feat(browser): reuse system Chrome/Edge, bundle playwright for desktop

feat(mcp): auto OAuth authorization for remote MCP servers

.github/ISSUE_TEMPLATE/1.bug.yml

@@ -1,131 +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
-        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
+        > 💡 English is recommended so global developers can help. 推荐使用英文提交，谢谢 ❤️
   - 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
-      description: >
-        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
-        或相关日志的关键词来查找是否存在类似问题。
-      options:
-        - label: 我已经搜索过issues和disscussions，没有跟我遇到的问题相关的issue
-          required: true
-  - type: markdown
-    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:
-        - wechatmp(公众号, 订阅号)
-        - wechatmp_service(公众号, 服务号)
-        - terminal
-        - other
+      label: Environment
+      description: "Version (`cow status`), OS, Python version, install method, model & channel."
+      placeholder: |
+        Version: v1.2.0
+        OS: macOS / Linux / Windows / Docker
+        Python: 3.11
+        Install: installer / Docker / source
+        Model & channel: deepseek-v4-flash, web
     validations:
       required: true
   - type: textarea
     attributes:
-      label: 复现步骤 🕹
-      description: |
-        **⚠️ 不能复现将会关闭issue.**
-  - type: textarea
-    attributes:
-      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。
+      label: What happened?
+      description: "Steps to reproduce, what you expected, and what happened instead. Screenshots welcome."
+      placeholder: |
+        1. ...
+        2. ...
 
-        <details>
-        <summary><i>示例</i></summary>
-        ```log
-        [DEBUG][2023-04-16 00:23:22][plugin_manager.py:157] - Plugin SUMMARY triggered by event Event.ON_HANDLE_CONTEXT
-        [DEBUG][2023-04-16 00:23:22][main.py:221] - [Summary] on_handle_context. content: $总结前100条消息
-        [DEBUG][2023-04-16 00:23:24][main.py:240] - [Summary] limit: 100, duration: -1 seconds
-        [ERROR][2023-04-16 00:23:24][chat_channel.py:244] - Worker return exception: name 'start_date' is not defined
-        Traceback (most recent call last):
-          File "C:\ProgramData\Anaconda3\lib\concurrent\futures\thread.py", line 57, in run
-            result = self.fn(*self.args, **self.kwargs)
-          File "D:\project\chatgpt-on-wechat\channel\chat_channel.py", line 132, in _handle
-            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>
-        ```
+        Expected: ...
+        Actual: ...
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: Logs
+      description: "Relevant logs from `run.log` (set `\"debug\": true` for more detail). ⚠️ Redact your API keys."
+      render: shell
+    validations:
+      required: false

.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
-      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。
+      label: Self check
       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
-      description: 描述feature的功能。
+      label: What's the problem?
+      description: "The pain point or what's not working for you right now."
+    validations:
+      required: true
   - type: textarea
     attributes:
-      label: 举例
-      description: 提供聊天示例，草图或相关网址。
-  - type: textarea
+      label: What would you like?
+      description: "How you'd expect it to work. Examples, sketches, or links welcome."
+    validations:
+      required: false
+  - type: checkboxes
     attributes:
-      label: 动机
-      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。
+      label: Contribution
+      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/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 +1,336 @@
+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
+
+      # Download the Windows signing CLI. The URL comes from a repo variable, so
+      # nothing about the signing setup is hardcoded in a public workflow. Only
+      # runs on the Windows leg and only when a URL is set; otherwise the build
+      # stays unsigned. SIGNTOOL_PATH is exported for the next step's
+      # electron-builder.win.js to invoke.
+      - name: Download Windows signing CLI
+        if: matrix.platform == 'win' && vars.SIGNTOOL_CLI_URL != ''
+        shell: bash
+        env:
+          SIGNTOOL_CLI_URL: ${{ vars.SIGNTOOL_CLI_URL }}
+        run: |
+          mkdir -p "$RUNNER_TEMP/signtool"
+          curl -fsSL "$SIGNTOOL_CLI_URL" -o "$RUNNER_TEMP/signtool/cli.zip"
+          # Unzip and locate the signtool executable regardless of nesting.
+          unzip -o "$RUNNER_TEMP/signtool/cli.zip" -d "$RUNNER_TEMP/signtool" >/dev/null
+          exe="$(find "$RUNNER_TEMP/signtool" -type f -iname 'signtool*.exe' | head -n1)"
+          if [ -z "$exe" ]; then
+            echo "signtool.exe not found in downloaded archive" >&2
+            find "$RUNNER_TEMP/signtool" -type f >&2
+            exit 1
+          fi
+          # Normalize to a Windows-style path for execFileSync in Node.
+          echo "SIGNTOOL_PATH=$(cygpath -w "$exe")" >> "$GITHUB_ENV"
+          echo "resolved signtool: $exe"
+
+      - 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 }}
+          # Windows code signing via the signing CLI. Credentials are
+          # secrets; SIGNTOOL_PATH was exported by the download step above.
+          # COW_SIGN_DRY_RUN (repo variable) lets us validate the whole pipeline
+          # with a self-signed cert before buying a real one — no quota used.
+          SIGNTOOL_ACCESS_KEY: ${{ secrets.SIGNTOOL_ACCESS_KEY }}
+          SIGNTOOL_ACCESS_SECRET: ${{ secrets.SIGNTOOL_ACCESS_SECRET }}
+          SIGNTOOL_CERT_CODE: ${{ secrets.SIGNTOOL_CERT_CODE }}
+          COW_SIGN_DRY_RUN: ${{ vars.COW_SIGN_DRY_RUN }}
+        run: |
+          # Pick the signing cert for THIS platform only. The mac and win secrets
+          # are both present in the job env, but a mac cert must never leak into a
+          # Windows build (electron-builder would try to load it and fail), and
+          # vice versa. electron-builder reads a single CSC_LINK/CSC_KEY_PASSWORD
+          # pair, so we set it per-platform. An empty CSC_LINK is treated by
+          # electron-builder as a broken cert path, so we leave it entirely unset
+          # for an unsigned build.
+          #
+          # NOTE: we only ever `export`, never `unset`, GitHub-injected env vars
+          # (an `unset` can return non-zero and abort under errexit).
+          # macOS keeps the classic CSC_LINK (.p12) flow. Windows no longer uses
+          # a local .pfx (EV private keys can't be exported since 2023); it signs
+          # via the CLI wired into electron-builder.win.js instead, using the
+          # SIGNTOOL_* env already set above — nothing to export here.
+          case "${{ matrix.platform }}" in
+            mac)
+              if [ -n "$MAC_CSC_LINK" ]; then
+                export CSC_LINK="$MAC_CSC_LINK"
+                export CSC_KEY_PASSWORD="$MAC_CSC_KEY_PASSWORD"
+              fi
+              ;;
+          esac
+
+          # Never let electron-builder publish: our publish target is a generic
+          # (read-only) feed served from R2/D1, which it can't upload to. We mirror
+          # installers to R2 and register them in D1 ourselves (publish-r2 job).
+          # `--publish never` still emits the latest*.yml files.
+          #
+          # CONFIG PER PLATFORM: each platform loads its OWN dynamic config.
+          #   mac -> electron-builder.js     (injects mac.binaries for signing)
+          #   win -> electron-builder.win.js (wires the sign hook; electron-builder
+          #                                   signs the app, backend and installer)
+          # HISTORY: passing --config on Windows previously broke the build (no
+          # installer, job still green). That happened because the MAC config
+          # (electron-builder.js) was a no-op on Windows yet still disturbed the
+          # run. The fix is a DEDICATED win config that correctly extends
+          # config.win — not sharing the mac one. If a build ever runs WITHOUT
+          # signing configured, electron-builder.win.js still returns the base
+          # config unchanged (sign hook just skips), so the installer is still
+          # produced.
+          #
+          # Invoke via `node <cli.js>` rather than `npx`: on Windows `npx` is
+          # npx.cmd (a batch wrapper) and running it from this Git Bash step can
+          # make bash return before the wrapped process finishes. node skips it.
+          case "${{ matrix.platform }}" in
+            mac) config_arg="--config electron-builder.js" ;;
+            win) config_arg="--config electron-builder.win.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

@@ -32,7 +32,6 @@ plugins/banwords/lib/__pycache__
 !plugins/role
 !plugins/keyword
 !plugins/linkai
-!plugins/agent
 !plugins/cow_cli
 client_config.json
 ref/
@@ -46,3 +45,20 @@ 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

@@ -49,6 +49,16 @@ class ChatService:
             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()
 
@@ -171,6 +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,
@@ -180,6 +196,7 @@ class ChatService:
             on_event=on_event,
             messages=messages_copy,
             max_context_turns=max_context_turns,
+            cancel_event=cancel_event,
         )
 
         try:
@@ -191,6 +208,15 @@ 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
 
         # Sync executor messages back to agent (thread-safe).
         # The executor may have trimmed context, making its list shorter than
@@ -254,10 +280,68 @@ 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:

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

@@ -12,11 +12,17 @@ Knowledge file layout (under workspace_root):
 
 import os
 import re
+import asyncio
+import shutil
+import threading
 from pathlib import Path
-from typing import Optional
+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:
@@ -25,9 +31,389 @@ class KnowledgeService:
     Operates directly on the filesystem.
     """
 
-    def __init__(self, workspace_root: str):
-        self.workspace_root = workspace_root
-        self.knowledge_dir = os.path.join(workspace_root, "knowledge")
+    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
@@ -98,14 +484,18 @@ class KnowledgeService:
                 if not is_root:
                     stats["pages"] += 1
                     stats["size"] += size
-                title = name.replace(".md", "")
-                try:
-                    with open(full, "r", encoding="utf-8") as f:
-                        first_line = f.readline().strip()
-                    if first_line.startswith("# "):
-                        title = first_line[2:].strip()
-                except Exception:
-                    pass
+                # 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
 
@@ -121,15 +511,8 @@ class KnowledgeService:
         :raises ValueError: if path is invalid or escapes knowledge dir
         :raises FileNotFoundError: if file does not exist
         """
-        if not rel_path or ".." in rel_path:
-            raise ValueError("invalid path")
-
-        full_path = os.path.normpath(os.path.join(self.knowledge_dir, rel_path))
-        allowed = os.path.normpath(self.knowledge_dir)
-        if not full_path.startswith(allowed + os.sep) and full_path != allowed:
-            raise ValueError("path outside knowledge dir")
-
-        if not os.path.isfile(full_path):
+        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:
@@ -228,13 +611,35 @@ class KnowledgeService:
                 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

@@ -7,7 +7,7 @@ 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
 
@@ -17,6 +17,7 @@ __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/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
@@ -109,6 +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.
@@ -210,7 +253,10 @@ def _group_into_display_turns(
         if 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})
 
         # Build an ordered list of steps preserving the original sequence:
@@ -265,6 +311,18 @@ def _group_into_display_turns(
                 step["result"] = tr.get("result", "")
                 step["is_error"] = tr.get("is_error", False)
 
+        # Detect a self-evolution bubble BEFORE cleaning the marker away, so the
+        # 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",
@@ -272,6 +330,8 @@ def _group_into_display_turns(
                 "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)
@@ -291,7 +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()
 
     # ------------------------------------------------------------------
@@ -509,6 +569,65 @@ class ConversationStore:
             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:
@@ -524,6 +643,109 @@ 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,
@@ -1053,3 +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/__init__.py

@@ -16,6 +16,7 @@ from agent.memory.embedding.provider import (
     OpenAIEmbeddingProvider,
     create_embedding_provider,
 )
+from agent.memory.embedding.factory import create_default_embedding_provider
 from agent.memory.embedding.rebuild import (
     RebuildResult,
     clear_index,
@@ -33,6 +34,7 @@ __all__ = [
     "EmbeddingProvider",
     "OpenAIEmbeddingProvider",
     "create_embedding_provider",
+    "create_default_embedding_provider",
     "RebuildResult",
     "clear_index",
     "rebuild_in_process",

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

@@ -7,10 +7,14 @@ Supports multiple OpenAI-compatible embedding vendors:
   - 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.
 """
@@ -138,6 +142,22 @@ EMBEDDING_VENDORS = {
         "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,
+    },
 }
 
 
@@ -472,10 +492,19 @@ def create_embedding_provider(
         )
 
     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=model or meta["default_model"],
+        model=resolved_model,
         api_key=api_key,
-        api_base=api_base or meta["default_base_url"],
+        api_base=resolved_base,
         extra_headers=extra_headers,
         dimensions=final_dim,
         supports_dim_param=meta["supports_dim_param"],

agent/memory/embedding/rebuild.py

@@ -163,10 +163,9 @@ def main() -> int:
     logger.info(f"[RebuildIndex] Workspace: {workspace_root}")
     logger.info(f"[RebuildIndex] Index db:  {memory_config.get_db_path()}")
 
-    from bridge.agent_initializer import AgentInitializer
+    from agent.memory.embedding import create_default_embedding_provider
 
-    initializer = AgentInitializer(bridge=None, agent_bridge=None)
-    embedding_provider = initializer._init_embedding_provider(memory_config, session_id=None)
+    embedding_provider = create_default_embedding_provider()
     if embedding_provider is None:
         logger.error(
             "[RebuildIndex] No embedding provider could be initialized. "

agent/memory/embedding/state.py

@@ -31,9 +31,13 @@ def detect_index_dim(storage) -> Optional[int]:
     if not row or not row["embedding"]:
         return None
     try:
-        emb = json.loads(row["embedding"])
+        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):
+    except (json.JSONDecodeError, TypeError, Exception):
         return None
 
 

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 EmbeddingProvider
+from agent.memory.embedding import EmbeddingProvider, EmbeddingCache
 from agent.memory.summarizer import MemoryFlushManager, create_memory_files_if_needed
 
 
@@ -61,7 +61,11 @@ class MemoryManager:
             logger.info(
                 "[MemoryManager] No embedding provider; memory will use keyword search only"
             )
-        
+
+        # Cache for query embeddings (avoids redundant API calls within a session)
+        self._embedding_cache = EmbeddingCache()
+
+
         # Initialize memory flush manager
         workspace_dir = self.config.get_workspace()
         self.flush_manager = MemoryFlushManager(
@@ -128,7 +132,14 @@ class MemoryManager:
         vector_results = []
         if self.embedding_provider:
             try:
-                query_embedding = self.embedding_provider.embed_query(query)
+                provider_name = type(self.embedding_provider).__name__
+                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,

agent/memory/service.py

@@ -34,13 +34,18 @@ class MemoryService:
     # ------------------------------------------------------------------
     def list_files(self, page: int = 1, page_size: int = 20, category: str = "memory") -> dict:
         """
-        List memory or dream files with metadata (without content).
+        List memory, dream, or evolution files with metadata (without content).
 
         Args:
             category: ``"memory"`` (default) — MEMORY.md + daily files;
-                      ``"dream"``  — dream diary files from memory/dreams/
+                      ``"dream"``     — dream diary files from memory/dreams/;
+                      ``"evolution"`` — self-evolution logs from memory/evolution/
+                                        merged with the nightly dream diaries, so
+                                        one tab shows everything the agent learned.
         """
-        if category == "dream":
+        if category == "evolution":
+            files = self._list_evolution_files()
+        elif category == "dream":
             files = self._list_dream_files()
         else:
             files = self._list_memory_files()
@@ -93,6 +98,26 @@ class MemoryService:
 
         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
     # ------------------------------------------------------------------
@@ -101,7 +126,7 @@ class MemoryService:
         Read the full content of a memory or dream file.
 
         :param filename: File name, e.g. ``MEMORY.md``, ``2026-02-20.md``
-        :param category: ``"memory"`` or ``"dream"``
+        :param category: ``"memory"``, ``"dream"`` or ``"evolution"``
         :return: dict with ``filename`` and ``content``
         :raises FileNotFoundError: if the file does not exist
         """
@@ -125,7 +150,7 @@ class MemoryService:
         Dispatch a memory management action.
 
         :param action: ``list`` or ``content``
-        :param payload: action-specific payload (supports ``category``: ``"memory"`` | ``"dream"``)
+        :param payload: action-specific payload (supports ``category``: ``"memory"`` | ``"dream"`` | ``"evolution"``)
         :return: protocol-compatible response dict
         """
         payload = payload or {}
@@ -166,6 +191,7 @@ class MemoryService:
         - ``MEMORY.md`` → ``{workspace_root}/MEMORY.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.
         """
@@ -173,6 +199,8 @@ class MemoryService:
             base_dir = self.workspace_root
         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
 

agent/memory/storage.py

@@ -5,12 +5,42 @@ Provides vector and keyword search capabilities
 """
 
 from __future__ import annotations
+import re
 import sqlite3
 import json
 import hashlib
+import threading
 from typing import List, Dict, Optional, Any
 from pathlib import Path
 from dataclasses import dataclass
+try:
+    import numpy as np
+    _HAS_NUMPY = True
+except ImportError:
+    _HAS_NUMPY = False
+    np = None  # type: ignore[assignment]
+
+# UPSERT (INSERT … ON CONFLICT DO UPDATE) requires SQLite ≥ 3.24.0 (2018).
+# Older systems (e.g. CentOS 7 ships SQLite 3.7) fall back to INSERT OR REPLACE,
+# which risks FTS5 rowid drift on chunk updates (see save_chunk docstring).
+_HAS_UPSERT = sqlite3.sqlite_version_info >= (3, 24, 0)
+
+# ---------------------------------------------------------------------------
+# CJK character ranges, compiled once at module load.
+# Covers: CJK Symbols/Punctuation, Japanese kana (hiragana + katakana),
+#         CJK Unified Ideographs + Extension A, Korean syllables (Hangul),
+#         CJK Compatibility Ideographs, and CJK Extension B–F.
+# ---------------------------------------------------------------------------
+_CJK_RANGES = (
+    r'\u3000-\u30ff'          # CJK Symbols/Punctuation + Japanese kana
+    r'\u3400-\u9fff'          # CJK Unified Ideographs (incl. Extension A)
+    r'\uac00-\ud7af'          # Korean syllables (Hangul)
+    r'\uf900-\ufaff'          # CJK Compatibility Ideographs
+    r'\U00020000-\U0002fa1f'  # CJK Extension B–F
+)
+_RE_CONTAINS_CJK   = re.compile(f'[{_CJK_RANGES}]')
+_RE_CJK_WORDS      = re.compile(f'[{_CJK_RANGES}]+')
+_RE_TRIGRAM_TOKENS = re.compile(f'[{_CJK_RANGES}]+|[A-Za-z0-9_]+')
 
 
 @dataclass
@@ -48,6 +78,10 @@ class MemoryStorage:
         self.db_path = db_path
         self.conn: Optional[sqlite3.Connection] = None
         self.fts5_available = False  # Track FTS5 availability
+        # RLock protects concurrent writes from the same process.
+        # SQLite WAL mode handles read/write concurrency at the file level,
+        # but same-process concurrent writes still need a Python-level lock.
+        self._lock = threading.RLock()
         self._init_db()
     
     def _check_fts5_support(self) -> bool:
@@ -69,6 +103,14 @@ class MemoryStorage:
             
             # Check FTS5 support
             self.fts5_available = self._check_fts5_support()
+            if not _HAS_UPSERT:
+                from common.log import logger
+                logger.warning(
+                    "[MemoryStorage] SQLite %s < 3.24 — UPSERT unavailable. "
+                    "Falling back to INSERT OR REPLACE; FTS5 rowid may drift on "
+                    "chunk updates (rebuild index periodically to recover).",
+                    sqlite3.sqlite_version,
+                )
             if not self.fts5_available:
                 from common.log import logger
                 logger.debug("[MemoryStorage] FTS5 not available, using LIKE-based keyword search")
@@ -175,6 +217,75 @@ class MemoryStorage:
                 )
                 self._rebuild_fts5_from_chunks()
 
+        # Internal key-value store for persistent flags (e.g. backfill tracking)
+        self.conn.execute("""
+            CREATE TABLE IF NOT EXISTS _meta (
+                key TEXT PRIMARY KEY,
+                value TEXT NOT NULL
+            )
+        """)
+
+        # Create trigram FTS5 table for CJK / mixed-language search
+        self.trigram_fts5_available = False
+        if self.fts5_available:
+            try:
+                self.conn.execute("""
+                    CREATE VIRTUAL TABLE IF NOT EXISTS chunks_fts_trigram USING fts5(
+                        text,
+                        id UNINDEXED,
+                        user_id UNINDEXED,
+                        path UNINDEXED,
+                        source UNINDEXED,
+                        scope UNINDEXED,
+                        content='chunks',
+                        content_rowid='rowid',
+                        tokenize='trigram case_sensitive 0'
+                    )
+                """)
+                self.conn.execute("""
+                    CREATE TRIGGER IF NOT EXISTS chunks_trigram_ai
+                    AFTER INSERT ON chunks BEGIN
+                        INSERT INTO chunks_fts_trigram(rowid, text, id, user_id, path, source, scope)
+                        VALUES (new.rowid, new.text, new.id, new.user_id, new.path, new.source, new.scope);
+                    END
+                """)
+                self.conn.execute("""
+                    CREATE TRIGGER IF NOT EXISTS chunks_trigram_ad
+                    AFTER DELETE ON chunks BEGIN
+                        DELETE FROM chunks_fts_trigram WHERE rowid = old.rowid;
+                    END
+                """)
+                self.conn.execute("""
+                    CREATE TRIGGER IF NOT EXISTS chunks_trigram_au
+                    AFTER UPDATE ON chunks BEGIN
+                        UPDATE chunks_fts_trigram
+                        SET text=new.text, id=new.id, user_id=new.user_id,
+                            path=new.path, source=new.source, scope=new.scope
+                        WHERE rowid = new.rowid;
+                    END
+                """)
+                # One-time backfill for existing rows.
+                # NOTE: COUNT(*) on an FTS5 content table always returns 0, so we
+                # use a persistent flag in _meta instead of counting trigram rows.
+                backfill_done = self.conn.execute(
+                    "SELECT 1 FROM _meta WHERE key = 'trigram_backfill_done'"
+                ).fetchone()
+                chunks_count = self.conn.execute(
+                    "SELECT COUNT(*) as c FROM chunks"
+                ).fetchone()['c']
+                if chunks_count > 0 and not backfill_done:
+                    self.conn.execute(
+                        "INSERT INTO chunks_fts_trigram(chunks_fts_trigram) VALUES('rebuild')"
+                    )
+                    self.conn.execute(
+                        "INSERT OR REPLACE INTO _meta(key, value) VALUES('trigram_backfill_done', '1')"
+                    )
+                self.trigram_fts5_available = True
+            except Exception:
+                from common.log import logger
+                logger.warning("[MemoryStorage] trigram FTS5 unavailable, CJK search will use LIKE fallback", exc_info=True)
+                self.trigram_fts5_available = False
+
         # Create files metadata table
         self.conn.execute("""
             CREATE TABLE IF NOT EXISTS files (
@@ -186,7 +297,7 @@ class MemoryStorage:
                 updated_at INTEGER DEFAULT (strftime('%s', 'now'))
             )
         """)
-        
+
         self.conn.commit()
 
     def _fts5_state_inconsistent(self) -> bool:
@@ -299,43 +410,98 @@ class MemoryStorage:
         self.conn.commit()
 
     def save_chunk(self, chunk: MemoryChunk):
-        """Save a memory chunk"""
-        self.conn.execute("""
-            INSERT OR REPLACE INTO chunks 
-            (id, user_id, scope, source, path, start_line, end_line, text, embedding, hash, metadata, updated_at)
-            VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, strftime('%s', 'now'))
-        """, (
-            chunk.id,
-            chunk.user_id,
-            chunk.scope,
-            chunk.source,
-            chunk.path,
-            chunk.start_line,
-            chunk.end_line,
-            chunk.text,
-            json.dumps(chunk.embedding) if chunk.embedding else None,
+        """Save a memory chunk (insert or update by id).
+
+        Uses SQLite UPSERT (INSERT … ON CONFLICT DO UPDATE) instead of
+        INSERT OR REPLACE.  INSERT OR REPLACE internally does DELETE+INSERT,
+        which changes the row's rowid.  Because both FTS5 tables use
+        content_rowid='rowid', a new rowid would leave the old FTS index
+        entries pointing at a non-existent rowid and trigger
+        "fts5: missing row N from content table" errors.
+        ON CONFLICT DO UPDATE fires the AFTER UPDATE trigger (chunks_au /
+        chunks_trigram_au) and keeps the original rowid intact.
+        """
+        if _HAS_UPSERT:
+            _SQL = """
+                INSERT INTO chunks
+                (id, user_id, scope, source, path, start_line, end_line,
+                 text, embedding, hash, metadata, updated_at)
+                VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, strftime('%s', 'now'))
+                ON CONFLICT(id) DO UPDATE SET
+                    user_id     = excluded.user_id,
+                    scope       = excluded.scope,
+                    source      = excluded.source,
+                    path        = excluded.path,
+                    start_line  = excluded.start_line,
+                    end_line    = excluded.end_line,
+                    text        = excluded.text,
+                    embedding   = excluded.embedding,
+                    hash        = excluded.hash,
+                    metadata    = excluded.metadata,
+                    updated_at  = strftime('%s', 'now')
+            """
+        else:
+            _SQL = """
+                INSERT OR REPLACE INTO chunks
+                (id, user_id, scope, source, path, start_line, end_line,
+                 text, embedding, hash, metadata, updated_at)
+                VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, strftime('%s', 'now'))
+            """
+        params = (
+            chunk.id, chunk.user_id, chunk.scope, chunk.source, chunk.path,
+            chunk.start_line, chunk.end_line, chunk.text,
+            self._encode_embedding(chunk.embedding),
             chunk.hash,
-            json.dumps(chunk.metadata) if chunk.metadata else None
-        ))
-        self.conn.commit()
-    
+            json.dumps(chunk.metadata) if chunk.metadata else None,
+        )
+        with self._lock:
+            self.conn.execute(_SQL, params)
+            self.conn.commit()
+
     def save_chunks_batch(self, chunks: List[MemoryChunk]):
-        """Save multiple chunks in a batch"""
-        self.conn.executemany("""
-            INSERT OR REPLACE INTO chunks 
-            (id, user_id, scope, source, path, start_line, end_line, text, embedding, hash, metadata, updated_at)
-            VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, strftime('%s', 'now'))
-        """, [
+        """Save multiple chunks in a batch (insert or update by id).
+
+        See save_chunk for why UPSERT is used instead of INSERT OR REPLACE.
+        """
+        if _HAS_UPSERT:
+            _SQL = """
+                INSERT INTO chunks
+                (id, user_id, scope, source, path, start_line, end_line,
+                 text, embedding, hash, metadata, updated_at)
+                VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, strftime('%s', 'now'))
+                ON CONFLICT(id) DO UPDATE SET
+                    user_id     = excluded.user_id,
+                    scope       = excluded.scope,
+                    source      = excluded.source,
+                    path        = excluded.path,
+                    start_line  = excluded.start_line,
+                    end_line    = excluded.end_line,
+                    text        = excluded.text,
+                    embedding   = excluded.embedding,
+                    hash        = excluded.hash,
+                    metadata    = excluded.metadata,
+                    updated_at  = strftime('%s', 'now')
+            """
+        else:
+            _SQL = """
+                INSERT OR REPLACE INTO chunks
+                (id, user_id, scope, source, path, start_line, end_line,
+                 text, embedding, hash, metadata, updated_at)
+                VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, strftime('%s', 'now'))
+            """
+        params_list = [
             (
                 c.id, c.user_id, c.scope, c.source, c.path,
                 c.start_line, c.end_line, c.text,
-                json.dumps(c.embedding) if c.embedding else None,
+                self._encode_embedding(c.embedding),
                 c.hash,
-                json.dumps(c.metadata) if c.metadata else None
+                json.dumps(c.metadata) if c.metadata else None,
             )
             for c in chunks
-        ])
-        self.conn.commit()
+        ]
+        with self._lock:
+            self.conn.executemany(_SQL, params_list)
+            self.conn.commit()
     
     def get_chunk(self, chunk_id: str) -> Optional[MemoryChunk]:
         """Get a chunk by ID"""
@@ -356,21 +522,21 @@ class MemoryStorage:
         limit: int = 10
     ) -> List[SearchResult]:
         """
-        Vector similarity search using in-memory cosine similarity
-        (sqlite-vec can be added later for better performance)
+        Vector similarity search using numpy-vectorized cosine similarity.
+        All embeddings are loaded then scored in a single BLAS matrix-vector
+        multiply, which is ~100x faster than the pure-Python per-row loop.
         """
         if scopes is None:
             scopes = ["shared"]
             if user_id:
                 scopes.append("user")
-        
-        # Build query
+
         scope_placeholders = ','.join('?' * len(scopes))
-        params = scopes
-        
+        params = list(scopes)
+
         if user_id:
             query = f"""
-                SELECT * FROM chunks 
+                SELECT * FROM chunks
                 WHERE scope IN ({scope_placeholders})
                 AND (scope = 'shared' OR user_id = ?)
                 AND embedding IS NOT NULL
@@ -378,51 +544,95 @@ class MemoryStorage:
             params.append(user_id)
         else:
             query = f"""
-                SELECT * FROM chunks 
+                SELECT * FROM chunks
                 WHERE scope IN ({scope_placeholders})
                 AND embedding IS NOT NULL
             """
-        
+
         rows = self.conn.execute(query, params).fetchall()
+        if not rows:
+            return []
 
-        # Calculate cosine similarity. We probe the first row's dim to fail
-        # loudly on a query/index dim mismatch — otherwise every doc would
-        # score 0 silently, leaving the user wondering why search broke.
-        results = []
-        query_dim = len(query_embedding)
-        if rows:
-            first = json.loads(rows[0]['embedding'])
-            if isinstance(first, list) and len(first) != query_dim:
-                raise ValueError(
-                    f"Embedding dim mismatch: query is {query_dim}-dim but "
-                    f"index stores {len(first)}-dim vectors. The configured "
-                    f"embedding model differs from the one that built the "
-                    f"index — run /memory rebuild-index to re-embed."
-                )
-
+        # Parse embeddings and build a (N, D) matrix in one pass.
+        # New rows store BLOB bytes (np.frombuffer); legacy rows fall back to JSON.
+        # Filter out rows whose embedding dimension differs from the query —
+        # mixing dimensions would cause np.array() to produce an object array
+        # and matrix @ q_vec to raise ValueError.
+        expected_dim = len(query_embedding)
+        valid_rows = []
+        vectors = []
         for row in rows:
-            embedding = json.loads(row['embedding'])
-            similarity = self._cosine_similarity(query_embedding, embedding)
+            vec = self._decode_embedding(row['embedding'])
+            if not vec:
+                continue
+            if len(vec) != expected_dim:
+                from common.log import logger
+                logger.warning(
+                    "[MemoryStorage] Skipping chunk %s: embedding dim %d != query dim %d",
+                    row['id'], len(vec), expected_dim
+                )
+                continue
+            valid_rows.append(row)
+            vectors.append(vec)
 
-            if similarity > 0:
-                results.append((similarity, row))
-        
-        # Sort by similarity and limit
-        results.sort(key=lambda x: x[0], reverse=True)
-        results = results[:limit]
-        
-        return [
-            SearchResult(
-                path=row['path'],
-                start_line=row['start_line'],
-                end_line=row['end_line'],
-                score=score,
-                snippet=self._truncate_text(row['text'], 500),
-                source=row['source'],
-                user_id=row['user_id']
-            )
-            for score, row in results
-        ]
+        if not vectors:
+            return []
+
+        if _HAS_NUMPY:
+            matrix = np.array(vectors, dtype=np.float32)        # (N, D)
+            q_vec = np.array(query_embedding, dtype=np.float32)  # (D,)
+
+            # Vectorized cosine similarity: dot(matrix, q) / (||matrix|| * ||q||)
+            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                           # (N,)
+
+            # Select TopK using argpartition (O(N) average), then sort only those K
+            k = min(limit, len(valid_rows))
+            top_idx = np.argpartition(sims, -k)[-k:]
+            top_idx = top_idx[np.argsort(sims[top_idx])[::-1]]
+
+            return [
+                SearchResult(
+                    path=valid_rows[i]['path'],
+                    start_line=valid_rows[i]['start_line'],
+                    end_line=valid_rows[i]['end_line'],
+                    score=float(sims[i]),
+                    snippet=self._truncate_text(valid_rows[i]['text'], 500),
+                    source=valid_rows[i]['source'],
+                    user_id=valid_rows[i]['user_id']
+                )
+                for i in top_idx
+                if sims[i] > 0
+            ]
+        else:
+            # Pure-Python cosine similarity fallback (numpy not installed)
+            import math
+            q = query_embedding
+            q_norm = math.sqrt(sum(x * x for x in q)) or 1e-10
+            scored = []
+            for i, vec in enumerate(vectors):
+                dot = sum(a * b for a, b in zip(vec, q))
+                v_norm = math.sqrt(sum(x * x for x in vec)) or 1e-10
+                sim = dot / (v_norm * q_norm)
+                if sim > 0:
+                    scored.append((sim, valid_rows[i]))
+            scored.sort(key=lambda x: x[0], reverse=True)
+            return [
+                SearchResult(
+                    path=row['path'],
+                    start_line=row['start_line'],
+                    end_line=row['end_line'],
+                    score=sim,
+                    snippet=self._truncate_text(row['text'], 500),
+                    source=row['source'],
+                    user_id=row['user_id']
+                )
+                for sim, row in scored[:limit]
+            ]
     
     def search_keyword(
         self,
@@ -445,12 +655,37 @@ class MemoryStorage:
             if user_id:
                 scopes.append("user")
 
-        if self.fts5_available:
+        # Step 1: Standard FTS5 (unicode61) — pure ASCII queries only.
+        # Skipped when query contains any CJK characters: unicode61 tokenises CJK
+        # as individual characters without forming meaningful tokens, so it would
+        # match only the ASCII portion of a mixed query (e.g. "Python" from
+        # "Python教程") and silently discard the CJK part.  Those queries go
+        # directly to Step 2 (trigram), which handles both ASCII and CJK together.
+        fts1_attempted = False
+        if (self.fts5_available
+                and not MemoryStorage._contains_cjk(query)
+                and MemoryStorage._build_fts_query(query)):
+            fts1_attempted = True
             fts_results = self._search_fts5(query, user_id, scopes, limit)
             if fts_results:
                 return fts_results
 
-        return self._search_like(query, user_id, scopes, limit)
+        # Step 2: Trigram FTS5 — CJK/mixed queries, plus fallback when unicode61
+        # returned nothing (trigram indexes all scripts with 3-char sliding windows,
+        # so it can catch terms that unicode61 tokenisation misses).
+        if self.trigram_fts5_available and (
+            MemoryStorage._contains_cjk(query) or fts1_attempted
+        ):
+            trigram_results = self._search_fts5_trigram(query, user_id, scopes, limit)
+            if trigram_results:
+                return trigram_results
+
+        # Step 3: LIKE fallback — last resort (FTS5 unavailable, or CJK tokens
+        # shorter than 3 characters that trigram cannot match, e.g. a single-char query).
+        if not self.fts5_available or MemoryStorage._contains_cjk(query):
+            return self._search_like(query, user_id, scopes, limit)
+
+        return []
     
     def _search_fts5(
         self,
@@ -471,7 +706,7 @@ class MemoryStorage:
             sql_query = f"""
                 SELECT chunks.*, bm25(chunks_fts) as rank
                 FROM chunks_fts
-                JOIN chunks ON chunks.id = chunks_fts.id
+                JOIN chunks ON chunks.rowid = chunks_fts.rowid
                 WHERE chunks_fts MATCH ? 
                 AND chunks.scope IN ({scope_placeholders})
                 AND (chunks.scope = 'shared' OR chunks.user_id = ?)
@@ -483,7 +718,7 @@ class MemoryStorage:
             sql_query = f"""
                 SELECT chunks.*, bm25(chunks_fts) as rank
                 FROM chunks_fts
-                JOIN chunks ON chunks.id = chunks_fts.id
+                JOIN chunks ON chunks.rowid = chunks_fts.rowid
                 WHERE chunks_fts MATCH ? 
                 AND chunks.scope IN ({scope_placeholders})
                 ORDER BY rank
@@ -505,13 +740,11 @@ class MemoryStorage:
                 )
                 for row in rows
             ]
-        except Exception as e:
+        except Exception:
             from common.log import logger
-            logger.error(
-                f"[MemoryStorage] FTS5 search failed (caller will fall back to LIKE): {e}"
-            )
+            logger.warning("[MemoryStorage] _search_fts5 failed, returning empty", exc_info=True)
             return []
-    
+
     def _search_like(
         self,
         query: str,
@@ -522,12 +755,11 @@ class MemoryStorage:
         """LIKE-based search.
 
         Used as the keyword-search fallback when FTS5 is unavailable, fails,
-        or returns empty. Supports both CJK runs and ASCII word tokens so it
-        can serve as a true safety net for any query.
+        or returns empty. Supports both CJK runs (1+ chars) and ASCII word
+        tokens (3+ chars) so it can serve as a true safety net for any query.
         """
-        import re
-        # CJK runs (2+ chars) + ASCII word tokens (3+ chars to avoid noise)
-        cjk_words = re.findall(r'[\u4e00-\u9fff]{2,}', query)
+        # CJK runs (1+ chars, wide Unicode range) + ASCII words (3+ chars to avoid noise)
+        cjk_words = _RE_CJK_WORDS.findall(query)
         ascii_words = [t for t in re.findall(r'[A-Za-z0-9_]+', query) if len(t) >= 3]
         words = cjk_words + ascii_words
         if not words:
@@ -565,44 +797,55 @@ class MemoryStorage:
         
         try:
             rows = self.conn.execute(sql_query, params).fetchall()
-            return [
-                SearchResult(
+            results = []
+            for row in rows:
+                # Dynamic score: reward chunks that contain more of the query words.
+                # Use all tokens (CJK + ASCII) so pure-ASCII queries are not skipped.
+                # matched_count is always ≥1 because the WHERE clause uses OR, but
+                # guard defensively so unexpected zero-match rows are never surfaced.
+                text_lower = row['text'].lower()
+                matched_count = sum(1 for w in words if w.lower() in text_lower)
+                if matched_count == 0:
+                    continue
+                score = min(0.85, 0.3 + 0.15 * matched_count)
+                results.append(SearchResult(
                     path=row['path'],
                     start_line=row['start_line'],
                     end_line=row['end_line'],
-                    score=0.5,  # Fixed score for LIKE search
+                    score=score,
                     snippet=self._truncate_text(row['text'], 500),
                     source=row['source'],
                     user_id=row['user_id']
-                )
-                for row in rows
-            ]
-        except Exception as e:
+                ))
+            results.sort(key=lambda r: r.score, reverse=True)
+            return results
+        except Exception:
             from common.log import logger
-            logger.error(f"[MemoryStorage] LIKE search failed: {e}")
+            logger.warning("[MemoryStorage] _search_like failed, returning empty", exc_info=True)
             return []
-    
+
     def delete_by_path(self, path: str):
-        """Delete all chunks from a file"""
-        self.conn.execute("""
-            DELETE FROM chunks WHERE path = ?
-        """, (path,))
-        self.conn.commit()
-    
+        """Delete all chunks and file metadata for a path."""
+        with self._lock:
+            self.conn.execute("DELETE FROM chunks WHERE path = ?", (path,))
+            self.conn.execute("DELETE FROM files WHERE path = ?", (path,))
+            self.conn.commit()
+
     def get_file_hash(self, path: str) -> Optional[str]:
         """Get stored file hash"""
         row = self.conn.execute("""
             SELECT hash FROM files WHERE path = ?
         """, (path,)).fetchone()
         return row['hash'] if row else None
-    
+
     def update_file_metadata(self, path: str, source: str, file_hash: str, mtime: int, size: int):
         """Update file metadata"""
-        self.conn.execute("""
-            INSERT OR REPLACE INTO files (path, source, hash, mtime, size, updated_at)
-            VALUES (?, ?, ?, ?, ?, strftime('%s', 'now'))
-        """, (path, source, file_hash, mtime, size))
-        self.conn.commit()
+        with self._lock:
+            self.conn.execute("""
+                INSERT OR REPLACE INTO files (path, source, hash, mtime, size, updated_at)
+                VALUES (?, ?, ?, ?, ?, strftime('%s', 'now'))
+            """, (path, source, file_hash, mtime, size))
+            self.conn.commit()
     
     def get_stats(self) -> Dict[str, int]:
         """Get storage statistics"""
@@ -632,7 +875,8 @@ class MemoryStorage:
                 self.conn.close()
                 self.conn = None  # Mark as closed
             except Exception as e:
-                print(f"⚠️  Error closing database connection: {e}")
+                from common.log import logger
+                logger.warning("[MemoryStorage] Error closing database connection: %s", e)
     
     def __del__(self):
         """Destructor to ensure connection is closed"""
@@ -642,7 +886,33 @@ class MemoryStorage:
             pass  # Ignore errors during cleanup
     
     # Helper methods
-    
+
+    @staticmethod
+    def _encode_embedding(embedding: Optional[List[float]]) -> Optional[bytes]:
+        """Encode embedding as float32 BLOB bytes (~6x smaller and faster than JSON).
+        Falls back to struct.pack when numpy is unavailable."""
+        if embedding is None:
+            return None
+        if _HAS_NUMPY:
+            return np.array(embedding, dtype=np.float32).tobytes()
+        import struct
+        return struct.pack(f'{len(embedding)}f', *embedding)
+
+    @staticmethod
+    def _decode_embedding(raw) -> Optional[List[float]]:
+        """Decode embedding from BLOB bytes or legacy JSON string.
+        Handles both numpy and numpy-free environments."""
+        if raw is None:
+            return None
+        if isinstance(raw, (bytes, bytearray)):
+            if _HAS_NUMPY:
+                return np.frombuffer(raw, dtype=np.float32).tolist()
+            import struct
+            n = len(raw) // 4
+            return list(struct.unpack(f'{n}f', raw))
+        # Legacy JSON format written by older versions
+        return json.loads(raw)
+
     def _row_to_chunk(self, row) -> MemoryChunk:
         """Convert database row to MemoryChunk"""
         return MemoryChunk(
@@ -654,32 +924,89 @@ class MemoryStorage:
             start_line=row['start_line'],
             end_line=row['end_line'],
             text=row['text'],
-            embedding=json.loads(row['embedding']) if row['embedding'] else None,
+            embedding=self._decode_embedding(row['embedding']),
             hash=row['hash'],
             metadata=json.loads(row['metadata']) if row['metadata'] else None
         )
     
     @staticmethod
-    def _cosine_similarity(vec1: List[float], vec2: List[float]) -> float:
-        """Calculate cosine similarity between two vectors"""
-        if len(vec1) != len(vec2):
-            return 0.0
-        
-        dot_product = sum(a * b for a, b in zip(vec1, vec2))
-        norm1 = sum(a * a for a in vec1) ** 0.5
-        norm2 = sum(b * b for b in vec2) ** 0.5
-        
-        if norm1 == 0 or norm2 == 0:
-            return 0.0
-        
-        return dot_product / (norm1 * norm2)
+    def _contains_cjk(text: str) -> bool:
+        """Check if text contains CJK or related characters (Chinese, Japanese, Korean)."""
+        return bool(_RE_CONTAINS_CJK.search(text))
     
     @staticmethod
-    def _contains_cjk(text: str) -> bool:
-        """Check if text contains CJK (Chinese/Japanese/Korean) characters"""
-        import re
-        return bool(re.search(r'[\u4e00-\u9fff]', text))
-    
+    def _build_trigram_query(raw_query: str) -> Optional[str]:
+        """
+        Build FTS5 MATCH query for the trigram tokenizer.
+        Extracts CJK sequences (including single characters) and ASCII words,
+        joining them with AND so all terms must appear in the matched chunk.
+        """
+        tokens = _RE_TRIGRAM_TOKENS.findall(raw_query)
+        tokens = [t for t in tokens if t]
+        if not tokens:
+            return None
+        # Escape embedded double-quotes (FTS5 uses "" inside quoted phrases)
+        quoted = [f'"{t.replace(chr(34), chr(34)*2)}"' for t in tokens]
+        return ' AND '.join(quoted)
+
+    def _search_fts5_trigram(
+        self,
+        query: str,
+        user_id: Optional[str],
+        scopes: List[str],
+        limit: int
+    ) -> List[SearchResult]:
+        """Trigram FTS5 search — handles CJK and mixed queries with BM25 ranking."""
+        trigram_query = self._build_trigram_query(query)
+        if not trigram_query:
+            return []
+
+        scope_placeholders = ','.join('?' * len(scopes))
+        params = [trigram_query] + list(scopes)
+
+        if user_id:
+            sql = f"""
+                SELECT chunks.*, bm25(chunks_fts_trigram) as rank
+                FROM chunks_fts_trigram
+                JOIN chunks ON chunks.rowid = chunks_fts_trigram.rowid
+                WHERE chunks_fts_trigram MATCH ?
+                AND chunks.scope IN ({scope_placeholders})
+                AND (chunks.scope = 'shared' OR chunks.user_id = ?)
+                ORDER BY rank
+                LIMIT ?
+            """
+            params.extend([user_id, limit])
+        else:
+            sql = f"""
+                SELECT chunks.*, bm25(chunks_fts_trigram) as rank
+                FROM chunks_fts_trigram
+                JOIN chunks ON chunks.rowid = chunks_fts_trigram.rowid
+                WHERE chunks_fts_trigram MATCH ?
+                AND chunks.scope IN ({scope_placeholders})
+                ORDER BY rank
+                LIMIT ?
+            """
+            params.append(limit)
+
+        try:
+            rows = self.conn.execute(sql, params).fetchall()
+            return [
+                SearchResult(
+                    path=row['path'],
+                    start_line=row['start_line'],
+                    end_line=row['end_line'],
+                    score=self._bm25_rank_to_score(row['rank']),
+                    snippet=self._truncate_text(row['text'], 500),
+                    source=row['source'],
+                    user_id=row['user_id']
+                )
+                for row in rows
+            ]
+        except Exception:
+            from common.log import logger
+            logger.warning("[MemoryStorage] _search_fts5_trigram failed, returning empty", exc_info=True)
+            return []
+
     @staticmethod
     def _build_fts_query(raw_query: str) -> Optional[str]:
         """
@@ -688,7 +1015,6 @@ class MemoryStorage:
         Works best for English and word-based languages.
         For CJK characters, LIKE search will be used as fallback.
         """
-        import re
         # Extract words (primarily English words and numbers)
         tokens = re.findall(r'[A-Za-z0-9_]+', raw_query)
         if not tokens:
@@ -701,9 +1027,22 @@ class MemoryStorage:
     
     @staticmethod
     def _bm25_rank_to_score(rank: float) -> float:
-        """Convert BM25 rank to 0-1 score"""
-        normalized = max(0, rank) if rank is not None else 999
-        return 1 / (1 + normalized)
+        """Convert SQLite BM25 rank to a [0, 1) relevance score.
+
+        SQLite's bm25() returns a non-positive float (0 or negative).
+        More negative = more relevant.  max(0, rank) would clip every
+        negative value to 0, making every score 1/(1+0) = 1.0 and
+        destroying all ranking information.
+
+        abs(rank) / (1 + abs(rank)) maps the absolute relevance magnitude
+        to [0, 1): larger |rank| (stronger match) → score closer to 1.
+        """
+        if rank is None:
+            return 0.0
+        # Add a floor of 0.3 so any FTS5 match always exceeds typical
+        # min_score thresholds (default 0.1).  Small-corpus ranks close to
+        # 0 would otherwise produce score≈0 and be filtered out downstream.
+        return 0.3 + 0.69 * (abs(rank) / (1.0 + abs(rank)))
     
     @staticmethod
     def _truncate_text(text: str, max_chars: int) -> str:

agent/memory/summarizer.py

@@ -16,7 +16,7 @@ from datetime import datetime
 from common.log import logger
 
 
-SUMMARIZE_SYSTEM_PROMPT = """你是一个对话记录助手。请将对话内容归纳为当天的日常记录。
+SUMMARIZE_SYSTEM_PROMPT_ZH = """你是一个对话记录助手。请将对话内容归纳为当天的日常记录。
 
 ## 要求
 
@@ -28,7 +28,23 @@ SUMMARIZE_SYSTEM_PROMPT = """你是一个对话记录助手。请将对话内容
 
 当对话没有任何记录价值（仅含问候或无意义内容），直接回复"无"。"""
 
-SUMMARIZE_USER_PROMPT = """请归纳以下对话的日常记录：
+SUMMARIZE_SYSTEM_PROMPT_EN = """You are a conversation-logging assistant. Summarize the conversation into a daily record.
+
+## Requirements
+
+Summarize by "event", not turn by turn:
+- One item per line, starting with "- "
+- Merge multiple turns about the same thing
+- Only record meaningful events; ignore small talk and greetings
+- Keep key decisions, conclusions and to-dos
+
+If the conversation has no record value (only greetings or meaningless content), reply with exactly "None"."""
+
+SUMMARIZE_USER_PROMPT_ZH = """请归纳以下对话的日常记录：
+
+{conversation}"""
+
+SUMMARIZE_USER_PROMPT_EN = """Summarize the daily record of the following conversation:
 
 {conversation}"""
 
@@ -36,7 +52,7 @@ SUMMARIZE_USER_PROMPT = """请归纳以下对话的日常记录：
 # Deep Dream prompts — distill daily memories → MEMORY.md + dream diary
 # ---------------------------------------------------------------------------
 
-DREAM_SYSTEM_PROMPT = """你是一个记忆整理助手，负责定期整理用户的长期记忆。
+DREAM_SYSTEM_PROMPT_ZH = """你是一个记忆整理助手，负责定期整理用户的长期记忆。
 
 你将收到两份材料：
 1. **当前长期记忆** — MEMORY.md 的全部现有内容
@@ -80,7 +96,51 @@ MEMORY.md 会注入每次对话的系统提示词中，因此必须保持精炼
 梦境日记内容...
 ```"""
 
-DREAM_USER_PROMPT = """## 当前长期记忆（MEMORY.md）
+DREAM_SYSTEM_PROMPT_EN = """You are a memory-curation assistant that periodically organizes the user's long-term memory.
+
+You will receive two inputs:
+1. **Current long-term memory** — the full existing content of MEMORY.md
+2. **Today's diary** — the daily records
+
+MEMORY.md is injected into the system prompt of every conversation, so it must stay concise and hold only valuable, memory-worthy content.
+
+**Important: organize strictly based on the provided material. Never fabricate, infer, or add information not present in it.**
+
+## Tasks
+
+### Part 1: Updated long-term memory ([MEMORY])
+
+Organize and distill on top of the existing memory, and output the complete updated content:
+- **Merge & distill**: combine semantically similar items into one dense statement rather than listing them
+- **Extract new**: pull memory-worthy new info from today's diary (preferences, decisions, people, rules, lessons)
+- **Resolve conflicts**: when new info contradicts an old item, prefer the new and replace the old
+- **Clean invalid**: remove temporary notes, blank items, formatting residue, meaningless or duplicate content
+- **Drop redundancy**: delete old items already covered by a more concise statement
+- One item per line, starting with "- ", without a date prefix
+- You may group related items under "## headings" for clarity
+- Goal: keep under 50 items, each ideally a single sentence
+
+### Part 2: Dream diary ([DREAM])
+
+Write a short diary in a concise narrative style recording what this curation found, keep it clean and readable:
+- Which duplicates or conflicts were found
+- What new insights were extracted from the diary
+- What cleanup and optimization was done
+- Overall feelings and observations
+
+## Output format (follow strictly)
+
+```
+[MEMORY]
+- memory item 1
+- memory item 2
+...
+
+[DREAM]
+dream diary content...
+```"""
+
+DREAM_USER_PROMPT_ZH = """## 当前长期记忆（MEMORY.md）
 
 {memory_content}
 
@@ -88,6 +148,47 @@ DREAM_USER_PROMPT = """## 当前长期记忆（MEMORY.md）
 
 {daily_content}"""
 
+DREAM_USER_PROMPT_EN = """## Current long-term memory (MEMORY.md)
+
+{memory_content}
+
+## Recent diary (last {days} days)
+
+{daily_content}"""
+
+
+def _is_en() -> bool:
+    """True when the resolved UI language is English."""
+    try:
+        from common import i18n
+        return i18n.get_language() == "en"
+    except Exception:
+        return False
+
+
+def _summarize_system_prompt() -> str:
+    return SUMMARIZE_SYSTEM_PROMPT_EN if _is_en() else SUMMARIZE_SYSTEM_PROMPT_ZH
+
+
+def _summarize_user_prompt() -> str:
+    return SUMMARIZE_USER_PROMPT_EN if _is_en() else SUMMARIZE_USER_PROMPT_ZH
+
+
+def _dream_system_prompt() -> str:
+    return DREAM_SYSTEM_PROMPT_EN if _is_en() else DREAM_SYSTEM_PROMPT_ZH
+
+
+def _dream_user_prompt() -> str:
+    return DREAM_USER_PROMPT_EN if _is_en() else DREAM_USER_PROMPT_ZH
+
+
+def _is_empty_sentinel(text: str) -> bool:
+    """Match the "no record value" sentinel in both zh ("无") and en ("None")."""
+    if not text:
+        return True
+    s = text.strip()
+    return s == "" or s == "无" or s.lower() == "none"
+
 
 
 class MemoryFlushManager:
@@ -224,7 +325,7 @@ class MemoryFlushManager:
         """Background worker: summarize with LLM, write daily memory file."""
         try:
             raw_summary = self._summarize_messages(messages, max_messages)
-            if not raw_summary or not raw_summary.strip() or raw_summary.strip() == "无":
+            if _is_empty_sentinel(raw_summary):
                 logger.info(f"[MemoryFlush] No valuable content to flush (reason={reason})")
                 return
 
@@ -264,7 +365,7 @@ class MemoryFlushManager:
     def _clean_summary_output(raw: str) -> str:
         """Strip legacy [DAILY]/[MEMORY] markers if present, return clean daily text."""
         raw = raw.strip()
-        if not raw or raw == "无":
+        if _is_empty_sentinel(raw):
             return ""
 
         # Strip [DAILY] marker
@@ -318,6 +419,17 @@ class MemoryFlushManager:
             lookback_days: How many days of daily files to read (default 1 for scheduled, 3 for manual)
             force: Skip input-hash dedup check (used by manual /memory dream trigger)
         """
+        # Config guard for scheduled runs. Manual trigger (force=True) always
+        # runs since it is an explicit user action.
+        if not force:
+            try:
+                from config import conf
+                if not conf().get("deep_dream_enabled", True):
+                    logger.info("[DeepDream] deep_dream_enabled=false, skipping")
+                    return False
+            except Exception:
+                pass
+
         if not self.llm_model:
             logger.warning("[DeepDream] No LLM model available, skipping")
             return False
@@ -355,21 +467,20 @@ class MemoryFlushManager:
         import time as _time
         t0 = _time.monotonic()
         try:
-            user_msg = DREAM_USER_PROMPT.format(
+            user_msg = _dream_user_prompt().format(
                 memory_content=memory_content or "(empty)",
                 days=lookback_days,
                 daily_content=daily_content or "(no recent daily records)",
             )
             from agent.protocol.models import LLMRequest
-            # Scale max_tokens based on input size to avoid truncating large MEMORY.md
-            input_chars = len(memory_content) + len(daily_content)
-            dream_max_tokens = max(2000, min(input_chars, 8000))
+            # No output cap: the prompt already keeps MEMORY.md concise (~50
+            # items), so a hard max_tokens would only risk truncating a large
+            # rewrite. Let the model use its default output budget.
             request = LLMRequest(
                 messages=[{"role": "user", "content": user_msg}],
                 temperature=0.3,
-                max_tokens=dream_max_tokens,
                 stream=False,
-                system=DREAM_SYSTEM_PROMPT,
+                system=_dream_system_prompt(),
             )
             response = self.llm_model.call(request)
             raw = self._extract_response_text(response)
@@ -501,9 +612,9 @@ class MemoryFlushManager:
         if self.llm_model:
             try:
                 summary = self._call_llm_for_summary(conversation_text)
-                if summary and summary.strip() and summary.strip() != "无":
+                if not _is_empty_sentinel(summary):
                     return summary.strip()
-                logger.info("[MemoryFlush] LLM returned empty or '无', skipping write")
+                logger.info("[MemoryFlush] LLM returned empty sentinel, skipping write")
                 return ""
             except Exception as e:
                 logger.warning(f"[MemoryFlush] LLM summarization failed, using fallback: {e}")
@@ -579,11 +690,11 @@ class MemoryFlushManager:
         from agent.protocol.models import LLMRequest
         
         request = LLMRequest(
-            messages=[{"role": "user", "content": SUMMARIZE_USER_PROMPT.format(conversation=conversation_text)}],
+            messages=[{"role": "user", "content": _summarize_user_prompt().format(conversation=conversation_text)}],
             temperature=0,
             max_tokens=500,
             stream=False,
-            system=SUMMARIZE_SYSTEM_PROMPT,
+            system=_summarize_system_prompt(),
         )
         
         response = self.llm_model.call(request)

agent/prompt/builder.py

@@ -15,13 +15,13 @@ 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"):
         """
@@ -88,97 +88,144 @@ def build_agent_system_prompt(
     **kwargs
 ) -> str:
     """
-    构建Agent系统提示词
-    
-    顺序说明（按重要性和逻辑关系排列）:
-    1. 工具系统 - 核心能力，最先介绍
-    2. 技能系统 - 紧跟工具，因为技能需要用 read 工具读取
-    3. 记忆系统 - 记忆检索与写入引导
-    3.5 知识系统 - 结构化知识库（knowledge/index.md 注入）
-    4. 工作空间 - 工作环境说明
-    5. 用户身份 - 用户信息（可选）
-    6. 项目上下文 - AGENT.md, USER.md, RULE.md, MEMORY.md, BOOTSTRAP.md
-    7. 运行时信息 - 元信息（时间、模型等）
-    
+    Build the agent system prompt.
+
+    Section order (by importance and logical flow):
+    1. Tooling - core capabilities, introduced first
+    2. Skills - right after tools, since skills are read via the read tool
+    3. Memory - memory recall and writing guidance
+    3.5 Knowledge - structured knowledge base (injects knowledge/index.md)
+    4. Workspace - working environment description
+    5. User identity - user info (optional)
+    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
-        language: 语言 ("zh" 或 "en")
-        base_persona: 基础人格描述（已废弃，由AGENT.md定义）
-        user_identity: 用户身份信息
-        tools: 工具列表
-        context_files: 上下文文件列表
-        skill_manager: 技能管理器
-        memory_manager: 记忆管理器
-        runtime_info: 运行时信息
-        **kwargs: 其他参数
-        
+        workspace_dir: workspace directory
+        language: language ("zh" or "en")
+        base_persona: base persona description (deprecated, defined by AGENT.md)
+        user_identity: user identity info
+        tools: tool list
+        context_files: context file list
+        skill_manager: skill manager
+        memory_manager: memory manager
+        runtime_info: runtime info
+        **kwargs: extra args
+
     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))
 
-    # 3.5 知识系统（结构化知识库）
+    # 3.5 Knowledge (structured knowledge base)
     if conf().get("knowledge", True):
         sections.extend(_build_knowledge_section(workspace_dir, language))
-    
-    # 4. 工作空间（工作环境说明）
+
+    # 4. Workspace (working environment description)
     sections.extend(_build_workspace_section(workspace_dir, language))
-    
-    # 5. 用户身份（如果有）
+
+    # 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"""
-    # 不再生成基础身份section，完全由AGENT.md定义
+    """Base identity section - no longer needed, identity is defined by AGENT.md."""
+    # 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 = {
-        "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）",
-    }
+    if is_en:
+        core_summaries = {
+            "read": "read file content",
+            "write": "create or overwrite a file",
+            "edit": "make precise edits to a file",
+            "ls": "list directory contents",
+            "grep": "search file contents",
+            "find": "find files by pattern",
+            "bash": "run shell commands",
+            "terminal": "manage background processes",
+            "web_search": "web search",
+            "web_fetch": "fetch URL content",
+            "browser": "control the browser (screenshot key results or send to the user when help is needed)",
+            "memory_search": "search memory",
+            "memory_get": "read memory content",
+            "env_config": "manage API keys and skill config",
+            "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 = [
@@ -205,30 +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 = [
-        "## 🔧 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",
-        "",
-    ]
+    if is_en:
+        lines = [
+            "## 🔧 Tooling",
+            "",
+            "Available tools (names are case-sensitive, call exactly as listed):",
+            "\n".join(tool_lines),
+            "",
+            "Tool-calling style:",
+            "",
+            "- For multi-step tasks, complex decisions or sensitive operations, briefly explain what you are doing and why, so the user follows key progress",
+            "- 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:
@@ -237,23 +300,40 @@ def _build_skills_section(skill_manager: Any, tools: Optional[List[Any]], langua
                 read_tool_name = tool_name
                 break
     
-    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："
-    ]
+    if language == "en":
+        lines = [
+            "## 🧩 Skills (mandatory)",
+            "",
+            "Before replying: scan the <description> of every skill in <available_skills> below.",
+            "",
+            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. "
+            "Prefer using a skill when one matches.",
+            "- If multiple skills apply, pick the best-matching one, then read and follow it.",
+            "- If no skill clearly applies: do not read any SKILL.md, just use the general tools.",
+            "",
+            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}")
@@ -271,7 +351,7 @@ 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 []
 
@@ -286,43 +366,82 @@ def _build_memory_section(memory_manager: Any, tools: Optional[List[Any]], langu
     from datetime import datetime
     today_file = datetime.now().strftime("%Y-%m-%d") + ".md"
 
-    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。",
-        "",
-    ]
+    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
 
@@ -339,37 +458,61 @@ def _build_knowledge_section(workspace_dir: str, language: str) -> List[str]:
     except Exception:
         return []
 
-    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 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([
-            "### 当前知识索引",
+            ("### Current knowledge index" if language == "en" else "### 当前知识索引"),
             "",
             index_content,
             "",
         ])
 
     lines.extend([
-        "**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）。",
+        ("**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）。"),
         "",
     ])
 
@@ -377,76 +520,118 @@ def _build_knowledge_section(workspace_dir: str, language: str) -> List[str]:
 
 
 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"""
-    # 不再生成文档section
+    """Docs-path section - removed, no longer needed."""
+    # No docs section is generated anymore.
     return []
 
 
 def _build_workspace_section(workspace_dir: str, language: str) -> List[str]:
-    """构建工作空间section"""
-    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",
-        "",
-    ]
+    """Build the workspace section."""
+    if language == "en":
+        lines = [
+            "## 📂 Workspace",
+            "",
+            f"Your working directory is: `{workspace_dir}`",
+            "",
+            "**Path rules** (very important):",
+            "",
+            f"1. **Base directory for relative paths**: all relative paths are relative to `{workspace_dir}`",
+            "   - ✅ Correct: use relative paths for files inside the workspace, e.g. `AGENT.md`",
+            f"   - ❌ Wrong: using a relative path for files in other directories (if not inside `{workspace_dir}`)",
+            "",
+            "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)
@@ -466,29 +651,42 @@ def _build_cloud_website_section(workspace_dir: str) -> List[str]:
 
 
 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 = [
-        "# 📋 项目上下文",
-        "",
-        "以下项目上下文文件已被加载：",
-        "",
-    ]
-    
+    is_en = language == "en"
+    if is_en:
+        lines = [
+            "# 📋 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("**`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。")
+        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("")
@@ -499,21 +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:
@@ -523,35 +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 = []
     # Support dynamic model via callable, fallback to static value
     if callable(runtime_info.get("_get_model")):
         try:
-            runtime_parts.append(f"模型={runtime_info['_get_model']()}")
+            runtime_parts.append(f"{model_label}={runtime_info['_get_model']()}")
         except Exception:
             if runtime_info.get("model"):
-                runtime_parts.append(f"模型={runtime_info['model']}")
+                runtime_parts.append(f"{model_label}={runtime_info['model']}")
     elif runtime_info.get("model"):
-        runtime_parts.append(f"模型={runtime_info['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

@@ -1,7 +1,7 @@
 """
-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
@@ -13,7 +13,7 @@ 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"
@@ -23,7 +23,7 @@ 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
@@ -33,14 +33,14 @@ class WorkspaceFiles:
 
 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
-        create_templates: 是否创建模板文件（首次运行时）
-        
+        workspace_dir: workspace directory path
+        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.
     """
     # Check if this is a brand new workspace (AGENT.md not yet created).
     # Cannot rely on directory existence because other modules (e.g. ConversationStore)
@@ -48,23 +48,23 @@ def ensure_workspace(workspace_dir: str, create_templates: bool = True) -> Works
     agent_path = os.path.join(workspace_dir, DEFAULT_AGENT_FILENAME)
     is_new_workspace = not os.path.exists(agent_path)
     
-    # 确保目录存在
+    # Ensure the directory exists
     os.makedirs(workspace_dir, exist_ok=True)
     
-    # 定义文件路径
+    # Define file paths
     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_dir = os.path.join(workspace_dir, "memory")  # 每日记忆子目录
+    memory_path = os.path.join(workspace_dir, DEFAULT_MEMORY_FILENAME)  # MEMORY.md at the root
+    memory_dir = os.path.join(workspace_dir, "memory")  # daily memory subdirectory
     
-    # 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)
 
-    # 创建websites子目录 (for web pages / sites generated by agent)
+    # 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)
 
@@ -74,7 +74,7 @@ def ensure_workspace(workspace_dir: str, create_templates: bool = True) -> Works
         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())
@@ -109,17 +109,17 @@ def ensure_workspace(workspace_dir: str, create_templates: bool = True) -> Works
 
 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
-        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
-        
+        workspace_dir: workspace directory
+        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,
@@ -151,7 +151,7 @@ def load_context_files(workspace_dir: str, files_to_load: Optional[List[str]] =
             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
 
@@ -173,7 +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:
@@ -214,19 +214,23 @@ def _truncate_memory_content(content: str) -> str:
 
 
 def _is_template_placeholder(content: str) -> bool:
-    """检查内容是否为模板占位符"""
-    # 常见的占位符模式
+    """Check whether the content is still a template placeholder."""
+    # 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):
@@ -256,11 +260,23 @@ def _is_onboarding_done(workspace_dir: str) -> bool:
     return False
 
 
-# ============= 模板内容 =============
+# ============= 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"""
-    return """# AGENT.md - 我是谁？
+    """Agent persona template (zh/en by resolved language)."""
+    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。_
 
@@ -301,9 +317,53 @@ _你不是一个聊天机器人，你正在成为某个人。_
 """
 
 
+_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"""
-    return """# USER.md - 用户基本信息
+    """User identity template (zh/en by resolved language)."""
+    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。*
 
@@ -331,9 +391,40 @@ 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"""
-    return """# RULE.md - 工作空间规则
+    """Workspace rules template (zh/en by resolved language)."""
+    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。
 
@@ -432,9 +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"""
-    return """# MEMORY.md - 长期记忆
+    """Long-term memory template (empty, agent fills it; zh/en header)."""
+    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。*
 
@@ -443,9 +636,32 @@ def _get_memory_template() -> str:
 """
 
 
+_MEMORY_TEMPLATE_EN = """# MEMORY.md - Long-term memory
+
+*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"""
-    return """# BOOTSTRAP.md - 首次初始化引导
+    """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.
+    """
+    try:
+        from common import i18n
+        if i18n.get_language() == "en":
+            return _BOOTSTRAP_TEMPLATE_EN
+    except Exception:
+        pass
+    return _BOOTSTRAP_TEMPLATE_ZH
+
+
+_BOOTSTRAP_TEMPLATE_ZH = """# BOOTSTRAP.md - 首次初始化引导
 
 _你刚刚启动，这是你的第一次对话。_ ✨
 
@@ -480,6 +696,41 @@ _你刚刚启动，这是你的第一次对话。_ ✨
 """
 
 
+_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 ""

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
@@ -114,16 +119,26 @@ class Agent:
 
             context_files = load_context_files(self.workspace_dir) if self.workspace_dir else None
 
-            builder = PromptBuilder(workspace_dir=self.workspace_dir or "", language="zh")
-            return builder.build(
+            try:
+                from common import i18n
+                lang = i18n.get_language()
+            except Exception:
+                lang = "zh"
+            builder = PromptBuilder(workspace_dir=self.workspace_dir or "", language=lang)
+            full = builder.build(
                 tools=self.tools,
                 context_files=context_files,
                 skill_manager=self.skill_manager,
                 memory_manager=self.memory_manager,
                 runtime_info=self.runtime_info,
             )
+            if self.extra_system_suffix:
+                full = f"{full}\n\n{self.extra_system_suffix}"
+            return full
         except Exception as e:
             logger.warning(f"Failed to rebuild system prompt, using cached version: {e}")
+            if self.extra_system_suffix:
+                return f"{self.system_prompt}\n\n{self.extra_system_suffix}"
             return self.system_prompt
 
     def refresh_skills(self):
@@ -365,7 +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)
 
@@ -374,6 +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
@@ -381,6 +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
@@ -424,7 +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

agent/protocol/agent_stream.py

@@ -7,10 +7,19 @@ import json
 import time
 from typing import List, Dict, Any, Optional, Callable, Tuple
 
+from agent.protocol.cancel import AgentCancelledError
 from agent.protocol.models import LLMRequest, LLMModel
 from agent.protocol.message_utils import sanitize_claude_messages, compress_turn_to_text_only
 from agent.tools.base_tool import BaseTool, ToolResult
 from common.log import logger
+from common.i18n import t as _t
+
+# Optional: repair malformed JSON args from non-strict providers (e.g. unescaped quotes in long content).
+try:
+    from json_repair import repair_json as _repair_json
+    _HAS_JSON_REPAIR = True
+except ImportError:
+    _HAS_JSON_REPAIR = False
 
 
 # Maximum number of characters of model "reasoning / thinking" content to persist
@@ -44,6 +53,30 @@ def _truncate_reasoning_for_storage(text: str) -> str:
     return head + _REASONING_TRUNCATE_MARKER.format(omitted=omitted) + tail
 
 
+def _parse_tool_args(args_str: str, finish_reason: Optional[str]) -> Tuple[dict, Optional[str]]:
+    """Parse tool args JSON. Returns (args, error_msg); error_msg is None on success.
+
+    On JSONDecodeError: detect truncation first (skip repair, surface max_tokens hint);
+    otherwise try json-repair for escape issues; finally fall back to the raw decoder error.
+    """
+    if not args_str:
+        return {}, None
+    try:
+        return json.loads(args_str), None
+    except json.JSONDecodeError as e:
+        if finish_reason in ("length", "max_tokens") or not args_str.rstrip().endswith("}"):
+            return {}, "Output truncated (max_tokens reached). Split content into smaller chunks across multiple tool calls."
+        if _HAS_JSON_REPAIR:
+            try:
+                repaired = _repair_json(args_str, return_objects=True)
+                if isinstance(repaired, dict):
+                    logger.warning(f"Tool args JSON repaired ({len(args_str)} chars)")
+                    return repaired, None
+            except Exception:
+                pass
+        return {}, f"Invalid JSON in tool arguments: {e.msg}"
+
+
 class AgentStreamExecutor:
     """
     Agent Stream Executor
@@ -64,7 +97,8 @@ class AgentStreamExecutor:
             max_turns: int = 50,
             on_event: Optional[Callable] = None,
             messages: Optional[List[Dict]] = None,
-            max_context_turns: int = 30
+            max_context_turns: int = 30,
+            cancel_event=None,
     ):
         """
         Initialize stream executor
@@ -78,6 +112,10 @@ class AgentStreamExecutor:
             on_event: Event callback function
             messages: Optional existing message history (for persistent conversations)
             max_context_turns: Maximum number of conversation turns to keep in context
+            cancel_event: Optional threading.Event used to signal user cancel.
+                Checked at every safe point (turn boundary, before tool execution,
+                during LLM streaming). When set, raises AgentCancelledError which
+                run_stream catches to gracefully wind down.
         """
         self.agent = agent
         self.model = model
@@ -87,6 +125,7 @@ class AgentStreamExecutor:
         self.max_turns = max_turns
         self.on_event = on_event
         self.max_context_turns = max_context_turns
+        self.cancel_event = cancel_event
 
         # Message history - use provided messages or create new list
         self.messages = messages if messages is not None else []
@@ -97,6 +136,73 @@ class AgentStreamExecutor:
         # Track files to send (populated by read tool)
         self.files_to_send = []  # List of file metadata dicts
 
+    def _check_cancelled(self) -> None:
+        """Raise AgentCancelledError if the user requested cancellation.
+
+        Called at safe points (turn start, between tool calls, between LLM
+        chunks). Cheap to call: just an Event.is_set() probe.
+        """
+        if self.cancel_event is not None and self.cancel_event.is_set():
+            raise AgentCancelledError("agent cancelled by user")
+
+    def _handle_cancelled(self, partial_response: str) -> None:
+        """Wind down ``self.messages`` after a user-initiated cancel.
+
+        The messages list may be in any of these states when we get here:
+          (a) Last message is an assistant message containing tool_use
+              blocks but the matching tool_result has not been appended yet.
+          (b) Last message is an assistant text-only reply (cancel happened
+              right before the next turn started).
+          (c) Last message is a user tool_result message and we cancelled
+              between turns.
+
+        For (a) we MUST synthesise tool_result blocks, otherwise the next
+        request will fail Claude/OpenAI's strict pairing validation. For
+        (b)/(c) the state is already valid and we just append a small
+        cancellation note so the user/LLM both see the boundary clearly.
+        """
+        try:
+            # Step 1: close any orphaned tool_use in the trailing assistant
+            # message by injecting matching tool_result blocks.
+            if self.messages and isinstance(self.messages[-1], dict) \
+                    and self.messages[-1].get("role") == "assistant":
+                last = self.messages[-1]
+                content = last.get("content")
+                if isinstance(content, list):
+                    pending_tool_use_ids = [
+                        block.get("id")
+                        for block in content
+                        if isinstance(block, dict) and block.get("type") == "tool_use"
+                    ]
+                    pending_tool_use_ids = [tid for tid in pending_tool_use_ids if tid]
+                    if pending_tool_use_ids:
+                        tool_result_blocks = [
+                            {
+                                "type": "tool_result",
+                                "tool_use_id": tid,
+                                "content": "Cancelled by user before this tool finished.",
+                                "is_error": True,
+                            }
+                            for tid in pending_tool_use_ids
+                        ]
+                        self.messages.append({
+                            "role": "user",
+                            "content": tool_result_blocks,
+                        })
+                        logger.info(
+                            f"[Agent] Injected {len(tool_result_blocks)} cancellation "
+                            f"tool_result blocks to keep message history valid"
+                        )
+
+            # Step 2: append a stable "interrupted" marker so the LLM sees a
+            # clear stop boundary on the next turn.
+            self.messages.append({
+                "role": "assistant",
+                "content": [{"type": "text", "text": "_(Cancelled by user)_"}],
+            })
+        except Exception as e:
+            logger.warning(f"[Agent] _handle_cancelled cleanup failed: {e}")
+
     def _emit_event(self, event_type: str, data: dict = None):
         """Emit event"""
         if self.on_event:
@@ -212,7 +318,10 @@ class AgentStreamExecutor:
         
         # Hard stop at 8 failures - abort with critical message
         if same_tool_failures >= 8:
-            return True, f"抱歉，我没能完成这个任务。可能是我理解有误或者当前方法不太合适。\n\n建议你：\n• 换个方式描述需求试试\n• 把任务拆分成更小的步骤\n• 或者换个思路来解决", True
+            return True, _t(
+                "抱歉，我没能完成这个任务。可能是我理解有误或者当前方法不太合适。\n\n建议你：\n• 换个方式描述需求试试\n• 把任务拆分成更小的步骤\n• 或者换个思路来解决",
+                "Sorry, I couldn't complete this task. I may have misunderstood, or my current approach isn't quite right.\n\nYou could try:\n• Rephrasing your request\n• Breaking the task into smaller steps\n• Taking a different approach",
+            ), True
         
         # Warning at 6 failures
         if same_tool_failures >= 6:
@@ -238,11 +347,14 @@ class AgentStreamExecutor:
         Returns:
             Final response text
         """
-        # Log user message with model info
-        
+        # Log user message with model info. Truncate very long messages (e.g.
+        # injected transcripts / large prompts) so logs stay readable.
         thinking_enabled = self._is_thinking_enabled()
         thinking_label = " | 💭 thinking" if thinking_enabled else ""
-        logger.info(f"🤖 {self.model.model}{thinking_label} | 👤 {user_message}")        
+        _log_msg = user_message if len(user_message) <= 500 else (
+            user_message[:500] + f" …(+{len(user_message) - 500} chars)"
+        )
+        logger.info(f"🤖 {self.model.model}{thinking_label} | 👤 {_log_msg}")        
         
         # Add user message (Claude format - use content blocks for consistency)
         self.messages.append({
@@ -267,13 +379,24 @@ class AgentStreamExecutor:
 
         self._emit_event("agent_start")
 
+        # Reset the run-scoped MCP tool-retrieval accumulator. On-demand tool
+        # retrieval only grows this set within a run, so a tool that already
+        # produced a tool_use never disappears from the schema mid-run (which
+        # would make Claude/MiniMax raise a message-format error).
+        self._retrieved_mcp_names = set()
+
         final_response = ""
         turn = 0
 
+        cancelled = False
         try:
             while turn < self.max_turns:
+                # Check at the very top of every turn so a cancel arriving
+                # between turns short-circuits cleanly.
+                self._check_cancelled()
+
                 turn += 1
-                logger.info(f"[Agent] 第 {turn} 轮")
+                logger.info(f"[Agent] Turn {turn}")
                 self._emit_event("turn_start", {"turn": turn})
 
                 # Call LLM (enable retry_on_empty for better reliability)
@@ -326,14 +449,16 @@ class AgentStreamExecutor:
                             elif not assistant_msg:
                                 # Still empty (no text and no tool_calls): use fallback
                                 logger.warning(f"[Agent] Still empty after explicit request")
-                                final_response = (
-                                    "抱歉，我暂时无法生成回复。请尝试换一种方式描述你的需求，或稍后再试。"
+                                final_response = _t(
+                                    "抱歉，我暂时无法生成回复。请尝试换一种方式描述你的需求，或稍后再试。",
+                                    "Sorry, I can't generate a reply right now. Please try rephrasing your request, or try again later.",
                                 )
                                 logger.info(f"Generated fallback response for empty LLM output")
                         else:
-                            # 第一轮就空回复，直接 fallback
-                            final_response = (
-                                "抱歉，我暂时无法生成回复。请尝试换一种方式描述你的需求，或稍后再试。"
+                            # First-turn empty reply, fall back directly
+                            final_response = _t(
+                                "抱歉，我暂时无法生成回复。请尝试换一种方式描述你的需求，或稍后再试。",
+                                "Sorry, I can't generate a reply right now. Please try rephrasing your request, or try again later.",
                             )
                             logger.info(f"Generated fallback response for empty LLM output")
                     else:
@@ -342,7 +467,7 @@ class AgentStreamExecutor:
                     # If the explicit-response retry produced tool_calls, skip the break
                     # and continue down to the tool execution branch in this same iteration.
                     if not tool_calls:
-                        logger.debug(f"✅ 完成 (无工具调用)")
+                        logger.debug(f"✅ Done (no tool calls)")
                         self._emit_event("turn_end", {
                             "turn": turn,
                             "has_tool_calls": False
@@ -375,6 +500,8 @@ class AgentStreamExecutor:
 
                 try:
                     for tool_call in tool_calls:
+                        # Honour cancel between tool invocations within the same turn
+                        self._check_cancelled()
                         result = self._execute_tool(tool_call)
                         tool_results.append(result)
                         
@@ -396,13 +523,13 @@ class AgentStreamExecutor:
                             result_data = result.get("result")
                             if result_data.get("type") == "file_to_send":
                                 self.files_to_send.append(result_data)
-                                logger.info(f"📎 检测到待发送文件: {result_data.get('file_name', result_data.get('path'))}")
+                                logger.info(f"📎 File queued for sending: {result_data.get('file_name', result_data.get('path'))}")
                                 self._emit_event("file_to_send", result_data)
                         
                         # Check for critical error - abort entire conversation
                         if result.get("status") == "critical_error":
-                            logger.error(f"💥 检测到严重错误，终止对话")
-                            final_response = result.get('result', '任务执行失败')
+                            logger.error(f"💥 Fatal error detected, aborting conversation")
+                            final_response = result.get('result') or _t("任务执行失败", "Task execution failed")
                             return final_response
                         
                         # Log tool result in compact format
@@ -513,7 +640,7 @@ class AgentStreamExecutor:
                 })
 
             if turn >= self.max_turns:
-                logger.warning(f"⚠️  已达到最大决策步数限制: {self.max_turns}")
+                logger.warning(f"⚠️  Reached max decision step limit: {self.max_turns}")
                 
                 # Force model to summarize without tool calls
                 logger.info(f"[Agent] Requesting summary from LLM after reaching max steps...")
@@ -538,15 +665,15 @@ class AgentStreamExecutor:
                         logger.info(f"💭 Summary: {summary_response[:150]}{'...' if len(summary_response) > 150 else ''}")
                     else:
                         # Fallback if model still doesn't respond
-                        final_response = (
-                            f"我已经执行了{turn}个决策步骤，达到了单次运行的步数上限。"
-                            "任务可能还未完全完成，建议你将任务拆分成更小的步骤，或者换一种方式描述需求。"
+                        final_response = _t(
+                            f"我已经执行了{turn}个决策步骤，达到了单次运行的步数上限。任务可能还未完全完成，建议你将任务拆分成更小的步骤，或者换一种方式描述需求。",
+                            f"I've taken {turn} decision steps and reached the per-run limit. The task may not be fully complete — try breaking it into smaller steps, or describe your request differently.",
                         )
                 except Exception as e:
                     logger.warning(f"Failed to get summary from LLM: {e}")
-                    final_response = (
-                        f"我已经执行了{turn}个决策步骤，达到了单次运行的步数上限。"
-                        "任务可能还未完全完成，建议你将任务拆分成更小的步骤，或者换一种方式描述需求。"
+                    final_response = _t(
+                        f"我已经执行了{turn}个决策步骤，达到了单次运行的步数上限。任务可能还未完全完成，建议你将任务拆分成更小的步骤，或者换一种方式描述需求。",
+                        f"I've taken {turn} decision steps and reached the per-run limit. The task may not be fully complete — try breaking it into smaller steps, or describe your request differently.",
                     )
                 finally:
                     # Remove the injected user prompt from history to avoid polluting
@@ -557,18 +684,94 @@ class AgentStreamExecutor:
                         self.messages.pop(prompt_insert_idx)
                         logger.debug("[Agent] Removed injected max-steps prompt from message history")
 
+        except AgentCancelledError:
+            # User-initiated stop: wind down message history cleanly so the
+            # next turn is unaffected; channels emit a "cancelled" UI event.
+            cancelled = True
+            logger.info(f"[Agent] 🛑 Cancelled by user (turn {turn})")
+            self._handle_cancelled(final_response)
+            if not final_response or not final_response.strip():
+                final_response = "_(Cancelled)_"
+
         except Exception as e:
-            logger.error(f"❌ Agent执行错误: {e}")
+            logger.error(f"❌ Agent execution error: {e}")
             self._emit_event("error", {"error": str(e)})
             raise
 
         finally:
             final_response = final_response.strip() if final_response else final_response
-            logger.info(f"[Agent] 🏁 完成 ({turn}轮)")
-            self._emit_event("agent_end", {"final_response": final_response})
+            if cancelled:
+                # Emit before agent_end so channels can mark UI as cancelled
+                self._emit_event("agent_cancelled", {"final_response": final_response})
+            logger.info(f"[Agent] 🏁 Done ({turn} turns)" + (" [cancelled]" if cancelled else ""))
+            self._emit_event("agent_end", {"final_response": final_response, "cancelled": cancelled})
 
         return final_response
 
+    def _select_tools_for_injection(self) -> list:
+        """Decide which tools to inject into the current LLM turn.
+
+        Built-in tools are ALWAYS injected in full (skills and core flows hard
+        depend on them). MCP tools are also injected in full UNLESS on-demand
+        retrieval is enabled AND the MCP tool count exceeds the configured
+        threshold — then only the most relevant MCP tools are injected, unioned
+        with those already selected earlier in this run (only-grows, so a tool
+        that already produced a tool_use never vanishes from the schema).
+
+        Degrades safely: disabled feature, no embedding provider, embedding
+        failure, count below threshold, or any error → inject all tools. Tools
+        are never silently dropped.
+        """
+        all_tools = list(self.tools.values())
+        try:
+            from config import conf
+            if not conf().get("mcp_tool_retrieval_enabled", False):
+                return all_tools
+
+            from agent.tools.mcp.mcp_tool import McpTool
+            mcp_tools = [t for t in all_tools if isinstance(t, McpTool)]
+            builtin_tools = [t for t in all_tools if not isinstance(t, McpTool)]
+
+            threshold = int(conf().get("mcp_tool_retrieval_threshold", 20) or 20)
+            if len(mcp_tools) <= threshold:
+                return all_tools
+
+            top_k = int(conf().get("mcp_tool_retrieval_top_k", 10) or 10)
+
+            from agent.tools import ToolManager
+            from agent.tools.mcp.tool_retrieval import (
+                build_retrieval_query,
+                select_mcp_tools,
+            )
+
+            tm = ToolManager()
+            tool_vectors = tm.get_mcp_tool_vectors()
+            query = build_retrieval_query(self.messages)
+            query_vector = tm.embed_query(query)
+
+            selected = select_mcp_tools(
+                query_vector,
+                tool_vectors,
+                top_k,
+                getattr(self, "_retrieved_mcp_names", set()),
+            )
+            if selected is None:
+                # No provider / empty index / error → full injection.
+                return all_tools
+
+            # Persist the accumulated selection for subsequent turns.
+            self._retrieved_mcp_names = selected
+
+            selected_mcp = [t for t in mcp_tools if t.name in selected]
+            logger.info(
+                f"[ToolRetrieval] Injecting {len(builtin_tools)} built-in + "
+                f"{len(selected_mcp)}/{len(mcp_tools)} MCP tool(s) (top_k={top_k})"
+            )
+            return builtin_tools + selected_mcp
+        except Exception as e:
+            logger.debug(f"[ToolRetrieval] full injection (retrieval skipped): {e}")
+            return all_tools
+
     def _call_llm_stream(self, retry_on_empty=True, retry_count=0, max_retries=3,
                          _overflow_retry: bool = False) -> Tuple[str, List[Dict]]:
         """
@@ -609,7 +812,7 @@ class AgentStreamExecutor:
         tools_schema = None
         if self.tools:
             tools_schema = []
-            for tool in self.tools.values():
+            for tool in self._select_tools_for_injection():
                 input_schema = tool.params
                 try:
                     dynamic = (tool.get_json_schema() or {}).get("parameters") or {}
@@ -623,6 +826,22 @@ class AgentStreamExecutor:
                     "input_schema": input_schema,
                 })
 
+        # Debug: dump the full system prompt and messages sent to the LLM.
+        # Gated behind `debug` config to avoid flooding normal logs.
+        # try:
+        #     from config import conf
+        #     if conf().get("debug", False):
+        #         logger.debug(
+        #             "[Agent][debug] system_prompt sent to LLM "
+        #             f"({len(self.system_prompt or '')} chars):\n"
+        #             "================ SYSTEM PROMPT BEGIN ================\n"
+        #             f"{self.system_prompt}\n"
+        #             "================ SYSTEM PROMPT END =================="
+        #         )
+        #         logger.info(f"[Agent][debug] messages sent to LLM: {messages}")
+        # except Exception:
+        #     pass
+
         # Create request
         request = LLMRequest(
             messages=messages,
@@ -644,7 +863,32 @@ class AgentStreamExecutor:
         try:
             stream = self.model.call_stream(request)
 
+            # Probe cancel every N chunks to bound reaction time without
+            # checking on every token.
+            _cancel_probe_counter = 0
+            _CANCEL_PROBE_EVERY = 8
+
             for chunk in stream:
+                _cancel_probe_counter += 1
+                if _cancel_probe_counter >= _CANCEL_PROBE_EVERY:
+                    _cancel_probe_counter = 0
+                    if self.cancel_event is not None and self.cancel_event.is_set():
+                        # Persist partial text only; tool_use args may be
+                        # truncated mid-stream and would fail validation.
+                        logger.info("[Agent] cancel detected mid-stream, aborting LLM call")
+                        if full_content:
+                            partial_msg = {
+                                "role": "assistant",
+                                "content": [{"type": "text", "text": full_content}],
+                            }
+                            self.messages.append(partial_msg)
+                        self._emit_event("message_end", {
+                            "content": full_content,
+                            "tool_calls": [],
+                            "cancelled": True,
+                        })
+                        raise AgentCancelledError("cancelled during LLM streaming")
+
                 # Check for errors
                 if isinstance(chunk, dict) and chunk.get("error"):
                     # Extract error message from nested structure
@@ -738,6 +982,10 @@ class AgentStreamExecutor:
                     elif isinstance(choice, dict) and choice.get("_gemini_raw_parts"):
                         gemini_raw_parts = choice["_gemini_raw_parts"]
 
+        except AgentCancelledError:
+            # Must propagate untouched; never treat as a retryable error.
+            raise
+
         except Exception as e:
             error_str = str(e)
             error_str_lower = error_str.lower()
@@ -800,13 +1048,15 @@ class AgentStreamExecutor:
                 self.messages.clear()
                 self._clear_session_db()
                 if is_context_overflow:
-                    raise Exception(
-                        "抱歉，对话历史过长导致上下文溢出。我已清空历史记录，请重新描述你的需求。"
-                    )
+                    raise Exception(_t(
+                        "抱歉，对话历史过长导致上下文溢出。我已清空历史记录，请重新描述你的需求。",
+                        "Sorry, the conversation history got too long and overflowed the context. I've cleared the history — please describe your request again.",
+                    ))
                 else:
-                    raise Exception(
-                        "抱歉，之前的对话出现了问题。我已清空历史记录，请重新发送你的消息。"
-                    )
+                    raise Exception(_t(
+                        "抱歉，之前的对话出现了问题。我已清空历史记录，请重新发送你的消息。",
+                        "Sorry, something went wrong with the earlier conversation. I've cleared the history — please send your message again.",
+                    ))
             
             # Check if error is rate limit (429)
             is_rate_limit = '429' in error_str_lower or 'rate limit' in error_str_lower
@@ -851,26 +1101,17 @@ class AgentStreamExecutor:
                 import uuid
                 tool_id = f"call_{uuid.uuid4().hex[:24]}"
 
-            try:
-                # Safely get arguments, handle None case
-                args_str = tc.get("arguments") or ""
-                arguments = json.loads(args_str) if args_str else {}
-            except json.JSONDecodeError as e:
-                # Handle None or invalid arguments safely
-                args_str = tc.get('arguments') or ""
-                args_preview = args_str[:200] if len(args_str) > 200 else args_str
-                logger.error(f"Failed to parse tool arguments for {tc['name']}")
-                logger.error(f"Arguments length: {len(args_str)} chars")
-                logger.error(f"Arguments preview: {args_preview}...")
-                logger.error(f"JSON decode error: {e}")
-
-                # Return a clear error message to the LLM instead of empty dict
-                # This helps the LLM understand what went wrong
+            args_str = tc.get("arguments") or ""
+            arguments, parse_err = _parse_tool_args(args_str, stop_reason)
+            if parse_err:
+                logger.error(
+                    f"Tool args parse failed for {tc['name']} ({len(args_str)} chars): {parse_err}"
+                )
                 tool_calls.append({
                     "id": tool_id,
                     "name": tc["name"],
                     "arguments": {},
-                    "_parse_error": f"Invalid JSON in tool arguments: {args_preview}... Error: {str(e)}. Tip: For large content, consider splitting into smaller chunks or using a different approach."
+                    "_parse_error": parse_err,
                 })
                 continue
 
@@ -958,14 +1199,11 @@ class AgentStreamExecutor:
         tool_id = tool_call["id"]
         arguments = tool_call["arguments"]
 
-        # Check if there was a JSON parse error
         if "_parse_error" in tool_call:
-            parse_error = tool_call["_parse_error"]
-            logger.error(f"Skipping tool execution due to parse error: {parse_error}")
             result = {
                 "status": "error",
-                "result": f"Failed to parse tool arguments. {parse_error}. Please ensure your tool call uses valid JSON format with all required parameters.",
-                "execution_time": 0
+                "result": tool_call["_parse_error"],
+                "execution_time": 0,
             }
             self._record_tool_result(tool_name, arguments, False)
             return result
@@ -1006,10 +1244,21 @@ class AgentStreamExecutor:
             # Set tool context
             tool.model = self.model
             tool.context = self.agent
+            tool.progress_callback = lambda message: self._emit_event(
+                "tool_execution_progress",
+                {
+                    "tool_call_id": tool_id,
+                    "tool_name": tool_name,
+                    "message": message,
+                }
+            )
 
             # Execute tool
             start_time = time.time()
-            result: ToolResult = tool.execute_tool(arguments)
+            try:
+                result: ToolResult = tool.execute_tool(arguments)
+            finally:
+                tool.progress_callback = None
             execution_time = time.time() - start_time
 
             result_dict = {
@@ -1397,8 +1646,8 @@ class AgentStreamExecutor:
             turns = turns[-keep_count:]
 
             logger.info(
-                f"💾 上下文轮次超限: {keep_count + removed_count} > {self.max_context_turns}，"
-                f"裁剪至 {keep_count} 轮（移除 {removed_count} 轮）"
+                f"💾 Context turns exceeded: {keep_count + removed_count} > {self.max_context_turns}, "
+                f"trimmed to {keep_count} turns (removed {removed_count})"
             )
 
             # Flush to daily memory + inject context summary (single async LLM call)
@@ -1446,7 +1695,7 @@ class AgentStreamExecutor:
             
             # Log if we removed messages due to turn limit
             if old_count > len(self.messages):
-                logger.info(f"   重建消息列表: {old_count} -> {len(self.messages)} 条消息")
+                logger.info(f"   Rebuilt message list: {old_count} -> {len(self.messages)} messages")
             return
 
         # Token limit exceeded — tiered strategy based on turn count:
@@ -1479,10 +1728,10 @@ class AgentStreamExecutor:
             self.messages = new_messages
 
             logger.info(
-                f"📦 上下文tokens超限(轮次<{COMPRESS_THRESHOLD}): "
-                f"~{current_tokens + system_tokens} > {max_tokens}，"
-                f"压缩全部 {len(turns)} 轮为纯文本 "
-                f"({old_count} -> {len(self.messages)} 条消息，"
+                f"📦 Context tokens exceeded (turns<{COMPRESS_THRESHOLD}): "
+                f"~{current_tokens + system_tokens} > {max_tokens}, "
+                f"compressed all {len(turns)} turns to plain text "
+                f"({old_count} -> {len(self.messages)} messages, "
                 f"~{current_tokens + system_tokens} -> ~{new_tokens + system_tokens} tokens)"
             )
             return
@@ -1495,8 +1744,8 @@ class AgentStreamExecutor:
         kept_tokens = sum(self._estimate_turn_tokens(t) for t in kept_turns)
 
         logger.info(
-            f"🔄 上下文tokens超限: ~{current_tokens + system_tokens} > {max_tokens}，"
-            f"裁剪至 {keep_count} 轮（移除 {removed_count} 轮）"
+            f"🔄 Context tokens exceeded: ~{current_tokens + system_tokens} > {max_tokens}, "
+            f"trimmed to {keep_count} turns (removed {removed_count})"
         )
 
         if self.agent.memory_manager:
@@ -1520,8 +1769,8 @@ class AgentStreamExecutor:
         self.messages = new_messages
 
         logger.info(
-            f"   移除了 {removed_count} 轮对话 "
-            f"({old_count} -> {len(self.messages)} 条消息，"
+            f"   Removed {removed_count} turns "
+            f"({old_count} -> {len(self.messages)} messages, "
             f"~{current_tokens + system_tokens} -> ~{kept_tokens + system_tokens} tokens)"
         )
 
@@ -1551,4 +1800,4 @@ class AgentStreamExecutor:
         not as a message. The AgentLLMModel will handle this.
         """
         # Don't add system message here - it will be handled separately by the LLM adapter
-        return self.messages
+        return self.messages

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/skills/service.py

@@ -34,6 +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
     # ------------------------------------------------------------------
@@ -107,7 +128,7 @@ class SkillService:
         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)
 
         tmp_dir = skill_dir + ".tmp"
         if os.path.exists(tmp_dir):
@@ -146,7 +167,7 @@ class SkillService:
             raise ValueError("package url is required")
 
         url = files[0]["url"]
-        skill_dir = os.path.join(self.manager.custom_dir, name)
+        skill_dir = self._safe_skill_dir(name)
 
         with tempfile.TemporaryDirectory() as tmp_dir:
             zip_path = os.path.join(tmp_dir, "package.zip")
@@ -217,7 +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/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"""
@@ -135,6 +138,7 @@ __all__ = [
     'Send',
     'MemorySearchTool',
     'MemoryGetTool',
+    'EvolutionUndoTool',
     'EnvConfig',
     'SchedulerTool',
     'WebSearch',

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

@@ -4,9 +4,12 @@ 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
@@ -19,6 +22,10 @@ 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.
@@ -69,8 +76,8 @@ SAFETY:
         if not command:
             return ToolResult.fail("Error: command parameter is required")
 
-        # Security check: Prevent accessing sensitive config files
-        if "~/.cow/.env" in command or "~/.cow" in command:
+        # Security check: Prevent direct access to the credential file
+        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."
             )
@@ -106,25 +113,35 @@ SAFETY:
             else:
                 logger.debug(f"[Bash] Process User: {os.environ.get('USERNAME', os.environ.get('USER', 'unknown'))}")
             
+            # Temp script written for long `python -c` commands (Windows only),
+            # cleaned up after execution.
+            temp_script_path = None
+
             # On Windows, convert $VAR references to %VAR% for cmd.exe
             if self._IS_WIN:
                 env["PYTHONIOENCODING"] = "utf-8"
                 command = self._convert_env_vars_for_windows(command, dotenv_vars)
+                # cmd.exe has an ~8191 char command line limit. Long
+                # `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}"
 
-            result = subprocess.run(
-                command,
-                shell=True,
-                cwd=self.cwd,
-                stdout=subprocess.PIPE,
-                stderr=subprocess.PIPE,
-                text=True,
-                encoding="utf-8",
-                errors="replace",
-                timeout=timeout,
-                env=env,
-            )
+            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)}")
@@ -185,8 +202,12 @@ SAFETY:
             total_bytes = len(output.encode('utf-8'))
 
             if total_bytes > DEFAULT_MAX_BYTES:
-                # Save full output to temp file
-                with tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.log', prefix='bash-') as f:
+                # Save full output to temp file. encoding='utf-8' is required:
+                # 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
 
@@ -236,6 +257,105 @@ 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 absolutely catastrophic commands only.
@@ -293,3 +413,43 @@ SAFETY:
             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/browser_env.py

@@ -0,0 +1,290 @@
+"""
+Browser environment detection and capability resolution.
+
+Centralizes everything about *where* a usable browser engine comes from, so
+both the runtime (browser_service) and the installer (cli/commands/install)
+agree on the same decisions:
+
+  - Whether the `playwright` Python package is importable.
+  - Whether a system Chrome / Edge is installed (Playwright can drive it via
+    the `channel="chrome"/"msedge"` launcher, no download needed).
+  - Where Playwright's own Chromium download lives (redirected to the writable
+    data dir so it survives frozen/desktop app updates).
+
+Resolution priority (see resolve_engine):
+  1. system-chrome  -> drive the user's installed Chrome / Edge (zero download)
+  2. playwright-chromium -> Playwright's own Chromium, if already downloaded
+  3. none -> nothing usable yet; caller should trigger onboarding
+"""
+
+import os
+import sys
+import shutil
+from typing import Optional, Dict, Any
+
+from common.log import logger
+
+
+# Playwright browser channels we accept for the "system-chrome" mode, in
+# preference order. "chrome" covers stable Google Chrome; "msedge" is the
+# Chromium-based Edge shipped on every Windows 10/11.
+_PREFERRED_CHANNELS = ("chrome", "msedge", "chrome-beta", "msedge-beta")
+
+
+def get_data_root() -> str:
+    """Writable data root (~/.cow on desktop, else CWD-based).
+
+    Mirrors the logic in common/log.py without importing config, to avoid a
+    circular import. The desktop build sets COW_DATA_DIR; source deployments
+    fall back to the current working directory.
+    """
+    data_dir = os.environ.get("COW_DATA_DIR")
+    if data_dir:
+        return os.path.expanduser(data_dir)
+    return os.getcwd()
+
+
+def browsers_download_dir() -> str:
+    """Directory Playwright downloads its Chromium into.
+
+    We pin it under the writable data root (~/.cow/ms-playwright) rather than
+    Playwright's default (~/.cache/ms-playwright or %USERPROFILE%). This keeps
+    the frozen desktop build self-contained and makes the download survive app
+    updates. Set as PLAYWRIGHT_BROWSERS_PATH for both install and runtime.
+    """
+    return os.path.join(get_data_root(), "ms-playwright")
+
+
+def apply_browsers_path_env() -> None:
+    """Point Playwright at our pinned download dir via env var (idempotent).
+
+    Only set it when not already provided by the user, so power users can
+    override the location. Must run before importing playwright's launcher.
+    """
+    if not os.environ.get("PLAYWRIGHT_BROWSERS_PATH"):
+        os.environ["PLAYWRIGHT_BROWSERS_PATH"] = browsers_download_dir()
+
+
+def is_frozen() -> bool:
+    """True when running inside a PyInstaller-frozen bundle (desktop backend).
+
+    In this mode sys.executable is the frozen exe (no pip), so the installer
+    must skip `pip install` and only download the browser binary.
+    """
+    return bool(getattr(sys, "frozen", False))
+
+
+def is_desktop() -> bool:
+    """True when running as the Electron desktop client (dev or packaged).
+
+    The desktop shell always sets COW_DESKTOP=1 (see python-manager.ts), both in
+    `npm run dev` (runs app.py with the user's Python) and in the packaged build
+    (frozen exe). Desktop users have no `cow` CLI, so onboarding must point them
+    at the in-chat `/install-browser` command rather than a terminal command.
+    """
+    return os.environ.get("COW_DESKTOP") == "1"
+
+
+def has_playwright_package() -> bool:
+    """True if the `playwright` Python package can be imported."""
+    try:
+        import playwright  # noqa: F401
+        return True
+    except Exception:
+        return False
+
+
+def _windows_program_dirs() -> list:
+    dirs = []
+    for var in ("PROGRAMFILES", "PROGRAMFILES(X86)", "LOCALAPPDATA"):
+        val = os.environ.get(var)
+        if val:
+            dirs.append(val)
+    return dirs
+
+
+def detect_system_chrome() -> Optional[Dict[str, str]]:
+    """Locate an installed Chromium-based browser Playwright can drive.
+
+    Returns a dict {"channel": <playwright channel>, "path": <exe path>} for
+    the first match, or None. The `channel` is what we hand to Playwright's
+    launcher; `path` is only informational (Playwright resolves the channel on
+    its own, but we keep the path for logging / onboarding messages).
+    """
+    candidates = []
+
+    if sys.platform == "darwin":
+        candidates = [
+            ("chrome", "/Applications/Google Chrome.app/Contents/MacOS/Google Chrome"),
+            ("msedge", "/Applications/Microsoft Edge.app/Contents/MacOS/Microsoft Edge"),
+            ("chrome-beta", "/Applications/Google Chrome Beta.app/Contents/MacOS/Google Chrome Beta"),
+        ]
+    elif sys.platform == "win32":
+        prog_dirs = _windows_program_dirs()
+        for base in prog_dirs:
+            candidates.append(("chrome", os.path.join(base, "Google", "Chrome", "Application", "chrome.exe")))
+            candidates.append(("msedge", os.path.join(base, "Microsoft", "Edge", "Application", "msedge.exe")))
+    else:
+        # Linux: rely on PATH lookups for the common binaries.
+        path_lookups = [
+            ("chrome", "google-chrome"),
+            ("chrome", "google-chrome-stable"),
+            ("chrome", "chromium"),
+            ("chrome", "chromium-browser"),
+            ("msedge", "microsoft-edge"),
+        ]
+        for channel, binary in path_lookups:
+            found = shutil.which(binary)
+            if found:
+                return {"channel": channel, "path": found}
+
+    for channel, path in candidates:
+        if path and os.path.exists(path):
+            return {"channel": channel, "path": path}
+
+    return None
+
+
+def has_downloaded_chromium() -> bool:
+    """True if Playwright already has a Chromium download available.
+
+    We check our pinned download dir for a chromium-* folder. This is a
+    lightweight heuristic (avoids importing/launching Playwright just to probe)
+    and matches how Playwright lays browsers out on disk.
+    """
+    download_dir = browsers_download_dir()
+    if not os.path.isdir(download_dir):
+        return False
+    try:
+        for name in os.listdir(download_dir):
+            # Playwright names its browser dirs like "chromium-1140",
+            # "chromium_headless_shell-1140".
+            if name.startswith("chromium"):
+                return True
+    except OSError:
+        pass
+    return False
+
+
+def resolve_engine(config: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
+    """Decide which browser engine to use, given config and environment.
+
+    Returns a dict describing the launch strategy:
+        {
+            "mode": "system-chrome" | "playwright-chromium" | "none",
+            "channel": Optional[str],   # for system-chrome
+            "path": Optional[str],      # for system-chrome (informational)
+            "has_playwright": bool,
+            "reason": str,              # human-readable, for logging / onboarding
+        }
+
+    Config keys under tools.browser that influence this:
+      - engine: "auto" (default) | "system-chrome" | "chromium"
+          Force a specific engine. "auto" prefers system Chrome, then falls
+          back to a downloaded Chromium.
+      - prefer_system_browser: bool (default True). When False under "auto",
+          skip system Chrome and go straight to Playwright's Chromium.
+    """
+    config = config or {}
+    apply_browsers_path_env()
+
+    has_pw = has_playwright_package()
+    engine_pref = str(config.get("engine", "auto")).strip().lower()
+    prefer_system = config.get("prefer_system_browser", True)
+
+    if not has_pw:
+        return {
+            "mode": "none",
+            "channel": None,
+            "path": None,
+            "has_playwright": False,
+            "reason": "playwright package not available",
+        }
+
+    system = None
+    if engine_pref in ("auto", "system-chrome") and prefer_system:
+        system = detect_system_chrome()
+
+    if engine_pref == "system-chrome":
+        # Explicitly requested: use system Chrome if found, else report none.
+        if system:
+            return {
+                "mode": "system-chrome",
+                "channel": system["channel"],
+                "path": system["path"],
+                "has_playwright": True,
+                "reason": f"using system browser ({system['channel']})",
+            }
+        return {
+            "mode": "none",
+            "channel": None,
+            "path": None,
+            "has_playwright": True,
+            "reason": "engine=system-chrome but no Chrome/Edge found",
+        }
+
+    if engine_pref == "chromium":
+        # Explicitly requested Playwright's own Chromium.
+        if has_downloaded_chromium():
+            return {
+                "mode": "playwright-chromium",
+                "channel": None,
+                "path": None,
+                "has_playwright": True,
+                "reason": "using downloaded Playwright Chromium",
+            }
+        return {
+            "mode": "none",
+            "channel": None,
+            "path": None,
+            "has_playwright": True,
+            "reason": "engine=chromium but Chromium not downloaded yet",
+        }
+
+    # auto: system Chrome first, then downloaded Chromium.
+    if system:
+        return {
+            "mode": "system-chrome",
+            "channel": system["channel"],
+            "path": system["path"],
+            "has_playwright": True,
+            "reason": f"auto: using system browser ({system['channel']})",
+        }
+    if has_downloaded_chromium():
+        return {
+            "mode": "playwright-chromium",
+            "channel": None,
+            "path": None,
+            "has_playwright": True,
+            "reason": "auto: using downloaded Playwright Chromium",
+        }
+
+    return {
+        "mode": "none",
+        "channel": None,
+        "path": None,
+        "has_playwright": True,
+        "reason": "no system Chrome/Edge and no downloaded Chromium",
+    }
+
+
+def capability_summary(config: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
+    """High-level browser capability status, for onboarding / diagnostics.
+
+    Combines resolve_engine with raw detection flags so the UI / tool layer can
+    craft a helpful message (e.g. "Chrome detected, click to enable" vs
+    "no browser, will download ~150MB").
+    """
+    engine = resolve_engine(config)
+    system = detect_system_chrome()
+    return {
+        "ready": engine["mode"] != "none",
+        "engine": engine,
+        "has_playwright": engine["has_playwright"],
+        "has_system_chrome": system is not None,
+        "system_chrome": system,
+        "has_downloaded_chromium": has_downloaded_chromium(),
+        "is_frozen": is_frozen(),
+        "is_desktop": is_desktop(),
+        "browsers_dir": browsers_download_dir(),
+    }

agent/tools/browser/browser_service.py

@@ -15,7 +15,7 @@ import threading
 from typing import Optional, Dict, Any, List, Callable
 
 from common.log import logger
-from common.utils import expand_path
+from common.utils import expand_path, is_cloud_deployment
 
 
 _DEFAULT_USER_DATA_DIR = "~/.cow/browser_profile"
@@ -326,12 +326,19 @@ class BrowserService:
         # - 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.
+        #
+        # Within persistent/fresh, the actual Chromium binary is resolved by
+        # browser_env.resolve_engine(): a system Chrome/Edge (channel-based, zero
+        # download) is preferred, falling back to Playwright's own downloaded
+        # Chromium. `self._channel` is the Playwright channel ("chrome"/"msedge")
+        # when driving a system browser, else None (bundled Chromium).
         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._channel: Optional[str] = None
         self._cdp_endpoint: str = cdp_endpoint.strip() if isinstance(cdp_endpoint, str) else ""
         if self._cdp_endpoint:
             self._launch_mode = "cdp"
@@ -343,6 +350,22 @@ class BrowserService:
             self._launch_mode = "fresh"
             self._user_data_dir = ""
 
+        # Resolve which browser engine to drive (system Chrome vs downloaded
+        # Chromium). Deferred detection failures are surfaced at launch time.
+        if self._launch_mode != "cdp":
+            try:
+                from agent.tools.browser.browser_env import resolve_engine
+                engine = resolve_engine(self._config)
+                if engine["mode"] == "system-chrome":
+                    self._channel = engine["channel"]
+                    logger.info(f"[Browser] Engine resolved: {engine['reason']}")
+                elif engine["mode"] == "playwright-chromium":
+                    logger.info(f"[Browser] Engine resolved: {engine['reason']}")
+                else:
+                    logger.info(f"[Browser] No ready engine yet: {engine['reason']}")
+            except Exception as e:
+                logger.debug(f"[Browser] Engine resolution skipped: {e}")
+
         # 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
@@ -428,6 +451,14 @@ class BrowserService:
 
     def _launch_browser(self):
         """Launch / connect Chromium on the background thread."""
+        # Point Playwright at our pinned download dir before any launch so a
+        # bundled-Chromium fallback finds the browser downloaded to ~/.cow.
+        try:
+            from agent.tools.browser.browser_env import apply_browsers_path_env
+            apply_browsers_path_env()
+        except Exception as e:
+            logger.debug(f"[Browser] apply_browsers_path_env skipped: {e}")
+
         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()
@@ -436,6 +467,20 @@ class BrowserService:
         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)
@@ -461,12 +506,20 @@ class BrowserService:
         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,
-        )
+        """Classic launch: brand new Chromium with an empty context.
+
+        When `self._channel` is set (e.g. "chrome"/"msedge"), Playwright drives
+        the user's installed system browser instead of its own Chromium.
+        """
+        engine_label = f"system:{self._channel}" if self._channel else "chromium"
+        logger.info(f"[Browser] Launching {engine_label} (fresh, headless={self._headless})")
+        launch_kwargs: Dict[str, Any] = {
+            "headless": self._headless,
+            "args": launch_args,
+        }
+        if self._channel:
+            launch_kwargs["channel"] = self._channel
+        self._browser = self._playwright.chromium.launch(**launch_kwargs)
         self._context = self._browser.new_context(
             viewport=viewport,
             user_agent=user_agent,
@@ -477,18 +530,25 @@ class BrowserService:
     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)
+        engine_label = f"system:{self._channel}" if self._channel else "chromium"
         logger.info(
-            f"[Browser] Launching Chromium (persistent, headless={self._headless}, "
+            f"[Browser] Launching {engine_label} (persistent, headless={self._headless}, "
             f"profile={self._user_data_dir})"
         )
+        persistent_kwargs: Dict[str, Any] = {
+            "user_data_dir": self._user_data_dir,
+            "headless": self._headless,
+            "args": launch_args,
+            "viewport": viewport,
+            "user_agent": user_agent,
+        }
+        # When driving a system browser, let it use its real UA instead of the
+        # spoofed Chromium one (avoids UA/engine mismatch on real Chrome/Edge).
+        if self._channel:
+            persistent_kwargs["channel"] = self._channel
+            persistent_kwargs.pop("user_agent", None)
         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,
-            )
+            self._context = self._playwright.chromium.launch_persistent_context(**persistent_kwargs)
         except Exception as e:
             # Profile is locked when another Chromium instance already holds it.
             msg = str(e).lower()

agent/tools/browser/browser_tool.py

@@ -15,15 +15,24 @@ Launch modes (configured under `tools.browser` in config.json):
   - 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."""
 
@@ -121,6 +130,95 @@ class BrowserTool(BaseTool):
         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 _check_engine_ready(self) -> Optional[ToolResult]:
+        """Return an actionable onboarding message if no browser engine is ready.
+
+        Returns None when a system Chrome/Edge or a downloaded Chromium is
+        available (so the tool can proceed). Otherwise returns a ToolResult with
+        clear guidance so the agent asks the user to enable the browser instead
+        of surfacing a raw Playwright launch error. CDP mode is exempt (the
+        endpoint is external and validated at connect time).
+        """
+        if self.config.get("cdp_endpoint"):
+            return None
+        try:
+            from agent.tools.browser.browser_env import capability_summary
+            summary = capability_summary(self.config)
+        except Exception as e:
+            logger.debug(f"[Browser] capability probe failed: {e}")
+            return None
+
+        if summary.get("ready"):
+            return None
+
+        # Desktop clients (dev or packaged) have no `cow` CLI — onboard via the
+        # in-chat `/install-browser` command. Source / web / server installs use
+        # the `cow install-browser` terminal command.
+        install_hint = (
+            "reply `/install-browser`" if summary.get("is_desktop")
+            else "run `cow install-browser` in a terminal"
+        )
+        return ToolResult.fail(
+            f"Browser tool not ready. Ask the user to {install_hint} (installs a browser engine; "
+            "skipped automatically if Google Chrome is already installed). "
+            "Do not retry until the user confirms."
+        )
+
     def execute(self, args: Dict[str, Any]) -> ToolResult:
         action = args.get("action", "").strip().lower()
         if not action:
@@ -131,6 +229,13 @@ class BrowserTool(BaseTool):
             valid = ", ".join(sorted(self._ACTION_MAP.keys()))
             return ToolResult.fail(f"Unknown action '{action}'. Valid actions: {valid}")
 
+        # Preflight: on desktop the playwright package is bundled but the browser
+        # binary may be missing; return actionable onboarding instead of a cryptic
+        # launch failure.
+        not_ready = self._check_engine_ready()
+        if not_ready is not None:
+            return not_ready
+
         try:
             return handler(self, args)
         except Exception as e:
@@ -145,8 +250,19 @@ class BrowserTool(BaseTool):
         url = args.get("url", "").strip()
         if not url:
             return ToolResult.fail("Error: 'url' is required for navigate action")
-        if not url.startswith(("http://", "https://")):
+        # 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)

agent/tools/edit/edit.py

@@ -13,7 +13,7 @@ from agent.tools.utils.diff import (
     detect_line_ending,
     normalize_to_lf,
     restore_line_endings,
-    normalize_for_fuzzy_match,
+    count_matches,
     fuzzy_find_text,
     generate_diff_string
 )
@@ -110,10 +110,10 @@ class Edit(BaseTool):
                         "The old text must match exactly including all whitespace and newlines."
                     )
                 
-                # Calculate occurrence count (use fuzzy normalized content for consistency)
-                fuzzy_content = normalize_for_fuzzy_match(normalized_content)
-                fuzzy_old_text = normalize_for_fuzzy_match(normalized_old_text)
-                occurrences = fuzzy_content.count(fuzzy_old_text)
+                # Count occurrences with the same matcher used to locate and
+                # replace (fuzzy_find_text), so the uniqueness guard cannot
+                # disagree with what actually gets replaced.
+                occurrences = count_matches(normalized_content, normalized_old_text)
                 
                 if occurrences > 1:
                     return ToolResult.fail(

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/mcp_client.py

@@ -1,13 +1,13 @@
 """
 MCP (Model Context Protocol) client module.
 
-Implements JSON-RPC 2.0 over stdio and SSE transports without any external
-MCP SDK dependency.
+Implements JSON-RPC 2.0 over stdio, SSE and Streamable HTTP transports
+without any external MCP SDK dependency.
 """
 
 import json
 import os
-import select
+import queue
 import subprocess
 import threading
 import urllib.request
@@ -17,30 +17,104 @@ 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"}
+
+
+# Optional callback invoked after an OAuth authorization completes, so the
+# tool manager can bring the newly-authorized server online. Signature:
+# reload_fn(server_name: str) -> None. Installed by the tool manager.
+_reload_callback = None
+
+
+def set_reload_callback(fn) -> None:
+    """Register a callback fired after a server's OAuth flow succeeds."""
+    global _reload_callback
+    _reload_callback = fn
+
+
+def notify_server_authorized(server_name: str) -> None:
+    """Called by the web callback once tokens are stored for a server."""
+    fn = _reload_callback
+    if fn is None:
+        logger.debug(f"[MCP:{server_name}] Authorized but no reload callback registered")
+        return
+    try:
+        fn(server_name)
+    except Exception as e:
+        logger.warning(f"[MCP:{server_name}] reload callback failed: {e}")
+
+
+def _oauth_redirect_uri() -> str:
+    """Build the OAuth redirect URI served by the web console callback.
+
+    Priority: explicit mcp_oauth_redirect_base config, otherwise the local
+    web console address (127.0.0.1:<web_port>). Both point at the shared
+    /mcp/oauth/callback route.
+    """
+    try:
+        from config import conf
+        base = (conf().get("mcp_oauth_redirect_base") or "").strip().rstrip("/")
+        if not base:
+            port = int(os.environ.get("COW_WEB_PORT") or conf().get("web_port", 9899))
+            base = f"http://127.0.0.1:{port}"
+    except Exception:
+        base = "http://127.0.0.1:9899"
+    return f"{base}/mcp/oauth/callback"
+
+
 class McpClient:
-    """Single MCP Server client supporting stdio and SSE transports."""
+    """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"}
+          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")
-        self.transport: str = config.get("type", "stdio")
+        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
+
+        # OAuth state (streamable-http only). Lazily created when the server
+        # responds with 401 and the user has not supplied a static token.
+        self._oauth = None  # OAuthHandler instance
+        # Set to True once a 401 could not be satisfied and the user must
+        # complete the browser authorization. Callers can surface this state.
+        self.needs_auth: bool = False
+
         # 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
 
     # ------------------------------------------------------------------
@@ -54,6 +128,8 @@ class McpClient:
                 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
@@ -109,6 +185,21 @@ class McpClient:
                     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
 
     # ------------------------------------------------------------------
@@ -139,6 +230,9 @@ class McpClient:
         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()
 
@@ -146,14 +240,35 @@ class McpClient:
         for line in self._proc.stderr:
             line = line.strip()
             if line:
-                logger.debug(f"[MCP:{self.name}] stderr: {line}")
+                logger.warning(f"[MCP:{self.name}] stderr: {line}")
 
-    def _readline_with_timeout(self, timeout: int = 30) -> str:
-        """Read one line from stdio stdout with a hard timeout."""
-        ready, _, _ = select.select([self._proc.stdout], [], [], timeout)
-        if not ready:
-            raise TimeoutError(f"[MCP:{self.name}] stdio read timed out after {timeout}s")
-        return self._proc.stdout.readline()
+    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."""
@@ -161,6 +276,7 @@ class McpClient:
         self._proc.stdin.write(raw)
         self._proc.stdin.flush()
 
+        expected_id = message.get("id")
         while True:
             line = self._readline_with_timeout()
             if not line:
@@ -175,6 +291,14 @@ class McpClient:
             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
 
     # ------------------------------------------------------------------
@@ -234,6 +358,243 @@ class McpClient:
             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()}
+
+        # Restore any previously stored OAuth credentials for this server so a
+        # restart reuses the token instead of forcing re-authorization.
+        self._maybe_load_oauth()
+
+        return self._handshake()
+
+    # ------------------------------------------------------------------
+    # OAuth helpers (streamable-http only)
+    # ------------------------------------------------------------------
+
+    def _has_static_auth(self) -> bool:
+        """True when the user supplied their own Authorization header."""
+        return any(k.lower() == "authorization" for k in self._http_headers)
+
+    def _maybe_load_oauth(self) -> None:
+        """Attach an OAuthHandler when stored credentials exist for this server."""
+        if self._has_static_auth():
+            return
+        try:
+            from agent.tools.mcp.mcp_oauth import OAuthHandler, load_server_record
+        except Exception:
+            return
+        rec = load_server_record(self.name)
+        # Only create a handler when we have something to reuse; otherwise it
+        # is created lazily on the first 401.
+        if rec.get("access_token") or rec.get("client_id"):
+            self._oauth = OAuthHandler(
+                server_name=self.name,
+                resource_url=self._http_url,
+                redirect_uri=_oauth_redirect_uri(),
+                scope=self.config.get("scope", ""),
+            )
+
+    def _current_bearer(self) -> Optional[str]:
+        """Return a valid access token, refreshing if needed."""
+        if self._oauth is None:
+            return None
+        return self._oauth.get_valid_access_token()
+
+    def _begin_oauth(self, www_authenticate: str = "") -> None:
+        """Kick off the OAuth flow after a 401: discover, register, prompt user."""
+        if self._has_static_auth():
+            return
+        try:
+            from agent.tools.mcp.mcp_oauth import OAuthHandler
+        except Exception as e:
+            logger.warning(f"[MCP:{self.name}] OAuth module unavailable: {e}")
+            return
+
+        if self._oauth is None:
+            self._oauth = OAuthHandler(
+                server_name=self.name,
+                resource_url=self._http_url,
+                redirect_uri=_oauth_redirect_uri(),
+                scope=self.config.get("scope", ""),
+            )
+
+        if not self._oauth.ensure_registered(www_authenticate):
+            logger.warning(
+                f"[MCP:{self.name}] OAuth discovery/registration failed; "
+                f"cannot authorize automatically"
+            )
+            return
+
+        auth_url = self._oauth.build_authorization_url()
+        if not auth_url:
+            logger.warning(f"[MCP:{self.name}] Failed to build authorization URL")
+            return
+
+        self.needs_auth = True
+        logger.warning(
+            f"[MCP:{self.name}] ⚠️  Authorization required. Open this URL in a "
+            f"browser to authorize, then this server will come online automatically:\n"
+            f"    {auth_url}"
+        )
+        # On a machine with a local browser (desktop/dev), open it directly.
+        if os.environ.get("COW_DESKTOP") == "1" or not os.environ.get("COW_HEADLESS"):
+            try:
+                import webbrowser
+                webbrowser.open(auth_url)
+            except Exception:
+                pass
+
+    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 _handle_401(self, err, message: dict, expect_response: bool, retried: bool) -> dict:
+        """Handle a 401: refresh the token and retry once, else begin OAuth."""
+        www_auth = ""
+        try:
+            www_auth = err.headers.get("WWW-Authenticate", "") or ""
+        except Exception:
+            pass
+        try:
+            err.read()
+        except Exception:
+            pass
+
+        # First try a silent refresh with the stored refresh token.
+        if not retried and self._oauth is not None and self._oauth.refresh():
+            logger.info(f"[MCP:{self.name}] Token refreshed after 401, retrying")
+            return self._streamable_http_post(message, expect_response, _retried=True)
+
+        # No usable token — start (or restart) the interactive OAuth flow.
+        self._begin_oauth(www_auth)
+        raise IOError(
+            f"[MCP:{self.name}] streamable-http HTTP 401: authorization required "
+            f"(complete the OAuth flow to enable this server)"
+        )
+
+    def _streamable_http_post(self, message: dict, expect_response: bool, _retried: bool = False) -> 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)
+        # Inject OAuth bearer token when we have one (unless the user set a
+        # static Authorization header, which takes precedence).
+        if not self._has_static_auth():
+            token = self._current_bearer()
+            if token:
+                headers["Authorization"] = f"Bearer {token}"
+
+        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:
+            # 401 is the spec-compliant "needs authorization" signal.
+            if e.code == 401 and not self._has_static_auth():
+                return self._handle_401(e, message, expect_response, _retried)
+            # 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
     # ------------------------------------------------------------------
@@ -262,13 +623,18 @@ class McpClient:
 
         message = self._build_request(method, params)
 
-        with self._call_lock:
-            if self.transport == "stdio":
+        # 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)
-            else:
-                raise ValueError(f"[MCP:{self.name}] Unsupported transport: {self.transport}")
+        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)."""
@@ -291,6 +657,11 @@ class McpClient:
                     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."""

agent/tools/mcp/mcp_oauth.py

@@ -0,0 +1,466 @@
+"""
+MCP OAuth 2.1 client (authorization code + PKCE) with zero external deps.
+
+Implements the subset of the MCP authorization spec needed to connect to
+remote MCP servers that guard their endpoint behind OAuth (e.g. Xmind):
+
+  1. Metadata discovery via RFC 9728 (protected-resource) + RFC 8414
+     (authorization-server) .well-known documents.
+  2. Dynamic Client Registration (RFC 7591) to obtain a client_id.
+  3. PKCE (RFC 7636, S256) authorization-code flow.
+  4. Token exchange + refresh, persisted to ~/.cow/mcp_oauth.json.
+
+The actual browser round-trip is completed out-of-band: McpClient generates
+an authorization URL, the user opens it, and the web console callback
+(/mcp/oauth/callback) feeds the returned code back into finish_authorization().
+"""
+
+import base64
+import hashlib
+import json
+import os
+import secrets
+import threading
+import time
+import urllib.parse
+import urllib.request
+import urllib.error
+from typing import Optional
+
+from common.log import logger
+
+
+# ------------------------------------------------------------------
+# Token store: ~/.cow/mcp_oauth.json  {server_name: {...credentials...}}
+# ------------------------------------------------------------------
+
+_STORE_LOCK = threading.Lock()
+
+
+def _store_path() -> str:
+    base = os.path.expanduser("~/.cow")
+    try:
+        os.makedirs(base, exist_ok=True)
+    except OSError:
+        pass
+    return os.path.join(base, "mcp_oauth.json")
+
+
+def _load_store() -> dict:
+    path = _store_path()
+    if not os.path.exists(path):
+        return {}
+    try:
+        with open(path, "r", encoding="utf-8") as f:
+            data = json.load(f)
+        return data if isinstance(data, dict) else {}
+    except Exception as e:
+        logger.warning(f"[MCP-OAuth] Failed to read token store: {e}")
+        return {}
+
+
+def _save_store(store: dict) -> None:
+    path = _store_path()
+    tmp = f"{path}.tmp"
+    try:
+        with open(tmp, "w", encoding="utf-8") as f:
+            json.dump(store, f, ensure_ascii=False, indent=2)
+        os.replace(tmp, path)
+        # Credentials file: restrict to owner read/write when possible.
+        try:
+            os.chmod(path, 0o600)
+        except OSError:
+            pass
+    except Exception as e:
+        logger.warning(f"[MCP-OAuth] Failed to persist token store: {e}")
+
+
+def load_server_record(server_name: str) -> dict:
+    with _STORE_LOCK:
+        return dict(_load_store().get(server_name, {}))
+
+
+def save_server_record(server_name: str, record: dict) -> None:
+    with _STORE_LOCK:
+        store = _load_store()
+        store[server_name] = record
+        _save_store(store)
+
+
+def clear_server_record(server_name: str) -> None:
+    with _STORE_LOCK:
+        store = _load_store()
+        if server_name in store:
+            store.pop(server_name, None)
+            _save_store(store)
+
+
+# ------------------------------------------------------------------
+# Pending authorizations, keyed by the OAuth `state` param.
+# Populated when an authorization URL is generated; consumed by the
+# web callback when the browser redirects back with ?code&state.
+# ------------------------------------------------------------------
+
+_PENDING_LOCK = threading.Lock()
+_PENDING: dict = {}  # state -> {"handler": OAuthHandler, "created": ts}
+_PENDING_TTL = 600  # seconds
+
+
+def _register_pending(state: str, handler: "OAuthHandler") -> None:
+    with _PENDING_LOCK:
+        _prune_pending_locked()
+        _PENDING[state] = {"handler": handler, "created": time.time()}
+
+
+def _prune_pending_locked() -> None:
+    now = time.time()
+    stale = [s for s, v in _PENDING.items() if now - v["created"] > _PENDING_TTL]
+    for s in stale:
+        _PENDING.pop(s, None)
+
+
+def pop_pending(state: str) -> Optional["OAuthHandler"]:
+    with _PENDING_LOCK:
+        _prune_pending_locked()
+        entry = _PENDING.pop(state, None)
+    return entry["handler"] if entry else None
+
+
+def has_pending() -> bool:
+    with _PENDING_LOCK:
+        _prune_pending_locked()
+        return bool(_PENDING)
+
+
+# ------------------------------------------------------------------
+# HTTP helpers (stdlib only)
+# ------------------------------------------------------------------
+
+_UA = "CowAgent-MCP-OAuth/1.0"
+
+
+def _http_get_json(url: str, timeout: int = 15) -> Optional[dict]:
+    req = urllib.request.Request(url, headers={"Accept": "application/json", "User-Agent": _UA})
+    try:
+        with urllib.request.urlopen(req, timeout=timeout) as resp:
+            raw = resp.read().decode("utf-8")
+            return json.loads(raw)
+    except urllib.error.HTTPError as e:
+        logger.debug(f"[MCP-OAuth] GET {url} -> HTTP {e.code}")
+        return None
+    except Exception as e:
+        logger.debug(f"[MCP-OAuth] GET {url} failed: {e}")
+        return None
+
+
+def _http_post_form(url: str, fields: dict, timeout: int = 20) -> dict:
+    body = urllib.parse.urlencode(fields).encode("utf-8")
+    req = urllib.request.Request(
+        url,
+        data=body,
+        method="POST",
+        headers={
+            "Content-Type": "application/x-www-form-urlencoded",
+            "Accept": "application/json",
+            "User-Agent": _UA,
+        },
+    )
+    with urllib.request.urlopen(req, timeout=timeout) as resp:
+        raw = resp.read().decode("utf-8")
+        return json.loads(raw) if raw else {}
+
+
+def _http_post_json(url: str, payload: dict, timeout: int = 20) -> dict:
+    body = json.dumps(payload).encode("utf-8")
+    req = urllib.request.Request(
+        url,
+        data=body,
+        method="POST",
+        headers={
+            "Content-Type": "application/json",
+            "Accept": "application/json",
+            "User-Agent": _UA,
+        },
+    )
+    with urllib.request.urlopen(req, timeout=timeout) as resp:
+        raw = resp.read().decode("utf-8")
+        return json.loads(raw) if raw else {}
+
+
+# ------------------------------------------------------------------
+# Discovery (RFC 9728 + RFC 8414)
+# ------------------------------------------------------------------
+
+def _origin(url: str) -> str:
+    p = urllib.parse.urlparse(url)
+    return f"{p.scheme}://{p.netloc}"
+
+
+def discover_metadata(resource_url: str, www_authenticate: str = "") -> Optional[dict]:
+    """
+    Resolve the authorization server metadata for a protected MCP resource.
+
+    Returns a dict with at least authorization_endpoint + token_endpoint,
+    plus registration_endpoint when the server supports DCR. Returns None
+    when discovery fails.
+    """
+    as_metadata_url = _parse_resource_metadata_url(www_authenticate)
+
+    # 1) Protected-resource metadata (RFC 9728) to locate the auth server.
+    auth_server = None
+    prm = None
+    if as_metadata_url:
+        prm = _http_get_json(as_metadata_url)
+    if prm is None:
+        origin = _origin(resource_url)
+        prm = _http_get_json(f"{origin}/.well-known/oauth-protected-resource")
+    if prm and isinstance(prm.get("authorization_servers"), list) and prm["authorization_servers"]:
+        auth_server = prm["authorization_servers"][0]
+
+    # 2) Authorization-server metadata (RFC 8414). Fall back to the resource
+    #    origin when the resource did not advertise a separate auth server.
+    base = auth_server or _origin(resource_url)
+    asm = _fetch_as_metadata(base)
+    if not asm:
+        return None
+
+    if not asm.get("authorization_endpoint") or not asm.get("token_endpoint"):
+        logger.warning("[MCP-OAuth] Authorization server metadata missing required endpoints")
+        return None
+
+    # Derive the scope to request. Prefer the resource's required_scopes
+    # (RFC 9728), then its scopes_supported, then the auth server's
+    # scopes_supported. Stored so callers don't have to configure it.
+    discovered_scope = ""
+    if prm:
+        scopes = prm.get("required_scopes") or prm.get("scopes_supported")
+        if isinstance(scopes, list) and scopes:
+            discovered_scope = " ".join(str(s) for s in scopes)
+    if not discovered_scope and isinstance(asm.get("scopes_supported"), list) and asm["scopes_supported"]:
+        discovered_scope = " ".join(str(s) for s in asm["scopes_supported"])
+    if discovered_scope:
+        asm["_discovered_scope"] = discovered_scope
+    return asm
+
+
+def _parse_resource_metadata_url(www_authenticate: str) -> Optional[str]:
+    """Extract resource_metadata="..." from a WWW-Authenticate: Bearer header."""
+    if not www_authenticate:
+        return None
+    # naive but sufficient parse for `resource_metadata="URL"`
+    marker = "resource_metadata="
+    idx = www_authenticate.find(marker)
+    if idx < 0:
+        return None
+    rest = www_authenticate[idx + len(marker):].strip()
+    if rest.startswith('"'):
+        end = rest.find('"', 1)
+        return rest[1:end] if end > 0 else None
+    # unquoted, up to comma/space
+    for sep in (",", " "):
+        if sep in rest:
+            rest = rest.split(sep, 1)[0]
+    return rest or None
+
+
+def _fetch_as_metadata(base: str) -> Optional[dict]:
+    """Try both RFC 8414 and OIDC well-known locations."""
+    base = base.rstrip("/")
+    candidates = [
+        f"{base}/.well-known/oauth-authorization-server",
+        f"{base}/.well-known/openid-configuration",
+    ]
+    for url in candidates:
+        data = _http_get_json(url)
+        if data and data.get("authorization_endpoint"):
+            return data
+    return None
+
+
+# ------------------------------------------------------------------
+# PKCE
+# ------------------------------------------------------------------
+
+def _b64url(data: bytes) -> str:
+    return base64.urlsafe_b64encode(data).decode("ascii").rstrip("=")
+
+
+def _make_pkce() -> tuple:
+    verifier = _b64url(secrets.token_bytes(32))
+    challenge = _b64url(hashlib.sha256(verifier.encode("ascii")).digest())
+    return verifier, challenge
+
+
+# ------------------------------------------------------------------
+# OAuthHandler: per-server OAuth state machine
+# ------------------------------------------------------------------
+
+class OAuthHandler:
+    """Drives the OAuth flow and token lifecycle for a single MCP server."""
+
+    def __init__(self, server_name: str, resource_url: str, redirect_uri: str,
+                 scope: str = "", client_name: str = "CowAgent"):
+        self.server_name = server_name
+        self.resource_url = resource_url
+        self.redirect_uri = redirect_uri
+        self.scope = scope
+        self.client_name = client_name
+
+        rec = load_server_record(server_name)
+        self.metadata: dict = rec.get("metadata", {})
+        self.client_id: Optional[str] = rec.get("client_id")
+        self.client_secret: Optional[str] = rec.get("client_secret")
+        self.access_token: Optional[str] = rec.get("access_token")
+        self.refresh_token: Optional[str] = rec.get("refresh_token")
+        self.expires_at: float = float(rec.get("expires_at", 0) or 0)
+        self._verifier: Optional[str] = None
+
+    # --- persistence -------------------------------------------------
+
+    def _persist(self) -> None:
+        save_server_record(self.server_name, {
+            "resource_url": self.resource_url,
+            "metadata": self.metadata,
+            "client_id": self.client_id,
+            "client_secret": self.client_secret,
+            "access_token": self.access_token,
+            "refresh_token": self.refresh_token,
+            "expires_at": self.expires_at,
+        })
+
+    # --- token access ------------------------------------------------
+
+    def get_valid_access_token(self, leeway: int = 60) -> Optional[str]:
+        """Return a usable access token, refreshing proactively when near expiry."""
+        if not self.access_token:
+            return None
+        if self.expires_at and time.time() >= self.expires_at - leeway:
+            if not self.refresh():
+                return None
+        return self.access_token
+
+    def refresh(self) -> bool:
+        """Refresh the access token using the stored refresh token."""
+        if not self.refresh_token or not self.metadata.get("token_endpoint"):
+            return False
+        fields = {
+            "grant_type": "refresh_token",
+            "refresh_token": self.refresh_token,
+            "client_id": self.client_id or "",
+        }
+        if self.client_secret:
+            fields["client_secret"] = self.client_secret
+        try:
+            resp = _http_post_form(self.metadata["token_endpoint"], fields)
+        except Exception as e:
+            logger.warning(f"[MCP-OAuth:{self.server_name}] refresh failed: {e}")
+            return False
+        return self._absorb_token_response(resp)
+
+    # --- authorization-code flow ------------------------------------
+
+    def ensure_registered(self, www_authenticate: str = "") -> bool:
+        """Discover metadata + register a client if not already done."""
+        if not self.metadata.get("authorization_endpoint"):
+            meta = discover_metadata(self.resource_url, www_authenticate)
+            if not meta:
+                return False
+            self.metadata = meta
+        # Adopt the scope discovered from metadata when the user didn't set one.
+        if not self.scope and self.metadata.get("_discovered_scope"):
+            self.scope = self.metadata["_discovered_scope"]
+            logger.info(f"[MCP-OAuth:{self.server_name}] Using discovered scope: {self.scope}")
+        if not self.client_id:
+            if not self._register_client():
+                return False
+        self._persist()
+        return True
+
+    def _register_client(self) -> bool:
+        reg_endpoint = self.metadata.get("registration_endpoint")
+        if not reg_endpoint:
+            logger.warning(
+                f"[MCP-OAuth:{self.server_name}] No registration_endpoint; "
+                f"DCR unavailable. Provide client_id manually."
+            )
+            return False
+        payload = {
+            "client_name": self.client_name,
+            "redirect_uris": [self.redirect_uri],
+            "grant_types": ["authorization_code", "refresh_token"],
+            "response_types": ["code"],
+            "token_endpoint_auth_method": "none",
+        }
+        if self.scope:
+            payload["scope"] = self.scope
+        try:
+            resp = _http_post_json(reg_endpoint, payload)
+        except Exception as e:
+            logger.warning(f"[MCP-OAuth:{self.server_name}] DCR failed: {e}")
+            return False
+        client_id = resp.get("client_id")
+        if not client_id:
+            logger.warning(f"[MCP-OAuth:{self.server_name}] DCR returned no client_id")
+            return False
+        self.client_id = client_id
+        self.client_secret = resp.get("client_secret")
+        logger.info(f"[MCP-OAuth:{self.server_name}] Registered client_id={client_id}")
+        return True
+
+    def build_authorization_url(self) -> Optional[str]:
+        """Create an authorization URL and register this handler as pending."""
+        if not self.metadata.get("authorization_endpoint") or not self.client_id:
+            return None
+        self._verifier, challenge = _make_pkce()
+        state = secrets.token_urlsafe(24)
+        params = {
+            "response_type": "code",
+            "client_id": self.client_id,
+            "redirect_uri": self.redirect_uri,
+            "code_challenge": challenge,
+            "code_challenge_method": "S256",
+            "state": state,
+        }
+        if self.scope:
+            params["scope"] = self.scope
+        # Advertise the resource we intend to access (RFC 8707).
+        params["resource"] = self.resource_url
+        _register_pending(state, self)
+        return f"{self.metadata['authorization_endpoint']}?{urllib.parse.urlencode(params)}"
+
+    def finish_authorization(self, code: str) -> bool:
+        """Exchange an authorization code for tokens."""
+        if not self.metadata.get("token_endpoint") or not self._verifier:
+            return False
+        fields = {
+            "grant_type": "authorization_code",
+            "code": code,
+            "redirect_uri": self.redirect_uri,
+            "client_id": self.client_id or "",
+            "code_verifier": self._verifier,
+            "resource": self.resource_url,
+        }
+        if self.client_secret:
+            fields["client_secret"] = self.client_secret
+        try:
+            resp = _http_post_form(self.metadata["token_endpoint"], fields)
+        except Exception as e:
+            logger.warning(f"[MCP-OAuth:{self.server_name}] token exchange failed: {e}")
+            return False
+        ok = self._absorb_token_response(resp)
+        self._verifier = None
+        return ok
+
+    def _absorb_token_response(self, resp: dict) -> bool:
+        access = resp.get("access_token")
+        if not access:
+            logger.warning(f"[MCP-OAuth:{self.server_name}] token response missing access_token: {resp}")
+            return False
+        self.access_token = access
+        if resp.get("refresh_token"):
+            self.refresh_token = resp["refresh_token"]
+        expires_in = resp.get("expires_in")
+        self.expires_at = time.time() + int(expires_in) if expires_in else 0
+        self._persist()
+        logger.info(f"[MCP-OAuth:{self.server_name}] Access token stored")
+        return True

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
 
 
@@ -87,8 +89,13 @@ class MemoryGetTool(BaseTool):
             
             file_path = (workspace_dir / path).resolve()
             workspace_resolved = workspace_dir.resolve()
-            
-            if not str(file_path).startswith(str(workspace_resolved) + '/') and file_path != workspace_resolved:
+
+            # 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():

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",
@@ -79,9 +86,9 @@ class Read(BaseTool):
         # Resolve path
         absolute_path = self._resolve_path(path)
         
-        # Security check: Prevent reading sensitive config files
-        env_config_path = expand_path("~/.cow/.env")
-        if os.path.abspath(absolute_path) == os.path.abspath(env_config_path):
+        # Security check: block credential files and their aliases.
+        # See issue #2913 (/proc/self/environ bypass) and #2863 (scope).
+        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."
             )
@@ -140,7 +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.)
@@ -258,8 +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)
-                    start_line = max(0, total_file_lines + offset)
+                    # -20 means "last 20 lines" → start from (total - 20).
+                    # 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

agent/tools/scheduler/integration.py

@@ -57,34 +57,44 @@ def init_scheduler(agent_bridge) -> bool:
                 _task_store = TaskStore(store_path)
                 logger.debug(f"[Scheduler] Task store initialized: {store_path}")
 
-            # Create execute callback
+            # Create execute callback. Returns True on success, False to ask
+            # the scheduler to retry on the next tick (e.g. channel not yet
+            # ready right after process start).
             def execute_task_callback(task: dict):
-                """Callback to execute a scheduled task"""
                 try:
                     action = task.get("action", {})
                     action_type = action.get("type")
+                    channel_type = action.get("channel_type", "unknown")
+                    receiver = action.get("receiver", "")
+
+                    if not _is_channel_ready(channel_type, receiver):
+                        logger.warning(
+                            f"[Scheduler] Task {task.get('id')}: channel "
+                            f"'{channel_type}' not ready for receiver={receiver} "
+                            f"(no inbound msg cached since restart?); deferring"
+                        )
+                        return False
 
                     if action_type == "agent_task":
-                        _execute_agent_task(task, agent_bridge)
+                        return _execute_agent_task(task, agent_bridge)
                     elif action_type == "send_message":
-                        # Legacy support for old tasks
-                        _execute_send_message(task, agent_bridge)
+                        return _execute_send_message(task, agent_bridge)
                     elif action_type == "tool_call":
-                        # Legacy support for old tasks
-                        _execute_tool_call(task, agent_bridge)
+                        return _execute_tool_call(task, agent_bridge)
                     elif action_type == "skill_call":
-                        # Legacy support for old tasks
-                        _execute_skill_call(task, agent_bridge)
+                        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.debug("[Scheduler] Scheduler service initialized and started")
+            logger.info("[Scheduler] Service initialized and started")
             return True
 
         except Exception as e:
@@ -92,6 +102,40 @@ def init_scheduler(agent_bridge) -> bool:
             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.warning(f"[Scheduler] Channel readiness check failed for {channel_type}: {e}")
+        return True
+
+
 def get_task_store():
     """Get the global task store instance"""
     return _task_store
@@ -145,13 +189,10 @@ def _remember_delivered_output(
         )
 
 
-def _execute_agent_task(task: dict, agent_bridge):
+def _execute_agent_task(task: dict, agent_bridge) -> bool:
     """
-    Execute an agent_task action - let Agent handle the task
-    
-    Args:
-        task: Task dictionary
-        agent_bridge: AgentBridge instance
+    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", {})
@@ -162,11 +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":
@@ -209,51 +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:
-                # 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)
-                        _remember_delivered_output(agent_bridge, task, channel_type, reply.content)
-                        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:
+
+            if not (reply and reply.content):
                 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):
-    """
-    Execute a send_message action
-    
-    Args:
-        task: Task dictionary
-        agent_bridge: AgentBridge instance
-    """
+def _execute_send_message(task: dict, agent_bridge) -> bool:
+    """Execute a send_message action. Returns True/False for delivery."""
     try:
         action = task.get("action", {})
         content = action.get("content", "")
@@ -263,7 +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)
@@ -308,169 +345,135 @@ def _execute_send_message(task: dict, agent_bridge):
         # 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)
-            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)
-                _remember_delivered_output(agent_bridge, task, channel_type, content)
-                logger.info(f"[Scheduler] Task {task['id']} executed: sent message to {receiver}")
-            else:
-                logger.error(f"[Scheduler] Failed to create channel: {channel_type}")
+            channel.send(reply, context)
         except Exception as e:
             logger.error(f"[Scheduler] Failed to send message: {e}")
-            import traceback
-            logger.error(f"[Scheduler] Traceback: {traceback.format_exc()}")
-            
+            return False
+
+        _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):
-    """
-    Execute a tool_call action
-    
-    Args:
-        task: Task dictionary
-        agent_bridge: AgentBridge instance
-    """
+def _execute_tool_call(task: dict, agent_bridge) -> bool:
+    """Execute a tool_call action. Returns True/False for delivery."""
     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
-        
-        # Get tool manager and create tool instance
+            return True
+
         from agent.tools.tool_manager import ToolManager
-        tool_manager = ToolManager()
-        tool = tool_manager.create_tool(tool_name)
-        
+        tool = ToolManager().create_tool(tool_name)
         if not tool:
             logger.error(f"[Scheduler] Task {task['id']}: Tool '{tool_name}' not found")
-            return
-        
-        # Execute tool
+            return True
+
         logger.info(f"[Scheduler] Task {task['id']}: Executing tool '{tool_name}' with params {tool_params}")
         result = tool.execute(tool_params)
-        
-        # Get result content
-        if hasattr(result, 'result'):
-            content = result.result
-        else:
-            content = str(result)
-        
-        # Add prefix if specified
+        content = result.result if hasattr(result, 'result') else str(result)
         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":
             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)
-            if channel:
-                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)
-                _remember_delivered_output(agent_bridge, task, channel_type, content)
-                logger.info(f"[Scheduler] Task {task['id']} executed: sent tool result to {receiver}")
-            else:
-                logger.error(f"[Scheduler] Failed to create channel: {channel_type}")
+            channel.send(reply, context)
         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):
-    """
-    Execute a skill_call action by asking Agent to run the skill
-    
-    Args:
-        task: Task dictionary
-        agent_bridge: AgentBridge instance
-    """
+def _execute_skill_call(task: dict, agent_bridge) -> bool:
+    """Execute a skill_call action by asking Agent to run the skill.
+    Returns True/False for delivery."""
     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]}"
@@ -481,49 +484,48 @@ def _execute_skill_call(task: dict, agent_bridge):
         elif channel_type == "wecom_bot":
             context["msg"] = None
 
-        # Use Agent to execute the skill
         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}"
-                
-                # Send the result 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'):
-                            req_id = context.get("request_id")
-                            if req_id:
-                                channel.request_to_session[req_id] = receiver
-                                logger.debug(f"[Scheduler] Registered request_id {req_id} -> session {receiver}")
-                        
-                        channel.send(Reply(ReplyType.TEXT, content), context)
-                        _remember_delivered_output(agent_bridge, task, channel_type, content)
-                except Exception as e:
-                    logger.error(f"[Scheduler] Failed to send skill result: {e}")
-                
-                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

@@ -52,7 +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"""
@@ -67,7 +66,7 @@ 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:
@@ -84,12 +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)
-                    
-                    # Update next run time
+                    ok = self._execute_task(task)
+                    if not ok:
+                        # 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'], {
@@ -97,7 +102,6 @@ class SchedulerService:
                             "last_run_at": now.isoformat()
                         })
                     else:
-                        # One-time task completed, remove it
                         self.task_store.delete_task(task['id'])
                         logger.info(f"[Scheduler] One-time task completed and removed: {task['id']}")
             except Exception as e:
@@ -128,30 +132,35 @@ class SchedulerService:
         try:
             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()
-                
-                # If overdue by more than 5 minutes, skip this run and schedule next
-                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")
-                    
-                    # For one-time tasks, remove them directly
-                    schedule = task.get("schedule", {})
-                    if schedule.get("type") == "once":
-                        self.task_store.delete_task(task['id'])
-                        logger.info(f"[Scheduler] One-time task {task['id']} expired, removed")
-                        return False
-                    
-                    # For recurring tasks, calculate next run from now
-                    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}")
+                schedule = task.get("schedule", {})
+                schedule_type = schedule.get("type")
+
+                # Catch-up window: fire if we're within 10 minutes of the
+                # scheduled tick. Beyond that we'd rather skip than push a
+                # stale daily report to the user.
+                if time_diff <= 600:
+                    return True
+
+                logger.warning(
+                    f"[Scheduler] Task {task['id']} is overdue by {int(time_diff)}s, "
+                    f"skipping and scheduling next run"
+                )
+
+                if schedule_type == "once":
+                    self.task_store.delete_task(task['id'])
+                    logger.info(f"[Scheduler] One-time task {task['id']} expired, removed")
                     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 as e:
             logger.error(
@@ -213,20 +222,22 @@ class SchedulerService:
         
         return None
     
-    def _execute_task(self, task: dict):
+    def _execute_task(self, task: dict) -> bool:
         """
-        Execute a task
-        
-        Args:
-            task: Task dictionary
+        Execute a task.
+
+        Returns True if delivery succeeded (caller should advance state),
+        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
-            self.execute_callback(task)
+            result = 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/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
-        task_list.sort(key=lambda t: t.get("next_run_at", float('inf')))
+        # Sort by enabled status (enabled first), then by next_run_at
+        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

@@ -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)
         
@@ -112,6 +117,46 @@ class Send(BaseTool):
 
         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

@@ -71,6 +71,22 @@ class ToolManager:
         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):
         """
@@ -450,21 +466,30 @@ class ToolManager:
         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_client import McpClient, McpClientRegistry, set_reload_callback
             from agent.tools.mcp.mcp_tool import McpTool
 
             registry = McpClientRegistry()
             self._mcp_registry = registry
+            # Let the OAuth web callback bring a server online once authorized.
+            set_reload_callback(self.reload_mcp_server)
 
             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"
-                        )
+                        if getattr(client, "needs_auth", False):
+                            self._mcp_status[server_name] = "needs_auth"
+                            logger.info(
+                                f"[MCP] Server '{server_name}' needs authorization — "
+                                f"waiting for the user to complete the OAuth flow"
+                            )
+                        else:
+                            self._mcp_status[server_name] = "failed"
+                            logger.warning(
+                                f"[MCP] Server '{server_name}' failed to initialize — skipping"
+                            )
                         continue
 
                     tool_schemas = client.list_tools()
@@ -502,6 +527,28 @@ class ToolManager:
         except Exception as e:
             logger.warning(f"[ToolManager] MCP background loader crashed: {e}")
 
+    def reload_mcp_server(self, server_name: str) -> None:
+        """Re-initialize a single MCP server (e.g. after OAuth authorization).
+
+        Tears down any existing client for the server and starts it again in
+        the background, so a freshly-stored access token is picked up and the
+        server's tools become available on the next message.
+        """
+        with self._mcp_lock:
+            cfg = self._mcp_active_configs.get(server_name)
+        if not cfg:
+            logger.warning(f"[MCP] reload requested for unknown server '{server_name}'")
+            return
+        logger.info(f"[MCP] Reloading server '{server_name}' after authorization")
+        self._teardown_mcp_server(server_name)
+        self._mcp_status[server_name] = "pending"
+        threading.Thread(
+            target=self._load_mcp_tools_async,
+            args=([cfg],),
+            daemon=True,
+            name=f"mcp-reload-{server_name}",
+        ).start()
+
     def list_mcp_status(self) -> dict:
         """Return {server_name: status} snapshot for UI / debugging."""
         return dict(self._mcp_status)
@@ -523,6 +570,16 @@ class ToolManager:
         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())
@@ -564,6 +621,91 @@ class ToolManager:
 
         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.

agent/tools/utils/__init__.py

@@ -15,11 +15,17 @@ from .diff import (
     normalize_to_lf,
     restore_line_endings,
     normalize_for_fuzzy_match,
+    count_matches,
     fuzzy_find_text,
     generate_diff_string,
     FuzzyMatchResult
 )
 
+from .url_safety import (
+    validate_url_safe,
+    assert_public_ip
+)
+
 __all__ = [
     'truncate_head',
     'truncate_tail',
@@ -34,7 +40,10 @@ __all__ = [
     'normalize_to_lf',
     'restore_line_endings',
     'normalize_for_fuzzy_match',
+    'count_matches',
     'fuzzy_find_text',
     'generate_diff_string',
-    'FuzzyMatchResult'
+    'FuzzyMatchResult',
+    'validate_url_safe',
+    'assert_public_ip'
 ]

agent/tools/utils/diff.py

@@ -93,6 +93,40 @@ class FuzzyMatchResult:
         self.content_for_replacement = content_for_replacement
 
 
+def _build_fuzzy_pattern(old_text: str) -> Optional[str]:
+    """
+    Build the whitespace-flexible regex used to locate ``old_text`` fuzzily.
+
+    Returns ``None`` when ``old_text`` has no non-whitespace content to match.
+    This is the single source of truth for fuzzy matching, so that *finding* a
+    match (:func:`fuzzy_find_text`) and *counting* occurrences
+    (:func:`count_matches`) always use the exact same rules.
+    """
+    stripped = old_text.strip('\n')
+    if not stripped.strip():
+        return None
+
+    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]*')
+    return '\n'.join(line_patterns)
+
+
 def fuzzy_find_text(content: str, old_text: str) -> FuzzyMatchResult:
     """
     Find text in content, try exact match first, then fuzzy match
@@ -110,25 +144,54 @@ def fuzzy_find_text(content: str, old_text: str) -> FuzzyMatchResult:
             match_length=len(old_text),
             content_for_replacement=content
         )
-    
-    # Try fuzzy match
-    fuzzy_content = normalize_for_fuzzy_match(content)
-    fuzzy_old_text = normalize_for_fuzzy_match(old_text)
-    
-    index = fuzzy_content.find(fuzzy_old_text)
-    if index != -1:
-        # Fuzzy match successful, use normalized content for replacement
-        return FuzzyMatchResult(
-            found=True,
-            index=index,
-            match_length=len(fuzzy_old_text),
-            content_for_replacement=fuzzy_content
-        )
-    
+
+    # Fuzzy match: the exact substring was not found, most likely because the
+    # whitespace differs (indentation, spaces around operators, trailing
+    # spaces). Locate the region in the ORIGINAL content using a
+    # whitespace-flexible pattern and return offsets into that original
+    # content.
+    #
+    # This must NOT replace inside a whitespace-normalized copy of the file:
+    # doing so previously returned the normalized copy as
+    # content_for_replacement, which caused the whole file to be rewritten
+    # with collapsed indentation (every untouched line got reformatted).
+    pattern = _build_fuzzy_pattern(old_text)
+    if pattern is not None:
+        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)
 
 
+def count_matches(content: str, old_text: str) -> int:
+    """
+    Count occurrences of ``old_text`` using the SAME strategy as
+    :func:`fuzzy_find_text`: an exact substring when one is present, otherwise
+    the whitespace-flexible fuzzy regex.
+
+    The edit tool's uniqueness guard must agree with the matcher that actually
+    performs the replacement. Counting through a separate normalization pass
+    (the previous approach) could disagree with the regex used to locate and
+    replace, so both paths now share :func:`_build_fuzzy_pattern`.
+    """
+    if not old_text:
+        return 0
+    # Mirror fuzzy_find_text: prefer exact matching when it applies.
+    if content.find(old_text) != -1:
+        return content.count(old_text)
+    pattern = _build_fuzzy_pattern(old_text)
+    if pattern is None:
+        return 0
+    return len(re.findall(pattern, content))
+
+
 def generate_diff_string(old_content: str, new_content: str) -> dict:
     """
     Generate unified diff string

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/vision.py

@@ -26,13 +26,14 @@ 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_55
-DEFAULT_TIMEOUT = 60
-MAX_TOKENS = 1000
+DEFAULT_MODEL = const.GPT_41_MINI
+DEFAULT_TIMEOUT = 180
+MAX_TOKENS = 4000
 COMPRESS_THRESHOLD = 1_048_576  # 1 MB
 
 SUPPORTED_EXTENSIONS = {
@@ -51,12 +52,13 @@ _MAIN_MODEL_PROVIDER_NAME = "MainModel"
 _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.QWEN36_PLUS, "DashScope"),
-    ("claude_api_key", const.CLAUDEAPI, const.CLAUDE_4_6_SONNET, "Claude"),
+    ("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.
@@ -73,11 +75,29 @@ _MODEL_PREFIX_TO_PROVIDER = [
     ("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:
@@ -142,7 +162,7 @@ class Vision(BaseTool):
                 "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. ernie-4.5-turbo-vl, qwen3.6-plus, claude-sonnet-4-6, gemini-2.0-flash)\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\")"
             )
@@ -211,13 +231,19 @@ class Vision(BaseTool):
         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 derived from tools.vision.model
-        if user_model:
+        # 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)
+        if preferred:
+            providers.extend(preferred)
 
         # Step 2: auto-discovery chain as fallback
         existing = {p.name for p in providers}
@@ -263,6 +289,24 @@ class Vision(BaseTool):
             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]:
         """
@@ -279,6 +323,60 @@ class Vision(BaseTool):
                 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.
@@ -504,6 +602,34 @@ class Vision(BaseTool):
             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:
         """
@@ -563,6 +689,22 @@ class Vision(BaseTool):
             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.
@@ -570,6 +712,7 @@ class Vision(BaseTool):
         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):

agent/tools/web_fetch/web_fetch.py

@@ -16,11 +16,15 @@ 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",
@@ -107,23 +111,65 @@ class WebFetch(BaseTool):
         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 = requests.get(
-                url,
-                headers=DEFAULT_HEADERS,
-                timeout=DEFAULT_TIMEOUT,
-                allow_redirects=True,
-            )
+            response = self._safe_get(url)
             response.raise_for_status()
         except requests.Timeout:
             return ToolResult.fail(f"Error: Request timed out after {DEFAULT_TIMEOUT}s")
@@ -131,6 +177,8 @@ class WebFetch(BaseTool):
             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}")
 
@@ -158,13 +206,7 @@ class WebFetch(BaseTool):
         logger.info(f"[WebFetch] Downloading document: {url} -> {local_path}")
 
         try:
-            response = requests.get(
-                url,
-                headers=DEFAULT_HEADERS,
-                timeout=DEFAULT_TIMEOUT,
-                stream=True,
-                allow_redirects=True,
-            )
+            response = self._safe_get(url, stream=True)
             response.raise_for_status()
 
             content_length = int(response.headers.get("Content-Length", 0))
@@ -191,6 +233,9 @@ class WebFetch(BaseTool):
             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}")

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
@@ -76,7 +81,15 @@ 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()
 
                 # Cloud client is optional. It is only started when
                 # use_linkai=True AND cloud_deployment_id is set.
@@ -231,10 +244,14 @@ def _clear_singleton_cache(channel_name: str):
         "wechatmp": "channel.wechatmp.wechatmp_channel.WechatMPChannel",
         "wechatmp_service": "channel.wechatmp.wechatmp_channel.WechatMPChannel",
         "wechatcom_app": "channel.wechatcom.wechatcomapp_channel.WechatComAppChannel",
+        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",
     }
@@ -288,6 +305,16 @@ def _warmup_mcp_tools():
         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
@@ -350,8 +377,18 @@ def run():
         _sync_builtin_skills()
 
         # Kick off MCP server loading in the background so first-message
-        # latency isn't dominated by npx package downloads.
-        _warmup_mcp_tools()
+        # 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}")
 

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
@@ -78,6 +78,7 @@ class AgentLLMModel(LLMModel):
         ("moonshot", const.MOONSHOT), ("kimi", const.MOONSHOT),
         ("doubao", const.DOUBAO), ("deepseek", const.DEEPSEEK),
         ("ernie", const.QIANFAN),
+        ("mimo-", const.MIMO),
     ]
 
     def __init__(self, bridge: Bridge, bot_type: str = "chat"):
@@ -285,6 +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
@@ -373,7 +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:
         """
@@ -390,11 +450,22 @@ class AgentBridge:
         """
         session_id = None
         agent = None
+        request_id = None
+        cancel_event = None
         try:
             # Extract session_id from context for user isolation
             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:
@@ -444,14 +515,40 @@ class AgentBridge:
                 )
                 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
@@ -459,10 +556,21 @@ 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 ""
-                new_messages = getattr(agent, '_last_run_new_messages', [])
+                new_messages = list(getattr(agent, '_last_run_new_messages', []))
+                # The leading user turn was already persisted eagerly above;
+                # 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:
@@ -476,6 +584,23 @@ class AgentBridge:
                         except Exception as e:
                             logger.warning(f"[AgentBridge] Failed to clear DB after recovery: {e}")
             
+            # 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;
@@ -512,6 +637,12 @@ class AgentBridge:
                         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):
@@ -553,11 +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 = f"file://{file_path}"
+            file_url = _to_channel_url(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)
@@ -567,7 +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))
@@ -577,7 +718,7 @@ class AgentBridge:
             return reply
         
         # For all other file types (tar.gz, zip, etc.), also use FILE type
-        file_url = f"file://{file_path}"
+        file_url = _to_channel_url(file_path)
         logger.info(f"[AgentBridge] Sending generic file: {file_url}")
         reply = Reply(ReplyType.FILE, file_url)
         reply.file_name = file_info.get("file_name", os.path.basename(file_path))
@@ -655,6 +796,48 @@ class AgentBridge:
             except Exception as 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:

bridge/agent_event_handler.py

@@ -2,44 +2,40 @@
 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
-        
+
         self.current_content = ""
         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":
@@ -52,25 +48,23 @@ class AgentEventHandler:
             self._handle_tool_execution_start(data)
         elif event_type == "tool_execution_end":
             self._handle_tool_execution_end(data)
-        
-        # Call original callback if provided
+        elif event_type == "agent_end":
+            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.current_content = ""
-    
+
     def _handle_message_update(self, data):
-        """Handle message update event (streaming content text)"""
         delta = data.get("delta", "")
         self.current_content += delta
-    
+
     def _handle_message_end(self, data):
-        """Handle message end event"""
         tool_calls = data.get("tool_calls", [])
-        
+
         if tool_calls:
             if self.current_content.strip():
                 logger.info(f"💭 {self.current_content.strip()[:200]}{'...' if len(self.current_content) > 200 else ''}")
@@ -78,35 +72,54 @@ class AgentEventHandler:
         else:
             if self.current_content.strip():
                 logger.debug(f"💬 {self.current_content.strip()[:200]}{'...' if len(self.current_content) > 200 else ''}")
-        
+            # Drain weixin buffer before final reply leaves chat_channel
+            self._flush_merged_now()
+
         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

@@ -17,10 +17,6 @@ from common.utils import expand_path
 # Module-level lock to serialize scheduler init across concurrent sessions
 _scheduler_init_lock = threading.Lock()
 
-# Track whether the embedding model log has been printed in this process,
-# so we avoid spamming it once per session.
-_embedding_logged: bool = False
-
 
 class AgentInitializer:
     """
@@ -306,186 +302,16 @@ class AgentInitializer:
         """
         Initialize the embedding provider for memory.
 
-        Two paths:
+        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. Existing 1536-dim indices
-             keep working.
+             Auto-init OpenAI -> LinkAI fallback.
           B. Explicit (`embedding_provider` is set):
-             Initialize the requested vendor with unified dim (default 1024).
-             If the index was built with a different dim, vector search will
-             quietly return no results (cosine returns 0) and keyword search
-             takes over until the user runs /memory rebuild-index.
+             Initialize the requested vendor.
         """
-        from agent.memory import create_embedding_provider
-        from config import conf
+        from agent.memory import create_default_embedding_provider
+        return create_default_embedding_provider()
 
-        explicit_provider = (conf().get("embedding_provider") or "").strip().lower()
-
-        if not explicit_provider:
-            return self._init_embedding_provider_legacy(session_id=session_id)
-
-        return self._init_embedding_provider_explicit(
-            memory_config, explicit_provider, session_id=session_id,
-        )
-
-    def _init_embedding_provider_legacy(self, session_id: Optional[str] = None):
-        """Legacy auto-init path: OpenAI -> LinkAI. Preserved verbatim for compat."""
-        from agent.memory 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"[AgentInitializer] 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"[AgentInitializer] LinkAI embedding failed: {e}")
-
-        if embedding_provider is not None and embedding_model:
-            global _embedding_logged
-            if not _embedding_logged:
-                logger.info(
-                    f"[AgentInitializer] Embedding model in use: {embedding_model} "
-                    f"(dim={embedding_provider.dimensions})"
-                )
-                _embedding_logged = True
-
-        return embedding_provider
-
-    def _init_embedding_provider_explicit(
-        self,
-        memory_config,
-        provider_key: str,
-        session_id: Optional[str] = None,
-    ):
-        """Explicit-provider path: build the configured vendor.
-
-        If the index was built with a different dim, vector search will
-        silently return no results (cosine returns 0 for mismatched dims)
-        and keyword search takes over. Users switch vendors by running
-        /memory rebuild-index — see docs.
-        """
-        from agent.memory import create_embedding_provider
-        from agent.memory.embedding import EMBEDDING_VENDORS
-        from config import conf
-
-        meta = EMBEDDING_VENDORS.get(provider_key)
-        if meta is None:
-            logger.error(
-                f"[AgentInitializer] Unknown embedding_provider '{provider_key}'. "
-                f"Supported: {sorted(EMBEDDING_VENDORS.keys())}. "
-                f"Memory will run in keyword-only mode."
-            )
-            return None
-
-        api_key = self._resolve_embedding_api_key(provider_key)
-        api_base = self._resolve_embedding_api_base(provider_key, meta["default_base_url"])
-
-        if not api_key:
-            logger.error(
-                f"[AgentInitializer] 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() or 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=provider_key,
-                model=model,
-                api_key=api_key,
-                api_base=api_base,
-                dimensions=dim,
-            )
-        except Exception as e:
-            logger.error(
-                f"[AgentInitializer] Failed to init embedding provider "
-                f"'{provider_key}/{model}': {e}"
-            )
-            return None
-
-        global _embedding_logged
-        if not _embedding_logged:
-            logger.info(
-                f"[AgentInitializer] Embedding model in use: "
-                f"{provider_key}/{model} (dim={provider.dimensions})"
-            )
-            _embedding_logged = True
-        return provider
-
-    @staticmethod
-    def _resolve_embedding_api_key(provider_key: str) -> str:
-        """Pick the API key for an explicit embedding provider from config."""
-        from config import conf
-
-        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
-
-    @staticmethod
-    def _resolve_embedding_api_base(provider_key: str, default_base: str) -> str:
-        """Pick the API base for an explicit embedding provider from config."""
-        from config import conf
-
-        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 _sync_memory(self, memory_manager, session_id: Optional[str] = None):
         """Sync memory database"""
         try:
@@ -524,6 +350,14 @@ class AgentInitializer:
                         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
                 if tool_name == "env_config":
                     from agent.tools import EnvConfig
@@ -643,16 +477,25 @@ class AgentInitializer:
             except Exception:
                 timezone_name = "UTC"
             
-            # Chinese weekday mapping
-            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_zh = weekday_map.get(now.strftime("%A"), now.strftime("%A"))
-            
+            # Weekday: English name in en, Chinese mapping otherwise
+            weekday_en = now.strftime("%A")
+            try:
+                from common import i18n
+                is_en = i18n.get_language() == "en"
+            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
             }
         

bridge/bridge.py

@@ -63,6 +63,10 @@ class Bridge(object):
             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"):

channel/channel_factory.py

@@ -27,6 +27,9 @@ def create_channel(channel_type) -> Channel:
     elif channel_type == "wechatcom_app":
         from channel.wechatcom.wechatcomapp_channel import WechatComAppChannel
         ch = WechatComAppChannel()
+    elif channel_type == const.WECHAT_KF:
+        from channel.wechat_kf.wechat_kf_channel import WechatKfChannel
+        ch = WechatKfChannel()
     elif channel_type == const.FEISHU:
         from channel.feishu.feishu_channel import FeiShuChanel
         ch = FeiShuChanel()
@@ -39,6 +42,15 @@ def create_channel(channel_type) -> Channel:
     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/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:
@@ -265,7 +266,7 @@ 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
@@ -438,8 +439,21 @@ 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] = [
@@ -451,6 +465,29 @@ class ChatChannel(Channel):
             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:
@@ -482,7 +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:
@@ -492,7 +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/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

@@ -752,6 +752,9 @@ class FeiShuChanel(ChatChannel):
         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 ----------------------------------------------------
@@ -1076,18 +1079,42 @@ class FeiShuChanel(ChatChannel):
                     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", "")
-                if not final_response:
-                    return
-                final_text = str(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。

channel/slack/__init__.py

@@ -0,0 +1 @@
+

channel/slack/slack_channel.py

@@ -0,0 +1,506 @@
+"""
+Slack channel via Bolt for Python (Socket Mode).
+
+Features:
+- Direct message & channel chat (text / image / file)
+- Channel trigger: @mention or reply in a thread the bot is in (configurable)
+- /cancel fast-path matches Web channel behaviour
+- Socket Mode: no public IP / callback URL required, works behind NAT
+
+Implementation note:
+    slack_bolt's SocketModeHandler is blocking and runs its own background
+    threads. We start it in a dedicated thread so the rest of cow (sync) stays
+    untouched. Inbound events are dispatched onto cow's existing sync
+    ChatChannel.produce() pipeline; outbound send() calls the Slack Web API
+    client directly (it is sync-safe).
+"""
+
+import os
+import re
+import threading
+
+import requests
+
+from bridge.context import Context, ContextType
+from bridge.reply import Reply, ReplyType
+from channel.chat_channel import ChatChannel, check_prefix
+from channel.slack.slack_message import SlackMessage
+from common.expired_dict import ExpiredDict
+from common.log import logger
+from common.singleton import singleton
+from config import conf
+
+
+@singleton
+class SlackChannel(ChatChannel):
+    NOT_SUPPORT_REPLYTYPE = []
+
+    def __init__(self):
+        super().__init__()
+        self.bot_token = ""
+        self.app_token = ""
+        self.bot_user_id = ""  # used to strip @mention and ignore self messages
+        self._app = None
+        self._handler = None
+        self._client = None
+        self._loop_thread = None
+        # Idempotent dedup; Slack retries event delivery on slow ack
+        self._received_msgs = ExpiredDict(60 * 60 * 1)
+
+        # Disable group whitelist / prefix checks (we handle triggering ourselves
+        # in _should_reply_in_channel), aligned with telegram / feishu channels.
+        conf()["group_name_white_list"] = ["ALL_GROUP"]
+        conf()["single_chat_prefix"] = [""]
+
+    # ------------------------------------------------------------------
+    # Lifecycle
+    # ------------------------------------------------------------------
+
+    def startup(self):
+        self.bot_token = conf().get("slack_bot_token", "")
+        self.app_token = conf().get("slack_app_token", "")
+        if not self.bot_token or not self.app_token:
+            err = "[Slack] slack_bot_token and slack_app_token are both required"
+            logger.error(err)
+            self.report_startup_error(err)
+            return
+
+        # Guard against the common mistake of swapping the two tokens:
+        # bot token must start with xoxb-, app-level token with xapp-.
+        if not self.bot_token.startswith("xoxb-") or not self.app_token.startswith("xapp-"):
+            err = (
+                "[Slack] token type mismatch: slack_bot_token must start with 'xoxb-' "
+                "and slack_app_token must start with 'xapp-' (they look swapped)"
+            )
+            logger.error(err)
+            self.report_startup_error(err)
+            return
+
+        try:
+            from slack_bolt import App
+            from slack_bolt.adapter.socket_mode import SocketModeHandler
+        except ImportError:
+            err = (
+                "[Slack] slack_bolt is not installed. "
+                "Run: pip install slack_bolt"
+            )
+            logger.error(err)
+            self.report_startup_error(err)
+            return
+
+        try:
+            self._app = App(token=self.bot_token)
+            self._client = self._app.client
+
+            # Resolve our own bot user id (needed for @mention strip / self-ignore)
+            auth = self._client.auth_test()
+            self.bot_user_id = auth.get("user_id", "")
+            self.name = self.bot_user_id  # ChatChannel uses self.name to strip @-mention
+            logger.info(f"[Slack] Bot logged in as user_id={self.bot_user_id}, team={auth.get('team')}")
+        except Exception as e:
+            err = f"[Slack] auth_test failed: {e}"
+            logger.error(err)
+            self.report_startup_error(err)
+            return
+
+        self._register_handlers()
+
+        self._handler = SocketModeHandler(self._app, self.app_token)
+
+        def _run():
+            try:
+                logger.info("[Slack] Starting Socket Mode connection...")
+                self.report_startup_success()
+                logger.info("[Slack] ✅ Slack bot ready, listening for events")
+                self._handler.start()
+            except Exception as e:
+                logger.error(f"[Slack] socket mode crashed: {e}", exc_info=True)
+                self.report_startup_error(str(e))
+            finally:
+                logger.info("[Slack] socket mode exited")
+
+        self._loop_thread = threading.Thread(target=_run, daemon=True, name="slack-socket")
+        self._loop_thread.start()
+        # Block startup() until the handler thread exits, matching other channels'
+        # behaviour (startup is a blocking call).
+        self._loop_thread.join()
+
+    def _register_handlers(self):
+        app = self._app
+
+        # app_mention: bot is @-mentioned in a channel
+        @app.event("app_mention")
+        def _on_app_mention(event, ack):
+            ack()
+            self._handle_event(event, is_group=True)
+
+        # message: DMs and channel messages (including thread replies)
+        @app.event("message")
+        def _on_message(event, ack):
+            ack()
+            self._handle_message_event(event)
+
+    def stop(self):
+        logger.info("[Slack] stop() called")
+        try:
+            if self._handler is not None:
+                self._handler.close()
+        except Exception as e:
+            logger.warning(f"[Slack] handler close error: {e}")
+        if self._loop_thread and self._loop_thread.is_alive():
+            try:
+                self._loop_thread.join(timeout=10)
+            except Exception:
+                pass
+        logger.info("[Slack] stop() completed")
+
+    # ------------------------------------------------------------------
+    # Inbound: slack event -> ChatMessage -> ChatChannel.produce
+    # ------------------------------------------------------------------
+
+    def _handle_message_event(self, event: dict):
+        """Route a raw `message` event: skip bot/system noise, decide grouping."""
+        try:
+            logger.debug(
+                f"[Slack] message event: channel_type={event.get('channel_type')}, "
+                f"subtype={event.get('subtype')}, user={event.get('user')}, "
+                f"ts={event.get('ts')}, thread_ts={event.get('thread_ts')}"
+            )
+            # Ignore bot messages (including our own) and message edits/deletes
+            if event.get("bot_id") or event.get("subtype") in ("bot_message", "message_changed", "message_deleted"):
+                return
+            if event.get("user") == self.bot_user_id:
+                return
+
+            channel_type = event.get("channel_type", "")
+            # DM (im) is single chat; channel/group is group chat. app_mention
+            # already covers channel @-mentions, so for plain channel messages we
+            # only react when configured / thread-following.
+            is_group = channel_type in ("channel", "group", "mpim")
+            if is_group:
+                # app_mention handler covers explicit @bot; here we only handle
+                # follow-up replies in threads the bot participates in.
+                if not self._should_reply_in_channel(event):
+                    return
+            self._handle_event(event, is_group=is_group)
+        except Exception as e:
+            logger.error(f"[Slack] _handle_message_event error: {e}", exc_info=True)
+
+    def _handle_event(self, event: dict, is_group: bool):
+        """Parse event -> build SlackMessage -> produce()."""
+        try:
+            channel_id = event.get("channel", "")
+            ts = event.get("ts", "")
+            if not channel_id:
+                return
+
+            # Idempotent dedup
+            msg_uid = f"{channel_id}:{ts}"
+            if self._received_msgs.get(msg_uid):
+                return
+            self._received_msgs[msg_uid] = True
+
+            # Parse type + download media if needed.
+            ctype, content, caption = self._parse_event(event)
+            if ctype is None:
+                logger.debug(f"[Slack] unsupported message type, skip. event={event}")
+                return
+
+            # Strip <@bot_user_id> mention from channel text
+            if is_group and self.bot_user_id:
+                if ctype == ContextType.TEXT and content:
+                    content = self._strip_at_mention(content)
+                if caption:
+                    caption = self._strip_at_mention(caption)
+
+            slack_msg = SlackMessage(
+                event,
+                is_group=is_group,
+                bot_user_id=self.bot_user_id,
+                ctype=ctype,
+                content=content,
+            )
+            slack_msg.is_at = is_group  # if we reached here in a channel, bot is mentioned/threaded
+
+            from channel.file_cache import get_file_cache
+            file_cache = get_file_cache()
+            session_id = self._compute_session_id(event, 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}]"
+                slack_msg.ctype = ContextType.TEXT
+                slack_msg.content = merged_text
+                ctype = ContextType.TEXT
+                logger.info(f"[Slack] 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"[Slack] 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"[Slack] 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"):
+                    self._do_cancel(session_id, channel_id, event)
+                    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']}]")
+                    slack_msg.content = (slack_msg.content or "") + "\n" + "\n".join(refs)
+                    file_cache.clear(session_id)
+                    logger.info(f"[Slack] Attached {len(cached_files)} cached file(s) to query")
+
+            # Reply in the originating thread when present, else start one on this msg
+            thread_ts = event.get("thread_ts") or ts
+
+            context = self._compose_context(
+                slack_msg.ctype,
+                slack_msg.content,
+                isgroup=is_group,
+                msg=slack_msg,
+                # Replies go back into the thread, no manual @mention needed
+                no_need_at=True,
+            )
+            if context:
+                context["session_id"] = session_id
+                context["receiver"] = channel_id
+                context["slack_channel"] = channel_id
+                context["slack_thread_ts"] = thread_ts if is_group else None
+                self.produce(context)
+            logger.debug(f"[Slack] received: type={ctype}, content={str(slack_msg.content)[:80]}")
+        except Exception as e:
+            logger.error(f"[Slack] _handle_event error: {e}", exc_info=True)
+
+    def _do_cancel(self, session_id: str, channel_id: str, event: dict):
+        """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."
+            thread_ts = event.get("thread_ts") or event.get("ts")
+            self._client.chat_postMessage(channel=channel_id, text=text, thread_ts=thread_ts)
+            logger.info(f"[Slack] /cancel session={session_id}, cancelled={cancelled}")
+        except Exception as e:
+            logger.error(f"[Slack] /cancel error: {e}", exc_info=True)
+
+    def _parse_event(self, event: dict):
+        """Parse a slack event and return (ctype, content, caption).
+
+        - content is text for ContextType.TEXT, otherwise the local file path
+        - caption is the optional text accompanying a file; empty for plain text
+        """
+        text = (event.get("text") or "").strip()
+        files = event.get("files") or []
+
+        if files:
+            # Handle the first attachment; caption is the accompanying message text
+            f = files[0]
+            mimetype = (f.get("mimetype") or "").lower()
+            url = f.get("url_private_download") or f.get("url_private")
+            name = f.get("name") or f.get("id") or "file"
+            if not url:
+                return (None, None, "")
+            path = self._download_file(url, name)
+            if not path:
+                return (None, None, "")
+            if mimetype.startswith("image/"):
+                return (ContextType.IMAGE, path, text)
+            return (ContextType.FILE, path, text)
+
+        if text:
+            return (ContextType.TEXT, text, "")
+
+        return (None, None, "")
+
+    def _download_file(self, url: str, name: str):
+        """Download a Slack private file (requires bot token auth) to local tmp dir."""
+        try:
+            headers = {"Authorization": f"Bearer {self.bot_token}"}
+            resp = requests.get(url, headers=headers, timeout=60, stream=True)
+            resp.raise_for_status()
+            tmp_dir = SlackMessage.get_tmp_dir()
+            # Sanitize the name and keep it unique-ish via the url tail
+            safe_name = re.sub(r"[^\w.\-]", "_", name)
+            local_path = os.path.join(tmp_dir, safe_name)
+            with open(local_path, "wb") as fp:
+                for chunk in resp.iter_content(chunk_size=8192):
+                    if chunk:
+                        fp.write(chunk)
+            logger.debug(f"[Slack] downloaded {name} -> {local_path}")
+            return local_path
+        except Exception as e:
+            logger.error(f"[Slack] download_file failed ({name}): {e}")
+            return None
+
+    # ------------------------------------------------------------------
+    # Channel trigger logic
+    # ------------------------------------------------------------------
+
+    def _should_reply_in_channel(self, event: dict) -> bool:
+        """Decide whether to reply to a plain channel message (no @mention).
+
+        app_mention already handles explicit @bot, so here we only deal with
+        follow-up messages. `all` replies to every message; `mention_or_reply`
+        replies inside threads the bot already participates in.
+        """
+        mode = conf().get("slack_group_trigger", "mention_or_reply")
+        if mode == "all":
+            return True
+        if mode == "mention_only":
+            return False
+        # mention_or_reply: follow up only within an existing thread
+        return bool(event.get("thread_ts"))
+
+    def _strip_at_mention(self, content: str) -> str:
+        """Strip <@BOT_USER_ID> from channel text."""
+        if not content or not self.bot_user_id:
+            return content
+        pattern = re.compile(r"<@" + re.escape(self.bot_user_id) + r">", re.IGNORECASE)
+        return pattern.sub("", content).strip()
+
+    @staticmethod
+    def _compute_session_id(event: dict, is_group: bool) -> str:
+        channel_id = event.get("channel", "")
+        user_id = event.get("user", "")
+        if is_group:
+            if conf().get("group_shared_session", True):
+                return f"slack_channel_{channel_id}"
+            return f"slack_channel_{channel_id}_{user_id}"
+        return f"slack_user_{user_id}"
+
+    # ------------------------------------------------------------------
+    # Override _compose_context: skip the parent's group whitelist/at checks
+    # (already handled via _should_reply_in_channel). Same idea as telegram.
+    # ------------------------------------------------------------------
+
+    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 -> Slack Web API
+    # ------------------------------------------------------------------
+
+    def send(self, reply: Reply, context: Context):
+        """Called from cow's sync main thread; Slack Web client is sync-safe."""
+        if self._client is None:
+            logger.warning("[Slack] client not ready, drop reply")
+            return
+
+        channel_id = context.get("slack_channel")
+        thread_ts = context.get("slack_thread_ts")
+        if not channel_id:
+            logger.warning("[Slack] no slack_channel in context, drop reply")
+            return
+
+        try:
+            self._do_send(reply, channel_id, thread_ts)
+            logger.info(f"[Slack] sent reply (type={reply.type}, channel={channel_id})")
+        except Exception as e:
+            logger.error(f"[Slack] send failed: {e}", exc_info=True)
+
+    def _do_send(self, reply: Reply, channel_id: str, thread_ts):
+        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
+            # Slack caps a message around 40k chars; split conservatively
+            for chunk in _split_text(text, 3500):
+                self._client.chat_postMessage(channel=channel_id, text=chunk, thread_ts=thread_ts)
+
+        elif rtype == ReplyType.IMAGE:
+            # Already a local BytesIO; upload it directly
+            content.seek(0)
+            self._client.files_upload_v2(
+                channel=channel_id, file=content, filename="image.png", thread_ts=thread_ts,
+            )
+
+        elif rtype == ReplyType.IMAGE_URL:
+            url = str(content)
+            if url.startswith("file://"):
+                local = url[7:]
+                self._client.files_upload_v2(
+                    channel=channel_id, file=local, thread_ts=thread_ts,
+                )
+            else:
+                # Post the URL as text; Slack will unfurl it as an image preview
+                self._client.chat_postMessage(channel=channel_id, text=url, thread_ts=thread_ts)
+
+        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
+            self._client.files_upload_v2(
+                channel=channel_id, file=local, initial_comment=caption, thread_ts=thread_ts,
+            )
+
+        else:
+            # Fallback: send as plain text
+            self._client.chat_postMessage(channel=channel_id, text=str(content), thread_ts=thread_ts)
+
+
+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/slack/slack_message.py

@@ -0,0 +1,60 @@
+"""
+Slack message adapter.
+
+Convert a Slack event payload into cow's unified ChatMessage.
+File downloads are NOT performed here; the channel layer downloads files
+on demand because it needs the bot token for authenticated download URLs.
+"""
+import os
+
+from bridge.context import ContextType
+from channel.chat_message import ChatMessage
+from common.utils import expand_path
+from config import conf
+
+
+class SlackMessage(ChatMessage):
+    """Wrap a Slack event into the unified ChatMessage."""
+
+    def __init__(self, event: dict, is_group: bool = False, bot_user_id: str = "",
+                 ctype: ContextType = ContextType.TEXT, content: str = ""):
+        super().__init__(event)
+        # Basic fields
+        self.msg_id = event.get("client_msg_id") or event.get("ts") or ""
+        try:
+            self.create_time = int(float(event.get("ts", 0)))
+        except (TypeError, ValueError):
+            self.create_time = 0
+        self.ctype = ctype
+        self.content = content
+
+        # Sender / chat info
+        from_user_id = event.get("user", "unknown")
+        channel_id = event.get("channel", "")
+        self.from_user_id = from_user_id
+        self.from_user_nickname = from_user_id
+        self.to_user_id = bot_user_id or "slack_bot"
+        self.to_user_nickname = bot_user_id or "slack_bot"
+
+        self.is_group = is_group
+        if is_group:
+            # Channel chat: other_user_id = channel_id, actual_user_id = sender id
+            self.other_user_id = channel_id
+            self.other_user_nickname = channel_id
+            self.actual_user_id = from_user_id
+            self.actual_user_nickname = from_user_id
+        else:
+            # DM: use channel_id so replies go back to the same DM channel
+            self.other_user_id = channel_id or from_user_id
+            self.other_user_nickname = from_user_id
+
+        # 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/telegram/telegram_channel.py

@@ -0,0 +1,719 @@
+"""
+Telegram channel via Bot API (long polling mode).
+
+Features:
+- Single chat & group chat (text / photo / voice / video / document)
+- Group trigger: @mention or reply-to-bot (configurable)
+- /cancel fast-path matches Web channel behaviour
+- Auto-register bot commands menu on startup (mirrors Web slash menu)
+- Optional HTTP/SOCKS5 proxy support for restricted networks
+
+Implementation note:
+    python-telegram-bot is async-first. We run the bot inside a dedicated
+    thread with its own asyncio loop so the rest of cow (which is sync)
+    stays untouched. Inbound updates 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.telegram.telegram_message import TelegramMessage
+from common.expired_dict import ExpiredDict
+from common.log import logger
+from common.singleton import singleton
+from config import conf
+
+# Bot command menu, aligned with Web slash commands.
+# Top-level commands only; sub-commands are entered with a space (e.g. "/skill list").
+TELEGRAM_BOT_COMMANDS = [
+    ("help", "Show command help"),
+    ("status", "Show running status"),
+    ("context", "View/clear conversation context (sub: clear)"),
+    ("skill", "Manage skills (list/search/install/...)"),
+    ("memory", "Manage memory (sub: dream)"),
+    ("knowledge", "Manage knowledge base (list/on/off)"),
+    ("config", "Show current config"),
+    ("cancel", "Cancel running agent task"),
+    ("logs", "Show recent logs"),
+    ("version", "Show version"),
+]
+
+
+@singleton
+class TelegramChannel(ChatChannel):
+    NOT_SUPPORT_REPLYTYPE = []
+
+    def __init__(self):
+        super().__init__()
+        self.bot_token = ""
+        self.bot_username = ""  # used for @-mention matching
+        self._bot = None
+        self._application = None
+        self._loop = None
+        self._loop_thread = None
+        self._stop_event = threading.Event()
+        # Idempotent dedup; TG occasionally redelivers the same update on flaky networks
+        self._received_msgs = ExpiredDict(60 * 60 * 1)
+
+        # Disable group whitelist / prefix checks (we handle triggering ourselves
+        # in _should_reply_in_group), aligned with feishu / wecom_bot channels.
+        conf()["group_name_white_list"] = ["ALL_GROUP"]
+        conf()["single_chat_prefix"] = [""]
+
+    # ------------------------------------------------------------------
+    # Lifecycle
+    # ------------------------------------------------------------------
+
+    def startup(self):
+        self.bot_token = conf().get("telegram_token", "")
+        if not self.bot_token:
+            err = "[Telegram] telegram_token is required"
+            logger.error(err)
+            self.report_startup_error(err)
+            return
+
+        try:
+            from telegram.ext import (
+                Application,
+                MessageHandler,
+                CommandHandler,
+                filters,
+            )
+        except ImportError:
+            err = (
+                "[Telegram] python-telegram-bot is not installed. "
+                "Run: pip install python-telegram-bot"
+            )
+            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(Application, MessageHandler, CommandHandler, filters))
+            except Exception as e:
+                logger.error(f"[Telegram] event loop crashed: {e}", exc_info=True)
+                self.report_startup_error(str(e))
+            finally:
+                try:
+                    self._loop.close()
+                except Exception:
+                    pass
+                logger.info("[Telegram] event loop exited")
+
+        self._loop_thread = threading.Thread(target=_run_loop, daemon=True, name="telegram-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, Application, MessageHandler, CommandHandler, filters):
+        """Build Application, register handlers, and run polling."""
+        builder = Application.builder().token(self.bot_token)
+
+        # Proxy: prefer telegram_proxy config, fall back to HTTPS_PROXY env var
+        proxy_url = conf().get("telegram_proxy", "") or os.environ.get("HTTPS_PROXY", "")
+        if proxy_url:
+            try:
+                builder = builder.proxy(proxy_url).get_updates_proxy(proxy_url)
+                logger.info(f"[Telegram] using proxy: {proxy_url}")
+            except Exception as e:
+                logger.warning(f"[Telegram] proxy config failed, fallback to direct: {e}")
+
+        # Media uploads (photo/voice/video/document) over a proxy can be slow,
+        # bump read/write/connect/pool timeouts.
+        builder = (
+            builder
+            .read_timeout(60)
+            .write_timeout(120)
+            .connect_timeout(30)
+            .pool_timeout(30)
+        )
+
+        application = builder.build()
+        self._application = application
+        self._bot = application.bot
+
+        # Fetch our own username (needed for @-mention matching in groups)
+        try:
+            me = await self._bot.get_me()
+            self.bot_username = me.username or ""
+            self.name = self.bot_username  # ChatChannel uses self.name to strip @-mention
+            logger.info(f"[Telegram] Bot logged in as @{self.bot_username} (id={me.id})")
+        except Exception as e:
+            err = f"[Telegram] get_me failed: {e}"
+            logger.error(err)
+            self.report_startup_error(err)
+            return
+
+        # Register the command menu (failure is non-fatal)
+        if conf().get("telegram_register_commands", True):
+            try:
+                from telegram import BotCommand
+                cmds = [BotCommand(name, desc) for name, desc in TELEGRAM_BOT_COMMANDS]
+                await self._bot.set_my_commands(cmds)
+                logger.info(f"[Telegram] Registered {len(cmds)} bot commands")
+            except Exception as e:
+                logger.warning(f"[Telegram] set_my_commands failed: {e}")
+
+        # Handlers:
+        # 1) /cancel uses the fast-path
+        application.add_handler(CommandHandler("cancel", self._on_cancel))
+        # 2) Normal messages (text + media)
+        application.add_handler(MessageHandler(filters.ALL & ~filters.COMMAND, self._on_message))
+        # 3) Other slash commands are forwarded as plain text for the agent to handle
+        application.add_handler(MessageHandler(filters.COMMAND, self._on_command_passthrough))
+
+        # Start polling. drop_pending_updates avoids replaying backlog after restart.
+        # Transient "Server disconnected" / RemoteProtocolError during get_updates
+        # are common over proxies/flaky networks; PTB's network loop auto-retries,
+        # so we only need to keep the noise down (see _quiet_polling_network_errors).
+        self._quiet_polling_network_errors()
+        logger.info("[Telegram] Starting long polling...")
+        await application.initialize()
+        await application.start()
+        await application.updater.start_polling(
+            drop_pending_updates=True,
+            # Long-poll hold time on the server side; smaller value = reconnect more
+            # often but each hung connection fails faster.
+            timeout=30,
+            # Retry forever on transient get_updates network errors instead of giving up.
+            bootstrap_retries=-1,
+        )
+        self.report_startup_success()
+        logger.info("[Telegram] ✅ Telegram bot ready, polling for updates")
+
+        # Block until stop()
+        try:
+            while not self._stop_event.is_set():
+                await asyncio.sleep(0.5)
+        finally:
+            try:
+                await application.updater.stop()
+                await application.stop()
+                await application.shutdown()
+            except Exception as e:
+                logger.warning(f"[Telegram] shutdown error: {e}")
+
+    @staticmethod
+    def _quiet_polling_network_errors():
+        """Downgrade PTB's noisy 'Exception happened while polling for updates' logs.
+
+        These transient get_updates errors (RemoteProtocolError / NetworkError /
+        TimedOut, typically over a proxy) are auto-retried by PTB's network loop,
+        so logging the full traceback at ERROR is just noise. We attach a filter
+        that drops these specific records while leaving real errors untouched.
+        """
+        import logging
+
+        class _PollingNoiseFilter(logging.Filter):
+            _NEEDLES = (
+                "Exception happened while polling for updates",
+                "Server disconnected without sending a response",
+            )
+
+            def filter(self, record: logging.LogRecord) -> bool:
+                try:
+                    msg = record.getMessage()
+                except Exception:
+                    return True
+                if any(n in msg for n in self._NEEDLES):
+                    # Keep a single-line breadcrumb at DEBUG, drop the traceback.
+                    logger.debug(f"[Telegram] transient polling network error (auto-retrying): {msg.splitlines()[0]}")
+                    return False
+                return True
+
+        noise_filter = _PollingNoiseFilter()
+        for name in ("telegram.ext.Updater", "telegram.ext._updater", "telegram.ext"):
+            logging.getLogger(name).addFilter(noise_filter)
+
+    def stop(self):
+        logger.info("[Telegram] 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("[Telegram] stop() completed")
+
+    # ------------------------------------------------------------------
+    # Inbound: telegram update -> ChatMessage -> ChatChannel.produce
+    # ------------------------------------------------------------------
+
+    async def _on_cancel(self, update, _context):
+        """Fast-path: /cancel calls cancel_session directly without going through agent."""
+        try:
+            from agent.protocol import get_cancel_registry
+            session_id = self._compute_session_id(update)
+            cancelled = get_cancel_registry().cancel_session(session_id)
+            text = "Current task cancelled." if cancelled else "No running task to cancel."
+            await update.effective_message.reply_text(text)
+            logger.info(f"[Telegram] /cancel session={session_id}, cancelled={cancelled}")
+        except Exception as e:
+            logger.error(f"[Telegram] /cancel error: {e}", exc_info=True)
+            try:
+                await update.effective_message.reply_text(f"⚠️ /cancel failed: {e}")
+            except Exception:
+                pass
+
+    async def _on_command_passthrough(self, update, _context):
+        """All non-/cancel commands fall through to plain message handling."""
+        await self._on_message(update, _context)
+
+    async def _on_message(self, update, _context):
+        """Telegram update entry: parse message -> build ChatMessage -> produce()."""
+        try:
+            message = update.effective_message
+            chat = update.effective_chat
+            if not message or not chat:
+                return
+
+            # Idempotent dedup
+            msg_uid = f"{chat.id}:{message.message_id}"
+            if self._received_msgs.get(msg_uid):
+                return
+            self._received_msgs[msg_uid] = True
+
+            is_group = chat.type in ("group", "supergroup")
+
+            # Debug log: helpful when group messages are silently dropped
+            if is_group:
+                logger.debug(
+                    f"[Telegram] group update received: chat_id={chat.id}, "
+                    f"text={(message.text or message.caption or '')[:40]!r}, "
+                    f"reply_to_bot={bool(message.reply_to_message and message.reply_to_message.from_user and message.reply_to_message.from_user.username == self.bot_username)}"
+                )
+
+            # Group trigger gate (silently drop if not triggered)
+            if is_group and not self._should_reply_in_group(update):
+                logger.debug(f"[Telegram] group message not triggered (need @{self.bot_username} or reply), skip")
+                return
+
+            # Parse message type + download media if needed.
+            # Media messages with caption return both the local path and the caption text.
+            ctype, content, caption = await self._parse_message(message)
+            if ctype is None:
+                logger.debug(f"[Telegram] unsupported message type, skip. msg={message}")
+                return
+
+            # Strip @bot mention for group text/caption
+            if is_group and self.bot_username:
+                if ctype == ContextType.TEXT and content:
+                    content = self._strip_at_mention(content)
+                if caption:
+                    caption = self._strip_at_mention(caption)
+
+            tg_msg = TelegramMessage(
+                update,
+                is_group=is_group,
+                bot_username=self.bot_username,
+                ctype=ctype,
+                content=content,
+            )
+            tg_msg.is_at = is_group  # If we got here in a group, the bot is mentioned/replied
+
+            # File cache: standalone media goes into cache, the next text query attaches them
+            from channel.file_cache import get_file_cache
+            file_cache = get_file_cache()
+            session_id = self._compute_session_id(update)
+
+            # 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}]"
+                tg_msg.ctype = ContextType.TEXT
+                tg_msg.content = merged_text
+                ctype = ContextType.TEXT
+                logger.info(f"[Telegram] 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"[Telegram] 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"[Telegram] File cached for session {session_id}: {content}")
+                return
+
+            if ctype == ContextType.TEXT:
+                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']}]")
+                    tg_msg.content = (tg_msg.content or "") + "\n" + "\n".join(refs)
+                    file_cache.clear(session_id)
+                    logger.info(f"[Telegram] Attached {len(cached_files)} cached file(s) to query")
+
+            # Dispatch to cow main pipeline (reuses ChatChannel._compose_context routing)
+            context = self._compose_context(
+                tg_msg.ctype,
+                tg_msg.content,
+                isgroup=is_group,
+                msg=tg_msg,
+            )
+            if context:
+                context["session_id"] = session_id
+                context["receiver"] = str(chat.id)
+                context["telegram_chat_id"] = chat.id
+                context["telegram_reply_to_msg_id"] = message.message_id if is_group else None
+                self.produce(context)
+            logger.debug(f"[Telegram] received: type={ctype}, content={str(tg_msg.content)[:80]}")
+
+        except Exception as e:
+            logger.error(f"[Telegram] _on_message error: {e}", exc_info=True)
+
+    async def _parse_message(self, message):
+        """Parse a telegram message and return (ctype, content, caption).
+
+        - content is text for ContextType.TEXT, otherwise the local file path
+        - caption is the optional text accompanying a media message; empty for plain text
+        """
+        caption = (message.caption or "").strip()
+
+        if message.photo:
+            largest = message.photo[-1]
+            path = await self._download_file(largest.file_id, suffix=".jpg")
+            return (ContextType.IMAGE, path, caption) if path else (None, None, "")
+
+        if message.voice or message.audio:
+            audio_obj = message.voice or message.audio
+            suffix = ".ogg" if message.voice else (
+                "." + (audio_obj.mime_type.split("/")[-1] if getattr(audio_obj, "mime_type", "") else "mp3")
+            )
+            path = await self._download_file(audio_obj.file_id, suffix=suffix)
+            return (ContextType.VOICE, path, caption) if path else (None, None, "")
+
+        if message.video or message.video_note:
+            video_obj = message.video or message.video_note
+            path = await self._download_file(video_obj.file_id, suffix=".mp4")
+            return (ContextType.FILE, path, caption) if path else (None, None, "")
+
+        if message.document:
+            doc = message.document
+            ext = ""
+            if doc.file_name and "." in doc.file_name:
+                ext = "." + doc.file_name.rsplit(".", 1)[-1]
+            path = await self._download_file(doc.file_id, suffix=ext, original_name=doc.file_name)
+            if not path:
+                return (None, None, "")
+            # Image-typed documents (user picked "send as file") are treated as images
+            mime = (doc.mime_type or "").lower()
+            if mime.startswith("image/"):
+                return (ContextType.IMAGE, path, caption)
+            return (ContextType.FILE, path, caption)
+
+        if message.text:
+            return (ContextType.TEXT, message.text.strip(), "")
+
+        return (None, None, "")
+
+    async def _download_file(self, file_id: str, suffix: str = "", original_name: str = ""):
+        """Download via bot.get_file into the local tmp dir; return path or None on failure."""
+        try:
+            f = await self._bot.get_file(file_id)
+            tmp_dir = TelegramMessage.get_tmp_dir()
+            base = original_name or f"{file_id}{suffix or ''}"
+            # Prefix with file_id to avoid name collisions / weird chars
+            safe_name = f"{file_id}_{base}" if original_name else base
+            local_path = os.path.join(tmp_dir, safe_name)
+            await f.download_to_drive(custom_path=local_path)
+            logger.debug(f"[Telegram] downloaded file_id={file_id} -> {local_path}")
+            return local_path
+        except Exception as e:
+            logger.error(f"[Telegram] download_file failed (file_id={file_id}): {e}")
+            return None
+
+    # ------------------------------------------------------------------
+    # Group trigger logic
+    # ------------------------------------------------------------------
+
+    def _should_reply_in_group(self, update) -> bool:
+        """Decide whether to reply to a group message based on configuration."""
+        mode = conf().get("telegram_group_trigger", "mention_or_reply")
+        if mode == "all":
+            return True
+
+        message = update.effective_message
+        if not message:
+            return False
+
+        # 1) Mentioned
+        if self.bot_username and self._is_mentioned(message, self.bot_username):
+            return True
+
+        # 2) Reply to a bot message
+        if mode == "mention_or_reply":
+            reply = message.reply_to_message
+            if reply and reply.from_user and reply.from_user.username == self.bot_username:
+                return True
+
+        return False
+
+    @staticmethod
+    def _is_mentioned(message, bot_username: str) -> bool:
+        """Check whether entities/caption_entities contain a @mention of the bot."""
+        bot_at = "@" + bot_username.lower()
+        text = (message.text or message.caption or "").lower()
+        if bot_at in text:
+            return True
+        # Also check entities strictly to support text_mention (no-username @)
+        for ent in (message.entities or []) + (message.caption_entities or []):
+            if ent.type == "mention":
+                src = message.text or message.caption or ""
+                if src[ent.offset: ent.offset + ent.length].lower() == bot_at:
+                    return True
+        return False
+
+    def _strip_at_mention(self, content: str) -> str:
+        """Strip @bot_username from group text (case-insensitive)."""
+        if not content or not self.bot_username:
+            return content
+        pattern = re.compile(r"@" + re.escape(self.bot_username), re.IGNORECASE)
+        return pattern.sub("", content).strip()
+
+    @staticmethod
+    def _compute_session_id(update) -> str:
+        chat = update.effective_chat
+        user = update.effective_user
+        is_group = chat.type in ("group", "supergroup")
+        if is_group:
+            if conf().get("group_shared_session", True):
+                return f"tg_group_{chat.id}"
+            return f"tg_group_{chat.id}_{user.id}"
+        return f"tg_user_{user.id}"
+
+    # ------------------------------------------------------------------
+    # Override _compose_context: skip the parent's group whitelist/at checks
+    # (already handled in _on_message via _should_reply_in_group). Same idea
+    # as the feishu channel.
+    # ------------------------------------------------------------------
+
+    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 -> Telegram API
+    # ------------------------------------------------------------------
+
+    def send(self, reply: Reply, context: Context):
+        """Called from cow's sync main thread; we marshal the coroutine onto the loop thread."""
+        if self._loop is None or self._bot is None:
+            logger.warning("[Telegram] bot not ready, drop reply")
+            return
+
+        chat_id = context.get("telegram_chat_id")
+        reply_to = context.get("telegram_reply_to_msg_id")
+        if chat_id is None:
+            logger.warning("[Telegram] no telegram_chat_id in context, drop reply")
+            return
+
+        coro = self._async_send(reply, chat_id, reply_to)
+        try:
+            future = asyncio.run_coroutine_threadsafe(coro, self._loop)
+            # Media uploads through a proxy can be slow; let PTB's own timeouts win
+            future.result(timeout=180)
+        except Exception as e:
+            logger.error(f"[Telegram] send failed: {e}")
+
+    # Number of retries for transient network errors (proxy hiccups etc.)
+    _SEND_RETRIES = 2
+    _SEND_RETRY_BACKOFF = 2.0  # seconds
+
+    async def _send_with_retry(self, send_fn, *, label: str):
+        """Run a single Telegram API call with retries for transient network errors."""
+        from telegram.error import NetworkError, TimedOut
+        last_err = None
+        for attempt in range(self._SEND_RETRIES + 1):
+            try:
+                return await send_fn()
+            except (NetworkError, TimedOut) as e:
+                last_err = e
+                if attempt >= self._SEND_RETRIES:
+                    break
+                wait = self._SEND_RETRY_BACKOFF * (attempt + 1)
+                logger.warning(
+                    f"[Telegram] {label} transient error (attempt {attempt + 1}/"
+                    f"{self._SEND_RETRIES + 1}): {e}; retry in {wait}s"
+                )
+                await asyncio.sleep(wait)
+        raise last_err
+
+    async def _async_send(self, reply: Reply, chat_id, reply_to_msg_id):
+        try:
+            rtype = reply.type
+            content = reply.content
+
+            if rtype == ReplyType.TEXT or rtype == ReplyType.INFO or rtype == ReplyType.ERROR:
+                # Telegram caps a single text message at 4096 chars; auto-split
+                text = str(content) if content is not None else ""
+                if not text:
+                    return
+                for chunk in _split_text(text, 4000):
+                    await self._send_with_retry(
+                        lambda c=chunk: self._bot.send_message(
+                            chat_id=chat_id,
+                            text=c,
+                            reply_to_message_id=reply_to_msg_id,
+                            # Avoid failing the whole send if reply_to was deleted
+                            allow_sending_without_reply=True,
+                        ),
+                        label="send_message",
+                    )
+
+            elif rtype == ReplyType.IMAGE:
+                # Already a local BytesIO; send it directly
+                content.seek(0)
+                await self._send_with_retry(
+                    lambda: self._bot.send_photo(
+                        chat_id=chat_id,
+                        photo=content,
+                        reply_to_message_id=reply_to_msg_id,
+                        allow_sending_without_reply=True,
+                    ),
+                    label="send_photo",
+                )
+
+            elif rtype == ReplyType.IMAGE_URL:
+                url = str(content)
+                if url.startswith("file://"):
+                    local = url[7:]
+                    # Open inside the lambda so each retry gets a fresh stream
+                    async def _send_local_photo():
+                        with open(local, "rb") as f:
+                            return await self._bot.send_photo(
+                                chat_id=chat_id, photo=f,
+                                reply_to_message_id=reply_to_msg_id,
+                                allow_sending_without_reply=True,
+                            )
+                    await self._send_with_retry(_send_local_photo, label="send_photo(file)")
+                else:
+                    await self._send_with_retry(
+                        lambda: self._bot.send_photo(
+                            chat_id=chat_id, photo=url,
+                            reply_to_message_id=reply_to_msg_id,
+                            allow_sending_without_reply=True,
+                        ),
+                        label="send_photo(url)",
+                    )
+
+            elif rtype == ReplyType.VOICE:
+                local = content[7:] if isinstance(content, str) and content.startswith("file://") else content
+                async def _send_voice():
+                    with open(local, "rb") as f:
+                        return await self._bot.send_voice(
+                            chat_id=chat_id, voice=f,
+                            reply_to_message_id=reply_to_msg_id,
+                            allow_sending_without_reply=True,
+                        )
+                await self._send_with_retry(_send_voice, label="send_voice")
+
+            elif rtype == ReplyType.FILE:
+                # Videos go through send_video, everything else through send_document
+                local = content[7:] if isinstance(content, str) and content.startswith("file://") else content
+                # File replies may carry an accompanying text caption
+                caption = getattr(reply, "text_content", None) or None
+                is_video = isinstance(local, str) and local.lower().endswith(
+                    (".mp4", ".mov", ".avi", ".mkv", ".webm")
+                )
+
+                async def _send_file():
+                    with open(local, "rb") as f:
+                        if is_video:
+                            return await self._bot.send_video(
+                                chat_id=chat_id, video=f, caption=caption,
+                                reply_to_message_id=reply_to_msg_id,
+                                allow_sending_without_reply=True,
+                            )
+                        return await self._bot.send_document(
+                            chat_id=chat_id, document=f, caption=caption,
+                            reply_to_message_id=reply_to_msg_id,
+                            allow_sending_without_reply=True,
+                        )
+                await self._send_with_retry(_send_file, label="send_video" if is_video else "send_document")
+
+            else:
+                # Fallback: send as plain text
+                await self._send_with_retry(
+                    lambda: self._bot.send_message(
+                        chat_id=chat_id, text=str(content),
+                        reply_to_message_id=reply_to_msg_id,
+                        allow_sending_without_reply=True,
+                    ),
+                    label="send_message(fallback)",
+                )
+
+            logger.info(f"[Telegram] sent reply (type={rtype}, chat_id={chat_id})")
+
+        except Exception as e:
+            logger.error(f"[Telegram] _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/telegram/telegram_message.py

@@ -0,0 +1,62 @@
+"""
+Telegram message adapter.
+
+Convert a python-telegram-bot Update into cow's unified ChatMessage.
+File downloads are NOT performed here; the channel layer triggers
+bot.get_file() on demand because it requires 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 TelegramMessage(ChatMessage):
+    """Wrap a Telegram Update into the unified ChatMessage."""
+
+    def __init__(self, update, is_group: bool = False, bot_username: str = "",
+                 ctype: ContextType = ContextType.TEXT, content: str = ""):
+        super().__init__(update)
+        message = update.effective_message
+        chat = update.effective_chat
+        user = update.effective_user
+
+        # Basic fields
+        self.msg_id = str(message.message_id) if message else ""
+        self.create_time = int(message.date.timestamp()) if message and message.date else 0
+        self.ctype = ctype
+        self.content = content
+
+        # Sender / chat info
+        from_user_id = str(user.id) if user else "unknown"
+        from_user_nick = (
+            user.full_name if user and user.full_name else (user.username if user else "unknown")
+        )
+        self.from_user_id = from_user_id
+        self.from_user_nickname = from_user_nick or from_user_id
+        self.to_user_id = bot_username or "telegram_bot"
+        self.to_user_nickname = bot_username or "telegram_bot"
+
+        self.is_group = is_group
+        if is_group:
+            # Group: other_user_id = group_id, actual_user_id = sender id
+            self.other_user_id = str(chat.id)
+            self.other_user_nickname = chat.title or str(chat.id)
+            self.actual_user_id = from_user_id
+            self.actual_user_nickname = self.from_user_nickname
+        else:
+            self.other_user_id = from_user_id
+            self.other_user_nickname = self.from_user_nickname
+
+        # Whether the bot was triggered by @-mention or reply (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/terminal/terminal_channel.py

@@ -1,4 +1,7 @@
+import json
+import os
 import sys
+import time
 
 from bridge.context import *
 from bridge.reply import Reply, ReplyType
@@ -8,6 +11,164 @@ from common.log import logger
 from config import conf
 
 
+class _Style:
+    """ANSI escape codes for terminal styling. Disabled when not a tty."""
+
+    enabled = sys.stdout.isatty()
+
+    RESET = "\033[0m"
+    BOLD = "\033[1m"
+    DIM = "\033[2m"
+    ITALIC = "\033[3m"
+
+    GRAY = "\033[90m"
+    RED = "\033[31m"
+    GREEN = "\033[32m"
+    YELLOW = "\033[33m"
+    BLUE = "\033[34m"
+    MAGENTA = "\033[35m"
+    CYAN = "\033[36m"
+
+    @classmethod
+    def wrap(cls, text, *codes):
+        if not cls.enabled or not codes:
+            return text
+        return "".join(codes) + text + cls.RESET
+
+
+class TerminalAgentRenderer:
+    """Render agent stream events to the terminal in real time.
+
+    Reuses the same `on_event` mechanism as the web channel so the terminal
+    can show reasoning, tool calls and streaming answer text just like the web UI.
+    """
+
+    def __init__(self):
+        self._reasoning_active = False
+        self._answer_active = False
+        self._has_output = False
+        # Track tool execution start time as a fallback when the event omits it
+        self._tool_started_at = {}
+
+    def _print(self, text, end="", flush=True):
+        sys.stdout.write(text)
+        if end:
+            sys.stdout.write(end)
+        if flush:
+            sys.stdout.flush()
+        self._has_output = True
+
+    def _close_section(self):
+        """Finish the currently open streaming section (reasoning or answer)."""
+        if self._reasoning_active:
+            self._print("", end="\n")
+            self._reasoning_active = False
+        if self._answer_active:
+            self._print("", end="\n")
+            self._answer_active = False
+
+    def _format_arguments(self, arguments):
+        try:
+            if isinstance(arguments, (dict, list)):
+                text = json.dumps(arguments, ensure_ascii=False)
+            else:
+                text = str(arguments)
+        except Exception:
+            text = str(arguments)
+        # Keep tool input compact in the terminal
+        if len(text) > 300:
+            text = text[:300] + "…"
+        return text
+
+    def handle_event(self, event: dict):
+        try:
+            self._handle_event(event)
+        except Exception as e:
+            logger.debug(f"[Terminal] render event error: {e}")
+
+    def _handle_event(self, event: dict):
+        event_type = event.get("type")
+        data = event.get("data", {}) or {}
+
+        if event_type == "agent_start":
+            self._print("\n" + _Style.wrap("Agent: ", _Style.BOLD, _Style.GREEN), end="\n")
+
+        elif event_type == "reasoning_update":
+            delta = data.get("delta", "")
+            if not delta:
+                return
+            if self._answer_active:
+                self._close_section()
+            if not self._reasoning_active:
+                self._print(_Style.wrap("💭 思考  ", _Style.DIM, _Style.MAGENTA), end="\n")
+                self._reasoning_active = True
+            self._print(_Style.wrap(delta, _Style.DIM, _Style.ITALIC))
+
+        elif event_type == "message_update":
+            delta = data.get("delta", "")
+            if not delta:
+                return
+            if self._reasoning_active:
+                self._close_section()
+            self._answer_active = True
+            self._print(delta)
+
+        elif event_type == "tool_execution_start":
+            self._close_section()
+            tool_name = data.get("tool_name", "tool")
+            tool_id = data.get("tool_call_id")
+            arguments = data.get("arguments", {})
+            self._tool_started_at[tool_id] = time.time()
+            header = _Style.wrap(f"🔧 {tool_name}", _Style.BOLD, _Style.CYAN)
+            args_str = self._format_arguments(arguments)
+            self._print(f"{header} {_Style.wrap(args_str, _Style.GRAY)}", end="\n")
+
+        elif event_type == "tool_execution_end":
+            tool_name = data.get("tool_name", "tool")
+            tool_id = data.get("tool_call_id")
+            status = data.get("status", "success")
+            result = data.get("result", "")
+            exec_time = data.get("execution_time")
+            if exec_time is None and tool_id in self._tool_started_at:
+                exec_time = time.time() - self._tool_started_at.pop(tool_id, time.time())
+            success = status == "success"
+            icon = "✓" if success else "✗"
+            color = _Style.GREEN if success else _Style.RED
+            result_str = str(result)
+            if len(result_str) > 500:
+                result_str = result_str[:500] + "…"
+            # Indent multi-line tool output for readability
+            result_str = result_str.replace("\n", "\n   ")
+            cost = f" ({exec_time:.2f}s)" if isinstance(exec_time, (int, float)) else ""
+            self._print(
+                _Style.wrap(f"   {icon} {tool_name}{cost}", color) + "  " + _Style.wrap(result_str, _Style.GRAY),
+                end="\n",
+            )
+
+        elif event_type == "file_to_send":
+            self._close_section()
+            file_path = data.get("path", "")
+            file_name = data.get("file_name", "")
+            label = file_name or file_path
+            self._print(_Style.wrap(f"📎 文件: {label}", _Style.BLUE), end="\n")
+
+        elif event_type == "error":
+            self._close_section()
+            err_msg = data.get("error") or "unknown error"
+            self._print(_Style.wrap(f"❌ {err_msg}", _Style.BOLD, _Style.RED), end="\n")
+
+        elif event_type == "agent_cancelled":
+            self._close_section()
+            self._print(_Style.wrap("⏹ 已中止", _Style.YELLOW), end="\n")
+
+        elif event_type == "agent_end":
+            self._close_section()
+
+    def finish(self):
+        """Ensure any open section is closed at the end of a turn."""
+        self._close_section()
+
+
 class TerminalMessage(ChatMessage):
     def __init__(
         self,
@@ -29,17 +190,33 @@ class TerminalMessage(ChatMessage):
 class TerminalChannel(ChatChannel):
     NOT_SUPPORT_REPLYTYPE = [ReplyType.VOICE]
 
+    def __init__(self):
+        super().__init__()
+        # Per-request renderers keyed by request_id; used to detect whether
+        # agent text was already streamed so send() can avoid duplicate output.
+        self._renderers = {}
+        # Callback that restores TTY attributes on exit (set in startup).
+        self._restore_terminal = None
+
     def send(self, reply: Reply, context: Context):
-        print("\nBot:")
+        request_id = context.get("request_id") if context else None
+        renderer = self._renderers.pop(request_id, None) if request_id else None
+        streamed = renderer is not None and renderer._has_output
+
+        if renderer is not None:
+            renderer.finish()
+
         if reply.type == ReplyType.IMAGE:
             from PIL import Image
 
             image_storage = reply.content
             image_storage.seek(0)
             img = Image.open(image_storage)
+            if not streamed:
+                print("\nAgent: ")
             print("<IMAGE>")
             img.show()
-        elif reply.type == ReplyType.IMAGE_URL:  # 从网络下载图片
+        elif reply.type == ReplyType.IMAGE_URL:  # download image from url
             import io
 
             import requests
@@ -52,38 +229,122 @@ class TerminalChannel(ChatChannel):
                 image_storage.write(block)
             image_storage.seek(0)
             img = Image.open(image_storage)
+            if not streamed:
+                print("\nAgent: ")
             print(img_url)
             img.show()
         else:
-            print(reply.content)
-        print("\nUser:", end="")
+            # When agent already streamed the answer, skip re-printing the
+            # final text to avoid duplication; just emit a trailing newline.
+            if streamed:
+                print()
+            else:
+                print("\nAgent: ")
+                print(reply.content)
+        print("\nUser: ", end="")
         sys.stdout.flush()
         return
 
+    def _silence_console_logging(self):
+        """Mute console log output so background-thread logs (web/MCP/scheduler)
+        don't flood the interactive terminal. Logs still go to run.log in full.
+
+        Configurable via `terminal_log_level` (default ERROR). The file handler
+        is untouched, so run.log keeps the complete log.
+        """
+        import logging
+
+        level_name = str(conf().get("terminal_log_level", "ERROR")).upper()
+        level = getattr(logging, level_name, logging.ERROR)
+        root_logger = logging.getLogger("log")
+        for handler in root_logger.handlers:
+            # Only raise the level of the stdout/stderr stream handler;
+            # keep FileHandler at the logger's level so run.log stays complete.
+            if isinstance(handler, logging.StreamHandler) and not isinstance(handler, logging.FileHandler):
+                handler.setLevel(level)
+
+    def _install_terminal_guard(self):
+        """Save TTY attributes and register restore hooks so the terminal is
+        never left in a broken state (no echo / raw mode / leftover ANSI) after
+        the process exits, especially when Ctrl+C interrupts a blocking input().
+        """
+        if not sys.stdin.isatty():
+            return
+        try:
+            import atexit
+            import termios
+
+            saved_attrs = termios.tcgetattr(sys.stdin.fileno())
+
+            def _restore():
+                try:
+                    termios.tcsetattr(sys.stdin.fileno(), termios.TCSADRAIN, saved_attrs)
+                except Exception:
+                    pass
+                try:
+                    if _Style.enabled:
+                        sys.stdout.write(_Style.RESET)
+                        sys.stdout.flush()
+                except Exception:
+                    pass
+
+            self._restore_terminal = _restore
+            atexit.register(_restore)
+        except Exception as e:
+            # termios is unavailable on Windows; skip the guard there.
+            logger.debug(f"[Terminal] terminal guard not installed: {e}")
+            self._restore_terminal = None
+
     def startup(self):
         context = Context()
-        logger.setLevel("WARN")
-        print("\nPlease input your question:\nUser:", end="")
+        self._silence_console_logging()
+        self._install_terminal_guard()
+        print("\nPlease input your question:\nUser: ", end="")
         sys.stdout.flush()
         msg_id = 0
         while True:
             try:
                 prompt = self.get_input()
-            except KeyboardInterrupt:
-                print("\nExiting...")
-                sys.exit()
+            except (KeyboardInterrupt, EOFError):
+                self._shutdown()
             msg_id += 1
             trigger_prefixs = conf().get("single_chat_prefix", [""])
             if check_prefix(prompt, trigger_prefixs) is None:
-                prompt = trigger_prefixs[0] + prompt  # 给没触发的消息加上触发前缀
+                prompt = trigger_prefixs[0] + prompt  # add trigger prefix to untriggered messages
 
             context = self._compose_context(ContextType.TEXT, prompt, msg=TerminalMessage(msg_id, prompt))
             context["isgroup"] = False
             if context:
+                # Attach an agent event renderer so reasoning / tool calls /
+                # streaming answer show up live in the terminal (web-like UX).
+                request_id = str(msg_id)
+                context["request_id"] = request_id
+                renderer = TerminalAgentRenderer()
+                self._renderers[request_id] = renderer
+                context["on_event"] = renderer.handle_event
                 self.produce(context)
             else:
                 raise Exception("context is None")
 
+    def _shutdown(self):
+        """Restore terminal state and terminate the whole process.
+
+        startup() runs in a daemon sub-thread, so sys.exit() would only kill
+        this thread and leave the main process (and web/MCP/scheduler threads)
+        alive, holding the terminal in a half-occupied state -> laggy input.
+        We reset any leftover ANSI styling and hard-exit the process instead.
+        """
+        # Restore TTY attributes and reset any leftover ANSI styling
+        # (e.g. interrupted mid-stream output) before terminating.
+        if self._restore_terminal:
+            self._restore_terminal()
+        elif _Style.enabled:
+            sys.stdout.write(_Style.RESET)
+        sys.stdout.write("\nExiting...\n")
+        sys.stdout.flush()
+        # Hard-exit the entire process from a daemon thread.
+        os._exit(0)
+
     def get_input(self):
         """
         Multi-line input function

channel/web/chat.html

@@ -47,11 +47,33 @@
          This runs synchronously in <head> so the correct class is on <html>
          before any CSS or body rendering occurs. -->
     <script>
+    // Map an arbitrary locale string (zh-CN, en-US, fr ...) to 'zh' / 'zh-Hant' / 'en',
+    // or '' when unrecognized so callers can fall through to the next source.
+    window.__cowNormalizeLang__ = function(raw) {
+        if (!raw) return '';
+        var v = String(raw).trim().toLowerCase().replace('_', '-');
+        if (v === 'auto') return '';
+        // Handle Traditional Chinese variants first (more specific)
+        if (v === 'zh-hant' || v.indexOf('zh-hant-') === 0 || v === 'zh-tw' || v === 'zh-hk') return 'zh-Hant';
+        // Then Simplified Chinese
+        if (v.indexOf('zh') === 0) return 'zh';
+        if (v.indexOf('en') === 0) return 'en';
+        return '';
+    };
+    // Resolve the console language by priority:
+    //   user choice (localStorage) -> backend-detected -> browser -> 'zh'.
+    window.__cowResolveLang__ = function() {
+        return window.__cowNormalizeLang__(localStorage.getItem('cow_lang'))
+            || window.__cowNormalizeLang__(window.__COW_DEFAULT_LANG__)
+            || window.__cowNormalizeLang__(navigator.language || (navigator.languages && navigator.languages[0]))
+            || 'zh';
+    };
     (function() {
+        // Backend-resolved default language (from cow_lang config / auto-detect).
+        window.__COW_DEFAULT_LANG__ = '{{COW_DEFAULT_LANG}}';
         var theme = localStorage.getItem('cow_theme') || 'dark';
         if (theme === 'dark') document.documentElement.classList.add('dark');
-        var lang = localStorage.getItem('cow_lang') || 'zh';
-        document.documentElement.setAttribute('lang', lang);
+        document.documentElement.setAttribute('lang', window.__cowResolveLang__());
     })();
     </script>
 </head>
@@ -248,14 +270,29 @@
 
                 <div class="flex-1"></div>
 
-                <!-- Language Toggle -->
-                <button id="lang-toggle" class="flex items-center gap-1.5 px-3 py-1.5 rounded-lg text-sm font-medium
-                                                 text-slate-500 dark:text-slate-400 hover:bg-slate-100 dark:hover:bg-white/10
-                                                 cursor-pointer transition-colors duration-150"
-                        onclick="toggleLanguage()">
-                    <i class="fas fa-globe text-xs"></i>
-                    <span id="lang-label">EN</span>
-                </button>
+                <!-- Language Selector (dropdown) -->
+                <div id="lang-selector" class="relative">
+                    <button id="lang-toggle" class="flex items-center gap-1.5 px-3 py-1.5 rounded-lg text-sm font-medium
+                                                     text-slate-500 dark:text-slate-400 hover:bg-slate-100 dark:hover:bg-white/10
+                                                     cursor-pointer transition-colors duration-150"
+                            onclick="toggleLangMenu(event)">
+                        <i class="fas fa-globe text-xs"></i>
+                        <span id="lang-label">EN</span>
+                        <i class="fas fa-chevron-down text-[10px] opacity-60"></i>
+                    </button>
+                    <div id="lang-menu" class="hidden absolute right-0 mt-1 min-w-[120px] py-1 rounded-lg z-50
+                                               bg-white dark:bg-slate-800 shadow-lg ring-1 ring-black/5 dark:ring-white/10">
+                        <button class="lang-menu-item w-full text-left px-3 py-1.5 text-sm text-slate-600 dark:text-slate-300
+                                       hover:bg-slate-100 dark:hover:bg-white/10 cursor-pointer" data-lang="zh"
+                                onclick="selectLanguage('zh')">简体中文</button>
+                        <button class="lang-menu-item w-full text-left px-3 py-1.5 text-sm text-slate-600 dark:text-slate-300
+                                       hover:bg-slate-100 dark:hover:bg-white/10 cursor-pointer" data-lang="zh-Hant"
+                                onclick="selectLanguage('zh-Hant')">繁體中文</button>
+                        <button class="lang-menu-item w-full text-left px-3 py-1.5 text-sm text-slate-600 dark:text-slate-300
+                                       hover:bg-slate-100 dark:hover:bg-white/10 cursor-pointer" data-lang="en"
+                                onclick="selectLanguage('en')">English</button>
+                    </div>
+                </div>
 
                 <!-- Theme Toggle -->
                 <button id="theme-toggle" class="p-2 rounded-lg text-slate-500 dark:text-slate-400
@@ -266,7 +303,7 @@
                 </button>
 
                 <!-- Docs Link -->
-                <a href="https://docs.cowagent.ai" target="_blank" rel="noopener noreferrer"
+                <a id="docs-link" href="https://docs.cowagent.ai" target="_blank" rel="noopener noreferrer"
                    class="p-2 rounded-lg text-slate-500 dark:text-slate-400 hover:bg-slate-100 dark:hover:bg-white/10
                           cursor-pointer transition-colors duration-150" title="Documentation">
                     <i class="fas fa-book text-base"></i>
@@ -285,6 +322,14 @@
                           cursor-pointer transition-colors duration-150" title="GitHub">
                     <i class="fab fa-github text-lg"></i>
                 </a>
+
+                <!-- Logout Button (hidden by default) -->
+                <button id="logout-btn-header" class="p-2 rounded-lg text-slate-500 dark:text-slate-400
+                                                       hover:bg-red-50 hover:text-red-500 dark:hover:bg-red-500/10 dark:hover:text-red-400
+                                                       cursor-pointer transition-colors duration-150 hidden"
+                        onclick="handleLogout()" title="Logout" data-i18n-title="logout">
+                    <i class="fas fa-sign-out-alt text-base"></i>
+                </button>
             </header>
 
             <!-- Content Area -->
@@ -445,7 +490,7 @@
                                                bg-primary-400 text-white hover:bg-primary-500
                                                disabled:bg-slate-300 dark:disabled:bg-slate-600
                                                disabled:cursor-not-allowed cursor-pointer transition-colors duration-150"
-                                        disabled onclick="sendMessage()">
+                                        disabled>
                                     <i class="fas fa-paper-plane text-sm"></i>
                                 </button>
                             </div>
@@ -601,6 +646,18 @@
                                                             after:rounded-full after:h-4 after:w-4 after:transition-all peer-checked:after:translate-x-full"></div>
                                             </label>
                                         </div>
+                                        <div class="flex items-center justify-between">
+                                            <label class="flex items-center gap-1.5 text-sm font-medium text-slate-600 dark:text-slate-400">
+                                                <span data-i18n="config_self_evolution">Self-Evolution</span>
+                                                <span class="cfg-tip" data-tip-key="config_self_evolution_hint"><i class="fas fa-circle-question"></i></span>
+                                            </label>
+                                            <label class="relative inline-flex items-center cursor-pointer">
+                                                <input id="cfg-self-evolution" type="checkbox" class="sr-only peer">
+                                                <div class="w-9 h-5 bg-slate-200 dark:bg-slate-700 peer-checked:bg-primary-400 rounded-full
+                                                            after:content-[''] after:absolute after:top-[2px] after:left-[2px] after:bg-white
+                                                            after:rounded-full after:h-4 after:w-4 after:transition-all peer-checked:after:translate-x-full"></div>
+                                            </label>
+                                        </div>
                                         <div class="flex items-center justify-end gap-3 pt-1">
                                             <span id="cfg-agent-status" class="text-xs text-primary-500 opacity-0 transition-opacity duration-300"></span>
                                             <button id="cfg-agent-save"
@@ -640,6 +697,31 @@
                                     </div>
                                 </div>
 
+                                <!-- Language Config Card -->
+                                <div class="bg-white dark:bg-[#1A1A1A] rounded-xl border border-slate-200 dark:border-white/10 p-6">
+                                    <div class="flex items-center gap-3 mb-5">
+                                        <div class="w-9 h-9 rounded-lg bg-sky-50 dark:bg-sky-900/30 flex items-center justify-center">
+                                            <i class="fas fa-language text-sky-500 text-sm"></i>
+                                        </div>
+                                        <h3 class="font-semibold text-slate-800 dark:text-slate-100" data-i18n="config_language">语言</h3>
+                                    </div>
+                                    <div class="space-y-4">
+                                        <div>
+                                            <label class="flex items-center gap-1.5 text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5">
+                                                <span data-i18n="config_language">语言</span>
+                                                <span class="cfg-tip" data-tip-key="config_language_hint"><i class="fas fa-circle-question"></i></span>
+                                            </label>
+                                            <div id="cfg-lang-select" class="cfg-dropdown" tabindex="0">
+                                                <div class="cfg-dropdown-selected">
+                                                    <span class="cfg-dropdown-text">--</span>
+                                                    <i class="fas fa-chevron-down cfg-dropdown-arrow"></i>
+                                                </div>
+                                                <div class="cfg-dropdown-menu"></div>
+                                            </div>
+                                        </div>
+                                    </div>
+                                </div>
+
                             </div>
                         </div>
                     </div>
@@ -716,7 +798,7 @@
                                         </button>
                                         <button id="memory-tab-dreams" onclick="switchMemoryTab('dreams')"
                                                 class="memory-tab px-3 py-1.5 rounded-md text-xs font-medium cursor-pointer transition-colors duration-150">
-                                            <i class="fas fa-moon mr-1.5"></i><span data-i18n="memory_tab_dreams">梦境日记</span>
+                                            <i class="fas fa-seedling mr-1.5"></i><span data-i18n="memory_tab_dreams">自主进化</span>
                                         </button>
                                     </div>
                                 </div>
@@ -773,17 +855,18 @@
                 <!-- VIEW: Knowledge                                         -->
                 <!-- ====================================================== -->
                 <div id="view-knowledge" class="view">
-                    <div class="flex-1 overflow-y-auto p-4 md:p-8 lg:p-10">
-                        <div class="w-full max-w-[1600px] mx-auto">
+                    <div class="flex-1 min-h-0 overflow-y-auto md:overflow-hidden p-4 md:p-8 lg:p-10 md:flex md:flex-col">
+                        <div class="w-full max-w-[1600px] mx-auto md:flex-1 md:min-h-0 md:flex md:flex-col">
 
                             <!-- Header -->
-                            <div class="flex flex-col sm:flex-row sm:items-center justify-between gap-3 mb-4 md:mb-6">
+                            <div class="flex flex-col sm:flex-row sm:items-center justify-between gap-3 mb-4 md:mb-6 md:flex-shrink-0">
                                 <div>
                                     <h2 class="text-xl font-bold text-slate-800 dark:text-slate-100" data-i18n="knowledge_title">知识库</h2>
                                     <p class="text-sm text-slate-500 dark:text-slate-400 mt-1" data-i18n="knowledge_desc">浏览和探索你的知识库</p>
                                 </div>
                                 <div class="flex items-center gap-2">
                                     <span id="knowledge-stats" class="text-xs text-slate-400 dark:text-slate-500 hidden sm:inline"></span>
+                                    <span id="knowledge-action-status" class="text-xs opacity-0 transition-opacity duration-200"></span>
                                     <div class="flex items-center bg-slate-100 dark:bg-white/10 rounded-lg p-0.5">
                                         <button id="knowledge-tab-docs" onclick="switchKnowledgeTab('docs')"
                                                 class="knowledge-tab px-3 py-1.5 rounded-md text-xs font-medium cursor-pointer transition-colors duration-150 active">
@@ -794,6 +877,28 @@
                                             <i class="fas fa-diagram-project mr-1.5"></i><span data-i18n="knowledge_tab_graph">图谱</span>
                                         </button>
                                     </div>
+                                    <div id="knowledge-new-menu" class="relative">
+                                        <button onclick="toggleKnowledgeNewMenu(event)"
+                                                class="flex items-center gap-1.5 px-3 py-1.5 rounded-lg bg-primary-500 hover:bg-primary-600 text-white text-xs font-medium cursor-pointer transition-colors">
+                                            <i class="fas fa-plus"></i><span data-i18n="knowledge_new">新建</span><i class="fas fa-chevron-down text-[9px] ml-0.5"></i>
+                                        </button>
+                                        <div id="knowledge-new-menu-list"
+                                             class="hidden absolute right-0 mt-1.5 w-44 z-50 bg-white dark:bg-[#1A1A1A] border border-slate-200 dark:border-white/10 rounded-lg shadow-lg py-1">
+                                            <button onclick="createKnowledgeCategory(); closeKnowledgeNewMenu()"
+                                                    class="w-full flex items-center gap-2.5 px-3 py-2 text-xs text-slate-600 dark:text-slate-300 hover:bg-slate-50 dark:hover:bg-white/5 cursor-pointer transition-colors">
+                                                <i class="fas fa-folder-plus w-3.5 text-slate-400"></i><span data-i18n="knowledge_new_category">新建分类</span>
+                                            </button>
+                                            <button onclick="createKnowledgeDocument(); closeKnowledgeNewMenu()"
+                                                    class="w-full flex items-center gap-2.5 px-3 py-2 text-xs text-slate-600 dark:text-slate-300 hover:bg-slate-50 dark:hover:bg-white/5 cursor-pointer transition-colors">
+                                                <i class="fas fa-file-circle-plus w-3.5 text-slate-400"></i><span data-i18n="knowledge_new_document">新建文档</span>
+                                            </button>
+                                            <button onclick="selectKnowledgeImportFiles(); closeKnowledgeNewMenu()"
+                                                    class="w-full flex items-center gap-2.5 px-3 py-2 text-xs text-slate-600 dark:text-slate-300 hover:bg-slate-50 dark:hover:bg-white/5 cursor-pointer transition-colors">
+                                                <i class="fas fa-file-arrow-up w-3.5 text-slate-400"></i><span data-i18n="knowledge_import_documents">导入文档</span>
+                                            </button>
+                                        </div>
+                                    </div>
+                                    <input id="knowledge-import-input" type="file" class="hidden" multiple accept=".md,.txt,text/markdown,text/plain">
                                 </div>
                             </div>
 
@@ -816,12 +921,12 @@
                             </div>
 
                             <!-- Documents panel -->
-                            <div id="knowledge-panel-docs" class="hidden">
-                                <div class="flex flex-col md:flex-row gap-4 md:gap-6" style="min-height: calc(100vh - 220px)">
+                            <div id="knowledge-panel-docs" class="hidden md:flex-1 md:min-h-0">
+                                <div class="flex flex-col md:flex-row gap-4 md:gap-6 md:h-full">
                                     <!-- File tree -->
-                                    <div id="knowledge-sidebar" class="w-full md:w-72 lg:w-80 flex-shrink-0">
-                                        <div class="bg-white dark:bg-[#1A1A1A] rounded-xl border border-slate-200 dark:border-white/10 overflow-hidden">
-                                            <div class="px-4 py-3 border-b border-slate-200 dark:border-white/10">
+                                    <div id="knowledge-sidebar" class="w-full md:w-72 lg:w-80 flex-shrink-0 md:h-full">
+                                        <div class="bg-white dark:bg-[#1A1A1A] rounded-xl border border-slate-200 dark:border-white/10 overflow-hidden flex flex-col md:h-full">
+                                            <div class="px-4 py-3 border-b border-slate-200 dark:border-white/10 flex-shrink-0">
                                                 <div class="relative">
                                                     <i class="fas fa-search absolute left-3 top-1/2 -translate-y-1/2 text-slate-400 text-xs"></i>
                                                     <input id="knowledge-search" type="text" placeholder="Search..."
@@ -829,19 +934,19 @@
                                                            oninput="filterKnowledgeTree(this.value)">
                                                 </div>
                                             </div>
-                                            <div id="knowledge-tree" class="p-2 overflow-y-auto max-h-[50vh] md:max-h-[calc(100vh-300px)]"></div>
+                                            <div id="knowledge-tree" class="p-2 overflow-y-auto flex-1 max-h-[50vh] md:max-h-none"></div>
                                         </div>
                                     </div>
                                     <!-- Content viewer -->
-                                    <div class="flex-1 min-w-0">
+                                    <div class="flex-1 min-w-0 md:h-full">
                                         <div id="knowledge-content-placeholder"
-                                             class="flex flex-col items-center justify-center py-20 text-slate-400 dark:text-slate-500">
+                                             class="flex flex-col items-center justify-center py-20 md:h-full text-slate-400 dark:text-slate-500 bg-white dark:bg-[#1A1A1A] rounded-xl border border-slate-200 dark:border-white/10">
                                             <i class="fas fa-file-lines text-3xl mb-3 opacity-40"></i>
                                             <p class="text-sm" data-i18n="knowledge_select_hint">选择一个文档查看</p>
                                         </div>
-                                        <div id="knowledge-content-viewer" class="hidden">
-                                            <div class="bg-white dark:bg-[#1A1A1A] rounded-xl border border-slate-200 dark:border-white/10 overflow-hidden">
-                                                <div class="flex items-center gap-3 px-4 md:px-5 py-3 border-b border-slate-200 dark:border-white/10">
+                                        <div id="knowledge-content-viewer" class="hidden md:h-full">
+                                            <div class="bg-white dark:bg-[#1A1A1A] rounded-xl border border-slate-200 dark:border-white/10 overflow-hidden flex flex-col md:h-full">
+                                                <div class="flex items-center gap-3 px-4 md:px-5 py-3 border-b border-slate-200 dark:border-white/10 flex-shrink-0">
                                                     <button onclick="knowledgeMobileBack()" class="md:hidden p-1 -ml-1 text-slate-400 hover:text-slate-600 dark:hover:text-slate-300 cursor-pointer">
                                                         <i class="fas fa-arrow-left text-xs"></i>
                                                     </button>
@@ -850,8 +955,7 @@
                                                     <span id="knowledge-viewer-path" class="text-xs text-slate-400 dark:text-slate-500 ml-auto font-mono truncate hidden md:inline"></span>
                                                 </div>
                                                 <div id="knowledge-viewer-body"
-                                                     class="p-4 md:p-5 overflow-y-auto text-sm msg-content text-slate-700 dark:text-slate-200"
-                                                     style="max-height: calc(100vh - 280px)"></div>
+                                                     class="p-4 md:p-5 overflow-y-auto flex-1 max-h-[60vh] md:max-h-none text-sm msg-content text-slate-700 dark:text-slate-200"></div>
                                             </div>
                                         </div>
                                     </div>
@@ -939,6 +1043,14 @@
                                     <h2 class="text-xl font-bold text-slate-800 dark:text-slate-100" data-i18n="tasks_title">定时任务</h2>
                                     <p class="text-sm text-slate-500 dark:text-slate-400 mt-1" data-i18n="tasks_desc">查看和管理定时任务</p>
                                 </div>
+                                <div class="flex items-center gap-2">
+                                    <button id="task-refresh-btn" onclick="refreshTasksView()"
+                                            class="px-3 py-2 rounded-lg border border-slate-200 dark:border-white/10
+                                                   text-slate-600 dark:text-slate-300 hover:bg-slate-50 dark:hover:bg-white/5
+                                                   text-sm font-medium cursor-pointer transition-colors duration-150">
+                                        <i class="fas fa-refresh text-xs"></i>
+                                    </button>
+                                </div>
                             </div>
                             <div id="tasks-empty" class="flex flex-col items-center justify-center py-20">
                                 <div class="w-16 h-16 rounded-2xl bg-rose-50 dark:bg-rose-900/20 flex items-center justify-center mb-4">
@@ -1012,6 +1124,62 @@
         </div><!-- /main-content -->
     </div><!-- /app -->
 
+    <!-- Knowledge Action Dialog -->
+    <div id="knowledge-dialog-overlay" class="fixed inset-0 bg-black/50 z-[200] hidden flex items-center justify-center">
+        <div id="knowledge-dialog-card" class="bg-white dark:bg-[#1A1A1A] rounded-2xl border border-slate-200 dark:border-white/10 shadow-xl w-full max-w-md mx-4">
+            <div class="p-6">
+                <div class="flex items-center gap-3 mb-5">
+                    <div class="w-10 h-10 rounded-xl bg-emerald-50 dark:bg-emerald-900/20 flex items-center justify-center">
+                        <i id="knowledge-dialog-icon" class="fas fa-folder text-emerald-500"></i>
+                    </div>
+                    <div>
+                        <h3 id="knowledge-dialog-title" class="font-semibold text-slate-800 dark:text-slate-100"></h3>
+                        <p id="knowledge-dialog-subtitle" class="text-xs text-slate-400 dark:text-slate-500 mt-0.5"></p>
+                    </div>
+                </div>
+                <label id="knowledge-dialog-label" class="block text-sm font-medium text-slate-600 dark:text-slate-300 mb-1.5"></label>
+                <input id="knowledge-dialog-input" type="text"
+                       class="w-full px-3 py-2 rounded-lg border border-slate-200 dark:border-slate-600 bg-slate-50 dark:bg-white/5 text-sm text-slate-800 dark:text-slate-100 focus:outline-none focus:border-primary-500">
+                <div id="knowledge-dialog-select" class="cfg-dropdown hidden w-full" tabindex="0">
+                    <div class="cfg-dropdown-selected">
+                        <span class="cfg-dropdown-text">--</span>
+                        <i class="fas fa-chevron-down cfg-dropdown-arrow"></i>
+                    </div>
+                    <div class="cfg-dropdown-menu"></div>
+                </div>
+                <textarea id="knowledge-dialog-textarea" rows="8"
+                          class="hidden w-full px-3 py-2 rounded-lg border border-slate-200 dark:border-slate-600 bg-slate-50 dark:bg-white/5 text-sm text-slate-800 dark:text-slate-100 focus:outline-none focus:border-primary-500 font-mono resize-y"></textarea>
+                <div id="knowledge-document-form" class="hidden space-y-3">
+                    <div class="rounded-lg bg-emerald-50 dark:bg-emerald-900/15 border border-emerald-100 dark:border-emerald-800/40 px-3 py-2">
+                        <div id="knowledge-document-category-label" class="text-[11px] text-emerald-600 dark:text-emerald-400 mb-0.5"></div>
+                        <div id="knowledge-document-path-preview" class="text-xs font-mono text-emerald-700 dark:text-emerald-300 break-all"></div>
+                    </div>
+                    <div>
+                        <label id="knowledge-document-filename-label" class="block text-sm font-medium text-slate-600 dark:text-slate-300 mb-1.5"></label>
+                        <input id="knowledge-document-filename" type="text"
+                               class="w-full px-3 py-2 rounded-lg border border-slate-200 dark:border-slate-600 bg-slate-50 dark:bg-white/5 text-sm text-slate-800 dark:text-slate-100 focus:outline-none focus:border-primary-500"
+                               placeholder="note.md">
+                    </div>
+                    <div>
+                        <div class="flex items-center justify-between mb-1.5">
+                            <label id="knowledge-document-content-label" class="block text-sm font-medium text-slate-600 dark:text-slate-300"></label>
+                            <button id="knowledge-document-template" type="button" class="text-xs text-primary-500 hover:text-primary-600"></button>
+                        </div>
+                        <textarea id="knowledge-document-content" rows="14"
+                                  class="w-full px-3 py-2 rounded-lg border border-slate-200 dark:border-slate-600 bg-slate-50 dark:bg-white/5 text-sm text-slate-800 dark:text-slate-100 focus:outline-none focus:border-primary-500 font-mono resize-y"
+                                  placeholder="# Title&#10;&#10;Write your notes here..."></textarea>
+                    </div>
+                </div>
+                <p id="knowledge-dialog-hint" class="mt-2 text-xs text-slate-400 dark:text-slate-500"></p>
+                <p id="knowledge-dialog-error" class="mt-2 text-xs text-red-500 hidden"></p>
+            </div>
+            <div class="flex justify-end gap-3 px-6 py-4 border-t border-slate-100 dark:border-white/5">
+                <button id="knowledge-dialog-cancel" class="px-4 py-2 rounded-lg border border-slate-200 dark:border-white/10 text-slate-600 dark:text-slate-300 text-sm hover:bg-slate-50 dark:hover:bg-white/5">取消</button>
+                <button id="knowledge-dialog-submit" class="px-4 py-2 rounded-lg bg-primary-500 hover:bg-primary-600 text-white text-sm font-medium disabled:opacity-50">确定</button>
+            </div>
+        </div>
+    </div>
+
     <!-- Confirm Dialog -->
     <div id="confirm-dialog-overlay" class="fixed inset-0 bg-black/50 z-[200] hidden flex items-center justify-center">
         <div class="bg-white dark:bg-[#1A1A1A] rounded-2xl border border-slate-200 dark:border-white/10 shadow-xl
@@ -1109,6 +1277,240 @@
         </div>
     </div>
 
+    <!-- Custom Provider Modal (multiple OpenAI-compatible providers) -->
+    <div id="custom-provider-modal-overlay" class="fixed inset-0 bg-black/50 z-[100] hidden flex items-center justify-center">
+        <div class="bg-white dark:bg-[#1A1A1A] rounded-2xl border border-slate-200 dark:border-white/10 shadow-xl
+                    w-full max-w-md mx-4">
+            <div class="p-6">
+                <div class="flex items-center gap-3 mb-5">
+                    <div class="w-10 h-10 rounded-xl bg-primary-50 dark:bg-primary-900/20 flex items-center justify-center flex-shrink-0">
+                        <i class="fas fa-sliders text-primary-500"></i>
+                    </div>
+                    <div class="min-w-0 flex-1">
+                        <h3 id="custom-provider-modal-title" class="font-semibold text-slate-800 dark:text-slate-100 text-base"></h3>
+                    </div>
+                </div>
+
+                <div class="space-y-4">
+                    <div>
+                        <label class="block text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5" data-i18n="models_custom_name">名称</label>
+                        <input id="custom-provider-name" type="text" autocomplete="off" data-1p-ignore data-lpignore="true"
+                               class="w-full px-3 py-2 rounded-lg border border-slate-200 dark:border-slate-600
+                                      bg-slate-50 dark:bg-white/5 text-sm text-slate-800 dark:text-slate-100
+                                      focus:outline-none focus:border-primary-500 transition-colors">
+                    </div>
+                    <div>
+                        <label class="block text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5">API Base</label>
+                        <input id="custom-provider-base" type="text"
+                               class="w-full px-3 py-2 rounded-lg border border-slate-200 dark:border-slate-600
+                                      bg-slate-50 dark:bg-white/5 text-sm text-slate-800 dark:text-slate-100
+                                      focus:outline-none focus:border-primary-500 font-mono transition-colors"
+                               placeholder="https://...../v1">
+                    </div>
+                    <div>
+                        <label class="block text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5">API Key</label>
+                        <input id="custom-provider-key" type="text" autocomplete="off" data-1p-ignore data-lpignore="true"
+                               class="w-full px-3 py-2 rounded-lg border border-slate-200 dark:border-slate-600
+                                      bg-slate-50 dark:bg-white/5 text-sm text-slate-800 dark:text-slate-100
+                                      focus:outline-none focus:border-primary-500 font-mono transition-colors">
+                    </div>
+                </div>
+            </div>
+            <div class="flex items-center justify-between gap-3 px-6 py-4 border-t border-slate-100 dark:border-white/5 rounded-b-2xl">
+                <button id="custom-provider-modal-delete"
+                        class="px-3 py-2 rounded-lg text-sm font-medium text-red-500 hover:bg-red-50 dark:hover:bg-red-900/20
+                               cursor-pointer transition-colors duration-150 hidden"
+                        data-i18n="models_custom_delete">删除</button>
+                <span id="custom-provider-modal-status"
+                      class="flex-1 text-xs text-primary-500 opacity-0 transition-opacity duration-300 text-left"></span>
+                <button id="custom-provider-modal-cancel"
+                        class="px-4 py-2 rounded-lg border border-slate-200 dark:border-white/10
+                               text-slate-600 dark:text-slate-300 text-sm font-medium
+                               hover:bg-slate-50 dark:hover:bg-white/5
+                               cursor-pointer transition-colors duration-150"
+                        data-i18n="cancel">取消</button>
+                <button id="custom-provider-modal-save"
+                        class="px-4 py-2 rounded-lg bg-primary-500 hover:bg-primary-600 text-white text-sm font-medium
+                               cursor-pointer transition-colors duration-150 disabled:opacity-50 disabled:cursor-not-allowed"
+                        data-i18n="save">保存</button>
+            </div>
+        </div>
+    </div>
+
+    <!-- Task Edit Modal -->
+    <div id="task-edit-modal-overlay" class="fixed inset-0 bg-black/50 z-[100] hidden flex items-center justify-center">
+        <div class="bg-white dark:bg-[#1A1A1A] rounded-2xl border border-slate-200 dark:border-white/10 shadow-xl
+                    w-full max-w-2xl mx-4 max-h-[90vh] overflow-y-auto">
+            <div class="p-6">
+                <div class="flex items-center gap-3 mb-5">
+                    <div class="w-10 h-10 rounded-xl bg-primary-50 dark:bg-primary-900/20 flex items-center justify-center flex-shrink-0">
+                        <i class="fas fa-clock text-primary-500"></i>
+                    </div>
+                    <div class="min-w-0 flex-1">
+                        <h3 class="font-semibold text-slate-800 dark:text-slate-100 text-base" data-i18n="task_edit_title">编辑定时任务</h3>
+                        <p id="task-edit-modal-subtitle" class="text-xs text-slate-500 dark:text-slate-400 mt-0.5 font-mono"></p>
+                    </div>
+                </div>
+
+                <div class="space-y-4">
+                    <!-- 任务名称和启用状态 -->
+                    <div class="flex gap-4 items-end">
+                        <div class="flex-1">
+                            <label class="block text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5">
+                                <span data-i18n="task_name">任务名称</span>
+                            </label>
+                            <input id="task-edit-name" type="text"
+                                   class="w-full px-3 py-2 rounded-lg border border-slate-200 dark:border-slate-600
+                                          bg-slate-50 dark:bg-white/5 text-sm text-slate-800 dark:text-slate-100
+                                          focus:outline-none focus:border-primary-500 transition-colors"
+                                   placeholder="任务名称">
+                        </div>
+                        <div class="flex items-center gap-2 pb-[2px]">
+                            <label class="text-xs font-medium text-slate-600 dark:text-slate-400">
+                                <span data-i18n="task_enabled">启用</span>
+                            </label>
+                            <label class="relative inline-flex items-center cursor-pointer">
+                                <input type="checkbox" id="task-edit-enabled" class="sr-only peer">
+                                <div class="w-11 h-6 bg-slate-200 peer-focus:outline-none rounded-full peer peer-checked:after:translate-x-full peer-checked:after:border-white after:content-[''] after:absolute after:top-[2px] after:left-[2px] after:bg-white after:rounded-full after:h-5 after:w-5 after:transition-all peer-checked:bg-primary-500 dark:bg-slate-600 dark:peer-checked:bg-primary-500"></div>
+                            </label>
+                        </div>
+                    </div>
+
+                    <!-- 调度类型 + 调度值 -->
+                    <div class="grid grid-cols-2 gap-4">
+                        <div>
+                            <label class="block text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5">
+                                <span data-i18n="task_schedule_type">调度类型</span>
+                            </label>
+                            <select id="task-edit-schedule-type"
+                                    class="w-full px-3 py-2 pr-8 rounded-lg border border-slate-200 dark:border-slate-600
+                                           bg-slate-50 dark:bg-[#1A1A1A] text-sm text-slate-800 dark:text-slate-100
+                                           focus:outline-none focus:border-primary-500 transition-colors
+                                           appearance-none bg-no-repeat bg-right"
+                                    style="background-image: url('data:image/svg+xml;charset=UTF-8,%3csvg xmlns=%27http://www.w3.org/2000/svg%27 viewBox=%270 0 20 20%27 fill=%27none%27%3e%3cpath d=%27M7 7l3 3 3-3%27 stroke=%27%23888%27 stroke-width=%272%27 stroke-linecap=%27round%27 stroke-linejoin=%27round%27/%3e%3c/svg%3e'); background-position: right 0.5rem center; background-size: 1.25rem;">
+                                <option value="cron" data-i18n="task_schedule_cron">Cron 表达式</option>
+                                <option value="interval" data-i18n="task_schedule_interval">固定间隔</option>
+                                <option value="once" data-i18n="task_schedule_once">一次性任务</option>
+                            </select>
+                        </div>
+
+                        <!-- Cron 表达式 -->
+                        <div id="task-edit-cron-wrap">
+                            <label class="block text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5">
+                                <span data-i18n="task_cron_expression">Cron 表达式</span>
+                            </label>
+                            <input id="task-edit-cron-expression" type="text"
+                                   class="w-full px-3 py-2 rounded-lg border border-slate-200 dark:border-slate-600
+                                          bg-slate-50 dark:bg-white/5 text-sm text-slate-800 dark:text-slate-100
+                                          focus:outline-none focus:border-primary-500 font-mono transition-colors"
+                                   placeholder="0 9 * * *">
+                        </div>
+
+                        <!-- 固定间隔 -->
+                        <div id="task-edit-interval-wrap" class="hidden">
+                            <label class="block text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5">
+                                <span data-i18n="task_interval_seconds">间隔秒数</span>
+                            </label>
+                            <input id="task-edit-interval-seconds" type="number" min="60"
+                                   class="w-full px-3 py-2 rounded-lg border border-slate-200 dark:border-slate-600
+                                          bg-slate-50 dark:bg-white/5 text-sm text-slate-800 dark:text-slate-100
+                                          focus:outline-none focus:border-primary-500 transition-colors"
+                                   placeholder="3600">
+                        </div>
+
+                        <!-- 一次性任务时间 -->
+                        <div id="task-edit-once-wrap" class="hidden">
+                            <label class="block text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5">
+                                <span data-i18n="task_once_time">执行时间</span>
+                            </label>
+                            <input id="task-edit-once-time" type="datetime-local" step="1"
+                                   class="w-full px-3 py-2 rounded-lg border border-slate-200 dark:border-slate-600
+                                          bg-slate-50 dark:bg-white/5 text-sm text-slate-800 dark:text-slate-100
+                                          focus:outline-none focus:border-primary-500 transition-colors
+                                          cursor-pointer"
+                                   onclick="this.showPicker && this.showPicker()">
+                        </div>
+                    </div>
+
+                    <!-- Cron/Interval 提示 -->
+                    <p id="task-edit-cron-hint" class="text-xs text-slate-400 dark:text-slate-500">
+                        <span data-i18n="task_cron_hint">格式: 分 时 日 月 周，例如 "0 9 * * *" 表示每天 9:00</span>
+                    </p>
+                    <p id="task-edit-interval-hint" class="text-xs text-slate-400 dark:text-slate-500 hidden">
+                        <span data-i18n="task_interval_hint">最小 60 秒，例如 3600 表示每小时执行一次</span>
+                    </p>
+
+                    <!-- 动作类型 + 通道类型 -->
+                    <div class="grid grid-cols-2 gap-4">
+                        <div>
+                            <label class="block text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5">
+                                <span data-i18n="task_action_type">动作类型</span>
+                            </label>
+                            <select id="task-edit-action-type"
+                                    class="w-full px-3 py-2 pr-8 rounded-lg border border-slate-200 dark:border-slate-600
+                                           bg-slate-50 dark:bg-[#1A1A1A] text-sm text-slate-800 dark:text-slate-100
+                                           focus:outline-none focus:border-primary-500 transition-colors
+                                           appearance-none bg-no-repeat bg-right"
+                                    style="background-image: url('data:image/svg+xml;charset=UTF-8,%3csvg xmlns=%27http://www.w3.org/2000/svg%27 viewBox=%270 0 20 20%27 fill=%27none%27%3e%3cpath d=%27M7 7l3 3 3-3%27 stroke=%27%23888%27 stroke-width=%272%27 stroke-linecap=%27round%27 stroke-linejoin=%27round%27/%3e%3c/svg%3e'); background-position: right 0.5rem center; background-size: 1.25rem;">
+                                <option value="send_message" data-i18n="task_action_send_message">发送消息</option>
+                                <option value="agent_task" data-i18n="task_action_agent_task">AI 任务</option>
+                            </select>
+                        </div>
+                        <div>
+                            <label class="block text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5">
+                                <span data-i18n="task_channel_type">通道类型</span>
+                            </label>
+                            <select id="task-edit-channel-type"
+                                    class="w-full px-3 py-2 pr-8 rounded-lg border border-slate-200 dark:border-slate-600
+                                           bg-slate-50 dark:bg-[#1A1A1A] text-sm text-slate-800 dark:text-slate-100
+                                           focus:outline-none focus:border-primary-500 transition-colors
+                                           appearance-none bg-no-repeat bg-right
+                                           disabled:opacity-100 disabled:text-slate-800 dark:disabled:text-slate-300 disabled:bg-slate-100 dark:disabled:bg-[#252525] disabled:cursor-not-allowed"
+                                    style="background-image: url('data:image/svg+xml;charset=UTF-8,%3csvg xmlns=%27http://www.w3.org/2000/svg%27 viewBox=%270 0 20 20%27 fill=%27none%27%3e%3cpath d=%27M7 7l3 3 3-3%27 stroke=%27%23888%27 stroke-width=%272%27 stroke-linecap=%27round%27 stroke-linejoin=%27round%27/%3e%3c/svg%3e'); background-position: right 0.5rem center; background-size: 1.25rem;">
+                            </select>
+                            <p class="text-xs text-slate-400 dark:text-slate-500 mt-1">
+                                <span data-i18n="task_channel_hint">选择定时消息发送的通道</span>
+                            </p>
+                        </div>
+                    </div>
+
+                    <!-- 隐藏的接收者ID字段（自动填充） -->
+                    <input id="task-edit-receiver" type="hidden" value="">
+
+                    <!-- 消息内容/任务描述 -->
+                    <div>
+                        <label class="block text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5">
+                            <span id="task-edit-content-label" data-i18n="task_message_content">消息内容</span>
+                        </label>
+                        <textarea id="task-edit-content" rows="3"
+                                  class="w-full px-3 py-2 rounded-lg border border-slate-200 dark:border-slate-600
+                                         bg-slate-50 dark:bg-white/5 text-sm text-slate-800 dark:text-slate-100
+                                         focus:outline-none focus:border-primary-500 transition-colors resize-none"
+                                  placeholder="输入消息内容或任务描述"></textarea>
+                    </div>
+                </div>
+            </div>
+            <div class="flex items-center justify-between gap-3 px-6 py-4 border-t border-slate-100 dark:border-white/5 rounded-b-2xl">
+                <button id="task-edit-modal-delete"
+                        class="px-4 py-2 rounded-lg text-sm font-medium text-red-500 hover:bg-red-50 dark:hover:bg-red-900/20
+                               cursor-pointer transition-colors duration-150 hidden"
+                        data-i18n="task_delete_btn">删除任务</button>
+                <span id="task-edit-modal-status"
+                      class="flex-1 text-xs text-primary-500 opacity-0 transition-opacity duration-300 text-left"></span>
+                <button id="task-edit-modal-cancel"
+                        class="px-4 py-2 rounded-lg border border-slate-200 dark:border-white/10
+                               text-slate-600 dark:text-slate-300 text-sm font-medium
+                               hover:bg-slate-50 dark:hover:bg-white/5
+                               cursor-pointer transition-colors duration-150"
+                        data-i18n="cancel">取消</button>
+                <button id="task-edit-modal-save"
+                        class="px-4 py-2 rounded-lg bg-primary-500 hover:bg-primary-600 text-white text-sm font-medium
+                               cursor-pointer transition-colors duration-150 disabled:opacity-50 disabled:cursor-not-allowed"
+                        data-i18n="save">保存</button>
+            </div>
+        </div>
+    </div>
+
     <script defer src="assets/js/console.js"></script>
 </body>
 </html>

channel/web/static/css/console.css

@@ -244,6 +244,52 @@
 }
 .dark .session-delete:hover { background: rgba(239, 68, 68, 0.15); }
 
+/* Rename button: shares the look of the delete button, sits to its left.
+   Negative right margin tightens the gap to the delete button only. */
+.session-rename {
+    flex-shrink: 0;
+    margin-right: -6px;
+    width: 22px;
+    height: 22px;
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    border-radius: 6px;
+    color: #9ca3af;
+    font-size: 11px;
+    opacity: 0;
+    transition: opacity 0.15s, color 0.15s, background 0.15s;
+    cursor: pointer;
+    background: none;
+    border: none;
+    padding: 0;
+}
+.session-item:hover .session-rename { opacity: 1; }
+.session-rename:hover {
+    color: #4ABE6E;
+    background: rgba(74, 190, 110, 0.12);
+}
+.dark .session-rename:hover { background: rgba(74, 190, 110, 0.18); }
+
+/* Inline title editor */
+.session-title-input {
+    flex: 1;
+    min-width: 0;
+    font-size: 13px;
+    font-family: inherit;
+    color: #111827;
+    background: #ffffff;
+    border: 1px solid #4ABE6E;
+    border-radius: 6px;
+    padding: 2px 6px;
+    outline: none;
+}
+.dark .session-title-input {
+    color: #e5e5e5;
+    background: rgba(255, 255, 255, 0.06);
+    border-color: #4ABE6E;
+}
+
 /* Context Divider */
 .context-divider {
     display: flex;
@@ -605,6 +651,18 @@
     color: inherit;
 }
 .tool-error-text { color: #f87171; }
+.tool-live-output:empty { display: none; }
+.tool-streaming .tool-live-output:not(:empty)::after {
+    content: ' ';
+    display: inline-block;
+    width: 0.45em;
+    height: 1em;
+    margin-left: 0.15em;
+    vertical-align: -0.15em;
+    background: currentColor;
+    animation: tool-cursor-blink 1s steps(1) infinite;
+}
+@keyframes tool-cursor-blink { 50% { opacity: 0; } }
 
 /* Log level highlighting */
 .log-line { display: block; }
@@ -854,6 +912,14 @@
     font-size: 11px;
     flex-shrink: 0;
 }
+/* "Custom" row is an add-new action: trailing + instead of ✓. */
+.vendor-picker-add-mark {
+    margin-left: auto;
+    padding-left: 12px;
+    color: #94a3b8;
+    font-size: 11px;
+    flex-shrink: 0;
+}
 
 /* Chat Input */
 #chat-input {
@@ -1191,6 +1257,34 @@
     background: #EDFDF3;
     color: #228547;
 }
+
+.knowledge-actions {
+    display: flex;
+    gap: 2px;
+    margin-left: auto;
+    opacity: 0;
+    transition: opacity 0.15s;
+}
+.knowledge-tree-file:hover .knowledge-actions,
+.knowledge-tree-group-btn:hover .knowledge-actions,
+.knowledge-tree-file:focus-within .knowledge-actions,
+.knowledge-tree-group-btn:focus-within .knowledge-actions {
+    opacity: 1;
+}
+.knowledge-action {
+    padding: 3px 5px;
+    border-radius: 5px;
+    color: #94a3b8;
+    font-size: 9px;
+}
+.knowledge-action:hover {
+    color: #228547;
+    background: rgba(34, 133, 71, 0.08);
+}
+.knowledge-action.danger:hover {
+    color: #ef4444;
+    background: rgba(239, 68, 68, 0.08);
+}
 .dark .knowledge-tree-file:hover {
     background: rgba(255,255,255,0.06);
     color: #e2e8f0;
@@ -1199,6 +1293,18 @@
     background: rgba(74, 190, 110, 0.1);
     color: #4ABE6E;
 }
+.knowledge-import-drag-over {
+    outline: 2px dashed rgba(74, 190, 110, 0.55);
+    outline-offset: 4px;
+    border-radius: 14px;
+}
+#knowledge-dialog-card.knowledge-document-dialog {
+    max-width: 760px;
+}
+#knowledge-document-content {
+    min-height: 320px;
+    line-height: 1.55;
+}
 
 /* Graph legend */
 .knowledge-graph-legend {
@@ -1367,3 +1473,213 @@
     text-align: right;
 }
 .voice-pill audio { display: none; }
+
+/* Send button toggles into a Stop button while an SSE stream is in flight.
+   Match the look of the disabled send button (light grey block + white
+   glyph) so it reads as the same visual element, just paused/idle from
+   sending perspective and clickable to stop. */
+#send-btn.send-btn-cancel {
+    background-color: rgb(203 213 225) !important; /* slate-300, == disabled send-btn */
+    color: white !important;
+}
+#send-btn.send-btn-cancel:hover {
+    background-color: rgb(148 163 184) !important; /* slate-400 */
+}
+#send-btn.send-btn-cancel:disabled {
+    background-color: rgb(226 232 240) !important; /* slate-200, while stop is in flight */
+    color: white !important;
+    cursor: progress;
+}
+.dark #send-btn.send-btn-cancel {
+    background-color: rgb(71 85 105) !important; /* slate-600, == dark disabled send-btn */
+    color: white !important;
+}
+.dark #send-btn.send-btn-cancel:hover {
+    background-color: rgb(100 116 139) !important; /* slate-500 */
+}
+.dark #send-btn.send-btn-cancel:disabled {
+    background-color: rgb(51 65 85) !important; /* slate-700 */
+    color: rgb(203 213 225) !important;
+}
+
+.agent-cancelled-tag {
+    font-style: italic;
+}
+
+/* =====================================================================
+   Code Block Enhancements
+   ===================================================================== */
+.code-block-wrapper {
+    position: relative;
+    margin: 1em 0;
+    border-radius: 8px;
+    overflow: hidden;
+    background: #f8f9fa;
+    border: 1px solid #e2e8f0;
+}
+
+.dark .code-block-wrapper {
+    background: #1e293b;
+    border-color: #334155;
+}
+
+.code-block-header {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    padding: 0.5em 1em;
+    background: #e2e8f0;
+    border-bottom: 1px solid #cbd5e1;
+    font-size: 0.85em;
+}
+
+.dark .code-block-header {
+    background: #0f172a;
+    border-bottom-color: #334155;
+}
+
+.code-block-lang {
+    color: #64748b;
+    font-weight: 500;
+    text-transform: lowercase;
+}
+
+.dark .code-block-lang {
+    color: #94a3b8;
+}
+
+.code-copy-btn {
+    background: transparent;
+    border: none;
+    color: #64748b;
+    cursor: pointer;
+    padding: 0.25em 0.5em;
+    border-radius: 4px;
+    transition: all 0.2s;
+    font-size: 0.9em;
+}
+
+.code-copy-btn:hover {
+    background: rgba(100, 116, 139, 0.1);
+    color: #475569;
+}
+
+.dark .code-copy-btn {
+    color: #94a3b8;
+}
+
+.dark .code-copy-btn:hover {
+    background: rgba(148, 163, 184, 0.1);
+    color: #cbd5e1;
+}
+
+.code-block-wrapper pre {
+    margin: 0;
+    border-radius: 0;
+    border: none;
+}
+
+/* =====================================================================
+   Drag and Drop Overlay
+   ===================================================================== */
+/* Anchor the absolutely-positioned overlay to the chat view. */
+#view-chat {
+    position: relative;
+}
+
+.drag-overlay {
+    position: absolute;
+    top: 0;
+    left: 0;
+    right: 0;
+    bottom: 0;
+    background: rgba(59, 130, 246, 0.1);
+    backdrop-filter: blur(2px);
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    z-index: 9999;
+    pointer-events: none;
+    opacity: 0;
+    transition: opacity 0.2s;
+}
+
+.drag-overlay.active {
+    opacity: 1;
+}
+
+.drag-overlay.hidden {
+    display: none;
+}
+
+.drag-overlay-content {
+    background: white;
+    border: 3px dashed #3b82f6;
+    border-radius: 16px;
+    padding: 3em 4em;
+    text-align: center;
+    box-shadow: 0 20px 25px -5px rgba(0, 0, 0, 0.1);
+    animation: bounce 1s ease infinite;
+}
+
+.dark .drag-overlay-content {
+    background: #1e293b;
+    border-color: #60a5fa;
+}
+
+.drag-overlay-content i {
+    font-size: 4em;
+    color: #3b82f6;
+    margin-bottom: 0.5em;
+}
+
+.dark .drag-overlay-content i {
+    color: #60a5fa;
+}
+
+.drag-overlay-content p {
+    font-size: 1.5em;
+    font-weight: 600;
+    color: #1e293b;
+    margin: 0;
+}
+
+.dark .drag-overlay-content p {
+    color: #f1f5f9;
+}
+
+@keyframes bounce {
+    0%, 100% { transform: translateY(0); }
+    50% { transform: translateY(-10px); }
+}
+
+/* =====================================================================
+   Message Action Buttons
+   ===================================================================== */
+.edit-msg-btn,
+.delete-msg-btn,
+.regenerate-msg-btn {
+    opacity: 0;
+    transition: opacity 0.2s, color 0.2s;
+}
+
+.user-message-group:hover .edit-msg-btn,
+.user-message-group:hover .delete-msg-btn,
+.bot-message-group:hover .regenerate-msg-btn {
+    opacity: 1;
+}
+
+.edit-msg-btn:hover,
+.regenerate-msg-btn:hover {
+    color: #3b82f6 !important;
+}
+
+.delete-msg-btn:hover {
+    color: #ef4444 !important;
+}
+
+.edit-msg-btn:disabled,
+.delete-msg-btn:disabled {
+    cursor: not-allowed !important;
+    opacity: 0.35 !important;
+}

channel/wechat_kf/README.md

@@ -0,0 +1,115 @@
+# 微信客服（WeChat Customer Service）通道
+
+> 与 `channel/wechatcom/`（企微自建应用）是两个**独立的 CoW 通道**：
+>
+> - 自建应用：**面向企业内部成员**（员工通过企业微信 App 与机器人对话）。
+> - 微信客服：**面向外部微信用户**（普通微信用户通过链接/二维码进入对话）。
+>
+> 但底层都基于"企微自建应用"——本通道是**通过把一个企微自建应用绑定到微信客服账号**来实现 AI 接管对外咨询，详见 [LinkAI 微信客服接入文档](https://docs.link-ai.tech/platform/link-app/wechat-customer-service)。
+
+## 一、接入流程概览
+
+```
+┌─────────────────────┐    ┌─────────────────────┐    ┌──────────────────┐
+│ 1. 企业微信后台      │ →  │ 2. CoW 配置回调      │ →  │ 3. 绑定微信客服   │
+│   创建一个自建应用   │    │   端口 9888          │    │   账号           │
+└─────────────────────┘    └─────────────────────┘    └──────────────────┘
+                                                              ↓
+                                                   外部微信用户通过
+                                                   链接/二维码 →
+                                                   消息 → CoW Bot
+```
+
+> **重要**：建议**单独再创建一个企微自建应用**用于微信客服，**不要复用**已经接入员工内部使用的那个 `wechatcom_app` 应用，否则两个通道会争抢同一个回调地址。
+
+## 二、企业微信后台配置
+
+### 1. 创建企微自建应用
+
+进入 企业微信管理后台 → **应用管理** → **创建应用**。
+
+### 2. 收集字段
+
+| 字段 | 来源 | 对应 CoW 配置项 |
+|---|---|---|
+| 企业ID（CorpId） | 「我的企业」最下方 | `wechat_kf_corp_id` |
+| Secret | 进入应用详情 → 点击「查看」（会推送到管理员手机端，在手机上查看） | `wechat_kf_secret` |
+| Token | 应用「接收消息 → 设置API接收」 | `wechat_kf_token` |
+| EncodingAESKey | 应用「接收消息 → 设置API接收」 | `wechat_kf_aes_key` |
+
+> AgentId 在本通道**不需要**（消息发送走的是 `cgi-bin/kf/send_msg`，不依赖 agent_id）。
+
+### 3. 配置回调地址 + 可信 IP
+
+在应用「**接收消息 → 设置API接收**」里填：
+
+- URL：`http://<your-host>:9888/wxkf/`（公网必须可达）
+- Token / EncodingAESKey：与下方 `config.json` 一致
+
+回到应用详情页，把服务器公网 IP 填入「**企业可信IP**」。
+
+### 4. 绑定微信客服账号
+
+进入 企业微信后台 → **微信客服** → 创建客服账号 → **将该账号绑定到上一步创建的企微自建应用**。
+
+绑定完成后，进入 **微信客服 → 微信客服账号详情** 页面，在「**接入链接**」一栏：
+
+- 「复制链接」可拿到形如 `https://work.weixin.qq.com/kfid/kfcd83e5896b9ba07be` 的访问链接
+- 「生成二维码」可拿到对应二维码
+
+把链接或二维码推给微信客户使用即可。
+
+## 三、CoW 配置（`config.json`）
+
+```json
+{
+  "channel_type": "wechat_kf",
+
+  "wechat_kf_corp_id": "ww1234567890abcdef",
+  "wechat_kf_secret": "<企微应用的 Secret>",
+  "wechat_kf_token": "<接收消息 Token>",
+  "wechat_kf_aes_key": "<EncodingAESKey>",
+  "wechat_kf_port": 9888
+}
+```
+
+| 字段 | 说明 |
+|---|---|
+| `wechat_kf_corp_id` | 企业 ID |
+| `wechat_kf_secret` | **绑定到微信客服**的那个企微自建应用的 Secret |
+| `wechat_kf_token` | 该应用「接收消息」配置的 Token |
+| `wechat_kf_aes_key` | 该应用「接收消息」配置的 EncodingAESKey |
+| `wechat_kf_port` | 监听端口，默认 `9888` |
+
+也支持环境变量：`WECHAT_KF_CORP_ID` / `WECHAT_KF_SECRET` / `WECHAT_KF_TOKEN` / `WECHAT_KF_AES_KEY`。
+
+## 四、运行
+
+```bash
+python app.py
+```
+
+启动后日志里会看到：
+
+```
+[wechat_kf] WeCom customer-service channel started
+[wechat_kf] Listening on http://0.0.0.0:9888/wxkf/
+```
+
+回到企微后台「设置API接收」点击保存——会触发 `GET /wxkf/?...&echostr=...`，CoW 通过 `crypto.check_signature` 校验后返回明文 `echostr`，验证成功。
+
+## 五、支持的回复类型
+
+| ReplyType | 是否支持 | 备注 |
+|---|---|---|
+| `TEXT` / `INFO` / `ERROR` | ✅ | 自动按 2048 字节切片分段发送 |
+| `IMAGE`（本地） / `IMAGE_URL`（网络） | ✅ | 大图自动压缩到 10MB 以内 |
+| `VOICE` | ✅ | 转 amr 后发送，>60s 自动切片 |
+| `VIDEO_URL` | ✅ | 通过临时素材接口上传 |
+| `FILE` | ✅ | |
+
+## 六、参考文档
+
+- [LinkAI 微信客服接入文档](https://docs.link-ai.tech/platform/link-app/wechat-customer-service)
+- [企业微信开放接口 - 微信客服 - 接收消息](https://developer.work.weixin.qq.com/document/path/94670)
+- [企业微信开放接口 - 微信客服 - 发送消息](https://developer.work.weixin.qq.com/document/path/95122)

channel/wechat_kf/wechat_kf_channel.py

@@ -0,0 +1,603 @@
+# -*- coding=utf-8 -*-
+"""
+WeChat Customer Service (微信客服) channel for CoW.
+
+Differences from `channel/wechatcom/` (企微自建应用):
+    1. Audience: external WeChat users (not internal members).
+    2. Receiver fields: `external_userid` + `open_kfid` instead of a single
+       member `userid`.
+    3. Inbound flow: callback only delivers an event token, the actual
+       message bodies must be pulled via `cgi-bin/kf/sync_msg` with a
+       persistent cursor. See `wechat_kf_cursor_store.py`.
+    4. Outbound flow: messages are sent via `cgi-bin/kf/send_msg` (each
+       request must specify both `touser` and `open_kfid`); wechatpy has
+       no native helper, so we call the HTTP endpoint directly.
+"""
+import io
+import json
+import os
+import threading
+import time
+import xml.etree.ElementTree as ET
+from collections import defaultdict
+from concurrent.futures import ThreadPoolExecutor
+from typing import Optional
+
+import requests
+import web
+from wechatpy.enterprise import WeChatClient
+from wechatpy.enterprise.crypto import WeChatCrypto
+from wechatpy.enterprise.exceptions import InvalidCorpIdException
+from wechatpy.exceptions import InvalidSignatureException, WeChatClientException
+
+from bridge.context import Context, ContextType
+from bridge.reply import Reply, ReplyType
+from channel.chat_channel import ChatChannel
+from channel.file_cache import get_file_cache
+from channel.wechat_kf.wechat_kf_cursor_store import CursorStore
+from channel.wechat_kf.wechat_kf_message import WechatKfMessage
+from common.log import logger
+from common.singleton import singleton
+from common.utils import (
+    compress_imgfile,
+    fsize,
+    remove_markdown_symbol,
+    split_string_by_utf8_length,
+)
+from config import conf
+
+try:
+    from voice.audio_convert import any_to_amr, split_audio
+except ImportError as e:  # voice features optional
+    logger.debug(
+        "[wechat_kf] import voice.audio_convert failed, voice will be disabled: {}".format(e)
+    )
+
+MAX_UTF8_LEN = 2048
+KF_API_BASE = "https://qyapi.weixin.qq.com/cgi-bin/kf"
+SYNC_MSG_LIMIT = 1000
+
+
+@singleton
+class WechatKfChannel(ChatChannel):
+    NOT_SUPPORT_REPLYTYPE = []
+
+    def __init__(self):
+        super().__init__()
+        self.corp_id = conf().get("wechat_kf_corp_id")
+        self.secret = conf().get("wechat_kf_secret")
+        self.token = conf().get("wechat_kf_token")
+        self.aes_key = conf().get("wechat_kf_aes_key")
+        self._http_server = None
+        logger.info(
+            "[wechat_kf] Initializing WeCom customer-service channel, corp_id: {}".format(
+                self.corp_id
+            )
+        )
+        self.crypto = WeChatCrypto(self.token, self.aes_key, self.corp_id)
+        # Use the stock wechatpy WeChatClient so that the access_token is
+        # cached and only refreshed when actually expired (~2h). The local
+        # `WechatComAppClient` subclass has a broken background refresh
+        # loop that re-fetches every 60s and a `fetch_access_token()`
+        # override that may return a dict instead of a string, which
+        # corrupts URLs and triggers errcode 40014.
+        self.client = WeChatClient(self.corp_id, self.secret)
+
+        # Persist sync_msg cursor under the user's home dir by default,
+        # so it survives `tmp/` cleanups and cwd changes across restarts.
+        cursor_path = os.path.expanduser(
+            conf().get("wechat_kf_cursor_path") or "~/.wechat_kf_cursors.json"
+        )
+        self.cursor_store = CursorStore(cursor_path)
+
+        # WeCom requires the callback HTTP response to return within ~5s,
+        # otherwise it retries the same notification. sync_msg pulling
+        # can easily exceed that, so we dispatch it to a background pool
+        # and let `Query.POST` reply success immediately.
+        self._callback_executor = ThreadPoolExecutor(
+            max_workers=4, thread_name_prefix="wxkf-cb"
+        )
+        # Per-open_kfid lock: serialize sync_msg for the same kf account
+        # so that callback retries (or rapid-fire events) don't race on
+        # the same cursor and produce duplicate replies.
+        self._kf_locks: dict = defaultdict(threading.Lock)
+        self._kf_locks_guard = threading.Lock()
+
+    # ------------------------------------------------------------------
+    # Lifecycle
+    # ------------------------------------------------------------------
+    def startup(self):
+        urls = ("/wxkf/?", "channel.wechat_kf.wechat_kf_channel.Query")
+        app = web.application(urls, globals(), autoreload=False)
+        port = conf().get("wechat_kf_port", 9888)
+        logger.info("[wechat_kf] WeCom customer-service channel started")
+        logger.info("[wechat_kf] Listening on http://0.0.0.0:{}/wxkf/".format(port))
+        func = web.httpserver.StaticMiddleware(app.wsgifunc())
+        func = web.httpserver.LogMiddleware(func)
+        server = web.httpserver.WSGIServer(("0.0.0.0", port), func)
+        self._http_server = server
+        try:
+            server.start()
+        except (KeyboardInterrupt, SystemExit):
+            server.stop()
+
+    def stop(self):
+        if self._http_server:
+            try:
+                self._http_server.stop()
+                logger.info("[wechat_kf] HTTP server stopped")
+            except Exception as e:
+                logger.warning(f"[wechat_kf] Error stopping HTTP server: {e}")
+            self._http_server = None
+        try:
+            self._callback_executor.shutdown(wait=False)
+        except Exception as e:
+            logger.warning(f"[wechat_kf] Error shutting down callback executor: {e}")
+
+    # ------------------------------------------------------------------
+    # Outbound — implementing the abstract `send` contract
+    # ------------------------------------------------------------------
+    def send(self, reply: Reply, context: Context):
+        receiver = context["receiver"]
+        msg = context.kwargs.get("msg")
+        external_userid = context.get("external_userid") or (msg.external_userid if msg else None)
+        open_kfid = context.get("open_kfid") or (msg.open_kfid if msg else None)
+
+        if not external_userid or not open_kfid:
+            logger.error(
+                "[wechat_kf] missing external_userid or open_kfid, cannot send: "
+                f"external_userid={external_userid}, open_kfid={open_kfid}"
+            )
+            return
+
+        if reply.type in [ReplyType.TEXT, ReplyType.ERROR, ReplyType.INFO]:
+            reply_text = remove_markdown_symbol(reply.content)
+            texts = split_string_by_utf8_length(reply_text, MAX_UTF8_LEN)
+            if len(texts) > 1:
+                logger.info(
+                    "[wechat_kf] text too long, split into {} parts".format(len(texts))
+                )
+            for i, text in enumerate(texts):
+                self._send_text(external_userid, open_kfid, text)
+                if i != len(texts) - 1:
+                    time.sleep(0.5)
+            logger.info("[wechat_kf] Do send text to {}: {}".format(receiver, reply_text))
+
+        elif reply.type == ReplyType.VOICE:
+            file_path = reply.content
+            try:
+                amr_file = os.path.splitext(file_path)[0] + ".amr"
+                any_to_amr(file_path, amr_file)
+                duration, files = split_audio(amr_file, 60 * 1000)
+                if len(files) > 1:
+                    logger.info(
+                        "[wechat_kf] voice too long {}s > 60s, split into {} parts".format(
+                            duration / 1000.0, len(files)
+                        )
+                    )
+                media_ids = []
+                for path in files:
+                    with open(path, "rb") as f:
+                        response = self.client.media.upload("voice", f)
+                    logger.debug("[wechat_kf] upload voice response: {}".format(response))
+                    media_ids.append(response["media_id"])
+            except ImportError as e:
+                logger.error("[wechat_kf] voice conversion failed: {}".format(e))
+                logger.error("[wechat_kf] please install pydub: pip install pydub")
+                return
+            except WeChatClientException as e:
+                logger.error("[wechat_kf] upload voice failed: {}".format(e))
+                return
+
+            try:
+                os.remove(file_path)
+                if amr_file != file_path:
+                    os.remove(amr_file)
+            except Exception:
+                pass
+
+            for media_id in media_ids:
+                self._send_voice(external_userid, open_kfid, media_id)
+                time.sleep(1)
+            logger.info("[wechat_kf] sendVoice={}, receiver={}".format(reply.content, receiver))
+
+        elif reply.type == ReplyType.IMAGE_URL:
+            img_url = reply.content
+            pic_res = requests.get(img_url, stream=True)
+            image_storage = io.BytesIO()
+            for block in pic_res.iter_content(1024):
+                image_storage.write(block)
+            sz = fsize(image_storage)
+            if sz >= 10 * 1024 * 1024:
+                logger.info("[wechat_kf] image too large, compressing, sz={}".format(sz))
+                image_storage = compress_imgfile(image_storage, 10 * 1024 * 1024 - 1)
+            image_storage.seek(0)
+            try:
+                response = self.client.media.upload("image", image_storage)
+            except WeChatClientException as e:
+                logger.error("[wechat_kf] upload image failed: {}".format(e))
+                return
+            self._send_image(external_userid, open_kfid, response["media_id"])
+            logger.info("[wechat_kf] sendImage url={}, receiver={}".format(img_url, receiver))
+
+        elif reply.type == ReplyType.IMAGE:
+            image_storage = reply.content
+            sz = fsize(image_storage)
+            if sz >= 10 * 1024 * 1024:
+                logger.info("[wechat_kf] image too large, compressing, sz={}".format(sz))
+                image_storage = compress_imgfile(image_storage, 10 * 1024 * 1024 - 1)
+            image_storage.seek(0)
+            try:
+                response = self.client.media.upload("image", image_storage)
+            except WeChatClientException as e:
+                logger.error("[wechat_kf] upload image failed: {}".format(e))
+                return
+            self._send_image(external_userid, open_kfid, response["media_id"])
+            logger.info("[wechat_kf] sendImage, receiver={}".format(receiver))
+
+        elif reply.type == ReplyType.VIDEO_URL:
+            video_url = reply.content
+            try:
+                response = self.client.media.upload(
+                    "video", requests.get(video_url, stream=True).content
+                )
+            except WeChatClientException as e:
+                logger.error("[wechat_kf] upload video failed: {}".format(e))
+                return
+            self._send_video(external_userid, open_kfid, response["media_id"])
+            logger.info("[wechat_kf] sendVideo url={}, receiver={}".format(video_url, receiver))
+
+        elif reply.type == ReplyType.FILE:
+            file_path = reply.content
+            try:
+                with open(file_path, "rb") as f:
+                    response = self.client.media.upload(
+                        "file", (os.path.basename(file_path), f.read())
+                    )
+            except WeChatClientException as e:
+                logger.error("[wechat_kf] upload file failed: {}".format(e))
+                return
+            self._send_file(external_userid, open_kfid, response["media_id"])
+            logger.info("[wechat_kf] sendFile={}, receiver={}".format(file_path, receiver))
+
+        else:
+            logger.warning("[wechat_kf] unsupported reply type: {}".format(reply.type))
+
+    # ------------------------------------------------------------------
+    # Inbound — pull messages by cursor
+    # ------------------------------------------------------------------
+    def _get_kf_lock(self, open_kfid: str) -> threading.Lock:
+        with self._kf_locks_guard:
+            return self._kf_locks[open_kfid]
+
+    def submit_callback(self, token: str, open_kfid: str):
+        """
+        Async entry point used by the HTTP handler. Submits the actual
+        sync_msg pulling to a background thread so the callback response
+        can return within WeCom's 5s deadline.
+        """
+        try:
+            self._callback_executor.submit(self._run_callback, token, open_kfid)
+        except RuntimeError as e:
+            # Executor may be shut down during process exit; fall back
+            # to inline execution so we don't silently drop the event.
+            logger.warning(f"[wechat_kf] executor unavailable, run inline: {e}")
+            self._run_callback(token, open_kfid)
+
+    def _run_callback(self, token: str, open_kfid: str):
+        # Block on the per-kfid lock so retried callbacks queue up
+        # behind the in-flight one. The queued worker will then call
+        # sync_msg with the (already advanced) cursor, which is cheap
+        # when there is nothing new and still picks up any messages
+        # that arrived after the previous worker's last pull.
+        lock = self._get_kf_lock(open_kfid)
+        with lock:
+            try:
+                self.consume_callback(token, open_kfid)
+            except Exception as e:
+                logger.exception(f"[wechat_kf] consume_callback error: {e}")
+
+    def consume_callback(self, token: str, open_kfid: str):
+        """
+        Called from the HTTP `Query.POST` handler whenever WeCom notifies
+        us that there are new messages for `open_kfid`. Pulls all new
+        messages via sync_msg and feeds them into `produce()`.
+        """
+        existing_cursor = self.cursor_store.get(open_kfid)
+
+        # First-time bootstrap: always skip history, otherwise WeCom would
+        # replay up to 14 days of messages on the very first callback and
+        # flood every user with auto-replies.
+        if not existing_cursor:
+            self._initialize_cursor(token, open_kfid)
+            return
+
+        msgs = self._pull_messages(token, open_kfid, existing_cursor)
+        if not msgs:
+            return
+        file_cache = get_file_cache()
+        for raw in msgs:
+            try:
+                kf_msg = WechatKfMessage(msg=raw, client=self.client)
+            except NotImplementedError as e:
+                logger.debug("[wechat_kf] {}".format(e))
+                continue
+
+            session_id = kf_msg.from_user_id
+
+            # Cache lone images/files and wait for the user's follow-up
+            # text. Agent mode never reads memory.USER_IMAGE_CACHE, so
+            # without this the attachment is effectively lost.
+            if kf_msg.ctype in (ContextType.IMAGE, ContextType.FILE):
+                ftype = "image" if kf_msg.ctype == ContextType.IMAGE else "file"
+                try:
+                    kf_msg.prepare()  # download to local tmp path
+                    file_cache.add(session_id, kf_msg.content, file_type=ftype)
+                    logger.info(
+                        "[wechat_kf] {} cached for session {}: {}".format(
+                            ftype, session_id, kf_msg.content
+                        )
+                    )
+                except Exception as e:
+                    logger.warning(f"[wechat_kf] cache {ftype} failed: {e}")
+                continue
+
+            # On a text turn, attach any pending images/files as references
+            # so the downstream agent can pick them up via the text content.
+            # Paths are already under agent_workspace/tmp (see
+            # WechatKfMessage._get_tmp_dir), so a relative ref also works.
+            if kf_msg.ctype == ContextType.TEXT:
+                cached_files = file_cache.get(session_id)
+                if cached_files:
+                    refs = []
+                    for fi in cached_files:
+                        ftype, fpath = fi["type"], fi["path"]
+                        if ftype == "image":
+                            refs.append(f"[图片: {fpath}]")
+                        else:
+                            refs.append(f"[文件: {fpath}]")
+                    kf_msg.content = kf_msg.content + "\n" + "\n".join(refs)
+                    file_cache.clear(session_id)
+
+            context = self._compose_context(
+                kf_msg.ctype,
+                kf_msg.content,
+                isgroup=False,
+                msg=kf_msg,
+            )
+            if context:
+                self.produce(context)
+            time.sleep(0.05)  # tiny gap between messages of the same batch
+
+    def _initialize_cursor(self, token: str, open_kfid: str):
+        """
+        Drain all current messages for this `open_kfid` without producing
+        any context, just to advance the cursor to "now". This prevents
+        a fresh deployment from replying to up to ~14 days of history.
+        """
+        next_cursor = ""
+        total_skipped = 0
+        while True:
+            data = self._call_sync_msg(token, open_kfid, next_cursor)
+            if data is None:
+                break
+            msg_list = data.get("msg_list") or []
+            total_skipped += len(msg_list)
+            cursor_after = data.get("next_cursor") or ""
+            if cursor_after:
+                self.cursor_store.set(open_kfid, cursor_after)
+            if not data.get("has_more"):
+                break
+            if not cursor_after or cursor_after == next_cursor:
+                break
+            next_cursor = cursor_after
+        logger.info(
+            "[wechat_kf] first-start bootstrap finished for open_kfid={}, "
+            "skipped {} historical messages".format(open_kfid, total_skipped)
+        )
+
+    def _pull_messages(self, token: str, open_kfid: str, next_cursor: Optional[str]) -> list:
+        """Loop sync_msg until `has_more` is false. Returns raw msg dicts."""
+        collected = []
+        cursor = next_cursor or ""
+        while True:
+            data = self._call_sync_msg(token, open_kfid, cursor)
+            if data is None:
+                break
+            for item in data.get("msg_list") or []:
+                # Only consume messages from external users; ignore replies
+                # generated by our own kf account, otherwise we would loop
+                # back into ourselves.
+                if not item.get("external_userid"):
+                    continue
+                if item.get("msgtype") in ("text", "image", "voice", "file"):
+                    collected.append(item)
+            cursor_after = data.get("next_cursor") or ""
+            if cursor_after:
+                self.cursor_store.set(open_kfid, cursor_after)
+            if not data.get("has_more"):
+                break
+            if not cursor_after or cursor_after == cursor:
+                break
+            cursor = cursor_after
+
+        if collected:
+            collected = _dedup_image_text_pair(collected)
+        logger.info(
+            "[wechat_kf] pulled {} messages for open_kfid={}".format(len(collected), open_kfid)
+        )
+        return collected
+
+    def _call_sync_msg(self, token: str, open_kfid: str, cursor: str) -> Optional[dict]:
+        # `client.access_token` is the cached string property; do not use
+        # `fetch_access_token()` here — wechatpy returns the raw response
+        # dict from that call, which corrupts the query string.
+        url = f"{KF_API_BASE}/sync_msg?access_token={self.client.access_token}"
+        payload = {
+            "token": token,
+            "open_kfid": open_kfid,
+            "limit": SYNC_MSG_LIMIT,
+        }
+        if cursor:
+            payload["cursor"] = cursor
+        try:
+            resp = requests.post(url, json=payload, timeout=10).json()
+        except Exception as e:
+            logger.error(f"[wechat_kf] sync_msg request failed: {e}")
+            return None
+
+        if resp.get("errcode") != 0:
+            logger.error(
+                f"[wechat_kf] sync_msg errcode={resp.get('errcode')}, "
+                f"errmsg={resp.get('errmsg')}, open_kfid={open_kfid}"
+            )
+            return None
+        return resp
+
+    # ------------------------------------------------------------------
+    # Outbound HTTP wrappers (kf/send_msg)
+    # ------------------------------------------------------------------
+    def _post_send_msg(self, payload: dict) -> dict:
+        url = f"{KF_API_BASE}/send_msg?access_token={self.client.access_token}"
+        try:
+            resp = requests.post(url, json=payload, timeout=10).json()
+        except Exception as e:
+            logger.error(f"[wechat_kf] send_msg request failed: {e}")
+            return {"errcode": -1, "errmsg": str(e)}
+        if resp.get("errcode") != 0:
+            logger.error(f"[wechat_kf] send_msg failed, payload={payload}, resp={resp}")
+        return resp
+
+    def _send_text(self, external_userid: str, open_kfid: str, content: str) -> dict:
+        return self._post_send_msg({
+            "touser": external_userid,
+            "open_kfid": open_kfid,
+            "msgtype": "text",
+            "text": {"content": content},
+        })
+
+    def _send_image(self, external_userid: str, open_kfid: str, media_id: str) -> dict:
+        return self._post_send_msg({
+            "touser": external_userid,
+            "open_kfid": open_kfid,
+            "msgtype": "image",
+            "image": {"media_id": media_id},
+        })
+
+    def _send_voice(self, external_userid: str, open_kfid: str, media_id: str) -> dict:
+        return self._post_send_msg({
+            "touser": external_userid,
+            "open_kfid": open_kfid,
+            "msgtype": "voice",
+            "voice": {"media_id": media_id},
+        })
+
+    def _send_video(self, external_userid: str, open_kfid: str, media_id: str) -> dict:
+        return self._post_send_msg({
+            "touser": external_userid,
+            "open_kfid": open_kfid,
+            "msgtype": "video",
+            "video": {"media_id": media_id},
+        })
+
+    def _send_file(self, external_userid: str, open_kfid: str, media_id: str) -> dict:
+        return self._post_send_msg({
+            "touser": external_userid,
+            "open_kfid": open_kfid,
+            "msgtype": "file",
+            "file": {"media_id": media_id},
+        })
+
+    def _send_link(self, external_userid: str, open_kfid: str, link_data: dict) -> dict:
+        return self._post_send_msg({
+            "touser": external_userid,
+            "open_kfid": open_kfid,
+            "msgtype": "link",
+            "link": link_data,
+        })
+
+
+def _dedup_image_text_pair(messages: list) -> list:
+    """
+    A WeChat user often sends an image immediately followed by a text
+    question (e.g. "what's in this picture?"). Only when the batch is
+    exactly that 2-message image+text pair within a 5s window do we
+    collapse it into a single [image, text] turn. Otherwise return
+    every message so rapid-fire texts/images are all processed —
+    cursor freshness is already guaranteed by sync_msg.
+    """
+    if not messages:
+        return []
+
+    if len(messages) == 2:
+        a, b = messages
+        types = {a["msgtype"], b["msgtype"]}
+        if types == {"image", "text"} and abs(a["send_time"] - b["send_time"]) <= 5:
+            img = a if a["msgtype"] == "image" else b
+            txt = b if a["msgtype"] == "image" else a
+            return [img, txt]
+
+    return messages
+
+
+# ----------------------------------------------------------------------
+# HTTP handlers (web.py)
+# ----------------------------------------------------------------------
+class Query:
+    def GET(self):
+        channel = WechatKfChannel()
+        params = web.input()
+        logger.info("[wechat_kf] verify params: {}".format(params))
+        try:
+            signature = params.msg_signature
+            timestamp = params.timestamp
+            nonce = params.nonce
+            echostr = params.echostr
+            echostr = channel.crypto.check_signature(signature, timestamp, nonce, echostr)
+        except (InvalidSignatureException, InvalidCorpIdException):
+            raise web.Forbidden()
+        return echostr
+
+    def POST(self):
+        channel = WechatKfChannel()
+        params = web.input()
+        try:
+            signature = params.msg_signature
+            timestamp = params.timestamp
+            nonce = params.nonce
+            raw_body = web.data()
+            decrypted = channel.crypto.decrypt_message(raw_body, signature, timestamp, nonce)
+        except (InvalidSignatureException, InvalidCorpIdException) as e:
+            logger.warning(f"[wechat_kf] invalid signature: {e}")
+            raise web.Forbidden()
+
+        # We need the Token + OpenKfId fields from the inner XML to call
+        # sync_msg. wechatpy's parsed object exposes neither, so we parse
+        # the raw XML directly.
+        try:
+            root = ET.fromstring(decrypted)
+        except ET.ParseError as e:
+            logger.error(f"[wechat_kf] xml parse error: {e}")
+            return "success"
+
+        msg_type = (root.findtext("MsgType") or "").strip()
+        event = (root.findtext("Event") or "").strip()
+        if msg_type != "event" or event != "kf_msg_or_event":
+            logger.debug(
+                f"[wechat_kf] ignored callback msg_type={msg_type}, event={event}"
+            )
+            return "success"
+
+        token = root.findtext("Token") or ""
+        open_kfid = root.findtext("OpenKfId") or ""
+        if not token or not open_kfid:
+            logger.warning(
+                f"[wechat_kf] callback missing token or open_kfid: {decrypted}"
+            )
+            return "success"
+
+        # Hand off to a background worker — WeCom requires the callback
+        # to return success within ~5 seconds, otherwise it will retry
+        # and we may race the same cursor window into duplicate replies.
+        channel.submit_callback(token, open_kfid)
+        return "success"

channel/wechat_kf/wechat_kf_cursor_store.py

@@ -0,0 +1,80 @@
+# -*- coding=utf-8 -*-
+"""
+Local-file based persistence for WeCom customer-service `next_cursor`.
+
+Why we need this:
+    The WeCom customer-service (微信客服) callback only notifies us that
+    "new messages exist". To actually fetch them we must call the
+    `cgi-bin/kf/sync_msg` endpoint with a `cursor` so that we only get
+    messages newer than the previously processed one. If we lose this
+    cursor (e.g. on process restart) WeCom will replay up to ~14 days of
+    history, which would cause the bot to flood users with duplicate
+    replies.
+
+This implementation deliberately avoids any external dependency
+(no Redis / no DB) — a single JSON file under the project's tmp dir is
+enough for a CoW-style single-process deployment.
+"""
+import json
+import os
+import threading
+from typing import Optional
+
+from common.log import logger
+
+
+class CursorStore:
+    """Thread-safe per-`open_kfid` cursor store backed by a JSON file."""
+
+    def __init__(self, file_path: str):
+        self._file_path = file_path
+        self._lock = threading.Lock()
+        self._data = self._load()
+
+    def _load(self) -> dict:
+        try:
+            if os.path.exists(self._file_path):
+                with open(self._file_path, "r", encoding="utf-8") as f:
+                    return json.load(f) or {}
+        except Exception as e:
+            logger.warning(f"[wechat_kf] failed to load cursor file {self._file_path}: {e}")
+        return {}
+
+    def _flush_locked(self):
+        # Atomic write: write to *.tmp first then rename, avoid corruption on crash.
+        tmp_path = self._file_path + ".tmp"
+        try:
+            os.makedirs(os.path.dirname(self._file_path) or ".", exist_ok=True)
+            with open(tmp_path, "w", encoding="utf-8") as f:
+                json.dump(self._data, f, ensure_ascii=False)
+            os.replace(tmp_path, self._file_path)
+            # Tighten permissions: cursor file lives in $HOME, restrict to owner.
+            # No-op on Windows.
+            try:
+                os.chmod(self._file_path, 0o600)
+            except Exception:
+                pass
+        except Exception as e:
+            logger.warning(f"[wechat_kf] failed to flush cursor file {self._file_path}: {e}")
+            try:
+                if os.path.exists(tmp_path):
+                    os.remove(tmp_path)
+            except Exception:
+                pass
+
+    def get(self, open_kfid: str) -> Optional[str]:
+        with self._lock:
+            return self._data.get(open_kfid)
+
+    def set(self, open_kfid: str, cursor: str):
+        if not cursor:
+            return
+        with self._lock:
+            if self._data.get(open_kfid) == cursor:
+                return
+            self._data[open_kfid] = cursor
+            self._flush_locked()
+
+    def has(self, open_kfid: str) -> bool:
+        with self._lock:
+            return open_kfid in self._data

channel/wechat_kf/wechat_kf_message.py

@@ -0,0 +1,134 @@
+# -*- coding=utf-8 -*-
+"""
+Adapter that turns a single `sync_msg` item from WeCom customer-service
+into a CoW `ChatMessage` object.
+"""
+import os
+import re
+
+from wechatpy.enterprise import WeChatClient
+
+from bridge.context import ContextType
+from channel.chat_message import ChatMessage
+from common.log import logger
+from common.utils import expand_path
+from config import conf
+
+
+def _get_tmp_dir() -> str:
+    """Save under agent_workspace/tmp/ so agent tools (e.g. `read`) can
+    resolve a relative path like `tmp/xxx.pdf` against their own
+    workspace root. Mirrors the convention used by weixin / wecom_bot.
+    """
+    ws_root = expand_path(conf().get("agent_workspace", "~/cow"))
+    tmp_dir = os.path.join(ws_root, "tmp")
+    os.makedirs(tmp_dir, exist_ok=True)
+    return tmp_dir
+
+
+def _extract_filename(content_disposition: str) -> str:
+    """Best-effort parse of `filename` / `filename*` from a Content-Disposition
+    header. Returns '' when nothing usable is found."""
+    if not content_disposition:
+        return ""
+    # RFC 5987 form: filename*=UTF-8''xxx
+    m = re.search(r"filename\*=(?:[^'\"]*'[^']*'\s*)?([^;]+)", content_disposition)
+    if m:
+        try:
+            from urllib.parse import unquote
+            return unquote(m.group(1).strip().strip('"'))
+        except Exception:
+            return m.group(1).strip().strip('"')
+    m = re.search(r'filename\s*=\s*"?([^";]+)"?', content_disposition)
+    return m.group(1).strip() if m else ""
+
+
+class WechatKfMessage(ChatMessage):
+    """
+    msg structure (from cgi-bin/kf/sync_msg):
+        {
+          "msgid": "...",
+          "send_time": 1700000000,
+          "origin": 3,
+          "msgtype": "text" | "image" | "voice" | ...,
+          "open_kfid": "wkxxxx",
+          "external_userid": "wmxxxx",
+          "text": {"content": "..."},
+          "image": {"media_id": "..."},
+          "voice": {"media_id": "..."},
+          ...
+        }
+    """
+
+    def __init__(self, msg: dict, client: WeChatClient = None, is_group: bool = False):
+        # NOTE: skip parent constructor because it expects a wechatpy parsed
+        # message object, while here we receive a raw dict from sync_msg.
+        super().__init__(msg)
+        self.is_group = is_group
+        self.msg_id = msg.get("msgid")
+        self.create_time = msg.get("send_time")
+        self.origin = msg.get("origin")
+        self.msgtype = msg.get("msgtype")
+        self.open_kfid = msg.get("open_kfid")
+        self.external_userid = msg.get("external_userid")
+
+        if self.msgtype == "text":
+            self.ctype = ContextType.TEXT
+            self.content = msg.get("text", {}).get("content", "")
+        elif self.msgtype == "image":
+            self.ctype = ContextType.IMAGE
+            media_id = msg.get("image", {}).get("media_id", "")
+            self.content = os.path.join(_get_tmp_dir(), media_id + ".jpg")
+
+            def download_image():
+                response = client.media.download(media_id)
+                if response.status_code == 200:
+                    with open(self.content, "wb") as f:
+                        f.write(response.content)
+                else:
+                    logger.info(f"[wechat_kf] Failed to download image, {response.content}")
+
+            self._prepare_fn = download_image
+        elif self.msgtype == "voice":
+            self.ctype = ContextType.VOICE
+            media_id = msg.get("voice", {}).get("media_id", "")
+            # WeCom returns amr by default; downstream voice pipeline will convert.
+            self.content = os.path.join(_get_tmp_dir(), media_id + ".amr")
+
+            def download_voice():
+                response = client.media.download(media_id)
+                if response.status_code == 200:
+                    with open(self.content, "wb") as f:
+                        f.write(response.content)
+                else:
+                    logger.info(f"[wechat_kf] Failed to download voice, {response.content}")
+
+            self._prepare_fn = download_voice
+        elif self.msgtype == "file":
+            self.ctype = ContextType.FILE
+            media_id = msg.get("file", {}).get("media_id", "")
+            # Provisional path; rewritten in download_file() once we have
+            # the original filename from Content-Disposition.
+            self.content = os.path.join(_get_tmp_dir(), media_id)
+
+            def download_file():
+                response = client.media.download(media_id)
+                if response.status_code == 200:
+                    filename = _extract_filename(
+                        response.headers.get("Content-Disposition", "")
+                    ) or media_id
+                    self.content = os.path.join(_get_tmp_dir(), filename)
+                    with open(self.content, "wb") as f:
+                        f.write(response.content)
+                else:
+                    logger.info(f"[wechat_kf] Failed to download file, {response.content}")
+
+            self._prepare_fn = download_file
+        else:
+            raise NotImplementedError(
+                f"[wechat_kf] Unsupported message type: {self.msgtype}"
+            )
+
+        self.from_user_id = self.external_userid
+        self.to_user_id = self.open_kfid
+        self.other_user_id = self.external_userid

channel/wechatmp/common.py

@@ -19,9 +19,15 @@ def verify_server(data):
         nonce = data.nonce
         echostr = data.get("echostr", None)
         token = conf().get("wechatmp_token")  # 请按照公众平台官网\基本配置中信息填写
+        # Reject when token is empty: an empty token reduces signature verification
+        # to a predictable hash over attacker-controlled values.
+        if not token:
+            raise web.Forbidden("wechatmp_token is not configured")
         check_signature(token, signature, timestamp, nonce)
         return echostr
     except InvalidSignatureException:
         raise web.Forbidden("Invalid signature")
+    except web.Forbidden:
+        raise
     except Exception as e:
         raise web.Forbidden(str(e))

channel/wechatmp/passive_reply.py

@@ -103,14 +103,21 @@ class Query:
                 task_running = True
                 waiting_until = request_time + 4
                 while time.time() < waiting_until:
-                    if from_user in channel.running:
-                        time.sleep(0.1)
-                    else:
+                    if from_user not in channel.running:
                         task_running = False
                         break
+                    # Task still running, but if it has already produced cached
+                    # segments (e.g. multi-turn thinking output), return them now
+                    # instead of forcing the user to wait for the whole task. The
+                    # remaining segments are fetched by the user's next message.
+                    if channel.cache_dict.get(from_user):
+                        break
+                    time.sleep(0.1)
 
                 reply_text = ""
-                if task_running:
+                # Only fall back to retry / "thinking" hint when the task is still
+                # running AND there is nothing cached to send yet.
+                if task_running and not channel.cache_dict.get(from_user):
                     if request_cnt < 3:
                         # waiting for timeout (the POST request will be closed by Wechat official server)
                         time.sleep(2)
@@ -131,8 +138,22 @@ class Query:
 
                 # Only one request can access to the cached data
                 try:
-                    (reply_type, reply_content) = channel.cache_dict[from_user].pop(0)
-                    if not channel.cache_dict[from_user]:  # If popping the message makes the list empty, delete the user entry from cache
+                    # WeChat passive reply allows only a single reply per request.
+                    # To avoid forcing the user to send an extra message for every
+                    # segment of multi-turn agent output, drain all consecutive
+                    # cached text segments at once and merge them into one reply.
+                    # Media (voice/image) can only be returned one at a time, so it
+                    # stops the merge and is returned on its own.
+                    cached = channel.cache_dict[from_user]
+                    if cached[0][0] == "text":
+                        reply_type = "text"
+                        merged_parts = []
+                        while cached and cached[0][0] == "text":
+                            merged_parts.append(cached.pop(0)[1])
+                        reply_content = "\n\n".join(merged_parts)
+                    else:
+                        (reply_type, reply_content) = cached.pop(0)
+                    if not channel.cache_dict[from_user]:  # If draining empties the list, delete the user entry from cache
                         del channel.cache_dict[from_user]
                 except IndexError:
                     return "success"

channel/wechatmp/wechatmp_channel.py

@@ -134,10 +134,16 @@ class WechatMPChannel(ChatChannel):
 
             elif reply.type == ReplyType.IMAGE_URL:  # 从网络下载图片
                 img_url = reply.content
-                pic_res = requests.get(img_url, stream=True)
                 image_storage = io.BytesIO()
-                for block in pic_res.iter_content(1024):
-                    image_storage.write(block)
+                if img_url.startswith("file://") or os.path.isfile(img_url):
+                    # Local file produced by the agent (e.g. a generated image)
+                    local_path = img_url[len("file://"):] if img_url.startswith("file://") else img_url
+                    with open(local_path, "rb") as f:
+                        image_storage.write(f.read())
+                else:
+                    pic_res = requests.get(img_url, stream=True)
+                    for block in pic_res.iter_content(1024):
+                        image_storage.write(block)
                 image_storage.seek(0)
                 image_type = imghdr.what(image_storage)
                 filename = receiver + "-" + str(context["msg"].msg_id) + "." + image_type
@@ -258,10 +264,16 @@ class WechatMPChannel(ChatChannel):
                 logger.info("[wechatmp] Do send voice to {}".format(receiver))
             elif reply.type == ReplyType.IMAGE_URL:  # 从网络下载图片
                 img_url = reply.content
-                pic_res = requests.get(img_url, stream=True)
                 image_storage = io.BytesIO()
-                for block in pic_res.iter_content(1024):
-                    image_storage.write(block)
+                if img_url.startswith("file://") or os.path.isfile(img_url):
+                    # Local file produced by the agent (e.g. a generated image)
+                    local_path = img_url[len("file://"):] if img_url.startswith("file://") else img_url
+                    with open(local_path, "rb") as f:
+                        image_storage.write(f.read())
+                else:
+                    pic_res = requests.get(img_url, stream=True)
+                    for block in pic_res.iter_content(1024):
+                        image_storage.write(block)
                 image_storage.seek(0)
                 image_type = imghdr.what(image_storage)
                 filename = receiver + "-" + str(context["msg"].msg_id) + "." + image_type

channel/wecom_bot/wecom_bot_channel.py

@@ -12,16 +12,19 @@ import hashlib
 import json
 import math
 import os
+import re
 import threading
 import time
 import uuid
 
 import requests
+import web
 import websocket
 
 from bridge.context import Context, ContextType
 from bridge.reply import Reply, ReplyType
 from channel.chat_channel import ChatChannel, check_prefix
+from channel.wecom_bot.wecom_bot_crypt import WecomBotCrypt
 from channel.wecom_bot.wecom_bot_message import WecomBotMessage
 from common.expired_dict import ExpiredDict
 from common.log import logger
@@ -32,6 +35,9 @@ from config import conf
 WECOM_WS_URL = "wss://openws.work.weixin.qq.com"
 HEARTBEAT_INTERVAL = 30
 MEDIA_CHUNK_SIZE = 512 * 1024  # 512KB per chunk (before base64 encoding)
+# Fixed URL path for the callback (webhook) HTTP server. The bot's
+# receive-message URL must point at this path, e.g. http://host:9892/wecombot
+CALLBACK_PATH = "/wecombot"
 
 
 def _escape_control_chars_inside_json_strings(s: str) -> str:
@@ -97,6 +103,14 @@ class WecomBotChannel(ChatChannel):
         self._pending_lock = threading.Lock()
         self._stream_states = {}  # req_id -> {"stream_id": str, "content": str}
 
+        # Transport mode: "websocket" (long connection) or "webhook" (HTTP callback)
+        self.mode = "websocket"
+        self._crypt = None
+        self._http_server = None
+        # stream_id -> {"committed", "current", "finished", "images", "last_access"}
+        self._callback_streams = ExpiredDict(60 * 10)  # auto-expire after 10min (max poll window is 6min)
+        self._callback_lock = threading.Lock()
+
         conf()["group_name_white_list"] = ["ALL_GROUP"]
         conf()["single_chat_prefix"] = [""]
 
@@ -105,6 +119,11 @@ class WecomBotChannel(ChatChannel):
     # ------------------------------------------------------------------
 
     def startup(self):
+        self.mode = conf().get("wecom_bot_mode", "websocket")
+        if self.mode == "webhook":
+            self._startup_callback()
+            return
+
         self.bot_id = conf().get("wecom_bot_id", "")
         self.bot_secret = conf().get("wecom_bot_secret", "")
 
@@ -127,6 +146,13 @@ class WecomBotChannel(ChatChannel):
                 pass
         self._ws = None
         self._connected = False
+        if self._http_server:
+            try:
+                self._http_server.stop()
+                logger.info("[WecomBot] Callback HTTP server stopped")
+            except Exception as e:
+                logger.warning(f"[WecomBot] Error stopping HTTP server: {e}")
+            self._http_server = None
 
     # ------------------------------------------------------------------
     # WebSocket connection
@@ -183,6 +209,192 @@ class WecomBotChannel(ChatChannel):
     def _gen_req_id(self) -> str:
         return uuid.uuid4().hex[:16]
 
+    # ------------------------------------------------------------------
+    # Callback (webhook) mode
+    # ------------------------------------------------------------------
+
+    def _startup_callback(self):
+        """Start an HTTP server that receives encrypted callbacks (webhook mode).
+
+        The bot's "接收消息" URL in the WeCom admin console should point at this
+        server (any path is accepted). Verification (GET) and message delivery
+        (POST) are both handled by ``WecomBotCallbackController``.
+        """
+        token = conf().get("wecom_bot_token", "")
+        aes_key = conf().get("wecom_bot_encoding_aes_key", "")
+        if not token or not aes_key:
+            err = "[WecomBot] callback mode requires wecom_bot_token and wecom_bot_encoding_aes_key"
+            logger.error(err)
+            self.report_startup_error(err)
+            return
+
+        try:
+            # Enterprise-internal smart bot: receive_id is an empty string.
+            self._crypt = WecomBotCrypt(token, aes_key, "")
+        except Exception as e:
+            err = f"[WecomBot] invalid callback credentials: {e}"
+            logger.error(err)
+            self.report_startup_error(err)
+            return
+
+        port = int(conf().get("wecom_bot_port", 9892))
+        logger.info(f"[WecomBot] Starting callback (webhook) server on port {port}, path {CALLBACK_PATH} ...")
+        # Only serve the fixed callback path; everything else 404s instead of being
+        # treated as a (signature-failing) WeCom callback.
+        urls = (re.escape(CALLBACK_PATH), "channel.wecom_bot.wecom_bot_channel.WecomBotCallbackController")
+        app = web.application(urls, globals(), autoreload=False)
+        func = web.httpserver.StaticMiddleware(app.wsgifunc())
+        func = web.httpserver.LogMiddleware(func)
+        server = web.httpserver.WSGIServer(("0.0.0.0", port), func)
+        self._http_server = server
+        self.report_startup_success()
+        try:
+            server.start()
+        except (KeyboardInterrupt, SystemExit):
+            server.stop()
+
+    def _new_callback_stream(self, response_url: str = "") -> str:
+        """Create a new stream state and return its id."""
+        stream_id = uuid.uuid4().hex[:16]
+        now = time.time()
+        with self._callback_lock:
+            self._callback_streams[stream_id] = {
+                "committed": "",
+                "current": "",
+                "finished": False,
+                "images": [],  # list of (base64_str, md5_str), flushed only at finish
+                "image_urls": [],  # public http(s) image urls (usable in response_url markdown)
+                "image_pending": False,  # an image reply is being prepared; don't finish on text yet
+                "last_access": now,
+                "created_at": now,
+                "response_url": response_url or "",
+                "delivered": False,  # final answer handed to WeCom via a poll
+                "url_sent": False,   # final answer pushed via response_url (active reply)
+            }
+        return stream_id
+
+    def _callback_handle_message(self, data: dict) -> dict:
+        """Handle a freshly-received user message in callback mode.
+
+        Produces the context for async processing and returns the initial passive
+        reply (a stream packet with finish=false) so WeCom starts polling for the
+        agent's streamed answer. Returns ``None`` when there's nothing to reply
+        (e.g. an image/file silently cached for the next query).
+        """
+        msg_id = data.get("msgid", "")
+        if msg_id and self.received_msgs.get(msg_id):
+            logger.debug(f"[WecomBot] Duplicate msg filtered: {msg_id}")
+            return None
+        if msg_id:
+            self.received_msgs[msg_id] = True
+
+        chattype = data.get("chattype", "single")
+        is_group = chattype == "group"
+
+        default_aeskey = conf().get("wecom_bot_encoding_aes_key", "")
+        result = self._build_context(data, is_group, default_aeskey=default_aeskey)
+        if not result:
+            return None
+        context, wecom_msg = result
+
+        # response_url lets us actively reply once within 1h, used as a fallback
+        # when the agent finishes after WeCom stops polling (max ~6min window).
+        response_url = data.get("response_url", "") or ""
+        stream_id = self._new_callback_stream(response_url=response_url)
+        wecom_msg.stream_id = stream_id
+        context["wecom_stream_id"] = stream_id
+        context["on_event"] = self._make_callback_stream_callback(stream_id)
+        self.produce(context)
+
+        # First passive reply: register the stream id, WeCom will poll for updates.
+        return {
+            "msgtype": "stream",
+            "stream": {"id": stream_id, "finish": False, "content": ""},
+        }
+
+    def _callback_handle_stream_poll(self, data: dict) -> dict:
+        """Handle a "流式消息刷新" poll: return the latest accumulated content."""
+        stream_id = data.get("stream", {}).get("id", "")
+        with self._callback_lock:
+            state = self._callback_streams.get(stream_id)
+            if state is None:
+                # Unknown / expired stream: tell WeCom we're done to stop polling.
+                return {"msgtype": "stream", "stream": {"id": stream_id, "finish": True, "content": ""}}
+            state["last_access"] = time.time()
+            if state.get("url_sent"):
+                # Final answer already pushed via response_url; finish silently.
+                return {"msgtype": "stream", "stream": {"id": stream_id, "finish": True, "content": ""}}
+            # We never force-finish on a timer: while a task is still running the
+            # bubble should keep spinning until either the task finishes or the
+            # user cancels. If WeCom's 6min window closes before completion, the
+            # answer is delivered later via response_url instead.
+            finished = state["finished"]
+            content = state["committed"] + state["current"]
+            images = state["images"] if finished else []
+            if finished:
+                state["delivered"] = True
+                logger.debug(f"[WecomBot] stream {stream_id} delivered via poll, len={len(content)}, images={len(images)}")
+
+        stream = {"id": stream_id, "finish": finished, "content": content}
+        if images:
+            stream["msg_item"] = [
+                {"msgtype": "image", "image": {"base64": b64, "md5": md5}}
+                for (b64, md5) in images
+            ]
+        return {"msgtype": "stream", "stream": stream}
+
+    def _make_callback_stream_callback(self, stream_id: str):
+        """Build an on_event callback that accumulates agent output into stream state.
+
+        Mirrors the websocket streaming behaviour: intermediate turns (text before
+        a tool call) are committed with a '---' separator; WeCom reads the full
+        accumulated content on each poll.
+        """
+        def on_event(event: dict):
+            event_type = event.get("type")
+            edata = event.get("data", {})
+            cancelled = False
+            with self._callback_lock:
+                state = self._callback_streams.get(stream_id)
+                if not state:
+                    return
+
+                if event_type == "turn_start":
+                    state["current"] = ""
+                elif event_type == "message_update":
+                    delta = edata.get("delta", "")
+                    if delta:
+                        state["current"] += delta
+                elif event_type == "message_end":
+                    tool_calls = edata.get("tool_calls", [])
+                    if tool_calls:
+                        if state["current"].strip():
+                            state["committed"] += state["current"].strip() + "\n\n---\n\n"
+                            state["current"] = ""
+                    else:
+                        state["committed"] += state["current"]
+                        state["current"] = ""
+                elif event_type == "agent_cancelled":
+                    # Mechanism 1: a cancelled run never reaches send(), so finalize
+                    # its stream here to stop the "···" bubble immediately.
+                    if state["current"]:
+                        state["committed"] += state["current"]
+                        state["current"] = ""
+                    state["committed"] = state["committed"].rstrip()
+                    if state["committed"].endswith("---"):
+                        state["committed"] = state["committed"][:-3].rstrip()
+                    if not state["committed"].strip():
+                        state["committed"] = "🛑 已中止"
+                    state["finished"] = True
+                    state["last_access"] = time.time()
+                    cancelled = True
+
+            if cancelled:
+                # Outside the lock: response_url fallback re-acquires it.
+                self._schedule_response_url_fallback(stream_id)
+
+        return on_event
+
     # ------------------------------------------------------------------
     # Subscribe & heartbeat
     # ------------------------------------------------------------------
@@ -287,16 +499,31 @@ class WecomBotChannel(ChatChannel):
         chattype = body.get("chattype", "single")
         is_group = chattype == "group"
 
+        result = self._build_context(body, is_group)
+        if not result:
+            return
+        context, wecom_msg = result
+        wecom_msg.req_id = req_id
+        if req_id:
+            context["on_event"] = self._make_stream_callback(req_id)
+        self.produce(context)
+
+    def _build_context(self, body: dict, is_group: bool, default_aeskey: str = ""):
+        """Parse a wecom message body into a Context, applying file-cache logic.
+
+        Shared by both the websocket (long-connection) and callback (webhook)
+        receive paths. Returns ``(context, wecom_msg)`` when the message should be
+        handed to the agent, or ``None`` when it was consumed (cached image/file,
+        parse failure, etc.).
+        """
         try:
-            wecom_msg = WecomBotMessage(body, is_group=is_group)
+            wecom_msg = WecomBotMessage(body, is_group=is_group, default_aeskey=default_aeskey)
         except NotImplementedError as e:
             logger.warning(f"[WecomBot] {e}")
-            return
+            return None
         except Exception as e:
             logger.error(f"[WecomBot] Failed to parse message: {e}", exc_info=True)
-            return
-
-        wecom_msg.req_id = req_id
+            return None
 
         # File cache logic (same pattern as feishu)
         from channel.file_cache import get_file_cache
@@ -314,13 +541,13 @@ class WecomBotChannel(ChatChannel):
             if hasattr(wecom_msg, "image_path") and wecom_msg.image_path:
                 file_cache.add(session_id, wecom_msg.image_path, file_type="image")
                 logger.info(f"[WecomBot] Image cached for session {session_id}")
-            return
+            return None
 
         if wecom_msg.ctype == ContextType.FILE:
             wecom_msg.prepare()
             file_cache.add(session_id, wecom_msg.content, file_type="file")
             logger.info(f"[WecomBot] File cached for session {session_id}: {wecom_msg.content}")
-            return
+            return None
 
         if wecom_msg.ctype == ContextType.TEXT:
             cached_files = file_cache.get(session_id)
@@ -346,10 +573,9 @@ class WecomBotChannel(ChatChannel):
             msg=wecom_msg,
             no_need_at=True,
         )
-        if context:
-            if req_id:
-                context["on_event"] = self._make_stream_callback(req_id)
-            self.produce(context)
+        if not context:
+            return None
+        return context, wecom_msg
 
     # ------------------------------------------------------------------
     # Event callback
@@ -440,6 +666,17 @@ class WecomBotChannel(ChatChannel):
                     state["current"] = ""
                 _push_stream(state, force=True)
 
+            elif event_type == "agent_cancelled":
+                # Flush partial output and strip trailing "---" separator
+                # left over from previous turn, to avoid a dangling divider.
+                if state["current"]:
+                    state["committed"] += state["current"]
+                    state["current"] = ""
+                state["committed"] = state["committed"].rstrip()
+                if state["committed"].endswith("---"):
+                    state["committed"] = state["committed"][:-3].rstrip()
+                _push_stream(state, force=True)
+
         return on_event
 
     # ------------------------------------------------------------------
@@ -479,11 +716,233 @@ class WecomBotChannel(ChatChannel):
 
         return context
 
+    # ------------------------------------------------------------------
+    # Callback (webhook) send: write the final reply into the stream state
+    # so the next "流式消息刷新" poll returns it with finish=true.
+    # ------------------------------------------------------------------
+
+    def _callback_send(self, reply: Reply, context: Context):
+        msg = context.get("msg")
+        stream_id = getattr(msg, "stream_id", None) if msg else None
+        if not stream_id:
+            stream_id = context.get("wecom_stream_id")
+        if not stream_id:
+            logger.warning("[WecomBot] callback send without stream_id, dropping reply")
+            return
+
+        if reply.type == ReplyType.TEXT:
+            self._callback_finalize_text(stream_id, reply.content)
+        elif reply.type in (ReplyType.IMAGE_URL, ReplyType.IMAGE):
+            self._callback_finalize_image(stream_id, reply.content)
+        elif reply.type == ReplyType.FILE:
+            # Passive callback replies only support text + image (base64); files
+            # are not supported by the protocol, so append a notice to whatever
+            # text the agent already streamed (do not drop it).
+            text = getattr(reply, "text_content", "") or ""
+            note = (text + "\n\n" if text else "") + "（文件无法在企微回调模式下直接发送）"
+            self._callback_finalize_text(stream_id, note, append=True)
+        elif reply.type in (ReplyType.VIDEO, ReplyType.VIDEO_URL, ReplyType.VOICE):
+            logger.warning(f"[WecomBot] reply type {reply.type} not supported in callback mode")
+            text = getattr(reply, "text_content", "") or ""
+            note = (text + "\n\n" if text else "") + "（该消息类型无法在企微回调模式下直接发送）"
+            self._callback_finalize_text(stream_id, note, append=True)
+        else:
+            self._callback_finalize_text(stream_id, str(reply.content))
+
+    def _callback_get_or_create_state(self, stream_id: str) -> dict:
+        state = self._callback_streams.get(stream_id)
+        if state is None:
+            now = time.time()
+            state = {
+                "committed": "",
+                "current": "",
+                "finished": False,
+                "images": [],
+                "image_urls": [],
+                "image_pending": False,
+                "last_access": now,
+                "created_at": now,
+                "response_url": "",
+                "delivered": False,
+                "url_sent": False,
+            }
+            self._callback_streams[stream_id] = state
+        return state
+
+    def _callback_finalize_text(self, stream_id: str, content: str, append: bool = False):
+        with self._callback_lock:
+            state = self._callback_get_or_create_state(stream_id)
+            accumulated = (state["committed"] + state["current"]).strip()
+            if append and accumulated:
+                state["committed"] = (accumulated + "\n\n" + (content or "")).strip()
+            else:
+                state["committed"] = accumulated if accumulated else (content or "")
+            state["current"] = ""
+            state["last_access"] = time.time()
+        # Don't finish synchronously: chat_channel splits an image-with-caption
+        # reply into a TEXT send followed (0.3s later) by the IMAGE send. If the
+        # text finished the stream immediately, WeCom would close it before the
+        # image arrives. Defer the finish so a trailing image can merge in.
+        self._schedule_text_finish(stream_id)
+
+    def _schedule_text_finish(self, stream_id: str, delay: float = 1.2):
+        def _run():
+            time.sleep(delay)
+            with self._callback_lock:
+                state = self._callback_streams.get(stream_id)
+                if not state or state["finished"] or state.get("image_pending"):
+                    return  # already finished, or an image reply is on its way
+                state["finished"] = True
+                state["last_access"] = time.time()
+            self._schedule_response_url_fallback(stream_id)
+
+        threading.Thread(target=_run, daemon=True, name=f"wecom-textfin-{stream_id}").start()
+
+    def _callback_finalize_image(self, stream_id: str, img_path_or_url: str):
+        # Mark the image as pending up front (before the slow load/compress) so a
+        # preceding text finalize won't close the stream while we work.
+        with self._callback_lock:
+            self._callback_get_or_create_state(stream_id)["image_pending"] = True
+        b64md5 = self._load_image_base64(img_path_or_url)
+        with self._callback_lock:
+            state = self._callback_get_or_create_state(stream_id)
+            accumulated = (state["committed"] + state["current"]).strip()
+            state["current"] = ""
+            if b64md5:
+                state["images"].append(b64md5)
+                state["committed"] = accumulated
+                # Remember the public url (if any) so the response_url fallback
+                # can embed it as markdown when the poll window has closed.
+                if img_path_or_url.startswith(("http://", "https://")):
+                    state["image_urls"].append(img_path_or_url)
+            else:
+                state["committed"] = accumulated or "[图片发送失败]"
+            state["finished"] = True
+            state["image_pending"] = False
+            state["last_access"] = time.time()
+        self._schedule_response_url_fallback(stream_id)
+
+    # ------------------------------------------------------------------
+    # Active reply fallback (response_url): rescue replies that finish after
+    # WeCom stops polling (the passive stream window is ~6 min from the user's
+    # message). A short delay lets an in-flight poll deliver first; only if no
+    # poll picks up the finished answer do we push it actively via response_url.
+    # ------------------------------------------------------------------
+
+    def _schedule_response_url_fallback(self, stream_id: str, delay: float = 3.0):
+        def _run():
+            time.sleep(delay)
+            with self._callback_lock:
+                state = self._callback_streams.get(stream_id)
+                if not state:
+                    return
+                if state.get("delivered") or state.get("url_sent"):
+                    return  # a poll already delivered (or fallback already ran)
+                response_url = state.get("response_url") or ""
+                if not response_url:
+                    logger.warning(
+                        f"[WecomBot] stream {stream_id} finished after poll window but no response_url; reply dropped"
+                    )
+                    return
+                content = (state["committed"] + state["current"]).strip()
+                image_urls = list(state.get("image_urls") or [])
+                has_images = bool(state.get("images"))
+                state["url_sent"] = True
+
+            self._send_via_response_url(stream_id, response_url, content, image_urls, has_images)
+
+        threading.Thread(target=_run, daemon=True, name=f"wecom-respurl-{stream_id}").start()
+
+    def _send_via_response_url(self, stream_id, response_url, content, image_urls, has_images):
+        """Push a one-shot active markdown reply to response_url (valid 1h, single use)."""
+        md = content or ""
+        if image_urls:
+            md += ("\n\n" if md else "") + "\n".join(f"![]({u})" for u in image_urls)
+        elif has_images:
+            md += ("\n\n" if md else "") + "（图片已生成，但因处理超时无法通过回调发送）"
+        if not md:
+            md = "（处理完成）"
+        payload = {"msgtype": "markdown", "markdown": {"content": md}}
+        try:
+            resp = requests.post(response_url, json=payload, timeout=15)
+            logger.info(
+                f"[WecomBot] response_url active reply sent for {stream_id}: "
+                f"status={resp.status_code}, body={resp.text[:200]}"
+            )
+        except Exception as e:
+            logger.error(f"[WecomBot] response_url active reply failed for {stream_id}: {e}")
+
+    def _load_image_base64(self, img_path_or_url: str):
+        """Load a local/remote image, ensure JPG/PNG within 10MB, return (base64, md5)."""
+        local_path = img_path_or_url
+        if local_path.startswith("file://"):
+            local_path = local_path[7:]
+
+        # Temp files we create here (downloads/conversions/compressions) must be
+        # cleaned up afterwards; the caller's original local file must not be.
+        temp_files = []
+        try:
+            if local_path.startswith(("http://", "https://")):
+                try:
+                    resp = requests.get(local_path, timeout=30)
+                    resp.raise_for_status()
+                    tmp_path = f"/tmp/wecom_cb_img_{uuid.uuid4().hex[:8]}"
+                    with open(tmp_path, "wb") as f:
+                        f.write(resp.content)
+                    temp_files.append(tmp_path)
+                    local_path = tmp_path
+                except Exception as e:
+                    logger.error(f"[WecomBot] Failed to download image for callback reply: {e}")
+                    return None
+
+            if not os.path.exists(local_path):
+                logger.error(f"[WecomBot] Image file not found: {local_path}")
+                return None
+
+            formatted = self._ensure_image_format(local_path)
+            if not formatted:
+                return None
+            if formatted != local_path:
+                temp_files.append(formatted)
+            local_path = formatted
+
+            # Unlike the long-connection path (which uploads and sends only a tiny
+            # media_id), the callback reply embeds the whole image as base64 inside
+            # an AES-encrypted body that is returned on EVERY poll. Empirically a
+            # ~1.5MB image (base64 ~2.1MB, encrypted ~2.8MB) makes WeCom reject the
+            # finish packet and poll forever, so cap well below that.
+            callback_max_size = 512 * 1024
+            if os.path.getsize(local_path) > callback_max_size:
+                compressed = self._compress_image(local_path, callback_max_size)
+                if compressed:
+                    temp_files.append(compressed)
+                    local_path = compressed
+                else:
+                    logger.warning("[WecomBot] callback image compress failed; sending original (may be rejected)")
+
+            try:
+                with open(local_path, "rb") as f:
+                    raw = f.read()
+                return base64.b64encode(raw).decode("utf-8"), hashlib.md5(raw).hexdigest()
+            except Exception as e:
+                logger.error(f"[WecomBot] Failed to read image for callback reply: {e}")
+                return None
+        finally:
+            for path in temp_files:
+                try:
+                    os.remove(path)
+                except OSError:
+                    pass
+
     # ------------------------------------------------------------------
     # Send reply
     # ------------------------------------------------------------------
 
     def send(self, reply: Reply, context: Context):
+        if self.mode == "webhook":
+            self._callback_send(reply, context)
+            return
+
         msg = context.get("msg")
         is_group = context.get("isgroup", False)
         receiver = context.get("receiver", "")
@@ -895,3 +1354,85 @@ class WecomBotChannel(ChatChannel):
         else:
             logger.error("[WecomBot] Failed to get media_id from finish response")
         return media_id
+
+
+class WecomBotCallbackController:
+    """HTTP controller for wecom bot callback (webhook) mode.
+
+    - GET  : URL verification (echo the decrypted echostr).
+    - POST : encrypted message / stream-refresh / event callbacks; returns an
+             encrypted passive reply (or "success" for an empty reply).
+    """
+
+    @staticmethod
+    def _channel() -> "WecomBotChannel":
+        return WecomBotChannel()
+
+    def GET(self):
+        channel = self._channel()
+        params = web.input(msg_signature="", timestamp="", nonce="", echostr="")
+        if not channel._crypt:
+            return "wecom bot callback not ready"
+        ret, echo = channel._crypt.verify_url(
+            params.msg_signature, params.timestamp, params.nonce, params.echostr
+        )
+        if ret != 0:
+            logger.error(f"[WecomBot] URL verify failed: ret={ret}")
+            return "verify fail"
+        if isinstance(echo, bytes):
+            echo = echo.decode("utf-8")
+        return echo
+
+    def POST(self):
+        channel = self._channel()
+        if not channel._crypt:
+            return "success"
+
+        params = web.input(msg_signature="", timestamp="", nonce="")
+        body = web.data()
+        ret, plain = channel._crypt.decrypt_msg(
+            body, params.msg_signature, params.timestamp, params.nonce
+        )
+        if ret != 0:
+            logger.error(f"[WecomBot] callback decrypt failed: ret={ret}")
+            return "success"
+
+        try:
+            data = json.loads(plain)
+        except Exception as e:
+            logger.error(f"[WecomBot] callback json parse failed: {e}")
+            return "success"
+
+        msgtype = data.get("msgtype", "")
+        # Stream polls arrive ~1/s; logging each is noisy, so only log non-poll
+        # callbacks here (poll completion is logged in the stream-poll handler).
+        if msgtype != "stream":
+            logger.debug(f"[WecomBot] callback received msgtype={msgtype}")
+
+        try:
+            if msgtype == "stream":
+                reply = channel._callback_handle_stream_poll(data)
+            elif msgtype == "event":
+                event_type = data.get("event", {}).get("eventtype", "")
+                logger.info(f"[WecomBot] callback event: {event_type}")
+                reply = None
+            elif msgtype in ("text", "image", "voice", "file", "video", "mixed"):
+                reply = channel._callback_handle_message(data)
+            else:
+                logger.warning(f"[WecomBot] unsupported callback msgtype: {msgtype}")
+                reply = None
+        except Exception as e:
+            logger.error(f"[WecomBot] callback handling error: {e}", exc_info=True)
+            reply = None
+
+        if not reply:
+            # Empty reply package is acceptable.
+            return "success"
+
+        plain_reply = json.dumps(reply, ensure_ascii=False)
+        ret, enc = channel._crypt.encrypt_msg(plain_reply, params.nonce, params.timestamp)
+        if ret != 0:
+            logger.error(f"[WecomBot] callback encrypt failed: ret={ret}")
+            return "success"
+        web.header("Content-Type", "application/json; charset=utf-8")
+        return json.dumps(enc, ensure_ascii=False)

channel/wecom_bot/wecom_bot_crypt.py

@@ -0,0 +1,203 @@
+"""
+WeCom (企业微信) smart-bot callback message encryption/decryption.
+
+Adapted from the official `WXBizJsonMsgCrypt` sample (JSON variant) used by the
+AI bot callback (webhook) mode. The bot's receive-message callback delivers
+AES-256-CBC encrypted JSON payloads, and passive replies must be encrypted the
+same way before being returned in the HTTP response.
+
+For an enterprise-internal smart bot, ``receive_id`` is always an empty string.
+"""
+
+import base64
+import hashlib
+import random
+import socket
+import struct
+import time
+
+from Crypto.Cipher import AES
+
+from common.log import logger
+
+# Error codes (mirrors the official ierror.py)
+WXBizMsgCrypt_OK = 0
+WXBizMsgCrypt_ValidateSignature_Error = -40001
+WXBizMsgCrypt_ParseJson_Error = -40002
+WXBizMsgCrypt_ComputeSignature_Error = -40003
+WXBizMsgCrypt_IllegalAesKey = -40004
+WXBizMsgCrypt_ValidateCorpid_Error = -40005
+WXBizMsgCrypt_EncryptAES_Error = -40006
+WXBizMsgCrypt_DecryptAES_Error = -40007
+WXBizMsgCrypt_IllegalBuffer = -40008
+WXBizMsgCrypt_EncodeBase64_Error = -40009
+WXBizMsgCrypt_DecodeBase64_Error = -40010
+WXBizMsgCrypt_GenReturnJson_Error = -40011
+
+
+class FormatException(Exception):
+    pass
+
+
+def _gen_sha1(token, timestamp, nonce, encrypt):
+    """Compute the WeCom message signature with SHA1 over the sorted parts."""
+    try:
+        if isinstance(encrypt, bytes):
+            encrypt = encrypt.decode("utf-8")
+        sortlist = [str(token), str(timestamp), str(nonce), str(encrypt)]
+        sortlist.sort()
+        sha = hashlib.sha1()
+        sha.update("".join(sortlist).encode("utf-8"))
+        return WXBizMsgCrypt_OK, sha.hexdigest()
+    except Exception as e:
+        logger.error(f"[WecomBot] compute signature error: {e}")
+        return WXBizMsgCrypt_ComputeSignature_Error, None
+
+
+class _PKCS7Encoder:
+    """PKCS#7 padding with a 32-byte block size (AES-256)."""
+
+    block_size = 32
+
+    def encode(self, text: bytes) -> bytes:
+        text_length = len(text)
+        amount_to_pad = self.block_size - (text_length % self.block_size)
+        if amount_to_pad == 0:
+            amount_to_pad = self.block_size
+        pad = bytes([amount_to_pad])
+        return text + pad * amount_to_pad
+
+    def decode(self, decrypted: bytes) -> bytes:
+        pad = decrypted[-1]
+        if pad < 1 or pad > 32:
+            pad = 0
+        return decrypted[:-pad] if pad else decrypted
+
+
+class _Prpcrypt:
+    """AES-256-CBC encrypt/decrypt for WeCom callback messages."""
+
+    def __init__(self, key: bytes):
+        self.key = key
+        self.mode = AES.MODE_CBC
+
+    def encrypt(self, text: str, receive_id: str):
+        text_bytes = text.encode()
+        # 16-byte random prefix + network-order length + body + receive_id
+        text_bytes = (
+            self._get_random_str()
+            + struct.pack("I", socket.htonl(len(text_bytes)))
+            + text_bytes
+            + receive_id.encode()
+        )
+        text_bytes = _PKCS7Encoder().encode(text_bytes)
+        try:
+            cryptor = AES.new(self.key, self.mode, self.key[:16])
+            ciphertext = cryptor.encrypt(text_bytes)
+            return WXBizMsgCrypt_OK, base64.b64encode(ciphertext)
+        except Exception as e:
+            logger.error(f"[WecomBot] AES encrypt error: {e}")
+            return WXBizMsgCrypt_EncryptAES_Error, None
+
+    def decrypt(self, text, receive_id: str):
+        try:
+            cryptor = AES.new(self.key, self.mode, self.key[:16])
+            plain_text = cryptor.decrypt(base64.b64decode(text))
+        except Exception as e:
+            logger.error(f"[WecomBot] AES decrypt error: {e}")
+            return WXBizMsgCrypt_DecryptAES_Error, None
+        try:
+            pad = plain_text[-1]
+            content = plain_text[16:-pad]
+            json_len = socket.ntohl(struct.unpack("I", content[:4])[0])
+            json_content = content[4 : json_len + 4].decode("utf-8")
+            from_receive_id = content[json_len + 4 :].decode("utf-8")
+        except Exception as e:
+            logger.error(f"[WecomBot] illegal buffer when decrypting: {e}")
+            return WXBizMsgCrypt_IllegalBuffer, None
+        if from_receive_id != receive_id:
+            logger.error(
+                f"[WecomBot] receive_id not match: expect={receive_id}, got={from_receive_id}"
+            )
+            return WXBizMsgCrypt_ValidateCorpid_Error, None
+        return WXBizMsgCrypt_OK, json_content
+
+    @staticmethod
+    def _get_random_str() -> bytes:
+        return str(random.randint(1000000000000000, 9999999999999999)).encode()
+
+
+class WecomBotCrypt:
+    """High-level helper for verifying URLs and (de)crypting callback messages."""
+
+    def __init__(self, token: str, encoding_aes_key: str, receive_id: str = ""):
+        try:
+            self.key = base64.b64decode(encoding_aes_key + "=")
+            assert len(self.key) == 32
+        except Exception:
+            raise FormatException("[WecomBot] invalid EncodingAESKey")
+        self.token = token
+        self.receive_id = receive_id
+
+    def verify_url(self, msg_signature, timestamp, nonce, echostr):
+        ret, signature = _gen_sha1(self.token, timestamp, nonce, echostr)
+        if ret != 0:
+            return ret, None
+        if signature != msg_signature:
+            return WXBizMsgCrypt_ValidateSignature_Error, None
+        pc = _Prpcrypt(self.key)
+        return pc.decrypt(echostr, self.receive_id)
+
+    def encrypt_msg(self, reply_msg: str, nonce: str, timestamp: str = None):
+        """Encrypt a passive-reply JSON string and return the full response JSON.
+
+        Returns (ret, response_dict). On success ret==0 and response_dict is a
+        dict with encrypt/msgsignature/timestamp/nonce fields.
+        """
+        pc = _Prpcrypt(self.key)
+        ret, encrypt = pc.encrypt(reply_msg, self.receive_id)
+        if ret != 0:
+            return ret, None
+        encrypt = encrypt.decode("utf-8")
+        if timestamp is None:
+            timestamp = str(int(time.time()))
+        ret, signature = _gen_sha1(self.token, timestamp, nonce, encrypt)
+        if ret != 0:
+            return ret, None
+        return WXBizMsgCrypt_OK, {
+            "encrypt": encrypt,
+            "msgsignature": signature,
+            "timestamp": timestamp,
+            "nonce": nonce,
+        }
+
+    def decrypt_msg(self, post_data, msg_signature, timestamp, nonce):
+        """Verify signature and decrypt the encrypted callback payload.
+
+        ``post_data`` may be the raw request body (bytes/str) containing
+        ``{"encrypt": "..."}`` or the already-extracted encrypt string.
+        Returns (ret, plaintext_json_str).
+        """
+        import json
+
+        encrypt = None
+        if isinstance(post_data, (bytes, bytearray)):
+            post_data = post_data.decode("utf-8")
+        if isinstance(post_data, str):
+            try:
+                encrypt = json.loads(post_data).get("encrypt")
+            except Exception:
+                encrypt = post_data
+        elif isinstance(post_data, dict):
+            encrypt = post_data.get("encrypt")
+        if not encrypt:
+            return WXBizMsgCrypt_ParseJson_Error, None
+
+        ret, signature = _gen_sha1(self.token, timestamp, nonce, encrypt)
+        if ret != 0:
+            return ret, None
+        if signature != msg_signature:
+            logger.error("[WecomBot] callback signature not match")
+            return WXBizMsgCrypt_ValidateSignature_Error, None
+        pc = _Prpcrypt(self.key)
+        return pc.decrypt(encrypt, self.receive_id)

channel/wecom_bot/wecom_bot_message.py

@@ -87,11 +87,14 @@ def _get_tmp_dir() -> str:
 class WecomBotMessage(ChatMessage):
     """Message wrapper for wecom bot (websocket long-connection mode)."""
 
-    def __init__(self, msg_body: dict, is_group: bool = False):
+    def __init__(self, msg_body: dict, is_group: bool = False, default_aeskey: str = ""):
         super().__init__(msg_body)
         self.msg_id = msg_body.get("msgid")
         self.create_time = msg_body.get("create_time")
         self.is_group = is_group
+        # In callback (webhook) mode the media bodies carry no per-message aeskey;
+        # the download url is encrypted with the bot's EncodingAESKey instead.
+        self._default_aeskey = default_aeskey
 
         msg_type = msg_body.get("msgtype")
         from_userid = msg_body.get("from", {}).get("userid", "")
@@ -113,7 +116,7 @@ class WecomBotMessage(ChatMessage):
             self.ctype = ContextType.IMAGE
             image_info = msg_body.get("image", {})
             image_url = image_info.get("url", "")
-            aeskey = image_info.get("aeskey", "")
+            aeskey = image_info.get("aeskey", "") or self._default_aeskey
             tmp_dir = _get_tmp_dir()
             image_path = os.path.join(tmp_dir, f"wecom_{self.msg_id}.png")
 
@@ -147,7 +150,7 @@ class WecomBotMessage(ChatMessage):
                 elif item_type == "image":
                     img_info = item.get("image", {})
                     img_url = img_info.get("url", "")
-                    img_aeskey = img_info.get("aeskey", "")
+                    img_aeskey = img_info.get("aeskey", "") or self._default_aeskey
                     img_path = os.path.join(tmp_dir, f"wecom_{self.msg_id}_{idx}.png")
                     try:
                         img_data = _decrypt_media(img_url, img_aeskey)
@@ -166,7 +169,7 @@ class WecomBotMessage(ChatMessage):
             self.ctype = ContextType.FILE
             file_info = msg_body.get("file", {})
             file_url = file_info.get("url", "")
-            aeskey = file_info.get("aeskey", "")
+            aeskey = file_info.get("aeskey", "") or self._default_aeskey
             tmp_dir = _get_tmp_dir()
             base_path = os.path.join(tmp_dir, f"wecom_{self.msg_id}")
             self.content = base_path
@@ -188,7 +191,7 @@ class WecomBotMessage(ChatMessage):
             self.ctype = ContextType.FILE
             video_info = msg_body.get("video", {})
             video_url = video_info.get("url", "")
-            aeskey = video_info.get("aeskey", "")
+            aeskey = video_info.get("aeskey", "") or self._default_aeskey
             tmp_dir = _get_tmp_dir()
             self.content = os.path.join(tmp_dir, f"wecom_{self.msg_id}.mp4")
 

channel/weixin/weixin_channel.py

@@ -24,7 +24,7 @@ from channel.weixin.weixin_message import WeixinMessage
 from common.expired_dict import ExpiredDict
 from common.log import logger
 from common.singleton import singleton
-from config import conf
+from config import conf, get_weixin_credentials_path
 
 MAX_CONSECUTIVE_FAILURES = 3
 BACKOFF_DELAY = 30
@@ -47,14 +47,16 @@ def _load_credentials(cred_path: str) -> dict:
 
 
 def _save_credentials(cred_path: str, data: dict):
-    """Save credentials to JSON file."""
+    """Atomically save credentials to JSON file (tmp + rename)."""
     os.makedirs(os.path.dirname(cred_path), exist_ok=True)
-    with open(cred_path, "w") as f:
+    tmp_path = f"{cred_path}.tmp"
+    with open(tmp_path, "w") as f:
         json.dump(data, f, indent=2)
     try:
-        os.chmod(cred_path, 0o600)
+        os.chmod(tmp_path, 0o600)
     except Exception:
         pass
+    os.replace(tmp_path, cred_path)
 
 
 @singleton
@@ -73,7 +75,10 @@ class WeixinChannel(ChatChannel):
         self.api = None
         self._stop_event = threading.Event()
         self._poll_thread = None
-        self._context_tokens = {}  # user_id -> context_token
+        # user_id -> context_token. Guarded by _context_tokens_lock for any
+        # mutation that races with disk persistence.
+        self._context_tokens = {}
+        self._context_tokens_lock = threading.Lock()
         self._received_msgs = ExpiredDict(60 * 60 * 7.1)
         self._get_updates_buf = ""
         self._credentials_path = ""
@@ -91,16 +96,21 @@ class WeixinChannel(ChatChannel):
         cdn_base_url = conf().get("weixin_cdn_base_url", CDN_BASE_URL)
         token = conf().get("weixin_token", "")
 
-        self._credentials_path = os.path.expanduser(
-            conf().get("weixin_credentials_path", "~/.weixin_cow_credentials.json")
-        )
+        self._credentials_path = get_weixin_credentials_path()
 
+        # Always load credentials so we can restore context_tokens even when
+        # the bot token itself comes from config.
+        creds = _load_credentials(self._credentials_path)
         if not token:
-            creds = _load_credentials(self._credentials_path)
             token = creds.get("token", "")
             if creds.get("base_url"):
                 base_url = creds["base_url"]
 
+        # Restore persisted context_tokens so scheduler can deliver pushes
+        # immediately after restart, without waiting for the user to ping
+        # the bot first.
+        self._restore_context_tokens_from_creds(creds)
+
         if not token:
             token, base_url = self._login_with_retry(base_url)
             if not token:
@@ -140,11 +150,16 @@ class WeixinChannel(ChatChannel):
     def _relogin(self) -> bool:
         """Re-login after session expiry. Returns True on success."""
         base_url = self.api.base_url if self.api else DEFAULT_BASE_URL
-        if os.path.exists(self._credentials_path):
-            try:
-                os.remove(self._credentials_path)
-            except Exception:
-                pass
+        # Clearing the whole credentials file is intentional: the new login
+        # will issue a fresh `token` and persisted context_tokens belong to
+        # the previous bot identity, so they must not survive.
+        with self._context_tokens_lock:
+            self._context_tokens.clear()
+            if os.path.exists(self._credentials_path):
+                try:
+                    os.remove(self._credentials_path)
+                except Exception:
+                    pass
         self.login_status = self.LOGIN_STATUS_WAITING
         result = self._qr_login(base_url)
         if not result:
@@ -156,9 +171,62 @@ class WeixinChannel(ChatChannel):
             cdn_base_url=self.api.cdn_base_url if self.api else CDN_BASE_URL,
         )
         self.login_status = self.LOGIN_STATUS_OK
-        self._context_tokens.clear()
         return True
 
+    # ── Context token persistence ──────────────────────────────────────
+    # ilink requires every outbound send to echo the context_token from the
+    # user's latest inbound message. We mirror the in-memory map into the
+    # credentials JSON so scheduled pushes survive process restarts.
+    # All mutation + disk IO is serialized via _context_tokens_lock so that
+    # concurrent updates can never lose each other's writes.
+
+    def _restore_context_tokens_from_creds(self, creds: dict) -> None:
+        if not isinstance(creds, dict):
+            return
+        tokens = creds.get("context_tokens")
+        if not isinstance(tokens, dict):
+            return
+        restored = 0
+        with self._context_tokens_lock:
+            for user_id, token in tokens.items():
+                if isinstance(user_id, str) and isinstance(token, str) and token:
+                    self._context_tokens[user_id] = token
+                    restored += 1
+        if restored:
+            logger.info(f"[Weixin] Restored {restored} context_tokens from credentials")
+
+    def _persist_context_tokens_locked(self) -> None:
+        """Flush the token map to disk. Caller must hold _context_tokens_lock."""
+        if not self._credentials_path:
+            return
+        try:
+            creds = _load_credentials(self._credentials_path) or {}
+            creds["context_tokens"] = dict(self._context_tokens)
+            _save_credentials(self._credentials_path, creds)
+        except Exception as e:
+            logger.warning(f"[Weixin] Failed to persist context_tokens: {e}")
+
+    def _update_context_token(self, user_id: str, token: str) -> None:
+        """Update the in-memory token for a user; flush to disk only on change."""
+        if not user_id or not token:
+            return
+        with self._context_tokens_lock:
+            if self._context_tokens.get(user_id) == token:
+                return
+            self._context_tokens[user_id] = token
+            self._persist_context_tokens_locked()
+
+    def _invalidate_context_token(self, user_id: str) -> None:
+        """Drop the cached token for a user (used after -14 / send rejection)."""
+        if not user_id:
+            return
+        with self._context_tokens_lock:
+            if user_id not in self._context_tokens:
+                return
+            del self._context_tokens[user_id]
+            logger.info(f"[Weixin] Invalidated stale context_token for {user_id}")
+            self._persist_context_tokens_locked()
+
     # ── QR Login ───────────────────────────────────────────────────────
 
     @staticmethod
@@ -391,7 +459,7 @@ class WeixinChannel(ChatChannel):
         context_token = raw_msg.get("context_token", "")
 
         if context_token and from_user:
-            self._context_tokens[from_user] = context_token
+            self._update_context_token(from_user, context_token)
 
         cdn_base_url = self.api.cdn_base_url if self.api else CDN_BASE_URL
         try:
@@ -510,10 +578,30 @@ class WeixinChannel(ChatChannel):
             return msg.context_token
         return self._context_tokens.get(receiver, "")
 
+    def _check_send_response(self, resp, receiver: str) -> None:
+        """Inspect a send-API response; drop stale context_token on -14.
+
+        ilink uses ret/errcode = -14 to signal that the session (and any
+        cached context_token) is no longer valid. The plugin keeps running
+        because the bot itself can re-login; we just need to forget the
+        per-user token so the next push won't retry forever.
+        """
+        if not isinstance(resp, dict):
+            return
+        ret = resp.get("ret")
+        errcode = resp.get("errcode")
+        if ret == -14 or errcode == -14:
+            logger.warning(
+                f"[Weixin] Send returned -14 (session expired) for "
+                f"receiver={receiver}; dropping cached context_token"
+            )
+            self._invalidate_context_token(receiver)
+
     def _send_text(self, text: str, receiver: str, context_token: str):
         if len(text) <= TEXT_CHUNK_LIMIT:
             try:
-                self.api.send_text(receiver, text, context_token)
+                resp = self.api.send_text(receiver, text, context_token)
+                self._check_send_response(resp, receiver)
                 logger.debug(f"[Weixin] Text sent to {receiver}, len={len(text)}")
             except Exception as e:
                 logger.error(f"[Weixin] Failed to send text: {e}")
@@ -522,7 +610,8 @@ class WeixinChannel(ChatChannel):
         chunks = self._split_text(text, TEXT_CHUNK_LIMIT)
         for i, chunk in enumerate(chunks):
             try:
-                self.api.send_text(receiver, chunk, context_token)
+                resp = self.api.send_text(receiver, chunk, context_token)
+                self._check_send_response(resp, receiver)
                 logger.debug(f"[Weixin] Text chunk {i+1}/{len(chunks)} sent to {receiver}, len={len(chunk)}")
             except Exception as e:
                 logger.error(f"[Weixin] Failed to send text chunk {i+1}/{len(chunks)}: {e}")
@@ -556,13 +645,14 @@ class WeixinChannel(ChatChannel):
             return
         try:
             result = upload_media_to_cdn(self.api, local_path, receiver, media_type=1)
-            self.api.send_image_item(
+            resp = self.api.send_image_item(
                 to=receiver,
                 context_token=context_token,
                 encrypt_query_param=result["encrypt_query_param"],
                 aes_key_b64=result["aes_key_b64"],
                 ciphertext_size=result["ciphertext_size"],
             )
+            self._check_send_response(resp, receiver)
             logger.info(f"[Weixin] Image sent to {receiver}")
         except Exception as e:
             logger.error(f"[Weixin] Image send failed: {e}")
@@ -575,7 +665,7 @@ class WeixinChannel(ChatChannel):
             return
         try:
             result = upload_media_to_cdn(self.api, local_path, receiver, media_type=3)
-            self.api.send_file_item(
+            resp = self.api.send_file_item(
                 to=receiver,
                 context_token=context_token,
                 encrypt_query_param=result["encrypt_query_param"],
@@ -583,6 +673,7 @@ class WeixinChannel(ChatChannel):
                 file_name=os.path.basename(local_path),
                 file_size=result["raw_size"],
             )
+            self._check_send_response(resp, receiver)
             logger.info(f"[Weixin] File sent to {receiver}")
         except Exception as e:
             logger.error(f"[Weixin] File send failed: {e}")
@@ -595,13 +686,14 @@ class WeixinChannel(ChatChannel):
             return
         try:
             result = upload_media_to_cdn(self.api, local_path, receiver, media_type=2)
-            self.api.send_video_item(
+            resp = self.api.send_video_item(
                 to=receiver,
                 context_token=context_token,
                 encrypt_query_param=result["encrypt_query_param"],
                 aes_key_b64=result["aes_key_b64"],
                 ciphertext_size=result["ciphertext_size"],
             )
+            self._check_send_response(resp, receiver)
             logger.info(f"[Weixin] Video sent to {receiver}")
         except Exception as e:
             logger.error(f"[Weixin] Video send failed: {e}")

cli/VERSION

@@ -1 +1 @@
-2.0.9
+2.1.3

cli/cli.py

@@ -3,7 +3,7 @@
 import click
 from cli import __version__
 from cli.commands.skill import skill
-from cli.commands.process import start, stop, restart, update, status, logs
+from cli.commands.process import start, stop, restart, self_restart, update, status, logs
 from cli.commands.context import context
 from cli.commands.install import install_browser
 from cli.commands.knowledge import knowledge
@@ -68,6 +68,7 @@ main.add_command(skill)
 main.add_command(start)
 main.add_command(stop)
 main.add_command(restart)
+main.add_command(self_restart)
 main.add_command(update)
 main.add_command(status)
 main.add_command(logs)

cli/commands/install.py

@@ -14,7 +14,7 @@ CHINA_MIRROR = "https://registry.npmmirror.com/-/binary/playwright"
 
 # stream(msg, fg=None) — fg is "yellow" | "green" | "red" | None
 StreamFn = Callable[[str, Optional[str]], None]
-# on_phase(msg) — coarse-grained progress for chat channels (Chinese)
+# on_phase(msg) — coarse-grained progress for chat channels (localized via i18n)
 PhaseFn = Callable[[str], None]
 
 
@@ -78,15 +78,79 @@ def _is_china_network() -> bool:
 
 
 def _pip_install(package_spec: str, stream: StreamFn) -> int:
-    """Install a package, retrying with --user on permission failure."""
+    """Install a package, preferring prebuilt wheels; retry with --user on perm error."""
     python = sys.executable
-    ret = subprocess.call([python, "-m", "pip", "install", package_spec])
+    base = [python, "-m", "pip", "install", "--prefer-binary"]
+    ret = subprocess.call(base + [package_spec])
     if ret != 0:
         stream("  Retrying with --user flag...", "yellow")
-        ret = subprocess.call([python, "-m", "pip", "install", "--user", package_spec])
+        ret = subprocess.call(base + ["--user", package_spec])
     return ret
 
 
+def _is_frozen() -> bool:
+    """True when running inside a PyInstaller-frozen bundle (desktop backend).
+
+    In this mode ``sys.executable`` is the frozen exe (no pip / no ``-m``), so
+    playwright is already bundled and we only need to download the browser
+    binary in-process rather than pip-installing anything.
+    """
+    return bool(getattr(sys, "frozen", False))
+
+
+def _playwright_cli(args: list, env: Optional[dict] = None) -> int:
+    """Invoke the Playwright CLI, working in both source and frozen builds.
+
+    Source builds shell out to ``python -m playwright <args>``. Frozen builds
+    can't use ``-m`` (the exe isn't a Python interpreter), so we call
+    Playwright's driver entrypoint in-process instead. ``env`` overrides are
+    applied to os.environ for the duration of the call (frozen path) or passed
+    through to the subprocess (source path).
+    """
+    if not _is_frozen():
+        cmd = [sys.executable, "-m", "playwright"] + args
+        return subprocess.call(cmd, env=env)
+
+    # Frozen: run the bundled Playwright driver in-process. compute_driver_executable
+    # returns the Node driver shipped inside the bundle; we spawn it directly.
+    prev_env = {}
+    if env:
+        for k, v in env.items():
+            prev_env[k] = os.environ.get(k)
+            os.environ[k] = v
+    try:
+        from playwright._impl._driver import compute_driver_executable, get_driver_env
+        driver = compute_driver_executable()
+        # compute_driver_executable may return a tuple (node, cli.js) on newer
+        # Playwright, or a single path on older ones.
+        if isinstance(driver, (list, tuple)):
+            cmd = list(driver) + args
+        else:
+            cmd = [str(driver)] + args
+        # get_driver_env() snapshots os.environ, which we've already patched with
+        # the caller's overrides (PLAYWRIGHT_BROWSERS_PATH / DOWNLOAD_HOST) above,
+        # so mirror + pinned browsers dir are honored here too.
+        return subprocess.call(cmd, env=get_driver_env())
+    except Exception as e:
+        # Last resort: try the module main via runpy (works if the frozen build
+        # kept playwright.__main__ importable).
+        try:
+            import runpy
+            sys.argv = ["playwright"] + args
+            runpy.run_module("playwright", run_name="__main__")
+            return 0
+        except SystemExit as se:
+            return int(se.code or 0)
+        except Exception:
+            return 1
+    finally:
+        for k, v in prev_env.items():
+            if v is None:
+                os.environ.pop(k, None)
+            else:
+                os.environ[k] = v
+
+
 def _default_stream(msg: str, fg: Optional[str] = None) -> None:
     """CLI: colored click output."""
     if fg == "yellow":
@@ -112,16 +176,28 @@ def run_install_browser(
         stream: Optional callback ``(message, fg)`` for each line. ``fg`` is
             ``yellow`` / ``green`` / ``red`` or None. Defaults to colored click output.
         on_phase: Optional callback for coarse progress (e.g. push to chat);
-            messages are short Chinese status lines.
+            messages are short status lines localized via i18n.
 
     Returns:
         0 on success, 1 on fatal failure (pip or chromium install failed).
     """
+    from cli.utils import get_cli_language
+
+    # Import `common` only after get_cli_language() runs ensure_sys_path(),
+    # so it works when `cow` is invoked from outside the project directory.
+    get_cli_language()  # resolve cow_lang so i18n.t reflects config
+    from common import i18n
+    _t = i18n.t
+
     stream = stream or _default_stream
     python = sys.executable
     legacy_mode = False
+    frozen = _is_frozen()
 
-    _phase(on_phase, "🔧 开始安装浏览器工具依赖（约几分钟，请耐心等待）…")
+    _phase(on_phase, _t(
+        "🔧 开始安装浏览器工具依赖（约几分钟，请耐心等待）…",
+        "🔧 Installing browser tool dependencies (a few minutes, please wait)…",
+    ))
 
     glibc = _get_glibc_version()
     if glibc and glibc < GLIBC_THRESHOLD:
@@ -136,29 +212,84 @@ def run_install_browser(
         stream("")
         _phase(
             on_phase,
-            f"ℹ️ 检测到 glibc {glibc_str}（较旧），将安装兼容版 Playwright {PLAYWRIGHT_LEGACY_VERSION}。",
+            _t(
+                f"ℹ️ 检测到 glibc {glibc_str}（较旧），将安装兼容版 Playwright {PLAYWRIGHT_LEGACY_VERSION}。",
+                f"ℹ️ Detected glibc {glibc_str} (older); installing compatible Playwright {PLAYWRIGHT_LEGACY_VERSION}.",
+            ),
         )
 
     target_version = PLAYWRIGHT_LEGACY_VERSION if legacy_mode else PLAYWRIGHT_VERSION
 
-    _phase(on_phase, "📦 [1/3] 正在安装 Playwright Python 包…")
-    stream("[1/3] Installing playwright Python package...", "yellow")
-    ret = _pip_install(f"playwright=={target_version}", stream)
-    if ret != 0:
-        stream("Failed to install playwright package.", "red")
-        _phase(on_phase, "❌ [1/3] Playwright Python 包安装失败。")
-        return 1
+    # Windows-only: greenlet 3.2.x ships no Windows wheel, so pip would build it
+    # from source (needs MSVC) and fail. Pre-install 3.1.x (has win wheels for
+    # py3.7-3.13) which still satisfies playwright's greenlet>=3.1.1,<4.
+    if sys.platform == "win32" and not frozen:
+        stream("[1/3] Pre-installing greenlet (prebuilt wheel) for Windows...", "yellow")
+        ret = subprocess.call(
+            [python, "-m", "pip", "install", "--only-binary=:all:", "greenlet>=3.1.1,<3.2"]
+        )
+        if ret != 0:
+            stream(
+                "  Could not pre-install a prebuilt greenlet wheel.\n"
+                "  playwright may try to build greenlet from source, which needs\n"
+                "  Microsoft C++ Build Tools: https://visualstudio.microsoft.com/visual-cpp-build-tools/",
+                "yellow",
+            )
 
-    installed = _get_installed_version()
-    if installed:
-        stream(f"  playwright {installed} installed.", "green")
-    stream("")
-    _phase(on_phase, f"✅ [1/3] Playwright 包已安装（{installed or target_version}）。")
+    if frozen:
+        # Desktop bundle: playwright is already shipped inside the app; there is
+        # no pip and nothing to install. Skip straight to downloading Chromium.
+        installed = _get_installed_version()
+        stream(f"[1/3] Playwright is bundled ({installed or 'ok'}), skipping pip install.", "green")
+        _phase(on_phase, _t(
+            "✅ [1/3] Playwright 已内置于客户端，跳过安装。",
+            "✅ [1/3] Playwright is bundled in the app; skipping install.",
+        ))
+    else:
+        _phase(on_phase, _t("📦 [1/3] 正在安装 Playwright Python 包…", "📦 [1/3] Installing Playwright Python package…"))
+        stream("[1/3] Installing playwright Python package...", "yellow")
+        ret = _pip_install(f"playwright=={target_version}", stream)
+        if ret != 0:
+            stream("Failed to install playwright package.", "red")
+            _phase(on_phase, _t("❌ [1/3] Playwright Python 包安装失败。", "❌ [1/3] Failed to install Playwright Python package."))
+            return 1
+
+        installed = _get_installed_version()
+        if installed:
+            stream(f"  playwright {installed} installed.", "green")
+        stream("")
+        _phase(on_phase, _t(
+            f"✅ [1/3] Playwright 包已安装（{installed or target_version}）。",
+            f"✅ [1/3] Playwright package installed ({installed or target_version}).",
+        ))
+
+    # With playwright available, prefer the user's system Chrome/Edge: the browser
+    # tool drives it directly (channel="chrome"/"msedge"), so we can skip the heavy
+    # ~150MB Chromium download entirely. Applies to every runtime (desktop, web,
+    # source) — only headless Linux servers, which usually lack a system browser,
+    # fall through to the download below. Honors prefer_system_browser via
+    # resolve_engine, so users who force downloaded Chromium still get it.
+    try:
+        from agent.tools.browser import browser_env
+        summary = browser_env.capability_summary()
+        if summary.get("ready") and summary.get("engine", {}).get("mode") == "system-chrome":
+            sc = summary.get("system_chrome") or {}
+            stream(f"System browser detected ({sc.get('channel')}), skipping Chromium download.", "green")
+            _phase(on_phase, _t(
+                f"✅ 检测到系统浏览器（{sc.get('channel')}），无需下载 Chromium，浏览器工具已就绪。",
+                f"✅ Detected system browser ({sc.get('channel')}); no Chromium download needed, browser tool is ready.",
+            ))
+            return 0
+    except Exception as e:
+        stream(f"  (system browser probe skipped: {e})", None)
 
     if sys.platform == "linux":
-        _phase(on_phase, "🔧 [2/3] 正在安装 Linux 系统依赖与轻量中文字体（文泉驿正黑，部分步骤可能需要 sudo）…")
+        _phase(on_phase, _t(
+            "🔧 [2/3] 正在安装 Linux 系统依赖与轻量中文字体（文泉驿正黑，部分步骤可能需要 sudo）…",
+            "🔧 [2/3] Installing Linux system deps and a lightweight CJK font (WenQuanYi Zen Hei; some steps may need sudo)…",
+        ))
         stream("[2/3] Installing system dependencies (Linux)...", "yellow")
-        ret = subprocess.call([python, "-m", "playwright", "install-deps", "chromium"])
+        ret = _playwright_cli(["install-deps", "chromium"])
         if ret != 0:
             stream(
                 "  Could not auto-install system deps (may need sudo).\n"
@@ -183,21 +314,30 @@ def run_install_browser(
             stream("  CJK font (wqy-zenhei) installed.", "green")
         _phase(
             on_phase,
-            "✅ [2/3] Linux 依赖与字体步骤已执行（若有权限问题请查看服务器日志或手动执行提示命令）。",
+            _t(
+                "✅ [2/3] Linux 依赖与字体步骤已执行（若有权限问题请查看服务器日志或手动执行提示命令）。",
+                "✅ [2/3] Linux deps and font steps executed (on permission issues, check the server log or run the suggested commands manually).",
+            ),
         )
     else:
         stream(f"[2/3] Skipping system deps (not needed on {sys.platform}).", "yellow")
-        _phase(on_phase, f"ℹ️ [2/3] 当前系统（{sys.platform}）跳过 Linux 专用依赖。")
+        _phase(on_phase, _t(
+            f"ℹ️ [2/3] 当前系统（{sys.platform}）跳过 Linux 专用依赖。",
+            f"ℹ️ [2/3] Skipping Linux-specific deps on this platform ({sys.platform}).",
+        ))
     stream("")
 
-    _phase(on_phase, "🌐 [3/3] 正在下载并安装 Chromium（体积较大，请耐心等待）…")
+    _phase(on_phase, _t(
+        "🌐 [3/3] 正在下载并安装 Chromium（体积较大，请耐心等待）…",
+        "🌐 [3/3] Downloading and installing Chromium (large download, please wait)…",
+    ))
     stream("[3/3] Installing Chromium browser...", "yellow")
-    cmd = [python, "-m", "playwright", "install", "chromium"]
+    pw_args = ["install", "chromium"]
 
     if _is_headless_linux() and not legacy_mode:
         ver = _version_tuple(installed or "")
         if ver >= (1, 57, 0):
-            cmd.append("--only-shell")
+            pw_args.append("--only-shell")
             stream("  (headless shell for Linux server)", None)
         else:
             stream("  (full Chromium)", None)
@@ -205,49 +345,78 @@ def run_install_browser(
         stream("  (full browser for Linux desktop)", None)
 
     env = os.environ.copy()
+    # Pin the download location so it survives desktop app updates and matches
+    # what the runtime looks up (see browser_env.browsers_download_dir()).
+    try:
+        from agent.tools.browser.browser_env import browsers_download_dir
+        env["PLAYWRIGHT_BROWSERS_PATH"] = browsers_download_dir()
+        stream(f"  (browsers dir: {env['PLAYWRIGHT_BROWSERS_PATH']})", None)
+    except Exception:
+        pass
+
     use_mirror = _is_china_network()
     if use_mirror:
         env["PLAYWRIGHT_DOWNLOAD_HOST"] = CHINA_MIRROR
         stream(f"  (using China mirror: {CHINA_MIRROR})", None)
-        _phase(on_phase, "📡 检测到国内 pip 源配置，Chromium 将优先走国内镜像下载。")
+        _phase(on_phase, _t(
+            "📡 检测到国内 pip 源配置，Chromium 将优先走国内镜像下载。",
+            "📡 Detected a China pip mirror; Chromium will be downloaded from the China mirror first.",
+        ))
 
-    ret = subprocess.call(cmd, env=env)
+    ret = _playwright_cli(pw_args, env=env)
 
     if ret != 0 and use_mirror:
         stream("  Mirror download failed, retrying with official CDN...", "yellow")
-        _phase(on_phase, "⚠️ 镜像下载失败，正在改用官方源重试…")
-        env_no_mirror = os.environ.copy()
+        _phase(on_phase, _t(
+            "⚠️ 镜像下载失败，正在改用官方源重试…",
+            "⚠️ Mirror download failed; retrying with the official CDN…",
+        ))
+        env_no_mirror = dict(env)
         env_no_mirror.pop("PLAYWRIGHT_DOWNLOAD_HOST", None)
-        ret = subprocess.call(cmd, env=env_no_mirror)
+        ret = _playwright_cli(pw_args, env=env_no_mirror)
 
     if ret != 0:
         stream("Failed to install Chromium.", "red")
-        _phase(on_phase, "❌ [3/3] Chromium 安装失败。")
+        _phase(on_phase, _t("❌ [3/3] Chromium 安装失败。", "❌ [3/3] Failed to install Chromium."))
         return 1
 
     stream("")
-    _phase(on_phase, "✅ [3/3] Chromium 已安装。")
+    _phase(on_phase, _t("✅ [3/3] Chromium 已安装。", "✅ [3/3] Chromium installed."))
 
     stream("Verifying browser installation...", None)
-    _phase(on_phase, "🔍 正在验证 Playwright 能否正常加载…")
-    ret = subprocess.call(
-        [python, "-c", "from playwright.sync_api import sync_playwright; print('OK')"],
-        stderr=subprocess.DEVNULL,
-    )
+    _phase(on_phase, _t("🔍 正在验证 Playwright 能否正常加载…", "🔍 Verifying that Playwright loads correctly…"))
+    if frozen:
+        # Frozen: no child interpreter to spawn; import in-process instead.
+        try:
+            from playwright.sync_api import sync_playwright  # noqa: F401
+            ret = 0
+        except Exception:
+            ret = 1
+    else:
+        ret = subprocess.call(
+            [python, "-c", "from playwright.sync_api import sync_playwright; print('OK')"],
+            stderr=subprocess.DEVNULL,
+        )
     if ret != 0:
         stream(
             "  Warning: playwright import failed. Browser tool may not work on this system.\n"
             "  Consider upgrading your OS or using Docker.",
             "yellow",
         )
-        _phase(on_phase, "⚠️ 验证未完全通过：本机可能仍无法使用浏览器工具，请查看日志或升级系统。")
+        _phase(on_phase, _t(
+            "⚠️ 验证未完全通过：本机可能仍无法使用浏览器工具，请查看日志或升级系统。",
+            "⚠️ Verification did not fully pass: the browser tool may still not work here; check the log or upgrade your system.",
+        ))
     else:
         stream("  Verification passed.", "green")
-        _phase(on_phase, "✅ 验证通过。")
+        _phase(on_phase, _t("✅ 验证通过。", "✅ Verification passed."))
 
     stream("")
     stream("Browser tool ready! Restart CowAgent to enable it.", "green")
-    _phase(on_phase, "🎉 全部步骤结束。请重启 CowAgent 后使用 browser 工具。")
+    _phase(on_phase, _t(
+        "🎉 全部步骤结束。请重启 CowAgent 后使用 browser 工具。",
+        "🎉 All steps finished. Restart CowAgent to use the browser tool.",
+    ))
     return 0
 
 

cli/commands/process.py

@@ -8,11 +8,28 @@ from typing import Optional
 
 import click
 
-from cli.utils import get_project_root
+from cli.utils import get_project_root, load_config_json
 
 _IS_WIN = sys.platform == "win32"
 
 
+def _is_terminal_only() -> bool:
+    """Whether terminal is the only configured channel.
+
+    Terminal needs an interactive stdin/tty, which is incompatible with the
+    background daemon mode (stdout/stdin detached). When terminal is the only
+    channel, `start` must run in the foreground so it can own the tty.
+    """
+    channel = load_config_json().get("channel_type", "")
+    if isinstance(channel, str):
+        names = [c.strip() for c in channel.split(",") if c.strip()]
+    elif isinstance(channel, (list, tuple)):
+        names = [str(c).strip() for c in channel if str(c).strip()]
+    else:
+        names = []
+    return names == ["terminal"]
+
+
 def _get_pid_file():
     return os.path.join(get_project_root(), ".cow.pid")
 
@@ -103,6 +120,12 @@ def start(foreground, no_logs):
 
     python = sys.executable
 
+    # Terminal-only setups need an interactive tty; force foreground so the
+    # terminal channel can read stdin instead of fighting the shell over the tty.
+    if not foreground and _is_terminal_only():
+        foreground = True
+        click.echo("Detected terminal-only channel, starting in foreground...")
+
     if foreground:
         click.echo("Starting CowAgent in foreground...")
         if _IS_WIN:
@@ -172,6 +195,120 @@ def restart(ctx, no_logs):
     ctx.invoke(start, no_logs=no_logs)
 
 
+# Detached relay that survives the caller's process tree. Run via `python -c`
+# with start_new_session=True so it keeps going after the agent's bash child
+# (and the main app it kills) both die. Flow: self-check the new code FIRST
+# (import app); abort without touching the old process if it fails. Only when
+# the new code is loadable does it SIGTERM the old PID, wait for exit (SIGKILL
+# fallback), then start a fresh app.py and write the pid.
+_RELAY_SCRIPT = r"""
+import os, sys, time, signal, subprocess
+
+root, python, app_py, pid_file, log_file = sys.argv[1:6]
+old_pid = int(sys.argv[6]) if len(sys.argv) > 6 and sys.argv[6] else 0
+
+
+def alive(pid):
+    if not pid:
+        return False
+    try:
+        os.kill(pid, 0)
+        return True
+    except OSError:
+        return False
+
+
+def log(msg):
+    try:
+        with open(log_file, "a") as f:
+            f.write("[self-restart] " + msg + "\n")
+    except OSError:
+        pass
+
+
+# 0) Self-check: make sure the new code actually loads BEFORE killing anything.
+# `import app` exercises top-level imports / syntax of the entry module. If it
+# fails, abort and leave the running service untouched — never end up with the
+# old process killed and the new one unable to start.
+check = subprocess.run(
+    [python, "-c", "import app"], cwd=root,
+    stdout=subprocess.PIPE, stderr=subprocess.STDOUT,
+)
+if check.returncode != 0:
+    detail = (check.stdout or b"").decode("utf-8", "replace").strip()
+    log("self-check FAILED, aborting restart; service left running:\n" + detail)
+    sys.exit(1)
+log("self-check passed")
+
+# 1) Ask the old process to exit gracefully (its SIGTERM handler persists state).
+if alive(old_pid):
+    try:
+        os.kill(old_pid, signal.SIGTERM)
+    except OSError:
+        pass
+    # 2) Wait up to ~15s for it to go, then force-kill as a backstop.
+    for _ in range(150):
+        if not alive(old_pid):
+            break
+        time.sleep(0.1)
+    else:
+        try:
+            os.kill(old_pid, signal.SIGKILL)
+        except OSError:
+            pass
+        time.sleep(0.5)
+
+# 3) Start a fresh instance, detached, logging to the same file.
+with open(log_file, "a") as f:
+    proc = subprocess.Popen(
+        [python, app_py], cwd=root,
+        stdout=f, stderr=f, start_new_session=True,
+    )
+with open(pid_file, "w") as f:
+    f.write(str(proc.pid))
+log("restarted, new pid=" + str(proc.pid))
+"""
+
+
+@click.command(name="self-restart", hidden=True)
+def self_restart():
+    """Restart from inside the running agent (detached; survives parent death).
+
+    Intended to be invoked by the agent itself (e.g. via bash after editing its
+    own code), not by users — so it is hidden from `cow help`. Unlike `restart`,
+    the actual stop+start runs in a detached relay process that outlives the
+    agent's bash child, which would otherwise die together with the main app it
+    kills.
+    """
+    if _IS_WIN:
+        click.echo("self-restart is not supported on Windows; use `cow restart`.", err=True)
+        sys.exit(1)
+
+    root = get_project_root()
+    app_py = os.path.join(root, "app.py")
+    if not os.path.exists(app_py):
+        click.echo("Error: app.py not found in project root.", err=True)
+        sys.exit(1)
+
+    python = sys.executable
+    pid = _read_pid() or 0
+
+    subprocess.Popen(
+        [
+            python, "-c", _RELAY_SCRIPT,
+            root, python, app_py, _get_pid_file(), _get_log_file(), str(pid),
+        ],
+        cwd=root,
+        start_new_session=True,
+        stdout=subprocess.DEVNULL,
+        stderr=subprocess.DEVNULL,
+    )
+    click.echo(click.style(
+        "✓ Restart scheduled. The service will stop and come back in a few seconds.",
+        fg="green",
+    ))
+
+
 @click.command()
 @click.pass_context
 def update(ctx):
@@ -252,7 +389,14 @@ def update(ctx):
 def status():
     """Show CowAgent running status."""
     from cli import __version__
-    from cli.utils import load_config_json
+    from cli.utils import load_config_json, get_cli_language, get_project_root
+
+    # get_cli_language() calls ensure_sys_path(), which adds the project root
+    # to sys.path. Import `common` only AFTER that, otherwise it fails with
+    # ModuleNotFoundError when `cow` runs from outside the project dir.
+    get_cli_language()  # resolve cow_lang so i18n.t reflects config
+    from common import i18n
+    _t = i18n.t
 
     pid = _read_pid()
     if pid:
@@ -260,17 +404,24 @@ def status():
     else:
         click.echo(click.style("● CowAgent is not running", fg="red"))
 
-    click.echo(f"  版本: v{__version__}")
+    click.echo(_t(f"  版本: v{__version__}", f"  Version: v{__version__}"))
+
+    # Project path bound to this `cow` CLI — disambiguates which checkout the
+    # command actually controls when the user has multiple clones.
+    project_root = get_project_root()
+    click.echo(_t(f"  路径: {project_root}", f"  Path: {project_root}"))
 
     cfg = load_config_json()
     if cfg:
         channel = cfg.get("channel_type", "unknown")
         if isinstance(channel, list):
             channel = ", ".join(channel)
-        click.echo(f"  通道: {channel}")
-        click.echo(f"  模型: {cfg.get('model', 'unknown')}")
+        click.echo(_t(f"  通道: {channel}", f"  Channel: {channel}"))
+        click.echo(_t(f"  模型: {cfg.get('model', 'unknown')}", f"  Model: {cfg.get('model', 'unknown')}"))
         mode = "Chat" if cfg.get("agent") is False else "Agent"
-        click.echo(f"  模式: {mode}")
+        click.echo(_t(f"  模式: {mode}", f"  Mode: {mode}"))
+        lang_label = "中文" if i18n.get_language() == "zh" else "English"
+        click.echo(_t(f"  语言: {lang_label}", f"  Language: {lang_label}"))
 
 
 @click.command()

cli/commands/skill.py

@@ -517,18 +517,26 @@ def _install_targz_bytes(content: bytes, name: str, skills_dir: str, result: Ins
 
 def _print_install_success(name: str, source: str):
     """Print a unified install success message with description and source."""
+    from cli.utils import get_cli_language
+
+    # Import `common` only after get_cli_language() runs ensure_sys_path(),
+    # so it works when `cow` is invoked from outside the project directory.
+    get_cli_language()  # resolve cow_lang so i18n.t reflects config
+    from common import i18n
+    _t = i18n.t
+
     skills_dir = get_skills_dir()
     config = load_skills_config()
     display = config.get(name, {}).get("display_name", "")
     desc = _read_skill_description(os.path.join(skills_dir, name))
     click.echo(click.style(f"✓ {name}", fg="green"))
     if display and display != name:
-        click.echo(f"  名称: {display}")
+        click.echo(_t(f"  名称: {display}", f"  Name: {display}"))
     if desc:
         if len(desc) > 60:
             desc = desc[:57] + "…"
-        click.echo(f"  描述: {desc}")
-    click.echo(f"  来源: {source}")
+        click.echo(_t(f"  描述: {desc}", f"  Description: {desc}"))
+    click.echo(_t(f"  来源: {source}", f"  Source: {source}"))
 
 
 def _validate_skill_name(name: str):