Repository navigation
Conversation
added 2 commits
October 25, 2026 15:10
Use the SQLite/FTS5 chunk store as the default candidate source, keep dense/reranker layers optional, and add a docs-only channel selected by a BM25 score margin. Exclude experiments from the index, prune stale rows on full text reindex, and provide a graph-only rebuild utility. Tests cover the docs channel, query plan, index guard and chunk-store pruning.
Align EN/RU/ZH main pages with the text-first runtime, measured quality and its limits. Rewrite ARCHITECTURE and SEARCH_PIPELINE for the default SQLite/FTS5 path and mark the historical deep-dive explicitly. Correct tool counts, Python requirement and the docs routing contract; remove unverified 95% and stale LanceDB-first claims.
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. Please check the settings in the CodeRabbit UI or the
 |
added 10 commits
October 25, 2026 21:21
P3 anchor degradation must not assume every Searcher instance has _chunk_store. The unit-test doubles exercise the degraded path directly; use getattr and keep the deterministic fallback.
Address pip-audit findings: certifi 2026.10.19, filelock 4.2.1, mcp 1.30.0. MCP stays on the 1.x transport; 2.x changes the protocol and is intentionally not adopted here. pip-audit on the lockfile now reports no known vulnerabilities.
The default runtime is text-first: dense_off and chunk augmentation are on, and on-demand rerank defaults on. Tests that exercise dense/cache paths now opt back into them explicitly instead of asserting the old defaults.
Mocked searchers return a truthy MagicMock from prefers_docs, which routed every test and every non-Searcher double into the docs channel. Require is True so only the real BM25-margin decision can switch channels.
The registered set now has 33 core classes + 16 intel + 13 inline + 4 dev = 66; execute_script is the 67th optional tool. Update the EN/RU/ZH contract and the real-project guard instead of publishing 64/65. The exact default-visible set is described as a curated allowlist rather than a stale hardcoded count.
The file imports tools/factory/ops.py, which is not tracked in this branch. Keep the PR focused on the Phase 3 search and docs changes; the factory work needs its own commit with its implementation.
The temporary project used a namespace-package src/ that can be shadowed by the installed package on CI. Add an explicit src/__init__.py so the acceptance command tests the edit, not an import accident.
The acceptance command runs inside a temporary project whose src/ may be shadowed by the installed package. Put the project directory first on PYTHONPATH so the edited file is the one under test.
A conftest in the fixture keeps the local src package ahead of the installed one on CI, so the acceptance command validates the edited file rather than an import accident.
pytest in the clean-state job resolves the installed src package before the temporary fixture. The acceptance command now imports the edited module directly from the project root, which is what the test is about.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
MSCODEBASE_DOCS_MARGIN, default 4.0); explicitintentstill wins.experiments/**from the index, prune stale rows on full text reindex, and addscripts/rebuild_graph.pyfor graph-only rebuilds.Measurements (internal 48-query panel, clean index)
These are panel results, not a universal benchmark; the README states the limits.
Verification
pip-audit -r requirements-lock.txt --no-deps→ no known vulnerabilities.ruff check src/ tests/→ clean.Not included
experiments/e30..e57run artifacts andllama_msvc.bak/are not staged. They need a separate experiments-data PR/cleanup.fix/gates-in-pre-committo keep the review diff focused.