zhayujie
c6824e5f5e
fix: add legacy-cgi dependency for Python 3.13+ #2758
...
Add conditional dependency `legacy-cgi` for Python 3.13+ to resolve
`web.py` installation failure caused by the removal of the `cgi` module
(PEP 594).
Thanks @sha156 for reporting.
2026-04-12 16:49:00 +08:00
zhayujie
199c21eede
Merge pull request #2761 from zhayujie/feat-knowledge
...
feat: personal knowledge base system
2026-04-12 16:47:07 +08:00
zhayujie
5162da5654
Merge branch 'master' into feat-knowledge
2026-04-12 16:46:38 +08:00
zhayujie
a1d82f6193
feat(knowledge): add cli and update docs
2026-04-12 16:39:06 +08:00
zhayujie
ea78e3d0c6
feat(knowledge): document link supports jumping to view
2026-04-11 20:16:43 +08:00
zhayujie
3497f00cb4
Merge pull request #2759 from zhayujie/feat-multimodel
...
feat(vision): prioritize main model for image recognition
2026-04-11 19:55:15 +08:00
zhayujie
5355d45031
Merge pull request #2756 from octo-patch/feature/add-minimax-m2.7-highspeed-tts
...
feat: add MiniMax-M2.7-highspeed model and MiniMax TTS support
2026-04-11 19:54:03 +08:00
zhayujie
26693acc3f
feat(vision): prioritize main model for image recognition with multi-provider fallback
...
- Add call_vision method to all bot implementations (DashScope, Claude,
Gemini, ZhipuAI, MiniMax, Doubao, Moonshot, OpenAICompatibleBot)
using each vendor's native multimodal API format
- Remove call_with_tools/call_vision from Bot base class to fix MRO
shadowing issue with OpenAICompatibleBot mixin
- Refactor vision tool provider resolution: MainModel → other configured
models (auto-discovered) → OpenAI → LinkAI, with automatic fallback
- Return actual model name used in call_vision responses
- Sync config.json API keys to .env bidirectionally on startup
- Fix bot instance cache to detect bot_type/use_linkai config changes
- Add SSE reconnection support for web console
- Preserve image path hints in Gemini text for correct vision tool calls
- Update docs/tools/vision.mdx
2026-04-11 19:46:11 +08:00
zhayujie
76e9fef3b2
feat(knowledge): add file list and graph in web channel
2026-04-11 19:02:55 +08:00
octo-patch
c34308cbd4
feat: add MiniMax-M2.7-highspeed model and MiniMax TTS support
...
- Add MiniMax-M2.7-highspeed constant to const.py and MODEL_LIST
- Update MinimaxBot default model from MiniMax-M2.1 to MiniMax-M2.7
- Add MinimaxVoice TTS provider (voice/minimax/minimax_voice.py)
- Supports speech-2.8-hd and speech-2.8-turbo models
- SSE streaming with hex-decoded audio chunks
- Reuses MINIMAX_API_KEY
- Register MinimaxVoice in voice factory
- Add unit tests (14 tests, all passing)
- Update README with MiniMax-M2.7-highspeed and TTS configuration
2026-04-11 17:03:44 +08:00
zhayujie
5a10476010
feat: add knowledge switch and cli
2026-04-11 16:44:25 +08:00
zhayujie
46e80dceec
Merge pull request #2755 from 6vision/fix/generic-file-send
...
fix: send generic file types (tar.gz, zip, etc.) as FILE instead of TEXT
2026-04-11 16:36:34 +08:00
6vision
90d1835353
fix: send generic file types (tar.gz, zip, etc.) as FILE instead of TEXT
...
Previously, files with extensions not in the known categories (image, document, video, audio) fell through to a fallback that returned ReplyType.TEXT, causing the file to never actually be sent to the user. Now the fallback uses ReplyType.FILE so all file types are delivered.
Made-with: Cursor
2026-04-11 15:45:34 +08:00
zhayujie
845fadd0aa
fix(knowledge): modify knowledge skill
2026-04-10 18:22:54 +08:00
zhayujie
5748ded52c
feat(knowledge): change knowledge base to index-driven self-organizing structure
2026-04-10 16:06:04 +08:00
zhayujie
6a737fb734
feat: display thinking content in web console
2026-04-10 15:07:23 +08:00
zhayujie
3cd92ccda3
feat: add port config
2026-04-09 21:29:53 +08:00
zhayujie
54e81aba11
feat(memory+knowledge): add knowledge wiki system and Light Dream memory extraction
...
- Add knowledge/ directory structure and knowledge-wiki skill for structured knowledge accumulation
- Auto-inject MEMORY.md into system prompt with truncation (last 200 lines)
- Light Dream: extend flush_memory to extract long-term memories into MEMORY.md with date stamps
- Add mandatory knowledge auto-write rules in system prompt (no user confirmation needed)
- Expand MemoryManager.sync() to index knowledge/ files for vector search
- Update RULE.md template with workspace conventions and knowledge guidelines
2026-04-09 21:22:43 +08:00
zhayujie
d86cb4ded6
fix(weixin): update weixin channel version
2026-04-09 09:55:07 +08:00
zhayujie
4d5375f6d6
fix(win): add Windows platform hint in bash tool description
2026-04-08 16:54:26 +08:00
zhayujie
424557fedb
fix(win): use PowerShell instead of cmd.exe
2026-04-08 16:50:45 +08:00
zhayujie
89251e603f
fix(win): use PowerShell instead of cmd.exe for bash tool on Windows
2026-04-08 16:18:56 +08:00
zhayujie
a653ed07eb
fix(win): defer pip install to a helper bat after cow.exe exits
2026-04-08 15:31:03 +08:00
zhayujie
ad86deb014
fix: prioritize using a custom master model for vision
2026-04-08 15:16:59 +08:00
zhayujie
9525dc7584
fix: avoid stale cow.exe on Windows by spawing fresh process
2026-04-08 12:07:18 +08:00
zhayujie
cd31dd27fd
fix: increase web console capacity and add frontend retry
2026-04-08 11:48:27 +08:00
zhayujie
360e3670eb
feat(browser): detect implicit interactive elements
2026-04-07 01:41:14 +08:00
zhayujie
8dabe3b4c8
fix: remove install-browser cmd display in /help
2026-04-04 23:28:57 +08:00
zhayujie
443e0c2806
feat: show video in web channel
2026-04-03 17:09:38 +08:00
zhayujie
9cc173cc4d
fix: use dynamic model name in system prompt runtime info
2026-04-02 17:01:56 +08:00
zhayujie
b5f33e5ecd
feat: support qwen3.6-plus
2026-04-02 16:46:58 +08:00
zhayujie
40dfc6860f
fix: skill list showing sub-skills inside collection
2026-04-02 11:47:24 +08:00
zhayujie
1c02a04423
fix: handle error when printing QR code on Windows GBK terminals
2026-04-01 17:23:57 +08:00
zhayujie
de0e45070c
chore: remove conflicting dependency
2026-04-01 17:19:15 +08:00
zhayujie
c169cc7d74
fix: remove conflicting dependency
2026-04-01 17:12:15 +08:00
zhayujie
cd62ad76f6
fix: cow CLI support python3.7
2026-04-01 16:51:23 +08:00
zhayujie
dd25b0fb5b
feat: refine system prompt style and tone guidance
2026-04-01 16:24:41 +08:00
zhayujie
a38b22a6a2
docs: update docs
2026-04-01 15:31:41 +08:00
zhayujie
830b8f2971
feat: release 2.0.5
2.0.5
2026-04-01 15:01:53 +08:00
zhayujie
b058af122c
feat: release 2.0.5
2026-04-01 12:24:21 +08:00
zhayujie
174ee0cafc
fix(security): prevent path traversal in memory content API
2026-04-01 10:03:58 +08:00
zhayujie
1c336380c0
docs: update release doc
2026-03-31 22:30:31 +08:00
zhayujie
3068880413
feat: save skill display name when downloading
2026-03-31 21:43:57 +08:00
zhayujie
be596681e5
Merge pull request #2735 from zhayujie/feat-wecom-bot-qrcode
...
feat(wecom_bot): add Wecom Bot QR code scan auth
2026-03-31 21:28:39 +08:00
zhayujie
66b71c50e9
feat(wecom_bot): add Wecom Bot QR code scan auth
2026-03-31 21:27:50 +08:00
zhayujie
8744810b25
fix: skill install timeout
2026-03-31 20:47:59 +08:00
zhayujie
7f94d37c2e
fix: auto-install font in browser
2026-03-31 20:20:13 +08:00
zhayujie
6d9b7baeb4
fix(weixin): file send failed
2026-03-31 18:14:49 +08:00
zhayujie
4470d4c352
fix: reduce docker image size
2026-03-31 16:56:27 +08:00
zhayujie
d2a462a279
fix: add apt source in docker file
2026-03-31 16:34:47 +08:00