Round 7 raised 5 issues; this round addresses all of them and fixes
the underlying causes (not just the comments) where applicable so
they don't get re-flagged in future passes.
Critical:
- verified_count description in SemanticSearchResponse said "unique
documents" but the value is len(verified_results), a chunk count.
Description rewritten to accurately document chunk-level granularity
AND explicitly call out the asymmetry with dropped_count (which
counts unique (doc_id, doc_type) pairs).
- _verify_files false-eviction risk: the round-6 doc-only fix was
re-flagged. Address at the source — widen WebDAVClient.get_file_info
to raise HTTPStatusError on 404 (matching the rest of the client
convention) and reserve None for the genuinely ambiguous
malformed-PROPFIND case. _verify_files now keeps the result on None
(cannot tell whether the file exists) and evicts only on a
definitive HTTPStatusError 404. Tests updated; new test added for
the malformed-XML keep-result path.
Non-critical:
- News verifier semaphore lifetime now explicitly documented: one
slot held for one deduplicated fetch per search is the correct
backpressure behaviour.
- Cross-reference comments in _verify_notes / _verify_deck_cards no
longer claim "Mirrors X" pointing at functions defined later in
the file; now use direction-neutral "parallel implementation in".
- accessible_by_type is mutated by concurrent run_verifier tasks; a
comment explains why this is race-free under anyio's cooperative
multitasking (distinct keys per task, no await between read and
write) so a future reader doesn't add a redundant lock.
- Knock-on: tests/integration/test_rag.py wraps get_file_info in a
try/except for the new contract.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The multi-user-basic integration job was consistently failing with
`CancelledError: Cancelled via cancel scope ... by <async_generator_athrow>`
followed by a cascade of `anyio.ClosedResourceError` in every subsequent
test. Root cause: `create_mcp_client_session` was declared as an async
generator driven by `async for session in ...:`, so Python's generator
finalizer (`aclose`) ran under pytest-asyncio's cleanup task instead of
the task that owned the nested `streamablehttp_client` cancel scope.
anyio then raised when the inner task group saw its scope being exited
from a foreign task, leaving the memory object streams half-closed and
poisoning the rest of the session.
Switching to `@asynccontextmanager` + `async with ... as session:` makes
`__aenter__`/`__aexit__` run in the frame that owns the context manager,
satisfying anyio's structured concurrency requirements.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- test_qdrant_collection_creation.py:
- Add get_vector_params() helper to handle named vectors format
- Collections use {"dense": VectorParams(...)} instead of direct VectorParams
- Fix otel_service_name setting in test_collection_name_generation
- test_sampling.py:
- Fix MCP response parsing: use json.loads(result.content[0].text)
instead of result.structuredContent (which is None)
- Add require_vector_sync_tools() helper for graceful skipping
- Add helper call to all 5 test functions
- test_rag.py:
- Add require_vector_sync_tools() helper for graceful skipping
- Fix MCP response parsing (same as sampling tests)
- Prevents 600s timeout when VECTOR_SYNC_ENABLED is not set
Tests now pass/skip cleanly when run independently. The anyio.WouldBlock
errors in full test suite runs are fixture isolation issues, not code bugs.
🤖 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>
