fez5587/commander-ai-lab
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
621 Commits 31 Branches 3 Tags
1fc99a5d4aafc9099ef304562b020408726482ac
Commit Graph
64 Commits
Author SHA1 Message Date
KoalaTrapLord e1bb2e7209 feat(coach): Phase 1 sim stats pass-through in prompt template (#108) 
Surfaces previously-computed-but-unused stats into the Claude prompt:

1. USER_PROMPT_TEMPLATE gains a new '### Sim Insights' section that shows:
   - Deck-level opening hand quality: avg keptInOpeningHandRate across all
     cards, plus the 3 worst offenders with their actual rates
   - Curve velocity: avg avgTurnCast weighted by castRate, flagging cards
     cast on avg turn > 6 as 'late'
   - Synergy outliers: bottom-3 synergyScore cards flagged as 'isolated'
   - Archetype weak spots: archetypes with winRate < 40% flagged explicitly

2. _format_archetypes() now annotates weak spots with [WEAK SPOT] and
   strong matchups with [STRENGTH] so Claude sees them immediately.

3. _format_top_cards() adds keptInOpeningHandRate to each line so
   the 'good' cards also show their hand-keepability signal.

4. New helper _format_sim_insights() computes all deck-level aggregates
   from CardPerformance list — no new fields on DeckMeta needed.

No schema changes. Fully backward-compatible with existing DeckReport.
 2026-03-29 05:55:51 -04:00
KoalaTrapLord aefd0cace6 feat(rag): Phase 1 — rewrite build_card_text to natural-language format (#137) 
* feat(rag): Phase 1 — rewrite build_card_text to natural-language format

* feat(rag): Phase 2 — Forge-enriched ChromaDB RAG store (2a–2e)

Phase 2a: Forge lazy import guard (_try_import_forge_lookup)
Phase 2b: _build_document appends Forge trigger/replacement/static/keyword tags
Phase 2c: _build_metadata adds has_trigger, has_replacement, has_static, trigger_modes fields
Phase 2d: query_cards extended with require_trigger, require_replacement, require_static params + ChromaDB where clause support
Phase 2e: get_rag_stats reports forge_enriched and forge_coverage; _write_build_meta tracks coverage; build loop counts enriched cards

* feat(rag): Phase 3 — add mtgrules second ChromaDB collection

Adds build_rules_index() and query_rules() operating on a separate
'mtgrules' ChromaDB collection. Chunks MagicCompRules.txt by rule-number
boundaries, embeds each chunk, and exposes semantic search. Completely
independent from the mtg_oracle card collection.

* feat(coach): Phase 4 — behavior-aware RAG + rules context in coach_service

Phase 4a: run_coaching_session uses dual RAG query
  - Primary: commander synergy (n=10)
  - Secondary: require_replacement=True for graveyard/protection cards (n=5)
  - Deduplicates by name before merging
Phase 4b: query_rules() fetches 3 Commander rules chunks to ground the prompt
  - Passed as rules_context kwarg to build_user_prompt()

* feat(rag): Phase 5 — add /api/rag/build-rules and /api/rag/query-rules endpoints
 2026-03-29 02:11:38 -04:00
KoalaTrapLord 22cf23b24d fix: correct query_cards kwarg names in coach_service (n= -> n_results=, colors= -> color_identity=) 2026-03-27 20:17:14 -04:00
KoalaTrapLord 0010b0f394 refactor: RAG improvements — shared card_text, Chroma fallback, staleness monitor (fixes #133, #134, #135) (#136) 
* refactor: add shared build_card_text() utility

* refactor: unify _build_document via shared card_text + add is_chroma_available/check_staleness (fixes #133, #134, #135)

* refactor: delegate embeddings._build_card_text to shared utility

* feat: add background RAG staleness monitor to lab_api lifespan (fixes #135)
 2026-03-27 16:46:33 -04:00
KoalaTrapLord d0cdafa66a feat(rag): Phase 3 — inject RAG cards into coach prompts (#132) 
* feat(rag): add RAG card injection to prompt_template.py

* feat(rag): wire RAG query into coach_service.py

* test(rag): add Phase 3 RAG injection tests
 2026-03-27 15:20:49 -04:00
KoalaTrapLord 83502ce726 feat: Phase 3/5 deep analysis + Quick Digest endpoint (issue #108) (#119) 
* feat(coach): Phase 3/5 JSON schema + QUICK_DIGEST prompt (issue #108)

- Append removalCoverage, rampQuality, drawEngineProfile, winConditions,
  antiSynergyFlags, podPresence, tempoAssessment, metaMatchups to schema
- Add 8 new RULES for Phase 3/5 analysis
- Add QUICK_DIGEST_SYSTEM_PROMPT constant
- Add build_quick_system_prompt() function

* feat(coach): Phase 3/5 JSON parsing + run_quick_digest() (issue #108)

* feat(routes): add POST /api/coach/decks/{deck_id}/quick endpoint (issue #108)

* feat(coach): Phase 3/5 parsing + run_quick_digest() (issue #108)

* feat(coach): Phase 3/5 parsing + run_quick_digest() (issue #108)

- Import RemovalCoverage, RampQuality, DrawEngineProfile, WinCondition,
  AntiSynergyFlag, PodPresence, TempoAssessment, MetaMatchup
- Add Phase 3/5 blocks to _populate_session_from_json()
- Add run_quick_digest() method

* feat(ui): Top Priority card + Quick/Deep buttons in coach.html (issue #108)

* feat(coach): Phase 3/5 parsing + run_quick_digest() (issue #108)

* feat(ui): wire Quick Digest button + displayTopPriority() (issue #108)
 2026-03-27 07:51:01 -04:00
KoalaTrapLord 864cefb8d1 feat(coach): Phase 5 - add PodPresence, TempoAssessment, MetaMatchup models + isQuickDigest flag (#108) 2026-03-27 04:22:23 -04:00
KoalaTrapLord 4b92a5f364 Update models.pyfeat(coach): Phase 3 - add RemovalCoverage, RampQuality, DrawEngineProfile, WinCondition, AntiSynergyFlag models (#108) 2026-03-27 04:01:25 -04:00
KoalaTrapLord da0193eb11 Update coach_service.pyfeat(coach): Phase 2 - parse upgradePriority, commanderDependency, mulliganAnalysis in coach_service (#108)feat(coach): Phase 2 - parse new fields in coach_service (#108) 2026-03-27 03:45:32 -04:00
KoalaTrapLord 71e0db4985 feat(coach): Phase 2 - add upgradePriority, commanderDependency, mulliganAnalysis to prompt schema (#108) 2026-03-27 03:32:03 -04:00
KoalaTrapLord 825946ae75 fix(deckgen): Phase 1 - non-destructive smart substitution + 99-card guarantee (#111) 
- Add SubstitutionMethod enum to track how each card was resolved
- smart_substitute() now always returns a valid card string (never None/drops)
  fallback chain: exact -> fuzzy -> functional analog -> original kept -> basic land
- apply_substitutions() loop no longer silently drops cards on failure
- _pad_to_99() circuit breaker added before BuildResult validation
- Pre-validation count logging per category for fast regression diagnosis
- Startup assertion: sum(SLOT_BUDGET) == 99 raises on app boot if misconfigured
- Prompt injection: slot budget + exact card count requirement sent to LLM
- run_substitution() anthropic fallback failure now pads with basic land instead of leaving slot missing
- SubstitutionBatchResult gains padded_slots field (> 0 = circuit breaker fired)
 2026-03-27 03:27:52 -04:00
KoalaTrapLord bd4df0c263 Update models.pyfeat(coach): Phase 2 - add UpgradePriority, CommanderDependency, MulliganAnalysis models (#108) 2026-03-27 02:52:01 -04:00
KoalaTrapLord 3f6d71ecbc fix(coach): switch all Anthropic calls to streaming to prevent 10-min timeout error (closes #109) 
- anthropic_client.py: all 4 methods (chat_structured, chat_plain, achat_structured, achat_plain) now use .messages.stream() context manager
- coach_service.py: inline aclient.messages.create() replaced with async streaming via aclient.messages.stream()
- _parse_response() updated to accept pre-extracted text string (since stream gives us text directly)
- check_status() left as non-streaming (max_tokens=10, safe from the 10min rule)
 2026-03-27 02:36:22 -04:00
KoalaTrapLord cd9d2eebd8 feat(coach): Phase 1 - pass richer card stats to Claude prompt (#108) 
- _format_underperformers: add synergyScore, clunkinessScore, avgTurnCast, keptInOpeningHandRate
- _format_top_cards: add synergyScore and avgTurnCast
- _format_matchups: append perArchetypeWinRates block from DeckMeta
- USER_PROMPT_TEMPLATE: add ### Archetype Win Rates section placeholder
 2026-03-27 01:32:51 -04:00
KoalaTrapLord a01a70f725 Use DEFAULT_MAX_TOKENS config for Anthropic max_tokens 2026-03-26 22:50:10 -04:00
KoalaTrapLord 4da58681a4 Enhance coach prompt for more detailed reports 2026-03-26 22:41:23 -04:00
KoalaTrapLord 224b4b5d5b feat: increase coach detail limits (MAX_UNDERPERFORMERS=8, MAX_TOKENS=16384) 2026-03-26 22:33:18 -04:00
KoalaTrapLord 8ec7db1612 fix: correct malformed string literals in config.py model defaults 2026-03-26 15:42:34 -04:00
KoalaTrapLord e0a75e2d04 fix: correct Anthropic model ID from claude-opus-4-0 to claude-opus-4 2026-03-26 15:36:23 -04:00
KoalaTrapLord 15bd6f42bb fix: resolve all ruff linting errors across coach module 2026-03-26 15:30:27 -04:00
KoalaTrapLord 0aa57ab7d2 fix: remove duplicate resp token on line 284 in run_coaching_session (#105) 2026-03-26 14:23:52 -04:00
KoalaTrapLord 9f5eb4a99f fix: add missing resp= assignment on line 284 (#105) 2026-03-26 14:11:35 -04:00
KoalaTrapLord a9f18f53da fix: correct indentation of try/except/else block in run_coaching_session (#105) 2026-03-26 14:06:27 -04:00
KoalaTrapLord c9e932ef43 fix: correct try: block indentation in run_coaching_session (#105) 2026-03-26 13:44:33 -04:00
KoalaTrapLord 2e316548e7 fix: repair resp= assignment and _re.sub typo in coach_service.py (#105) 2026-03-26 13:11:55 -04:00
KoalaTrapLord af2a71d1a5 fix: eliminate event-loop-blocking sync calls in async FastAPI routes (#106) 
* feat: add async DB wrapper and eliminate event-loop blocking

* fix: rewrite llm_client.py with native async httpx - removes urlopen and run_in_executor

* fix: rewrite routes/coach.py - replace all sync DB/HTTP with async (aiosqlite + httpx)

* fix: add async DB shutdown hook to lab_api.py

* feat: add aiosqlite>=0.19.0 to requirements
 2026-03-25 19:17:41 -04:00
KoalaTrapLord c9227dac70 Update substitution_prompt.pyfeat: update substitution_prompt.py docstring from Perplexity to Claude Opus (#105) 2026-03-25 16:41:47 -04:00
KoalaTrapLord 34b1ea2e30 feat: update deck_gen_user.py docstring from Perplexity to Claude Opus (#105) 2026-03-25 16:41:24 -04:00
KoalaTrapLord 1c6454dce5 feat: update substitution_schema.py source field from perplexity to anthropic (#105) 2026-03-25 16:39:16 -04:00
KoalaTrapLord 464dd732d5 feat: update deck_schema.py docstring from Perplexity to Claude Opus (#105) 2026-03-25 16:36:22 -04:00
KoalaTrapLord c58f561df4 feat: replace PerplexityClient with AnthropicClient in deck_generator.py (#105) 2026-03-25 14:34:18 -04:00
KoalaTrapLord 6cf1e58018 feat: replace Perplexity with Anthropic Claude in coach_service.py (#105) 2026-03-25 14:30:40 -04:00
KoalaTrapLord 1382d25e46 feat: update clients __init__.py comment to reference Anthropic (#105) 2026-03-25 12:25:56 -04:00
KoalaTrapLord 55379a98ef feat: replace Perplexity config with Anthropic Claude settings (#105) 2026-03-25 12:20:33 -04:00
KoalaTrapLord 34dee24399 feat: add AnthropicClient as drop-in replacement for PerplexityClient (closes #105 phase 1) 2026-03-25 12:16:14 -04:00
KoalaTrapLord e710287c35 fix: run_coaching_session respects COACH_PROVIDER for Perplexity API 
The coaching pipeline in coach_service.py was always calling self.llm (Ollama) regardless of COACH_PROVIDER setting. Now branches on COACH_PROVIDER == 'perplexity' to call the Perplexity API directly via httpx, matching the pattern used in routes/coach.py coach_chat endpoint.
 2026-03-25 10:42:49 -04:00
KoalaTrapLord 21f032d32e fix: set DECK_GEN_PROVIDER default to perplexity and DECK_GEN_MODEL to sonar-pro 2026-03-25 10:29:54 -04:00
KoalaTrapLord 2881309d41 fix: set COACH_PROVIDER default to perplexity, remove stale DeepSeek comment 2026-03-25 10:13:58 -04:00
KoalaTrapLord e7ffccf3e8 feat: persist coach sessions to SQLite with disk fallback 2026-03-24 23:44:20 -04:00
KoalaTrapLord d70d74d753 feat: add Scryfall on-the-fly embedding fallback for unknown cards 2026-03-24 20:09:27 -04:00
KoalaTrapLord 41b711c17e fix: normalize deck report slug matching (spaces/hyphens/underscores) 2026-03-24 13:31:52 -04:00
KoalaTrapLord a6940ca61a fix: update get_status() to check Perplexity connection when COACH_PROVIDER=perplexity 2026-03-24 13:29:16 -04:00
KoalaTrapLord a515049542 feat: add COACH_PROVIDER config for Perplexity-powered coach chat 2026-03-24 12:50:21 -04:00
KoalaTrapLord 5a499442e6 feat: add PPLX_MODEL env var for configurable Perplexity model 2026-03-24 12:45:40 -04:00
KoalaTrapLord f9007effa3 rename: update report_generator.py glob from batch- to ml-decision- 2026-03-23 23:05:25 -04:00
KoalaTrapLordandClaude Code f0dfb41f2f fix: default Ollama endpoints to localhost instead of 192.168.0.240 (#98) 
The hardcoded 192.168.0.240 IP was a developer-specific LAN address
that breaks out-of-the-box for anyone running Ollama locally or via
WSL2 on Windows. Switch every default and docstring reference to
localhost so the project works without manual configuration.

Files changed:
- coach/config.py: LLM_URL and DECK_GEN_BASE_URL defaults
- ui/simulator.html: API endpoint input value and placeholder
- lab_api.py: remove LAN IP from default CORS origins
- routes/coach.py: warning message text
- src/commander_ai_lab/sim/deepseek_brain.py: docstrings
- src/commander_ai_lab/sim/deepseek_engine.py: docstring example
- src/commander_ai_lab/sim/validator_brain.py: docstring example

Co-authored-by: Claude Code <noreply@anthropic.com>
 2026-03-23 21:03:17 -04:00
KoalaTrapLordClaudeClaude Opus 4.6
 		2b6d4dcdb1 fix: deduplicate LLM duplicate cards in _check_ownership (#78) (#79) 
Co-authored-by: Claude <claude@anthropic.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-23 09:42:33 -04:00
KoalaTrapLord f986d236ab Reduce coach prompt limits and raise LLM timeout for R1 compatibility 2026-03-21 19:08:24 -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