- Add user-decks/ directory and USER_DECKS_DIR config for exported decks
- Update export-to-sim to write to user-decks/ with static mount in lab_api
- Replace import/paste UI with API-backed "My Decks" dropdown in LAN client
and AI Lab, fetching from GET /api/lab/decks with source grouping
- Fix GET /api/lab/decks to JOIN deck_cards for totalCards count
- Fix deckgenerator: add missing DOM elements (dg-strategy-bar, dg-stats-bar,
dg-card-groups) inside #dg-results, null guards on render functions,
fix setLoading always hiding results
- Replace gpt-oss:20b with claude-opus-4-20250514 across all files
- Add user-decks/ to _BUILTIN_DECK_DIRS in deck_service.py
- Enrich missing type_line from Forge card cache in DB deck path
- Collapse import bar behind <details> toggle in AI Lab
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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.
- 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)
- 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)
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.
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>
