Add module-scoped autouse fixture `reset_all_singletons` in
tests/integration/conftest.py that resets all global singletons
between test modules:
- _qdrant_client (vector/qdrant_client.py)
- _embedding_service, _bm25_service (embedding/service.py)
- _provider (providers/registry.py)
- _vector_sync_state with memory streams (app.py)
- _tracer (observability/tracing.py)
- _registry (auth/client_registry.py)
- _token_exchange_service (auth/token_exchange.py)
This fixes anyio.WouldBlock errors that occurred when running the
full integration test suite together. The errors were caused by
stale singleton state holding references to dead event loops or
closed memory streams from previous test modules.
Results:
- Before: 22 passed, 26 errors (WouldBlock), 12 failed
- After: 48 passed, 25 skipped, 1 failed (unrelated timeout)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Increase sampling timeout from 30s to 300s in semantic.py to accommodate
slower local LLMs like Ollama
- Refactor RAG integration tests to support multiple providers (ollama,
openai, anthropic, bedrock)
- Remove unnecessary embedding_provider fixture since MCP server handles
embeddings internally
- Add --provider flag via tests/integration/conftest.py
- Add provider_fixtures.py with factory functions for generation providers
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Chris Coutinho