fez5587/commander-ai-lab
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
317 Commits 31 Branches 3 Tags
80f63f192a2bc1500a4f375bebd8a427af37f45c
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
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
KoalaTrapLord 5fe0ac2bd6 feat(phase-8): add core __init__ exports 2026-03-19 11:26:04 -04:00
KoalaTrapLord fc09249ad3 feat(phase-7): add pipeline __init__ exports 2026-03-19 11:24:47 -04:00
KoalaTrapLord d2c7783ce1 feat(phase-7): implement 7-step deck build pipeline 2026-03-19 11:23:38 -04:00
KoalaTrapLord 0ccf35f241 feat(phase-5): implement collection filter with CSV loader 2026-03-19 11:22:09 -04:00
KoalaTrapLord 9a5105b0d6 feat(phase-5): implement rules engine with ban list and validation 2026-03-19 11:19:42 -04:00
KoalaTrapLord 6a688d1cd0 feat(phase-4): implement Ollama gpt-oss:20b client with 6 core functions 2026-03-19 11:18:13 -04:00
KoalaTrapLord d9639a8414 feat(phase-3): implement EDHrec JSON client 2026-03-19 11:16:28 -04:00
KoalaTrapLord 633fd43b28 fix: replace sonar/sonar-pro model options with gpt-oss:20b in UI 2026-03-19 11:15:43 -04:00
KoalaTrapLord 45c72aadc9 feat(phase-2): implement Scryfall API client 2026-03-19 11:14:58 -04:00
KoalaTrapLord 81ab7ac34a feat(phase-1): implement Pydantic models for deck builder 2026-03-19 11:13:06 -04:00
KoalaTrapLord e0fe4144ae Create test_collection_filter.py 2026-03-19 10:49:06 -04:00
KoalaTrapLord 68aa6eac3f Create test_rules_engine.py 2026-03-19 10:48:23 -04:00
KoalaTrapLord c870dd35fb Create __init__.py 2026-03-19 10:47:49 -04:00
KoalaTrapLord 35ce67ed6f Create collection.csv.example 2026-03-19 10:47:18 -04:00
KoalaTrapLord 232750a951 Create main.py 2026-03-19 10:46:45 -04:00
KoalaTrapLord 46c1c8cb01 Create build_deck.py 2026-03-19 10:46:14 -04:00
KoalaTrapLord 64a4cd3c7c Create __init__.py 2026-03-19 10:45:36 -04:00
KoalaTrapLord 3f6b66fce3 Create deck_assembler.py 2026-03-19 10:44:53 -04:00
KoalaTrapLord 2887c09550 Create collection_filter.py 2026-03-19 10:44:18 -04:00
KoalaTrapLord 84d84a211f Create rules_engine.py 2026-03-19 10:43:45 -04:00
KoalaTrapLord 12f90dd276 Create models.py 2026-03-19 10:43:15 -04:00
KoalaTrapLord 0b755c8428 Create __init__.py 2026-03-19 10:42:40 -04:00
KoalaTrapLord 50f36f284c Create ollama_client.py 2026-03-19 10:42:12 -04:00
KoalaTrapLord 369cc9243f Create community_scraper.py 2026-03-19 10:41:45 -04:00
KoalaTrapLord 22d3b64c2d Create edhrec.py 2026-03-19 10:41:07 -04:00
KoalaTrapLord beb3dac4d5 Create scryfall.py 2026-03-19 10:40:40 -04:00
KoalaTrapLord 330801107c Create __init__.py 2026-03-19 10:40:11 -04:00
KoalaTrapLord 95c5a93584 feat(task-0.1): scaffold deck_builder subpackage structure 2026-03-19 10:39:21 -04:00
KoalaTrapLord 377a704a90 fix: update lab_api_new.py monolith to use local Ollama for deck gen 2026-03-19 10:32:56 -04:00
KoalaTrapLord cc481bd71b feat: switch deck generation from Perplexity to local Ollama (gpt-oss:20b) 2026-03-19 10:26:24 -04:00
KoalaTrapLord c6d02fd38c Fix bracket field handling: support both int and dict from AI response 2026-03-19 08:25:23 -04:00
KoalaTrapLord 0f2d3583ac Remove unsupported response_format from Perplexity API call 2026-03-19 08:14:44 -04:00
KoalaTrapLord 2b355ed9ba Fix NameError: _coach_embeddings not defined in V3 status endpoint 2026-03-19 08:05:26 -04:00
KoalaTrapLord b4d8c2f50e Fix indentation error on line 47 of forge_runner.py 2026-03-19 06:54:16 -04:00
KoalaTrapLord 9db1ed112f Increase _STALL_LIMIT from 300s to 600s (10 min) to prevent premature batch kills 2026-03-19 06:30:03 -04:00
KoalaTrapLord 75568bfdb1 fix: expose full V3 init traceback in _deck_gen_v3_error for easier debugging 2026-03-19 06:27:04 -04:00
KoalaTrapLord d834247885 Fix forge_runner.py: restore full file, fix sim mode arg 
- Restored _run_deepseek_batch_thread and _get_deepseek_brain
  (accidentally removed in prior commit)
- Changed '-sim' to 'sim' — Forge expects positional mode, not flag
 2026-03-19 10:13:11 +00:00
KoalaTrapLord ef7bde841f Fix forge_runner.py: sim mode arg + indentation corruption 
- Changed '-sim' to 'sim' (Forge expects positional mode, not flag)
- Fixed indentation: build_java_command, _run_process_blocking,
  run_batch_subprocess were incorrectly nested inside get_java17()
- Fixed last_activity assignment stuck inside except block
- Added docstrings
 2026-03-19 10:09:59 +00:00
KoalaTrapLord 87abfd801e Fix V3 500 error: replace json_schema response_format with json_object 
- 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
 2026-03-19 10:04:36 +00:00
KoalaTrapLord f2a782f0bd feat(unity-ui): add MainMenu.uss styles for nav hub, server config, module cards 2026-03-19 04:00:31 -04:00
KoalaTrapLord da67879491 feat(unity-ui): add MainMenu.uxml nav hub with server config and module cards 2026-03-19 03:59:31 -04:00
KoalaTrapLord 18beb9192e feat(unity-ui): add UXML+USS layouts for all 5 GUI screens 
- CollectionTracker.uxml  — card grid, filter sidebar, detail panel
- CoachPanel.uxml         — chat bubbles, analytics, mana curve chart
- DeckGenerator.uxml      — 4-step wizard (commander → strategy → generate → result)
- SimulationPanel.uxml    — 4-player config, progress bar, results table
- TrainingPanel.uxml      — stats, start/stop, live charts, log, model history

- CommanderLabShared.uss  — dark MTG theme shared across all screens
- CollectionTracker.uss
- CoachPanel.uss
- DeckGenerator.uss
- SimulationPanel.uss
- TrainingPanel.uss
 2026-03-19 03:55:13 -04:00
KoalaTrapLord 85224f082e fix: handle wrapped JSON object from /api/ml/models endpoint 
The API returns {"models":[...]} rather than a bare array.
Added MlModelsResponse wrapper class and updated LoadModelHistory
to unwrap the list before iterating, preventing the deserialization
exception in TrainingController.
 2026-03-19 02:57:46 -04:00
KoalaTrapLord 3f7f40d626 Make _call_pplx_api async with httpx.AsyncClient 
- 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
 2026-03-19 06:32:18 +00:00
KoalaTrapLord bc023ab6f6 Fix indentation in coach.py _build_deck_report_from_db (2-space -> 4-space) 2026-03-19 06:26:27 +00:00
KoalaTrapLord 83a8f288b7 Fix scrambled deck_service.py: close SQL query in _load_deck_cards_by_name, remove orphaned lines 2026-03-19 06:24:13 +00:00
KoalaTrapLord e3f0787c73 Optimize deckgen: push colour-identity filtering into SQL with json_each 
- 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
 2026-03-19 06:18:32 +00:00
KoalaTrapLord 2936fd37eb Refactor routes/ml.py: replace state dicts with dataclasses + threading locks 
- 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
 2026-03-19 06:06:11 +00:00
KoalaTrapLord cad2f00ec7 Fix all Unity C# errors: 4 truncated Editor scripts + 11 controller/model compilation fixes 2026-03-19 05:53:04 +00:00
KoalaTrapLord 6b50c6ee7d Add PreconListWrapper and CollectionResponse classes to DeckGeneratorController 2026-03-19 01:40:50 -04:00
KoalaTrapLord 40a166188a fix: unify DB connection management — init_collection_db() uses _get_db_conn() 
Previously, init_collection_db() opened a separate sqlite3.connect() call,
ran migrations, then closed that connection — entirely outside the
thread-local pool that route handlers use via _get_db_conn().

This meant:
- The migration connection and the request-serving connection were
  independent objects with no ordering guarantee under concurrent startup.
- The warm-up connection was thrown away immediately, so every handler
  thread still had to open its own connection on first use.

Fix:
- init_collection_db() now calls _get_db_conn() directly, so schema
  creation and migrations run on the same thread-local connection that
  will serve subsequent requests.
- Added _close_db_conn() helper for explicit teardown on thread exit
  (e.g. FastAPI lifespan shutdown or worker thread cleanup).
- Removed the redundant standalone conn.close() that discarded the
  init connection without ever making it available to route handlers.
 2026-03-19 01:24:24 -04:00