Skip to content

feat: v1.6.0 — CKB embedding integration layer#4

Merged
SimplyLiz merged 3 commits intomainfrom
develop
Apr 13, 2026
Merged

feat: v1.6.0 — CKB embedding integration layer#4
SimplyLiz merged 3 commits intomainfrom
develop

Conversation

@SimplyLiz
Copy link
Copy Markdown
Contributor

Summary

Five new API features requested by CKB to close gaps in its embedding/search integration:

  • ReindexFiles { uris } — targeted re-index of specific files from disk, bypassing the directory scan. Returns DeltaAck.
  • Similarity { uri_a, uri_b } — pairwise cosine similarity of two stored embeddings. Returns SimilarityResult { score: Option<f32> }. Safe inside BatchQuery.
  • QueryExpansion { query, top_k, model } — embed a query string, find nearest symbols, return display names as expansion terms. Requires LIP_EMBEDDING_URL.
  • Cluster { uris, radius } — greedy single-link grouping of URIs by embedding proximity within a cosine-similarity radius.
  • ExportEmbeddings { uris } — return raw stored embedding vectors for external pipelines. Safe inside BatchQuery.

Similarity and ExportEmbeddings are handled in process_query_sync (pure reads, safe in BatchQuery). ReindexFiles, QueryExpansion, and Cluster return a clear error when submitted inside a batch.

Test plan

  • cargo test -p lip — 207 unit tests + 6 integration tests + 1 doc-test, all green
  • 14 new round-trip and batchability tests in types.rs
  • Version bumped to 1.6.0 across Cargo.toml / README.md / CHANGELOG.md

🤖 Generated with Claude Code

SimplyLiz and others added 3 commits April 13, 2026 13:46
Add five new ClientMessage/ServerMessage pairs requested by CKB:

- ReindexFiles: targeted re-index of specific URIs from disk, bypassing
  the directory scan. Useful after selective git checkout or out-of-band
  file changes.
- Similarity: pairwise cosine similarity of two stored embeddings
  (lip:// or file://) — returns Option<f32>, None when either is missing.
- QueryExpansion: embed a query string, find top-k nearest symbols in
  the symbol store, return their display_names as expansion terms for
  compound workspace-symbol searches.
- Cluster: greedy single-link grouping of URIs by embedding proximity
  within a given cosine-similarity radius.
- ExportEmbeddings: return raw stored embedding vectors for external
  pipelines (e.g. CKB's re-ranking tier).

Similarity and ExportEmbeddings are safe inside BatchQuery (pure reads).
ReindexFiles, QueryExpansion, and Cluster are rejected in the sync batch
context with a clear error message.

14 new round-trip and batchability tests added in types.rs.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- cli-reference.mdx: add reindex-files, similarity, query-expansion,
  cluster, export-embeddings subcommands with examples
- embeddings.mdx: add advanced section (similarity, clustering, export)
  and expand MCP tools table to 10 tools; update agent workflow example
- mcp.mdx: bump tool count to 24, add full reference sections for all
  5 new v1.6 tools, expand CKB → LIP mapping table
- comparisons.mdx: add 5 new v1.6 "exceeds SCIP" bullets
- README.md: add CLI examples for the 5 new commands

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@SimplyLiz SimplyLiz merged commit 6109973 into main Apr 13, 2026
7 checks passed
@SimplyLiz SimplyLiz deleted the develop branch April 13, 2026 12:11
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant