36fa50173f
Tasks completed: 2/2 - Backend prompts router with 4 CRUD endpoints - Frontend Prompt Editor page with types, hooks, route, sidebar SUMMARY: .planning/phases/02-prompt-control-output-review/02-01-SUMMARY.md Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
3.2 KiB
Project State
Project Reference
See: .planning/PROJECT.md (updated 2026-03-07)
Core value: Generare un calendario di 13 caroselli Instagram strategicamente orchestrati, pronti per Canva Bulk Create, con un click dalla Web UI. Current focus: Phase 2 in corso — Prompt Control + Output Review
Current Position
Phase: 2 of 4 (Prompt Control + Output Review) Plan: 1 of 2 in current phase Status: In progress — 02-01 completato, 02-02 da eseguire Last activity: 2026-03-08 — Completed 02-01-PLAN.md (Prompt CRUD + Prompt Editor UI)
Progress: [█████░░░░░] 55% (5/9 piani totali)
Performance Metrics
Velocity:
- Total plans completed: 5
- Average duration: ~7 min
- Total execution time: 38 min
By Phase:
| Phase | Plans | Total | Avg/Plan |
|---|---|---|---|
| 01-core-generation-pipeline | 4/4 COMPLETA | 33 min | 8 min |
| 02-prompt-control-output-review | 1/2 | 5 min | 5 min |
Recent Trend:
- Last 5 plans: 6 min, 9 min, 8 min, 10 min, 5 min
- Trend: velocita' in aumento
Updated after each plan completion
Accumulated Context
Decisions
Decisions are logged in PROJECT.md Key Decisions table. Recent decisions affecting current work:
- [Setup]: FastAPI root_path SOLO via Uvicorn (--root-path), mai nel costruttore FastAPI()
- [Setup]: CSV encoding = utf-8-sig (BOM) sempre; CANVA_FIELDS locked come costante
- [Setup]: Prompt di sistema scritti IN italiano
- [Setup]: Per-item error isolation dal primo loop di generazione
- [01-01]: root_path SOLO via Uvicorn --root-path nel Dockerfile CMD
- [01-01]: API_BASE='/postgenerator/api' nel frontend — Pitfall #9 risolto
- [01-02]: CANVA_FIELDS 33 colonne con _image_keyword (non URL) — URL Unsplash in Phase 4
- [01-02]: PromptService usa ValueError per variabili mancanti
- [01-03]: LLMService._parse_retry_after() legge header HTTP per wait esatto (fallback 60s)
- [01-03]: asyncio.to_thread wrappa LLM sync calls nel background task async
- [01-03]: Settings.api_key merge: PUT non sovrascrive con None se non inclusa nel body
- [01-03]: Pipeline singleton in generate.py per mantenere _jobs tra request, con fallback da disco
- [01-04]: Palette stone/amber per design B2B non generico (non gradienti viola)
- [01-04]: Download CSV sempre via POST con edits inline (non GET originale)
- [01-04]: localResults separato in OutputReview per edit inline senza mutare cache TanStack Query
- [verification-fix]: GenerateResponse include calendar per badge PN/Schwartz nel frontend
- [02-01]: PromptService init lazy via _get_prompt_service() per sincronizzazione con lifespan directory
Blockers/Concerns
- [Phase 1]: Validare token usage reale per batch 13 post con claude-sonnet-4-5 — inter_request_delay=2.0s configurato, da validare in produzione
- [Phase 1]: Baseline qualita' prompt italiani da validare dopo prima generazione reale
- [Deploy]: Phase 1 completa — serve vps-lab-deploy per testare end-to-end il sistema
Session Continuity
Last session: 2026-03-08 Stopped at: Completed 02-01-PLAN.md (Prompt CRUD + Prompt Editor UI) Resume file: None
Next Actions
- Eseguire 02-02-PLAN.md (Output Review enhancements)
- Completare Phase 2
vps-lab-deployper deployare su VPS e testare end-to-end