel not yet
-                    # Legacy support for old tasks
+            # ready right after process start).
-                    _execute_tool_call(task, agent_bridge)
+            def execute_task_callback(task: dict):
-                elif action_type == "skill_call":
+                try:
-                    # Legacy support for old tasks
+                    action = task.get("action", {})
-                    _execute_skill_call(task, agent_bridge)
+                    action_type = action.get("type")
-                else:
+                    channel_type = action.get("channel_type", "unknown")
-                    logger.warning(f"[Scheduler] Unknown action type: {action_type}")
+                    receiver = action.get("receiver", "")
-            except Exception as e:
+
-                logger.error(f"[Scheduler] Error executing task {task.get('id')}: {e}")
+                    if not _is_channel_ready(channel_type, receiver):
-        
+                        logger.warning(
-        # Create scheduler service
+                            f"[Scheduler] Task {task.get('id')}: channel "
-        _scheduler_service = SchedulerService(_task_store, execute_task_callback)
+                            f"'{channel_type}' not ready for receiver={receiver} "
-        _scheduler_service.start()
+                            f"(no inbound msg cached since restart?); deferring"
-        
+                        )
-        logger.debug("[Scheduler] Scheduler service initialized and started")
+                        return False
+
+                    if action_type == "agent_task":
+                        return _execute_agent_task(task, agent_bridge)
+                    elif action_type == "send_message":
+                        return _execute_send_message(task, agent_bridge)
+                    elif action_type == "tool_call":
+                        return _execute_tool_call(task, agent_bridge)
+                    elif action_type == "skill_call":
+                        return _execute_skill_call(task, agent_bridge)
+                    else:
+                        logger.warning(f"[Scheduler] Unknown action type: {action_type}")
+                        return True
+                except Exception as e:
+                    logger.error(f"[Scheduler] Error executing task {task.get('id')}: {e}")
+                    return False
+
+            # Create scheduler service
+            _scheduler_service = SchedulerService(_task_store, execute_task_callback)
+            _scheduler_service.start()
+
+            logger.info("[Scheduler] Service initialized and started")
+            return True
+
+        except Exception as e:
+            logger.error(f"[Scheduler] Failed to initialize scheduler: {e}")
+            return False
+
+
+def _is_channel_ready(channel_type: str, receiver: str) -> bool:
+    """Best-effort readiness probe for outbound channels.
+
+    Returns False when we know the send will drop (e.g. weixin not yet
+    logged in, web session has no polling queue), so the scheduler can
+    defer instead of consuming the task. Unknown channels return True
+    to preserve previous behaviour.
+    """
+    if not channel_type or channel_type == "unknown":
+        return True
+    try:
+        from channel.channel_factory import create_channel
+        channel = create_channel(channel_type)
+        if channel is None:
+            return False
+
+        if channel_type == "weixin":
+            tokens = getattr(channel, "_context_tokens", None)
+            if not tokens or receiver not in tokens:
+                return False
+            return True
+
+        if channel_type == "web":
+            queues = getattr(channel, "session_queues", None)
+            if not queues or receiver not in queues:
+                return False
+            return True
+
         return True
-        
     except Exception as e:
-        logger.error(f"[Scheduler] Failed to initialize scheduler: {e}")
+        logger.warning(f"[Scheduler] Channel readiness check failed for {channel_type}: {e}")
-        return False
+        return True
 
 
 def get_task_store():
@@ -84,13 +146,53 @@ def get_scheduler_service():
     return _scheduler_service
 
 
-def _execute_agent_task(task: dict, agent_bridge):
+def _remember_delivered_output(
+    agent_bridge,
+    task: dict,
+    channel_type: str,
+    content: str,
+) -> None:
+    """Best-effort persistence of the message the scheduler sent to a user.
+
+    Uses notify_session_id (the real chat session_id stored at task creation time)
+    so that group chats correctly associate the output with the user's conversation.
+    Falls back to receiver for backward compatibility with old tasks.
+
+    Per-action-type behaviour:
+        - agent_task / tool_call / skill_call: gated by ``scheduler_inject_to_session``
+          (default True). These produce AI-generated content worth remembering.
+        - send_message: additionally gated by ``scheduler_inject_send_message``
+          (default False). Fixed reminder text rarely benefits follow-up Q&A and
+          would just consume context tokens.
     """
-    Execute an agent_task action - let Agent handle the task
+    if not content:
-    
+        return
-    Args:
+    action = task.get("action", {})
-        task: Task dictionary
+    action_type = action.get("type", "")
-        agent_bridge: AgentBridge instance
+
+    # send_message defaults to NOT being injected; explicit opt-in via config.
+    if action_type == "send_message":
+        if not conf().get("scheduler_inject_send_message", False):
+            return
+
+    session_id = action.get("notify_session_id") or action.get("receiver")
+    if not session_id:
+        return
+    try:
+        remember = getattr(agent_bridge, "remember_scheduled_output", None)
+        if remember:
+            task_desc = action.get("task_description") or action.get("content", "")
+            remember(session_id, str(content), channel_type=channel_type, task_description=task_desc)
+    except Exception as e:
+        logger.warning(
+            f"[Scheduler] Failed to remember delivered output for {session_id}: {e}"
+        )
+
+
+def _execute_agent_task(task: dict, agent_bridge) -> bool:
+    """
+    Execute an agent_task action - let Agent handle the task.
+    Returns True on successful delivery, False to retry next tick.
     """
     try:
         action = task.get("action", {})
@@ -101,11 +203,11 @@ def _execute_agent_task(task: dict, agent_bridge):
         
         if not task_description:
             logger.error(f"[Scheduler] Task {task['id']}: No task_description specified")
-            return
+            return True  # malformed task, don't loop forever
         
         if not receiver:
             logger.error(f"[Scheduler] Task {task['id']}: No receiver specified")
-            return
+            return True
         
         # Check for unsupported channels
         if channel_type == "dingtalk":
@@ -134,12 +236,13 @@ def _execute_agent_task(task: dict, agent_bridge):
         elif channel_type == "dingtalk":
             # DingTalk requires msg object, set to None for scheduled tasks
             context["msg"] = None
-            # 如果是单聊，需要传递 sender_staff_id
             if not is_group:
                 sender_staff_id = action.get("dingtalk_sender_staff_id")
                 if sender_staff_id:
                     context["dingtalk_sender_staff_id"] = sender_staff_id
-        
+        elif channel_type == "wecom_bot":
+            context["msg"] = None
+
         # Use Agent to execute the task
         # Mark this as a scheduled task execution to prevent recursive task creation
         context["is_scheduled_task"] = True
@@ -147,50 +250,47 @@ def _execute_agent_task(task: dict, agent_bridge):
         try:
             # Don't clear history - scheduler tasks use isolated session_id so they won't pollute user conversations
             reply = agent_bridge.agent_reply(task_description, context=context, on_event=None, clear_history=False)
-            
+
-            if reply and reply.content:
+            if not (reply and reply.content):
-                # Send the reply via channel
-                from channel.channel_factory import create_channel
-                
-                try:
-                    channel = create_channel(channel_type)
-                    if channel:
-                        # For web channel, register request_id
-                        if channel_type == "web" and hasattr(channel, 'request_to_session'):
-                            request_id = context.get("request_id")
-                            if request_id:
-                                channel.request_to_session[request_id] = receiver
-                                logger.debug(f"[Scheduler] Registered request_id {request_id} -> session {receiver}")
-                        
-                        # Send the reply
-                        channel.send(reply, context)
-                        logger.info(f"[Scheduler] Task {task['id']} executed successfully, result sent to {receiver}")
-                    else:
-                        logger.error(f"[Scheduler] Failed to create channel: {channel_type}")
-                except Exception as e:
-                    logger.error(f"[Scheduler] Failed to send result: {e}")
-            else:
                 logger.error(f"[Scheduler] Task {task['id']}: No result from agent execution")
-                
+                return True  # agent ran but produced nothing; don't loop
+
+            from channel.channel_factory import create_channel
+            channel = create_channel(channel_type)
+            if not channel:
+                logger.error(f"[Scheduler] Failed to create channel: {channel_type}")
+                return False
+
+            if channel_type == "web" and hasattr(channel, 'request_to_session'):
+                request_id = context.get("request_id")
+                if request_id:
+                    channel.request_to_session[request_id] = receiver
+
+            try:
+                channel.send(reply, context)
+            except Exception as e:
+                logger.error(f"[Scheduler] Failed to send result: {e}")
+                return False
+
+            _remember_delivered_output(agent_bridge, task, channel_type, reply.content)
+            logger.info(f"[Scheduler] Task {task['id']} executed successfully, result sent to {receiver}")
+            return True
+
         except Exception as e:
             logger.error(f"[Scheduler] Failed to execute task via Agent: {e}")
             import traceback
             logger.error(f"[Scheduler] Traceback: {traceback.format_exc()}")
-            
+            return False
+
     except Exception as e:
         logger.error(f"[Scheduler] Error in _execute_agent_task: {e}")
         import traceback
         logger.error(f"[Scheduler] Traceback: {traceback.format_exc()}")
+        return False
 
 
-def _execute_send_message(task: dict, agent_bridge):
+def _execute_send_message(task: dict, agent_bridge) -> bool:
-    """
+    """Execute a send_message action. Returns True/False for delivery."""
-    Execute a send_message action
-    
-    Args:
-        task: Task dictionary
-        agent_bridge: AgentBridge instance
-    """
     try:
         action = task.get("action", {})
         content = action.get("content", "")
@@ -200,7 +300,7 @@ def _execute_send_message(task: dict, agent_bridge):
         
         if not receiver:
             logger.error(f"[Scheduler] Task {task['id']}: No receiver specified")
-            return
+            return True
         
         # Create context for sending message
         context = Context(ContextType.TEXT, content)
@@ -234,174 +334,146 @@ def _execute_send_message(task: dict, agent_bridge):
                     logger.debug(f"[Scheduler] DingTalk single chat: sender_staff_id={sender_staff_id}")
                 else:
                     logger.warning(f"[Scheduler] Task {task['id']}: DingTalk single chat message missing sender_staff_id")
-        
+        elif channel_type == "wecom_bot":
+            context["msg"] = None
+        elif channel_type == "qq":
+            context["msg"] = None
+
         # Create reply
         reply = Reply(ReplyType.TEXT, content)
         
         # Get channel and send
         from channel.channel_factory import create_channel
         
+        channel = create_channel(channel_type)
+        if not channel:
+            logger.error(f"[Scheduler] Failed to create channel: {channel_type}")
+            return False
+
+        if channel_type == "web" and hasattr(channel, 'request_to_session'):
+            channel.request_to_session[request_id] = receiver
+
         try:
-            channel = create_channel(channel_type)
+            channel.send(reply, context)
-            if channel:
-                # For web channel, register the request_id to session mapping
-                if channel_type == "web" and hasattr(channel, 'request_to_session'):
-                    channel.request_to_session[request_id] = receiver
-                    logger.debug(f"[Scheduler] Registered request_id {request_id} -> session {receiver}")
-                
-                channel.send(reply, context)
-                logger.info(f"[Scheduler] Task {task['id']} executed: sent message to {receiver}")
-            else:
-                logger.error(f"[Scheduler] Failed to create channel: {channel_type}")
         except Exception as e:
             logger.error(f"[Scheduler] Failed to send message: {e}")
-            import traceback
+            return False
-            logger.error(f"[Scheduler] Traceback: {traceback.format_exc()}")
+
-            
+        _remember_delivered_output(agent_bridge, task, channel_type, content)
+        logger.info(f"[Scheduler] Task {task['id']} executed: sent message to {receiver}")
+        return True
+
     except Exception as e:
         logger.error(f"[Scheduler] Error in _execute_send_message: {e}")
         import traceback
         logger.error(f"[Scheduler] Traceback: {traceback.format_exc()}")
+        return False
 
 
-def _execute_tool_call(task: dict, agent_bridge):
+def _execute_tool_call(task: dict, agent_bridge) -> bool:
-    """
+    """Execute a tool_call action. Returns True/False for delivery."""
-    Execute a tool_call action
-    
-    Args:
-        task: Task dictionary
-        agent_bridge: AgentBridge instance
-    """
     try:
         action = task.get("action", {})
-        # Support both old and new field names
         tool_name = action.get("call_name") or action.get("tool_name")
         tool_params = action.get("call_params") or action.get("tool_params", {})
         result_prefix = action.get("result_prefix", "")
         receiver = action.get("receiver")
         is_group = action.get("is_group", False)
         channel_type = action.get("channel_type", "unknown")
-        
+
         if not tool_name:
             logger.error(f"[Scheduler] Task {task['id']}: No tool_name specified")
-            return
+            return True
-        
         if not receiver:
             logger.error(f"[Scheduler] Task {task['id']}: No receiver specified")
-            return
+            return True
-        
+
-        # Get tool manager and create tool instance
         from agent.tools.tool_manager import ToolManager
-        tool_manager = ToolManager()
+        tool = ToolManager().create_tool(tool_name)
-        tool = tool_manager.create_tool(tool_name)
-        
         if not tool:
             logger.error(f"[Scheduler] Task {task['id']}: Tool '{tool_name}' not found")
-            return
+            return True
-        
+
-        # Execute tool
         logger.info(f"[Scheduler] Task {task['id']}: Executing tool '{tool_name}' with params {tool_params}")
         result = tool.execute(tool_params)
-        
+        content = result.result if hasattr(result, 'result') else str(result)
-        # Get result content
-        if hasattr(result, 'result'):
-            content = result.result
-        else:
-            content = str(result)
-        
-        # Add prefix if specified
         if result_prefix:
             content = f"{result_prefix}\n\n{content}"
-        
+
-        # Send result as message
         context = Context(ContextType.TEXT, content)
         context["receiver"] = receiver
         context["isgroup"] = is_group
         context["session_id"] = receiver
-        
+
-        # Channel-specific context setup
+        request_id = None
         if channel_type == "web":
-            # Web channel needs request_id
             import uuid
             request_id = f"scheduler_{task['id']}_{uuid.uuid4().hex[:8]}"
             context["request_id"] = request_id
-            logger.debug(f"[Scheduler] Generated request_id for web channel: {request_id}")
         elif channel_type == "feishu":
-            # Feishu channel: for scheduled tasks, send as new message (no msg_id to reply to)
             context["receive_id_type"] = "chat_id" if is_group else "open_id"
             context["msg"] = None
-            logger.debug(f"[Scheduler] Feishu: receive_id_type={context['receive_id_type']}, is_group={is_group}, receiver={receiver}")
+        elif channel_type == "wecom_bot":
-        
+            context["msg"] = None
+
         reply = Reply(ReplyType.TEXT, content)
-        
+
-        # Get channel and send
         from channel.channel_factory import create_channel
-        
+        channel = create_channel(channel_type)
+        if not channel:
+            logger.error(f"[Scheduler] Failed to create channel: {channel_type}")
+            return False
+
+        if channel_type == "web" and request_id and hasattr(channel, 'request_to_session'):
+            channel.request_to_session[request_id] = receiver
+
         try:
-            channel = create_channel(channel_type)
+            channel.send(reply, context)
-            if channel:
-                # For web channel, register the request_id to session mapping
-                if channel_type == "web" and hasattr(channel, 'request_to_session'):
-                    channel.request_to_session[request_id] = receiver
-                    logger.debug(f"[Scheduler] Registered request_id {request_id} -> session {receiver}")
-                
-                channel.send(reply, context)
-                logger.info(f"[Scheduler] Task {task['id']} executed: sent tool result to {receiver}")
-            else:
-                logger.error(f"[Scheduler] Failed to create channel: {channel_type}")
         except Exception as e:
             logger.error(f"[Scheduler] Failed to send tool result: {e}")
-            
+            return False
+
+        _remember_delivered_output(agent_bridge, task, channel_type, content)
+        logger.info(f"[Scheduler] Task {task['id']} executed: sent tool result to {receiver}")
+        return True
+
     except Exception as e:
         logger.error(f"[Scheduler] Error in _execute_tool_call: {e}")
+        return False
 
 
-def _execute_skill_call(task: dict, agent_bridge):
+def _execute_skill_call(task: dict, agent_bridge) -> bool:
-    """
+    """Execute a skill_call action by asking Agent to run the skill.
-    Execute a skill_call action by asking Agent to run the skill
+    Returns True/False for delivery."""
-    
-    Args:
-        task: Task dictionary
-        agent_bridge: AgentBridge instance
-    """
     try:
         action = task.get("action", {})
-        # Support both old and new field names
         skill_name = action.get("call_name") or action.get("skill_name")
         skill_params = action.get("call_params") or action.get("skill_params", {})
         result_prefix = action.get("result_prefix", "")
         receiver = action.get("receiver")
         is_group = action.get("isgroup", False)
         channel_type = action.get("channel_type", "unknown")
-        
+
         if not skill_name:
             logger.error(f"[Scheduler] Task {task['id']}: No skill_name specified")
-            return
+            return True
-        
         if not receiver:
             logger.error(f"[Scheduler] Task {task['id']}: No receiver specified")
-            return
+            return True
-        
+
         logger.info(f"[Scheduler] Task {task['id']}: Executing skill '{skill_name}' with params {skill_params}")
-        
+
-        # Create a unique session_id for this scheduled task to avoid polluting user's conversation
-        # Format: scheduler_<receiver>_<task_id> to ensure isolation
         scheduler_session_id = f"scheduler_{receiver}_{task['id']}"
-        
-        # Build a natural language query for the Agent to execute the skill
-        # Format: "Use skill-name to do something with params"
         param_str = ", ".join([f"{k}={v}" for k, v in skill_params.items()])
         query = f"Use {skill_name} skill"
         if param_str:
             query += f" with {param_str}"
-        
+
-        # Create context for Agent
         context = Context(ContextType.TEXT, query)
         context["receiver"] = receiver
         context["isgroup"] = is_group
         context["session_id"] = scheduler_session_id
-        
+
-        # Channel-specific setup
         if channel_type == "web":
             import uuid
             request_id = f"scheduler_{task['id']}_{uuid.uuid4().hex[:8]}"
@@ -409,32 +481,51 @@ def _execute_skill_call(task: dict, agent_bridge):
         elif channel_type == "feishu":
             context["receive_id_type"] = "chat_id" if is_group else "open_id"
             context["msg"] = None
-        
+        elif channel_type == "wecom_bot":
-        # Use Agent to execute the skill
+            context["msg"] = None
+
         try:
-            # Don't clear history - scheduler tasks use isolated session_id so they won't pollute user conversations
             reply = agent_bridge.agent_reply(query, context=context, on_event=None, clear_history=False)
-            
-            if reply and reply.content:
-                content = reply.content
-                
-                # Add prefix if specified
-                if result_prefix:
-                    content = f"{result_prefix}\n\n{content}"
-                
-                logger.info(f"[Scheduler] Task {task['id']} executed: skill result sent to {receiver}")
-            else:
-                logger.error(f"[Scheduler] Task {task['id']}: No result from skill execution")
-                
         except Exception as e:
             logger.error(f"[Scheduler] Failed to execute skill via Agent: {e}")
             import traceback
             logger.error(f"[Scheduler] Traceback: {traceback.format_exc()}")
-            
+            return False
+
+        if not (reply and reply.content):
+            logger.error(f"[Scheduler] Task {task['id']}: No result from skill execution")
+            return True
+
+        content = reply.content
+        if result_prefix:
+            content = f"{result_prefix}\n\n{content}"
+
+        from channel.channel_factory import create_channel
+        channel = create_channel(channel_type)
+        if not channel:
+            logger.error(f"[Scheduler] Failed to create channel: {channel_type}")
+            return False
+
+        if channel_type == "web" and hasattr(channel, 'request_to_session'):
+            req_id = context.get("request_id")
+            if req_id:
+                channel.request_to_session[req_id] = receiver
+
+        try:
+            channel.send(Reply(ReplyType.TEXT, content), context)
+        except Exception as e:
+            logger.error(f"[Scheduler] Failed to send skill result: {e}")
+            return False
+
+        _remember_delivered_output(agent_bridge, task, channel_type, content)
+        logger.info(f"[Scheduler] Task {task['id']} executed: skill result sent to {receiver}")
+        return True
+
     except Exception as e:
         logger.error(f"[Scheduler] Error in _execute_skill_call: {e}")
         import traceback
         logger.error(f"[Scheduler] Traceback: {traceback.format_exc()}")
+        return False
 
 
 def attach_scheduler_to_tool(tool, context: Context = None):

agent/tools/scheduler/scheduler_service.py

@@ -10,6 +10,19 @@ from croniter import croniter
 from common.log import logger
 
 
+def _parse_naive_local(iso_str: str) -> datetime:
+    """Parse an ISO datetime and coerce it to tz-naive local time.
+
+    The scheduler uses ``datetime.now()`` (tz-naive) for all comparisons,
+    so any persisted timestamp must be normalized to the same flavor —
+    otherwise comparing naive vs aware raises TypeError.
+    """
+    dt = datetime.fromisoformat(iso_str)
+    if dt.tzinfo is not None:
+        dt = dt.astimezone().replace(tzinfo=None)
+    return dt
+
+
 class SchedulerService:
     """
     Background service that executes scheduled tasks
@@ -39,7 +52,6 @@ class SchedulerService:
             self.running = True
             self.thread = threading.Thread(target=self._run_loop, daemon=True)
             self.thread.start()
-            logger.debug("[Scheduler] Service started")
     
     def stop(self):
         """Stop the scheduler service"""
@@ -54,15 +66,14 @@ class SchedulerService:
     
     def _run_loop(self):
         """Main scheduler loop"""
-        logger.debug("[Scheduler] Scheduler loop started")
+        logger.info("[Scheduler] Scheduler loop started")
         
         while self.running:
             try:
                 self._check_and_execute_tasks()
             except Exception as e:
                 logger.error(f"[Scheduler] Error in scheduler loop: {e}")
-            
+
-            # Sleep for 30 seconds between checks
             time.sleep(30)
     
     def _check_and_execute_tasks(self):
@@ -72,12 +83,18 @@ class SchedulerService:
         
         for task in tasks:
             try:
-                # Check if task is due
                 if self._is_task_due(task, now):
                     logger.info(f"[Scheduler] Executing task: {task['id']} - {task['name']}")
-                    self._execute_task(task)
+                    ok = self._execute_task(task)
-                    
+                    if not ok:
-                    # Update next run time
+                        # Leave next_run_at as-is so the next loop retries.
+                        # Cron tasks within the catch-up window will keep
+                        # firing; beyond it _is_task_due will reschedule.
+                        logger.warning(
+                            f"[Scheduler] Task {task['id']} delivery failed, will retry next tick"
+                        )
+                        continue
+
                     next_run = self._calculate_next_run(task, now)
                     if next_run:
                         self.task_store.update_task(task['id'], {
@@ -85,12 +102,8 @@ class SchedulerService:
                             "last_run_at": now.isoformat()
                         })
                     else:
-                        # One-time task, disable it
+                        self.task_store.delete_task(task['id'])
-                        self.task_store.update_task(task['id'], {
+                        logger.info(f"[Scheduler] One-time task completed and removed: {task['id']}")
-                            "enabled": False,
-                            "last_run_at": now.isoformat()
-                        })
-                        logger.info(f"[Scheduler] One-time task completed and disabled: {task['id']}")
             except Exception as e:
                 logger.error(f"[Scheduler] Error processing task {task.get('id')}: {e}")
     
@@ -117,37 +130,43 @@ class SchedulerService:
             return False
         
         try:
-            next_run = datetime.fromisoformat(next_run_str)
+            next_run = _parse_naive_local(next_run_str)
-            
+
-            # Check if task is overdue (e.g., service restart)
             if next_run < now:
                 time_diff = (now - next_run).total_seconds()
-                
+                schedule = task.get("schedule", {})
-                # If overdue by more than 5 minutes, skip this run and schedule next
+                schedule_type = schedule.get("type")
-                if time_diff > 300:  # 5 minutes
+
-                    logger.warning(f"[Scheduler] Task {task['id']} is overdue by {int(time_diff)}s, skipping and scheduling next run")
+                # Catch-up window: fire if we're within 10 minutes of the
-                    
+                # scheduled tick. Beyond that we'd rather skip than push a
-                    # For one-time tasks, disable them
+                # stale daily report to the user.
-                    schedule = task.get("schedule", {})
+                if time_diff <= 600:
-                    if schedule.get("type") == "once":
+                    return True
-                        self.task_store.update_task(task['id'], {
+
-                            "enabled": False,
+                logger.warning(
-                            "last_run_at": now.isoformat()
+                    f"[Scheduler] Task {task['id']} is overdue by {int(time_diff)}s, "
-                        })
+                    f"skipping and scheduling next run"
-                        logger.info(f"[Scheduler] One-time task {task['id']} expired, disabled")
+                )
-                        return False
+
-                    
+                if schedule_type == "once":
-                    # For recurring tasks, calculate next run from now
+                    self.task_store.delete_task(task['id'])
-                    next_next_run = self._calculate_next_run(task, now)
+                    logger.info(f"[Scheduler] One-time task {task['id']} expired, removed")
-                    if next_next_run:
-                        self.task_store.update_task(task['id'], {
-                            "next_run_at": next_next_run.isoformat()
-                        })
-                        logger.info(f"[Scheduler] Rescheduled task {task['id']} to {next_next_run}")
                     return False
-            
+
+                next_next_run = self._calculate_next_run(task, now)
+                if next_next_run:
+                    self.task_store.update_task(task['id'], {
+                        "next_run_at": next_next_run.isoformat()
+                    })
+                    logger.info(f"[Scheduler] Rescheduled task {task['id']} to {next_next_run}")
+                return False
+
             return now >= next_run
-        except Exception:
+        except Exception as e:
+            logger.error(
+                f"[Scheduler] Failed to evaluate due-state for task "
+                f"{task.get('id')} (next_run_at={next_run_str!r}): {e}"
+            )
             return False
     
     def _calculate_next_run(self, task: dict, from_time: datetime) -> Optional[datetime]:
@@ -191,30 +210,34 @@ class SchedulerService:
                 return None
             
             try:
-                run_at = datetime.fromisoformat(run_at_str)
+                run_at = _parse_naive_local(run_at_str)
-                # Only return if in the future
                 if run_at > from_time:
                     return run_at
-            except Exception:
+            except Exception as e:
-                pass
+                logger.error(
+                    f"[Scheduler] Failed to parse once-task run_at "
+                    f"{run_at_str!r}: {e}"
+                )
             return None
         
         return None
     
-    def _execute_task(self, task: dict):
+    def _execute_task(self, task: dict) -> bool:
         """
-        Execute a task
+        Execute a task.
-        
+
-        Args:
+        Returns True if delivery succeeded (caller should advance state),
-            task: Task dictionary
+        False if it failed (caller should keep next_run_at so the next
+        loop iteration retries). Callback may return None for legacy
+        behaviour, treated as success.
         """
         try:
-            # Call the execute callback
+            result = self.execute_callback(task)
-            self.execute_callback(task)
+            return False if result is False else True
         except Exception as e:
             logger.error(f"[Scheduler] Error executing task {task['id']}: {e}")
-            # Update task with error
             self.task_store.update_task(task['id'], {
                 "last_error": str(e),
                 "last_error_at": datetime.now().isoformat()
             })
+            return False

agent/tools/scheduler/scheduler_tool.py

@@ -158,6 +158,11 @@ class SchedulerTool(BaseTool):
         # Create task
         task_id = str(uuid.uuid4())[:8]
         
+        # Capture the real chat session_id at task creation time so that scheduler
+        # can later inject the delivered output into the user's actual conversation
+        # (in group chats, session_id != receiver, e.g. "user_id:group_id" on feishu).
+        notify_session_id = context.get("session_id")
+
         # Build action based on message or ai_task
         if message:
             action = {
@@ -166,7 +171,8 @@ class SchedulerTool(BaseTool):
                 "receiver": context.get("receiver"),
                 "receiver_name": self._get_receiver_name(context),
                 "is_group": context.get("isgroup", False),
-                "channel_type": self.config.get("channel_type", "unknown")
+                "channel_type": self.config.get("channel_type", "unknown"),
+                "notify_session_id": notify_session_id,
             }
         else:  # ai_task
             action = {
@@ -175,7 +181,8 @@ class SchedulerTool(BaseTool):
                 "receiver": context.get("receiver"),
                 "receiver_name": self._get_receiver_name(context),
                 "is_group": context.get("isgroup", False),
-                "channel_type": self.config.get("channel_type", "unknown")
+                "channel_type": self.config.get("channel_type", "unknown"),
+                "notify_session_id": notify_session_id,
             }
         
         # 针对钉钉单聊，额外存储 sender_staff_id
@@ -357,9 +364,12 @@ class SchedulerTool(BaseTool):
                         logger.error(f"[SchedulerTool] Invalid relative time format: {schedule_value}")
                         return None
                 else:
-                    # Absolute time in ISO format
+                    # Absolute ISO time. Normalize to tz-naive local so it
-                    datetime.fromisoformat(schedule_value)
+                    # stays comparable with the scheduler's datetime.now().
-                    return {"type": "once", "run_at": schedule_value}
+                    parsed = datetime.fromisoformat(schedule_value)
+                    if parsed.tzinfo is not None:
+                        parsed = parsed.astimezone().replace(tzinfo=None)
+                    return {"type": "once", "run_at": parsed.isoformat()}
             
         except Exception as e:
             logger.error(f"[SchedulerTool] Invalid schedule: {e}")

agent/tools/scheduler/task_store.py

@@ -182,8 +182,15 @@ class TaskStore:
         if enabled_only:
             task_list = [t for t in task_list if t.get("enabled", True)]
         
-        # Sort by next_run_at
+        # Sort by enabled status (enabled first), then by next_run_at
-        task_list.sort(key=lambda t: t.get("next_run_at", float('inf')))
+        def sort_key(t):
+            enabled = t.get("enabled", True)
+            next_run = t.get("next_run_at", "")
+            # Enabled tasks first (0), disabled tasks second (1)
+            # Then sort by next_run_at (empty string sorts last)
+            return (0 if enabled else 1, next_run if next_run else "9999-12-31")
+        
+        task_list.sort(key=sort_key)
         
         return task_list
     

agent/tools/send/send.py

@@ -14,14 +14,14 @@ class Send(BaseTool):
     """Tool for sending files to the user"""
     
     name: str = "send"
-    description: str = "Send a file (image, video, audio, document) to the user. Use this when the user explicitly asks to send/share a file."
+    description: str = "Send a LOCAL file (image, video, audio, document) to the user. Only for local file paths. Do NOT use this for URLs — URLs should be included directly in your text reply, the system will handle them automatically."
     
     params: dict = {
         "type": "object",
         "properties": {
             "path": {
                 "type": "string",
-                "description": "Path to the file to send. Can be absolute path or relative to workspace."
+                "description": "Local file path to send. Must be an absolute path or relative to workspace. Do NOT pass URLs here."
             },
             "message": {
                 "type": "string",
@@ -54,6 +54,11 @@ class Send(BaseTool):
         if not path:
             return ToolResult.fail("Error: path parameter is required")
         
+        # Pass through remote URLs directly (no local file check): the client
+        # renders the link inline, so no download is needed.
+        if path.lower().startswith(("http://", "https://")):
+            return self._build_url_result(path, message)
+        
         # Resolve path
         absolute_path = self._resolve_path(path)
         
@@ -98,9 +103,60 @@ class Send(BaseTool):
             "size_formatted": self._format_size(file_size),
             "message": message or f"正在发送 {file_name}"
         }
-        
+
+        try:
+            from common.cloud_client import get_website_base_url, copy_send_file
+
+            # Do nothing when in local env
+            if get_website_base_url():
+                url = copy_send_file(absolute_path, self.cwd)
+                if url:
+                    result["url"] = url
+        except Exception:
+            pass
+
         return ToolResult.success(result)
     
+    def _build_url_result(self, url: str, message: str) -> ToolResult:
+        """Build a file_to_send result for a remote http(s) URL.
+
+        The URL is passed through as both ``path`` and ``url`` so downstream
+        channels render it inline without downloading it locally.
+        """
+        # Infer file type from the URL path extension (ignore query string).
+        from urllib.parse import urlparse
+        url_path = urlparse(url).path
+        file_ext = Path(url_path).suffix.lower()
+        file_name = Path(url_path).name or "file"
+
+        if file_ext in self.image_extensions:
+            file_type = "image"
+            mime_type = self._get_image_mime_type(file_ext)
+        elif file_ext in self.video_extensions:
+            file_type = "video"
+            mime_type = self._get_video_mime_type(file_ext)
+        elif file_ext in self.audio_extensions:
+            file_type = "audio"
+            mime_type = self._get_audio_mime_type(file_ext)
+        elif file_ext in self.document_extensions:
+            file_type = "document"
+            mime_type = self._get_document_mime_type(file_ext)
+        else:
+            # Default to image: most pass-through URLs are generated images.
+            file_type = "image"
+            mime_type = "image/jpeg"
+
+        result = {
+            "type": "file_to_send",
+            "file_type": file_type,
+            "path": url,
+            "url": url,
+            "file_name": file_name,
+            "mime_type": mime_type,
+            "message": message or f"正在发送 {file_name}",
+        }
+        return ToolResult.success(result)
+
     def _resolve_path(self, path: str) -> str:
         """Resolve path to absolute path"""
         path = expand_path(path)

agent/tools/tool_manager.py

@@ -1,5 +1,6 @@
 import importlib
 import importlib.util
+import threading
 from pathlib import Path
 from typing import Dict, Any, Type
 from agent.tools.base_tool import BaseTool
@@ -7,6 +8,26 @@ from common.log import logger
 from config import conf
 
 
+def _normalize_mcp_configs(raw) -> list:
+    """
+    Convert MCP server config to internal list format.
+    Supports:
+      - list format (mcp_servers):  [{"name": "x", "type": "stdio", ...}]
+      - dict format (mcpServers):   {"x": {"command": "npx", ...}}
+    """
+    if isinstance(raw, list):
+        return raw
+    if isinstance(raw, dict):
+        result = []
+        for name, cfg in raw.items():
+            entry = {"name": name, **cfg}
+            if "type" not in entry:
+                entry["type"] = "sse" if "url" in entry else "stdio"
+            result.append(entry)
+        return result
+    return []
+
+
 class ToolManager:
     """
     Tool manager for managing tools.
@@ -25,6 +46,47 @@ class ToolManager:
         # Initialize only once
         if not hasattr(self, 'tool_classes'):
             self.tool_classes = {}  # Dictionary to store tool classes
+        if not hasattr(self, '_mcp_registry'):
+            self._mcp_registry = None  # Lazy init: only created when MCP servers are configured
+        if not hasattr(self, '_mcp_tool_instances'):
+            self._mcp_tool_instances: dict = {}  # tool_name -> McpTool instance
+        if not hasattr(self, '_mcp_lock'):
+            # Guards _mcp_loaded check-then-set so concurrent callers
+            # don't trigger duplicate background loaders.
+            self._mcp_lock = threading.Lock()
+        if not hasattr(self, '_mcp_loaded'):
+            # Idempotency flag. Flipped to True the moment the first loader
+            # is dispatched (synchronously, inside _mcp_lock). Subsequent
+            # _load_mcp_tools() calls become no-ops, so per-session agent
+            # initialization never re-forks MCP subprocesses.
+            self._mcp_loaded = False
+        if not hasattr(self, '_mcp_status'):
+            # server_name -> "pending" / "ready" / "failed"
+            # Useful for UI / introspection while async loading is in progress.
+            self._mcp_status: dict = {}
+        if not hasattr(self, '_mcp_signature'):
+            # (mtime, sha256) of mcp.json the last time we loaded.
+            # Used by refresh_mcp_if_changed() to skip re-parsing when nothing changed.
+            self._mcp_signature: tuple = (None, None)
+        if not hasattr(self, '_mcp_active_configs'):
+            # server_name -> normalized config dict, for diff-based reload.
+            self._mcp_active_configs: dict = {}
+        if not hasattr(self, '_mcp_tool_vectors'):
+            # mcp_tool_name -> embedding vector, used by on-demand tool
+            # retrieval. Populated lazily on first retrieval so users who
+            # never enable the feature pay zero embedding cost.
+            self._mcp_tool_vectors: dict = {}
+        if not hasattr(self, '_mcp_vector_lock'):
+            # Guards incremental index builds so concurrent turns don't
+            # double-embed the same newly-loaded MCP tools.
+            self._mcp_vector_lock = threading.Lock()
+        if not hasattr(self, '_embedding_provider_initialized'):
+            # The embedding provider is created once, lazily, and reused for
+            # both tool-index and per-query embeddings. None means keyword-only
+            # mode (no provider configured) — retrieval then falls back to full
+            # injection at the caller.
+            self._embedding_provider_initialized = False
+            self._embedding_provider = None
 
     def load_tools(self, tools_dir: str = "", config_dict=None):
         """
@@ -39,6 +101,8 @@ class ToolManager:
             self._load_tools_from_init()
             self._configure_tools_from_config(config_dict)
 
+        self._load_mcp_tools()
+
     def _load_tools_from_init(self) -> bool:
         """
         Load tool classes from tools.__init__.__all__
@@ -70,10 +134,14 @@ class ToolManager:
                                     and cls != BaseTool
                             ):
                                 try:
-                                    # Skip memory tools (they need special initialization with memory_manager)
+                                    # Skip tools that need special initialization
                                     if class_name in ["MemorySearchTool", "MemoryGetTool"]:
                                         logger.debug(f"Skipped tool {class_name} (requires memory_manager)")
                                         continue
+                                    # McpTool instances are registered dynamically via _load_mcp_tools()
+                                    if class_name == "McpTool":
+                                        logger.debug(f"Skipped tool {class_name} (registered dynamically via mcp_servers config)")
+                                        continue
                                     
                                     # Create a temporary instance to get the name
                                     temp_instance = cls()
@@ -84,11 +152,11 @@ class ToolManager:
                                 except ImportError as e:
                                     # Handle missing dependencies with helpful messages
                                     error_msg = str(e)
-                                    if "browser-use" in error_msg or "browser_use" in error_msg:
+                                    if "playwright" in error_msg:
                                         logger.warning(
                                             f"[ToolManager] Browser tool not loaded - missing dependencies.\n"
                                             f"  To enable browser tool, run:\n"
-                                            f"    pip install browser-use markdownify playwright\n"
+                                            f"    pip install playwright\n"
                                             f"    playwright install chromium"
                                         )
                                     elif "markdownify" in error_msg:
@@ -154,11 +222,11 @@ class ToolManager:
                             except ImportError as e:
                                 # Handle missing dependencies with helpful messages
                                 error_msg = str(e)
-                                if "browser-use" in error_msg or "browser_use" in error_msg:
+                                if "playwright" in error_msg:
                                     logger.warning(
                                         f"[ToolManager] Browser tool not loaded - missing dependencies.\n"
                                         f"  To enable browser tool, run:\n"
-                                        f"    pip install browser-use markdownify playwright\n"
+                                        f"    pip install playwright\n"
                                         f"    playwright install chromium"
                                     )
                                 elif "markdownify" in error_msg:
@@ -197,7 +265,7 @@ class ToolManager:
                         logger.warning(
                             f"[ToolManager] Browser tool is configured but not loaded.\n"
                             f"  To enable browser tool, run:\n"
-                            f"    pip install browser-use markdownify playwright\n"
+                            f"    pip install playwright\n"
                             f"    playwright install chromium"
                         )
                     elif tool_name == "google_search":
@@ -212,6 +280,401 @@ class ToolManager:
         except Exception as e:
             logger.error(f"Error configuring tools from config: {e}")
 
+    def _mcp_json_path(self) -> str:
+        import os
+        workspace = os.path.expanduser(conf().get("agent_workspace", "~/cow"))
+        return os.path.join(workspace, "mcp.json")
+
+    def _read_mcp_json_signature(self):
+        """
+        Return (mtime, sha256_of_bytes) for ~/cow/mcp.json without parsing.
+        Returns (None, None) if the file doesn't exist or is unreadable.
+        Cheap enough (one stat + one small read) to call on every agent init.
+        """
+        import os
+        import hashlib
+        path = self._mcp_json_path()
+        try:
+            mtime = os.path.getmtime(path)
+        except OSError:
+            return (None, None)
+        try:
+            with open(path, "rb") as f:
+                digest = hashlib.sha256(f.read()).hexdigest()
+        except OSError:
+            return (mtime, None)
+        return (mtime, digest)
+
+    def _load_mcp_configs(self) -> list:
+        """
+        Load MCP server configs with priority:
+          1. ~/cow/mcp.json  (supports both mcpServers and mcp_servers keys)
+          2. config.json mcp_servers field (fallback)
+        """
+        import os
+        import json as _json
+
+        mcp_json_path = self._mcp_json_path()
+
+        if os.path.exists(mcp_json_path):
+            try:
+                with open(mcp_json_path, "r", encoding="utf-8") as f:
+                    data = _json.load(f)
+                raw = data.get("mcpServers") or data.get("mcp_servers") or data
+                logger.info(f"[ToolManager] Loading MCP config from {mcp_json_path}")
+                return _normalize_mcp_configs(raw)
+            except Exception as e:
+                logger.warning(f"[ToolManager] Failed to read {mcp_json_path}: {e}, falling back to config.json")
+
+        raw = conf().get("mcp_servers", [])
+        return _normalize_mcp_configs(raw)
+
+    def _load_mcp_tools(self):
+        """
+        Trigger MCP tool loading in a background thread (idempotent).
+
+        Returns immediately. Booting MCP servers (npx, uvx, etc.) takes
+        seconds to tens of seconds on first run, which would otherwise
+        block agent initialization and the user's first message.
+        Built-in tools work fine without MCP, so we let the agent serve
+        traffic right away and let MCP servers come online in the
+        background. Per-session agents read a snapshot of whatever is
+        ready at construction time and gracefully ignore the rest.
+        """
+        with self._mcp_lock:
+            if self._mcp_loaded:
+                return
+            mcp_servers_config = self._load_mcp_configs()
+            # Snapshot the signature now so future refresh_mcp_if_changed()
+            # calls can short-circuit when nothing has changed on disk.
+            self._mcp_signature = self._read_mcp_json_signature()
+            self._mcp_active_configs = {
+                cfg.get("name", "<unnamed>"): cfg for cfg in mcp_servers_config
+            }
+            if not mcp_servers_config:
+                # Mark as loaded even when there is nothing to load,
+                # so we don't re-read the config file on every call.
+                self._mcp_loaded = True
+                return
+
+            # Mark pending immediately so list_mcp_status() callers see
+            # the in-progress state instead of an empty dict.
+            for cfg in mcp_servers_config:
+                name = cfg.get("name", "<unnamed>")
+                self._mcp_status[name] = "pending"
+
+            self._mcp_loaded = True
+            threading.Thread(
+                target=self._load_mcp_tools_async,
+                args=(mcp_servers_config,),
+                daemon=True,
+                name="mcp-loader",
+            ).start()
+            logger.info(
+                f"[ToolManager] MCP loading started in background "
+                f"({len(mcp_servers_config)} server(s) configured)"
+            )
+
+    def refresh_mcp_if_changed(self):
+        """
+        Cheap check whether ~/cow/mcp.json has changed since last load.
+        If it has, do a diff-based reload: start newly added servers,
+        shut down removed ones, and restart any whose config was edited.
+        Untouched servers are left running.
+
+        Designed to be called on every agent creation. The fast path is
+        a single os.stat() — completely free when nothing has changed.
+        """
+        with self._mcp_lock:
+            new_sig = self._read_mcp_json_signature()
+            if new_sig == self._mcp_signature:
+                return  # no-op fast path
+
+            try:
+                new_configs = self._load_mcp_configs()
+            except Exception as e:
+                logger.warning(f"[ToolManager] MCP reload — failed to parse config: {e}")
+                return
+
+            new_by_name = {
+                cfg.get("name", "<unnamed>"): cfg for cfg in new_configs
+            }
+            old_by_name = self._mcp_active_configs
+
+            added = [n for n in new_by_name if n not in old_by_name]
+            removed = [n for n in old_by_name if n not in new_by_name]
+            changed = [
+                n for n in new_by_name
+                if n in old_by_name and new_by_name[n] != old_by_name[n]
+            ]
+
+            if not (added or removed or changed):
+                # Signature drifted but content is logically identical
+                # (e.g. user re-saved the file without edits). Just sync.
+                self._mcp_signature = new_sig
+                return
+
+            logger.info(
+                f"[ToolManager] mcp.json changed — "
+                f"adding={added}, removing={removed}, restarting={changed}"
+            )
+
+            # Tear down removed + changed servers (changed ones get restarted below)
+            for name in removed + changed:
+                self._teardown_mcp_server(name)
+
+            # Spin up newly added + changed servers in the background
+            to_start = [new_by_name[n] for n in added + changed]
+            if to_start:
+                for cfg in to_start:
+                    self._mcp_status[cfg.get("name", "<unnamed>")] = "pending"
+                threading.Thread(
+                    target=self._load_mcp_tools_async,
+                    args=(to_start,),
+                    daemon=True,
+                    name="mcp-loader-reload",
+                ).start()
+
+            self._mcp_active_configs = new_by_name
+            self._mcp_signature = new_sig
+
+    def _teardown_mcp_server(self, server_name: str):
+        """Shut down one MCP server and drop its tools from the registry."""
+        if self._mcp_registry is None:
+            return
+        client = None
+        with self._mcp_registry._registry_lock:
+            client = self._mcp_registry._clients.pop(server_name, None)
+        if client is not None:
+            try:
+                client.shutdown()
+            except Exception as e:
+                logger.warning(f"[MCP] Error shutting down '{server_name}': {e}")
+        # Drop tools that belonged to this server.
+        for tool_name in list(self._mcp_tool_instances.keys()):
+            tool = self._mcp_tool_instances.get(tool_name)
+            if tool is not None and getattr(tool, "server_name", None) == server_name:
+                self._mcp_tool_instances.pop(tool_name, None)
+        self._mcp_status.pop(server_name, None)
+
+    def _load_mcp_tools_async(self, mcp_servers_config):
+        """
+        Background worker: bring up each MCP server one-by-one and
+        publish ready tools to _mcp_tool_instances as they come online.
+
+        Server failures are isolated — one bad server cannot block
+        the others, and never raises out of the worker thread.
+        """
+        try:
+            from agent.tools.mcp.mcp_client import McpClient, McpClientRegistry
+            from agent.tools.mcp.mcp_tool import McpTool
+
+            registry = McpClientRegistry()
+            self._mcp_registry = registry
+
+            for cfg in mcp_servers_config:
+                server_name = cfg.get("name", "<unnamed>")
+                try:
+                    client = McpClient(cfg)
+                    if not client.initialize():
+                        self._mcp_status[server_name] = "failed"
+                        logger.warning(
+                            f"[MCP] Server '{server_name}' failed to initialize — skipping"
+                        )
+                        continue
+
+                    tool_schemas = client.list_tools()
+                    added = []
+                    for schema in tool_schemas:
+                        tool_name = schema.get("name", "")
+                        if not tool_name:
+                            continue
+                        mcp_tool = McpTool(client, schema, server_name)
+                        # Atomic dict assignment is GIL-safe; readers iterate
+                        # over a list() snapshot to avoid concurrent mutation.
+                        self._mcp_tool_instances[tool_name] = mcp_tool
+                        added.append(tool_name)
+
+                    # Register client into the shared registry only after its
+                    # tools are visible, so callers never see a half-loaded server.
+                    with registry._registry_lock:
+                        registry._clients[server_name] = client
+                    self._mcp_status[server_name] = "ready"
+                    logger.info(
+                        f"[MCP] Server '{server_name}' ready — "
+                        f"{len(added)} tool(s): {added}"
+                    )
+                except Exception as e:
+                    self._mcp_status[server_name] = "failed"
+                    logger.warning(f"[MCP] Server '{server_name}' load failed: {e}")
+
+            ready = sum(1 for s in self._mcp_status.values() if s == "ready")
+            total = len(self._mcp_status)
+            logger.info(
+                f"[ToolManager] MCP loading complete: "
+                f"{ready}/{total} server(s) ready, "
+                f"{len(self._mcp_tool_instances)} tool(s) available"
+            )
+        except Exception as e:
+            logger.warning(f"[ToolManager] MCP background loader crashed: {e}")
+
+    def list_mcp_status(self) -> dict:
+        """Return {server_name: status} snapshot for UI / debugging."""
+        return dict(self._mcp_status)
+
+    def sync_mcp_into_agent(self, agent) -> tuple:
+        """
+        Reconcile a live agent's tool collection with the current MCP tool registry.
+
+        Adds tools that finished loading after the agent was created,
+        and removes tools whose MCP server was torn down. Built-in tools
+        on the agent are left untouched.
+
+        Handles both representations CowAgent uses:
+          - Agent.tools: list[BaseTool]               (default Agent class)
+          - AgentStream.tools: dict[str, BaseTool]    (streaming agent)
+
+        Returns (added_names, removed_names) for logging.
+        """
+        if agent is None or not hasattr(agent, "tools"):
+            return ([], [])
+
+        # Never re-inject MCP tools into a restricted Self-Evolution review agent.
+        # The review agent is created with a deliberately reduced, workspace-guarded
+        # toolset; silently re-adding configured MCP tools here would bypass that
+        # policy boundary (see agent/evolution/executor.py). The flag may live on
+        # the agent itself (Agent) or on the wrapping stream executor's .agent.
+        if getattr(agent, "_evolution_restricted", False) or getattr(
+            getattr(agent, "agent", None), "_evolution_restricted", False
+        ):
+            return ([], [])
+
+        from agent.tools.mcp.mcp_tool import McpTool
+        current = self._mcp_tool_instances
+        registry_names = set(current.keys())
+
+        agent_tools = agent.tools
+
+        if isinstance(agent_tools, dict):
+            agent_mcp_names = {
+                name for name, tool in agent_tools.items()
+                if isinstance(tool, McpTool)
+            }
+            added = registry_names - agent_mcp_names
+            removed = agent_mcp_names - registry_names
+            if not (added or removed):
+                return ([], [])
+            for name in added:
+                agent_tools[name] = current[name]
+            for name in removed:
+                agent_tools.pop(name, None)
+
+        elif isinstance(agent_tools, list):
+            agent_mcp_names = {
+                t.name for t in agent_tools if isinstance(t, McpTool)
+            }
+            added = registry_names - agent_mcp_names
+            removed = agent_mcp_names - registry_names
+            if not (added or removed):
+                return ([], [])
+            if removed:
+                agent.tools = [
+                    t for t in agent_tools
+                    if not (isinstance(t, McpTool) and t.name in removed)
+                ]
+            for name in added:
+                agent.tools.append(current[name])
+
+        else:
+            return ([], [])
+
+        return (sorted(added), sorted(removed))
+
+    # ------------------------------------------------------------------
+    # On-demand MCP tool retrieval support
+    #
+    # The vector index and the embedding provider are owned here (singleton,
+    # process-wide, aligned with the MCP tool lifecycle). The context-aware
+    # selection itself lives in agent.tools.mcp.tool_retrieval, driven by the
+    # executor which is the only place that knows the conversation context.
+    # ------------------------------------------------------------------
+
+    def count_mcp_tools(self) -> int:
+        """Return the number of currently loaded MCP tools."""
+        return len(self._mcp_tool_instances)
+
+    def get_mcp_tool_vectors(self) -> dict:
+        """Return ``{mcp_tool_name: vector}`` for currently loaded MCP tools.
+
+        Lazily embeds any MCP tools not yet in the cache (MCP servers load
+        asynchronously, so tools may appear over time). Returns an empty dict
+        when no embedding provider is available or embedding fails — the caller
+        then falls back to full injection. Never raises.
+        """
+        try:
+            self._ensure_mcp_tool_vectors()
+        except Exception as e:
+            logger.debug(f"[ToolManager] MCP tool vector build skipped: {e}")
+        return dict(self._mcp_tool_vectors)
+
+    def embed_query(self, text: str):
+        """Embed a retrieval query with the shared provider.
+
+        Returns the embedding vector, or None if no provider is available or
+        the call fails (caller falls back to full injection). Never raises.
+        """
+        if not text:
+            return None
+        provider = self._get_embedding_provider()
+        if provider is None:
+            return None
+        try:
+            return provider.embed_query(text)
+        except Exception as e:
+            logger.debug(f"[ToolManager] query embedding failed: {e}")
+            return None
+
+    def _ensure_mcp_tool_vectors(self) -> None:
+        """Incrementally embed MCP tools that are not yet cached."""
+        # Snapshot to avoid concurrent-mutation while the async loader runs.
+        current = dict(self._mcp_tool_instances)
+        missing = [name for name in current if name not in self._mcp_tool_vectors]
+        if not missing:
+            return
+
+        provider = self._get_embedding_provider()
+        if provider is None:
+            return
+
+        with self._mcp_vector_lock:
+            # Re-check under lock: another thread may have filled these in.
+            missing = [name for name in current if name not in self._mcp_tool_vectors]
+            if not missing:
+                return
+            texts = [self._mcp_tool_embed_text(current[name]) for name in missing]
+            vectors = provider.embed_batch(texts)
+            for name, vec in zip(missing, vectors):
+                self._mcp_tool_vectors[name] = vec
+
+    @staticmethod
+    def _mcp_tool_embed_text(tool) -> str:
+        """Build the text that represents an MCP tool for embedding."""
+        name = getattr(tool, "name", "") or ""
+        description = getattr(tool, "description", "") or ""
+        return f"{name}: {description}".strip()
+
+    def _get_embedding_provider(self):
+        """Lazily create and cache the shared embedding provider (or None)."""
+        if not self._embedding_provider_initialized:
+            try:
+                from agent.memory.embedding import create_default_embedding_provider
+                self._embedding_provider = create_default_embedding_provider()
+            except Exception as e:
+                logger.warning(f"[ToolManager] embedding provider init failed: {e}")
+                self._embedding_provider = None
+            self._embedding_provider_initialized = True
+        return self._embedding_provider
+
     def create_tool(self, name: str) -> BaseTool:
         """
         Get a new instance of a tool by name.
@@ -229,6 +692,12 @@ class ToolManager:
                 tool_instance.config = self.tool_configs[name]
 
             return tool_instance
+
+        # Fall back to MCP tool instances
+        mcp_tool = self._mcp_tool_instances.get(name)
+        if mcp_tool:
+            return mcp_tool
+
         return None
 
     def list_tools(self) -> dict:
@@ -245,4 +714,17 @@ class ToolManager:
                 "description": temp_instance.description,
                 "parameters": temp_instance.get_json_schema()
             }
+
+        # Include MCP tool instances
+        for name, mcp_tool in self._mcp_tool_instances.items():
+            result[name] = {
+                "description": mcp_tool.description,
+                "parameters": mcp_tool.params,
+            }
+
         return result
+
+    def shutdown_mcp(self):
+        """Shut down all MCP server clients."""
+        if self._mcp_registry:
+            self._mcp_registry.shutdown_all()

agent/tools/utils/__init__.py

@@ -20,6 +20,11 @@ from .diff import (
     FuzzyMatchResult
 )
 
+from .url_safety import (
+    validate_url_safe,
+    assert_public_ip
+)
+
 __all__ = [
     'truncate_head',
     'truncate_tail',
@@ -36,5 +41,7 @@ __all__ = [
     'normalize_for_fuzzy_match',
     'fuzzy_find_text',
     'generate_diff_string',
-    'FuzzyMatchResult'
+    'FuzzyMatchResult',
+    'validate_url_safe',
+    'assert_public_ip'
 ]

agent/tools/utils/diff.py

@@ -111,20 +111,46 @@ def fuzzy_find_text(content: str, old_text: str) -> FuzzyMatchResult:
             content_for_replacement=content
         )
     
-    # Try fuzzy match
+    # Fuzzy match: the exact substring was not found, most likely because the
-    fuzzy_content = normalize_for_fuzzy_match(content)
+    # whitespace differs (indentation, spaces around operators, trailing
-    fuzzy_old_text = normalize_for_fuzzy_match(old_text)
+    # spaces). Locate the region in the ORIGINAL content using a
-    
+    # whitespace-flexible pattern and return offsets into that original
-    index = fuzzy_content.find(fuzzy_old_text)
+    # content.
-    if index != -1:
+    #
-        # Fuzzy match successful, use normalized content for replacement
+    # This must NOT replace inside a whitespace-normalized copy of the file:
-        return FuzzyMatchResult(
+    # doing so previously returned the normalized copy as
-            found=True,
+    # content_for_replacement, which caused the whole file to be rewritten
-            index=index,
+    # with collapsed indentation (every untouched line got reformatted).
-            match_length=len(fuzzy_old_text),
+    stripped = old_text.strip('\n')
-            content_for_replacement=fuzzy_content
+    if stripped.strip():
-        )
+        source_lines = stripped.split('\n')
-    
+        line_patterns = []
+        for i, line in enumerate(source_lines):
+            tokens = line.split()
+            if not tokens:
+                line_patterns.append(r'[ \t]*')
+                continue
+            # Tolerate any run of blanks between tokens.
+            core = r'[ \t]+'.join(re.escape(tok) for tok in tokens)
+            # First-line leading whitespace is folded into the match only when
+            # old_text itself was indented here; otherwise it stays OUTSIDE the
+            # match so a no-indent old_text preserves (does not swallow and drop)
+            # the file's existing indentation -- mirroring an exact substring
+            # match. Inner lines always tolerate indentation: it sits inside the
+            # matched region and is re-supplied by new_text.
+            if i > 0 or line[:1] in (' ', '\t'):
+                core = r'[ \t]*' + core
+            line_patterns.append(core + r'[ \t]*')
+        pattern = '\n'.join(line_patterns)
+        match = re.search(pattern, content)
+        if match:
+            return FuzzyMatchResult(
+                found=True,
+                index=match.start(),
+                match_length=match.end() - match.start(),
+                content_for_replacement=content
+            )
+
     # Not found
     return FuzzyMatchResult(found=False)
 

agent/tools/utils/truncate.py

@@ -8,7 +8,10 @@ Truncation is based on two independent limits - whichever is hit first wins:
 Never returns partial lines (except bash tail truncation edge case).
 """
 
-from typing import Dict, Any, Optional, Literal, Tuple
+from __future__ import annotations
+from typing import Dict, Any, Optional, Tuple, TYPE_CHECKING
+if TYPE_CHECKING:
+    from typing import Literal
 
 
 DEFAULT_MAX_LINES = 2000

agent/tools/utils/url_safety.py

@@ -0,0 +1,96 @@
+"""
+Shared SSRF guard utilities for tools that fetch model-supplied URLs.
+
+SSRF protection is OPT-IN and disabled by default, because legitimate use
+cases (local dev servers, LAN services, proxy fake-ip resolution) need to
+reach non-public addresses. Enable it by setting the config option
+``web_security_ssrf_protection: true`` (or env ``WEB_SECURITY_SSRF_PROTECTION``).
+
+When enabled, a URL is only considered safe when it uses an http/https
+scheme, has a hostname, that hostname resolves, and every resolved address
+is a public (internet-routable) address. Loopback, private (RFC1918 / ULA),
+link-local (incl. the 169.254.169.254 cloud-metadata endpoint) and otherwise
+reserved addresses are rejected, for both IPv4 and IPv6.
+"""
+
+import ipaddress
+import os
+import socket
+from urllib.parse import urlparse
+
+
+def _ssrf_protection_enabled() -> bool:
+    """Return True only when SSRF protection is explicitly turned on.
+
+    Disabled by default. Reads the env var first, then falls back to the
+    global config; any failure to read config is treated as "disabled" so
+    the guard never breaks normal fetching.
+    """
+    env = os.getenv("WEB_SECURITY_SSRF_PROTECTION")
+    if env is not None:
+        return env.strip().lower() in ("1", "true", "yes", "on")
+    try:
+        from config import conf
+        return bool(conf().get("web_security_ssrf_protection", False))
+    except Exception:
+        return False
+
+
+def _is_blocked_ip(ip: "ipaddress._BaseAddress") -> bool:
+    """Return True if the address is not safe to connect to (non-public)."""
+    return (
+        ip.is_private
+        or ip.is_loopback
+        or ip.is_link_local
+        or ip.is_reserved
+        or ip.is_multicast
+        or ip.is_unspecified
+    )
+
+
+def assert_public_ip(ip_str: str) -> None:
+    """Raise ValueError if the given literal IP is a non-public address.
+
+    No-op when SSRF protection is disabled (the default). Used to re-validate
+    the concrete address a redirect resolved to.
+    """
+    if not _ssrf_protection_enabled():
+        return
+    ip = ipaddress.ip_address(ip_str)
+    if _is_blocked_ip(ip):
+        raise ValueError(
+            f"URL resolves to a non-public address ({ip_str}), "
+            f"request blocked for security"
+        )
+
+
+def validate_url_safe(url: str) -> None:
+    """Reject URLs that target private/loopback/link-local addresses (SSRF guard).
+
+    No-op when SSRF protection is disabled (the default). When enabled,
+    resolves the hostname to its IP address(es) and blocks any that fall
+    into non-public ranges. Also rejects URLs with no host, non-HTTP(S)
+    schemes, or hosts that fail DNS resolution.
+
+    Raises:
+        ValueError: if the URL targets a disallowed address.
+    """
+    if not _ssrf_protection_enabled():
+        return
+
+    parsed = urlparse(url)
+    if parsed.scheme not in ("http", "https"):
+        raise ValueError(f"Unsupported URL scheme: {parsed.scheme}")
+
+    hostname = parsed.hostname
+    if not hostname:
+        raise ValueError("URL has no hostname")
+
+    try:
+        # Resolve all addresses for the hostname.
+        addr_infos = socket.getaddrinfo(hostname, None, socket.AF_UNSPEC, socket.SOCK_STREAM)
+    except socket.gaierror:
+        raise ValueError(f"Cannot resolve hostname: {hostname}")
+
+    for family, _, _, _, sockaddr in addr_infos:
+        assert_public_ip(sockaddr[0])

agent/tools/vision/__init__.py

@@ -0,0 +1 @@
+from agent.tools.vision.vision import Vision

agent/tools/vision/vision.py

@@ -0,0 +1,866 @@
+"""
+Vision tool - Analyze images using Vision API.
+Supports local files (auto base64-encoded) and HTTP URLs.
+
+Provider resolution:
+  - tools.vision.model (if set) means "prefer this model first; fall back to
+    other configured providers if it fails". The model name is mapped to its
+    native provider (e.g. doubao-* → Doubao, kimi-* → Moonshot, gpt-* →
+    OpenAI/LinkAI). That provider is tried first, then the standard auto
+    chain runs as fallback (with the preferred provider de-duplicated).
+  - Auto chain priority:
+      1. Main model via bot.call_vision — only when the main bot is known
+         to actually support vision (not just expose a call_vision method).
+      2. Other models whose API key is configured.
+      3. OpenAI / LinkAI raw HTTP.
+    When use_linkai=true, LinkAI is promoted to #1.
+"""
+
+import base64
+import os
+import subprocess
+import tempfile
+from dataclasses import dataclass, field
+from typing import Any, Dict, List, Optional
+
+import requests
+
+from agent.tools.base_tool import BaseTool, ToolResult
+from agent.tools.utils.url_safety import validate_url_safe
+from common import const
+from common.log import logger
+from config import conf
+
+DEFAULT_MODEL = const.GPT_41_MINI
+DEFAULT_TIMEOUT = 180
+MAX_TOKENS = 4000
+COMPRESS_THRESHOLD = 1_048_576  # 1 MB
+
+SUPPORTED_EXTENSIONS = {
+    "jpg": "image/jpeg",
+    "jpeg": "image/jpeg",
+    "png": "image/png",
+    "gif": "image/gif",
+    "webp": "image/webp",
+}
+
+_MAIN_MODEL_PROVIDER_NAME = "MainModel"
+
+# (config_key_for_api_key, bot_type, default_vision_model, provider_display_name)
+# Auto-discovered as fallback vision providers when their API key is configured.
+# OpenAI and LinkAI are handled separately (raw HTTP providers), so not listed here.
+_DISCOVERABLE_MODELS = [
+    ("moonshot_api_key", const.MOONSHOT, const.KIMI_K2_6, "Moonshot"),
+    ("ark_api_key", const.DOUBAO, const.DOUBAO_SEED_2_PRO, "Doubao"),
+    ("dashscope_api_key", const.QWEN_DASHSCOPE, const.QWEN37_PLUS, "DashScope"),
+    ("claude_api_key", const.CLAUDEAPI, const.CLAUDE_SONNET_5, "Claude"),
+    ("gemini_api_key", const.GEMINI, const.GEMINI_35_FLASH, "Gemini"),
+    ("qianfan_api_key", const.QIANFAN, const.ERNIE_45_TURBO_VL, "Qianfan"),
+    ("zhipu_ai_api_key", const.ZHIPU_AI, const.GLM_4_7, "ZhipuAI"),
+    ("minimax_api_key", const.MiniMax, const.MINIMAX_M2_7, "MiniMax"),
+    ("mimo_api_key", const.MIMO, const.MIMO_V2_5_PRO, "MiMo"),
+]
+
+# Model name prefix → discoverable provider display_name.
+# Used to auto-route tools.vision.model to its native provider.
+# Matched case-insensitively; longest prefix wins.
+_MODEL_PREFIX_TO_PROVIDER = [
+    ("doubao-", "Doubao"),
+    ("kimi-", "Moonshot"),
+    ("moonshot-", "Moonshot"),
+    ("qwen", "DashScope"),       # qwen-*, qwen3-*, qwen3.6-*, etc.
+    ("claude-", "Claude"),
+    ("ernie-", "Qianfan"),
+    ("gemini-", "Gemini"),
+    ("glm-", "ZhipuAI"),
+    ("minimax-", "MiniMax"),
+    ("abab", "MiniMax"),
+    ("mimo-", "MiMo"),
+]
+
+# Model prefixes that natively belong to OpenAI / LinkAI (raw HTTP providers).
+_OPENAI_MODEL_PREFIXES = ("gpt-", "o1-", "o3-", "o4-", "chatgpt-")
+
+# Maps the UI provider id (persisted in tools.vision.provider) to the internal
+# display name used in VisionProvider.name. Keep in sync with _DISCOVERABLE_MODELS
+# and the openai/linkai branches in _route_by_model_name.
+_PROVIDER_ID_TO_DISPLAY = {
+    "openai": "OpenAI",
+    "linkai": "LinkAI",
+    "moonshot": "Moonshot",
+    "doubao": "Doubao",
+    "dashscope": "DashScope",
+    "claudeAPI": "Claude",
+    "gemini": "Gemini",
+    "qianfan": "Qianfan",
+    "zhipu": "ZhipuAI",
+    "minimax": "MiniMax",
+    "mimo": "MiMo",
+}
+
+
+@dataclass
+class VisionProvider:
+    """A single Vision API provider configuration."""
+    name: str
+    api_key: str
+    api_base: str
+    extra_headers: dict = field(default_factory=dict)
+    model_override: Optional[str] = None
+    use_bot: bool = False  # When True, call via bot.call_vision instead of raw HTTP
+    fallback_bot: Any = None  # Bot instance for non-main-model providers
+
+
+class VisionAPIError(Exception):
+    """Raised when a Vision API call fails and should trigger fallback."""
+    pass
+
+
+class Vision(BaseTool):
+    """Analyze images using Vision API"""
+
+    name: str = "vision"
+    description: str = (
+        "Analyze a local image or image URL (jpg/jpeg/png) using Vision API. "
+        "Can describe content, extract text, identify objects, colors, etc. "
+    )
+
+    params: dict = {
+        "type": "object",
+        "properties": {
+            "image": {
+                "type": "string",
+                "description": "Local file path or HTTP(S) URL of the image to analyze",
+            },
+            "question": {
+                "type": "string",
+                "description": "Question to ask about the image",
+            },
+        },
+        "required": ["image", "question"],
+    }
+
+    def __init__(self, config: dict = None):
+        self.config = config or {}
+
+    @staticmethod
+    def is_available() -> bool:
+        return True
+
+    def execute(self, args: Dict[str, Any]) -> ToolResult:
+        image = args.get("image", "").strip()
+        question = args.get("question", "").strip()
+
+        if not image:
+            return ToolResult.fail("Error: 'image' parameter is required")
+        if not question:
+            return ToolResult.fail("Error: 'question' parameter is required")
+
+        providers = self._resolve_providers()
+        if not providers:
+            return ToolResult.fail(
+                "Error: No model available for Vision.\n"
+                "The main model does not support vision and no other API keys are configured.\n"
+                "Options:\n"
+                "  1. Switch to a multimodal model (e.g. claude-sonnet-5, qwen3.7-plus, gemini-2.0-flash, ernie-4.5-turbo-vl)\n"
+                "  2. Configure OPENAI_API_KEY: env_config(action=\"set\", key=\"OPENAI_API_KEY\", value=\"your-key\")\n"
+                "  3. Configure LINKAI_API_KEY: env_config(action=\"set\", key=\"LINKAI_API_KEY\", value=\"your-key\")"
+            )
+
+        try:
+            image_content = self._build_image_content(image)
+        except Exception as e:
+            return ToolResult.fail(f"Error: {e}")
+
+        # Default model is only used as a last-resort placeholder for providers
+        # whose VisionProvider.model_override is None (e.g. raw OpenAI provider
+        # when the user did not configure tools.vision.model).
+        return self._call_with_fallback(providers, DEFAULT_MODEL, question, image_content)
+
+    def _call_with_fallback(self, providers: List[VisionProvider], model: str,
+                            question: str, image_content: dict) -> ToolResult:
+        """Try each provider in order; fall back to the next one on failure."""
+        errors: List[str] = []
+        for i, provider in enumerate(providers):
+            use_model = provider.model_override or model
+            try:
+                logger.info(f"[Vision] Trying provider '{provider.name}' "
+                            f"with model '{use_model}' ({i + 1}/{len(providers)})")
+                if provider.use_bot:
+                    result = self._call_via_bot(use_model, question, image_content, provider)
+                else:
+                    result = self._call_api(provider, use_model, question, image_content)
+                logger.info(f"[Vision] ✅ Success via {provider.name} (model={use_model})")
+                return result
+            except VisionAPIError as e:
+                errors.append(f"[{provider.name}/{use_model}] {e}")
+                logger.warning(f"[Vision] Provider '{provider.name}' failed: {e}")
+            except requests.Timeout:
+                errors.append(f"[{provider.name}/{use_model}] Request timed out after {DEFAULT_TIMEOUT}s")
+                logger.warning(f"[Vision] Provider '{provider.name}' timed out")
+            except requests.ConnectionError:
+                errors.append(f"[{provider.name}/{use_model}] Connection failed")
+                logger.warning(f"[Vision] Provider '{provider.name}' connection failed")
+            except Exception as e:
+                errors.append(f"[{provider.name}/{use_model}] {e}")
+                logger.error(f"[Vision] Provider '{provider.name}' unexpected error: {e}", exc_info=True)
+
+        return ToolResult.fail(
+            "Error: All Vision API providers failed.\n" + "\n".join(f"  - {err}" for err in errors)
+        )
+
+    def _resolve_providers(self) -> List[VisionProvider]:
+        """
+        Build an ordered list of providers to try.
+
+        Semantics of `tools.vision.model`:
+          "Prefer this model first; fall back to other configured providers
+           if it fails."
+
+        Order:
+          1. The provider that natively serves `tools.vision.model` (if any
+             and its API key is configured) — using the user-specified model
+             name verbatim.
+          2. Auto-discovery chain as fallback:
+               - use_linkai=true → [LinkAI, MainModel?, OtherModels…, OpenAI]
+               - default         → [MainModel?, OtherModels…, OpenAI, LinkAI]
+             MainModel is only included when the main bot is known to support
+             vision (see _main_bot_supports_vision).
+
+        Providers that share the same display name as the preferred provider
+        are de-duplicated to avoid retrying the same endpoint twice.
+        """
+        user_model = self._resolve_user_vision_model()
+        user_provider = self._resolve_user_vision_provider()
+        providers: List[VisionProvider] = []
+
+        # Step 1: preferred provider — explicit `tools.vision.provider`
+        # wins so custom model names can still be routed correctly. Falls
+        # through to model-name prefix inference when provider is unset.
+        preferred = None
+        if user_provider and user_model:
+            preferred = self._route_by_provider_id(user_provider, user_model)
+        if not preferred and user_model:
+            preferred = self._route_by_model_name(user_model)
+        if preferred:
+            providers.extend(preferred)
+
+        # Step 2: auto-discovery chain as fallback
+        existing = {p.name for p in providers}
+        fallback: List[VisionProvider] = []
+        use_linkai = conf().get("use_linkai", False) and conf().get("linkai_api_key")
+
+        if use_linkai:
+            self._append_provider(fallback, lambda: self._build_linkai_provider(user_model))
+            self._append_provider(fallback, self._build_main_model_provider)
+            self._append_other_model_providers(fallback, preferred_model=user_model)
+            self._append_provider(fallback, lambda: self._build_openai_provider(user_model))
+        else:
+            self._append_provider(fallback, self._build_main_model_provider)
+            self._append_other_model_providers(fallback, preferred_model=user_model)
+            self._append_provider(fallback, lambda: self._build_openai_provider(user_model))
+            self._append_provider(fallback, lambda: self._build_linkai_provider(user_model))
+
+        for p in fallback:
+            if p.name in existing:
+                continue
+            providers.append(p)
+            existing.add(p.name)
+
+        return providers
+
+    @staticmethod
+    def _append_provider(providers: List[VisionProvider], builder) -> None:
+        p = builder()
+        if p:
+            providers.append(p)
+
+    @staticmethod
+    def _resolve_user_vision_model() -> Optional[str]:
+        """Read tools.vision.model (singular ``tool`` kept as runtime fallback)."""
+        tools_conf = conf().get("tools") or conf().get("tool") or {}
+        if not isinstance(tools_conf, dict):
+            return None
+        vision_conf = tools_conf.get("vision", {})
+        if not isinstance(vision_conf, dict):
+            return None
+        m = vision_conf.get("model")
+        if isinstance(m, str) and m.strip():
+            return m.strip()
+        return None
+
+    @staticmethod
+    def _resolve_user_vision_provider() -> Optional[str]:
+        """Read tools.vision.provider — the UI-persisted vendor id.
+
+        Lets users pin a vendor for custom model names that prefix-inference
+        can't recognize. Returns None when unset/blank.
+        """
+        tools_conf = conf().get("tools") or conf().get("tool") or {}
+        if not isinstance(tools_conf, dict):
+            return None
+        vision_conf = tools_conf.get("vision", {})
+        if not isinstance(vision_conf, dict):
+            return None
+        p = vision_conf.get("provider")
+        if isinstance(p, str) and p.strip():
+            return p.strip()
+        return None
+
+    @staticmethod
+    def _infer_provider_from_model(model_name: str) -> Optional[str]:
+        """
+        Infer the provider display name from a model name's prefix.
+        Returns None when no rule matches (or for OpenAI-family names, which
+        are handled separately by the caller).
+        """
+        if not model_name:
+            return None
+        lower = model_name.lower()
+        # Sort by prefix length desc so e.g. "moonshot-" wins over hypothetical "moo-"
+        for prefix, display_name in sorted(_MODEL_PREFIX_TO_PROVIDER, key=lambda x: -len(x[0])):
+            if lower.startswith(prefix.lower()):
+                return display_name
+        return None
+
+    def _route_by_provider_id(self, provider_id: str, user_model: str) -> Optional[List[VisionProvider]]:
+        """Route by the UI-persisted provider id.
+
+        Returns:
+          - [provider] : provider id is known and its key is configured.
+          - None       : unknown provider id, or the bot can't be created.
+                         Caller falls through to model-name-based routing.
+        """
+        # Custom OpenAI-compatible providers — read credentials from
+        # custom_providers list, same pattern as embedding.
+        if provider_id.startswith("custom:"):
+            p = self._build_custom_provider(provider_id, user_model)
+            return [p] if p else None
+
+        display_name = _PROVIDER_ID_TO_DISPLAY.get(provider_id)
+        if not display_name:
+            return None
+
+        # OpenAI / LinkAI use raw HTTP providers, not the discoverable bot path.
+        if provider_id == "openai":
+            p = self._build_openai_provider(user_model)
+            return [p] if p else None
+        if provider_id == "linkai":
+            p = self._build_linkai_provider(user_model)
+            return [p] if p else None
+
+        # Discoverable bot-backed providers.
+        for config_key, bot_type, _default_model, name in _DISCOVERABLE_MODELS:
+            if name != display_name:
+                continue
+            api_key = conf().get(config_key, "")
+            if not api_key or not api_key.strip():
+                logger.warning(f"[Vision] tools.vision.provider='{provider_id}' "
+                               f"but '{config_key}' is not configured. Falling back.")
+                return None
+            try:
+                from models.bot_factory import create_bot
+                bot = create_bot(bot_type)
+                if not hasattr(bot, 'call_vision'):
+                    logger.warning(f"[Vision] '{display_name}' bot does not implement call_vision.")
+                    return None
+            except Exception as e:
+                logger.warning(f"[Vision] Failed to create '{display_name}' bot: {e}")
+                return None
+            return [VisionProvider(
+                name=display_name,
+                api_key="",
+                api_base="",
+                model_override=user_model,
+                use_bot=True,
+                fallback_bot=bot,
+            )]
+        return None
+
+    def _route_by_model_name(self, user_model: str) -> Optional[List[VisionProvider]]:
+        """
+        Try to build a provider list using the user-specified model name.
+        Returns:
+          - [provider]  : matched and the provider's key is configured
+          - []          : matched but key missing → tell caller to surface this
+                          as a hard error rather than silently falling back
+          - None        : no rule matches → caller should fall through to auto
+        """
+        lower = user_model.lower()
+
+        # OpenAI / LinkAI family
+        if lower.startswith(_OPENAI_MODEL_PREFIXES):
+            providers: List[VisionProvider] = []
+            # Prefer LinkAI when explicitly enabled, else OpenAI first
+            use_linkai = conf().get("use_linkai", False) and conf().get("linkai_api_key")
+            if use_linkai:
+                self._append_provider(providers, lambda: self._build_linkai_provider(user_model))
+                self._append_provider(providers, lambda: self._build_openai_provider(user_model))
+            else:
+                self._append_provider(providers, lambda: self._build_openai_provider(user_model))
+                self._append_provider(providers, lambda: self._build_linkai_provider(user_model))
+            if providers:
+                return providers
+            logger.warning(f"[Vision] tools.vision.model='{user_model}' looks like an OpenAI "
+                           f"model but neither OPENAI_API_KEY nor LINKAI_API_KEY is configured.")
+            return None  # fall through to auto
+
+        # Discoverable native providers (Doubao, Moonshot, etc.)
+        target_display = self._infer_provider_from_model(user_model)
+        if not target_display:
+            return None  # unknown prefix → auto
+
+        for config_key, bot_type, _default_model, display_name in _DISCOVERABLE_MODELS:
+            if display_name != target_display:
+                continue
+            api_key = conf().get(config_key, "")
+            if not api_key or not api_key.strip():
+                logger.warning(f"[Vision] tools.vision.model='{user_model}' routes to "
+                               f"'{display_name}' but '{config_key}' is not configured. "
+                               f"Falling back to auto-discovery.")
+                return None  # fall through to auto
+            try:
+                from models.bot_factory import create_bot
+                bot = create_bot(bot_type)
+                if not hasattr(bot, 'call_vision'):
+                    logger.warning(f"[Vision] '{display_name}' bot does not implement call_vision.")
+                    return None
+            except Exception as e:
+                logger.warning(f"[Vision] Failed to create '{display_name}' bot: {e}")
+                return None
+
+            return [VisionProvider(
+                name=display_name,
+                api_key="",
+                api_base="",
+                model_override=user_model,
+                use_bot=True,
+                fallback_bot=bot,
+            )]
+
+        return None
+
+    def _append_other_model_providers(self, providers: List[VisionProvider],
+                                       preferred_model: Optional[str] = None) -> None:
+        """
+        Auto-discover other models whose API key is configured.
+        Skip the main model's own bot_type (already covered by MainModel
+        provider), unless the main model itself does not support vision —
+        in that case we still want the vendor's dedicated vision model
+        as a fallback. Also skip bot_types that already appear in the
+        provider list.
+
+        If preferred_model matches a provider's family, use it instead
+        of that provider's hard-coded default model.
+        """
+        main_bot_type = None
+        main_bot_supports_vision = False
+        if self.model and hasattr(self.model, '_resolve_bot_type'):
+            main_bot_type = self.model._resolve_bot_type(conf().get("model", ""))
+            main_bot = getattr(self.model, "bot", None)
+            main_bot_supports_vision = self._main_bot_supports_vision(main_bot)
+
+        existing_names = {p.name for p in providers}
+        preferred_provider = self._infer_provider_from_model(preferred_model) if preferred_model else None
+
+        for config_key, bot_type, default_model, display_name in _DISCOVERABLE_MODELS:
+            if display_name in existing_names:
+                continue
+            # Same bot_type as the main model is normally handled by the
+            # MainModel provider; only skip it here if the main model
+            # actually supports vision. Otherwise fall through and add
+            # the vendor's dedicated vision model as a fallback.
+            if bot_type == main_bot_type and main_bot_supports_vision:
+                continue
+            api_key = conf().get(config_key, "")
+            if not api_key or not api_key.strip():
+                continue
+
+            try:
+                from models.bot_factory import create_bot
+                bot = create_bot(bot_type)
+                if not hasattr(bot, 'call_vision'):
+                    continue
+            except Exception:
+                continue
+
+            model_for_provider = (preferred_model
+                                  if preferred_provider == display_name and preferred_model
+                                  else default_model)
+
+            provider = VisionProvider(
+                name=display_name,
+                api_key="",
+                api_base="",
+                model_override=model_for_provider,
+                use_bot=True,
+                fallback_bot=bot,
+            )
+
+            # Same vendor as the main bot is the most natural fallback when
+            # the main model itself does not support vision — promote it to
+            # the front of the list instead of relying on declaration order.
+            if bot_type == main_bot_type:
+                providers.insert(0, provider)
+            else:
+                providers.append(provider)
+
+    def _main_bot_supports_vision(self, bot) -> bool:
+        """
+        Whether the main bot is known to natively support vision.
+
+        Having a `call_vision` method is necessary but not sufficient —
+        some bots implement the method against an endpoint that does not
+        actually serve vision models, which causes silent failures when a
+        vendor-foreign model name is forwarded.
+
+        Resolution order:
+          1. If the bot explicitly declares `supports_vision`, trust it.
+             This lets bots opt in or out based on their own runtime
+             configuration (e.g. the currently selected model).
+          2. Otherwise, fall back to a model-name prefix heuristic: trust
+             call_vision when the main model looks like an OpenAI family
+             model or matches a known multimodal vendor prefix.
+        """
+        if bot is None:
+            return False
+        if hasattr(bot, "supports_vision"):
+            return bool(getattr(bot, "supports_vision"))
+        main_model = (conf().get("model") or "").lower()
+        if not main_model:
+            return False
+        if main_model.startswith(_OPENAI_MODEL_PREFIXES):
+            return True
+        return self._infer_provider_from_model(main_model) is not None
+
+    def _build_main_model_provider(self) -> Optional[VisionProvider]:
+        """
+        Use the vendor's own model for vision via bot.call_vision.
+        Gated by _main_bot_supports_vision so non-vision bots (DeepSeek, etc.)
+        do not get routed vendor-foreign model names.
+        """
+        if not (self.model and hasattr(self.model, 'bot')):
+            return None
+        try:
+            bot = self.model.bot
+        except Exception:
+            return None
+        if not hasattr(bot, 'call_vision'):
+            return None
+        if not self._main_bot_supports_vision(bot):
+            return None
+
+        # Use the configured main model name; do NOT inject tools.vision.model
+        # here, because by the time we reach this branch the tools.vision.model
+        # routing has already been attempted (and either matched the main bot
+        # or failed to find a provider).
+        main_model_name = conf().get("model") or None
+
+        return VisionProvider(
+            name=_MAIN_MODEL_PROVIDER_NAME,
+            api_key="",
+            api_base="",
+            model_override=main_model_name,
+            use_bot=True,
+        )
+
+    def _build_openai_provider(self, preferred_model: Optional[str] = None) -> Optional[VisionProvider]:
+        api_key = conf().get("open_ai_api_key") or os.environ.get("OPENAI_API_KEY")
+        if not api_key:
+            return None
+        api_base = (conf().get("open_ai_api_base") or os.environ.get("OPENAI_API_BASE", "")).rstrip("/") \
+            or "https://api.openai.com/v1"
+        # Only honor preferred_model when it looks like an OpenAI-family name;
+        # otherwise the OpenAI endpoint would 400 on a vendor-specific name.
+        model_override = preferred_model if (
+            preferred_model and preferred_model.lower().startswith(_OPENAI_MODEL_PREFIXES)
+        ) else None
+        return VisionProvider(
+            name="OpenAI",
+            api_key=api_key,
+            api_base=self._ensure_v1(api_base),
+            model_override=model_override,
+        )
+
+    def _build_linkai_provider(self, preferred_model: Optional[str] = None) -> Optional[VisionProvider]:
+        api_key = conf().get("linkai_api_key") or os.environ.get("LINKAI_API_KEY")
+        if not api_key:
+            return None
+        api_base = (conf().get("linkai_api_base") or os.environ.get("LINKAI_API_BASE", "")).rstrip("/") \
+            or "https://api.link-ai.tech"
+        from common.utils import get_cloud_headers
+        extra = get_cloud_headers(api_key)
+        extra.pop("Authorization", None)
+        extra.pop("Content-Type", None)
+        # LinkAI is a multi-vendor proxy and accepts most model names, so we
+        # honor any user-configured model name here.
+        return VisionProvider(
+            name="LinkAI",
+            api_key=api_key,
+            api_base=self._ensure_v1(api_base),
+            extra_headers=extra,
+            model_override=preferred_model,
+        )
+
+    def _build_custom_provider(self, provider_id: str, preferred_model: Optional[str] = None) -> Optional[VisionProvider]:
+        """Build a VisionProvider from a custom:<id> entry in custom_providers.
+        Uses the standard OpenAI /chat/completions endpoint — any
+        OpenAI-compatible multimodal endpoint works."""
+        from models.custom_provider import parse_custom_bot_type, get_custom_providers, _find_provider_by_id
+        _, custom_id = parse_custom_bot_type(provider_id)
+        if not custom_id:
+            return None
+        entry = _find_provider_by_id(get_custom_providers(), custom_id)
+        if not entry:
+            logger.warning(f"[Vision] custom provider '{provider_id}' not found in custom_providers")
+            return None
+        api_key = (entry.get("api_key") or "").strip()
+        api_base = (entry.get("api_base") or "").strip()
+        if not api_key or not api_base:
+            logger.warning(f"[Vision] custom provider '{provider_id}' missing api_key or api_base")
+            return None
+        model = preferred_model or entry.get("model") or ""
+        if not model:
+            logger.warning(f"[Vision] custom provider '{provider_id}' has no model configured")
+            return None
+        return VisionProvider(
+            name=entry.get("name") or provider_id,
+            api_key=api_key,
+            api_base=self._ensure_v1(api_base.rstrip("/")),
+            model_override=model,
+        )
+
+    def _call_via_bot(self, model: str, question: str, image_content: dict,
+                      provider: Optional[VisionProvider] = None) -> ToolResult:
+        """
+        Call a model's call_vision with vendor-native API format.
+        Uses the provider's _fallback_bot if set, otherwise the main model bot.
+        Raises VisionAPIError on failure so fallback can proceed.
+        """
+        try:
+            bot = (provider and provider.fallback_bot) or self.model.bot
+        except Exception as e:
+            raise VisionAPIError(f"Cannot access bot: {e}")
+
+        # Extract the raw image URL from the OpenAI-format image_content block
+        image_url = image_content.get("image_url", {}).get("url", "")
+        if not image_url:
+            raise VisionAPIError("No image URL in content block")
+
+        try:
+            response = bot.call_vision(
+                image_url=image_url,
+                question=question,
+                model=model,
+                max_tokens=MAX_TOKENS,
+            )
+        except Exception as e:
+            raise VisionAPIError(f"call_vision failed: {e}")
+
+        if response is NotImplemented:
+            raise VisionAPIError("Bot does not support vision")
+
+        if isinstance(response, dict) and response.get("error"):
+            raise VisionAPIError(f"API error - {response.get('message', 'Unknown')}")
+
+        content = response.get("content", "") if isinstance(response, dict) else ""
+        if not content:
+            raise VisionAPIError("Empty response from main model")
+
+        usage_info = response.get("usage", {}) if isinstance(response, dict) else {}
+
+        # Use the actual model name from the bot response if available
+        actual_model = response.get("model", model) if isinstance(response, dict) else model
+        provider_name = provider.name if provider else _MAIN_MODEL_PROVIDER_NAME
+        return ToolResult.success({
+            "model": actual_model,
+            "provider": provider_name,
+            "content": content,
+            "usage": usage_info,
+        })
+
+    @staticmethod
+    def _ensure_v1(api_base: str) -> str:
+        """Append /v1 if the base URL doesn't already end with a versioned path."""
+        if not api_base:
+            return api_base
+        # Already has /v1 or similar version suffix
+        if api_base.rstrip("/").split("/")[-1].startswith("v"):
+            return api_base
+        return api_base.rstrip("/") + "/v1"
+
+    @staticmethod
+    def _validate_url_safe(url: str) -> None:
+        """Reject URLs that target private/loopback/link-local addresses (SSRF guard).
+
+        Resolves the hostname to its IP address(es) and blocks any that fall
+        into non-public ranges.  Also rejects URLs with no host, non-HTTP(S)
+        schemes, or hosts that fail DNS resolution.
+
+        Delegates to the shared ``agent.tools.utils.url_safety`` helper so the
+        same guard protects every tool that fetches model-supplied URLs.
+
+        Raises:
+            ValueError: if the URL targets a disallowed address.
+        """
+        validate_url_safe(url)
+
+    def _build_image_content(self, image: str) -> dict:
+        """
+        Build the image_url content block.
+        Both remote URLs and local files are converted to base64 data URLs
+        so every bot backend can consume them without extra downloads.
+        """
+        if image.startswith(("http://", "https://")):
+            self._validate_url_safe(image)
+            return self._download_to_data_url(image)
+
+        if not os.path.isfile(image):
+            raise FileNotFoundError(f"Image file not found: {image}")
+
+        ext = image.rsplit(".", 1)[-1].lower() if "." in image else ""
+        mime_type = SUPPORTED_EXTENSIONS.get(ext)
+        if not mime_type:
+            raise ValueError(
+                f"Unsupported image format '.{ext}'. "
+                f"Supported: {', '.join(SUPPORTED_EXTENSIONS.keys())}"
+            )
+
+        file_path = self._maybe_compress(image)
+        try:
+            with open(file_path, "rb") as f:
+                b64 = base64.b64encode(f.read()).decode("ascii")
+        finally:
+            if file_path != image and os.path.exists(file_path):
+                os.remove(file_path)
+
+        data_url = f"data:{mime_type};base64,{b64}"
+        return {"type": "image_url", "image_url": {"url": data_url}}
+
+    @staticmethod
+    def _download_to_data_url(url: str) -> dict:
+        """Download a remote image and return it as a base64 data URL."""
+        resp = requests.get(url, timeout=30)
+        if resp.status_code != 200:
+            raise VisionAPIError(f"Failed to download image: HTTP {resp.status_code}")
+        content_type = resp.headers.get("Content-Type", "image/jpeg").split(";")[0].strip()
+        if not content_type.startswith("image/"):
+            content_type = "image/jpeg"
+        b64 = base64.b64encode(resp.content).decode("ascii")
+        data_url = f"data:{content_type};base64,{b64}"
+        return {"type": "image_url", "image_url": {"url": data_url}}
+
+    @staticmethod
+    def _maybe_compress(path: str) -> str:
+        """Compress image to under COMPRESS_THRESHOLD with max long-edge 1536px."""
+        file_size = os.path.getsize(path)
+        if file_size <= COMPRESS_THRESHOLD:
+            return path
+
+        tmp = tempfile.NamedTemporaryFile(suffix=".jpg", delete=False)
+        tmp.close()
+
+        def _try_sips(max_dim: str, quality: str) -> bool:
+            try:
+                subprocess.run(
+                    ["sips", "-Z", max_dim, "-s", "formatOptions", quality,
+                     path, "--out", tmp.name],
+                    capture_output=True, check=True,
+                )
+                return True
+            except (FileNotFoundError, subprocess.CalledProcessError):
+                return False
+
+        def _try_convert(max_dim: str, quality: str) -> bool:
+            try:
+                subprocess.run(
+                    ["convert", path, "-resize", f"{max_dim}x{max_dim}>",
+                     "-quality", quality, tmp.name],
+                    capture_output=True, check=True,
+                )
+                return True
+            except (FileNotFoundError, subprocess.CalledProcessError):
+                return False
+
+        attempts = [
+            ("1536", "85"),
+            ("1536", "70"),
+            ("1536", "50"),
+        ]
+
+        for max_dim, quality in attempts:
+            ok = _try_sips(max_dim, quality) or _try_convert(max_dim, quality)
+            if not ok:
+                continue
+            new_size = os.path.getsize(tmp.name)
+            logger.debug(f"[Vision] Compressed image "
+                         f"({file_size // 1024}KB -> {new_size // 1024}KB, "
+                         f"max_dim={max_dim}, q={quality})")
+            if new_size <= COMPRESS_THRESHOLD:
+                return tmp.name
+
+        if os.path.exists(tmp.name) and os.path.getsize(tmp.name) > 0:
+            return tmp.name
+
+        os.remove(tmp.name)
+        return path
+
+    def _call_api(self, provider: VisionProvider, model: str,
+                  question: str, image_content: dict) -> ToolResult:
+        """
+        Call a single provider's Vision API.
+        Raises VisionAPIError on recoverable failures so the caller can try
+        the next provider.
+        """
+        payload = {
+            "model": model,
+            "messages": [
+                {
+                    "role": "user",
+                    "content": [
+                        {"type": "text", "text": question},
+                        image_content,
+                    ],
+                }
+            ],
+        }
+
+        headers = {
+            "Authorization": f"Bearer {provider.api_key}",
+            "Content-Type": "application/json",
+            **provider.extra_headers,
+        }
+
+        resp = requests.post(
+            f"{provider.api_base}/chat/completions",
+            headers=headers,
+            json=payload,
+            timeout=DEFAULT_TIMEOUT,
+        )
+
+        if resp.status_code != 200:
+            raise VisionAPIError(f"HTTP {resp.status_code}: {resp.text[:200]}")
+
+        data = resp.json()
+
+        if "error" in data:
+            msg = data["error"].get("message", "Unknown API error")
+            raise VisionAPIError(f"API error - {msg}")
+
+        content = ""
+        choices = data.get("choices", [])
+        if choices:
+            content = choices[0].get("message", {}).get("content", "")
+
+        usage = data.get("usage", {})
+        result = {
+            "model": model,
+            "provider": provider.name,
+            "content": content,
+            "usage": {
+                "prompt_tokens": usage.get("prompt_tokens", 0),
+                "completion_tokens": usage.get("completion_tokens", 0),
+                "total_tokens": usage.get("total_tokens", 0),
+            },
+        }
+        return ToolResult.success(result)

agent/tools/web_fetch/web_fetch.py

@@ -0,0 +1,489 @@
+"""
+Web Fetch tool - Fetch and extract readable content from web pages and remote files.
+
+Supports:
+- HTML web pages: extracts readable text content
+- Document files (PDF, Word, TXT, Markdown, etc.): downloads to workspace/tmp and parses content
+"""
+
+import os
+import re
+import uuid
+from typing import Dict, Any, Optional, Set
+from urllib.parse import urlparse, unquote
+
+import requests
+
+from agent.tools.base_tool import BaseTool, ToolResult
+from agent.tools.utils.truncate import truncate_head, format_size
+from agent.tools.utils.url_safety import validate_url_safe
+from common.log import logger
+
+
+DEFAULT_TIMEOUT = 30
+MAX_FILE_SIZE = 50 * 1024 * 1024  # 50MB
+# Cap on how many redirects we follow; each hop's target is re-validated
+# against the SSRF guard so a public URL cannot bounce us into an internal one.
+MAX_REDIRECTS = 10
+
+DEFAULT_HEADERS = {
+    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36",
+    "Accept": "*/*",
+}
+
+# Supported document file extensions
+PDF_SUFFIXES: Set[str] = {".pdf"}
+WORD_SUFFIXES: Set[str] = {".docx"}
+TEXT_SUFFIXES: Set[str] = {".txt", ".md", ".markdown", ".rst", ".csv", ".tsv", ".log"}
+SPREADSHEET_SUFFIXES: Set[str] = {".xls", ".xlsx"}
+PPT_SUFFIXES: Set[str] = {".ppt", ".pptx"}
+
+ALL_DOC_SUFFIXES = PDF_SUFFIXES | WORD_SUFFIXES | TEXT_SUFFIXES | SPREADSHEET_SUFFIXES | PPT_SUFFIXES
+
+_CHARSET_RE = re.compile(r'charset\s*=\s*["\']?\s*([\w\-]+)', re.IGNORECASE)
+_META_CHARSET_RE = re.compile(rb'<meta[^>]+charset\s*=\s*["\']?\s*([\w\-]+)', re.IGNORECASE)
+_META_HTTP_EQUIV_RE = re.compile(
+    rb'<meta[^>]+http-equiv\s*=\s*["\']?Content-Type["\']?[^>]+content\s*=\s*["\'][^"\']*charset=([\w\-]+)',
+    re.IGNORECASE,
+)
+
+
+def _extract_charset_from_content_type(content_type: str) -> Optional[str]:
+    """Extract charset from Content-Type header value."""
+    m = _CHARSET_RE.search(content_type)
+    return m.group(1) if m else None
+
+
+def _extract_charset_from_html_meta(raw_bytes: bytes) -> Optional[str]:
+    """Extract charset from HTML <meta> tags in the first few KB of raw bytes."""
+    m = _META_CHARSET_RE.search(raw_bytes)
+    if m:
+        return m.group(1).decode("ascii", errors="ignore")
+    m = _META_HTTP_EQUIV_RE.search(raw_bytes)
+    if m:
+        return m.group(1).decode("ascii", errors="ignore")
+    return None
+
+
+def _get_url_suffix(url: str) -> str:
+    """Extract file extension from URL path, ignoring query params."""
+    path = urlparse(url).path
+    return os.path.splitext(path)[-1].lower()
+
+
+def _is_document_url(url: str) -> bool:
+    """Check if URL points to a downloadable document file."""
+    suffix = _get_url_suffix(url)
+    return suffix in ALL_DOC_SUFFIXES
+
+
+class WebFetch(BaseTool):
+    """Tool for fetching web pages and remote document files"""
+
+    name: str = "web_fetch"
+    description: str = (
+        "Fetch content from a http/https URL. For web pages, extracts readable text. "
+        "For document files (PDF, Word, TXT, Markdown, Excel, PPT), downloads and parses the file content. "
+        "Supported file types: .pdf, .docx, .txt, .md, .csv, .xls, .xlsx, .ppt, .pptx"
+    )
+
+    params: dict = {
+        "type": "object",
+        "properties": {
+            "url": {
+                "type": "string",
+                "description": "The HTTP/HTTPS URL to fetch (web page or document file link)"
+            }
+        },
+        "required": ["url"]
+    }
+
+    def __init__(self, config: dict = None):
+        self.config = config or {}
+        self.cwd = self.config.get("cwd", os.getcwd())
+
+    def execute(self, args: Dict[str, Any]) -> ToolResult:
+        url = args.get("url", "").strip()
+        if not url:
+            return ToolResult.fail("Error: 'url' parameter is required")
+
+        parsed = urlparse(url)
+        if parsed.scheme not in ("http", "https"):
+            return ToolResult.fail("Error: Invalid URL (must start with http:// or https://)")
+
+        # SSRF guard: reject URLs that resolve to private/loopback/link-local/
+        # cloud-metadata addresses before any request is issued.
+        try:
+            validate_url_safe(url)
+        except ValueError as e:
+            return ToolResult.fail(f"Error: {e}")
+
+        if _is_document_url(url):
+            return self._fetch_document(url)
+
+        return self._fetch_webpage(url)
+
+    # ---- Safe request helper ----
+
+    @staticmethod
+    def _safe_get(url: str, **kwargs) -> requests.Response:
+        """Issue a GET request while re-validating every redirect hop (SSRF guard).
+
+        Auto-redirect is disabled and each hop is followed manually so the
+        target of every redirect is re-resolved and checked against the SSRF
+        guard. This prevents a public URL from 3xx-bouncing into a private,
+        loopback, link-local or cloud-metadata address. ``kwargs`` are passed
+        through to ``requests.get`` (e.g. ``stream``).
+
+        Raises:
+            ValueError: if any hop resolves to a non-public address.
+        """
+        kwargs.pop("allow_redirects", None)
+        current = url
+        for _ in range(MAX_REDIRECTS + 1):
+            response = requests.get(
+                current,
+                headers=DEFAULT_HEADERS,
+                timeout=DEFAULT_TIMEOUT,
+                allow_redirects=False,
+                **kwargs,
+            )
+            if not response.is_redirect and not response.is_permanent_redirect:
+                return response
+
+            location = response.headers.get("Location")
+            if not location:
+                return response
+
+            # Resolve the redirect target relative to the current URL, then
+            # re-validate it before following.
+            current = requests.compat.urljoin(current, location)
+            validate_url_safe(current)
+            response.close()
+
+        raise ValueError(f"Too many redirects (>{MAX_REDIRECTS})")
+
+    # ---- Web page fetching ----
+
+    def _fetch_webpage(self, url: str) -> ToolResult:
+        """Fetch and extract readable text from an HTML web page."""
+        parsed = urlparse(url)
+        try:
+            response = self._safe_get(url)
+            response.raise_for_status()
+        except requests.Timeout:
+            return ToolResult.fail(f"Error: Request timed out after {DEFAULT_TIMEOUT}s")
+        except requests.ConnectionError:
+            return ToolResult.fail(f"Error: Failed to connect to {parsed.netloc}")
+        except requests.HTTPError as e:
+            return ToolResult.fail(f"Error: HTTP {e.response.status_code} for URL: {url}")
+        except ValueError as e:
+            return ToolResult.fail(f"Error: {e}")
+        except Exception as e:
+            return ToolResult.fail(f"Error: Failed to fetch URL: {e}")
+
+        content_type = response.headers.get("Content-Type", "")
+        if self._is_binary_content_type(content_type) and not _is_document_url(url):
+            return self._handle_download_by_content_type(url, response, content_type)
+
+        response.encoding = self._detect_encoding(response)
+        html = response.text
+        title = self._extract_title(html)
+        text = self._extract_text(html)
+
+        return ToolResult.success(f"Title: {title}\n\nContent:\n{text}")
+
+    # ---- Document fetching ----
+
+    def _fetch_document(self, url: str) -> ToolResult:
+        """Download a document file and extract its text content."""
+        suffix = _get_url_suffix(url)
+        parsed = urlparse(url)
+        filename = self._extract_filename(url)
+        tmp_dir = self._ensure_tmp_dir()
+
+        local_path = os.path.join(tmp_dir, filename)
+        logger.info(f"[WebFetch] Downloading document: {url} -> {local_path}")
+
+        try:
+            response = self._safe_get(url, stream=True)
+            response.raise_for_status()
+
+            content_length = int(response.headers.get("Content-Length", 0))
+            if content_length > MAX_FILE_SIZE:
+                return ToolResult.fail(
+                    f"Error: File too large ({format_size(content_length)} > {format_size(MAX_FILE_SIZE)})"
+                )
+
+            downloaded = 0
+            with open(local_path, "wb") as f:
+                for chunk in response.iter_content(chunk_size=8192):
+                    downloaded += len(chunk)
+                    if downloaded > MAX_FILE_SIZE:
+                        f.close()
+                        os.remove(local_path)
+                        return ToolResult.fail(
+                            f"Error: File too large (>{format_size(MAX_FILE_SIZE)}), download aborted"
+                        )
+                    f.write(chunk)
+
+        except requests.Timeout:
+            return ToolResult.fail(f"Error: Download timed out after {DEFAULT_TIMEOUT}s")
+        except requests.ConnectionError:
+            return ToolResult.fail(f"Error: Failed to connect to {parsed.netloc}")
+        except requests.HTTPError as e:
+            return ToolResult.fail(f"Error: HTTP {e.response.status_code} for URL: {url}")
+        except ValueError as e:
+            self._cleanup_file(local_path)
+            return ToolResult.fail(f"Error: {e}")
+        except Exception as e:
+            self._cleanup_file(local_path)
+            return ToolResult.fail(f"Error: Failed to download file: {e}")
+
+        try:
+            text = self._parse_document(local_path, suffix)
+        except Exception as e:
+            self._cleanup_file(local_path)
+            return ToolResult.fail(f"Error: Failed to parse document: {e}")
+
+        if not text or not text.strip():
+            file_size = os.path.getsize(local_path)
+            return ToolResult.success(
+                f"File downloaded to: {local_path} ({format_size(file_size)})\n"
+                f"No text content could be extracted. The file may contain only images or be encrypted."
+            )
+
+        truncation = truncate_head(text)
+        result_text = truncation.content
+
+        file_size = os.path.getsize(local_path)
+        header = f"[Document: {filename} | Size: {format_size(file_size)} | Saved to: {local_path}]\n\n"
+
+        if truncation.truncated:
+            header += f"[Content truncated: showing {truncation.output_lines} of {truncation.total_lines} lines]\n\n"
+
+        return ToolResult.success(header + result_text)
+
+    def _parse_document(self, file_path: str, suffix: str) -> str:
+        """Parse document file and return extracted text."""
+        if suffix in PDF_SUFFIXES:
+            return self._parse_pdf(file_path)
+        elif suffix in WORD_SUFFIXES:
+            return self._parse_word(file_path)
+        elif suffix in TEXT_SUFFIXES:
+            return self._parse_text(file_path)
+        elif suffix in SPREADSHEET_SUFFIXES:
+            return self._parse_spreadsheet(file_path)
+        elif suffix in PPT_SUFFIXES:
+            return self._parse_ppt(file_path)
+        else:
+            return self._parse_text(file_path)
+
+    def _parse_pdf(self, file_path: str) -> str:
+        """Extract text from PDF using pypdf."""
+        try:
+            from pypdf import PdfReader
+        except ImportError:
+            raise ImportError("pypdf library is required for PDF parsing. Install with: pip install pypdf")
+
+        reader = PdfReader(file_path)
+        text_parts = []
+        for page_num, page in enumerate(reader.pages, 1):
+            page_text = page.extract_text()
+            if page_text and page_text.strip():
+                text_parts.append(f"--- Page {page_num}/{len(reader.pages)} ---\n{page_text}")
+
+        return "\n\n".join(text_parts)
+
+    def _parse_word(self, file_path: str) -> str:
+        """Extract text from Word documents (.docx)."""
+        try:
+            from docx import Document
+        except ImportError:
+            raise ImportError(
+                "python-docx library is required for .docx parsing. Install with: pip install python-docx"
+            )
+        doc = Document(file_path)
+        paragraphs = [p.text for p in doc.paragraphs if p.text.strip()]
+        return "\n\n".join(paragraphs)
+
+    def _parse_text(self, file_path: str) -> str:
+        """Read plain text files (txt, md, csv, etc.)."""
+        encodings = ["utf-8", "utf-8-sig", "gbk", "gb2312", "latin-1"]
+        for enc in encodings:
+            try:
+                with open(file_path, "r", encoding=enc) as f:
+                    return f.read()
+            except (UnicodeDecodeError, UnicodeError):
+                continue
+        raise ValueError(f"Unable to decode file with any supported encoding: {encodings}")
+
+    def _parse_spreadsheet(self, file_path: str) -> str:
+        """Extract text from Excel files (.xls/.xlsx)."""
+        try:
+            import openpyxl
+        except ImportError:
+            raise ImportError(
+                "openpyxl library is required for .xlsx parsing. Install with: pip install openpyxl"
+            )
+
+        wb = openpyxl.load_workbook(file_path, read_only=True, data_only=True)
+        result_parts = []
+
+        for sheet_name in wb.sheetnames:
+            ws = wb[sheet_name]
+            rows = []
+            for row in ws.iter_rows(values_only=True):
+                cells = [str(c) if c is not None else "" for c in row]
+                if any(cells):
+                    rows.append(" | ".join(cells))
+            if rows:
+                result_parts.append(f"--- Sheet: {sheet_name} ---\n" + "\n".join(rows))
+
+        wb.close()
+        return "\n\n".join(result_parts)
+
+    def _parse_ppt(self, file_path: str) -> str:
+        """Extract text from PowerPoint files (.ppt/.pptx)."""
+        try:
+            from pptx import Presentation
+        except ImportError:
+            raise ImportError(
+                "python-pptx library is required for .pptx parsing. Install with: pip install python-pptx"
+            )
+
+        prs = Presentation(file_path)
+        text_parts = []
+
+        for slide_num, slide in enumerate(prs.slides, 1):
+            slide_texts = []
+            for shape in slide.shapes:
+                if shape.has_text_frame:
+                    for paragraph in shape.text_frame.paragraphs:
+                        text = paragraph.text.strip()
+                        if text:
+                            slide_texts.append(text)
+            if slide_texts:
+                text_parts.append(f"--- Slide {slide_num}/{len(prs.slides)} ---\n" + "\n".join(slide_texts))
+
+        return "\n\n".join(text_parts)
+
+    # ---- Encoding detection ----
+
+    @staticmethod
+    def _detect_encoding(response: requests.Response) -> str:
+        """Detect response encoding with priority: Content-Type header > HTML meta > chardet > utf-8."""
+        # 1. Check Content-Type header for explicit charset
+        content_type = response.headers.get("Content-Type", "")
+        charset = _extract_charset_from_content_type(content_type)
+        if charset:
+            return charset
+
+        # 2. Scan raw bytes for HTML meta charset declaration
+        raw = response.content[:4096]
+        charset = _extract_charset_from_html_meta(raw)
+        if charset:
+            return charset
+
+        # 3. Use apparent_encoding (chardet-based detection) if confident enough
+        apparent = response.apparent_encoding
+        if apparent:
+            apparent_lower = apparent.lower()
+            # Trust CJK / Windows encodings detected by chardet
+            trusted_prefixes = ("utf", "gb", "big5", "euc", "shift_jis", "iso-2022", "windows", "ascii")
+            if any(apparent_lower.startswith(p) for p in trusted_prefixes):
+                return apparent
+
+        # 4. Fallback
+        return "utf-8"
+
+    # ---- Helper methods ----
+
+    def _ensure_tmp_dir(self) -> str:
+        """Ensure workspace/tmp directory exists and return its path."""
+        tmp_dir = os.path.join(self.cwd, "tmp")
+        os.makedirs(tmp_dir, exist_ok=True)
+        return tmp_dir
+
+    def _extract_filename(self, url: str) -> str:
+        """Extract a safe filename from URL, with a short UUID prefix to avoid collisions."""
+        path = urlparse(url).path
+        basename = os.path.basename(unquote(path))
+        if not basename or basename == "/":
+            basename = "downloaded_file"
+        # Sanitize: keep only safe chars
+        basename = re.sub(r'[^\w.\-]', '_', basename)
+        short_id = uuid.uuid4().hex[:8]
+        return f"{short_id}_{basename}"
+
+    @staticmethod
+    def _cleanup_file(path: str):
+        """Remove a file if it exists, ignoring errors."""
+        try:
+            if os.path.exists(path):
+                os.remove(path)
+        except Exception:
+            pass
+
+    @staticmethod
+    def _is_binary_content_type(content_type: str) -> bool:
+        """Check if Content-Type indicates a binary/document response."""
+        binary_types = [
+            "application/pdf",
+            "application/vnd.openxmlformats",
+            "application/vnd.ms-excel",
+            "application/vnd.ms-powerpoint",
+            "application/octet-stream",
+        ]
+        ct_lower = content_type.lower()
+        return any(bt in ct_lower for bt in binary_types)
+
+    def _handle_download_by_content_type(self, url: str, response: requests.Response, content_type: str) -> ToolResult:
+        """Handle a URL that returned binary content instead of HTML."""
+        ct_lower = content_type.lower()
+        suffix_map = {
+            "application/pdf": ".pdf",
+            "application/vnd.openxmlformats-officedocument.wordprocessingml": ".docx",
+            "application/vnd.ms-excel": ".xls",
+            "application/vnd.openxmlformats-officedocument.spreadsheetml": ".xlsx",
+            "application/vnd.ms-powerpoint": ".ppt",
+            "application/vnd.openxmlformats-officedocument.presentationml": ".pptx",
+        }
+        detected_suffix = None
+        for ct_prefix, ext in suffix_map.items():
+            if ct_prefix in ct_lower:
+                detected_suffix = ext
+                break
+
+        if detected_suffix and detected_suffix in ALL_DOC_SUFFIXES:
+            # Re-fetch as document
+            return self._fetch_document(url if _get_url_suffix(url) in ALL_DOC_SUFFIXES
+                                        else self._rewrite_url_with_suffix(url, detected_suffix))
+        return ToolResult.fail(f"Error: URL returned binary content ({content_type}), not a supported document type")
+
+    @staticmethod
+    def _rewrite_url_with_suffix(url: str, suffix: str) -> str:
+        """Append a suffix to the URL path so _get_url_suffix works correctly."""
+        parsed = urlparse(url)
+        new_path = parsed.path.rstrip("/") + suffix
+        return parsed._replace(path=new_path).geturl()
+
+    # ---- HTML extraction (unchanged) ----
+
+    @staticmethod
+    def _extract_title(html: str) -> str:
+        match = re.search(r"<title[^>]*>(.*?)</title>", html, re.IGNORECASE | re.DOTALL)
+        return match.group(1).strip() if match else "Untitled"
+
+    @staticmethod
+    def _extract_text(html: str) -> str:
+        text = re.sub(r"<script[^>]*>.*?</script>", "", html, flags=re.IGNORECASE | re.DOTALL)
+        text = re.sub(r"<style[^>]*>.*?</style>", "", text, flags=re.IGNORECASE | re.DOTALL)
+        text = re.sub(r"<[^>]+>", "", text)
+        text = text.replace("&amp;", "&").replace("&lt;", "<").replace("&gt;", ">")
+        text = text.replace("&quot;", '"').replace("&#39;", "'").replace("&nbsp;", " ")
+        text = re.sub(r"[^\S\n]+", " ", text)
+        text = re.sub(r"\n{3,}", "\n\n", text)
+        lines = [line.strip() for line in text.splitlines()]
+        text = "\n".join(lines)
+        return text.strip()

agent/tools/web_search/web_search.py

@@ -1,33 +1,95 @@
-"""
+"""Web Search tool. Supports four backends with a unified response format:
-Web Search tool - Search the web using Bocha or LinkAI search API.
+  - bocha   (https://open.bochaai.com)
-Supports two backends with unified response format:
+  - zhipu   (https://docs.bigmodel.cn/cn/guide/tools/web-search)
-  1. Bocha Search (primary, requires BOCHA_API_KEY)
+  - qianfan (https://cloud.baidu.com/doc/qianfan/s/2mh4su4uy)
-  2. LinkAI Search (fallback, requires LINKAI_API_KEY)
+  - linkai  (https://link-ai.tech, fallback)
+
+Provider selection
+  - strategy 'auto' (default): pick the first configured provider in the
+    canonical order [bocha, zhipu, qianfan, linkai]. When the caller passes
+    an explicit `provider` it overrides the pick; an invalid/unconfigured
+    one silently falls back to the auto order.
+  - strategy 'fixed': use the configured provider; if its credential is
+    missing at call time, silently fall back to auto order (no card hint).
+
+Credentials
+  - bocha   : tools.web_search.bocha_api_key  ->  env BOCHA_API_KEY
+  - zhipu   : conf.zhipu_ai_api_key            ->  env ZHIPUAI_API_KEY
+  - qianfan : conf.qianfan_api_key             ->  env QIANFAN_API_KEY
+  - linkai  : conf.linkai_api_key              ->  env LINKAI_API_KEY
 """
 
-import os
 import json
-from typing import Dict, Any, Optional
+import os
+from typing import Any, Dict, List, Optional
 
 import requests
 
 from agent.tools.base_tool import BaseTool, ToolResult
 from common.log import logger
+from config import conf
 
 
-# Default timeout for API requests (seconds)
 DEFAULT_TIMEOUT = 30
 
+# Canonical fallback order. Empirically ordered by Chinese real-time
+# quality + relevance: bocha (best overall), qianfan (best for hot news),
+# zhipu (strong on long-form articles), linkai (cloud aggregator, last
+# resort).
+PROVIDER_ORDER = ("bocha", "qianfan", "zhipu", "linkai")
+
+PROVIDER_LABELS = {
+    "bocha":   "Bocha",
+    "zhipu":   "Zhipu",
+    "qianfan": "Baidu Qianfan",
+    "linkai":  "LinkAI",
+}
+
+
+def _tools_web_search_conf() -> dict:
+    """Return the tools.web_search config block (dict-like)."""
+    tools_cfg = conf().get("tools") or {}
+    if not isinstance(tools_cfg, dict):
+        return {}
+    block = tools_cfg.get("web_search") or {}
+    return block if isinstance(block, dict) else {}
+
+
+def _get_api_key(provider: str) -> str:
+    """Resolve API key for a provider, with conf -> env fallback."""
+    if provider == "bocha":
+        key = (_tools_web_search_conf().get("bocha_api_key") or "").strip()
+        return key or os.environ.get("BOCHA_API_KEY", "").strip()
+    if provider == "zhipu":
+        key = (conf().get("zhipu_ai_api_key") or "").strip()
+        return key or os.environ.get("ZHIPUAI_API_KEY", "").strip()
+    if provider == "qianfan":
+        key = (conf().get("qianfan_api_key") or "").strip()
+        return key or os.environ.get("QIANFAN_API_KEY", "").strip()
+    if provider == "linkai":
+        key = (conf().get("linkai_api_key") or "").strip()
+        return key or os.environ.get("LINKAI_API_KEY", "").strip()
+    return ""
+
+
+def configured_providers() -> List[str]:
+    """Return configured providers in canonical order."""
+    return [p for p in PROVIDER_ORDER if _get_api_key(p)]
+
+
+def _configured_strategy() -> str:
+    return (_tools_web_search_conf().get("strategy") or "auto").strip().lower()
+
+
+def _configured_provider() -> str:
+    return (_tools_web_search_conf().get("provider") or "").strip().lower()
+
 
 class WebSearch(BaseTool):
-    """Tool for searching the web using Bocha or LinkAI search API"""
+    """Tool for searching the web across multiple providers."""
 
     name: str = "web_search"
-    description: str = (
+    description: str = "Search the web for real-time information. Returns titles, URLs, and snippets."
-        "Search the web for current information, news, research topics, or any real-time data. "
-        "Returns web page titles, URLs, snippets, and optional summaries. "
-        "Use this when the user asks about recent events, needs fact-checking, or wants up-to-date information."
-    )
 
     params: dict = {
         "type": "object",
@@ -58,265 +120,368 @@ class WebSearch(BaseTool):
 
     def __init__(self, config: dict = None):
         self.config = config or {}
-        self._backend = None  # Will be resolved on first execute
 
     @staticmethod
     def is_available() -> bool:
-        """Check if web search is available (at least one API key is configured)"""
+        """Tool is offered to the agent when at least one provider has a key."""
-        return bool(os.environ.get("BOCHA_API_KEY") or os.environ.get("LINKAI_API_KEY"))
+        return bool(configured_providers())
 
-    def _resolve_backend(self) -> Optional[str]:
+    @classmethod
-        """
+    def get_json_schema(cls) -> dict:
-        Determine which search backend to use.
+        """Augment the static schema with a `provider` field — only when the
-        Priority: Bocha > LinkAI
+        user has ≥2 providers configured AND strategy is 'auto'. Otherwise
+        the backend picks silently and exposing the field would only waste
+        the agent's tokens."""
+        schema = {
+            "name": cls.name,
+            "description": cls.description,
+            "parameters": json.loads(json.dumps(cls.params)),  # deep copy
+        }
+        if _configured_strategy() != "auto":
+            return schema
+        available = configured_providers()
+        if len(available) < 2:
+            return schema
 
-        :return: 'bocha', 'linkai', or None
+        schema["parameters"]["properties"]["provider"] = {
+            "type": "string",
+            "enum": available,
+            "description": "Optional. Specifies the search backend. You may switch between providers when the user wants results from a particular source or from multiple sources.",
+        }
+        return schema
+
+    # ------------------------------------------------------------------
+    # Provider resolution
+    # ------------------------------------------------------------------
+
+    def _resolve_provider(self, requested: Optional[str]) -> Optional[str]:
+        """Pick a provider for this call.
+
+        Priority: caller-supplied (if configured) > fixed strategy (if
+        configured) > first configured in PROVIDER_ORDER. Silent fallback
+        when the desired one has no key.
         """
-        if os.environ.get("BOCHA_API_KEY"):
+        available = configured_providers()
-            return "bocha"
+        if not available:
-        if os.environ.get("LINKAI_API_KEY"):
+            return None
-            return "linkai"
+
-        return None
+        if requested:
+            req = requested.strip().lower()
+            if req in available:
+                return req
+            logger.warning(f"[WebSearch] requested provider '{requested}' unavailable, falling back")
+
+        if _configured_strategy() == "fixed":
+            pinned = _configured_provider()
+            if pinned in available:
+                return pinned
+            if pinned:
+                logger.warning(f"[WebSearch] pinned provider '{pinned}' unavailable, falling back to auto")
+
+        return available[0]
+
+    @staticmethod
+    def _resolution_reason(requested: Optional[str], chosen: str) -> str:
+        """Human-readable explanation for why `chosen` won the resolver."""
+        if requested and requested.strip().lower() == chosen:
+            return "caller-requested"
+        strategy = _configured_strategy()
+        if strategy == "fixed" and _configured_provider() == chosen:
+            return "fixed-strategy"
+        return "auto-fallback"
+
+    # ------------------------------------------------------------------
+    # Entry point
+    # ------------------------------------------------------------------
 
     def execute(self, args: Dict[str, Any]) -> ToolResult:
-        """
+        query = (args.get("query") or "").strip()
-        Execute web search
-
-        :param args: Search parameters (query, count, freshness, summary)
-        :return: Search results
-        """
-        query = args.get("query", "").strip()
         if not query:
             return ToolResult.fail("Error: 'query' parameter is required")
 
         count = args.get("count", 10)
         freshness = args.get("freshness", "noLimit")
         summary = args.get("summary", False)
-
-        # Validate count
         if not isinstance(count, int) or count < 1 or count > 50:
             count = 10
 
-        # Resolve backend
+        requested = args.get("provider")
-        backend = self._resolve_backend()
+        provider = self._resolve_provider(requested)
-        if not backend:
+        if not provider:
             return ToolResult.fail(
-                "Error: No search API key configured. "
+                "Error: No search provider configured. "
-                "Please set BOCHA_API_KEY or LINKAI_API_KEY using env_config tool.\n"
+                "Configure one of BOCHA_API_KEY / zhipu_ai_api_key / qianfan_api_key / linkai_api_key."
-                "  - Bocha Search: https://open.bocha.cn\n"
-                "  - LinkAI Search: https://link-ai.tech"
             )
 
+        # Always log the routing decision so multi-provider deployments can
+        # tell at a glance which backend served any given query.
+        available = configured_providers()
+        reason = self._resolution_reason(requested, provider)
+        q_preview = query if len(query) <= 60 else (query[:57] + "...")
+        logger.info(
+            f"[WebSearch] provider={provider} reason={reason} "
+            f"available={list(available)} query={q_preview!r} count={count} freshness={freshness}"
+        )
+
         try:
-            if backend == "bocha":
+            if provider == "bocha":
                 return self._search_bocha(query, count, freshness, summary)
-            else:
+            if provider == "zhipu":
+                return self._search_zhipu(query, count, freshness)
+            if provider == "qianfan":
+                return self._search_qianfan(query, count, freshness)
+            if provider == "linkai":
                 return self._search_linkai(query, count, freshness)
+            return ToolResult.fail(f"Error: Unknown provider '{provider}'")
         except requests.Timeout:
             return ToolResult.fail(f"Error: Search request timed out after {DEFAULT_TIMEOUT}s")
         except requests.ConnectionError:
             return ToolResult.fail("Error: Failed to connect to search API")
         except Exception as e:
-            logger.error(f"[WebSearch] Unexpected error: {e}", exc_info=True)
+            logger.error(f"[WebSearch] Unexpected error ({provider}): {e}", exc_info=True)
             return ToolResult.fail(f"Error: Search failed - {str(e)}")
 
+    # ------------------------------------------------------------------
+    # Bocha
+    # ------------------------------------------------------------------
+
     def _search_bocha(self, query: str, count: int, freshness: str, summary: bool) -> ToolResult:
-        """
+        api_key = _get_api_key("bocha")
-        Search using Bocha API
+        url = "https://api.bochaai.com/v1/web-search"
-
-        :param query: Search query
-        :param count: Number of results
-        :param freshness: Time range filter
-        :param summary: Whether to include summary
-        :return: Formatted search results
-        """
-        api_key = os.environ.get("BOCHA_API_KEY", "")
-        url = "https://api.bocha.cn/v1/web-search"
-
         headers = {
             "Authorization": f"Bearer {api_key}",
             "Content-Type": "application/json",
-            "Accept": "application/json"
+            "Accept": "application/json",
         }
+        payload = {"query": query, "count": count, "freshness": freshness, "summary": summary}
 
-        payload = {
+        logger.debug(f"[WebSearch] bocha: query='{query}', count={count}")
-            "query": query,
+        resp = requests.post(url, headers=headers, json=payload, timeout=DEFAULT_TIMEOUT)
-            "count": count,
-            "freshness": freshness,
-            "summary": summary
-        }
 
-        logger.debug(f"[WebSearch] Bocha search: query='{query}', count={count}")
+        if resp.status_code == 401:
+            return ToolResult.fail("Error: Invalid bocha API key.")
+        if resp.status_code == 403:
+            return ToolResult.fail("Error: bocha API — insufficient balance. Top up at https://open.bochaai.com")
+        if resp.status_code == 429:
+            return ToolResult.fail("Error: bocha API rate limit reached.")
+        if resp.status_code != 200:
+            return ToolResult.fail(f"Error: bocha API returned HTTP {resp.status_code}")
 
-        response = requests.post(url, headers=headers, json=payload, timeout=DEFAULT_TIMEOUT)
+        data = resp.json()
-
-        if response.status_code == 401:
-            return ToolResult.fail("Error: Invalid BOCHA_API_KEY. Please check your API key.")
-        if response.status_code == 403:
-            return ToolResult.fail("Error: Bocha API - insufficient balance. Please top up at https://open.bocha.cn")
-        if response.status_code == 429:
-            return ToolResult.fail("Error: Bocha API rate limit reached. Please try again later.")
-        if response.status_code != 200:
-            return ToolResult.fail(f"Error: Bocha API returned HTTP {response.status_code}")
-
-        data = response.json()
-
-        # Check API-level error code
         api_code = data.get("code")
         if api_code is not None and api_code != 200:
             msg = data.get("msg") or "Unknown error"
-            return ToolResult.fail(f"Error: Bocha API error (code={api_code}): {msg}")
+            return ToolResult.fail(f"Error: bocha API error (code={api_code}): {msg}")
-
-        # Extract and format results
-        return self._format_bocha_results(data, query)
-
-    def _format_bocha_results(self, data: dict, query: str) -> ToolResult:
-        """
-        Format Bocha API response into unified result structure
-
-        :param data: Raw API response
-        :param query: Original query
-        :return: Formatted ToolResult
-        """
-        search_data = data.get("data", {})
-        web_pages = search_data.get("webPages", {})
-        pages = web_pages.get("value", [])
-
-        if not pages:
-            return ToolResult.success({
-                "query": query,
-                "backend": "bocha",
-                "total": 0,
-                "results": [],
-                "message": "No results found"
-            })
 
+        pages = (data.get("data") or {}).get("webPages", {}).get("value", []) or []
         results = []
-        for page in pages:
+        for p in pages:
-            result = {
+            item = {
-                "title": page.get("name", ""),
+                "title": p.get("name", ""),
-                "url": page.get("url", ""),
+                "url": p.get("url", ""),
-                "snippet": page.get("snippet", ""),
+                "snippet": p.get("snippet", ""),
-                "siteName": page.get("siteName", ""),
+                "siteName": p.get("siteName", ""),
-                "datePublished": page.get("datePublished") or page.get("dateLastCrawled", ""),
+                "datePublished": p.get("datePublished") or p.get("dateLastCrawled", ""),
             }
-            # Include summary only if present
+            if p.get("summary"):
-            if page.get("summary"):
+                item["summary"] = p["summary"]
-                result["summary"] = page["summary"]
+            results.append(item)
-            results.append(result)
+        total = (data.get("data") or {}).get("webPages", {}).get("totalEstimatedMatches", len(results))
-
-        total = web_pages.get("totalEstimatedMatches", len(results))
-
         return ToolResult.success({
-            "query": query,
+            "query": query, "backend": "bocha",
-            "backend": "bocha",
+            "total": total, "count": len(results), "results": results,
-            "total": total,
-            "count": len(results),
-            "results": results
         })
 
-    def _search_linkai(self, query: str, count: int, freshness: str) -> ToolResult:
+    # ------------------------------------------------------------------
-        """
+    # Zhipu
-        Search using LinkAI plugin API
+    # ------------------------------------------------------------------
-
-        :param query: Search query
-        :param count: Number of results
-        :param freshness: Time range filter
-        :return: Formatted search results
-        """
-        api_key = os.environ.get("LINKAI_API_KEY", "")
-        url = "https://api.link-ai.tech/v1/plugin/execute"
 
+    def _search_zhipu(self, query: str, count: int, freshness: str) -> ToolResult:
+        api_key = _get_api_key("zhipu")
+        api_base = (conf().get("zhipu_ai_api_base") or "https://open.bigmodel.cn/api/paas/v4").rstrip("/")
+        url = f"{api_base}/web_search"
         headers = {
+            "Authorization": f"Bearer {api_key}",
             "Content-Type": "application/json",
-            "Authorization": f"Bearer {api_key}"
         }
 
-        payload = {
+        # Zhipu Web Search expects `search_query` <= 70 chars; truncate
-            "code": "web-search",
+        # gracefully so a long agent-supplied query doesn't get rejected.
-            "args": {
+        trimmed_query = (query or "")[:70]
-                "query": query,
+        engine = (_tools_web_search_conf().get("zhipu_search_engine") or "search_pro").strip().lower()
-                "count": count,
+        if engine not in ("search_std", "search_pro", "search_pro_sogou", "search_pro_quark"):
-                "freshness": freshness
+            engine = "search_pro"
-            }
+
+        payload: Dict[str, Any] = {
+            "search_engine": engine,
+            "search_query": trimmed_query,
+            "search_intent": False,
+            "count": max(1, min(int(count or 10), 50)),
+            "search_recency_filter": freshness if freshness in (
+                "oneDay", "oneWeek", "oneMonth", "oneYear", "noLimit"
+            ) else "noLimit",
+        }
+        content_size = (_tools_web_search_conf().get("zhipu_content_size") or "").strip().lower()
+        if content_size in ("medium", "high"):
+            payload["content_size"] = content_size
+
+        logger.debug(f"[WebSearch] zhipu: query='{trimmed_query}', count={payload['count']}, engine={engine}")
+        resp = requests.post(url, headers=headers, json=payload, timeout=DEFAULT_TIMEOUT)
+
+        if resp.status_code == 401:
+            return ToolResult.fail("Error: Invalid Zhipu API key.")
+        if resp.status_code != 200:
+            return ToolResult.fail(f"Error: Zhipu API returned HTTP {resp.status_code}: {resp.text[:200]}")
+
+        data = resp.json()
+        # Business-level errors (1701/1702/1703 etc.) come back as
+        # {"error": {"code","message"}} even on HTTP 200.
+        if isinstance(data, dict) and data.get("error"):
+            err = data["error"] or {}
+            return ToolResult.fail(f"Error: Zhipu returned {err.get('code')}: {err.get('message','')}")
+
+        items = data.get("search_result") or (data.get("data") or {}).get("search_result") or []
+        results = []
+        for it in items:
+            results.append({
+                "title": it.get("title", ""),
+                "url": it.get("link") or it.get("url", ""),
+                "snippet": it.get("content") or it.get("snippet", ""),
+                "siteName": it.get("media") or it.get("siteName", ""),
+                "datePublished": it.get("publish_date") or it.get("datePublished", ""),
+            })
+        return ToolResult.success({
+            "query": query, "backend": "zhipu",
+            "total": len(results), "count": len(results), "results": results,
+        })
+
+    # ------------------------------------------------------------------
+    # Qianfan (Baidu)
+    # ------------------------------------------------------------------
+
+    def _search_qianfan(self, query: str, count: int, freshness: str) -> ToolResult:
+        api_key = _get_api_key("qianfan")
+        api_base = (conf().get("qianfan_api_base") or "https://qianfan.baidubce.com/v2").rstrip("/")
+        url = f"{api_base}/ai_search/web_search"
+        headers = {
+            "Authorization": f"Bearer {api_key}",
+            "Content-Type": "application/json",
+            "X-Appbuilder-From": "cow",
         }
 
-        logger.debug(f"[WebSearch] LinkAI search: query='{query}', count={count}")
+        count = max(1, min(int(count or 10), 50))
+        payload: Dict[str, Any] = {
+            "messages": [{"role": "user", "content": query}],
+            "search_source": "baidu_search_v2",
+            "resource_type_filter": [{"type": "web", "top_k": count}],
+        }
 
-        response = requests.post(url, headers=headers, json=payload, timeout=DEFAULT_TIMEOUT)
+        # Baidu AI Search expects freshness as a date-range filter, not a
+        # named recency token. Translate our shared vocabulary into the
+        # underlying page_time range expected by the API.
+        search_filter = self._qianfan_build_freshness_filter(freshness)
+        if search_filter:
+            payload["search_filter"] = search_filter
 
-        if response.status_code == 401:
+        logger.debug(f"[WebSearch] qianfan: query='{query}', count={count}, freshness={freshness!r}")
-            return ToolResult.fail("Error: Invalid LINKAI_API_KEY. Please check your API key.")
+        resp = requests.post(url, headers=headers, json=payload, timeout=DEFAULT_TIMEOUT)
-        if response.status_code != 200:
-            return ToolResult.fail(f"Error: LinkAI API returned HTTP {response.status_code}")
 
-        data = response.json()
+        if resp.status_code == 401:
+            return ToolResult.fail("Error: Invalid Qianfan API key.")
+        if resp.status_code != 200:
+            return ToolResult.fail(f"Error: Qianfan API returned HTTP {resp.status_code}: {resp.text[:200]}")
 
+        data = resp.json()
+        # Even on HTTP 200 Baidu surfaces business errors as {"code","message"}.
+        if isinstance(data, dict) and data.get("code"):
+            return ToolResult.fail(f"Error: Qianfan returned {data.get('code')}: {data.get('message','')}")
+
+        refs = data.get("references") or []
+        results = []
+        for d in refs:
+            results.append({
+                "title": d.get("title", ""),
+                "url": d.get("url", ""),
+                "snippet": (d.get("content") or "")[:200],
+                "siteName": d.get("web_anchor") or d.get("website") or "",
+                "datePublished": d.get("date", ""),
+            })
+        return ToolResult.success({
+            "query": query, "backend": "qianfan",
+            "total": len(results), "count": len(results), "results": results,
+        })
+
+    @staticmethod
+    def _qianfan_build_freshness_filter(freshness: str) -> Optional[Dict[str, Any]]:
+        if not freshness or freshness == "noLimit":
+            return None
+        delta_days = {"oneDay": 1, "oneWeek": 7, "oneMonth": 30, "oneYear": 365}.get(freshness)
+        if not delta_days:
+            return None
+        from datetime import datetime, timedelta
+        now = datetime.now()
+        end_date = (now + timedelta(days=1)).strftime("%Y-%m-%d")
+        start_date = (now - timedelta(days=delta_days)).strftime("%Y-%m-%d")
+        return {"range": {"page_time": {"gte": start_date, "lt": end_date}}}
+
+    # ------------------------------------------------------------------
+    # LinkAI (plugin)
+    # ------------------------------------------------------------------
+
+    def _search_linkai(self, query: str, count: int, freshness: str) -> ToolResult:
+        api_key = _get_api_key("linkai")
+        api_base = (conf().get("linkai_api_base") or "https://api.link-ai.tech").rstrip("/")
+        url = f"{api_base}/v1/plugin/execute"
+
+        from common.utils import get_cloud_headers
+        headers = get_cloud_headers(api_key)
+
+        payload = {"code": "web-search", "args": {"query": query, "count": count, "freshness": freshness}}
+        logger.debug(f"[WebSearch] linkai: query='{query}', count={count}")
+        resp = requests.post(url, headers=headers, json=payload, timeout=DEFAULT_TIMEOUT)
+
+        if resp.status_code == 401:
+            return ToolResult.fail("Error: Invalid LinkAI API key.")
+        if resp.status_code != 200:
+            return ToolResult.fail(f"Error: LinkAI API returned HTTP {resp.status_code}")
+
+        data = resp.json()
         if not data.get("success"):
             msg = data.get("message") or "Unknown error"
             return ToolResult.fail(f"Error: LinkAI search failed: {msg}")
 
-        return self._format_linkai_results(data, query)
+        raw = data.get("data", "")
-
+        if isinstance(raw, str):
-    def _format_linkai_results(self, data: dict, query: str) -> ToolResult:
-        """
-        Format LinkAI API response into unified result structure.
-        LinkAI returns the search data in data.data field, which follows
-        the same Bing-compatible format as Bocha.
-
-        :param data: Raw API response
-        :param query: Original query
-        :return: Formatted ToolResult
-        """
-        raw_data = data.get("data", "")
-
-        # LinkAI may return data as a JSON string
-        if isinstance(raw_data, str):
             try:
-                raw_data = json.loads(raw_data)
+                raw = json.loads(raw)
             except (json.JSONDecodeError, TypeError):
-                # If data is plain text, return it as a single result
                 return ToolResult.success({
-                    "query": query,
+                    "query": query, "backend": "linkai",
-                    "backend": "linkai",
+                    "total": 1, "count": 1, "results": [{"content": raw}],
-                    "total": 1,
-                    "count": 1,
-                    "results": [{"content": raw_data}]
                 })
 
-        # If the response follows Bing-compatible structure
+        if isinstance(raw, dict):
-        if isinstance(raw_data, dict):
+            pages = (raw.get("webPages") or {}).get("value", []) or []
-            web_pages = raw_data.get("webPages", {})
-            pages = web_pages.get("value", [])
-
             if pages:
                 results = []
-                for page in pages:
+                for p in pages:
-                    result = {
+                    item = {
-                        "title": page.get("name", ""),
+                        "title": p.get("name", ""),
-                        "url": page.get("url", ""),
+                        "url": p.get("url", ""),
-                        "snippet": page.get("snippet", ""),
+                        "snippet": p.get("snippet", ""),
-                        "siteName": page.get("siteName", ""),
+                        "siteName": p.get("siteName", ""),
-                        "datePublished": page.get("datePublished") or page.get("dateLastCrawled", ""),
+                        "datePublished": p.get("datePublished") or p.get("dateLastCrawled", ""),
                     }
-                    if page.get("summary"):
+                    if p.get("summary"):
-                        result["summary"] = page["summary"]
+                        item["summary"] = p["summary"]
-                    results.append(result)
+                    results.append(item)
-
+                total = (raw.get("webPages") or {}).get("totalEstimatedMatches", len(results))
-                total = web_pages.get("totalEstimatedMatches", len(results))
                 return ToolResult.success({
-                    "query": query,
+                    "query": query, "backend": "linkai",
-                    "backend": "linkai",
+                    "total": total, "count": len(results), "results": results,
-                    "total": total,
-                    "count": len(results),
-                    "results": results
                 })
 
-        # Fallback: return raw data
         return ToolResult.success({
-            "query": query,
+            "query": query, "backend": "linkai",
-            "backend": "linkai",
+            "total": 1, "count": 1, "results": [{"content": str(raw)}],
-            "total": 1,
-            "count": 1,
-            "results": [{"content": str(raw_data)}]
         })

app.py

@@ -15,6 +15,11 @@ import threading
 
 _channel_mgr = None
 
+# Desktop mode: a lighter runtime for the packaged Electron client. Plugins are
+# loaded in a background thread (so command plugins like cow_cli/godcmd work
+# without slowing startup), while MCP warmup is still skipped to keep it fast.
+DESKTOP_MODE = os.environ.get("COW_DESKTOP") == "1"
+
 
 def get_channel_manager():
     return _channel_mgr
@@ -47,6 +52,7 @@ class ChannelManager:
         self._threads = {}         # channel_name -> thread
         self._primary_channel = None
         self._lock = threading.Lock()
+        self.cloud_mode = False    # set to True when cloud client is active
 
     @property
     def channel(self):
@@ -65,6 +71,7 @@ class ChannelManager:
             channels = []
             for name in channel_names:
                 ch = channel_factory.create_channel(name)
+                ch.cloud_mode = self.cloud_mode
                 self._channels[name] = ch
                 channels.append((name, ch))
                 if self._primary_channel is None and name != "web":
@@ -74,9 +81,23 @@ class ChannelManager:
                 self._primary_channel = channels[0][1]
 
             if first_start:
-                PluginManager().load_plugins()
+                if DESKTOP_MODE:
+                    # Load plugins in the background so command plugins
+                    # (cow_cli / godcmd, e.g. /status, #help) work in the
+                    # desktop client, without blocking web-service readiness.
+                    threading.Thread(
+                        target=PluginManager().load_plugins, daemon=True
+                    ).start()
+                else:
+                    PluginManager().load_plugins()
 
-                if conf().get("use_linkai"):
+                # Cloud client is optional. It is only started when
+                # use_linkai=True AND cloud_deployment_id is set.
+                # By default neither is configured, so the app runs
+                # entirely locally without any remote connection.
+                if conf().get("use_linkai") and (
+                    os.environ.get("CLOUD_DEPLOYMENT_ID") or conf().get("cloud_deployment_id")
+                ):
                     try:
                         from common import cloud_client
                         threading.Thread(
@@ -136,13 +157,22 @@ class ChannelManager:
                     self._interrupt_thread(th, name)
                 continue
             logger.info(f"[ChannelManager] Stopping channel '{name}'...")
-            try:
+            graceful = False
-                if hasattr(ch, 'stop'):
+            if hasattr(ch, 'stop'):
+                try:
                     ch.stop()
-            except Exception as e:
+                    graceful = True
-                logger.warning(f"[ChannelManager] Error during channel '{name}' stop: {e}")
+                except Exception as e:
+                    logger.warning(f"[ChannelManager] Error during channel '{name}' stop: {e}")
             if th and th.is_alive():
-                self._interrupt_thread(th, name)
+                th.join(timeout=5)
+                if th.is_alive():
+                    if graceful:
+                        logger.info(f"[ChannelManager] Channel '{name}' thread still alive after stop(), "
+                                    "leaving daemon thread to finish on its own")
+                    else:
+                        logger.warning(f"[ChannelManager] Channel '{name}' thread did not exit in 5s, forcing interrupt")
+                        self._interrupt_thread(th, name)
 
     @staticmethod
     def _interrupt_thread(th: threading.Thread, name: str):
@@ -175,6 +205,34 @@ class ChannelManager:
         self.start([new_channel_name], first_start=False)
         logger.info(f"[ChannelManager] Channel restarted to '{new_channel_name}' successfully")
 
+    def add_channel(self, channel_name: str):
+        """
+        Dynamically add and start a new channel.
+        If the channel is already running, restart it instead.
+        """
+        with self._lock:
+            if channel_name in self._channels:
+                logger.info(f"[ChannelManager] Channel '{channel_name}' already exists, restarting")
+        if self._channels.get(channel_name):
+            self.restart(channel_name)
+            return
+        logger.info(f"[ChannelManager] Adding channel '{channel_name}'...")
+        _clear_singleton_cache(channel_name)
+        self.start([channel_name], first_start=False)
+        logger.info(f"[ChannelManager] Channel '{channel_name}' added successfully")
+
+    def remove_channel(self, channel_name: str):
+        """
+        Dynamically stop and remove a running channel.
+        """
+        with self._lock:
+            if channel_name not in self._channels:
+                logger.warning(f"[ChannelManager] Channel '{channel_name}' not found, nothing to remove")
+                return
+        logger.info(f"[ChannelManager] Removing channel '{channel_name}'...")
+        self.stop(channel_name)
+        logger.info(f"[ChannelManager] Channel '{channel_name}' removed successfully")
+
 
 def _clear_singleton_cache(channel_name: str):
     """
@@ -182,16 +240,20 @@ def _clear_singleton_cache(channel_name: str):
     a new instance can be created with updated config.
     """
     cls_map = {
-        "wx": "channel.wechat.wechat_channel.WechatChannel",
-        "wxy": "channel.wechat.wechaty_channel.WechatyChannel",
-        "wcf": "channel.wechat.wcf_channel.WechatfChannel",
         "web": "channel.web.web_channel.WebChannel",
         "wechatmp": "channel.wechatmp.wechatmp_channel.WechatMPChannel",
         "wechatmp_service": "channel.wechatmp.wechatmp_channel.WechatMPChannel",
         "wechatcom_app": "channel.wechatcom.wechatcomapp_channel.WechatComAppChannel",
-        "wework": "channel.wework.wework_channel.WeworkChannel",
+        const.WECHAT_KF: "channel.wechat_kf.wechat_kf_channel.WechatKfChannel",
         const.FEISHU: "channel.feishu.feishu_channel.FeiShuChanel",
         const.DINGTALK: "channel.dingtalk.dingtalk_channel.DingTalkChanel",
+        const.WECOM_BOT: "channel.wecom_bot.wecom_bot_channel.WecomBotChannel",
+        const.QQ: "channel.qq.qq_channel.QQChannel",
+        const.TELEGRAM: "channel.telegram.telegram_channel.TelegramChannel",
+        const.SLACK: "channel.slack.slack_channel.SlackChannel",
+        const.DISCORD: "channel.discord.discord_channel.DiscordChannel",
+        const.WEIXIN: "channel.weixin.weixin_channel.WeixinChannel",
+        "wx": "channel.weixin.weixin_channel.WeixinChannel",
     }
     module_path = cls_map.get(channel_name)
     if not module_path:
@@ -229,6 +291,63 @@ def sigterm_handler_wrap(_signo):
     signal.signal(_signo, func)
 
 
+def _warmup_mcp_tools():
+    """
+    Kick off MCP server loading at process startup so subprocesses
+    (npx / uvx etc.) finish initializing before the first user message
+    arrives. Returns immediately — the actual work happens on a daemon
+    thread inside ToolManager. Safe to call when MCP is not configured.
+    """
+    try:
+        from agent.tools import ToolManager
+        ToolManager()._load_mcp_tools()
+    except Exception as e:
+        logger.warning(f"[App] MCP warmup failed (non-fatal): {e}")
+
+
+def _warmup_scheduler():
+    """Eager-init AgentBridge so the scheduler thread starts at process
+    boot rather than waiting for the first user message."""
+    try:
+        from bridge.bridge import Bridge
+        Bridge().get_agent_bridge()
+    except Exception as e:
+        logger.warning(f"[App] Scheduler warmup failed: {e}")
+
+
+def _sync_builtin_skills():
+    """Sync builtin skills from project skills/ to workspace skills/ on startup."""
+    import shutil
+    try:
+        workspace = conf().get("agent_workspace", "~/cow")
+        workspace = os.path.expanduser(workspace)
+        project_root = os.path.dirname(os.path.abspath(__file__))
+        builtin_dir = os.path.join(project_root, "skills")
+        custom_dir = os.path.join(workspace, "skills")
+
+        if not os.path.isdir(builtin_dir):
+            return
+
+        os.makedirs(custom_dir, exist_ok=True)
+        synced = 0
+        for name in os.listdir(builtin_dir):
+            src = os.path.join(builtin_dir, name)
+            if not os.path.isdir(src) or not os.path.isfile(os.path.join(src, "SKILL.md")):
+                continue
+            dst = os.path.join(custom_dir, name)
+            try:
+                if os.path.isdir(dst):
+                    shutil.rmtree(dst)
+                shutil.copytree(src, dst)
+                synced += 1
+            except Exception as e:
+                logger.warning(f"[App] Failed to sync builtin skill '{name}': {e}")
+        if synced:
+            logger.info(f"[App] Synced {synced} builtin skill(s) to workspace")
+    except Exception as e:
+        logger.warning(f"[App] Builtin skills sync failed: {e}")
+
+
 def run():
     global _channel_mgr
     try:
@@ -249,14 +368,28 @@ def run():
             if not channel_names:
                 channel_names = ["web"]
 
-        if "wxy" in channel_names:
-            os.environ["WECHATY_LOG"] = "warn"
-
         # Auto-start web console unless explicitly disabled
         web_console_enabled = conf().get("web_console", True)
         if web_console_enabled and "web" not in channel_names:
             channel_names.append("web")
 
+        # Sync builtin skills to workspace before channels start
+        _sync_builtin_skills()
+
+        # Kick off MCP server loading in the background so first-message
+        # latency isn't dominated by npx package downloads. Skipped in desktop
+        # mode (MCP relies on external npx/uvx runtimes that aren't bundled).
+        if not DESKTOP_MODE:
+            _warmup_mcp_tools()
+
+        if DESKTOP_MODE:
+            # Defer the (heavy) AgentBridge/scheduler warmup to a background
+            # thread so the web API becomes available within a couple seconds.
+            # The scheduler still starts; it just doesn't block UI readiness.
+            threading.Thread(target=_warmup_scheduler, daemon=True).start()
+        else:
+            _warmup_scheduler()
+
         logger.info(f"[App] Starting channels: {channel_names}")
 
         _channel_mgr = ChannelManager()
@@ -264,6 +397,8 @@ def run():
 
         while True:
             time.sleep(1)
+    except KeyboardInterrupt:
+        pass
     except Exception as e:
         logger.error("App startup failed!")
         logger.exception(e)

bridge/agent_bridge.py

@@ -5,7 +5,7 @@ Agent Bridge - Integrates Agent system with existing COW bridge
 import os
 from typing import Optional, List
 
-from agent.protocol import Agent, LLMModel, LLMRequest
+from agent.protocol import Agent, LLMModel, LLMRequest, get_cancel_registry
 from bridge.agent_event_handler import AgentEventHandler
 from bridge.agent_initializer import AgentInitializer
 from bridge.bridge import Bridge
@@ -14,6 +14,7 @@ from bridge.reply import Reply, ReplyType
 from common import const
 from common.log import logger
 from common.utils import expand_path
+from config import conf
 from models.openai_compatible_bot import OpenAICompatibleBot
 
 
@@ -67,18 +68,20 @@ class AgentLLMModel(LLMModel):
 
     _MODEL_BOT_TYPE_MAP = {
         "wenxin": const.BAIDU, "wenxin-4": const.BAIDU,
-        "xunfei": const.XUNFEI, const.QWEN: const.QWEN,
+        "xunfei": const.XUNFEI, const.QWEN: const.QWEN_DASHSCOPE,
+        const.QIANFAN: const.QIANFAN,
         const.MODELSCOPE: const.MODELSCOPE,
     }
     _MODEL_PREFIX_MAP = [
         ("qwen", const.QWEN_DASHSCOPE), ("qwq", const.QWEN_DASHSCOPE), ("qvq", const.QWEN_DASHSCOPE),
         ("gemini", const.GEMINI), ("glm", const.ZHIPU_AI), ("claude", const.CLAUDEAPI),
         ("moonshot", const.MOONSHOT), ("kimi", const.MOONSHOT),
-        ("doubao", const.DOUBAO),
+        ("doubao", const.DOUBAO), ("deepseek", const.DEEPSEEK),
+        ("ernie", const.QIANFAN),
+        ("mimo-", const.MIMO),
     ]
 
     def __init__(self, bridge: Bridge, bot_type: str = "chat"):
-        from config import conf
         super().__init__(model=conf().get("model", const.GPT_41))
         self.bridge = bridge
         self.bot_type = bot_type
@@ -87,7 +90,6 @@ class AgentLLMModel(LLMModel):
 
     @property
     def model(self):
-        from config import conf
         return conf().get("model", const.GPT_41)
 
     @model.setter
@@ -96,11 +98,15 @@ class AgentLLMModel(LLMModel):
 
     def _resolve_bot_type(self, model_name: str) -> str:
         """Resolve bot type from model name, matching Bridge.__init__ logic."""
-        from config import conf
         if conf().get("use_linkai", False) and conf().get("linkai_api_key"):
             return const.LINKAI
+        # Support custom bot type configuration
+        configured_bot_type = conf().get("bot_type")
+        if configured_bot_type:
+            return configured_bot_type
+       
         if not model_name or not isinstance(model_name, str):
-            return const.CHATGPT
+            return const.OPENAI
         if model_name in self._MODEL_BOT_TYPE_MAP:
             return self._MODEL_BOT_TYPE_MAP[model_name]
         if model_name.lower().startswith("minimax") or model_name in ["abab6.5-chat"]:
@@ -109,23 +115,25 @@ class AgentLLMModel(LLMModel):
             return const.QWEN_DASHSCOPE
         if model_name in [const.MOONSHOT, "moonshot-v1-8k", "moonshot-v1-32k", "moonshot-v1-128k"]:
             return const.MOONSHOT
-        if model_name in [const.DEEPSEEK_CHAT, const.DEEPSEEK_REASONER]:
+        if conf().get("bot_type") == "modelscope":
-            return const.CHATGPT
+            return const.MODELSCOPE
+        lowered_model = model_name.lower()
         for prefix, btype in self._MODEL_PREFIX_MAP:
-            if model_name.startswith(prefix):
+            if lowered_model.startswith(prefix):
                 return btype
-        return const.CHATGPT
+        return const.OPENAI
 
     @property
     def bot(self):
-        """Lazy load the bot, re-create when model changes"""
+        """Lazy load the bot, re-create when model or bot_type changes"""
         from models.bot_factory import create_bot
         cur_model = self.model
-        if self._bot is None or self._bot_model != cur_model:
+        cur_bot_type = self._resolve_bot_type(cur_model)
-            bot_type = self._resolve_bot_type(cur_model)
+        if self._bot is None or self._bot_model != cur_model or getattr(self, '_bot_type', None) != cur_bot_type:
-            self._bot = create_bot(bot_type)
+            self._bot = create_bot(cur_bot_type)
             self._bot = add_openai_compatible_support(self._bot)
             self._bot_model = cur_model
+            self._bot_type = cur_bot_type
         return self._bot
 
     def call(self, request: LLMRequest):
@@ -146,12 +154,37 @@ class AgentLLMModel(LLMModel):
                 # Only pass max_tokens if it's explicitly set
                 if request.max_tokens is not None:
                     kwargs['max_tokens'] = request.max_tokens
-                
+
                 # Extract system prompt if present
                 system_prompt = getattr(request, 'system', None)
                 if system_prompt:
                     kwargs['system'] = system_prompt
-                
+
+                # Pass context metadata to bot
+                channel_type = getattr(self, 'channel_type', None) or ''
+                if channel_type:
+                    kwargs['channel_type'] = channel_type
+                session_id = getattr(self, 'session_id', None)
+                if session_id:
+                    kwargs['session_id'] = session_id
+
+                # Thinking mode is a global toggle independent of the channel.
+                # IM channels (WeChat/WeCom/DingTalk/Feishu) won't render the
+                # reasoning trace, but still benefit from the higher answer
+                # quality the thinking pass produces.
+                from config import conf
+                thinking_enabled = bool(conf().get("enable_thinking", False))
+                kwargs['thinking'] = (
+                    {"type": "enabled"} if thinking_enabled
+                    else {"type": "disabled"}
+                )
+                # Reasoning effort is only meaningful when thinking is on.
+                # Bots that don't understand the kwarg drop it silently.
+                if thinking_enabled:
+                    effort = conf().get("reasoning_effort", "high")
+                    if effort in ("high", "max"):
+                        kwargs['reasoning_effort'] = effort
+
                 response = self.bot.call_with_tools(**kwargs)
                 return self._format_response(response)
             else:
@@ -189,10 +222,30 @@ class AgentLLMModel(LLMModel):
                 if system_prompt:
                     kwargs['system'] = system_prompt
 
-                # Pass channel_type for linkai tracking
+                # Pass context metadata to bot
-                channel_type = getattr(self, 'channel_type', None)
+                channel_type = getattr(self, 'channel_type', None) or ''
                 if channel_type:
                     kwargs['channel_type'] = channel_type
+                session_id = getattr(self, 'session_id', None)
+                if session_id:
+                    kwargs['session_id'] = session_id
+
+                # Thinking mode is a global toggle independent of the channel.
+                # IM channels (WeChat/WeCom/DingTalk/Feishu) won't render the
+                # reasoning trace, but still benefit from the higher answer
+                # quality the thinking pass produces.
+                from config import conf
+                thinking_enabled = bool(conf().get("enable_thinking", False))
+                kwargs['thinking'] = (
+                    {"type": "enabled"} if thinking_enabled
+                    else {"type": "disabled"}
+                )
+                # Reasoning effort is only meaningful when thinking is on.
+                # Bots that don't understand the kwarg drop it silently.
+                if thinking_enabled:
+                    effort = conf().get("reasoning_effort", "high")
+                    if effort in ("high", "max"):
+                        kwargs['reasoning_effort'] = effort
 
                 stream = self.bot.call_with_tools(**kwargs)
                 
@@ -233,6 +286,23 @@ class AgentBridge:
         
         # Create helper instances
         self.initializer = AgentInitializer(bridge, self)
+
+        # Eager-start the scheduler so cron tasks fire without waiting
+        # for the first user message. init_scheduler is idempotent.
+        try:
+            from agent.tools.scheduler.integration import init_scheduler
+            if init_scheduler(self):
+                self.scheduler_initialized = True
+        except Exception as e:
+            logger.warning(f"[AgentBridge] Eager scheduler init failed: {e}")
+
+        # Start the self-evolution idle trigger (idempotent, daemon thread).
+        try:
+            from agent.evolution.trigger import start_evolution_trigger
+            start_evolution_trigger(self)
+        except Exception as e:
+            logger.warning(f"[AgentBridge] Evolution trigger init failed: {e}")
+
     def create_agent(self, system_prompt: str, tools: List = None, **kwargs) -> Agent:
         """
         Create the super agent with COW integration
@@ -256,10 +326,13 @@ class AgentBridge:
             tool_manager.load_tools()
             
             tools = []
+            workspace_dir = kwargs.get("workspace_dir")
             for tool_name in tool_manager.tool_classes.keys():
                 try:
                     tool = tool_manager.create_tool(tool_name)
                     if tool:
+                        if workspace_dir and hasattr(tool, 'cwd'):
+                            tool.cwd = workspace_dir
                         tools.append(tool)
                 except Exception as e:
                     logger.warning(f"[AgentBridge] Failed to load tool {tool_name}: {e}")
@@ -272,12 +345,13 @@ class AgentBridge:
             tools=tools,
             max_steps=kwargs.get("max_steps", 15),
             output_mode=kwargs.get("output_mode", "logger"),
-            workspace_dir=kwargs.get("workspace_dir"),  # Pass workspace for skills loading
+            workspace_dir=kwargs.get("workspace_dir"),
-            enable_skills=kwargs.get("enable_skills", True),  # Enable skills by default
+            skill_manager=kwargs.get("skill_manager"),
-            memory_manager=kwargs.get("memory_manager"),  # Pass memory manager
+            enable_skills=kwargs.get("enable_skills", True),
+            memory_manager=kwargs.get("memory_manager"),
             max_context_tokens=kwargs.get("max_context_tokens"),
             context_reserve_tokens=kwargs.get("context_reserve_tokens"),
-            runtime_info=kwargs.get("runtime_info")  # Pass runtime_info for dynamic time updates
+            runtime_info=kwargs.get("runtime_info"),
         )
 
         # Log skill loading details
@@ -317,7 +391,49 @@ class AgentBridge:
         """Initialize agent for a specific session"""
         agent = self.initializer.initialize_agent(session_id=session_id)
         self.agents[session_id] = agent
-    
+
+    def sync_session_messages_from_store(self, session_id: str) -> int:
+        """Reload an agent's in-memory ``messages`` list from the persistent
+        conversation store.
+
+        Used after an external mutation (e.g. user edits / deletes a message
+        via the web console) so the agent's next turn sees the same history
+        as the database. The operation is a no-op when the agent has not been
+        instantiated yet for the session.
+
+        Returns:
+            Number of messages now held in the agent's memory. Returns -1 if
+            the agent does not exist or has no compatible ``messages`` attr.
+        """
+        if not session_id or session_id not in self.agents:
+            return -1
+        agent = self.agents[session_id]
+        if not (hasattr(agent, "messages") and hasattr(agent, "messages_lock")):
+            return -1
+        try:
+            from agent.memory import get_conversation_store
+            store = get_conversation_store()
+            # No turn cap here: we want a faithful mirror of what the store
+            # has for this session after deletion.
+            remaining = store.load_messages(session_id, max_turns=10**6)
+        except Exception as e:
+            logger.warning(
+                f"[AgentBridge] Failed to load messages for sync (session={session_id}): {e}"
+            )
+            return -1
+        with agent.messages_lock:
+            agent.messages.clear()
+            for msg in remaining:
+                agent.messages.append({
+                    "role": msg["role"],
+                    "content": msg["content"],
+                })
+            count = len(agent.messages)
+        logger.info(
+            f"[AgentBridge] Synced agent memory for session={session_id}, messages={count}"
+        )
+        return count
+
     def agent_reply(self, query: str, context: Context = None, 
                    on_event=None, clear_history: bool = False) -> Reply:
         """
@@ -332,12 +448,24 @@ class AgentBridge:
         Returns:
             Reply object
         """
+        session_id = None
+        agent = None
+        request_id = None
+        cancel_event = None
         try:
             # Extract session_id from context for user isolation
-            session_id = None
             if context:
                 session_id = context.kwargs.get("session_id") or context.get("session_id")
-            
+                request_id = context.kwargs.get("request_id") or context.get("request_id")
+
+            # Register a cancel token. Prefer per-turn request_id (web),
+            # fall back to session_id (IM channels). The Event is polled by
+            # AgentStreamExecutor at safe checkpoints.
+            registry = get_cancel_registry()
+            token_key = request_id or session_id
+            if token_key:
+                cancel_event = registry.register(token_key, session_id=session_id)
+
             # Get agent for this session (will auto-initialize if needed)
             agent = self.get_agent(session_id=session_id)
             if not agent:
@@ -367,22 +495,60 @@ class AgentBridge:
                                 logger.warning(f"[AgentBridge] Failed to attach context to scheduler: {e}")
                             break
             
-            # Pass channel_type to model so linkai requests carry it
+            # Pass context metadata to model for downstream API requests
             if context and hasattr(agent, 'model'):
                 agent.model.channel_type = context.get("channel_type", "")
+                agent.model.session_id = session_id or ""
 
-            # Record message count before execution so we can diff new messages
+            # Store session_id on agent so executor can clear DB on fatal errors
-            with agent.messages_lock:
+            agent._current_session_id = session_id
-                pre_run_len = len(agent.messages)
+
+            # Bound the in-memory context for scheduler sessions before each run.
+            # Scheduler sessions are stable per-task and append every trigger,
+            # so without trimming they would grow unbounded across runs and
+            # blow up prompt cost. Regular user chats are not touched here —
+            # the agent's own context manager handles that path.
+            if session_id and session_id.startswith("scheduler_"):
+                from config import conf
+                scheduler_keep_turns = max(
+                    1, int(conf().get("agent_max_context_turns", 20)) // 5
+                )
+                self._trim_in_memory_to_turns(agent, scheduler_keep_turns)
+
+            # Eagerly persist the user message BEFORE running the agent so the
+            # session and the user's bubble are immediately visible — even if
+            # the user switches away or refreshes before the reply finishes.
+            # The reply (assistant/tool messages) is appended once the run
+            # completes; the final persist skips this already-stored user turn.
+            pre_persisted = self._pre_persist_user_message(
+                session_id, query, context, clear_history
+            )
+
+            # Mark this session as mid-run so the self-evolution idle scan does
+            # not fire concurrently when a single turn runs longer than
+            # idle_minutes.
+            try:
+                from agent.evolution.trigger import mark_run_active
+                mark_run_active(agent, True)
+            except Exception:
+                pass
 
             try:
                 # Use agent's run_stream method with event handler
                 response = agent.run_stream(
                     user_message=query,
                     on_event=event_handler.handle_event,
-                    clear_history=clear_history
+                    clear_history=clear_history,
+                    cancel_event=cancel_event,
                 )
             finally:
+                # Clear the mid-run flag so idle scans can review this session.
+                try:
+                    from agent.evolution.trigger import mark_run_active
+                    mark_run_active(agent, False)
+                except Exception:
+                    pass
+
                 # Restore original tools
                 if context and context.get("is_scheduled_task"):
                     agent.tools = original_tools
@@ -390,14 +556,58 @@ class AgentBridge:
                 # Log execution summary
                 event_handler.log_summary()
 
+                # Release cancel token; keep registry bounded.
+                if token_key:
+                    try:
+                        registry.unregister(token_key)
+                    except Exception:
+                        pass
+
             # Persist new messages generated during this run
             if session_id:
                 channel_type = (context.get("channel_type") or "") if context else ""
-                with agent.messages_lock:
+                new_messages = list(getattr(agent, '_last_run_new_messages', []))
-                    new_messages = agent.messages[pre_run_len:]
+                # The leading user turn was already persisted eagerly above;
-                self._persist_messages(session_id, list(new_messages), channel_type)
+                # drop it here so it isn't stored twice.
+                if pre_persisted and new_messages and new_messages[0].get("role") == "user":
+                    new_messages = new_messages[1:]
+                if new_messages:
+                    self._persist_messages(session_id, list(new_messages), channel_type)
+                else:
+                    with agent.messages_lock:
+                        msg_count = len(agent.messages)
+                    if msg_count == 0:
+                        try:
+                            from agent.memory import get_conversation_store
+                            get_conversation_store().clear_session(session_id)
+                            logger.info(f"[AgentBridge] Cleared DB for recovered session: {session_id}")
+                        except Exception as e:
+                            logger.warning(f"[AgentBridge] Failed to clear DB after recovery: {e}")
             
-            # Check if there are files to send (from read tool)
+            # Record this user turn for the self-evolution idle trigger. Skip
+            # scheduler-injected / scheduled-task sessions so internal runs do
+            # not count as user activity.
+            if session_id and not session_id.startswith("scheduler_") and not (
+                context and context.get("is_scheduled_task")
+            ):
+                try:
+                    from agent.evolution.trigger import note_user_turn
+                    ch = (context.get("channel_type") or "") if context else ""
+                    rcv = (context.get("receiver") or "") if context else ""
+                    is_group = bool(context.get("isgroup")) if context else False
+                    # Only enable proactive push for single chats (group push is
+                    # noisy); group sessions still evolve, just without notify.
+                    note_user_turn(agent, channel_type=ch, receiver=(rcv if not is_group else ""))
+                except Exception:
+                    pass
+
+            # Post-message hot-reload: detect edits to ~/cow/mcp.json and
+            # sync any new/removed MCP tools into the live agent in the
+            # background. Off the critical path so user latency is unaffected;
+            # changes take effect on the user's next message.
+            self._schedule_mcp_hot_reload(agent)
+
+            # Check if there are files to send (from send/read tool)
             if hasattr(agent, 'stream_executor') and hasattr(agent.stream_executor, 'files_to_send'):
                 files_to_send = agent.stream_executor.files_to_send
                 if files_to_send:
@@ -415,8 +625,51 @@ class AgentBridge:
             
         except Exception as e:
             logger.error(f"Agent reply error: {e}")
+            # If the agent cleared its messages due to format error / overflow,
+            # also purge the DB so the next request starts clean.
+            if session_id and agent:
+                try:
+                    with agent.messages_lock:
+                        msg_count = len(agent.messages)
+                    if msg_count == 0:
+                        from agent.memory import get_conversation_store
+                        get_conversation_store().clear_session(session_id)
+                        logger.info(f"[AgentBridge] Cleared DB for session after error: {session_id}")
+                except Exception as db_err:
+                    logger.warning(f"[AgentBridge] Failed to clear DB after error: {db_err}")
+            # Release cancel token on error path too (idempotent).
+            if cancel_event is not None and (request_id or session_id):
+                try:
+                    get_cancel_registry().unregister(request_id or session_id)
+                except Exception:
+                    pass
             return Reply(ReplyType.ERROR, f"Agent error: {str(e)}")
     
+    def _schedule_mcp_hot_reload(self, agent):
+        """
+        Fire-and-forget: detect mcp.json edits and reconcile the agent's
+        tool dict in the background. Runs after the user's reply is sent,
+        so any cost (file stat, hash, server boot) never adds to user latency.
+        Failures are isolated and never raise into the message pipeline.
+        """
+        import threading
+        from agent.tools import ToolManager
+
+        def _run():
+            try:
+                tm = ToolManager()
+                tm.refresh_mcp_if_changed()
+                added, removed = tm.sync_mcp_into_agent(agent)
+                if added or removed:
+                    logger.info(
+                        f"[AgentBridge] Agent tools synced — "
+                        f"added={added}, removed={removed}"
+                    )
+            except Exception as e:
+                logger.warning(f"[AgentBridge] MCP hot-reload failed (non-fatal): {e}")
+
+        threading.Thread(target=_run, daemon=True, name="mcp-hot-reload").start()
+
     def _create_file_reply(self, file_info: dict, text_response: str, context: Context = None) -> Reply:
         """
         Create a reply for sending files
@@ -431,11 +684,21 @@ class AgentBridge:
         """
         file_type = file_info.get("file_type", "file")
         file_path = file_info.get("path")
-        
+        # Remote URLs are passed through as-is; local paths get a file:// prefix
+        # so the channel can read them from disk.
+        remote_url = file_info.get("url", "")
+        is_remote = bool(remote_url) and remote_url.lower().startswith(("http://", "https://"))
+
+        def _to_channel_url(p: str) -> str:
+            if is_remote:
+                return remote_url
+            if p and p.lower().startswith(("http://", "https://")):
+                return p
+            return f"file://{p}"
+
         # For images, use IMAGE_URL type (channel will handle upload)
         if file_type == "image":
-            # Convert local path to file:// URL for channel processing
+            file_url = _to_channel_url(file_path)
-            file_url = f"file://{file_path}"
             logger.info(f"[AgentBridge] Sending image: {file_url}")
             reply = Reply(ReplyType.IMAGE_URL, file_url)
             # Attach text message if present (for channels that support text+image)
@@ -445,7 +708,7 @@ class AgentBridge:
         
         # For all file types (document, video, audio), use FILE type
         if file_type in ["document", "video", "audio"]:
-            file_url = f"file://{file_path}"
+            file_url = _to_channel_url(file_path)
             logger.info(f"[AgentBridge] Sending {file_type}: {file_url}")
             reply = Reply(ReplyType.FILE, file_url)
             reply.file_name = file_info.get("file_name", os.path.basename(file_path))
@@ -454,22 +717,26 @@ class AgentBridge:
                 reply.text_content = text_response
             return reply
         
-        # For other unknown file types, return text with file info
+        # For all other file types (tar.gz, zip, etc.), also use FILE type
-        message = text_response or file_info.get("message", "文件已准备")
+        file_url = _to_channel_url(file_path)
-        message += f"\n\n[文件: {file_info.get('file_name', file_path)}]"
+        logger.info(f"[AgentBridge] Sending generic file: {file_url}")
-        return Reply(ReplyType.TEXT, message)
+        reply = Reply(ReplyType.FILE, file_url)
+        reply.file_name = file_info.get("file_name", os.path.basename(file_path))
+        if text_response:
+            reply.text_content = text_response
+        return reply
     
     def _migrate_config_to_env(self, workspace_root: str):
         """
-        Migrate API keys from config.json to .env file if not already set
+        Sync API keys from config.json to .env file.
-        
+        Adds new keys and updates changed values on each startup.
+
         Args:
             workspace_root: Workspace directory path (not used, kept for compatibility)
         """
         from config import conf
         import os
         
-        # Mapping from config.json keys to environment variable names
         key_mapping = {
             "open_ai_api_key": "OPENAI_API_KEY",
             "open_ai_api_base": "OPENAI_API_BASE",
@@ -478,10 +745,9 @@ class AgentBridge:
             "linkai_api_key": "LINKAI_API_KEY",
         }
         
-        # Use fixed secure location for .env file
         env_file = expand_path("~/.cow/.env")
         
-        # Read existing env vars from .env file
+        # Read existing env vars (key -> value)
         existing_env_vars = {}
         if os.path.exists(env_file):
             try:
@@ -489,49 +755,89 @@ class AgentBridge:
                     for line in f:
                         line = line.strip()
                         if line and not line.startswith('#') and '=' in line:
-                            key, _ = line.split('=', 1)
+                            key, val = line.split('=', 1)
-                            existing_env_vars[key.strip()] = True
+                            existing_env_vars[key.strip()] = val.strip()
             except Exception as e:
                 logger.warning(f"[AgentBridge] Failed to read .env file: {e}")
         
-        # Check which keys need to be migrated
+        # Sync config.json values into .env (add/update/remove)
-        keys_to_migrate = {}
+        updated = False
         for config_key, env_key in key_mapping.items():
-            # Skip if already in .env file
+            raw = conf().get(config_key, "")
-            if env_key in existing_env_vars:
+            value = raw.strip() if raw else ""
-                continue
+            old_value = existing_env_vars.get(env_key)
-            
+
-            # Get value from config.json
+            if value:
-            value = conf().get(config_key, "")
+                if old_value == value:
-            if value and value.strip():  # Only migrate non-empty values
+                    continue
-                keys_to_migrate[env_key] = value.strip()
+                existing_env_vars[env_key] = value
-        
+                os.environ[env_key] = value
-        # Log summary if there are keys to skip
+                updated = True
-        if existing_env_vars:
+            else:
-            logger.debug(f"[AgentBridge] {len(existing_env_vars)} env vars already in .env")
+                if old_value is None:
-        
+                    continue
-        # Write new keys to .env file
+                existing_env_vars.pop(env_key, None)
-        if keys_to_migrate:
+                os.environ.pop(env_key, None)
+                updated = True
+            updated = True
+
+        if updated:
             try:
-                # Ensure ~/.cow directory and .env file exist
                 env_dir = os.path.dirname(env_file)
-                if not os.path.exists(env_dir):
+                os.makedirs(env_dir, exist_ok=True)
-                    os.makedirs(env_dir, exist_ok=True)
+
-                if not os.path.exists(env_file):
+                with open(env_file, 'w', encoding='utf-8') as f:
-                    open(env_file, 'a').close()
+                    f.write('# Environment variables for agent\n')
-                
+                    f.write('# Auto-managed - synced from config.json on startup\n\n')
-                # Append new keys
+                    for key, value in sorted(existing_env_vars.items()):
-                with open(env_file, 'a', encoding='utf-8') as f:
-                    f.write('\n# Auto-migrated from config.json\n')
-                    for key, value in keys_to_migrate.items():
                         f.write(f'{key}={value}\n')
-                        # Also set in current process
+
-                        os.environ[key] = value
+                logger.info(f"[AgentBridge] Synced API keys from config.json to .env")
-                
-                logger.info(f"[AgentBridge] Migrated {len(keys_to_migrate)} API keys from config.json to .env: {list(keys_to_migrate.keys())}")
             except Exception as e:
-                logger.warning(f"[AgentBridge] Failed to migrate API keys: {e}")
+                logger.warning(f"[AgentBridge] Failed to sync API keys: {e}")
     
+    def _pre_persist_user_message(
+        self, session_id: str, query: str, context: Context, clear_history: bool
+    ) -> bool:
+        """Persist the user's message before the agent runs.
+
+        This makes a brand-new session (and the user's bubble) visible even if
+        the reply hasn't finished — switching away or refreshing no longer
+        loses the in-flight session. Returns True when the user turn was
+        stored, so the caller can skip it in the post-run persist.
+
+        Best-effort: any failure is swallowed and reported as not-persisted.
+        """
+        if not session_id or not query:
+            return False
+        # Only real user turns: skip scheduler-injected / scheduled-task runs.
+        if session_id.startswith("scheduler_") or (
+            context and context.get("is_scheduled_task")
+        ):
+            return False
+        try:
+            from config import conf
+            if not conf().get("conversation_persistence", True):
+                return False
+            from agent.memory import get_conversation_store
+            store = get_conversation_store()
+            # clear_history starts a fresh transcript: wipe the store first so
+            # the eager user turn becomes seq 0, matching in-memory state.
+            if clear_history:
+                store.clear_session(session_id)
+            channel_type = (context.get("channel_type") or "") if context else ""
+            user_msg = {
+                "role": "user",
+                "content": [{"type": "text", "text": query}],
+            }
+            store.append_messages(session_id, [user_msg], channel_type=channel_type)
+            return True
+        except Exception as e:
+            logger.warning(
+                f"[AgentBridge] Failed to pre-persist user message for session={session_id}: {e}"
+            )
+            return False
+
     def _persist_messages(
         self, session_id: str, new_messages: list, channel_type: str = ""
     ) -> None:
@@ -546,18 +852,245 @@ class AgentBridge:
             from config import conf
             if not conf().get("conversation_persistence", True):
                 return
+            # When deep-thinking display is disabled, strip "thinking" content
+            # blocks before persisting so they don't resurface on history reload.
+            # The in-memory message list keeps them intact for this run's
+            # multi-turn LLM context.
+            thinking_enabled = bool(conf().get("enable_thinking", False))
         except Exception:
-            pass
+            thinking_enabled = False
+
+        messages_to_store = new_messages
+        if not thinking_enabled:
+            messages_to_store = self._strip_thinking_blocks(new_messages)
+
         try:
             from agent.memory import get_conversation_store
             get_conversation_store().append_messages(
-                session_id, new_messages, channel_type=channel_type
+                session_id, messages_to_store, channel_type=channel_type
             )
         except Exception as e:
             logger.warning(
                 f"[AgentBridge] Failed to persist messages for session={session_id}: {e}"
             )
 
+    # Marker used to identify scheduler-injected user messages so we can apply
+    # a sliding window without touching real user turns. The legacy prefix
+    # "Scheduled task" (written by the v2 PR) is also recognised when pruning,
+    # so old data can be aged out instead of leaking forever.
+    _SCHEDULED_MARKER = "[SCHEDULED]"
+    _SCHEDULED_LEGACY_MARKERS = ("Scheduled task",)
+
+    def remember_scheduled_output(
+        self,
+        session_id: str,
+        content: str,
+        channel_type: str = "",
+        task_description: str = "",
+    ) -> None:
+        """Add the visible output of a scheduled task to the receiver's session.
+
+        Scheduled task execution uses an isolated session so internal planning and
+        tool calls do not leak into the user's chat. The final message is still
+        part of the conversation from the user's point of view, so keep a small
+        visible turn in the receiver session for follow-up questions.
+
+        Configuration:
+            scheduler_inject_to_session (bool, default True):
+                Master switch. When False, this method is a no-op.
+            scheduler_inject_max_per_session (int, default 3):
+                Maximum scheduler-injected user/assistant pairs retained per
+                session. Older injections are pruned automatically.
+
+        Content is truncated to 2000 chars to prevent a single high-volume task
+        from bloating one entry.
+        """
+        from config import conf
+        if not conf().get("scheduler_inject_to_session", True):
+            return
+        if not session_id or not content:
+            return
+
+        max_len = 2000
+        if len(content) > max_len:
+            content = content[:max_len] + "..."
+
+        user_text = self._SCHEDULED_MARKER
+        if task_description:
+            user_text = f"{self._SCHEDULED_MARKER} {task_description}"
+
+        messages = [
+            {"role": "user", "content": [{"type": "text", "text": user_text}]},
+            {"role": "assistant", "content": [{"type": "text", "text": content}]},
+        ]
+
+        # Persist first so the new pair gets a stable seq, then prune old
+        # scheduler pairs in DB, then sync the in-memory agent.messages buffer.
+        self._persist_messages(session_id, messages, channel_type)
+
+        keep_last_n = max(int(conf().get("scheduler_inject_max_per_session", 3) or 0), 0)
+        try:
+            from agent.memory import get_conversation_store
+            deleted = get_conversation_store().prune_scheduled_messages(
+                session_id, keep_last_n=keep_last_n
+            )
+            if deleted:
+                logger.debug(
+                    f"[AgentBridge] Pruned {deleted} old scheduler messages "
+                    f"for session={session_id} (keep_last_n={keep_last_n})"
+                )
+        except Exception as e:
+            logger.warning(
+                f"[AgentBridge] Failed to prune scheduled messages "
+                f"for session={session_id}: {e}"
+            )
+
+        agent = self.agents.get(session_id)
+        if agent:
+            try:
+                with agent.messages_lock:
+                    agent.messages.extend(messages)
+                    self._prune_scheduled_in_memory(agent, keep_last_n)
+            except Exception as e:
+                logger.warning(
+                    f"[AgentBridge] Failed to update in-memory scheduled output "
+                    f"for session={session_id}: {e}"
+                )
+
+    @staticmethod
+    def _trim_in_memory_to_turns(agent, keep_turns: int) -> None:
+        """Bound ``agent.messages`` to the most recent ``keep_turns`` real
+        user/assistant turns, dropping older history together with any
+        intermediate tool_use/tool_result blocks that belonged to it.
+
+        A "real" user message is any user message whose content is not solely a
+        tool_result block — matches the heuristic used elsewhere when filtering
+        history (see ``AgentInitializer._filter_text_only_messages``).
+
+        No-op when the session is already within budget. Caller does not need
+        to hold the lock; this method acquires it itself.
+        """
+        if keep_turns <= 0:
+            return
+
+        def _is_real_user(msg) -> bool:
+            if not isinstance(msg, dict) or msg.get("role") != "user":
+                return False
+            content = msg.get("content")
+            if isinstance(content, list):
+                if any(
+                    isinstance(b, dict) and b.get("type") == "tool_result"
+                    for b in content
+                ):
+                    return False
+                return any(
+                    isinstance(b, dict) and b.get("type") == "text" and b.get("text")
+                    for b in content
+                )
+            if isinstance(content, str):
+                return bool(content.strip())
+            return False
+
+        with agent.messages_lock:
+            msgs = agent.messages
+            real_user_indices = [i for i, m in enumerate(msgs) if _is_real_user(m)]
+            if len(real_user_indices) <= keep_turns:
+                return
+
+            # Cut at the (k-th from the end) real user message; keep everything
+            # from there onwards so the surviving slice is still a valid
+            # user/assistant sequence.
+            cut_idx = real_user_indices[-keep_turns]
+            if cut_idx == 0:
+                return
+
+            kept = msgs[cut_idx:]
+            msgs.clear()
+            msgs.extend(kept)
+            logger.debug(
+                f"[AgentBridge] Trimmed in-memory messages to last "
+                f"{keep_turns} turns ({len(kept)} messages remain)"
+            )
+
+    @classmethod
+    def _prune_scheduled_in_memory(cls, agent, keep_last_n: int) -> None:
+        """Mirror conversation_store.prune_scheduled_messages on agent.messages.
+
+        Caller must hold ``agent.messages_lock``.
+        """
+        if keep_last_n < 0:
+            keep_last_n = 0
+
+        markers = (cls._SCHEDULED_MARKER,) + cls._SCHEDULED_LEGACY_MARKERS
+
+        def _is_marker_user(msg) -> bool:
+            if not isinstance(msg, dict) or msg.get("role") != "user":
+                return False
+            content = msg.get("content")
+            text = ""
+            if isinstance(content, str):
+                text = content
+            elif isinstance(content, list):
+                for block in content:
+                    if isinstance(block, dict) and block.get("type") == "text":
+                        text = block.get("text", "")
+                        break
+            return any(text.startswith(m) for m in markers)
+
+        msgs = agent.messages
+        pair_indices = []  # list of (user_idx, assistant_idx_or_None)
+        for idx, msg in enumerate(msgs):
+            if not _is_marker_user(msg):
+                continue
+            assistant_idx = None
+            if idx + 1 < len(msgs):
+                nxt = msgs[idx + 1]
+                if isinstance(nxt, dict) and nxt.get("role") == "assistant":
+                    assistant_idx = idx + 1
+            pair_indices.append((idx, assistant_idx))
+
+        if len(pair_indices) <= keep_last_n:
+            return
+
+        to_drop = pair_indices[: len(pair_indices) - keep_last_n]
+        drop_set = set()
+        for u_idx, a_idx in to_drop:
+            drop_set.add(u_idx)
+            if a_idx is not None:
+                drop_set.add(a_idx)
+
+        # Rebuild the list in place to keep external references stable.
+        kept = [m for i, m in enumerate(msgs) if i not in drop_set]
+        msgs.clear()
+        msgs.extend(kept)
+
+    @staticmethod
+    def _strip_thinking_blocks(messages: list) -> list:
+        """Return a shallow copy of messages with assistant "thinking" blocks removed."""
+        cleaned = []
+        for msg in messages:
+            if not isinstance(msg, dict):
+                cleaned.append(msg)
+                continue
+            if msg.get("role") != "assistant":
+                cleaned.append(msg)
+                continue
+            content = msg.get("content")
+            if not isinstance(content, list):
+                cleaned.append(msg)
+                continue
+            filtered_blocks = [
+                b for b in content
+                if not (isinstance(b, dict) and b.get("type") == "thinking")
+            ]
+            if len(filtered_blocks) == len(content):
+                cleaned.append(msg)
+            else:
+                new_msg = dict(msg)
+                new_msg["content"] = filtered_blocks
+                cleaned.append(new_msg)
+        return cleaned
+
     def clear_session(self, session_id: str):
         """
         Clear a specific session's agent and conversation history
@@ -643,4 +1176,4 @@ class AgentBridge:
                 agent.tools = [t for t in agent.tools if t.name != "web_search"]
                 logger.info("[AgentBridge] web_search tool removed (API key no longer available)")
         except Exception as e:
-            logger.debug(f"[AgentBridge] Failed to refresh conditional tools: {e}")
+            logger.debug(f"[AgentBridge] Failed to refresh conditional tools: {e}")

bridge/agent_event_handler.py

@@ -2,114 +2,124 @@
 Agent Event Handler - Handles agent events and thinking process output
 """
 
+from common import const
 from common.log import logger
 
+# Cap intermediate thinking messages on weixin to stay within send quota.
+WEIXIN_THINKING_INSTANT_MAX = 7
+
 
 class AgentEventHandler:
     """
     Handles agent events and optionally sends intermediate messages to channel
     """
-    
+
     def __init__(self, context=None, original_callback=None):
-        """
-        Initialize event handler
-        
-        Args:
-            context: COW context (for accessing channel)
-            original_callback: Original event callback to chain
-        """
         self.context = context
         self.original_callback = original_callback
-        
+
-        # Get channel for sending intermediate messages
         self.channel = None
         if context:
             self.channel = context.kwargs.get("channel") if hasattr(context, "kwargs") else None
-        
+
-        # Track current thinking for channel output
+        self.current_content = ""
-        self.current_thinking = ""
         self.turn_number = 0
-    
+
+        channel_type = ""
+        if context and hasattr(context, "kwargs"):
+            channel_type = context.kwargs.get("channel_type", "") or ""
+        self._is_weixin = channel_type == const.WEIXIN
+        self._thinking_sent_count = 0
+        self._merged_buf: list[str] = []
+
     def handle_event(self, event):
-        """
-        Main event handler
-        
-        Args:
-            event: Event dict with type and data
-        """
         event_type = event.get("type")
         data = event.get("data", {})
-        
+
-        # Dispatch to specific handlers
         if event_type == "turn_start":
             self._handle_turn_start(data)
         elif event_type == "message_update":
             self._handle_message_update(data)
         elif event_type == "message_end":
             self._handle_message_end(data)
+        elif event_type == "reasoning_update":
+            pass
         elif event_type == "tool_execution_start":
             self._handle_tool_execution_start(data)
         elif event_type == "tool_execution_end":
             self._handle_tool_execution_end(data)
-        
+        elif event_type == "agent_end":
-        # Call original callback if provided
+            self._handle_agent_end(data)
+
         if self.original_callback:
             self.original_callback(event)
-    
+
     def _handle_turn_start(self, data):
-        """Handle turn start event"""
         self.turn_number = data.get("turn", 0)
-        self.has_tool_calls_in_turn = False
+        self.current_content = ""
-        self.current_thinking = ""
+
-    
     def _handle_message_update(self, data):
-        """Handle message update event (streaming text)"""
         delta = data.get("delta", "")
-        self.current_thinking += delta
+        self.current_content += delta
-    
+
     def _handle_message_end(self, data):
-        """Handle message end event"""
         tool_calls = data.get("tool_calls", [])
-        
+
-        # Only send thinking process if followed by tool calls
         if tool_calls:
-            if self.current_thinking.strip():
+            if self.current_content.strip():
-                logger.info(f"💭 {self.current_thinking.strip()[:200]}{'...' if len(self.current_thinking) > 200 else ''}")
+                logger.info(f"💭 {self.current_content.strip()[:200]}{'...' if len(self.current_content) > 200 else ''}")
-                # Send thinking process to channel
+                self._send_to_channel(self.current_content.strip())
-                self._send_to_channel(f"{self.current_thinking.strip()}")
         else:
-            # No tool calls = final response (logged at agent_stream level)
+            if self.current_content.strip():
-            if self.current_thinking.strip():
+                logger.debug(f"💬 {self.current_content.strip()[:200]}{'...' if len(self.current_content) > 200 else ''}")
-                logger.debug(f"💬 {self.current_thinking.strip()[:200]}{'...' if len(self.current_thinking) > 200 else ''}")
+            # Drain weixin buffer before final reply leaves chat_channel
-        
+            self._flush_merged_now()
-        self.current_thinking = ""
+
-    
+        self.current_content = ""
+
+    def _handle_agent_end(self, data):
+        self._flush_merged_now()
+
     def _handle_tool_execution_start(self, data):
-        """Handle tool execution start event - logged by agent_stream.py"""
         pass
-    
+
     def _handle_tool_execution_end(self, data):
-        """Handle tool execution end event - logged by agent_stream.py"""
         pass
-    
+
     def _send_to_channel(self, message):
-        """
-        Try to send intermediate message to channel.
-        Skipped in SSE mode because thinking text is already streamed via on_event.
-        """
         if self.context and self.context.get("on_event"):
             return
+        if not self.channel:
+            return
+
+        if not self._is_weixin:
+            self._do_send(message)
+            return
+
+        if self._thinking_sent_count < WEIXIN_THINKING_INSTANT_MAX:
+            self._do_send(message)
+            self._thinking_sent_count += 1
+            return
+
+        self._merged_buf.append(message)
+
+    def _flush_merged_now(self):
+        if not self._merged_buf:
+            return
+        merged = "\n\n".join(self._merged_buf)
+        count = len(self._merged_buf)
+        self._merged_buf = []
+        logger.debug(f"[AgentEventHandler] Flushing {count} merged thinking msgs, len={len(merged)}")
+        self._do_send(merged)
+        self._thinking_sent_count += 1
+
+    def _do_send(self, message):
+        try:
+            from bridge.reply import Reply, ReplyType
+            reply = Reply(ReplyType.TEXT, message)
+            self.channel._send(reply, self.context)
+        except Exception as e:
+            logger.debug(f"[AgentEventHandler] Failed to send to channel: {e}")
 
-        if self.channel:
-            try:
-                from bridge.reply import Reply, ReplyType
-                reply = Reply(ReplyType.TEXT, message)
-                self.channel._send(reply, self.context)
-            except Exception as e:
-                logger.debug(f"[AgentEventHandler] Failed to send to channel: {e}")
-    
     def log_summary(self):
-        """Log execution summary - simplified"""
-        # Summary removed as per user request
-        # Real-time logging during execution is sufficient
         pass

bridge/agent_initializer.py

@@ -5,6 +5,7 @@ Agent Initializer - Handles agent initialization logic
 import os
 import asyncio
 import datetime
+import threading
 import time
 from typing import Optional, List
 
@@ -13,6 +14,9 @@ from agent.tools import ToolManager
 from common.log import logger
 from common.utils import expand_path
 
+# Module-level lock to serialize scheduler init across concurrent sessions
+_scheduler_init_lock = threading.Lock()
+
 
 class AgentInitializer:
     """
@@ -77,10 +81,6 @@ class AgentInitializer:
         # Initialize skill manager
         skill_manager = self._initialize_skill_manager(workspace_root, session_id)
         
-        # Check if first conversation
-        from agent.prompt.workspace import is_first_conversation, mark_conversation_started
-        is_first = is_first_conversation(workspace_root)
-        
         # Build system prompt
         prompt_builder = PromptBuilder(workspace_dir=workspace_root, language="zh")
         runtime_info = self._get_runtime_info(workspace_root)
@@ -91,12 +91,8 @@ class AgentInitializer:
             skill_manager=skill_manager,
             memory_manager=memory_manager,
             runtime_info=runtime_info,
-            is_first_conversation=is_first
         )
         
-        if is_first:
-            mark_conversation_started(workspace_root)
-        
         # Get cost control parameters
         from config import conf
         max_steps = conf().get("agent_max_steps", 20)
@@ -115,14 +111,19 @@ class AgentInitializer:
             runtime_info=runtime_info  # Pass runtime_info for dynamic time updates
         )
         
-        # Attach memory manager
+        # Attach memory manager and share LLM model for summarization
         if memory_manager:
             agent.memory_manager = memory_manager
+            if hasattr(agent, 'model') and agent.model:
+                memory_manager.flush_manager.llm_model = agent.model
 
         # Restore persisted conversation history for this session
         if session_id:
             self._restore_conversation_history(agent, session_id)
 
+        # Start daily memory flush timer (once, on first agent init regardless of session)
+        self._start_daily_flush_timer()
+
         return agent
 
     def _restore_conversation_history(self, agent, session_id: str) -> None:
@@ -130,8 +131,14 @@ class AgentInitializer:
         Load persisted conversation messages from SQLite and inject them
         into the agent's in-memory message list.
 
-        Only runs when conversation persistence is enabled (default: True).
+        Only user text and assistant text are restored. Tool call chains
-        Respects agent_max_context_turns to limit how many turns are loaded.
+        (tool_use / tool_result) are stripped out because:
+        1. They are intermediate process, the value is already in the final
+           assistant text reply.
+        2. They consume massive context tokens (often 80%+ of history).
+        3. Different models have incompatible tool message formats, so
+           restoring tool chains across model switches causes 400 errors.
+        4. Eliminates the entire class of tool_use/tool_result pairing bugs.
         """
         from config import conf
         if not conf().get("conversation_persistence", True):
@@ -140,25 +147,107 @@ class AgentInitializer:
         try:
             from agent.memory import get_conversation_store
             store = get_conversation_store()
-            # On restore, load at most min(10, max_turns // 2) turns so that
+            max_turns = conf().get("agent_max_context_turns", 20)
-            # a long-running session does not immediately fill the context window
+            # Scheduler tasks run on a stable isolated session per task and
-            # after a restart.  The full max_turns budget is reserved for the
+            # can fire many times a day; a smaller restore window keeps prompt
-            # live conversation that follows.
+            # cost bounded while still letting the agent see "last few" runs
-            max_turns = conf().get("agent_max_context_turns", 30)
+            # for trend / dedup style logic. Regular chat sessions keep the
-            restore_turns = max(4, max_turns // 5)
+            # original heuristic so user dialogues feel continuous.
+            if session_id.startswith("scheduler_"):
+                restore_turns = max(1, max_turns // 5)
+            else:
+                restore_turns = max(3, max_turns // 6)
             saved = store.load_messages(session_id, max_turns=restore_turns)
             if saved:
-                with agent.messages_lock:
+                filtered = self._filter_text_only_messages(saved)
-                    agent.messages = saved
+                if filtered:
-                logger.debug(
+                    with agent.messages_lock:
-                    f"[AgentInitializer] Restored {len(saved)} messages "
+                        agent.messages = filtered
-                    f"({restore_turns} turns cap) for session={session_id}"
+                    logger.debug(
-                )
+                        f"[AgentInitializer] Restored {len(filtered)} text messages "
+                        f"(from {len(saved)} total, {restore_turns} turns cap) "
+                        f"for session={session_id}"
+                    )
         except Exception as e:
             logger.warning(
                 f"[AgentInitializer] Failed to restore conversation history for "
                 f"session={session_id}: {e}"
             )
+
+    @staticmethod
+    def _filter_text_only_messages(messages: list) -> list:
+        """
+        Extract clean user/assistant turn pairs from raw message history.
+
+        Groups messages into turns (each starting with a real user query),
+        then keeps only:
+        - The first user text in each turn (the actual user input)
+        - The last assistant text in each turn (the final answer)
+
+        All tool_use, tool_result, intermediate assistant thoughts, and
+        internal hint messages injected by the agent loop are discarded.
+        """
+
+        def _extract_text(content) -> str:
+            if isinstance(content, str):
+                return content.strip()
+            if isinstance(content, list):
+                parts = [
+                    b.get("text", "")
+                    for b in content
+                    if isinstance(b, dict) and b.get("type") == "text"
+                ]
+                return "\n".join(p for p in parts if p).strip()
+            return ""
+
+        def _is_real_user_msg(msg: dict) -> bool:
+            """True for actual user input, False for tool_result or internal hints."""
+            if msg.get("role") != "user":
+                return False
+            content = msg.get("content")
+            if isinstance(content, list):
+                has_tool_result = any(
+                    isinstance(b, dict) and b.get("type") == "tool_result"
+                    for b in content
+                )
+                if has_tool_result:
+                    return False
+            text = _extract_text(content)
+            return bool(text)
+
+        # Group into turns: each turn starts with a real user message
+        turns = []
+        current_turn = None
+        for msg in messages:
+            if _is_real_user_msg(msg):
+                if current_turn is not None:
+                    turns.append(current_turn)
+                current_turn = {"user": msg, "assistants": []}
+            elif current_turn is not None and msg.get("role") == "assistant":
+                text = _extract_text(msg.get("content"))
+                if text:
+                    current_turn["assistants"].append(text)
+        if current_turn is not None:
+            turns.append(current_turn)
+
+        # Build result: one user msg + one assistant msg per turn
+        filtered = []
+        for turn in turns:
+            user_text = _extract_text(turn["user"].get("content"))
+            if not user_text:
+                continue
+            filtered.append({
+                "role": "user",
+                "content": [{"type": "text", "text": user_text}]
+            })
+            if turn["assistants"]:
+                final_reply = turn["assistants"][-1]
+                filtered.append({
+                    "role": "assistant",
+                    "content": [{"type": "text", "text": final_reply}]
+                })
+
+        return filtered
     
     def _load_env_file(self):
         """Load environment variables from .env file"""
@@ -183,37 +272,19 @@ class AgentInitializer:
         memory_tools = []
         
         try:
-            from agent.memory import MemoryManager, MemoryConfig, create_embedding_provider
+            from agent.memory import MemoryManager, MemoryConfig
             from agent.tools import MemorySearchTool, MemoryGetTool
             from config import conf
-            
+
-            # Get OpenAI config
-            openai_api_key = conf().get("open_ai_api_key", "")
-            openai_api_base = conf().get("open_ai_api_base", "")
-            
-            # Initialize embedding provider
-            embedding_provider = None
-            if openai_api_key and openai_api_key not in ["", "YOUR API KEY", "YOUR_API_KEY"]:
-                try:
-                    embedding_provider = create_embedding_provider(
-                        provider="openai",
-                        model="text-embedding-3-small",
-                        api_key=openai_api_key,
-                        api_base=openai_api_base or "https://api.openai.com/v1"
-                    )
-                    if session_id is None:
-                        logger.info("[AgentInitializer] OpenAI embedding initialized")
-                except Exception as e:
-                    logger.warning(f"[AgentInitializer] OpenAI embedding failed: {e}")
-            
-            # Create memory manager
             memory_config = MemoryConfig(workspace_root=workspace_root)
+
+            embedding_provider = self._init_embedding_provider(
+                memory_config, session_id=session_id
+            )
+
             memory_manager = MemoryManager(memory_config, embedding_provider=embedding_provider)
-            
-            # Sync memory
             self._sync_memory(memory_manager, session_id)
-            
+
-            # Create memory tools
             memory_tools = [
                 MemorySearchTool(memory_manager),
                 MemoryGetTool(memory_manager)
@@ -226,7 +297,21 @@ class AgentInitializer:
             logger.warning(f"[AgentInitializer] Memory system not available: {e}")
         
         return memory_manager, memory_tools
-    
+
+    def _init_embedding_provider(self, memory_config, session_id: Optional[str] = None):
+        """
+        Initialize the embedding provider for memory.
+
+        Delegates to the shared factory so agent init, knowledge sync and
+        index rebuild all select the same provider:
+          A. Default (no `embedding_provider` in config.json):
+             Auto-init OpenAI -> LinkAI fallback.
+          B. Explicit (`embedding_provider` is set):
+             Initialize the requested vendor.
+        """
+        from agent.memory import create_default_embedding_provider
+        return create_default_embedding_provider()
+
     def _sync_memory(self, memory_manager, session_id: Optional[str] = None):
         """Sync memory database"""
         try:
@@ -262,7 +347,15 @@ class AgentInitializer:
                 if tool_name == "web_search":
                     from agent.tools.web_search.web_search import WebSearch
                     if not WebSearch.is_available():
-                        logger.debug("[AgentInitializer] WebSearch skipped - no BOCHA_API_KEY or LINKAI_API_KEY")
+                        logger.debug("[AgentInitializer] WebSearch skipped - no search provider configured")
+                        continue
+
+                # Skip evolution_undo when self-evolution is disabled: with no
+                # evolution there is nothing to roll back, so the tool is dead weight.
+                if tool_name == "evolution_undo":
+                    from agent.evolution.config import get_evolution_config
+                    if not get_evolution_config().enabled:
+                        logger.debug("[AgentInitializer] evolution_undo skipped - self-evolution disabled")
                         continue
 
                 # Special handling for EnvConfig tool
@@ -273,16 +366,33 @@ class AgentInitializer:
                     tool = tool_manager.create_tool(tool_name)
 
                 if tool:
-                    # Apply workspace config to file operation tools
+                    # Apply workspace config to file operation tools.
-                    if tool_name in ['read', 'write', 'edit', 'bash', 'grep', 'find', 'ls']:
+                    # Merge into the existing tool.config (set by ToolManager from
-                        tool.config = file_config
+                    # config.json's `tools.<name>` section) instead of replacing
-                        tool.cwd = file_config.get("cwd", getattr(tool, 'cwd', None))
+                    # it, otherwise per-tool user configs (e.g. browser.cdp_endpoint)
-                        if 'memory_manager' in file_config:
+                    # would be silently dropped.
-                            tool.memory_manager = file_config['memory_manager']
+                    if tool_name in ['read', 'write', 'edit', 'bash', 'grep', 'find', 'ls', 'web_fetch', 'send', 'browser']:
+                        merged_config = dict(getattr(tool, 'config', None) or {})
+                        merged_config.update(file_config)
+                        tool.config = merged_config
+                        tool.cwd = merged_config.get("cwd", getattr(tool, 'cwd', None))
+                        if 'memory_manager' in merged_config:
+                            tool.memory_manager = merged_config['memory_manager']
                     tools.append(tool)
             except Exception as e:
                 logger.warning(f"[AgentInitializer] Failed to load tool {tool_name}: {e}")
-        
+
+        # Add MCP tools (snapshot to avoid races with the background loader)
+        mcp_tools_snapshot = list(tool_manager._mcp_tool_instances.items())
+        if mcp_tools_snapshot:
+            for _, mcp_tool in mcp_tools_snapshot:
+                tools.append(mcp_tool)
+            if session_id is None:
+                names = [name for name, _ in mcp_tools_snapshot]
+                logger.info(
+                    f"[AgentInitializer] Added {len(names)} MCP tool(s): {names}"
+                )
+
         # Add memory tools
         if memory_tools:
             tools.extend(memory_tools)
@@ -295,16 +405,23 @@ class AgentInitializer:
         return tools
     
     def _initialize_scheduler(self, tools: List, session_id: Optional[str] = None):
-        """Initialize scheduler service if needed"""
+        """Initialize scheduler service if needed.
+
+        Serialize the check-and-set under a module-level lock so concurrent
+        first-time session inits cannot each create a new SchedulerService
+        (which would leak background scanning threads).
+        """
         if not self.agent_bridge.scheduler_initialized:
-            try:
+            with _scheduler_init_lock:
-                from agent.tools.scheduler.integration import init_scheduler
+                if not self.agent_bridge.scheduler_initialized:
-                if init_scheduler(self.agent_bridge):
+                    try:
-                    self.agent_bridge.scheduler_initialized = True
+                        from agent.tools.scheduler.integration import init_scheduler
-                    if session_id is None:
+                        if init_scheduler(self.agent_bridge):
-                        logger.info("[AgentInitializer] Scheduler service initialized")
+                            self.agent_bridge.scheduler_initialized = True
-            except Exception as e:
+                            if session_id is None:
-                logger.warning(f"[AgentInitializer] Failed to initialize scheduler: {e}")
+                                logger.info("[AgentInitializer] Scheduler service initialized")
+                    except Exception as e:
+                        logger.warning(f"[AgentInitializer] Failed to initialize scheduler: {e}")
         
         # Inject scheduler dependencies
         if self.agent_bridge.scheduler_initialized:
@@ -360,21 +477,34 @@ class AgentInitializer:
             except Exception:
                 timezone_name = "UTC"
             
-            # Chinese weekday mapping
+            # Weekday: English name in en, Chinese mapping otherwise
-            weekday_map = {
+            weekday_en = now.strftime("%A")
-                'Monday': '星期一', 'Tuesday': '星期二', 'Wednesday': '星期三',
+            try:
-                'Thursday': '星期四', 'Friday': '星期五', 'Saturday': '星期六', 'Sunday': '星期日'
+                from common import i18n
-            }
+                is_en = i18n.get_language() == "en"
-            weekday_zh = weekday_map.get(now.strftime("%A"), now.strftime("%A"))
+            except Exception:
-            
+                is_en = False
+            if is_en:
+                weekday = weekday_en
+            else:
+                weekday_map = {
+                    'Monday': '星期一', 'Tuesday': '星期二', 'Wednesday': '星期三',
+                    'Thursday': '星期四', 'Friday': '星期五', 'Saturday': '星期六', 'Sunday': '星期日'
+                }
+                weekday = weekday_map.get(weekday_en, weekday_en)
+
             return {
                 'time': now.strftime("%Y-%m-%d %H:%M:%S"),
-                'weekday': weekday_zh,
+                'weekday': weekday,
                 'timezone': timezone_name
             }
         
+        def get_model():
+            """Get current model name dynamically from config"""
+            return conf().get("model", "unknown")
+
         return {
-            "model": conf().get("model", "unknown"),
+            "_get_model": get_model,
             "workspace": workspace_root,
             "channel": ", ".join(conf().get("channel_type")) if isinstance(conf().get("channel_type"), list) else conf().get("channel_type", "unknown"),
             "_get_current_time": get_current_time  # Dynamic time function
@@ -394,7 +524,7 @@ class AgentInitializer:
         
         env_file = expand_path("~/.cow/.env")
         
-        # Read existing env vars
+        # Read existing env vars (key -> value)
         existing_env_vars = {}
         if os.path.exists(env_file):
             try:
@@ -402,35 +532,126 @@ class AgentInitializer:
                     for line in f:
                         line = line.strip()
                         if line and not line.startswith('#') and '=' in line:
-                            key, _ = line.split('=', 1)
+                            key, val = line.split('=', 1)
-                            existing_env_vars[key.strip()] = True
+                            existing_env_vars[key.strip()] = val.strip()
             except Exception as e:
                 logger.warning(f"[AgentInitializer] Failed to read .env file: {e}")
         
-        # Check which keys need migration
+        # Sync config.json values into .env (add/update/remove)
-        keys_to_migrate = {}
+        updated = False
         for config_key, env_key in key_mapping.items():
-            if env_key in existing_env_vars:
+            raw = conf().get(config_key, "")
-                continue
+            value = raw.strip() if raw else ""
-            value = conf().get(config_key, "")
+            old_value = existing_env_vars.get(env_key)
-            if value and value.strip():
+
-                keys_to_migrate[env_key] = value.strip()
+            if value:
-        
+                if old_value == value:
-        # Write new keys
+                    continue
-        if keys_to_migrate:
+                existing_env_vars[env_key] = value
+                os.environ[env_key] = value
+                updated = True
+            else:
+                if old_value is None:
+                    continue
+                existing_env_vars.pop(env_key, None)
+                os.environ.pop(env_key, None)
+                updated = True
+
+        if updated:
             try:
                 env_dir = os.path.dirname(env_file)
-                if not os.path.exists(env_dir):
+                os.makedirs(env_dir, exist_ok=True)
-                    os.makedirs(env_dir, exist_ok=True)
+
-                if not os.path.exists(env_file):
+                # Rewrite the entire .env file to ensure consistency
-                    open(env_file, 'a').close()
+                with open(env_file, 'w', encoding='utf-8') as f:
-                
+                    f.write('# Environment variables for agent\n')
-                with open(env_file, 'a', encoding='utf-8') as f:
+                    f.write('# Auto-managed - synced from config.json on startup\n\n')
-                    f.write('\n# Auto-migrated from config.json\n')
+                    for key, value in sorted(existing_env_vars.items()):
-                    for key, value in keys_to_migrate.items():
                         f.write(f'{key}={value}\n')
-                        os.environ[key] = value
+
-                
+                logger.info(f"[AgentInitializer] Synced API keys from config.json to .env")
-                logger.info(f"[AgentInitializer] Migrated {len(keys_to_migrate)} API keys to .env: {list(keys_to_migrate.keys())}")
             except Exception as e:
-                logger.warning(f"[AgentInitializer] Failed to migrate API keys: {e}")
+                logger.warning(f"[AgentInitializer] Failed to sync API keys: {e}")
+
+    def _start_daily_flush_timer(self):
+        """Start a background thread that flushes all agents' memory daily at 23:55."""
+        if getattr(self.agent_bridge, '_daily_flush_started', False):
+            return
+        self.agent_bridge._daily_flush_started = True
+
+        import threading
+
+        def _daily_flush_loop():
+            import random
+            last_run_date = None  # Track last successful run date to prevent same-day re-trigger
+            while True:
+                try:
+                    now = datetime.datetime.now()
+                    jitter_min = random.randint(50, 55)
+                    jitter_sec = random.randint(0, 59)
+                    target = now.replace(hour=23, minute=jitter_min, second=jitter_sec, microsecond=0)
+                    # Always schedule for tomorrow if we already ran today, or if target time has passed
+                    if target <= now or (last_run_date == now.date()):
+                        target += datetime.timedelta(days=1)
+                    wait_seconds = (target - now).total_seconds()
+                    logger.info(f"[DailyFlush] Next flush at {target.strftime('%Y-%m-%d %H:%M:%S')} (in {wait_seconds/3600:.1f}h)")
+                    time.sleep(wait_seconds)
+
+                    self._flush_all_agents()
+                    last_run_date = datetime.datetime.now().date()
+                except Exception as e:
+                    logger.warning(f"[DailyFlush] Error in daily flush loop: {e}")
+                    time.sleep(3600)
+
+        t = threading.Thread(target=_daily_flush_loop, daemon=True)
+        t.start()
+
+    def _flush_all_agents(self):
+        """Flush memory for all active agent sessions, then run Deep Dream."""
+        agents = []
+        if self.agent_bridge.default_agent:
+            agents.append(("default", self.agent_bridge.default_agent))
+        for sid, agent in self.agent_bridge.agents.items():
+            agents.append((sid, agent))
+
+        if not agents:
+            return
+
+        # Phase 1: flush daily summaries
+        flushed = 0
+        flush_threads = []
+        dream_candidate = None
+        for label, agent in agents:
+            try:
+                if not agent.memory_manager:
+                    continue
+                with agent.messages_lock:
+                    messages = list(agent.messages)
+                if not messages:
+                    continue
+                result = agent.memory_manager.flush_manager.create_daily_summary(messages)
+                if result:
+                    flushed += 1
+                    t = agent.memory_manager.flush_manager._last_flush_thread
+                    if t:
+                        flush_threads.append(t)
+                if dream_candidate is None:
+                    dream_candidate = agent.memory_manager.flush_manager
+            except Exception as e:
+                logger.warning(f"[DailyFlush] Failed for session {label}: {e}")
+
+        if flushed:
+            logger.info(f"[DailyFlush] Flushed {flushed}/{len(agents)} agent session(s)")
+
+        # Wait for all flush threads to finish before dreaming
+        for t in flush_threads:
+            t.join(timeout=60)
+
+        # Phase 2: Deep Dream — distill daily memories → MEMORY.md + dream diary
+        if dream_candidate:
+            try:
+                result = dream_candidate.deep_dream()
+                if result:
+                    logger.info("[DeepDream] Memory distillation completed successfully")
+            except Exception as e:
+                logger.warning(f"[DeepDream] Failed: {e}")

bridge/bridge.py

@@ -13,8 +13,10 @@ from voice.factory import create_voice
 class Bridge(object):
     def __init__(self):
         self.btype = {
-            "chat": const.CHATGPT,
+            "chat": const.OPENAI,
-            "voice_to_text": conf().get("voice_to_text", "openai"),
+            # Empty `voice_to_text` (the default in new configs) triggers
+            # the auto-pick below — see _auto_pick_voice_to_text for order.
+            "voice_to_text": conf().get("voice_to_text") or self._auto_pick_voice_to_text(),
             "text_to_voice": conf().get("text_to_voice", "google"),
             "translate": conf().get("translate", "baidu"),
         }
@@ -39,11 +41,8 @@ class Bridge(object):
                 self.btype["chat"] = const.BAIDU
             if model_type in ["xunfei"]:
                 self.btype["chat"] = const.XUNFEI
-            if model_type in [const.QWEN]:
+            if model_type in [const.QWEN, const.QWEN_TURBO, const.QWEN_PLUS, const.QWEN_MAX]:
-                self.btype["chat"] = const.QWEN
-            if model_type in [const.QWEN_TURBO, const.QWEN_PLUS, const.QWEN_MAX]:
                 self.btype["chat"] = const.QWEN_DASHSCOPE
-            # Support Qwen3 and other DashScope models
             if model_type and (model_type.startswith("qwen") or model_type.startswith("qwq") or model_type.startswith("qvq")):
                 self.btype["chat"] = const.QWEN_DASHSCOPE
             if model_type and model_type.startswith("gemini"):
@@ -61,6 +60,18 @@ class Bridge(object):
             if model_type and model_type.startswith("doubao"):
                 self.btype["chat"] = const.DOUBAO
 
+            if model_type and model_type.startswith("deepseek"):
+                self.btype["chat"] = const.DEEPSEEK
+
+            # 小米 MiMo 系列模型，全部以 mimo- 开头
+            if model_type and model_type.startswith("mimo-"):
+                self.btype["chat"] = const.MIMO
+
+            if model_type and isinstance(model_type, str):
+                lowered_model_type = model_type.lower()
+                if lowered_model_type == const.QIANFAN or lowered_model_type.startswith("ernie"):
+                    self.btype["chat"] = const.QIANFAN
+
             if model_type in [const.MODELSCOPE]:
                 self.btype["chat"] = const.MODELSCOPE
             
@@ -79,6 +90,46 @@ class Bridge(object):
         self.chat_bots = {}
         self._agent_bridge = None
 
+    def refresh_voice(self):
+        """Re-read voice_to_text / text_to_voice from config and drop the
+        cached voice bots so the next call picks up the new provider.
+        Used by the web console after the user edits voice settings.
+        Does NOT touch the agent_bridge / agent state.
+        """
+        new_v2t = conf().get("voice_to_text") or self._auto_pick_voice_to_text()
+        new_t2v = conf().get("text_to_voice", "google")
+        if conf().get("use_linkai") and conf().get("linkai_api_key"):
+            if not conf().get("voice_to_text") or conf().get("voice_to_text") in ["openai"]:
+                new_v2t = const.LINKAI
+            if not conf().get("text_to_voice") or conf().get("text_to_voice") in ["openai", const.TTS_1, const.TTS_1_HD]:
+                new_t2v = const.LINKAI
+        self.btype["voice_to_text"] = new_v2t
+        self.btype["text_to_voice"] = new_t2v
+        self.bots.pop("voice_to_text", None)
+        self.bots.pop("text_to_voice", None)
+        logger.info(f"[Bridge] voice refreshed: voice_to_text={new_v2t}, text_to_voice={new_t2v}")
+
+    @staticmethod
+    def _auto_pick_voice_to_text() -> str:
+        """Pick an ASR provider by configured api keys when voice_to_text is
+        unset. Order matches the web console: openai → dashscope → zhipu →
+        linkai. Falls back to 'openai' when nothing is configured so the
+        original "missing key" error is preserved.
+        """
+        def has(k: str) -> bool:
+            v = (conf().get(k) or "").strip()
+            return v != "" and v not in ("YOUR API KEY", "YOUR_API_KEY")
+
+        for key, provider in (
+            ("open_ai_api_key", "openai"),
+            ("dashscope_api_key", "dashscope"),
+            ("zhipu_ai_api_key", "zhipu"),
+            ("linkai_api_key", "linkai"),
+        ):
+            if has(key):
+                return provider
+        return "openai"
+
     # 模型对应的接口
     def get_bot(self, typename):
         if self.bots.get(typename) is None:

channel/channel.py

@@ -13,12 +13,38 @@ class Channel(object):
     channel_type = ""
     NOT_SUPPORT_REPLYTYPE = [ReplyType.VOICE, ReplyType.IMAGE]
 
+    def __init__(self):
+        import threading
+        self._startup_event = threading.Event()
+        self._startup_error = None
+        self.cloud_mode = False  # set to True by ChannelManager when running with cloud client
+
     def startup(self):
         """
         init channel
         """
         raise NotImplementedError
 
+    def report_startup_success(self):
+        self._startup_error = None
+        self._startup_event.set()
+
+    def report_startup_error(self, error: str):
+        self._startup_error = error
+        self._startup_event.set()
+
+    def wait_startup(self, timeout: float = 3) -> (bool, str):
+        """
+        Wait for channel startup result.
+        Returns (success: bool, error_msg: str).
+        """
+        ready = self._startup_event.wait(timeout=timeout)
+        if not ready:
+            return True, ""
+        if self._startup_error:
+            return False, self._startup_error
+        return True, ""
+
     def stop(self):
         """
         stop channel gracefully, called before restart
@@ -47,7 +73,7 @@ class Channel(object):
         Build reply content, using agent if enabled in config
         """
         # Check if agent mode is enabled
-        use_agent = conf().get("agent", False)
+        use_agent = conf().get("agent", True)
 
         if use_agent:
             try:

channel/channel_factory.py

@@ -12,16 +12,7 @@ def create_channel(channel_type) -> Channel:
     :return: channel instance
     """
     ch = Channel()
-    if channel_type == "wx":
+    if channel_type == "terminal":
-        from channel.wechat.wechat_channel import WechatChannel
-        ch = WechatChannel()
-    elif channel_type == "wxy":
-        from channel.wechat.wechaty_channel import WechatyChannel
-        ch = WechatyChannel()
-    elif channel_type == "wcf":
-        from channel.wechat.wcf_channel import WechatfChannel
-        ch = WechatfChannel()
-    elif channel_type == "terminal":
         from channel.terminal.terminal_channel import TerminalChannel
         ch = TerminalChannel()
     elif channel_type == 'web':
@@ -36,15 +27,34 @@ def create_channel(channel_type) -> Channel:
     elif channel_type == "wechatcom_app":
         from channel.wechatcom.wechatcomapp_channel import WechatComAppChannel
         ch = WechatComAppChannel()
-    elif channel_type == "wework":
+    elif channel_type == const.WECHAT_KF:
-        from channel.wework.wework_channel import WeworkChannel
+        from channel.wechat_kf.wechat_kf_channel import WechatKfChannel
-        ch = WeworkChannel()
+        ch = WechatKfChannel()
     elif channel_type == const.FEISHU:
         from channel.feishu.feishu_channel import FeiShuChanel
         ch = FeiShuChanel()
     elif channel_type == const.DINGTALK:
         from channel.dingtalk.dingtalk_channel import DingTalkChanel
         ch = DingTalkChanel()
+    elif channel_type == const.WECOM_BOT:
+        from channel.wecom_bot.wecom_bot_channel import WecomBotChannel
+        ch = WecomBotChannel()
+    elif channel_type == const.QQ:
+        from channel.qq.qq_channel import QQChannel
+        ch = QQChannel()
+    elif channel_type == const.TELEGRAM:
+        from channel.telegram.telegram_channel import TelegramChannel
+        ch = TelegramChannel()
+    elif channel_type == const.SLACK:
+        from channel.slack.slack_channel import SlackChannel
+        ch = SlackChannel()
+    elif channel_type == const.DISCORD:
+        from channel.discord.discord_channel import DiscordChannel
+        ch = DiscordChannel()
+    elif channel_type in (const.WEIXIN, "wx"):
+        from channel.weixin.weixin_channel import WeixinChannel
+        ch = WeixinChannel()
+        channel_type = const.WEIXIN
     else:
         raise RuntimeError
     ch.channel_type = channel_type

channel/chat_channel.py

@@ -10,6 +10,7 @@ from bridge.reply import *
 from channel.channel import Channel
 from common.dequeue import Dequeue
 from common import memory
+from common.i18n import t as _t
 from plugins import *
 
 try:
@@ -26,6 +27,7 @@ class ChatChannel(Channel):
     user_id = None  # 登录的用户id
 
     def __init__(self):
+        super().__init__()
         # Instance-level attributes so each channel subclass has its own
         # independent session queue and lock. Previously these were class-level,
         # which caused contexts from one channel (e.g. Feishu) to be consumed
@@ -170,7 +172,13 @@ class ChatChannel(Channel):
             if "desire_rtype" not in context and conf().get("always_reply_voice") and ReplyType.VOICE not in self.NOT_SUPPORT_REPLYTYPE:
                 context["desire_rtype"] = ReplyType.VOICE
         elif context.type == ContextType.VOICE:
-            if "desire_rtype" not in context and conf().get("voice_reply_voice") and ReplyType.VOICE not in self.NOT_SUPPORT_REPLYTYPE:
+            # Voice input replies with voice when either voice_reply_voice
+            # (mirror voice) or the global always_reply_voice toggle is on.
+            if (
+                "desire_rtype" not in context
+                and (conf().get("voice_reply_voice") or conf().get("always_reply_voice"))
+                and ReplyType.VOICE not in self.NOT_SUPPORT_REPLYTYPE
+            ):
                 context["desire_rtype"] = ReplyType.VOICE
         return context
 
@@ -258,11 +266,13 @@ class ChatChannel(Channel):
                 if reply.type in self.NOT_SUPPORT_REPLYTYPE:
                     logger.error("[chat_channel]reply type not support: " + str(reply.type))
                     reply.type = ReplyType.ERROR
-                    reply.content = "不支持发送的消息类型: " + str(reply.type)
+                    reply.content = _t("不支持发送的消息类型: ", "Unsupported message type: ") + str(reply.type)
 
                 if reply.type == ReplyType.TEXT:
                     reply_text = reply.content
                     if desire_rtype == ReplyType.VOICE and ReplyType.VOICE not in self.NOT_SUPPORT_REPLYTYPE:
+                        # Preserve original text for the "text-then-voice" pattern in _send_reply.
+                        context["voice_reply_text"] = reply.content
                         reply = super().build_text_to_voice(reply.content)
                         return self._decorate_reply(context, reply)
                     if context.get("isgroup", False):
@@ -296,8 +306,12 @@ class ChatChannel(Channel):
                 logger.debug("[chat_channel] sending reply: {}, context: {}".format(reply, context))
                 
                 # 如果是文本回复，尝试提取并发送图片
-                if reply.type == ReplyType.TEXT:
+                # Web channel renders images/videos inline via renderMarkdown,
+                # so skip the extract-and-send step to avoid duplicate media.
+                if reply.type == ReplyType.TEXT and context.get("channel_type") != "web":
                     self._extract_and_send_images(reply, context)
+                elif reply.type == ReplyType.TEXT:
+                    self._send(reply, context)
                 # 如果是图片回复但带有文本内容，先发文本再发图片
                 elif reply.type == ReplyType.IMAGE_URL and hasattr(reply, 'text_content') and reply.text_content:
                     # 先发送文本
@@ -306,6 +320,15 @@ class ChatChannel(Channel):
                     # 短暂延迟后发送图片
                     time.sleep(0.3)
                     self._send(reply, context)
+                # Send text bubble before voice, unless channel already streamed
+                # the text (feishu) or natively renders STT under the voice (wechatcom).
+                elif reply.type == ReplyType.VOICE and context.get("voice_reply_text") \
+                        and not context.get("feishu_streamed") \
+                        and context.get("channel_type") not in ("wechatcom_app",):
+                    text_reply = Reply(ReplyType.TEXT, context.get("voice_reply_text"))
+                    self._send(text_reply, context)
+                    time.sleep(0.3)
+                    self._send(reply, context)
                 else:
                     self._send(reply, context)
     
@@ -346,38 +369,30 @@ class ChatChannel(Channel):
         if media_items:
             logger.info(f"[chat_channel] Extracted {len(media_items)} media item(s) from reply")
             
-            # 先发送文本（保持原文本不变）
+            # Send text first (the frontend will embed video players via renderMarkdown).
             logger.info(f"[chat_channel] Sending text content before media: {reply.content[:100]}...")
             self._send(reply, context)
             logger.info(f"[chat_channel] Text sent, now sending {len(media_items)} media item(s)")
             
-            # 然后逐个发送媒体文件
             for i, (url, media_type) in enumerate(media_items):
                 try:
-                    # 判断是本地文件还是URL
+                    # Determine whether it is a remote URL or a local file.
                     if url.startswith(('http://', 'https://')):
-                        # 网络资源
                         if media_type == 'video':
-                            # 视频使用 FILE 类型发送
                             media_reply = Reply(ReplyType.FILE, url)
                             media_reply.file_name = os.path.basename(url)
                         else:
-                            # 图片使用 IMAGE_URL 类型
                             media_reply = Reply(ReplyType.IMAGE_URL, url)
                     elif os.path.exists(url):
-                        # 本地文件
                         if media_type == 'video':
-                            # 视频使用 FILE 类型，转换为 file:// URL
                             media_reply = Reply(ReplyType.FILE, f"file://{url}")
                             media_reply.file_name = os.path.basename(url)
                         else:
-                            # 图片使用 IMAGE_URL 类型，转换为 file:// URL
                             media_reply = Reply(ReplyType.IMAGE_URL, f"file://{url}")
                     else:
                         logger.warning(f"[chat_channel] Media file not found or invalid URL: {url}")
                         continue
                     
-                    # 发送媒体文件（添加小延迟避免频率限制）
                     if i > 0:
                         time.sleep(0.5)
                     self._send(media_reply, context)
@@ -424,19 +439,55 @@ class ChatChannel(Channel):
 
         return func
 
+    # Chat commands that must bypass the per-session serial queue,
+    # otherwise /cancel would queue behind the task it tries to cancel.
+    # Use /cancel (not /stop) to avoid colliding with `cow stop` CLI.
+    _BYPASS_QUEUE_COMMANDS = ("/cancel",)
+
     def produce(self, context: Context):
         session_id = context["session_id"]
+
+        # Fast path: /cancel must not enter the queue.
+        if context.type == ContextType.TEXT and context.content:
+            stripped = context.content.strip().lower()
+            if stripped in self._BYPASS_QUEUE_COMMANDS:
+                self._handle_cancel_command(context, session_id)
+                return
+
         with self.lock:
             if session_id not in self.sessions:
                 self.sessions[session_id] = [
                     Dequeue(),
-                    threading.BoundedSemaphore(conf().get("concurrency_in_session", 4)),
+                    threading.BoundedSemaphore(conf().get("concurrency_in_session", 1)),
                 ]
             if context.type == ContextType.TEXT and context.content.startswith("#"):
                 self.sessions[session_id][0].putleft(context)  # 优先处理管理命令
             else:
                 self.sessions[session_id][0].put(context)
 
+    def _handle_cancel_command(self, context: Context, session_id: str) -> None:
+        """Cancel any in-flight agent run for *session_id* and reply inline.
+
+        Runs synchronously on the caller's thread. Reply is sent through
+        _send_reply so plugins (e.g. logging) still observe it.
+        """
+        try:
+            from agent.protocol import get_cancel_registry
+            from bridge.reply import Reply, ReplyType
+
+            cancelled = get_cancel_registry().cancel_session(session_id)
+            text = (
+                _t("🛑 已中止", "🛑 Cancelled")
+                if cancelled > 0
+                else _t("当前没有可中止的任务。", "Nothing to cancel.")
+            )
+            logger.info(
+                f"[chat_channel] /cancel fast-path: session={session_id}, cancelled={cancelled}"
+            )
+            self._send_reply(context, Reply(ReplyType.TEXT, text))
+        except Exception as e:
+            logger.warning(f"[chat_channel] /cancel fast-path failed: {e}")
+
     # 消费者函数，单独线程，用于从消息队列中取出消息并处理
     def consume(self):
         while True:
@@ -468,7 +519,10 @@ class ChatChannel(Channel):
     def cancel_session(self, session_id):
         with self.lock:
             if session_id in self.sessions:
-                for future in self.futures[session_id]:
+                # futures[session_id] is only created in consume() when a task is
+                # dispatched, so it may be absent if cancel happens right after
+                # produce() but before the first dispatch. Default to [].
+                for future in self.futures.get(session_id, []):
                     future.cancel()
                 cnt = self.sessions[session_id][0].qsize()
                 if cnt > 0:
@@ -478,7 +532,7 @@ class ChatChannel(Channel):
     def cancel_all_session(self):
         with self.lock:
             for session_id in self.sessions:
-                for future in self.futures[session_id]:
+                for future in self.futures.get(session_id, []):
                     future.cancel()
                 cnt = self.sessions[session_id][0].qsize()
                 if cnt > 0:

channel/chat_message.py

@@ -1,5 +1,5 @@
 """
-本类表示聊天消息，用于对itchat和wechaty的消息进行统一的封装。
+Unified chat message class for different channel implementations.
 
 填好必填项(群聊6个，非群聊8个)，即可接入ChatChannel，并支持插件，参考TerminalChannel
 

channel/dingtalk/dingtalk_channel.py

@@ -86,6 +86,8 @@ def _check(func):
 
 @singleton
 class DingTalkChanel(ChatChannel, dingtalk_stream.ChatbotHandler):
+    NOT_SUPPORT_REPLYTYPE = []
+
     dingtalk_client_id = conf().get('dingtalk_client_id')
     dingtalk_client_secret = conf().get('dingtalk_client_secret')
 
@@ -115,6 +117,35 @@ class DingTalkChanel(ChatChannel, dingtalk_stream.ChatbotHandler):
         # Robot code cache (extracted from incoming messages)
         self._robot_code = None
 
+    def _open_connection(self, client):
+        """
+        Open a DingTalk stream connection directly, bypassing SDK's internal error-swallowing.
+        Returns (connection_dict, error_str). On success error_str is empty; on failure
+        connection_dict is None and error_str contains a human-readable message.
+        """
+        try:
+            resp = requests.post(
+                "https://api.dingtalk.com/v1.0/gateway/connections/open",
+                headers={"Content-Type": "application/json", "Accept": "application/json"},
+                json={
+                    "clientId": client.credential.client_id,
+                    "clientSecret": client.credential.client_secret,
+                    "subscriptions": [{"type": "CALLBACK",
+                                       "topic": dingtalk_stream.chatbot.ChatbotMessage.TOPIC}],
+                    "ua": "dingtalk-sdk-python/cow",
+                    "localIp": "",
+                },
+                timeout=10,
+            )
+            body = resp.json()
+            if not resp.ok:
+                code = body.get("code", resp.status_code)
+                message = body.get("message", resp.reason)
+                return None, f"open connection failed: [{code}] {message}"
+            return body, ""
+        except Exception as e:
+            return None, f"open connection failed: {e}"
+
     def startup(self):
         import asyncio
         self.dingtalk_client_id = conf().get('dingtalk_client_id')
@@ -125,34 +156,80 @@ class DingTalkChanel(ChatChannel, dingtalk_stream.ChatbotHandler):
         self._stream_client = client
         client.register_callback_handler(dingtalk_stream.chatbot.ChatbotMessage.TOPIC, self)
         logger.info("[DingTalk] ✅ Stream client initialized, ready to receive messages")
+
+        # Run the connection loop ourselves instead of delegating to client.start(),
+        # so we can get detailed error messages and respond to stop() quickly.
+        import urllib.parse as _urlparse
+        import websockets as _ws
+        import json as _json
+        client.pre_start()
         _first_connect = True
         while self._running:
+            # Open connection using our own request so we get detailed error info.
+            connection, err_msg = self._open_connection(client)
+
+            if connection is None:
+                if _first_connect:
+                    logger.warning(f"[DingTalk] {err_msg}")
+                    self.report_startup_error(err_msg)
+                    _first_connect = False
+                else:
+                    logger.warning(f"[DingTalk] {err_msg}, retrying in 10s...")
+
+                # Interruptible sleep: checks _running every 100ms.
+                for _ in range(100):
+                    if not self._running:
+                        break
+                    time.sleep(0.1)
+                continue
+
+            if _first_connect:
+                logger.info("[DingTalk] ✅ Connected to DingTalk stream")
+                self.report_startup_success()
+                _first_connect = False
+            else:
+                logger.info("[DingTalk] Reconnected to DingTalk stream")
+
+            # Run the WebSocket session in an asyncio loop.
+            uri = '%s?ticket=%s' % (
+                connection['endpoint'],
+                _urlparse.quote_plus(connection['ticket'])
+            )
             loop = asyncio.new_event_loop()
             asyncio.set_event_loop(loop)
             self._event_loop = loop
             try:
-                if not _first_connect:
+                async def _session():
-                    logger.info("[DingTalk] Reconnecting...")
+                    async with _ws.connect(uri) as websocket:
-                _first_connect = False
+                        client.websocket = websocket
-                loop.run_until_complete(client.start())
+                        async for raw_message in websocket:
+                            json_message = _json.loads(raw_message)
+                            result = await client.route_message(json_message)
+                            if result == dingtalk_stream.DingTalkStreamClient.TAG_DISCONNECT:
+                                break
+
+                loop.run_until_complete(_session())
             except (KeyboardInterrupt, SystemExit):
-                logger.info("[DingTalk] Startup loop received stop signal, exiting")
+                logger.info("[DingTalk] Session loop received stop signal, exiting")
                 break
             except Exception as e:
                 if not self._running:
                     break
-                logger.warning(f"[DingTalk] Stream connection error: {e}, reconnecting in 3s...")
+                logger.warning(f"[DingTalk] Stream session error: {e}, reconnecting in 3s...")
-                time.sleep(3)
+                for _ in range(30):
+                    if not self._running:
+                        break
+                    time.sleep(0.1)
             finally:
                 self._event_loop = None
                 try:
                     loop.close()
                 except Exception:
                     pass
+
         logger.info("[DingTalk] Startup loop exited")
 
     def stop(self):
-        import asyncio
         logger.info("[DingTalk] stop() called, setting _running=False")
         self._running = False
         loop = self._event_loop
@@ -795,6 +872,48 @@ class DingTalkChanel(ChatChannel, dingtalk_stream.ChatbotHandler):
                     self.reply_text("抱歉，文件上传失败", incoming_message)
             return
         
+        # Native sampleAudio. Upload only accepts ogg/amr, so convert TTS mp3/wav to amr.
+        elif reply.type == ReplyType.VOICE:
+            logger.info(f"[DingTalk] Sending voice: {reply.content}")
+            access_token = self.get_access_token()
+            if not access_token:
+                logger.error("[DingTalk] Cannot get access token for voice")
+                self.reply_text("抱歉，语音发送失败（无法获取token）", incoming_message)
+                return
+
+            voice_path = reply.content
+            if voice_path.startswith("file://"):
+                voice_path = voice_path[7:]
+
+            amr_path = voice_path
+            duration_ms = 0
+            if not voice_path.lower().endswith((".amr", ".ogg")):
+                try:
+                    from voice.audio_convert import any_to_amr
+                    amr_path = os.path.splitext(voice_path)[0] + ".amr"
+                    duration_ms = int(any_to_amr(voice_path, amr_path) or 0)
+                except Exception as e:
+                    logger.error(f"[DingTalk] Failed to convert voice to amr: {e}")
+                    self.reply_text("抱歉，语音转码失败", incoming_message)
+                    return
+
+            media_id = self.upload_media(amr_path, media_type="voice")
+            if not media_id:
+                logger.error("[DingTalk] Failed to upload voice media")
+                self.reply_text("抱歉，语音上传失败", incoming_message)
+                return
+
+            msg_param = {
+                "mediaId": media_id,
+                "duration": str(duration_ms or 1000),
+            }
+            success = self._send_file_message(
+                access_token, incoming_message, "sampleAudio", msg_param, isgroup
+            )
+            if not success:
+                self.reply_text("抱歉，语音发送失败", incoming_message)
+            return
+
         # 处理文本消息
         elif reply.type == ReplyType.TEXT:
             logger.info(f"[DingTalk] Sending text message, length={len(reply.content)}")

channel/discord/discord_channel.py

@@ -0,0 +1,500 @@
+"""
+Discord channel via the Gateway (WebSocket) using discord.py.
+
+Features:
+- Direct message & guild channel chat (text / image / file)
+- Guild trigger: @mention or reply-to-bot (configurable)
+- /cancel fast-path matches Web channel behaviour
+- Gateway long connection: no public IP / callback URL required, works behind NAT
+
+Implementation note:
+    discord.py is async-first. We run the client inside a dedicated thread
+    with its own asyncio loop so the rest of cow (which is sync) stays
+    untouched. Inbound messages are dispatched onto cow's existing sync
+    ChatChannel.produce() pipeline; outbound send() schedules coroutines
+    back onto that loop via asyncio.run_coroutine_threadsafe.
+"""
+
+import asyncio
+import os
+import re
+import threading
+
+from bridge.context import Context, ContextType
+from bridge.reply import Reply, ReplyType
+from channel.chat_channel import ChatChannel, check_prefix
+from channel.discord.discord_message import DiscordMessage
+from common.expired_dict import ExpiredDict
+from common.log import logger
+from common.singleton import singleton
+from config import conf
+
+# Discord caps a single message at 2000 chars; split conservatively below.
+DISCORD_MSG_LIMIT = 1900
+
+
+@singleton
+class DiscordChannel(ChatChannel):
+    NOT_SUPPORT_REPLYTYPE = []
+
+    def __init__(self):
+        super().__init__()
+        self.bot_token = ""
+        self.bot_user_id = ""  # used to strip @mention and ignore self messages
+        self.bot_username = ""
+        self._client = None
+        self._loop = None
+        self._loop_thread = None
+        self._stop_event = threading.Event()
+        # Idempotent dedup; guard against rare duplicate dispatch
+        self._received_msgs = ExpiredDict(60 * 60 * 1)
+
+        # Disable group whitelist / prefix checks (we handle triggering ourselves
+        # in _should_reply_in_guild), aligned with telegram / slack channels.
+        conf()["group_name_white_list"] = ["ALL_GROUP"]
+        conf()["single_chat_prefix"] = [""]
+
+    # ------------------------------------------------------------------
+    # Lifecycle
+    # ------------------------------------------------------------------
+
+    def startup(self):
+        self.bot_token = conf().get("discord_token", "")
+        if not self.bot_token:
+            err = "[Discord] discord_token is required"
+            logger.error(err)
+            self.report_startup_error(err)
+            return
+
+        try:
+            import discord
+        except ImportError:
+            err = (
+                "[Discord] discord.py is not installed. "
+                "Run: pip install discord.py"
+            )
+            logger.error(err)
+            self.report_startup_error(err)
+            return
+
+        # Run the asyncio event loop in a dedicated thread so the sync cow body
+        # is untouched.
+        self._loop = asyncio.new_event_loop()
+
+        def _run_loop():
+            asyncio.set_event_loop(self._loop)
+            try:
+                self._loop.run_until_complete(self._async_main(discord))
+            except Exception as e:
+                logger.error(f"[Discord] event loop crashed: {e}", exc_info=True)
+                self.report_startup_error(str(e))
+            finally:
+                try:
+                    self._loop.close()
+                except Exception:
+                    pass
+                logger.info("[Discord] event loop exited")
+
+        self._loop_thread = threading.Thread(target=_run_loop, daemon=True, name="discord-loop")
+        self._loop_thread.start()
+        # Block startup() until the loop thread exits, matching other channels'
+        # behaviour (startup is a blocking call).
+        self._loop_thread.join()
+
+    async def _async_main(self, discord):
+        """Build the discord client, register handlers, and connect to the Gateway."""
+        # message_content is a privileged intent; it must be enabled in the
+        # Developer Portal (Bot -> Privileged Gateway Intents) to read text.
+        intents = discord.Intents.default()
+        intents.message_content = True
+        client = discord.Client(intents=intents)
+        self._client = client
+
+        channel = self
+
+        @client.event
+        async def on_ready():
+            channel.bot_user_id = str(client.user.id)
+            channel.bot_username = client.user.name or ""
+            channel.name = channel.bot_user_id  # ChatChannel uses self.name to strip @-mention
+            logger.info(f"[Discord] Bot logged in as {client.user} (id={client.user.id})")
+            channel.report_startup_success()
+            logger.info("[Discord] ✅ Discord bot ready, listening for messages")
+
+        @client.event
+        async def on_message(message):
+            await channel._on_message(message)
+
+        # Connect to the Gateway; discord.py auto-reconnects on transient errors.
+        logger.info("[Discord] Connecting to Gateway...")
+
+        # client.start() handles login + Gateway connection and runs until
+        # close(); it is the standard entrypoint across discord.py versions.
+        runner_task = asyncio.create_task(client.start(self.bot_token))
+
+        # Block until stop()
+        try:
+            while not self._stop_event.is_set():
+                if runner_task.done():
+                    # Surface a startup/connection failure (e.g. bad token)
+                    exc = runner_task.exception()
+                    if exc:
+                        logger.error(f"[Discord] client stopped: {exc}", exc_info=exc)
+                        self.report_startup_error(str(exc))
+                    break
+                await asyncio.sleep(0.5)
+        finally:
+            try:
+                if not client.is_closed():
+                    await client.close()
+            except Exception as e:
+                logger.warning(f"[Discord] shutdown error: {e}")
+
+    def stop(self):
+        logger.info("[Discord] stop() called")
+        self._stop_event.set()
+        if self._loop_thread and self._loop_thread.is_alive():
+            try:
+                self._loop_thread.join(timeout=10)
+            except Exception:
+                pass
+        logger.info("[Discord] stop() completed")
+
+    # ------------------------------------------------------------------
+    # Inbound: discord message -> ChatMessage -> ChatChannel.produce
+    # ------------------------------------------------------------------
+
+    async def _on_message(self, message):
+        """Discord message entry: parse -> build ChatMessage -> produce()."""
+        try:
+            # Ignore our own messages and other bots. self._client.user may be
+            # None until on_ready completes, so guard against that.
+            if self._client and self._client.user and message.author.id == self._client.user.id:
+                return
+            if message.author.bot:
+                return
+
+            # Idempotent dedup
+            msg_uid = f"{message.channel.id}:{message.id}"
+            if self._received_msgs.get(msg_uid):
+                return
+            self._received_msgs[msg_uid] = True
+
+            # guild is None for DMs
+            is_group = message.guild is not None
+
+            # Guild trigger gate (silently drop if not triggered)
+            if is_group and not self._should_reply_in_guild(message):
+                logger.debug(f"[Discord] guild message not triggered (need @mention or reply), skip")
+                return
+
+            # Parse message type + download attachments if needed.
+            ctype, content, caption = await self._parse_message(message)
+            if ctype is None:
+                logger.debug(f"[Discord] unsupported message type, skip. msg_id={message.id}")
+                return
+
+            # Strip the bot mention from guild text/caption
+            if is_group:
+                if ctype == ContextType.TEXT and content:
+                    content = self._strip_at_mention(content)
+                if caption:
+                    caption = self._strip_at_mention(caption)
+
+            dc_msg = DiscordMessage(
+                message,
+                is_group=is_group,
+                bot_user_id=self.bot_user_id,
+                ctype=ctype,
+                content=content,
+            )
+            dc_msg.is_at = is_group  # if we reached here in a guild, bot is mentioned/replied
+
+            from channel.file_cache import get_file_cache
+            file_cache = get_file_cache()
+            session_id = self._compute_session_id(message, is_group)
+
+            # Media + caption together: treat as a complete query and bypass the cache
+            if ctype in (ContextType.IMAGE, ContextType.FILE) and caption:
+                tag = "image" if ctype == ContextType.IMAGE else "file"
+                merged_text = f"{caption}\n[{tag}: {content}]"
+                dc_msg.ctype = ContextType.TEXT
+                dc_msg.content = merged_text
+                ctype = ContextType.TEXT
+                logger.info(f"[Discord] Media+caption merged for session {session_id}")
+                # fallthrough to the TEXT branch below
+
+            elif ctype == ContextType.IMAGE:
+                file_cache.add(session_id, content, file_type="image")
+                logger.info(f"[Discord] Image cached for session {session_id}, waiting for query...")
+                return
+            elif ctype == ContextType.FILE:
+                file_cache.add(session_id, content, file_type="file")
+                logger.info(f"[Discord] File cached for session {session_id}: {content}")
+                return
+
+            if ctype == ContextType.TEXT:
+                # Fast-path: /cancel mirrors Web channel behaviour
+                if (content or "").strip().lower() in ("/cancel", "cancel"):
+                    await self._do_cancel(session_id, message)
+                    return
+
+                cached_files = file_cache.get(session_id)
+                if cached_files:
+                    refs = []
+                    for fi in cached_files:
+                        ftype = fi["type"]
+                        tag = ftype if ftype in ("image", "video") else "file"
+                        refs.append(f"[{tag}: {fi['path']}]")
+                    dc_msg.content = (dc_msg.content or "") + "\n" + "\n".join(refs)
+                    file_cache.clear(session_id)
+                    logger.info(f"[Discord] Attached {len(cached_files)} cached file(s) to query")
+
+            context = self._compose_context(
+                dc_msg.ctype,
+                dc_msg.content,
+                isgroup=is_group,
+                msg=dc_msg,
+                # Replies use Discord's reply mechanism, no manual @mention needed
+                no_need_at=True,
+            )
+            if context:
+                context["session_id"] = session_id
+                context["receiver"] = str(message.channel.id)
+                context["discord_channel_id"] = message.channel.id
+                context["discord_reply_to_msg_id"] = message.id if is_group else None
+                self.produce(context)
+            logger.debug(f"[Discord] received: type={ctype}, content={str(dc_msg.content)[:80]}")
+
+        except Exception as e:
+            logger.error(f"[Discord] _on_message error: {e}", exc_info=True)
+
+    async def _do_cancel(self, session_id: str, message):
+        """Fast-path: /cancel calls cancel_session directly without going through agent."""
+        try:
+            from agent.protocol import get_cancel_registry
+            cancelled = get_cancel_registry().cancel_session(session_id)
+            text = "Current task cancelled." if cancelled else "No running task to cancel."
+            await message.channel.send(text)
+            logger.info(f"[Discord] /cancel session={session_id}, cancelled={cancelled}")
+        except Exception as e:
+            logger.error(f"[Discord] /cancel error: {e}", exc_info=True)
+
+    async def _parse_message(self, message):
+        """Parse a discord message and return (ctype, content, caption).
+
+        - content is text for ContextType.TEXT, otherwise the local file path
+        - caption is the optional text accompanying an attachment; empty for plain text
+        """
+        text = (message.content or "").strip()
+        attachments = message.attachments or []
+
+        if attachments:
+            # Handle the first attachment; caption is the accompanying message text
+            att = attachments[0]
+            content_type = (att.content_type or "").lower()
+            name = att.filename or str(att.id)
+            path = await self._download_attachment(att, name)
+            if not path:
+                return (None, None, "")
+            is_image = content_type.startswith("image/") or name.lower().endswith(
+                (".jpg", ".jpeg", ".png", ".gif", ".webp", ".bmp")
+            )
+            if is_image:
+                return (ContextType.IMAGE, path, text)
+            return (ContextType.FILE, path, text)
+
+        if text:
+            return (ContextType.TEXT, text, "")
+
+        return (None, None, "")
+
+    async def _download_attachment(self, attachment, name: str):
+        """Download a discord attachment into the local tmp dir; return path or None."""
+        try:
+            tmp_dir = DiscordMessage.get_tmp_dir()
+            safe_name = re.sub(r"[^\w.\-]", "_", name)
+            # Prefix with attachment id to avoid name collisions
+            local_path = os.path.join(tmp_dir, f"{attachment.id}_{safe_name}")
+            await attachment.save(local_path)
+            logger.debug(f"[Discord] downloaded {name} -> {local_path}")
+            return local_path
+        except Exception as e:
+            logger.error(f"[Discord] download_attachment failed ({name}): {e}")
+            return None
+
+    # ------------------------------------------------------------------
+    # Guild trigger logic
+    # ------------------------------------------------------------------
+
+    def _should_reply_in_guild(self, message) -> bool:
+        """Decide whether to reply to a guild channel message based on configuration."""
+        mode = conf().get("discord_group_trigger", "mention_or_reply")
+        if mode == "all":
+            return True
+
+        # self._client.user may be None until on_ready completes
+        if not self._client or not self._client.user:
+            return False
+
+        # 1) Mentioned (direct @bot, not @everyone / @role)
+        if self._client.user in message.mentions:
+            return True
+
+        # 2) Reply to a bot message
+        if mode == "mention_or_reply":
+            ref = message.reference
+            resolved = getattr(ref, "resolved", None) if ref else None
+            if resolved and getattr(resolved, "author", None):
+                if resolved.author.id == self._client.user.id:
+                    return True
+
+        return False
+
+    def _strip_at_mention(self, content: str) -> str:
+        """Strip <@BOT_ID> / <@!BOT_ID> from guild text."""
+        if not content or not self.bot_user_id:
+            return content
+        pattern = re.compile(r"<@!?" + re.escape(self.bot_user_id) + r">")
+        return pattern.sub("", content).strip()
+
+    @staticmethod
+    def _compute_session_id(message, is_group: bool) -> str:
+        channel_id = message.channel.id
+        user_id = message.author.id
+        if is_group:
+            if conf().get("group_shared_session", True):
+                return f"discord_channel_{channel_id}"
+            return f"discord_channel_{channel_id}_{user_id}"
+        return f"discord_user_{user_id}"
+
+    # ------------------------------------------------------------------
+    # Override _compose_context: skip the parent's group whitelist/at checks
+    # (already handled via _should_reply_in_guild). Same idea as telegram / slack.
+    # ------------------------------------------------------------------
+
+    def _compose_context(self, ctype: ContextType, content, **kwargs):
+        context = Context(ctype, content)
+        context.kwargs = kwargs
+        if "channel_type" not in context:
+            context["channel_type"] = self.channel_type
+        if "origin_ctype" not in context:
+            context["origin_ctype"] = ctype
+
+        cmsg = context["msg"]
+        if cmsg.is_group:
+            if conf().get("group_shared_session", True):
+                context["session_id"] = cmsg.other_user_id
+            else:
+                context["session_id"] = f"{cmsg.from_user_id}:{cmsg.other_user_id}"
+        else:
+            context["session_id"] = cmsg.from_user_id
+        context["receiver"] = cmsg.other_user_id
+
+        if ctype == ContextType.TEXT:
+            img_match_prefix = check_prefix(content, conf().get("image_create_prefix"))
+            if img_match_prefix:
+                content = content.replace(img_match_prefix, "", 1)
+                context.type = ContextType.IMAGE_CREATE
+            else:
+                context.type = ContextType.TEXT
+            context.content = (content or "").strip()
+            if "desire_rtype" not in context and conf().get("always_reply_voice"):
+                context["desire_rtype"] = ReplyType.VOICE
+        elif ctype == ContextType.VOICE:
+            if "desire_rtype" not in context and (
+                conf().get("voice_reply_voice") or conf().get("always_reply_voice")
+            ):
+                context["desire_rtype"] = ReplyType.VOICE
+
+        return context
+
+    # ------------------------------------------------------------------
+    # Outbound: ChatChannel.send -> Discord Gateway/REST
+    # ------------------------------------------------------------------
+
+    def send(self, reply: Reply, context: Context):
+        """Called from cow's sync main thread; marshal the coroutine onto the loop thread."""
+        if self._loop is None or self._client is None:
+            logger.warning("[Discord] client not ready, drop reply")
+            return
+
+        channel_id = context.get("discord_channel_id")
+        if channel_id is None:
+            logger.warning("[Discord] no discord_channel_id in context, drop reply")
+            return
+
+        coro = self._async_send(reply, channel_id)
+        try:
+            future = asyncio.run_coroutine_threadsafe(coro, self._loop)
+            future.result(timeout=180)
+        except Exception as e:
+            logger.error(f"[Discord] send failed: {e}")
+
+    async def _async_send(self, reply: Reply, channel_id):
+        try:
+            import discord
+
+            channel = self._client.get_channel(channel_id)
+            if channel is None:
+                # Not in cache (e.g. DM channel); fetch it explicitly
+                channel = await self._client.fetch_channel(channel_id)
+
+            rtype = reply.type
+            content = reply.content
+
+            if rtype in (ReplyType.TEXT, ReplyType.INFO, ReplyType.ERROR):
+                text = str(content) if content is not None else ""
+                if not text:
+                    return
+                for chunk in _split_text(text, DISCORD_MSG_LIMIT):
+                    await channel.send(chunk)
+
+            elif rtype == ReplyType.IMAGE:
+                # Already a local BytesIO; send it directly
+                content.seek(0)
+                await channel.send(file=discord.File(content, filename="image.png"))
+
+            elif rtype == ReplyType.IMAGE_URL:
+                url = str(content)
+                if url.startswith("file://"):
+                    local = url[7:]
+                    await channel.send(file=discord.File(local))
+                else:
+                    # Post the URL as text; Discord will unfurl it as an image preview
+                    await channel.send(url)
+
+            elif rtype in (ReplyType.VOICE, ReplyType.FILE):
+                local = content[7:] if isinstance(content, str) and content.startswith("file://") else content
+                caption = getattr(reply, "text_content", None) or None
+                await channel.send(content=caption, file=discord.File(local))
+
+            else:
+                # Fallback: send as plain text
+                await channel.send(str(content))
+
+            logger.info(f"[Discord] sent reply (type={rtype}, channel={channel_id})")
+
+        except Exception as e:
+            logger.error(f"[Discord] _async_send error: {e}", exc_info=True)
+
+
+def _split_text(text: str, limit: int):
+    """Split long text preferring line breaks to keep markdown structure intact."""
+    if len(text) <= limit:
+        yield text
+        return
+    buf = []
+    size = 0
+    for line in text.splitlines(keepends=True):
+        if size + len(line) > limit and buf:
+            yield "".join(buf)
+            buf, size = [], 0
+        # Hard-split single lines that exceed the limit
+        while len(line) > limit:
+            yield line[:limit]
+            line = line[limit:]
+        buf.append(line)
+        size += len(line)
+    if buf:
+        yield "".join(buf)

channel/discord/discord_message.py

@@ -0,0 +1,60 @@
+"""
+Discord message adapter.
+
+Convert a discord.py Message into cow's unified ChatMessage.
+File downloads are NOT performed here; the channel layer downloads
+attachments on demand inside the async event loop.
+"""
+import os
+
+from bridge.context import ContextType
+from channel.chat_message import ChatMessage
+from common.utils import expand_path
+from config import conf
+
+
+class DiscordMessage(ChatMessage):
+    """Wrap a discord.py Message into the unified ChatMessage."""
+
+    def __init__(self, message, is_group: bool = False, bot_user_id: str = "",
+                 ctype: ContextType = ContextType.TEXT, content: str = ""):
+        super().__init__(message)
+        # Basic fields
+        self.msg_id = str(message.id)
+        self.create_time = int(message.created_at.timestamp()) if message.created_at else 0
+        self.ctype = ctype
+        self.content = content
+
+        author = message.author
+        channel = message.channel
+
+        # Sender / chat info
+        from_user_id = str(author.id)
+        from_user_nick = getattr(author, "display_name", None) or getattr(author, "name", None) or from_user_id
+        self.from_user_id = from_user_id
+        self.from_user_nickname = from_user_nick
+        self.to_user_id = bot_user_id or "discord_bot"
+        self.to_user_nickname = bot_user_id or "discord_bot"
+
+        self.is_group = is_group
+        if is_group:
+            # Guild channel: other_user_id = channel_id, actual_user_id = sender id
+            self.other_user_id = str(channel.id)
+            self.other_user_nickname = getattr(channel, "name", None) or str(channel.id)
+            self.actual_user_id = from_user_id
+            self.actual_user_nickname = from_user_nick
+        else:
+            # DM: use channel_id so replies go back to the same DM channel
+            self.other_user_id = str(channel.id)
+            self.other_user_nickname = from_user_nick
+
+        # Whether the bot was triggered by @-mention (set by channel layer)
+        self.is_at = False
+
+    @staticmethod
+    def get_tmp_dir() -> str:
+        """Local download directory, aligned with other channels (agent_workspace/tmp)."""
+        workspace_root = expand_path(conf().get("agent_workspace", "~/cow"))
+        tmp_dir = os.path.join(workspace_root, "tmp")
+        os.makedirs(tmp_dir, exist_ok=True)
+        return tmp_dir

channel/feishu/feishu_channel.py

@@ -11,6 +11,7 @@
 @Date 2023/11/19
 """
 
+import importlib.util
 import json
 import logging
 import os
@@ -38,15 +39,190 @@ logging.getLogger("Lark").setLevel(logging.WARNING)
 
 URL_VERIFICATION = "url_verification"
 
-# 尝试导入飞书SDK,如果未安装则websocket模式不可用
+# Lazy-check for lark_oapi SDK availability without importing it at module level.
-try:
+# The full `import lark_oapi` pulls in 10k+ files and takes 4-10s, so we defer
-    import lark_oapi as lark
+# the actual import to _startup_websocket() where it is needed.
+LARK_SDK_AVAILABLE = importlib.util.find_spec("lark_oapi") is not None
+lark = None  # will be populated on first use via _ensure_lark_imported()
 
-    LARK_SDK_AVAILABLE = True
+
-except ImportError:
+def _ensure_lark_imported():
-    LARK_SDK_AVAILABLE = False
+    """Import lark_oapi on first use (takes 4-10s due to 10k+ source files)."""
-    logger.warning(
+    global lark
-        "[FeiShu] lark_oapi not installed, websocket mode is not available. Install with: pip install lark-oapi")
+    if lark is None:
+        import lark_oapi as _lark
+        lark = _lark
+    return lark
+
+
+def _print_qr_to_terminal(qr_url: str):
+    """Render a QR code as ASCII art and emit it via logger.
+
+    走 logger 而非 print 是为了避免 nohup/cow 后台启动场景下 stdout 块缓冲导致
+    二维码滞后输出（看起来像出现了两次）。logger 的 StreamHandler 是行缓冲，
+    既能在前台终端看到，也能进 run.log。
+    """
+    qr_lines = []
+    try:
+        import qrcode as qr_lib
+        import io
+        qr = qr_lib.QRCode(error_correction=qr_lib.constants.ERROR_CORRECT_L, box_size=1, border=1)
+        qr.add_data(qr_url)
+        qr.make(fit=True)
+        buf = io.StringIO()
+        qr.print_ascii(out=buf, invert=True)
+        qr_lines = buf.getvalue().splitlines()
+    except ImportError:
+        qr_lines = ["(未安装 qrcode 包，无法渲染 ASCII 二维码：pip install qrcode)"]
+    except Exception as e:
+        qr_lines = [f"(渲染二维码失败：{e})"]
+
+    header = "=" * 60
+    banner = [
+        "",
+        header,
+        "  飞书一键创建应用：请使用 飞书 App 扫描下方二维码",
+        "  （二维码 10 分钟内有效，仅供一次扫描）",
+        header,
+    ]
+    footer = [
+        f"  或点击链接创建: {qr_url}",
+        "  等待扫码...",
+        "",
+    ]
+    full = banner + qr_lines + footer
+    logger.info("[FeiShu] One-click 飞书应用创建二维码（请用飞书 App 扫码）：\n" + "\n".join(full))
+
+
+def _persist_feishu_credentials(app_id: str, app_secret: str) -> bool:
+    """Write feishu_app_id / feishu_app_secret + ensure feishu in channel_type into config.json.
+
+    Returns True on success, False on failure (e.g. config.json missing or unwritable).
+    """
+    try:
+        config_path = os.path.join(
+            os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))),
+            "config.json",
+        )
+        if os.path.exists(config_path):
+            with open(config_path, "r", encoding="utf-8") as f:
+                file_cfg = json.load(f)
+        else:
+            file_cfg = {}
+
+        file_cfg["feishu_app_id"] = app_id
+        file_cfg["feishu_app_secret"] = app_secret
+
+        # 保证 channel_type 中包含 feishu（用户可能纯通过 CLI 启动单通道）
+        ch_type = file_cfg.get("channel_type", conf().get("channel_type", "")) or ""
+        existing = [s.strip() for s in ch_type.split(",") if s.strip()]
+        if "feishu" not in existing:
+            existing.append("feishu")
+            file_cfg["channel_type"] = ",".join(existing)
+
+        with open(config_path, "w", encoding="utf-8") as f:
+            json.dump(file_cfg, f, indent=4, ensure_ascii=False)
+
+        # 同步到内存中的 conf()，让本次启动直接生效
+        conf()["feishu_app_id"] = app_id
+        conf()["feishu_app_secret"] = app_secret
+        if "channel_type" in file_cfg:
+            conf()["channel_type"] = file_cfg["channel_type"]
+
+        try:
+            os.chmod(config_path, 0o600)
+        except Exception:
+            pass
+        return True
+    except Exception as e:
+        logger.error(f"[FeiShu] Failed to persist credentials to config.json: {e}")
+        return False
+
+
+def _register_via_qr_in_terminal() -> bool:
+    """CLI-side one-click app creation via lark_oapi.register_app.
+
+    Blocks the calling thread (typically the channel startup thread) until the user
+    finishes scanning, the QR code expires, or registration is cancelled.
+
+    Returns True if credentials were obtained AND persisted; False otherwise.
+    The caller should fall back to the original "missing credentials" error in that case.
+    """
+    if not LARK_SDK_AVAILABLE:
+        logger.error(
+            "[FeiShu] 缺少 feishu_app_id / feishu_app_secret。"
+            "未安装 lark-oapi SDK，无法在终端发起扫码创建。"
+            "请执行 pip install -U 'lark-oapi>=1.5.5' 后重试，或手动在 config.json 中填入凭据。"
+        )
+        return False
+
+    try:
+        lark_mod = _ensure_lark_imported()
+    except Exception as e:
+        logger.error(f"[FeiShu] Import lark_oapi failed: {e}")
+        return False
+
+    # register_app 是 lark-oapi 1.5.5 才引入的能力，旧版本调用会得到难以理解的
+    # AttributeError。提前显式检查，给出明确的升级提示。
+    if not hasattr(lark_mod, "register_app"):
+        try:
+            from importlib.metadata import version as _pkg_version
+            installed = _pkg_version("lark-oapi")
+        except Exception:
+            installed = "unknown"
+        logger.error(
+            f"[FeiShu] 当前 lark-oapi 版本 ({installed}) 不支持一键创建应用，需要 >= 1.5.5。"
+            "请执行 pip install -U 'lark-oapi>=1.5.5' 后重试，或手动在 config.json 中填入凭据。"
+        )
+        return False
+
+    logger.info("[FeiShu] 检测到尚未配置 feishu_app_id / feishu_app_secret，"
+                "正在向飞书申请一键创建应用...")
+
+    def _on_qr(info):
+        url = info.get("url", "")
+        if url:
+            _print_qr_to_terminal(url)
+
+    def _on_status(info):
+        # 过滤 polling 心跳（每 5 秒一次），保留 slow_down / domain_switched 等
+        status = info.get("status")
+        if status == "polling":
+            return
+        logger.info(f"[FeiShu] register_app status: {info}")
+
+    try:
+        result = lark_mod.register_app(
+            on_qr_code=_on_qr,
+            on_status_change=_on_status,
+            source="cowagent",
+        )
+    except Exception as e:
+        err_cls = e.__class__.__name__
+        if "Expired" in err_cls:
+            logger.error("[FeiShu] 二维码已过期，请重启程序后重试。")
+        elif "Denied" in err_cls:
+            logger.error("[FeiShu] 已取消授权。")
+        else:
+            logger.error(f"[FeiShu] 一键创建失败：{e}")
+        return False
+
+    app_id = result.get("client_id", "")
+    app_secret = result.get("client_secret", "")
+    if not app_id or not app_secret:
+        logger.error("[FeiShu] 创建结果缺少 app_id/app_secret，无法继续。")
+        return False
+
+    if not _persist_feishu_credentials(app_id, app_secret):
+        logger.error(
+            "[FeiShu] 应用创建成功但写入 config.json 失败，请手动复制以下值到配置文件：\n"
+            f"        feishu_app_id     = {app_id}\n"
+            f"        feishu_app_secret = {app_secret}"
+        )
+        return False
+
+    logger.info(f"[FeiShu] 应用创建成功，凭据已写入 config.json (app_id={app_id})。")
+    return True
 
 
 @singleton
@@ -55,6 +231,10 @@ class FeiShuChanel(ChatChannel):
     feishu_app_secret = conf().get('feishu_app_secret')
     feishu_token = conf().get('feishu_token')
     feishu_event_mode = conf().get('feishu_event_mode', 'websocket')  # webhook 或 websocket
+    # 覆盖父类默认值 [ReplyType.VOICE, ReplyType.IMAGE]。
+    # 飞书原生支持发送音频（opus 格式，通过文件上传接口）和图片，
+    # 所有回复类型均已处理，置为空列表以启用语音和图片回复。
+    NOT_SUPPORT_REPLYTYPE = []
 
     def __init__(self):
         super().__init__()
@@ -63,6 +243,7 @@ class FeiShuChanel(ChatChannel):
         self._http_server = None
         self._ws_client = None
         self._ws_thread = None
+        self._bot_open_id = None  # cached bot open_id for @-mention matching
         logger.debug("[FeiShu] app_id={}, app_secret={}, verification_token={}, event_mode={}".format(
             self.feishu_app_id, self.feishu_app_secret, self.feishu_token, self.feishu_event_mode))
         # 无需群校验和前缀
@@ -79,11 +260,45 @@ class FeiShuChanel(ChatChannel):
         self.feishu_app_secret = conf().get('feishu_app_secret')
         self.feishu_token = conf().get('feishu_token')
         self.feishu_event_mode = conf().get('feishu_event_mode', 'websocket')
+
+        # 命令行启动场景：缺少凭据时尝试通过 lark.register_app 在终端弹二维码
+        # 引导用户扫码创建应用。Web 控制台启动同样会走到这里，但控制台用户通常
+        # 已经通过 /api/feishu/register 完成了创建并写回 config.json。
+        if not self.feishu_app_id or not self.feishu_app_secret:
+            if _register_via_qr_in_terminal():
+                self.feishu_app_id = conf().get('feishu_app_id')
+                self.feishu_app_secret = conf().get('feishu_app_secret')
+            else:
+                err = "[FeiShu] feishu_app_id 与 feishu_app_secret 缺失，无法启动通道"
+                logger.error(err)
+                self.report_startup_error(err)
+                return
+
+        self._fetch_bot_open_id()
         if self.feishu_event_mode == 'websocket':
             self._startup_websocket()
         else:
             self._startup_webhook()
 
+    def _fetch_bot_open_id(self):
+        """Fetch the bot's own open_id via API so we can match @-mentions without feishu_bot_name."""
+        try:
+            access_token = self.fetch_access_token()
+            if not access_token:
+                logger.warning("[FeiShu] Cannot fetch bot info: no access_token")
+                return
+            headers = {"Authorization": "Bearer " + access_token}
+            resp = requests.get("https://open.feishu.cn/open-apis/bot/v3/info/", headers=headers, timeout=5)
+            if resp.status_code == 200:
+                data = resp.json()
+                if data.get("code") == 0:
+                    self._bot_open_id = data.get("bot", {}).get("open_id")
+                    logger.info(f"[FeiShu] Bot open_id fetched: {self._bot_open_id}")
+                else:
+                    logger.warning(f"[FeiShu] Fetch bot info failed: code={data.get('code')}, msg={data.get('msg')}")
+        except Exception as e:
+            logger.warning(f"[FeiShu] Fetch bot open_id error: {e}")
+
     def stop(self):
         import ctypes
         logger.info("[FeiShu] stop() called")
@@ -134,17 +349,22 @@ class FeiShuChanel(ChatChannel):
 
     def _startup_websocket(self):
         """启动长连接接收事件(websocket模式)"""
+        _ensure_lark_imported()
         logger.debug("[FeiShu] Starting in websocket mode...")
 
         # 创建事件处理器
         def handle_message_event(data: lark.im.v1.P2ImMessageReceiveV1) -> None:
             """处理接收消息事件 v2.0"""
             try:
-                logger.debug(f"[FeiShu] websocket receive event: {lark.JSON.marshal(data, indent=2)}")
-
-                # 转换为标准的event格式
                 event_dict = json.loads(lark.JSON.marshal(data))
                 event = event_dict.get("event", {})
+                msg = event.get("message", {})
+
+                # Skip group messages that don't @-mention the bot (reduce log noise)
+                if msg.get("chat_type") == "group" and not msg.get("mentions") and msg.get("message_type") == "text":
+                    return
+
+                logger.debug(f"[FeiShu] websocket receive event: {lark.JSON.marshal(data, indent=2)}")
 
                 # 处理消息
                 self._handle_message_event(event)
@@ -169,10 +389,20 @@ class FeiShuChanel(ChatChannel):
                 context.verify_mode = ssl.CERT_NONE
                 return context
 
-            # Give this thread its own event loop so lark SDK can call run_until_complete
+            # lark_oapi.ws.client captures the event loop at module-import time as a module-
+            # level global variable.  When a previous ws thread is force-killed via ctypes its
+            # loop may still be marked as "running", which causes the next ws_client.start()
+            # call (in this new thread) to raise "This event loop is already running".
+            # Fix: replace the module-level loop with a brand-new, idle loop before starting.
             loop = asyncio.new_event_loop()
             asyncio.set_event_loop(loop)
+            try:
+                import lark_oapi.ws.client as _lark_ws_client_mod
+                _lark_ws_client_mod.loop = loop
+            except Exception:
+                pass
 
+            startup_error = None
             for attempt in range(2):
                 try:
                     if attempt == 1:
@@ -202,8 +432,11 @@ class FeiShuChanel(ChatChannel):
                         logger.warning(f"[FeiShu] SSL error: {error_msg}, retrying...")
                         continue
                     logger.error(f"[FeiShu] Websocket client error: {e}", exc_info=True)
+                    startup_error = error_msg
                     ssl_module.create_default_context = original_create_default_context
                     break
+            if startup_error:
+                self.report_startup_error(startup_error)
             try:
                 loop.close()
             except Exception:
@@ -216,6 +449,27 @@ class FeiShuChanel(ChatChannel):
         logger.info("[FeiShu] ✅ Websocket thread started, ready to receive messages")
         ws_thread.join()
 
+    def _is_mention_bot(self, mentions: list) -> bool:
+        """Check whether any mention in the list refers to this bot.
+
+        Priority:
+        1. Match by open_id (obtained from /bot/v3/info at startup, no config needed)
+        2. Fallback to feishu_bot_name config for backward compatibility
+        3. If neither is available, assume the first mention is the bot (Feishu only
+           delivers group messages that @-mention the bot, so this is usually correct)
+        """
+        if self._bot_open_id:
+            return any(
+                m.get("id", {}).get("open_id") == self._bot_open_id
+                for m in mentions
+            )
+        bot_name = conf().get("feishu_bot_name")
+        if bot_name:
+            return any(m.get("name") == bot_name for m in mentions)
+        # Feishu event subscription only delivers messages that @-mention the bot,
+        # so reaching here means the bot was indeed mentioned.
+        return True
+
     def _handle_message_event(self, event: dict):
         """
         处理消息事件的核心逻辑
@@ -250,10 +504,9 @@ class FeiShuChanel(ChatChannel):
             if not msg.get("mentions") and msg.get("message_type") == "text":
                 # 群聊中未@不响应
                 return
-            if msg.get("mentions") and msg.get("mentions")[0].get("name") != conf().get("feishu_bot_name") and msg.get(
+            if msg.get("mentions") and msg.get("message_type") == "text":
-                    "message_type") == "text":
+                if not self._is_mention_bot(msg.get("mentions")):
-                # 不是@机器人，不响应
+                    return
-                return
             # 群聊
             is_group = True
             receive_id_type = "chat_id"
@@ -289,6 +542,32 @@ class FeiShuChanel(ChatChannel):
             # 单张图片不直接处理，等待用户提问
             return
 
+        # 如果是文件消息，触发实际下载并缓存，等待用户后续提问时一并带上。
+        # 与 wecom_bot 行为对齐：发文件后静默缓存（飞书客户端会显示"已读"），
+        # 用户下一条文本消息会自动 attach 上文件路径给 agent。
+        if feishu_msg.ctype == ContextType.FILE:
+            try:
+                feishu_msg.prepare()
+                # prepare 通过 _prepared 标记保证幂等，重复调用安全
+                if not os.path.exists(feishu_msg.content):
+                    raise FileNotFoundError(feishu_msg.content)
+            except Exception as e:
+                logger.warning(f"[FeiShu] prepare file failed: {e}")
+                # 文件下载失败时主动通知用户，避免静默丢失
+                try:
+                    err_reply = Reply(ReplyType.TEXT, f"⚠️ 文件下载失败，请重新发送：{e}")
+                    self._send(err_reply, self._compose_context(
+                        ContextType.TEXT, "",
+                        isgroup=is_group, msg=feishu_msg,
+                        receive_id_type=receive_id_type, no_need_at=True,
+                    ))
+                except Exception:
+                    pass
+                return
+            file_cache.add(session_id, feishu_msg.content, file_type='file')
+            logger.info(f"[FeiShu] File cached for session {session_id}: {feishu_msg.content}")
+            return
+
         # 如果是文本消息，检查是否有缓存的文件
         if feishu_msg.ctype == ContextType.TEXT:
             cached_files = file_cache.get(session_id)
@@ -319,10 +598,22 @@ class FeiShuChanel(ChatChannel):
             no_need_at=True
         )
         if context:
+            # 流式回复模式：向 context 注入 on_event 回调，agent 每产出一段文字时会调用它。
+            # 回调内部先发送一条占位消息获取 message_id，之后通过 PATCH 接口原地更新内容，
+            # 实现打字机效果。回调结束时设置 context["feishu_streamed"]=True，
+            # 让 send() 跳过重复发送，避免最终完整回复再被重复投递一次。
+            # 默认开启流式打字机回复。需机器人开通 cardkit:card:write 权限且飞书客户端 7.20+，
+            # 任意环节失败会自动降级为非流式文本回复。
+            if conf().get("feishu_stream_reply", True):
+                context["on_event"] = self._make_feishu_stream_callback(context, feishu_msg.access_token)
             self.produce(context)
         logger.debug(f"[FeiShu] query={feishu_msg.content}, type={feishu_msg.ctype}")
 
     def send(self, reply: Reply, context: Context):
+        # 如果文本回复已通过流式传输发送，则跳过重复发送
+        if reply.type == ReplyType.TEXT and context.get("feishu_streamed"):
+            logger.debug("[FeiShu] streaming already delivered text reply, skipping send()")
+            return
         msg = context.get("msg")
         is_group = context["isgroup"]
         if msg:
@@ -385,11 +676,21 @@ class FeiShuChanel(ChatChannel):
                 msg_type = "file"
                 content_key = "file_key"
 
+        elif reply.type == ReplyType.VOICE:
+            # 语音回复：上传音频文件到飞书，然后发送 audio 类型消息
+            file_key = self._upload_audio(reply.content, access_token)
+            if not file_key:
+                logger.warning("[FeiShu] upload audio failed")
+                return
+            reply_content = file_key
+            msg_type = "audio"
+            content_key = "file_key"
+
         # Check if we can reply to an existing message (need msg_id)
         can_reply = is_group and msg and hasattr(msg, 'msg_id') and msg.msg_id
 
         # Build content JSON
-        content_json = json.dumps(reply_content) if content_key is None else json.dumps({content_key: reply_content})
+        content_json = json.dumps(reply_content, ensure_ascii=False) if content_key is None else json.dumps({content_key: reply_content}, ensure_ascii=False)
         logger.debug(f"[FeiShu] Sending message: msg_type={msg_type}, content={content_json[:200]}")
 
         if can_reply:
@@ -416,6 +717,423 @@ class FeiShuChanel(ChatChannel):
         else:
             logger.error(f"[FeiShu] send message failed, code={res.get('code')}, msg={res.get('msg')}")
 
+    def _make_feishu_stream_callback(self, context, access_token):
+        """
+        基于飞书官方"流式更新卡片"API 实现打字机回复。
+
+        流程：
+        1. message_update 首次到达 → POST /cardkit/v1/cards 创建带 streaming_mode 的卡片实体，
+           随后用 POST /im/v1/messages（或 reply）以 card_id 把卡片发出去
+        2. 后续 message_update → PUT /cardkit/v1/cards/{id}/elements/{eid}/content
+           传入"当前轮"的全量文本，飞书平台自动计算增量并以打字机效果上屏
+           （流式模式下不受 10 QPS 限制）
+        3. message_end（一轮 LLM 输出结束，且本轮触发了工具调用）→ 把 current 累计到 committed
+           并加入分隔符；下一轮 message_update 又从空白开始，避免多轮内容串到一起
+        4. agent_end → 用 final_response 强制覆盖卡片，再 PATCH /cardkit/v1/cards/{id}/settings
+           关闭 streaming_mode，标记 context["feishu_streamed"]=True 让 chat_channel 跳过普通 send()
+
+        前提条件：
+        - 机器人已开通 cardkit:card:write 权限
+        - 飞书客户端 7.20+
+
+        失败降级：
+        - 创建卡片实体失败（缺权限、网络等）→ 不设置 feishu_streamed 标记，让 chat_channel
+          走普通文本回复路径，用户收到完整回复但无打字机效果，并打 warning 日志
+        """
+        # 共享状态（受 lock 保护）
+        # 多轮 agent 模式下，每个"中间过场消息"会作为一张独立卡片发送。
+        # current_text 只承载当前正在流式渲染的那张卡片的内容；message_end / agent_end
+        # 时会把它定型并 reset。
+        current_text = [""]                # 当前卡片正在累加的 LLM 输出
+        card_id = [None]                   # 当前流式卡片的实体 ID（每段独立）
+        message_id = [None]                # 当前卡片发送后的消息 ID（仅日志用）
+        # 占位发送是同步进行的，但用一个 in-flight 标记防止并发的多条 message_update
+        # 事件各自触发一次创建+发送，导致发出多张卡片。
+        init_in_flight = [False]
+        # 一旦初始化失败就长期标记为 disabled，本次回复不再尝试任何流式调用
+        disabled = [False]
+        # True after agent_cancelled: agent_end stops rewriting the card
+        # with stale final_response and just finalizes current content.
+        cancelled = [False]
+        lock = threading.Lock()
+
+        # ---- 异步推送队列 ----------------------------------------------------
+        # 同步 requests.put 单次 100~300ms，会阻塞 LLM stream 线程读下一个 chunk。
+        # 把推送丢给独立 worker 线程消费 queue，回调本身只做内存追加，立即返回。
+        # 队列里只放"最新累积文本"的快照；worker 用 deduplication 避免重复推同一个
+        # 内容（高频 chunk 场景下队列会堆积，只推最后一个就够了）。
+        import queue as _queue
+        push_queue: "_queue.Queue[str | None]" = _queue.Queue()
+
+        def _push_worker():
+            while True:
+                snapshot = push_queue.get()
+                if snapshot is None:
+                    push_queue.task_done()
+                    return
+                # 合并队列中已堆积的快照：只推最后一个，省 PUT 次数同时降低延迟
+                merged_count = 1
+                stop = False
+                while True:
+                    try:
+                        nxt = push_queue.get_nowait()
+                    except _queue.Empty:
+                        break
+                    merged_count += 1
+                    if nxt is None:
+                        stop = True
+                        break
+                    snapshot = nxt
+                try:
+                    _stream_update_text(snapshot)
+                finally:
+                    for _ in range(merged_count):
+                        push_queue.task_done()
+                if stop:
+                    return
+
+        push_thread = threading.Thread(target=_push_worker, daemon=True, name="feishu-stream-push")
+        push_thread.start()
+
+        def _drain_push_queue():
+            """等当前队列里所有 PUT 都完成。message_end/agent_end 在做最终定型前必须 drain，
+            否则 worker 里堆积的旧快照可能在 final_text PUT 之后到达，把最终内容覆盖掉。"""
+            try:
+                push_queue.join()
+            except Exception:
+                pass
+
+        msg = context.get("msg")
+        is_group = context.get("isgroup", False)
+        receiver = context.get("receiver")
+        receive_id_type = context.get("receive_id_type", "open_id")
+        # 客户端打字机渲染参数（飞书 App 侧实际"出字"速度）：
+        #   - print_freq_ms：每次刷新的间隔
+        #   - print_step：每次刷新出多少个字符
+        # 当前 40ms × 4 字 ≈ 100 字/秒，接近 ChatGPT/DeepSeek 网页端的节奏。
+        print_freq_ms = 40
+        print_step = 4
+        print_strategy = "fast"
+
+        headers = {
+            "Authorization": "Bearer " + access_token,
+            "Content-Type": "application/json; charset=utf-8",
+        }
+        # 卡片中富文本组件的 element_id，后续所有 PUT 流式更新都打到这个组件
+        ELEMENT_ID = "stream_md"
+        # 操作序号，每次 PUT 必须严格递增（飞书要求）
+        sequence = [0]
+
+        def _next_sequence():
+            sequence[0] += 1
+            return sequence[0]
+
+        def _build_card_json():
+            """卡片 JSON 2.0 结构 + streaming_mode + 单 markdown 组件"""
+            return json.dumps({
+                "schema": "2.0",
+                "config": {
+                    "streaming_mode": True,
+                    "summary": {"content": "[正在生成回复...]"},
+                    "streaming_config": {
+                        "print_frequency_ms": {"default": print_freq_ms},
+                        "print_step": {"default": print_step},
+                        "print_strategy": print_strategy,
+                    },
+                },
+                "body": {
+                    "elements": [
+                        {
+                            "tag": "markdown",
+                            "content": "...",
+                            "element_id": ELEMENT_ID,
+                        }
+                    ],
+                },
+                # 注意：JSON 2.0 不支持自定义 fallback 字段（传入会报错）。
+                # 客户端 < 7.20 时，飞书会自动展示"请升级客户端"占位，无需配置。
+            }, ensure_ascii=False)
+
+        def _create_and_send_card():
+            """同步执行：创建卡片实体 → 发送消息。任意一步失败则 disabled=True 触发降级"""
+            try:
+                # 步骤 1: 创建卡片实体
+                create_url = "https://open.feishu.cn/open-apis/cardkit/v1/cards"
+                create_body = {"type": "card_json", "data": _build_card_json()}
+                res = requests.post(
+                    create_url, headers=headers, json=create_body, timeout=(5, 10)
+                )
+                res_json = res.json()
+                if res_json.get("code") != 0:
+                    logger.warning(
+                        f"[FeiShu] Stream: create card failed "
+                        f"(code={res_json.get('code')}, msg={res_json.get('msg')}). "
+                        f"本次回复已自动降级为普通文本回复（一次性返回完整内容）。"
+                        f"如需开启流式打字机效果与完整 Markdown 渲染，请到飞书开放平台 "
+                        f"https://open.feishu.cn/app 给机器人开通 cardkit:card:write 权限"
+                        f"（创建与更新卡片）并重新发布版本，同时确保飞书客户端 >= 7.20。"
+                    )
+                    with lock:
+                        disabled[0] = True
+                    return
+                cid = res_json["data"]["card_id"]
+                with lock:
+                    card_id[0] = cid
+
+                # 步骤 2: 通过 card_id 发送消息（群聊优先用 reply，单聊直接 send）
+                content_payload = json.dumps(
+                    {"type": "card", "data": {"card_id": cid}}, ensure_ascii=False
+                )
+                can_reply = is_group and msg and hasattr(msg, "msg_id") and msg.msg_id
+                if can_reply:
+                    send_url = (
+                        f"https://open.feishu.cn/open-apis/im/v1/messages/"
+                        f"{msg.msg_id}/reply"
+                    )
+                    send_body = {"msg_type": "interactive", "content": content_payload}
+                    send_res = requests.post(
+                        send_url, headers=headers, json=send_body, timeout=(5, 10)
+                    )
+                else:
+                    send_url = "https://open.feishu.cn/open-apis/im/v1/messages"
+                    params = {"receive_id_type": receive_id_type}
+                    send_body = {
+                        "receive_id": receiver,
+                        "msg_type": "interactive",
+                        "content": content_payload,
+                    }
+                    send_res = requests.post(
+                        send_url, headers=headers, params=params, json=send_body,
+                        timeout=(5, 10),
+                    )
+                send_json = send_res.json()
+                if send_json.get("code") != 0:
+                    logger.warning(
+                        f"[FeiShu] Stream: send card failed: {send_json}. 降级为普通文本。"
+                    )
+                    with lock:
+                        disabled[0] = True
+                    return
+                mid = send_json["data"]["message_id"]
+                with lock:
+                    message_id[0] = mid
+                logger.info(
+                    f"[FeiShu] Stream: card created and sent, "
+                    f"card_id={cid}, message_id={mid}"
+                )
+            except Exception as e:
+                logger.warning(
+                    f"[FeiShu] Stream: create/send card exception: {e}. 降级为普通文本。"
+                )
+                with lock:
+                    disabled[0] = True
+            finally:
+                with lock:
+                    init_in_flight[0] = False
+
+        def _stream_update_text(full_text):
+            """PUT 流式更新文本组件。content 必须是当前组件的全量文本。"""
+            with lock:
+                cid = card_id[0]
+            if not cid:
+                return
+            url = (
+                f"https://open.feishu.cn/open-apis/cardkit/v1/cards/"
+                f"{cid}/elements/{ELEMENT_ID}/content"
+            )
+            body = {
+                "content": full_text,
+                "sequence": _next_sequence(),
+            }
+            try:
+                res = requests.put(url, headers=headers, json=body, timeout=(5, 10))
+                res_json = res.json()
+                if res_json.get("code") != 0:
+                    logger.warning(
+                        f"[FeiShu] Stream: update text failed: {res_json}"
+                    )
+            except Exception as e:
+                logger.warning(f"[FeiShu] Stream: update text exception: {e}")
+
+        def _close_streaming_mode(final_text: str = ""):
+            """关闭流式模式（卡片转入"普通"状态，可被转发）。
+
+            同时通过整卡更新接口把 summary 改成最终内容的预览，否则飞书会话列表
+            会一直显示创建卡片时的占位摘要（"[正在生成回复...]"）。
+            """
+            with lock:
+                cid = card_id[0]
+            if not cid:
+                return
+
+            # 1) 通过整卡更新接口把 streaming_mode 关掉，并改写 summary
+            #    （settings 接口的 config 不接受 summary 字段，会报 code=2200）
+            preview_src = (final_text or "").strip().replace("\n", " ")
+            preview = preview_src[:30] if preview_src else ""
+            full_card = {
+                "schema": "2.0",
+                "config": {
+                    "streaming_mode": False,
+                    "summary": {"content": preview or " "},
+                },
+                "body": {
+                    "elements": [
+                        {
+                            "tag": "markdown",
+                            "content": final_text or " ",
+                            "element_id": ELEMENT_ID,
+                        }
+                    ],
+                },
+            }
+            put_url = f"https://open.feishu.cn/open-apis/cardkit/v1/cards/{cid}"
+            put_body = {
+                "card": {"type": "card_json", "data": json.dumps(full_card, ensure_ascii=False)},
+                "sequence": _next_sequence(),
+            }
+            try:
+                res = requests.put(put_url, headers=headers, json=put_body, timeout=(5, 10))
+                res_json = res.json()
+                if res_json.get("code") != 0:
+                    logger.warning(
+                        f"[FeiShu] Stream: finalize card (close+summary) failed: {res_json}"
+                    )
+            except Exception as e:
+                logger.warning(
+                    f"[FeiShu] Stream: finalize card exception: {e}"
+                )
+
+        def on_event(event: dict):
+            event_type = event.get("type")
+            data = event.get("data", {})
+
+            # 一旦降级，本次回复不再做任何流式操作
+            with lock:
+                if disabled[0]:
+                    return
+
+            if event_type == "message_update":
+                delta = data.get("delta", "")
+                if not delta:
+                    return
+
+                # 第一段：判断是否需要初始化（创建卡片 + 发送）
+                need_init = False
+                with lock:
+                    if card_id[0] is None and not init_in_flight[0]:
+                        init_in_flight[0] = True
+                        need_init = True
+
+                if need_init:
+                    _create_and_send_card()
+                    # 初始化失败已标记 disabled，下次循环直接 return
+                    with lock:
+                        if disabled[0]:
+                            return
+
+                # 第二段：累加文本，把快照丢给 push worker 异步推送。
+                # 这里不能直接 requests.put，否则会阻塞 LLM stream 线程读下一个 chunk
+                # （实测 DeepSeek 高频小 chunk 场景每个 PUT ~150ms，累积起来非常卡）。
+                snapshot = ""
+                should_push = False
+                with lock:
+                    current_text[0] += delta
+                    if card_id[0]:
+                        snapshot = current_text[0]
+                        should_push = True
+
+                if should_push:
+                    push_queue.put(snapshot)
+
+            elif event_type == "message_end":
+                # 一轮 LLM 输出结束。如果本轮触发了工具调用，说明当前轮的文本是
+                # "中间过场消息"（如"来看看！"），应该作为独立卡片定型，然后为下一轮
+                # 重新创建一张新卡片。这样最终用户看到的是：
+                #   [卡片1: 中间过场1]
+                #   [卡片2: 中间过场2]
+                #   ...
+                #   [卡片N: 最终回复]
+                # 与 wecom_bot 的多消息流式体验对齐。
+                tool_calls = data.get("tool_calls", []) or []
+                if not tool_calls:
+                    # 没有工具调用：本轮即最终回复，留给 agent_end 统一处理。
+                    return
+
+                with lock:
+                    text_to_finalize = current_text[0].rstrip()
+                    current_text[0] = ""
+
+                if not text_to_finalize:
+                    return
+
+                # 等异步队列里堆积的快照都推完，避免它们晚于 final 文本到达把内容覆盖掉
+                _drain_push_queue()
+                # 用最终文本覆盖当前卡片并关闭流式模式（凝固成普通卡片，
+                # 同时把会话列表的 summary 改成预览，不再显示"正在生成回复..."）
+                _stream_update_text(text_to_finalize)
+                _close_streaming_mode(text_to_finalize)
+
+                # 重置卡片状态，下一段 message_update 会触发新卡片的创建
+                with lock:
+                    card_id[0] = None
+                    message_id[0] = None
+                    sequence[0] = 0
+
+            elif event_type == "agent_cancelled":
+                # Lock channel into "no-rewrite" mode: the subsequent
+                # agent_end's final_response is from the last *completed*
+                # turn (the user already saw it), so rewriting the card
+                # would duplicate it visually.
+                with lock:
+                    cancelled[0] = True
+
+            elif event_type == "agent_end":
+                # 最终回复：用 final_response 覆盖当前流式卡片，然后关闭流式模式。
+                final_response = data.get("final_response", "")
+                # 标记 streamed 让 chat_channel 跳过 send()
+                context["feishu_streamed"] = True
+
+                with lock:
+                    was_cancelled = cancelled[0]
+                    has_card = card_id[0] is not None
+                    init_busy = init_in_flight[0]
+                    pending_text = current_text[0]
+
+                if was_cancelled:
+                    # Cancelled path: finalize the in-flight card with
+                    # partial output (or a short marker if empty); drop
+                    # stale final_response to avoid duplicating last turn.
+                    if has_card:
+                        _drain_push_queue()
+                        partial = (pending_text or "").rstrip()
+                        final_text = partial or "_(已中止)_"
+                        _stream_update_text(final_text)
+                        _close_streaming_mode(final_text)
+                    push_queue.put(None)
+                    return
+
+                if not final_response:
+                    return
+                final_text = str(final_response)
+
+                # 罕见情况：agent_end 触发时还没创建过卡片（极快返回 / 没有
+                # message_update），主动创建一张承载 final_text。
+                if not has_card and not init_busy:
+                    with lock:
+                        init_in_flight[0] = True
+                    _create_and_send_card()
+                    with lock:
+                        if disabled[0]:
+                            return
+
+                _drain_push_queue()
+                _stream_update_text(final_text)
+                _close_streaming_mode(final_text)
+                # 通知 push worker 退出（本次回复彻底结束）
+                push_queue.put(None)
+
+        return on_event
+
     def fetch_access_token(self) -> str:
         url = "https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal/"
         headers = {
@@ -622,6 +1340,66 @@ class FeiShuChanel(ChatChannel):
                 except Exception as e:
                     logger.warning(f"[FeiShu] Failed to remove temp file {temp_file}: {e}")
 
+    def _upload_audio(self, audio_path, access_token):
+        """
+        Upload a local audio file to Feishu and return file_key.
+        audio_path is a plain local file path (no file:// prefix).
+        Feishu audio messages only support opus format; non-opus files are converted first.
+        """
+        logger.debug(f"[FeiShu] start upload audio, path={audio_path}")
+
+        if not os.path.exists(audio_path):
+            logger.error(f"[FeiShu] audio file not found: {audio_path}")
+            return None
+
+        # Feishu only plays audio messages in opus format.
+        # Convert if the TTS engine produced a different format (e.g. mp3 from OpenAI TTS).
+        upload_path = audio_path
+        if not audio_path.lower().endswith('.opus'):
+            opus_path = os.path.splitext(audio_path)[0] + '.opus'
+            try:
+                from pydub import AudioSegment
+                audio = AudioSegment.from_file(audio_path)
+                audio.export(opus_path, format='opus')
+                upload_path = opus_path
+                logger.info(f"[FeiShu] Converted audio to opus: {opus_path}")
+            except Exception as e:
+                logger.warning(f"[FeiShu] Failed to convert audio to opus, uploading original: {e}")
+                upload_path = audio_path
+
+        file_name = os.path.splitext(os.path.basename(upload_path))[0] + '.opus'
+        upload_url = "https://open.feishu.cn/open-apis/im/v1/files"
+        data = {'file_type': 'opus', 'file_name': file_name}
+        headers = {'Authorization': f'Bearer {access_token}'}
+
+        try:
+            with open(upload_path, "rb") as f:
+                upload_response = requests.post(
+                    upload_url,
+                    files={"file": f},
+                    data=data,
+                    headers=headers,
+                    timeout=(5, 30)
+                )
+                logger.info(
+                    f"[FeiShu] upload audio response, status={upload_response.status_code}, res={upload_response.content}")
+                response_data = upload_response.json()
+                if response_data.get("code") == 0:
+                    return response_data.get("data").get("file_key")
+                else:
+                    logger.error(f"[FeiShu] upload audio failed: {response_data}")
+                    return None
+        except Exception as e:
+            logger.error(f"[FeiShu] upload audio exception: {e}")
+            return None
+        finally:
+            # 无论上传成功与否都清理转换产生的临时 opus 文件，避免失败路径下磁盘堆积。
+            if upload_path != audio_path and os.path.exists(upload_path):
+                try:
+                    os.remove(upload_path)
+                except Exception as e:
+                    logger.warning(f"[FeiShu] Failed to remove temp opus file {upload_path}: {e}")
+
     def _upload_file_url(self, file_url, access_token):
         """
         Upload file to Feishu
@@ -764,10 +1542,16 @@ class FeiShuChanel(ChatChannel):
             else:
                 context.type = ContextType.TEXT
             context.content = content.strip()
+            # Text input opts into voice replies only when the always-on toggle is set.
+            if "desire_rtype" not in context and conf().get("always_reply_voice"):
+                context["desire_rtype"] = ReplyType.VOICE
 
         elif context.type == ContextType.VOICE:
-            # 2.语音请求
+            # 2.语音请求: voice input replies with voice if either
-            if "desire_rtype" not in context and conf().get("voice_reply_voice"):
+            # voice_reply_voice (mirror reply) or always_reply_voice is on.
+            if "desire_rtype" not in context and (
+                conf().get("voice_reply_voice") or conf().get("always_reply_voice")
+            ):
                 context["desire_rtype"] = ReplyType.VOICE
 
         return context

channel/feishu/feishu_message.py

@@ -144,7 +144,14 @@ class FeishuMessage(ChatMessage):
             file_key = content.get("file_key")
             file_name = content.get("file_name")
 
-            self.content = TmpDir().path() + file_key + "." + utils.get_path_suffix(file_name)
+            # 落到 agent_workspace/tmp 下（绝对路径），与图片处理一致；
+            # 否则相对路径 ./tmp 在 agent 工作区里 read 时会找不到。
+            workspace_root = expand_path(conf().get("agent_workspace", "~/cow"))
+            tmp_dir = os.path.join(workspace_root, "tmp")
+            os.makedirs(tmp_dir, exist_ok=True)
+            self.content = os.path.join(
+                tmp_dir, f"{file_key}.{utils.get_path_suffix(file_name)}"
+            )
 
             def _download_file():
                 # 如果响应状态码是200，则将响应内容写入本地文件
@@ -162,6 +169,42 @@ class FeishuMessage(ChatMessage):
                 else:
                     logger.info(f"[FeiShu] Failed to download file, key={file_key}, res={response.text}")
             self._prepare_fn = _download_file
+        elif msg_type == "audio":
+            # 飞书用户发送的语音消息类型为 "audio"，文件为 opus 编码格式。
+            # 映射为 ContextType.VOICE，交由 chat_channel 的语音转文字（STT）流程处理。
+            # 文件通过 _prepare_fn 延迟下载，在 chat_channel 调用 cmsg.prepare() 时才执行。
+            self.ctype = ContextType.VOICE
+            content = json.loads(msg.get("content"))
+            file_key = content.get("file_key")
+
+            # 落到 agent_workspace/tmp 下（绝对路径），保证语音 STT 流程可读到
+            workspace_root = expand_path(conf().get("agent_workspace", "~/cow"))
+            tmp_dir = os.path.join(workspace_root, "tmp")
+            os.makedirs(tmp_dir, exist_ok=True)
+            self.content = os.path.join(tmp_dir, f"{file_key}.opus")
+            logger.info(f"[FeiShu] audio message: file_key={file_key}, save_path={self.content}")
+
+            def _download_audio():
+                logger.info(f"[FeiShu] downloading audio: file_key={file_key}, msg_id={self.msg_id}")
+                url = f"https://open.feishu.cn/open-apis/im/v1/messages/{self.msg_id}/resources/{file_key}"
+                headers = {
+                    "Authorization": "Bearer " + access_token,
+                }
+                params = {
+                    "type": "file"
+                }
+                try:
+                    response = requests.get(url=url, headers=headers, params=params)
+                    logger.info(f"[FeiShu] download audio response: status={response.status_code}, size={len(response.content)} bytes")
+                    if response.status_code == 200:
+                        with open(self.content, "wb") as f:
+                            f.write(response.content)
+                        logger.info(f"[FeiShu] audio saved to: {self.content}")
+                    else:
+                        logger.error(f"[FeiShu] Failed to download audio, key={file_key}, status={response.status_code}, res={response.text}")
+                except Exception as e:
+                    logger.error(f"[FeiShu] Exception downloading audio, key={file_key}: {e}", exc_info=True)
+            self._prepare_fn = _download_audio
         else:
             raise NotImplementedError("Unsupported message type: Type:{} ".format(msg_type))
 

channel/qq/qq_channel.py

@@ -0,0 +1,736 @@
+"""
+QQ Bot channel via WebSocket long connection.
+
+Supports:
+- Group chat (@bot), single chat (C2C), guild channel, guild DM
+- Text / image / file message send & receive
+- Heartbeat keep-alive and auto-reconnect with session resume
+"""
+
+import base64
+import json
+import os
+import threading
+import time
+
+import requests
+import websocket
+
+from bridge.context import Context, ContextType
+from bridge.reply import Reply, ReplyType
+from channel.chat_channel import ChatChannel, check_prefix
+from channel.qq.qq_message import QQMessage
+from common.expired_dict import ExpiredDict
+from common.log import logger
+from common.singleton import singleton
+from common.ws_client_compat import websocket_app_run_forever
+from config import conf
+
+# Rich media file_type constants
+QQ_FILE_TYPE_IMAGE = 1
+QQ_FILE_TYPE_VIDEO = 2
+QQ_FILE_TYPE_VOICE = 3
+QQ_FILE_TYPE_FILE = 4
+
+QQ_API_BASE = "https://api.sgroup.qq.com"
+
+# Intents: GROUP_AND_C2C_EVENT(1<<25) | PUBLIC_GUILD_MESSAGES(1<<30)
+DEFAULT_INTENTS = (1 << 25) | (1 << 30)
+
+# OpCode constants
+OP_DISPATCH = 0
+OP_HEARTBEAT = 1
+OP_IDENTIFY = 2
+OP_RESUME = 6
+OP_RECONNECT = 7
+OP_INVALID_SESSION = 9
+OP_HELLO = 10
+OP_HEARTBEAT_ACK = 11
+
+# Resumable error codes
+RESUMABLE_CLOSE_CODES = {4008, 4009}
+
+
+@singleton
+class QQChannel(ChatChannel):
+
+    def __init__(self):
+        super().__init__()
+        self.app_id = ""
+        self.app_secret = ""
+
+        self._access_token = ""
+        self._token_expires_at = 0
+
+        self._ws = None
+        self._ws_thread = None
+        self._heartbeat_thread = None
+        self._connected = False
+        self._stop_event = threading.Event()
+        self._token_lock = threading.Lock()
+
+        self._session_id = None
+        self._last_seq = None
+        self._heartbeat_interval = 45000
+        self._can_resume = False
+
+        self.received_msgs = ExpiredDict(60 * 60 * 7.1)
+        self._msg_seq_counter = {}
+
+        conf()["group_name_white_list"] = ["ALL_GROUP"]
+        conf()["single_chat_prefix"] = [""]
+
+    # ------------------------------------------------------------------
+    # Lifecycle
+    # ------------------------------------------------------------------
+
+    def startup(self):
+        self.app_id = conf().get("qq_app_id", "")
+        self.app_secret = conf().get("qq_app_secret", "")
+
+        if not self.app_id or not self.app_secret:
+            err = "[QQ] qq_app_id and qq_app_secret are required"
+            logger.error(err)
+            self.report_startup_error(err)
+            return
+
+        self._refresh_access_token()
+        if not self._access_token:
+            err = "[QQ] Failed to get initial access_token"
+            logger.error(err)
+            self.report_startup_error(err)
+            return
+
+        self._stop_event.clear()
+        self._start_ws()
+
+    def stop(self):
+        logger.info("[QQ] stop() called")
+        self._stop_event.set()
+        if self._ws:
+            try:
+                self._ws.close()
+            except Exception:
+                pass
+        self._ws = None
+        self._connected = False
+
+    # ------------------------------------------------------------------
+    # Access Token
+    # ------------------------------------------------------------------
+
+    def _refresh_access_token(self):
+        try:
+            resp = requests.post(
+                "https://bots.qq.com/app/getAppAccessToken",
+                json={"appId": self.app_id, "clientSecret": self.app_secret},
+                timeout=10,
+            )
+            resp.raise_for_status()
+            data = resp.json()
+            self._access_token = data.get("access_token", "")
+            expires_in = int(data.get("expires_in", 7200))
+            self._token_expires_at = time.time() + expires_in - 60
+            logger.debug(f"[QQ] Access token refreshed, expires_in={expires_in}s")
+        except Exception as e:
+            logger.error(f"[QQ] Failed to refresh access_token: {e}")
+
+    def _get_access_token(self) -> str:
+        with self._token_lock:
+            if time.time() >= self._token_expires_at:
+                self._refresh_access_token()
+            return self._access_token
+
+    def _get_auth_headers(self) -> dict:
+        return {
+            "Authorization": f"QQBot {self._get_access_token()}",
+            "Content-Type": "application/json",
+        }
+
+    # ------------------------------------------------------------------
+    # WebSocket connection
+    # ------------------------------------------------------------------
+
+    def _get_ws_url(self) -> str:
+        try:
+            resp = requests.get(
+                f"{QQ_API_BASE}/gateway",
+                headers=self._get_auth_headers(),
+                timeout=10,
+            )
+            resp.raise_for_status()
+            url = resp.json().get("url", "")
+            logger.debug(f"[QQ] Gateway URL: {url}")
+            return url
+        except Exception as e:
+            logger.error(f"[QQ] Failed to get gateway URL: {e}")
+            return ""
+
+    def _start_ws(self):
+        ws_url = self._get_ws_url()
+        if not ws_url:
+            logger.error("[QQ] Cannot start WebSocket without gateway URL")
+            self.report_startup_error("Failed to get gateway URL")
+            return
+
+        def _on_open(ws):
+            logger.debug("[QQ] WebSocket connected, waiting for Hello...")
+
+        def _on_message(ws, raw):
+            try:
+                data = json.loads(raw)
+                self._handle_ws_message(data)
+            except Exception as e:
+                logger.error(f"[QQ] Failed to handle ws message: {e}", exc_info=True)
+
+        def _on_error(ws, error):
+            logger.error(f"[QQ] WebSocket error: {error}")
+
+        def _on_close(ws, close_status_code, close_msg):
+            logger.warning(f"[QQ] WebSocket closed: status={close_status_code}, msg={close_msg}")
+            self._connected = False
+            if not self._stop_event.is_set():
+                if close_status_code in RESUMABLE_CLOSE_CODES and self._session_id:
+                    self._can_resume = True
+                    logger.info("[QQ] Will attempt resume in 3s...")
+                    time.sleep(3)
+                else:
+                    self._can_resume = False
+                    logger.info("[QQ] Will reconnect in 5s...")
+                    time.sleep(5)
+                if not self._stop_event.is_set():
+                    self._start_ws()
+
+        self._ws = websocket.WebSocketApp(
+            ws_url,
+            on_open=_on_open,
+            on_message=_on_message,
+            on_error=_on_error,
+            on_close=_on_close,
+        )
+
+        def run_forever():
+            try:
+                websocket_app_run_forever(self._ws, ping_interval=0, reconnect=0)
+            except (SystemExit, KeyboardInterrupt):
+                logger.info("[QQ] WebSocket thread interrupted")
+            except Exception as e:
+                logger.error(f"[QQ] WebSocket run_forever error: {e}")
+
+        self._ws_thread = threading.Thread(target=run_forever, daemon=True)
+        self._ws_thread.start()
+        self._ws_thread.join()
+
+    def _ws_send(self, data: dict):
+        if self._ws:
+            self._ws.send(json.dumps(data, ensure_ascii=False))
+
+    # ------------------------------------------------------------------
+    # Identify & Resume & Heartbeat
+    # ------------------------------------------------------------------
+
+    def _send_identify(self):
+        self._ws_send({
+            "op": OP_IDENTIFY,
+            "d": {
+                "token": f"QQBot {self._get_access_token()}",
+                "intents": DEFAULT_INTENTS,
+                "shard": [0, 1],
+                "properties": {
+                    "$os": "linux",
+                    "$browser": "chatgpt-on-wechat",
+                    "$device": "chatgpt-on-wechat",
+                },
+            },
+        })
+        logger.debug(f"[QQ] Identify sent with intents={DEFAULT_INTENTS}")
+
+    def _send_resume(self):
+        self._ws_send({
+            "op": OP_RESUME,
+            "d": {
+                "token": f"QQBot {self._get_access_token()}",
+                "session_id": self._session_id,
+                "seq": self._last_seq,
+            },
+        })
+        logger.debug(f"[QQ] Resume sent: session_id={self._session_id}, seq={self._last_seq}")
+
+    def _start_heartbeat(self, interval_ms: int):
+        if self._heartbeat_thread and self._heartbeat_thread.is_alive():
+            return
+        self._heartbeat_interval = interval_ms
+        interval_sec = interval_ms / 1000.0
+
+        def heartbeat_loop():
+            while not self._stop_event.is_set() and self._connected:
+                try:
+                    self._ws_send({
+                        "op": OP_HEARTBEAT,
+                        "d": self._last_seq,
+                    })
+                except Exception as e:
+                    logger.warning(f"[QQ] Heartbeat send failed: {e}")
+                    break
+                self._stop_event.wait(interval_sec)
+
+        self._heartbeat_thread = threading.Thread(target=heartbeat_loop, daemon=True)
+        self._heartbeat_thread.start()
+
+    # ------------------------------------------------------------------
+    # Incoming message dispatch
+    # ------------------------------------------------------------------
+
+    def _handle_ws_message(self, data: dict):
+        op = data.get("op")
+        d = data.get("d")
+        t = data.get("t")
+        s = data.get("s")
+
+        if s is not None:
+            self._last_seq = s
+
+        if op == OP_HELLO:
+            heartbeat_interval = d.get("heartbeat_interval", 45000) if d else 45000
+            logger.debug(f"[QQ] Received Hello, heartbeat_interval={heartbeat_interval}ms")
+            self._heartbeat_interval = heartbeat_interval
+            if self._can_resume and self._session_id:
+                self._send_resume()
+            else:
+                self._send_identify()
+
+        elif op == OP_HEARTBEAT_ACK:
+            pass
+
+        elif op == OP_HEARTBEAT:
+            self._ws_send({"op": OP_HEARTBEAT, "d": self._last_seq})
+
+        elif op == OP_RECONNECT:
+            logger.warning("[QQ] Server requested reconnect")
+            self._can_resume = True
+            if self._ws:
+                self._ws.close()
+
+        elif op == OP_INVALID_SESSION:
+            logger.warning("[QQ] Invalid session, re-identifying...")
+            self._session_id = None
+            self._can_resume = False
+            time.sleep(2)
+            self._send_identify()
+
+        elif op == OP_DISPATCH:
+            if t == "READY":
+                self._session_id = d.get("session_id", "")
+                user = d.get("user", {})
+                bot_name = user.get('username', '')
+                logger.info(f"[QQ] ✅ Connected successfully (bot={bot_name})")
+                self._connected = True
+                self._can_resume = False
+                self._start_heartbeat(self._heartbeat_interval)
+                self.report_startup_success()
+
+            elif t == "RESUMED":
+                logger.info("[QQ] Session resumed successfully")
+                self._connected = True
+                self._can_resume = False
+                self._start_heartbeat(self._heartbeat_interval)
+
+            elif t in ("GROUP_AT_MESSAGE_CREATE", "C2C_MESSAGE_CREATE",
+                        "AT_MESSAGE_CREATE", "DIRECT_MESSAGE_CREATE"):
+                self._handle_msg_event(d, t)
+
+            elif t in ("GROUP_ADD_ROBOT", "FRIEND_ADD"):
+                logger.info(f"[QQ] Event: {t}")
+
+            else:
+                logger.debug(f"[QQ] Dispatch event: {t}")
+
+    # ------------------------------------------------------------------
+    # Message event handling
+    # ------------------------------------------------------------------
+
+    def _handle_msg_event(self, event_data: dict, event_type: str):
+        msg_id = event_data.get("id", "")
+        if self.received_msgs.get(msg_id):
+            logger.debug(f"[QQ] Duplicate msg filtered: {msg_id}")
+            return
+        self.received_msgs[msg_id] = True
+
+        try:
+            qq_msg = QQMessage(event_data, event_type)
+        except NotImplementedError as e:
+            logger.warning(f"[QQ] {e}")
+            return
+        except Exception as e:
+            logger.error(f"[QQ] Failed to parse message: {e}", exc_info=True)
+            return
+
+        is_group = qq_msg.is_group
+
+        from channel.file_cache import get_file_cache
+        file_cache = get_file_cache()
+
+        if is_group:
+            session_id = qq_msg.other_user_id
+        else:
+            session_id = qq_msg.from_user_id
+
+        if qq_msg.ctype == ContextType.IMAGE:
+            if hasattr(qq_msg, "image_path") and qq_msg.image_path:
+                file_cache.add(session_id, qq_msg.image_path, file_type="image")
+                logger.info(f"[QQ] Image cached for session {session_id}")
+            return
+
+        if qq_msg.ctype == ContextType.TEXT:
+            cached_files = file_cache.get(session_id)
+            if cached_files:
+                file_refs = []
+                for fi in cached_files:
+                    ftype = fi["type"]
+                    fpath = fi["path"]
+                    if ftype == "image":
+                        file_refs.append(f"[图片: {fpath}]")
+                    elif ftype == "video":
+                        file_refs.append(f"[视频: {fpath}]")
+                    else:
+                        file_refs.append(f"[文件: {fpath}]")
+                qq_msg.content = qq_msg.content + "\n" + "\n".join(file_refs)
+                logger.info(f"[QQ] Attached {len(cached_files)} cached file(s)")
+                file_cache.clear(session_id)
+
+        context = self._compose_context(
+            qq_msg.ctype,
+            qq_msg.content,
+            isgroup=is_group,
+            msg=qq_msg,
+            no_need_at=True,
+        )
+        if context:
+            self.produce(context)
+
+    # ------------------------------------------------------------------
+    # _compose_context
+    # ------------------------------------------------------------------
+
+    def _compose_context(self, ctype: ContextType, content, **kwargs):
+        context = Context(ctype, content)
+        context.kwargs = kwargs
+        if "channel_type" not in context:
+            context["channel_type"] = self.channel_type
+        if "origin_ctype" not in context:
+            context["origin_ctype"] = ctype
+
+        cmsg = context["msg"]
+
+        if cmsg.is_group:
+            context["session_id"] = cmsg.other_user_id
+        else:
+            context["session_id"] = cmsg.from_user_id
+
+        context["receiver"] = cmsg.other_user_id
+
+        if ctype == ContextType.TEXT:
+            img_match_prefix = check_prefix(content, conf().get("image_create_prefix"))
+            if img_match_prefix:
+                content = content.replace(img_match_prefix, "", 1)
+                context.type = ContextType.IMAGE_CREATE
+            else:
+                context.type = ContextType.TEXT
+            context.content = content.strip()
+
+        return context
+
+    # ------------------------------------------------------------------
+    # Send reply
+    # ------------------------------------------------------------------
+
+    def send(self, reply: Reply, context: Context):
+        msg = context.get("msg")
+        is_group = context.get("isgroup", False)
+        receiver = context.get("receiver", "")
+
+        if not msg:
+            # Active send (e.g. scheduled tasks), no original message to reply to
+            self._active_send_text(reply.content if reply.type == ReplyType.TEXT else str(reply.content),
+                                   receiver, is_group)
+            return
+
+        event_type = getattr(msg, "event_type", "")
+        msg_id = getattr(msg, "msg_id", "")
+
+        if reply.type == ReplyType.TEXT:
+            self._send_text(reply.content, msg, event_type, msg_id)
+        elif reply.type in (ReplyType.IMAGE_URL, ReplyType.IMAGE):
+            self._send_image(reply.content, msg, event_type, msg_id)
+        elif reply.type == ReplyType.FILE:
+            if hasattr(reply, "text_content") and reply.text_content:
+                self._send_text(reply.text_content, msg, event_type, msg_id)
+                time.sleep(0.3)
+            self._send_file(reply.content, msg, event_type, msg_id)
+        elif reply.type in (ReplyType.VIDEO, ReplyType.VIDEO_URL):
+            self._send_media(reply.content, msg, event_type, msg_id, QQ_FILE_TYPE_VIDEO)
+        else:
+            logger.warning(f"[QQ] Unsupported reply type: {reply.type}, falling back to text")
+            self._send_text(str(reply.content), msg, event_type, msg_id)
+
+    # ------------------------------------------------------------------
+    # Send helpers
+    # ------------------------------------------------------------------
+
+    def _get_next_msg_seq(self, msg_id: str) -> int:
+        seq = self._msg_seq_counter.get(msg_id, 1)
+        self._msg_seq_counter[msg_id] = seq + 1
+        return seq
+
+    def _build_msg_url_and_base_body(self, msg: QQMessage, event_type: str, msg_id: str):
+        """Build the API URL and base body dict for sending a message."""
+        if event_type == "GROUP_AT_MESSAGE_CREATE":
+            group_openid = msg._rawmsg.get("group_openid", "")
+            url = f"{QQ_API_BASE}/v2/groups/{group_openid}/messages"
+            body = {
+                "msg_id": msg_id,
+                "msg_seq": self._get_next_msg_seq(msg_id),
+            }
+            return url, body, "group", group_openid
+
+        elif event_type == "C2C_MESSAGE_CREATE":
+            user_openid = msg._rawmsg.get("author", {}).get("user_openid", "") or msg.from_user_id
+            url = f"{QQ_API_BASE}/v2/users/{user_openid}/messages"
+            body = {
+                "msg_id": msg_id,
+                "msg_seq": self._get_next_msg_seq(msg_id),
+            }
+            return url, body, "c2c", user_openid
+
+        elif event_type == "AT_MESSAGE_CREATE":
+            channel_id = msg._rawmsg.get("channel_id", "")
+            url = f"{QQ_API_BASE}/channels/{channel_id}/messages"
+            body = {"msg_id": msg_id}
+            return url, body, "channel", channel_id
+
+        elif event_type == "DIRECT_MESSAGE_CREATE":
+            guild_id = msg._rawmsg.get("guild_id", "")
+            url = f"{QQ_API_BASE}/dms/{guild_id}/messages"
+            body = {"msg_id": msg_id}
+            return url, body, "dm", guild_id
+
+        return None, None, None, None
+
+    def _post_message(self, url: str, body: dict, event_type: str):
+        try:
+            resp = requests.post(url, json=body, headers=self._get_auth_headers(), timeout=10)
+            if resp.status_code in (200, 201, 202, 204):
+                logger.info(f"[QQ] Message sent successfully: event_type={event_type}")
+            else:
+                logger.error(f"[QQ] Failed to send message: status={resp.status_code}, "
+                             f"body={resp.text}")
+        except Exception as e:
+            logger.error(f"[QQ] Send message error: {e}")
+
+    # ------------------------------------------------------------------
+    # Active send (no original message, e.g. scheduled tasks)
+    # ------------------------------------------------------------------
+
+    def _active_send_text(self, content: str, receiver: str, is_group: bool):
+        """Send text without an original message (active push). QQ limits active messages to 4/month per user."""
+        if not receiver:
+            logger.warning("[QQ] No receiver for active send")
+            return
+        if is_group:
+            url = f"{QQ_API_BASE}/v2/groups/{receiver}/messages"
+        else:
+            url = f"{QQ_API_BASE}/v2/users/{receiver}/messages"
+        body = {
+            "content": content,
+            "msg_type": 0,
+        }
+        event_label = "GROUP_ACTIVE" if is_group else "C2C_ACTIVE"
+        self._post_message(url, body, event_label)
+
+    # ------------------------------------------------------------------
+    # Send text
+    # ------------------------------------------------------------------
+
+    def _send_text(self, content: str, msg: QQMessage, event_type: str, msg_id: str):
+        url, body, _, _ = self._build_msg_url_and_base_body(msg, event_type, msg_id)
+        if not url:
+            logger.warning(f"[QQ] Cannot send reply for event_type: {event_type}")
+            return
+        body["content"] = content
+        body["msg_type"] = 0
+        self._post_message(url, body, event_type)
+
+    # ------------------------------------------------------------------
+    # Rich media upload & send (image / video / file)
+    # ------------------------------------------------------------------
+
+    def _upload_rich_media(self, file_url: str, file_type: int, msg: QQMessage,
+                           event_type: str) -> str:
+        """
+        Upload media via QQ rich media API and return file_info.
+        For group: POST /v2/groups/{group_openid}/files
+        For c2c:   POST /v2/users/{openid}/files
+        """
+        if event_type == "GROUP_AT_MESSAGE_CREATE":
+            group_openid = msg._rawmsg.get("group_openid", "")
+            upload_url = f"{QQ_API_BASE}/v2/groups/{group_openid}/files"
+        elif event_type == "C2C_MESSAGE_CREATE":
+            user_openid = (msg._rawmsg.get("author", {}).get("user_openid", "")
+                           or msg.from_user_id)
+            upload_url = f"{QQ_API_BASE}/v2/users/{user_openid}/files"
+        else:
+            logger.warning(f"[QQ] Rich media upload not supported for event_type: {event_type}")
+            return ""
+
+        upload_body = {
+            "file_type": file_type,
+            "url": file_url,
+            "srv_send_msg": False,
+        }
+
+        try:
+            resp = requests.post(
+                upload_url, json=upload_body,
+                headers=self._get_auth_headers(), timeout=30,
+            )
+            if resp.status_code in (200, 201):
+                data = resp.json()
+                file_info = data.get("file_info", "")
+                logger.info(f"[QQ] Rich media uploaded: file_type={file_type}, "
+                            f"file_uuid={data.get('file_uuid', '')}")
+                return file_info
+            else:
+                logger.error(f"[QQ] Rich media upload failed: status={resp.status_code}, "
+                             f"body={resp.text}")
+                return ""
+        except Exception as e:
+            logger.error(f"[QQ] Rich media upload error: {e}")
+            return ""
+
+    def _upload_rich_media_base64(self, file_path: str, file_type: int, msg: QQMessage,
+                                  event_type: str) -> str:
+        """Upload local file via base64 file_data field."""
+        if event_type == "GROUP_AT_MESSAGE_CREATE":
+            group_openid = msg._rawmsg.get("group_openid", "")
+            upload_url = f"{QQ_API_BASE}/v2/groups/{group_openid}/files"
+        elif event_type == "C2C_MESSAGE_CREATE":
+            user_openid = (msg._rawmsg.get("author", {}).get("user_openid", "")
+                           or msg.from_user_id)
+            upload_url = f"{QQ_API_BASE}/v2/users/{user_openid}/files"
+        else:
+            logger.warning(f"[QQ] Rich media upload not supported for event_type: {event_type}")
+            return ""
+
+        try:
+            with open(file_path, "rb") as f:
+                file_data = base64.b64encode(f.read()).decode("utf-8")
+        except Exception as e:
+            logger.error(f"[QQ] Failed to read file for upload: {e}")
+            return ""
+
+        upload_body = {
+            "file_type": file_type,
+            "file_data": file_data,
+            "srv_send_msg": False,
+        }
+
+        try:
+            resp = requests.post(
+                upload_url, json=upload_body,
+                headers=self._get_auth_headers(), timeout=30,
+            )
+            if resp.status_code in (200, 201):
+                data = resp.json()
+                file_info = data.get("file_info", "")
+                logger.info(f"[QQ] Rich media uploaded (base64): file_type={file_type}, "
+                            f"file_uuid={data.get('file_uuid', '')}")
+                return file_info
+            else:
+                logger.error(f"[QQ] Rich media upload (base64) failed: status={resp.status_code}, "
+                             f"body={resp.text}")
+                return ""
+        except Exception as e:
+            logger.error(f"[QQ] Rich media upload (base64) error: {e}")
+            return ""
+
+    def _send_media_msg(self, file_info: str, msg: QQMessage, event_type: str, msg_id: str):
+        """Send a message with msg_type=7 (rich media) using file_info."""
+        url, body, _, _ = self._build_msg_url_and_base_body(msg, event_type, msg_id)
+        if not url:
+            return
+        body["msg_type"] = 7
+        body["media"] = {"file_info": file_info}
+        self._post_message(url, body, event_type)
+
+    def _send_image(self, img_path_or_url: str, msg: QQMessage, event_type: str, msg_id: str):
+        """Send image reply. Supports URL and local file path."""
+        if event_type not in ("GROUP_AT_MESSAGE_CREATE", "C2C_MESSAGE_CREATE"):
+            self._send_text(str(img_path_or_url), msg, event_type, msg_id)
+            return
+
+        if img_path_or_url.startswith("file://"):
+            img_path_or_url = img_path_or_url[7:]
+
+        if img_path_or_url.startswith(("http://", "https://")):
+            file_info = self._upload_rich_media(
+                img_path_or_url, QQ_FILE_TYPE_IMAGE, msg, event_type)
+        elif os.path.exists(img_path_or_url):
+            file_info = self._upload_rich_media_base64(
+                img_path_or_url, QQ_FILE_TYPE_IMAGE, msg, event_type)
+        else:
+            logger.error(f"[QQ] Image not found: {img_path_or_url}")
+            self._send_text("[Image send failed]", msg, event_type, msg_id)
+            return
+
+        if file_info:
+            self._send_media_msg(file_info, msg, event_type, msg_id)
+        else:
+            self._send_text("[Image upload failed]", msg, event_type, msg_id)
+
+    def _send_file(self, file_path_or_url: str, msg: QQMessage, event_type: str, msg_id: str):
+        """Send file reply."""
+        if event_type not in ("GROUP_AT_MESSAGE_CREATE", "C2C_MESSAGE_CREATE"):
+            self._send_text(str(file_path_or_url), msg, event_type, msg_id)
+            return
+
+        if file_path_or_url.startswith("file://"):
+            file_path_or_url = file_path_or_url[7:]
+
+        if file_path_or_url.startswith(("http://", "https://")):
+            file_info = self._upload_rich_media(
+                file_path_or_url, QQ_FILE_TYPE_FILE, msg, event_type)
+        elif os.path.exists(file_path_or_url):
+            file_info = self._upload_rich_media_base64(
+                file_path_or_url, QQ_FILE_TYPE_FILE, msg, event_type)
+        else:
+            logger.error(f"[QQ] File not found: {file_path_or_url}")
+            self._send_text("[File send failed]", msg, event_type, msg_id)
+            return
+
+        if file_info:
+            self._send_media_msg(file_info, msg, event_type, msg_id)
+        else:
+            self._send_text("[File upload failed]", msg, event_type, msg_id)
+
+    def _send_media(self, path_or_url: str, msg: QQMessage, event_type: str,
+                    msg_id: str, file_type: int):
+        """Generic media send for video/voice etc."""
+        if event_type not in ("GROUP_AT_MESSAGE_CREATE", "C2C_MESSAGE_CREATE"):
+            self._send_text(str(path_or_url), msg, event_type, msg_id)
+            return
+
+        if path_or_url.startswith("file://"):
+            path_or_url = path_or_url[7:]
+
+        if path_or_url.startswith(("http://", "https://")):
+            file_info = self._upload_rich_media(path_or_url, file_type, msg, event_type)
+        elif os.path.exists(path_or_url):
+            file_info = self._upload_rich_media_base64(path_or_url, file_type, msg, event_type)
+        else:
+            logger.error(f"[QQ] Media not found: {path_or_url}")
+            return
+
+        if file_info:
+            self._send_media_msg(file_info, msg, event_type, msg_id)
+        else:
+            logger.error(f"[QQ] Media upload failed: {path_or_url}")