LLM call logging, plan persistence API, quote-to-feedback UX, requirement input improvements

- Add llm_call_log table and per-call timing/token tracking in agent loop
- New GET /workflows/{id}/plan endpoint to restore plan from snapshots on page load
- New GET /workflows/{id}/llm-calls endpoint + WS LlmCallLog broadcast
- Parse Usage from LLM API response (prompt_tokens, completion_tokens)
- Detailed mode toggle in execution log showing LLM call cards with phase/tokens/latency
- Quote-to-feedback: hover quote buttons on plan steps and log entries, multi-quote chips in comment input
- Requirement input: larger textarea, multi-line display with pre-wrap and scroll

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-03-02 09:16:51 +00:00
parent 46424cfbc4
commit 0a8eee0285
14 changed files with 601 additions and 26 deletions

View File

@@ -1,9 +1,7 @@
需求输入和展示,多行,复杂需求,界面不够优化,输入框不够大。
Agent runtime 重构:统一 ProjectState + 单写者模型、context 压缩、plan-centric 反馈处理(详见 doc/context.md
在前端计划和日志每一个条目都应有一个小小的comment按钮按一下直接快速引用然后输入docus到反馈输入那里表示要评论的是这
个地方。这样llm也知道用户具体在指啥。 同时允许多处引用再点一个其他的comment按钮就引用两处等等。按钮做的不要太眨眼间
如用hover显示或者就是小一点不占地方但要ui意图清晰易用。
template
---
时间观察app
---