# 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 COMPLETA — Prompt Control + Output Review ## Current Position Phase: 2 of 4 (Prompt Control + Output Review) Plan: 2 of 2 in current phase — PHASE COMPLETE Status: Phase 2 complete — ready for Phase 3 or deploy Last activity: 2026-03-08 — Completed 02-02-PLAN.md (Per-item Regeneration + Summary Counter) Progress: [██████░░░░] 66% (6/9 piani totali) ## Performance Metrics **Velocity:** - Total plans completed: 6 - Average duration: ~7 min - Total execution time: 42 min **By Phase:** | Phase | Plans | Total | Avg/Plan | |-------|-------|-------|----------| | 01-core-generation-pipeline | 4/4 COMPLETA | 33 min | 8 min | | 02-prompt-control-output-review | 2/2 COMPLETA | 9 min | 4.5 min | **Recent Trend:** - Last 5 plans: 9 min, 8 min, 10 min, 5 min, 4 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 - [02-02]: Regen notes passate via campo tono in GenerateRequest (pragmatico, no backend changes) - [02-02]: Edit detection manuale via JSON.stringify comparison (trascurabile con 13 post) ### 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 2 completa — serve vps-lab-deploy per testare end-to-end il sistema ## Session Continuity Last session: 2026-03-08 Stopped at: Completed 02-02-PLAN.md (Per-item Regeneration + Summary Counter) — Phase 2 COMPLETE Resume file: None ## Next Actions 1. `vps-lab-deploy` per deployare su VPS e testare end-to-end 2. Pianificare Phase 3 (Canva-ready CSV polish + advanced export) 3. Eseguire Phase 3