kaiyuan/chatgpt-on-wechat
1
0
Fork 0
mirror of https://github.com/zhayujie/chatgpt-on-wechat.git synced 2026-06-02 00:57:41 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(models): unify enable_thinking for deepseek-v4 and other thinking models

Browse Source
This commit is contained in:
zhayujie
2026-04-24 15:22:45 +08:00
parent 472a8605c0
commit ae11159918
12 changed files with 91 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/intro/architecture.mdx
View File

@@ -81,5 +81,5 @@ Agent 的工作空间默认位于 `~/cow` 目录，用于存储系统提示词
| `agent_max_context_tokens` | 最大上下文 token 数 | `50000` |
| `agent_max_context_turns` | 最大上下文记忆轮次 | `20` |
| `agent_max_steps` | 单次任务最大决策步数 | `20` |
| `enable_thinking` | 是否启用深度思考，开启后 Web 端展示推理过程，关闭可加速响应 | `false` |
| `enable_thinking` | 是否启用深度思考模式（适用于 deepseek-v4-pro/flash、deepseek-reasoner、kimi-k2-thinking 等思考型模型）。开启后所有渠道下模型都会先思考再回答，回答质量更高但首字延迟增加；Web 端会展示思考过程，IM 渠道（微信/企微/钉钉/飞书）虽不展示但同样获得更好答案 | `false` |
| `knowledge` | 是否启用个人知识库 | `true` |