4f2449f79b
feat: Implement ai_blueprint_v2.md — Exp 5, 6 & 7 (persona validation, mid-gen consistency, two-pass drafting)
...
Exp 6 — Iterative Persona Validation (story/style_persona.py + cli/engine.py):
- Added validate_persona(): generates ~200-word sample in persona voice, scores 1–10 via
lightweight voice-quality prompt; accepts if ≥ 7/10
- cli/engine.py retries create_initial_persona() up to 3× until validation passes
- Expected: -20% Phase 3 voice-drift rewrites
Exp 5 — Mid-gen Consistency Snapshots (cli/engine.py):
- analyze_consistency() called every 10 chapters inside the writing loop
- Issues logged as ⚠️ warnings; non-blocking; score and summary emitted
- Expected: -30% post-generation continuity error rate
Exp 7 — Two-Pass Drafting (story/writer.py):
- After Flash rough draft, Pro model (model_logic) polishes prose against a strict
checklist: filter words, deep POV, active voice, AI-isms, chapter hook
- max_attempts reduced 3 → 2 since polished prose needs fewer rewrite cycles
- Expected: +0.3 HQS with no increase in per-chapter cost
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-02-22 22:08:47 -05:00
2100ca2312
feat: Implement ai_blueprint.md action plan — architectural review & optimisations
...
Steps 1–7 of the ai_blueprint.md action plan executed:
DOCUMENTATION (Steps 1–3, 6–7):
- docs/current_state_analysis.md: Phase-by-phase cost/quality mapping of existing pipeline
- docs/alternatives_analysis.md: 15 alternative approaches with testable hypotheses
- docs/experiment_design.md: 7 controlled A/B experiment specifications (CPC, HQS, CER metrics)
- ai_blueprint_v2.md: New recommended architecture with cost projections and experiment roadmap
CODE IMPROVEMENTS (Step 4 — Experiments 1–4 implemented):
- story/writer.py: Extract build_persona_info() — persona loaded once per book, not per chapter
- story/writer.py: Adaptive scoring thresholds — SCORE_PASSING scales 6.5→7.5 by chapter position
- story/writer.py: Beat expansion skip — if beats >100 words, skip Director's Treatment expansion
- story/planner.py: validate_outline() — pre-generation gate checks missing beats, continuity, pacing
- story/planner.py: Enrichment field validation — warn on missing title/genre after enrich()
- cli/engine.py: Wire persona cache, outline validation gate, chapter_position threading
Expected savings: ~285K tokens per 30-chapter novel (~7% cost reduction)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-02-22 22:01:30 -05:00
51b98c9399
refactor: Migrate file-based data storage to database
2026-02-22 10:23:40 -05:00
81340a18ea
Auto-commit: v2.14 — Stuck job robustness (heartbeat, retry, stale watcher, granular logging)
...
- web/db.py: Add last_heartbeat column to Run model
- core/utils.py: Add set_heartbeat_callback() and send_heartbeat()
- web/tasks.py: Add _robust_update_run_status() with 5-retry exponential backoff;
add db_heartbeat_callback(); remove all bare except:pass on DB status updates;
set start_time + last_heartbeat when marking run as 'running'
- web/app.py: Add last_heartbeat column migration; add _stale_job_watcher()
background thread (checks every 5 min, 15-min heartbeat threshold, 2-hr start_time threshold)
- cli/engine.py: Add phase-level logging banners and try/except wrappers in
process_book(); add utils.send_heartbeat() after each chapter save;
add start/finish logging in run_generation()
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-02-21 19:00:29 -05:00
83a6a4315b
Blueprint v2.4-2.6: Style Rules UI, Lore RAG, Thread Tracking, Redo Book
...
v2.4 — Item 7: Refresh Style Guidelines
- web/routes/admin.py: Added /admin/refresh-style-guidelines route (AJAX-aware)
- templates/system_status.html: Added 'Refresh Style Rules' button with spinner
v2.5 — Item 8: Lore & Location RAG-Lite
- story/bible_tracker.py: Added update_lore_index() — extracts location/item
descriptions from chapters into tracking_lore.json
- story/writer.py: Reads chapter locations/key_items, builds LORE_CONTEXT block
injected into the prompt (graceful degradation if no tags)
- cli/engine.py: Loads tracking_lore.json on resume, calls update_lore_index
after each chapter, saves tracking_lore.json
v2.5 — Item 9: Structured Story State (Thread Tracking)
- story/state.py (new): load_story_state, update_story_state (extracts
active_threads, immediate_handoff, resolved_threads via model_logic),
format_for_prompt (structured context replacing the prev_sum blob)
- cli/engine.py: Loads story_state.json on resume, uses format_for_prompt as
summary_ctx for write_chapter, updates state after each chapter accepted
v2.6 — Item 10: Redo Book
- templates/consistency_report.html: Added 'Redo Book' form with instruction
input and confirmation dialog
- web/routes/run.py: Added revise_book route — creates new Run, queues
generate_book_task with user instruction as feedback
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-02-21 01:35:43 -05:00
f7099cc3e4
v2.0.0: Modularize project into single-responsibility packages
...
Replaced monolithic modules/ package with a clean architecture:
- core/ config.py, utils.py
- ai/ models.py (ResilientModel), setup.py (init_models)
- story/ planner.py, writer.py, editor.py, style_persona.py, bible_tracker.py
- marketing/ cover.py, blurb.py, fonts.py, assets.py
- export/ exporter.py
- web/ app.py (Flask factory), db.py, helpers.py, tasks.py, routes/{auth,project,run,persona,admin}.py
- cli/ engine.py (run_generation), wizard.py (BookWizard)
Flask routes split into 5 Blueprints; all templates updated with blueprint-
prefixed url_for() calls. Dockerfile and docker-compose updated to use
web.app entry point and new package paths.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-02-20 22:20:53 -05:00
