fez5587/commander-ai-lab
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
368 Commits 31 Branches 3 Tags
11978736a171ea0104780a00c4762d9eb66fa273
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
KoalaTrapLord 11978736a1 fix: raise BRAIN_TIMEOUT default from 30s to 120s (#71) 2026-03-21 19:39:29 -04:00
KoalaTrapLord 8ed3fbc627 feat(ml): add quality gate & validation module (#67) 
Phase 3 of closed-loop distillation pipeline.

- QualityGateConfig with configurable thresholds
- create_forge_holdout() for Forge-only eval split (12% by game_id)
- check_accuracy_gate() rejects PPO batch if Forge eval accuracy drops
- check_win_rate_gate() blocks export below configurable win rate
- compute_quality_metrics() logs action entropy, reward distribution
- QualityGate orchestrator class with evaluate_ppo_batch()
 2026-03-21 19:34:37 -04:00
KoalaTrapLord 4d50449145 feat(ml): add source awareness to dataset builder (#66) 
Phase 2 of closed-loop distillation pipeline.

- Scan both ml-decisions-sim-*.jsonl (Forge) and ml-decisions-ppo-*.jsonl (PPO)
- Add source_weights config for configurable sampling ratios
- Add min_reward_threshold filter for PPO data quality
- Tag each sample with source for downstream analysis
- New CLI args: --forge-weight, --ppo-weight, --min-reward
- NPZ output now includes 'sources' array
 2026-03-21 19:28:22 -04:00
KoalaTrapLord f986d236ab Reduce coach prompt limits and raise LLM timeout for R1 compatibility 2026-03-21 19:08:24 -04:00
KoalaTrapLord 3957285a2e feat(ml): add PPO DecisionExporter for closed-loop distillation (#65) 
Phase 1 of closed-loop distillation pipeline.

Adds DecisionExporter class that captures PPO self-play decisions
as JSONL files compatible with the Forge DecisionSnapshot schema.
Includes PPO-specific metadata fields (source, model_version,
reward, episode_return) and configurable win-only filtering.
 2026-03-21 18:06:45 -04:00
KoalaTrapLord 3cca49c5a9 docs: add closed-loop iterative distillation implementation roadmap 2026-03-21 17:55:18 -04:00
KoalaTrapLord f290523ce1 fix(ml): replace undefined 'log' with 'logger' in labeler.py 2026-03-21 15:47:47 -04:00
KoalaTrapLord 448cec128c feat(ui): add 12 and 16 thread options to batch runner dropdown 2026-03-21 15:22:20 -04:00
KoalaTrapLord 6612f3d213 fix: use correct key best_val_acc in training completion message 2026-03-21 15:21:35 -04:00
KoalaTrapLord 06f007e605 fix: invert guard in _load_deck_cards_by_name — was if not deck_row (crash on None[0]) 
The guard condition was inverted: `if not deck_row:` entered the query
block when no deck was found, causing `deck_row[0]` to crash with
'NoneType' object is not subscriptable. Flipped to `if deck_row:`
so the query runs only when the deck exists.
 2026-03-21 15:11:08 -04:00
KoalaTrapLord 1397f93b91 feat(ml): wire ML decision flush in _finish_sim for all sim threads 2026-03-21 14:30:47 -04:00
KoalaTrapLord f86a4af86f feat(ml): add ML decision logging to base GameEngine 
- Add ml_log param, ml_decisions list, flush_ml_decisions() to GameEngine
- Capture ML snapshots at each player turn in run_n()
- Stamp game_outcome (win/loss per seat) on all decisions
- Add _capture_ml_snapshot() matching DeepSeekGameEngine format
- Add game_id and archetype params to run_n() for ML tracking
- Import logging, uuid; add logger
 2026-03-21 13:54:33 -04:00
KoalaTrapLord 0e99f814fc chore: remove unused React scaffold frontend/ 2026-03-21 13:45:08 -04:00
KoalaTrapLord 8c34cb0966 feat: Phase 8 — surface player_explanation in simulation results JSON 
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.
 2026-03-21 13:37:09 -04:00
KoalaTrapLord c67ce422d8 refactor: rename LM_STUDIO/LMStudioClient to LLM/LLMClient in routes/coach.py 2026-03-21 13:34:21 -04:00
KoalaTrapLord cb4b48e362 refactor: rename LMStudioClient to LLMClient in coach_service.py 2026-03-21 13:33:00 -04:00
KoalaTrapLord 4a8db4db6b refactor: rename LM_STUDIO/LMStudioClient to LLM/LLMClient in llm_client.py 2026-03-21 13:31:32 -04:00
KoalaTrapLord 9c0fa64a69 feat: Phase 7 — add validation field to decision log schema 
Add "validation" key to _log_decision() entry dict in deepseek_brain.py.
Captures result.get("validation") (None if validator disabled)
for R1-14B output preservation and future analysis.
 2026-03-21 13:31:08 -04:00
KoalaTrapLord c338f16965 refactor: rename LM_STUDIO_* to LLM_* in coach/config.py 2026-03-21 13:29:51 -04:00
KoalaTrapLord a7ab0e43a5 feat: Phase 6 — make primary brain env-configurable (BRAIN_* vars) 
Replace hardcoded DEEPSEEK_API_BASE/DEEPSEEK_MODEL env vars in
_get_deepseek_brain() with new BRAIN_* environment variables:
- BRAIN_API_BASE (default: http://localhost:11434)
- BRAIN_MODEL (default: gpt-oss:20b)
- BRAIN_TEMPERATURE (default: 0.3)
- BRAIN_MAX_TOKENS (default: 1024)
- BRAIN_TIMEOUT (default: 30.0)

All params now passed directly to DeepSeekConfig constructor.
 2026-03-21 13:21:58 -04:00
KoalaTrapLord 8b527d7c30 fix: remove duplicate ml_log=True kwarg in deepseek.py 2026-03-21 12:48:56 -04:00
KoalaTrapLord 36760dd922 fix(ml): rename log -> logger in dataset_builder.py to fix NameError 2026-03-21 12:42:02 -04:00
KoalaTrapLord 963a5db638 fix(ml): enable ml_log=True in deepseek route engine calls 2026-03-21 12:41:01 -04:00
KoalaTrapLord b1996a8deb fix: indent __init__ into DeepSeekGameEngine class body 2026-03-20 22:01:25 -04:00
KoalaTrapLord c44d0b32bb Update DeepSeek port from 1234 to 11434 in deepseek_engine.py 2026-03-20 21:55:10 -04:00
KoalaTrapLord a78df75014 Update DeepSeek port from 1234 to 11434 in SimulatorPage.tsx 2026-03-20 21:54:22 -04:00
KoalaTrapLord 9020d29745 Update DeepSeek port from 1234 to 11434 in deepseek_brain.py 2026-03-20 21:53:27 -04:00
KoalaTrapLord b0a34ae9e2 Update DeepSeek port from 1234 to 11434 in coach.py 2026-03-20 21:52:39 -04:00
KoalaTrapLord 4c4f5ce0ff Update DeepSeek API port from 1234 to 11434 in config.py 2026-03-20 21:51:42 -04:00
KoalaTrapLord 1e7f4b4e31 Update DeepSeek API port from 1234 to 11434 (Ollama) 2026-03-20 21:49:49 -04:00
KoalaTrapLord 488575f3df fix(routes): correct indentation of validator line in _run_sim_thread_deepseek 2026-03-20 21:42:11 -04:00
KoalaTrapLord fd7f0258f3 feat(routes): add validator singleton and /api/validator endpoints 2026-03-20 21:27:15 -04:00
KoalaTrapLord 7284b8617d feat(sim): wire DeepSeek-R1-14B validator into deepseek_engine 2026-03-20 21:16:16 -04:00
KoalaTrapLord 678cc13fe0 feat: enable ML logging by default in lab.py 2026-03-20 21:05:37 -04:00
KoalaTrapLord 19f83a546b feat: enable ML logging by default in shared.py 2026-03-20 21:01:40 -04:00
KoalaTrapLord c53e82bfeb feat(sim): add DeepSeek-R1-14B validator brain module 2026-03-20 17:20:30 -04:00
KoalaTrapLord f8b13703b8 fix: CAST_PATTERN now matches both 'cast' and 'casts' for Forge compatibility 2026-03-20 15:04:37 -04:00
KoalaTrapLord eb59a2cd2e fix: increase default clock from 120s to 300s for Commander games to prevent premature timeouts 2026-03-20 14:58:24 -04:00
KoalaTrapLord ff6040b53e Remove stray closing brace that would break compilation 2026-03-20 13:31:50 -04:00
KoalaTrapLord db7bc62d7e Fix commander damage tracking, add PLAYER_DAMAGE_SOURCE_PATTERN and diagnostic logging 2026-03-20 13:28:54 -04:00
KoalaTrapLord fbffe81846 feat: auto-detect commander card names from .dck files for commander cast tracking 2026-03-20 12:48:48 -04:00
KoalaTrapLord 9369cf5450 docs: fix adapter.py docstring to reference lab_api.py instead of deleted lab_api_new.py 2026-03-20 12:19:07 -04:00
KoalaTrapLord e38401a740 chore: remove obsolete lab_api_backup.py (superseded by lab_api.py + routes/) 2026-03-20 12:17:44 -04:00
KoalaTrapLord 111764615d chore: remove obsolete lab_api_new.py (superseded by lab_api.py + routes/) 2026-03-20 12:16:50 -04:00
KoalaTrapLord 2088da6fd8 fix: correct indentation in _resolve_forge_dir forge-gui sibling check 2026-03-20 11:33:42 -04:00
KoalaTrapLord a2fbc30b2b fix: resolve forge_dir to forge-gui sibling when res/ not found in forge-gui-desktop 2026-03-20 11:22:44 -04:00
KoalaTrapLord a62640668b fix: update DeepSeek endpoint IP in lab_api_backup.py 2026-03-20 11:11:07 -04:00
KoalaTrapLord b8e12dff1b fix: update DeepSeek endpoint IP in lab_api_new.py 2026-03-20 11:10:15 -04:00
KoalaTrapLord ea0a785174 fix: update DeepSeek endpoint IP in SimulatorPage.tsx 2026-03-20 11:09:27 -04:00
KoalaTrapLord 9f1277f233 fix: update DeepSeek endpoint IP in deepseek_engine.py 2026-03-20 11:08:32 -04:00
KoalaTrapLord 66ce887fe3 fix: update DeepSeek endpoint IP in deepseek_brain.py docstring 2026-03-20 11:07:38 -04:00
KoalaTrapLord 80f63f192a fix: update DeepSeek endpoint IP in coach.py 2026-03-20 11:06:30 -04:00
KoalaTrapLord 46ed2f5606 fix: update DeepSeek endpoint IP from 192.168.0.122 to 192.168.0.240 in simulator.html 2026-03-20 11:05:10 -04:00
KoalaTrapLord 93a421b90a fix: make colons optional in all regex patterns to match Forge output format (no colons after Game Outcome, Life, Add To Stack, Land, Zone Change, etc.); fix VERBOSE_TURN_PATTERN for 'Turn Turn N AiX' format; fix LIFE_CHANGE_PATTERN to use space instead of > separator 2026-03-20 09:26:02 -04:00
KoalaTrapLord ee95f26bc4 fix: restore double-backslash escaping in Ai regex patterns (fixes compilation errors) 2026-03-20 09:03:55 -04:00
KoalaTrapLord 2ee574f678 diag: add [COMBAT-LINE] logging to identify Forge verbose output format for combat stats parsing 2026-03-20 08:15:03 -04:00
KoalaTrapLord 473a2bdcc7 fix: make Ai regex patterns support both Ai(N) and AiN formats for Forge output compatibility 2026-03-19 23:29:53 -04:00
KoalaTrapLord a6e50ee0f0 feat: aggregate combat stats in StatsAggregator 2026-03-19 22:45:05 -04:00
KoalaTrapLord e2a6a75fd9 feat: add combat stat fields to DeckSummary schema 2026-03-19 22:39:51 -04:00
KoalaTrapLord 030bdf2b81 fix: CAST_PATTERN and LAND_PLAY_PATTERN regex to match Forge verbose log prefixes 
- CAST_PATTERN: Add optional (?:Add To Stack:\s*)? prefix to match Forge's verbose log format
- LAND_PLAY_PATTERN: Add optional (?:Land:\s*)? prefix to match Forge's verbose log format
- Add [PARSE] diagnostic logging after combat stats parsing to confirm spells/lands/cmdr stats per seat

Root cause: Forge verbose output prefixes cast lines with "Add To Stack: " and land lines with "Land: "
but the regexes expected Ai(N) at the start of the line, causing 0 matches for all combat stats.
 2026-03-19 22:06:17 -04:00
KoalaTrapLord e5377ef4bc fix: correct indentation and add forge-gui candidate path 2026-03-19 18:24:57 -04:00
KoalaTrapLord 56ea2602b4 fix: scan sibling dirs for res/ in _resolve_forge_dir (finds forge-gui/res) 2026-03-19 18:19:32 -04:00
KoalaTrapLord d86109c5c0 Fix duplicate WHERE clause in _load_deck_cards_by_name SQL query 2026-03-19 17:54:34 -04:00
KoalaTrapLord d9dd098ca3 fix: add power, toughness, keywords to _load_deck_cards_by_name SQL query 2026-03-19 17:43:57 -04:00
KoalaTrapLord 69ce5b340e fix: normalize indentation in _finish_sim (line 184-185) 2026-03-19 17:13:13 -04:00
KoalaTrapLord 103a74a0e1 fix: update DeepSeek brain default api_base to 192.168.0.240:1234 2026-03-19 17:11:56 -04:00
KoalaTrapLord 147121582b fix: update DeepSeek/LM Studio default URL to 192.168.0.240:1234 2026-03-19 17:10:14 -04:00
KoalaTrapLord 8be96ab47d fix: use coach.report_generator for deck report generation 2026-03-19 17:05:03 -04:00
KoalaTrapLord e2653b3f72 fix: align sim results path with coach (routes/results) 2026-03-19 17:03:00 -04:00
KoalaTrapLord 7efac34279 fix: persist sim results to disk + auto-generate deck reports 2026-03-19 16:59:55 -04:00
KoalaTrapLord b00df14f30 fix: use card_name key from _load_deck_cards_by_name (KeyError: 'name') 2026-03-19 16:51:27 -04:00
KoalaTrapLord 3542efd982 fix: align build_java_command with LabCli picocli args (--forge-jar, --forge-dir, --deck1..4) 2026-03-19 16:42:03 -04:00
KoalaTrapLord 1f93b5510d fix: add missing load_weights() to rules.py 2026-03-19 15:49:00 -04:00
KoalaTrapLord 5c31be6023 fix: add Config extra=ignore to DeckCardWithStatus to prevent 422 from adapter extra fields 2026-03-19 15:34:18 -04:00
KoalaTrapLord 76139477be fix: replace pplx.model with getattr, update V3 error messages for Ollama 2026-03-19 15:26:15 -04:00
KoalaTrapLord 0e5d7ba7d3 fix: harden _find_java17 to search multiple vendors, JAVA_HOME, and warn on wrong version 2026-03-19 15:23:44 -04:00
KoalaTrapLord 4ec6ed57d5 fix: add missing urllib imports to deckbuilder.py for Scryfall card lookup 2026-03-19 15:11:33 -04:00
KoalaTrapLord 08d81a4336 fix: remove stale Perplexity API key error message, allow Ollama/local mode to generate without hard block 2026-03-19 14:58:39 -04:00
KoalaTrapLord f6ed40a253 fix: correct indentation in init_coach_service V3 deck gen block 2026-03-19 14:46:16 -04:00
KoalaTrapLord 9fd39e42c7 feat(phase-10): add DeckBuilderAdapter unit tests 2026-03-19 14:35:00 -04:00
KoalaTrapLord 72107df2ae feat(phase-10): add comprehensive Pydantic model tests 2026-03-19 14:32:43 -04:00
KoalaTrapLord 2738bbdba4 feat: add scrython>=2.0.0 to requirements.txt 2026-03-19 14:28:38 -04:00
KoalaTrapLord 0bbc78ef23 fix: rewire routes/coach.py to use DeckBuilderAdapter + fix IndentationError 2026-03-19 14:02:23 -04:00
KoalaTrapLord c2b470e251 refactor: replace DeckGeneratorV3 import with DeckBuilderAdapter alias 2026-03-19 13:50:30 -04:00
KoalaTrapLord 6135feb644 feat: add run_substitution stub + clean up adapter 2026-03-19 13:49:13 -04:00
KoalaTrapLord b3b664872b refactor: rewire V3 deck gen init to use DeckBuilderAdapter (Ollama) 2026-03-19 13:41:15 -04:00
KoalaTrapLord a80e8908e1 fix: indent _deck_gen_v3_error inside if block in coach.py 2026-03-19 13:35:44 -04:00
KoalaTrapLord a8ef10d5b7 feat: add DeckBuilderAdapter to bridge Ollama pipeline to legacy API 2026-03-19 13:24:29 -04:00
KoalaTrapLord 86af4b6de5 fix: close missing paren in _call_pplx_api client.post() 2026-03-19 13:16:22 -04:00
KoalaTrapLord 332606d6b5 Merge pull request #62 from KoalaTrapLord/feat/deck-builder-phase0 
feat: Commander AI Deck Builder (Ollama gpt-oss:20b)
 2026-03-19 12:45:04 -04:00
KoalaTrapLord 70dfa3d3e0 fix: robust JSON extraction for LLM responses (_extract_json) 2026-03-19 12:29:49 -04:00
KoalaTrapLord f970b6d571 fix: api __init__ imports modules not classes 2026-03-19 12:08:26 -04:00
KoalaTrapLord 5ade916207 fix: make conversation log always visible with initial ready message 2026-03-19 11:50:52 -04:00
KoalaTrapLord cc53c58344 feat(phase-0): add deck builder deps (requests, bs4, ollama) 2026-03-19 11:33:45 -04:00
KoalaTrapLord 3e64aa67eb feat(phase-6): implement deck assembler (Ollama JSON parser) 2026-03-19 11:32:14 -04:00
KoalaTrapLord 70a7c07b81 feat: add conversation log panel below Generate Deck button 2026-03-19 11:31:10 -04:00
KoalaTrapLord 1b4e9f5a66 feat(phase-3): implement community scraper (Moxfield + Archidekt) 2026-03-19 11:30:53 -04:00
KoalaTrapLord c962d1f16a feat(phase-9): implement FastAPI + CLI entrypoint 2026-03-19 11:29:29 -04:00
KoalaTrapLord dcdf15c56a feat(phase-8): add deck_builder package init with public API 2026-03-19 11:28:08 -04:00
KoalaTrapLord b0214009f4 feat(phase-8): add api __init__ exports 2026-03-19 11:27:07 -04:00