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

..

clients

feat: switch deck generation from Perplexity to local Ollama (gpt-oss:20b)

2026-03-19 10:26:24 -04:00

prompts

Fix deck gen truncation: increase max_tokens to 16384, add JSON repair

2026-03-12 14:47:41 +00:00

schemas

fix: add Config extra=ignore to DeckCardWithStatus to prevent 422 from adapter extra fields

2026-03-19 15:34:18 -04:00

services

fix: deduplicate LLM duplicate cards in _check_ownership (#78) (#79)

2026-03-23 09:42:33 -04:00

__init__.py

Initial commit

2026-03-10 12:13:56 -04:00

coach_service.py

fix: run_coaching_session respects COACH_PROVIDER for Perplexity API

2026-03-25 10:42:49 -04:00

config.py

fix: set DECK_GEN_PROVIDER default to perplexity and DECK_GEN_MODEL to sonar-pro

2026-03-25 10:29:54 -04:00

embeddings.py

feat: add Scryfall on-the-fly embedding fallback for unknown cards

2026-03-24 20:09:27 -04:00

llm_client.py

refactor: rename LM_STUDIO/LMStudioClient to LLM/LLMClient in llm_client.py

2026-03-21 13:31:32 -04:00

models.py

Initial commit

2026-03-10 12:13:56 -04:00

prompt_template.py

v23: React + TypeScript SPA migration

2026-03-12 01:12:02 +00:00

report_generator.py

rename: update report_generator.py glob from batch- to ml-decision-

2026-03-23 23:05:25 -04:00