gongzhiyongandClaude Sonnet 4.6
c6ca9dc126
workspace/ files existed on disk but were not included in previous incremental commit, causing git to record them as deleted. Re-adding all workspace card components, AgentWorkspace, ActivityTimeline, and WorkspaceCardRenderer to properly track them. Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
29 lines
1.1 KiB
Markdown
29 lines
1.1 KiB
Markdown
# CoT (Chain of Thought) 实现方案
|
||
|
||
> 目标：当用户选择 Auto 或 Pro 模式时，实时展示模型推理过程（正在做什么）
|
||
|
||
## 文档结构
|
||
|
||
- [architecture.md](./architecture.md) — 整体架构与数据流
|
||
- [backend.md](./backend.md) — 后端实现方案（Python/LangGraph）
|
||
- [frontend.md](./frontend.md) — 前端实现方案（Next.js/React）
|
||
|
||
## 核心结论
|
||
|
||
**方案选择：Prompt 标签 + 流式状态机解析**
|
||
|
||
| 方案 | 描述 | 结论 |
|
||
|------|------|------|
|
||
| A. 原生 reasoning tokens | Azure o1/o3 的 reasoning_content | 备用升级路径，gpt-5.4 支持情况待验证 |
|
||
| B. Prompt 标签解析 ✅ | 注入 `<think>` 标签，流式解析 | **默认实现**，兼容所有 GPT 模型 |
|
||
| C. LangGraph 多节点 | 专门的 thinking 节点 | 双倍延迟/成本，不采用 |
|
||
|
||
## Auto vs Pro 差异
|
||
|
||
| 维度 | Flash | Auto | Pro |
|
||
|------|-------|------|-----|
|
||
| CoT | 关闭 | 轻量（关键决策点） | 完整（每步详细推理） |
|
||
| max_tokens | 500 | 2048 | 4096 |
|
||
| temperature | 0.2 | 0.3 | 0.3 |
|
||
| 前端 thinking UI | 无 | 3个脉冲点，done后消失 | 可折叠 thinking block |
|