Andrew Simonson
20dae0dce3
- Add LLMProvider registry (llm/registry.py) that builds a provider from env vars (LLM_PROVIDER, GEMINI_API_KEY, GEMINI_MODEL) - Add GeminiLLMProvider using the google-genai SDK - Wire build_llm_provider() into CLI and web pipeline route (replacing llm=None) - Wrap pass 2 and pass 4 LLM calls in per-combo try/except so API errors skip individual combos rather than aborting the whole run - Add gemini optional dep to pyproject.toml; Dockerfile installs [web,gemini] - Document env vars in .env.example and README - Lower requires-python to >=3.10 to match installed system Python Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
12 lines
333 B
Plaintext
12 lines
333 B
Plaintext
# Copy to .env — FLASK_SECRET_KEY is auto-generated on first run if omitted.
|
|
FLASK_SECRET_KEY=
|
|
|
|
# LLM provider (leave blank to use stub estimation)
|
|
# Supported: gemini
|
|
LLM_PROVIDER=
|
|
|
|
# Gemini (required when LLM_PROVIDER=gemini)
|
|
# Install: pip install -e '.[gemini]' (from repo root)
|
|
GEMINI_API_KEY=
|
|
GEMINI_MODEL=gemini-2.0-flash
|