feat(codebase): deep-enrich + graph-aware recall + team-wiki-codebase skill - #56
Merged
Merged
Conversation
This was referenced Jun 26, 2026
m0Nst3r873
force-pushed
the
feat/deep-enrich-v2
branch
4 times, most recently
from
June 29, 2026 04:02
47c1c52 to
52bfa84
Compare
… skill Complete code knowledge pipeline with AI-powered deep generation and graph-boosted retrieval. Base layer (wiki-engine + enrichment, same as PR Tencent#55): - Deterministic code extraction pipeline (5-language extractors) - AI enrichment + knowledge reconciler + manifest compiler - Wiki index rebuild with domain grouping Deep-enrich (this PR's additions): - deep-enrich.ts: background AI knowledge generation with resume support and --max-modules cost control - code-knowledge-recall.ts: BM25 + graph-boost retrieval engine with CJK bigram segmentation and camelCase splitting - codebase-upgrade-wiki.ts: migration from docs/team-codebase/ to teamwiki/ - codebase-wiki-lint.ts: graph health diagnostics Recall improvements: - --depth option (route/context/lookup) with per-level descriptions - Graph boost via slug/title matching (fixes dead-code path mismatch) - BM25 normalization to prevent score domination over learnings - 2-hop neighbor extension for graph edges Integration: - CI: MR comment API + graph change detection - import-iwiki.ts: iWiki document import - team-wiki-codebase skill bundle (methodology + agent prompts) - Security hardening (shell-quote, JSON parse guards, path validation) Tests: restore 3 import-org tests (replace stale clusterRepos assertions)
m0Nst3r873
force-pushed
the
feat/deep-enrich-v2
branch
from
June 29, 2026 04:05
52bfa84 to
fe43de4
Compare
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
2 participants
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
Part 3 of 3. Depends on #55 (
feat/import-enrichment-v2).deep-enrich.ts: Background AI knowledge generation (component design docs + architecture overview + graph docs G1-G3) with resume support via_review/progress.jsoncode-knowledge-recall.ts: BM25 + graph-boost retrieval engine for teamwiki/ knowledge graphcodebase-upgrade-wiki.ts: Migration fromdocs/team-codebase/toteamwiki/formatcodebase-wiki-lint.ts: Graph health diagnostics (connectivity, orphans, staleness)team-wiki-codebaseskill bundle (909-line methodology)--depthoption (route/context/lookup), graph-aware agent instructions, model_hintCritical recall pipeline fixes
dlused deduplicated token count → broke length normalization. Fixed.getUserById→ get, user, by, id).How it's reachable
teamai deep-enrich --project <slug>→ generate docs/*.mdteamai codebase --lint(when teamwiki/ exists) → wiki-lint health checkteamai codebase --upgrade-wiki→ migrate legacy formatteamai recall --depth lookup <query>→ graph-boosted retrievalTest plan
npx tsc --noEmit— zero errorsnpx vitest run— 1505 tests passedDependency chain
Replaces #52 + #53.