- Create ml/eval/elo_tracker.py:
- EloTracker class with standard ELO formula (K=32, start=1200)
- EloResult dataclass for tournament output
- EloHistory class for JSON persistence (data/elo_history.json)
- run_elo_tournament(): round-robin ELO-rated matches using
existing run_match() from tournament.py
- run_generation_tournament(): discovers gen-*/best_policy.pt
checkpoints and runs cross-generation ELO tournament
- CLI entry point: python -m ml.eval.elo_tracker
- Add ELO API endpoints to routes/ml.py:
- POST /api/ml/elo/tournament — start background ELO tournament
- GET /api/ml/elo/tournament/status — poll progress
- GET /api/ml/elo/history — load ELO history from disk
- Integrate ELO convergence in distillation_loop.py:
- New config fields: elo_convergence_enabled (default False),
elo_convergence_threshold (20.0), elo_tournament_episodes (30)
- New field: GenerationRecord.elo_rating
- _run_elo_mini_tournament() runs after quality gate pass
- _check_convergence() checks ELO delta when enabled
- Add ELO UI to distillation page:
- ELO Ratings panel with canvas multi-line chart showing per-model
ELO progression across generations
- Run Tournament button with progress indicator
- ELO leaderboard table with rank, rating, and visual bars
- Responsive chart resize handling
Closes#70
- Add distillation API endpoints to routes/ml.py:
- POST /api/ml/distill/start — start closed-loop distillation pipeline
- GET /api/ml/distill/status — poll loop status and generation data
- POST /api/ml/distill/stop — graceful stop after current generation
- GET /api/ml/distill/history — load persisted generation history
- Add 'Distill' nav entry in ui/nav.js with loop icon
- Create ui/distillation.html:
- Status overview cards (status, generation, best win rate, gate passes)
- Control panel with hyperparameter inputs for supervised, PPO, and
quality gate settings
- Start/Stop buttons with progress bar and phase badge
- Win rate trend chart (canvas-based, no dependencies)
- Data composition stacked bar chart (Forge vs PPO per generation)
- Generation history table with status, metrics, and gate results
- Create ui/distillation.js:
- Polling loop for real-time status updates during distillation
- Canvas chart rendering for win rate trends and data composition
- History table rendering with color-coded status tags
- Responsive resize handling for charts
- Create ui/distillation.css:
- Page-specific styles following training.css patterns
- Chart container, history table, and responsive grid styles
Closes#69
Extract player_explanation from validation dict in each turn log
entry within _run_game_loop(). The React frontend can now render
validator explanations when player_explanation is non-null.
- Sonar does not support response_format type json_schema
- Switch to {"type": "json_object"} which Sonar supports
- Keep json_schema/schema_name params for call-site compatibility (ignored)
- Add exc_info=True to V3 generate error logging for full tracebacks
collection.py re-defined _ScryfallCache, _scryfall_cache,
_scryfall_rate_limit, _fetch_scryfall_api, _enrich_from_scryfall,
_parse_finish, _parse_text_line, _auto_infer_mapping, _parse_csv_content,
_TYPE_PRIORITY, and _TYPE_TARGETS locally (lines 333-509).
These local definitions shadowed the correct imports from
routes/shared.py -> services/scryfall.py. Critically, the local
_fetch_scryfall_api used Request and urlopen without importing them,
causing a NameError at runtime that was silently swallowed by the
broad except clause — making every card fail Scryfall enrichment
during collection import.
Removed all ~470 lines of duplicate code. The import endpoint now
correctly uses the functions imported from shared.py, which have
proper urllib imports and a working Scryfall cache.
- Replace blocking urlopen with async httpx.AsyncClient
- Add await at both call sites (deck_research, deck_generate_ai)
- Uvicorn event loop no longer stalled during Perplexity API calls
- Replace SELECT * + Python-side color loop in _get_collection_for_colors()
with projected SELECT + NOT EXISTS json_each() sub-query
- Apply same pattern to _build_collection_summary(), removing card_fits_identity()
- Add partial index idx_ce_quantity on collection_entries(quantity) WHERE qty > 0
- Handle NULL and empty-string color_identity via CASE guard
- Fix colorless commander bug: old code skipped color check entirely for []
- Add scripts/bench_deckgen.py benchmark (3-5x speedup on filtered queries)
- Add tests/test_deckgen_color_filter.py with 7 regression tests
- Add @dataclass classes _TrainingState, _PPOState, _TournamentState with snapshot() method
- Wrap all state mutations in threading.Lock() for thread safety
- Replace dict bracket access with attribute access
- Remove unnecessary global declarations from pipeline functions
- GET /api/lab/result: Starlette's JSONResponse uses allow_nan=False,
so NaN/Infinity floats from simulation output cause a ValueError crash.
Add _sanitize_floats() to replace non-finite floats with null before
returning. Also wrap json.load in try/except for better error reporting.
- POST /api/lab/precons/install-batch: Frontend sends {"names": [...]}
but backend expected {"fileNames": [...]}. Accept both field names.
- POST /api/lab/precons/install: Same mismatch — frontend sends {"name"}
but backend expected {"fileName"}. Accept both field names.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The precon deck list was missing after the monolith refactor because
PRECON_DIR was hardcoded in services/precon_service.py with no CLI arg,
env var, or auto-resolve fallback — unlike forge_jar, forge_dir, etc.
Changes:
- Add precon_dir field to Config class (models/state.py)
- Add --precon-dir CLI arg and PRECON_DIR env var support
- Add _resolve_precon_dir() with project-root, parent-dir, and
forge_dir-relative detection; creates dir as fallback for downloads
- Refactor precon_service.py to use _get_precon_dir() helper that reads
CFG.precon_dir at runtime instead of a hardcoded module-level Path
- Update routes/precon.py to use _get_precon_dir() for install endpoints
- Wire _on_startup to resolve precon_dir for uvicorn-direct launches
- Remove unused PRECON_DIR/PRECON_INDEX imports from routes/lab.py
- Audit confirms all other CFG path fields already have fallbacks
- Add POST /api/sim/run-n-player endpoint accepting 2-4 deck IDs for
N-player batch simulations using the existing engine.run_n() method
- Add _run_sim_thread_n_player tracking per-seat wins and stats
- Create SimulatorPage.tsx with 4 deck selection slots, config row,
progress bar, results table, CSS bar chart, and per-game logs
- Add simulator types in frontend/src/types/simulator.ts
- Add /simulator route and nav bar to App.tsx
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
rgriffith