Fam Zheng 0a8eee0285 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>

2026-03-02 09:16:51 +00:00

..

context.md

Refactor agent runtime: state machine, feedback processing, execution log

2026-03-02 08:54:43 +00:00

deploy.md

Add deployment documentation and deploy script

2026-02-28 10:56:51 +00:00

design.md

Tori: AI agent workflow manager - initial implementation

2026-02-28 10:36:50 +00:00

kb.md

Add global knowledge base with RAG search

2026-03-01 08:15:50 +00:00

templates.md

App-templates: LLM auto-selects project template based on user requirement

2026-03-01 21:33:40 +00:00

todo.md

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

2026-03-02 09:16:51 +00:00