Commit Graph

136 Commits

Author SHA1 Message Date
zhayujie
73bf83d2ff docs: add public-access notes for server deployment 2026-05-25 00:09:52 +08:00
zhayujie
36e1988fee docs: update README.md 2026-05-24 19:21:06 +08:00
zhayujie
aad6ef635e docs: update README.md 2026-05-24 19:11:34 +08:00
zhayujie
96659cd616 docs: update project docs 2026-05-24 18:58:10 +08:00
zhayujie
91d427c8f9 docs: update docs and readme 2026-05-24 18:29:57 +08:00
zhayujie
29af855ecd docs: update README.md 2026-05-24 18:03:33 +08:00
zhayujie
0a146a245d docs: refactor README 2026-05-24 17:52:47 +08:00
zhayujie
069bffa3e8 feat: release 2.0.9 2026-05-22 12:25:22 +08:00
zhayujie
2517f2add8 feat(models): support gpt-5.5 2026-05-22 11:04:55 +08:00
zhayujie
a534266025 feat(models): add qwen3.7-max 2026-05-22 10:54:56 +08:00
zhayujie
8c25395805 feat(models): support gemini-3.5-flash 2026-05-22 10:39:04 +08:00
zhayujie
36b913124b docs: update models and channels doc 2026-05-22 10:10:07 +08:00
zhayujie
b8333e351c feat(voice): rework TTS/ASR stack and unify tool/skill config schema 2026-05-21 16:00:54 +08:00
zhayujie
a0dfdb79df feat(browser): persistent login + CDP attach mode #2809
Browser sessions now reuse a Chromium user profile across runs by default
(`~/.cow/browser_profile`), so users only log in to a site once.
Three launch modes are selectable via `tools.browser` in config.json:
  - persistent (default): Playwright Chromium with a persistent user_data_dir
  - cdp: attach to an externally launched real Chrome via `cdp_endpoint`
    (full fingerprints, ideal for sites with strict bot detection)
  - fresh: clean context every run, set `persistent: false`

Also:
  - Self-heal when the user closes the browser window mid-session: detect
    closed page/context/browser via close listeners and exception scanning,
    then transparently relaunch on the next request.
  - Graceful CDP shutdown: disconnect only, never kill the user's Chrome.
  - Friendly errors when the CDP endpoint is unreachable or the persistent
    profile is locked, so the LLM can guide the user instead of looping.
  - Fix tool config being silently overwritten by workspace config in
    AgentInitializer; per-tool user settings (e.g. browser.cdp_endpoint)
    are now merged instead of replaced.
  - Update zh / en / ja docs with the new login-persistence section,
    including the Chrome 137+ requirement to pair --remote-debugging-port
    with a dedicated --user-data-dir.
2026-05-19 11:52:11 +08:00
zhayujie
16d9b449c9 feat(web): set the web_host to the default value of 127.0.0.1 2026-05-16 18:18:17 +08:00
zhayujie
8761997757 feat(web): add web_host config and password hint for safer deployment 2026-05-16 17:37:07 +08:00
zhayujie
f5479c56af feat(models): support reasoning_effort config for DeepSeek V4 2026-05-15 18:17:35 +08:00
zhayujie
ff5d477fa5 Merge pull request #2808 from yangluxin613/fix/update-username-in-docs
docs: update contributor username from ooaaooaa123 to yangluxin613
2026-05-10 18:42:09 +08:00
zhayujie
907825601d feat(models): add baidu ernie-5.1 2026-05-10 18:39:38 +08:00
ooaaooaa123
c2ec26910a docs: update contributor username from ooaaooaa123 to yangluxin613 2026-05-10 18:12:00 +08:00
zhayujie
fb341b869b docs(mcp): add MCP tools guide 2026-05-08 16:14:48 +08:00
zhayujie
55aaf60a57 feat: release 2.0.8 2026-05-06 16:19:20 +08:00
zhayujie
a5790d82f6 feat(qianfan): scope vision support to multimodal models 2026-05-06 16:11:10 +08:00
jimmyzhuu
fb7962c7f2 fix: use available qianfan vision model 2026-05-06 13:34:39 +08:00
jimmyzhuu
76e6b7b471 docs: document qianfan vision support 2026-05-06 13:28:46 +08:00
zhayujie
c322c0e3a5 docs(models): add ernie-5.0 2026-05-06 12:15:14 +08:00
zhayujie
530fc20596 Merge pull request #2790 from jimmyzhuu/feat/qianfan-provider
Add first-class Baidu Qianfan / ERNIE provider
2026-05-06 11:43:32 +08:00
zhayujie
a9c8a59f58 feat(feishu): one-click QR-scan app creation 2026-05-05 18:32:58 +08:00
zhayujie
b80c3fe5a8 feat(feishu): enhance #2791 with cardkit streaming + ASR fixes
- rewrite streaming reply to official cardkit v2.0 API (default on, auto-fallback)
- fix Whisper hallucination: bump ASR sample rate to 16k, pass language=zh
- fix lock-over-IO and tmp file cleanup from #2791
- drop deprecated feishu_bot_name; quiet unknown-key warnings
- docs: cardkit permission and feishu_stream_reply usage
2026-05-05 14:15:25 +08:00
zhayujie
80e9062041 fix(vision): respect tool.vision.model and add automatic fallback #2792 2026-05-03 22:28:32 +08:00
zhayujie
67bd3420ed perf(scheduler): bound isolated session context to agent_max_context_turns/5 2026-05-03 21:49:59 +08:00
zhayujie
aea081703f fix(scheduler): inject delivered output into receiver session with sliding window
Further refinements on top of #2795:

- persist real session_id (notify_session_id) at task creation so group chats
  correctly map back to the user's actual conversation
- mark scheduler turns with [SCHEDULED] (recognise legacy "Scheduled task"
  prefix too for backward-compatible pruning)
- prune both DB and in-memory to scheduler_inject_max_per_session (default 3),
  only marker-tagged pairs are touched; regular user turns never deleted
- send_message type gated by scheduler_inject_send_message (default false) —
  fixed reminder text rarely benefits follow-up Q&A

Co-authored-by: huangrichao2020 <grdomai43881@gmail.com>
2026-05-03 21:27:24 +08:00
jimmyzhuu
bc7f953fcc docs: add qianfan provider guide 2026-04-29 16:41:25 +08:00
zhayujie
0e556b3468 feat: switch default model to deepseek-v4-flash 2026-04-26 15:54:50 +08:00
zhayujie
31820f56e7 fix(deepseek): back-fill reasoning_content for all assistant turns 2026-04-24 16:39:48 +08:00
zhayujie
ae11159918 feat(models): unify enable_thinking for deepseek-v4 and other thinking models 2026-04-24 15:22:45 +08:00
zhayujie
472a8605c0 feat(models): support deepseek-v4-pro and deepseek-v4-flash 2026-04-24 11:35:38 +08:00
zhayujie
64511593c4 feat: release 2.0.7 2026-04-23 17:16:17 +08:00
zhayujie
b0e00dfceb feat: support glm-5.1 2026-04-23 16:43:05 +08:00
zhayujie
fc465b463d feat: support kimi coding plan by temporary solution 2026-04-23 16:24:37 +08:00
zhayujie
68ce2e5232 feat(skill): multi-provider image generation with auto-fallback
- Add Gemini, Seedream (Volcengine Ark), Qwen (DashScope), MiniMax
  providers to image-generation skill with universal sequential
  fallback: OpenAI → Gemini → Seedream → Qwen → MiniMax → LinkAI
- Each provider filters unsupported size tiers to valid values
  (e.g. Seedream 1K→2K, Qwen 3K→2K, Gemini 3K→2K)
- Pinned model only tries its native provider; auto-routing uses
  each provider's default model
- Support skill-namespaced config (config.skill.image-generation.model
  → SKILL_IMAGE_GENERATION_MODEL env var)
- Add image lightbox (click-to-enlarge) in web console
- Add  docs for built-in skills (skill-creator, knowledge-wiki,
  image-generation) under docs/skills/
2026-04-23 12:39:39 +08:00
zhayujie
2c13e1b923 feat(models): support kimi-k2.6 2026-04-22 12:01:40 +08:00
zhayujie
54c7676a44 docs: update architecture diagram 2026-04-18 23:08:36 +08:00
zhayujie
26e630c2dd feat(cli): /config support set enable_thinking 2026-04-17 16:09:43 +08:00
zhayujie
13370d2056 fix: thinking display is disabled by default 2026-04-17 15:31:59 +08:00
zhayujie
35282db9e0 feat(models): support claude-opus-4-7 2026-04-16 23:24:16 +08:00
zhayujie
3830f76729 feat: add custom model provider 2026-04-15 12:26:05 +08:00
zhayujie
cabd24605f fix: add random jitter to daily dream schedule 2026-04-15 00:33:33 +08:00
zhayujie
1c18bd9889 docs(memory): update long-term memory docs 2026-04-14 17:14:28 +08:00
zhayujie
60e9d98d0a feat: release 2.0.6 2026-04-14 12:37:53 +08:00