zhayujie
ab28ee58ab
feat: add doubao-2.0-code model and update README
2026-02-14 16:49:44 +08:00
zhayujie
48db538a2e
feat: support Minimax-M2.5, glm-5, kimi-k2.5
2026-02-14 15:27:44 +08:00
cowagent
23fd6b8d2b
fix: handle non-string model_type to prevent AttributeError
...
When numeric model names (e.g., '1') are used with vLLM and configured
in YAML without quotes, they are parsed as integers. This causes
AttributeError when calling startswith() method.
Changes:
- Add type checking for model_type
- Convert non-string model_type to string with warning log
- Prevents crash when using custom numeric model names
Fixes #2664
2026-02-10 11:07:10 +08:00
zhayujie
4f0ea5d756
feat: make web search a built-in tool
2026-02-09 11:37:11 +08:00
zhayujie
051ffd78a3
fix: windows path and encoding adaptation
2026-02-06 18:37:05 +08:00
cowagent
eaa413caf0
fix: 补充缺失的 runtime_info 参数传递
...
问题：
PR #2655 已合并，但遗漏了关键的参数传递环节。runtime_info 在 agent_initializer.py 中创建并传递给 create_agent()，但 agent_bridge.py 的 create_agent() 方法中没有将其传递给 Agent 实例，导致动态时间更新功能无法生效。
影响：
- Agent 实例的 self.runtime_info 为 None
- get_full_system_prompt() 无法检测到动态时间函数
- 时间戳仍然是静态的，不会实时更新
修复：
在 agent_bridge.py 第 236 行添加：
runtime_info=kwargs.get("runtime_info")
这确保了完整的参数传递链路：
agent_initializer → agent_bridge.create_agent → Agent.__init__
---
*来自 [CowAgent](https://github.com/zhayujie/chatgpt-on-wechat ) 项目的 AI Agent*
2026-02-04 22:49:54 +08:00
cowagent
e4fcfa356a
refactor: 改用动态函数实现运行时信息更新（更健壮的方案）
...
改进点：
1. builder.py: _build_runtime_section() 支持 callable 动态时间函数
2. agent_initializer.py: 传入 get_current_time 函数而非静态时间值
3. agent.py: _rebuild_runtime_section() 动态调用时间函数并重建该部分
优势：
- 解耦模板：不依赖具体的提示词格式
- 健壮性：提示词模板改变不会导致功能失效
- 向后兼容：保留对静态时间的支持
- 性能优化：只在需要时才计算时间
相比之前的正则匹配方案，这个方案更加优雅和可维护。
2026-02-04 22:37:19 +08:00
saboteur7
501866d12a
feat: optimize document and model usage
2026-02-03 02:58:15 +08:00
zhayujie
46bcd87c23
feat: support minimax M2 models
2026-02-02 23:36:23 +08:00
zhayujie
ab74be8e33
feat: add qwen models tool call
2026-02-02 23:08:24 +08:00
zhayujie
d8298b3eab
fix: support glm-4.7
2026-02-02 22:43:08 +08:00
zhayujie
50e60e6d05
fix: bug fixes
2026-02-02 22:22:10 +08:00
zhayujie
46fa07e4a9
feat: optimize agent configuration and memory
2026-02-02 11:48:53 +08:00
zhayujie
a8d5309c90
feat: add skills and upgrade feishu/dingtalk channel
2026-02-02 00:42:39 +08:00
zhayujie
4c8712d683
feat: key management and scheduled task tools
2026-02-01 19:21:12 +08:00
zhayujie
c693e39196
feat: improve the memory system
2026-02-01 17:04:46 +08:00
zhayujie
4a1fae3cb4
chore: the bot directory was changed to models
2026-02-01 15:21:28 +08:00
zhayujie
0e85fcfe51
fix: optimize suggestion words and retries
2026-02-01 14:00:28 +08:00
zhayujie
9bf5b0fc48
fix: tool call failed problem
2026-02-01 12:31:58 +08:00
zhayujie
07959a3bff
fix: first conversation bug
2026-01-31 17:53:12 +08:00
zhayujie
86a6182e41
fix: add logs
2026-01-31 17:29:32 +08:00
zhayujie
624917fac4
fix: memory and path bug
2026-01-31 16:53:33 +08:00
saboteur7
dd6a9c26bd
feat: support skills creator and gemini models
2026-01-30 18:00:10 +08:00
saboteur7
49fb4034c6
feat: support skills
2026-01-30 14:27:03 +08:00
saboteur7
bb850bb6c5
feat: personal ai agent framework
2026-01-30 09:53:46 +08:00
6vision
f2e4f6607d
feat：support claude-4-opus and claude-4-sonnet models
2025-05-23 17:07:46 +08:00
yanrk123
cec900168f
Modify model list
2025-03-14 13:56:00 +08:00
yanrk123
c139fd9a57
support stream mode for QwQ-32B
2025-03-12 15:45:52 +08:00
yanrk123
7777a53a82
Add supported model list
2025-03-11 16:34:43 +08:00
yanrk123
3e185dbbfe
Add support for ModelScope API
2025-03-11 11:12:57 +08:00
vision
8b0b360d25
Merge pull request #2288 from KuroIVeko/patch-3
...
Support more models from Zhipu AI
2024-09-25 22:28:16 +08:00
KurolVeko
6b02bae957
Update bridge.py
2024-09-05 10:59:57 +08:00
6vision
f6e6805453
fix: "model":"mooshoot", which defaults to "moonshot-v1-32k".
2024-08-31 16:09:10 +08:00
6vision
bb2880191a
update gemini model
2024-07-04 01:22:55 +08:00
Saboteur7
7090722565
Merge branch 'master' into master
2024-06-20 15:21:20 +08:00
6vision
ca8e06e562
兼容符合openai请求格式的三方服务，根目录的config.json里增加配置"bot_type": "chatGPT"
2024-06-13 16:43:03 +08:00
limy26
200cd33a8e
feat#add minmax model
2024-06-12 19:30:24 +08:00
zhayujie
fb72b601aa
fix: model config
2024-05-03 19:41:12 +08:00
zhayujie
e4ac3afa4d
Merge pull request #1849 from wayshall/kimi
...
feat: 增加moonshot api集成
2024-04-26 15:17:52 +08:00
weishao zeng
5e399c46b1
feat: 通义千问使用新版的sdk实现
...
现在项目使用的通义千问是旧版本的百炼sdk，
这里增加一个新版本sdk(dashscope)的实现
2024-03-27 19:12:39 +08:00
weishao zeng
38e1db7a37
feat: 增加moonshot api集成
...
moonshot本来可直接使用openai sdk，
但是要求openai sdk必须在1.0以上，与本项目冲突，
故现使用http接口对接的方式集成
2024-03-27 15:02:51 +08:00
zhayujie
cac7a6228a
fix: claude api optimize
2024-03-25 21:41:40 +08:00
zhayujie
674fbc3f69
Merge pull request #1810 from FB208/master
...
增加了claude api的调用方法
2024-03-25 20:42:59 +08:00
rowan.wu
8093fcc64c
修复两处BUG
...
1、类型定义中使用了驼峰，但其他位置使用的大写
2、微信channel中，发送IMAGE，多余了seek方法
2024-03-16 12:34:40 +08:00
FB208
805bea0d5f
增加了claude api的调用方法
2024-03-12 10:39:51 +08:00
zR
d6fdf8ca2a
支持ZhipuAI GLM系列模型和画图代码
2024-02-01 11:31:56 +08:00
zhayujie
23a237074e
feat: support gemini model
2023-12-15 10:19:48 +08:00
zhayujie
ae4077ed6c
fix: config adjust
2023-12-08 14:29:14 +08:00
zhayujie
6eb3c90e18
feat: qwen model modify
2023-12-08 14:12:21 +08:00
zhayujie
74db1e0308
Merge pull request #1537 from hanfangyuan4396/master
...
支持阿里云百炼平台通义千问模型
2023-12-08 13:27:52 +08:00
