6vision
d0a70d3339
update:Adjust bot_type resolution priority in Agent mode
2026-03-10 15:14:01 +08:00
zhayujie
f37e4675dd
Merge pull request #2691 from Weikjssss/fix-bot-type-conf
...
fix: pass bot_type in agent mode
2026-03-10 15:00:04 +08:00
zhayujie
4e32f67eeb
fix: validate tool_call_id pairing #2690
2026-03-10 14:52:07 +08:00
Weikjssss
36d54cab52
fix: pass bot_type in agent mode
2026-03-10 14:28:39 +08:00
zhayujie
9d8df10dcf
feat: clarify send tool is local-only
2026-03-10 12:10:10 +08:00
zhayujie
45ea88e070
Merge pull request #2689 from cowagent/fix/openai-compat-complete
...
fix: complete openai_compat migration across all model bots (openai>=1.0 compatibility)
2026-03-10 10:10:58 +08:00
cowagent
d5d0b947f5
fix: complete openai_compat migration across all model bots
...
Replace all direct openai.error.* usages with the openai_compat
compatibility layer to support openai>=1.0.
Affected files:
- models/chatgpt/chat_gpt_bot.py: fix isinstance checks (RateLimitError, Timeout, APIError, APIConnectionError)
- models/openai/open_ai_bot.py: replace import + fix isinstance checks
- models/ali/ali_qwen_bot.py: replace import + fix isinstance checks
- models/modelscope/modelscope_bot.py: remove unused openai.error import
The openai_compat layer (models/openai/openai_compat.py) already
handles both openai<1.0 and openai>=1.0 gracefully. This completes
the migration started in the existing PR #2688 .
2026-03-10 10:06:04 +08:00
zhayujie
f775f1f11e
Merge pull request #2688 from JasonOA888/fix/openai-compat
...
fix: use openai_compat layer for error handling (openai>=1.0 compatibility)
2026-03-10 10:02:41 +08:00
JasonOA888
f1e888f3de
fix: use openai_compat layer for error handling
...
The code was directly importing openai.error which fails with openai>=1.0.
The project already has an openai_compat.py compatibility layer that handles
both old (<1.0) and new (>=1.0) OpenAI SDK versions.
This commit updates chat_gpt_bot.py to use the compatibility layer.
Related: #2687
2026-03-10 00:33:45 +08:00
zhayujie
71c8436e90
fix: skill download to temp dir
2026-03-09 18:43:28 +08:00
zhayujie
08c69f5e9b
fix: clean existing skill directory before remote install to ensure full overwrite
2026-03-09 17:23:09 +08:00
zhayujie
a50fafaca2
refactor: convert image vision from skill to native tool
2026-03-09 16:01:56 +08:00
zhayujie
3c6781d240
refactor: inline skill-creator reference files into SKILL.md
2026-03-09 12:02:52 +08:00
zhayujie
3b8b5625f8
feat: add image vision provider
2026-03-09 11:37:45 +08:00
zhayujie
6be2034110
feat: add fallback embedding provider
2026-03-09 11:03:31 +08:00
zhayujie
924dc79f00
perf: lazy import to avoid 4-10s startup delay
2026-03-09 10:21:58 +08:00
zhayujie
ccb9030d3c
refactor: convert web-fetch from skill to native tool
2026-03-09 10:13:48 +08:00
zhayujie
8623287ac1
docs: update memory system docs
2026-03-08 22:06:28 +08:00
zhayujie
022c13f3a4
feat: upgrade memory flush system
...
- Use LLM to summarize discarded context into concise daily memory entries
- Batch trim to half when exceeding max_turns/max_tokens, reducing flush frequency
- Run summarization asynchronously in background thread, no blocking on replies
- Add daily scheduled flush (23:55) as fallback for low-activity days
- Sync trimmed messages back to agent to keep context state consistent
2026-03-08 21:56:12 +08:00
zhayujie
0687916e7f
fix: Safari IME enter key triggering message send
...
Made-with: Cursor
2026-03-08 13:21:31 +08:00
zhayujie
bb868b83ba
feat: add chat history query
2026-03-08 13:03:27 +08:00
zhayujie
24298130b9
fix: minimax tool_id missing
2026-03-06 18:42:03 +08:00
zhayujie
6e5ee92ebd
docs: add gpt-5.4
2026-03-06 12:25:50 +08:00
zhayujie
5b91fe04aa
fix: send tool process url
2026-03-06 12:22:22 +08:00
zhayujie
1623deb3ee
feat: support gpt-5.4
2026-03-06 12:04:40 +08:00
zhayujie
4a16e05b7a
fix: rebuild skills when installing
2026-03-05 21:11:34 +08:00
zhayujie
f1c04bc60d
feat: improve channel connection stability
2026-03-05 15:55:16 +08:00
zhayujie
84c6f31c76
fix: update agent skill metadata
2026-03-03 18:16:42 +08:00
zhayujie
9d528190bf
feat: add skill category
2026-03-03 16:06:37 +08:00
zhayujie
0f23b209ad
fix: adjust the context of restart loading
2026-03-03 11:38:14 +08:00
zhayujie
63d9325900
Merge pull request #2683 from pelioo/master
...
更新.gitignore文件添加python目录忽略规则
2026-03-01 19:41:27 +08:00
peli
f342097f81
Merge remote-tracking branch 'upstream/master'
2026-03-01 00:24:14 +08:00
zhayujie
b4806c4366
fix: model provider config
2026-02-28 18:35:04 +08:00
zhayujie
ff37d8a577
Merge branch 'master' of github.com:zhayujie/chatgpt-on-wechat
2026-02-28 18:10:55 +08:00
zhayujie
a773eb7893
fix: filter history to one user and one assistant per turn
2026-02-28 18:09:02 +08:00
zhayujie
7c67513d24
fix: convert bash-style $VAR to %VAR% on Windows
2026-02-28 18:02:06 +08:00
zhayujie
6ed85029c5
fix: agent skills
2026-02-28 16:46:49 +08:00
zhayujie
e9c57ddf4d
fix: adjust default turns
2026-02-28 15:25:20 +08:00
zhayujie
a33ce97ed9
fix: restore only user/assistant text from history, strip tool calls
...
Made-with: Cursor
2026-02-28 15:14:56 +08:00
zhayujie
b788a3dd4e
fix: incomplete historical session messages
2026-02-28 15:03:33 +08:00
zhayujie
fccfa92d7e
docs: update channel docs
2026-02-28 14:50:55 +08:00
zhayujie
8705bf0a70
feat: update docs
2026-02-28 10:53:16 +08:00
peli
9318138af7
```
...
build(env): 更新.gitignore文件添加python目录忽略规则
在.gitignore文件中新增了python目录的忽略配置，
避免将Python环境相关文件提交到版本控制系统中。
```
2026-02-27 23:49:35 +08:00
zhayujie
269fa7d2d5
feat: 2.0.2 en docs
2026-02-27 18:37:22 +08:00
zhayujie
e99837a8b9
feat: release 2.0.2
2026-02-27 18:04:00 +08:00
zhayujie
553861a2c4
docs: update README.md
2026-02-27 16:57:18 +08:00
zhayujie
628a85d1be
docs: update README.md
2026-02-27 16:48:23 +08:00
zhayujie
2cb54514a4
Merge pull request #2681 from zhayujie/feat-docs
...
feat: docs update
2026-02-27 16:04:17 +08:00
zhayujie
6db22827f2
feat: docs update
2026-02-27 16:03:47 +08:00
zhayujie
4cc6d5426b
Merge pull request #2680 from zhayujie/feat-web-config
...
feat: web console config
2026-02-27 14:40:44 +08:00
