google/gemini-embedding-001 became paid on OpenRouter, leaving
users without credit unable to run the semantic_search tool. The
old code hardcoded the model and 3072 dimensions in three places.
Make OpenRouterEmbedder accept model/dimension via constructor
args or OPENROUTER_EMBEDDING_MODEL / OPENROUTER_EMBEDDING_DIMENSION
env vars, with the previous values as backward-compatible defaults.
Switch the VectorStore and the response payload in mcp_server_main
to read embedder.dimension instead of the hardcoded 3072 so a
configured non-Gemini model does not produce shape mismatches.
Bad dimension input (non-int or non-positive) now raises a clear
ValueError instead of a downstream shape error.
Documented the new env vars in .env.example.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Replace EmbeddingGemma local model with OpenRouter API integration
- Use google/gemini-embedding-001 model via OpenRouter (3072 dimensions)
- Add conditional tool registration: auto-disable if OPENROUTER_API_KEY not set
- Add openai and numpy dependencies to pyproject.toml
- Update .env.example with OPENROUTER_API_KEY configuration
- Fix ruff lint issues in semantic_search module
Remove hard-coded URLs from OAuth configuration and use environment
variables instead for better security and configurability:
- Add CLERK_ISSUER and BASE_URL environment variables
- Update asgi_app.py OAuth endpoints to use env vars
- Update oauth_router.py to use configurable URLs
- Update .env.example with new environment variables
- Fix fetch tool bug: doc.content → doc.markdown_content
Environment variables:
- CLERK_ISSUER: Clerk domain issuer URL
- BASE_URL: Base URL for OAuth callbacks and API URLs
- CLERK_DOMAIN: Clerk domain name
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
