Kevin Carter 36ae76143f Phase 3B: Implement pluggable LLM client for summary generation ...

- Create llm_client.py with 5 provider implementations (Anthropic, OpenAI, Ollama, OpenRouter, Google)
- Add build_prompt() helper to construct system/user prompts from templates
- Wire up POST /transcribe/sessions/{id}/summaries endpoint to call LLM client
- Return generated content + token counts (input_tokens, output_tokens)
- API keys passed per-request, never stored or logged
- Uses prompt templates from prompts.py based on summary_type

2026-05-20 22:20:19 +00:00

..

__init__.py

feat(transcription): add Supabase schema and API endpoints for CIS

2026-05-20 21:03:00 +00:00

llm_client.py

Phase 3B: Implement pluggable LLM client for summary generation

2026-05-20 22:20:19 +00:00

models.py

feat(transcription): add Supabase schema and API endpoints for CIS

2026-05-20 21:03:00 +00:00

prompts.py

feat(transcription): add Supabase schema and API endpoints for CIS

2026-05-20 21:03:00 +00:00