105 findings to zero. Most were mechanical — 67 unused imports, and assorted
f-strings without placeholders. Three groups needed a decision.
The 15 F821 "undefined name" were forward references, not runtime errors. Each
annotation is quoted — `-> "WikiService"`, `Optional["IngestionService"]` — with
the real import inside the function body to break an import cycle. A quoted
annotation is never evaluated, so the code ran; the names were simply
unresolvable to any checker. They now have a TYPE_CHECKING block, which costs
nothing at import time and keeps the cycle broken.
The 6 E402 split two ways. `import secrets`, `Security`, `Request` and
`HTTPBearer` in dependencies.py had drifted below several hundred lines of
factory functions for no reason — stdlib and fastapi, no cycle to avoid — and
moved up. The other three are deliberate and now say so: the VectorService and
GraphService aliases import back into dependencies.py, and main.py's routers
expect a configured app, so both must stay put.
Bare `except:` narrowed to `except Exception:` in three places, which stops them
swallowing KeyboardInterrupt and SystemExit.
The 5 unused locals were all genuinely dead. One is worth naming rather than
fixing: qdrant_client.delete()'s return value was bound and never read, so a
failed delete is indistinguishable from a successful one — the assignment is
gone, but nothing checks the status either way and that has not changed here.
`timing = {}` in _retrieve_parallel looked like it might mean the reported
per-leg timings were always zero; traced, and they come from output["timing"],
so the local was only vestigial.
426 passed, 29 skipped, unchanged. The app imports and the service aliases still
resolve, which is the check that mattered after moving imports in
dependencies.py.
The gate still prints "not gated here yet: test (T-56)" — lint is green, tests
remain unwired, and that is left visible rather than silently absent.
Co-Authored-By: Claude <noreply@anthropic.com>
- CORS: drop allow_credentials (wildcard origin + credentials told
browsers to attach credentials for any site); origins configurable via
CORS_ALLOW_ORIGINS (default * is safe without credentials). Verified
live: preflight no longer advertises access-control-allow-credentials.
- Scheduler tasks: auth moved from a plain Authorization header (which
the Scheduler's rest_api_executor does NOT env-substitute) to its
auth {type: bearer, token: ${LIBRARY_API_KEY}} block, substituted from
the Scheduler's own environment at execution time. The registrar no
longer resolves the real key client-side, so it can never be persisted
into the scheduled_tasks.config JSONB column. Also fixed: JSON bodies
moved from the ignored "body" key to "payload" (the executor only
reads config["payload"], so the tasks would have POSTed empty bodies
and failed required-user validation).
- Reranker: parsed ranking indices are deduplicated preserving first
occurrence (an LLM answer like "3,3,1" duplicated a result).
- HybridRAG wiring consolidated into dependencies.get_hybrid_rag_service
(now including volatile_service); the inline copies in /query/hybrid
and /wiki/pages/smart-create are gone - smart-create previously ran
without the volatile leg, and the singleton was unused.
- Remaining Neo4j writes (GraphService ingestion/deletes/purges/entity
mentions, webhook rename+delete cleanup, document-sync _index_graph,
consolidation mark-processed/add-entity) moved from auto-commit
execute_query to execute_write managed transactions with retry.
Verified end-to-end on the local dev server as llm_tester: /query/hybrid
200 with all five legs ok (volatile now active), background persistence
landed as one transaction.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QbFZyDvYksazX6nYQYZ67L
The deployed container sets OLLAMA_MODEL=nomic-embed-text for embeddings,
which shadowed the generation-model setting and broke Phase 0 keyword
extraction and Phase 4 LLM re-ranking on every request. The setting is now
ollama_llm_model (env: OLLAMA_LLM_MODEL, default gemma4:e2b), startup logs
the resolved generation model, and Phase 0/Phase 4 LLM calls are wrapped in
a 12s asyncio.wait_for with graceful fallback so a hung call cannot gate
retrieval for the full 120s client timeout.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- Add MemoryRouteClassification and MemoryRoutingResult models
- Implement unified classifier (_classify_web_results_unified) that routes
web results to: wiki, volatile, file (Paperless), prefetch, or skip
- Add routing methods: _route_to_volatile, _route_to_files, _register_prefetch
- Update _process_search to use unified classifier instead of separate analysis
- Add get_volatile_cache_service factory to dependencies
- Wire volatile_service and settings_client into ConsolidationService
- Update ConsolidationResult/Response with new routing counters
Test fixes:
- Fix WikiJSClient fixtures to use api_token instead of username/password
- Fix entity linking test assertions to expect full user-namespaced paths
- Add sample_unified_classification fixture for new classifier format
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
jpmschweitzerandClaude