Problem
All navigation is grep + glob — pattern matching on names. On a large codebase, explore/plan quality is capped because the agent cannot find functions by semantic intent (e.g. "functions that validate A2A envelopes").
Design
New tool: semantic_search
semantic_search(query: Str, top_k: Int) -> List[SearchResult]
Each result: file path, function name, SigId, relevance score, one-line summary.
Implementation requires:
- Index builder: walk all
.lex files, extract function signatures + docstrings + examples {} blocks, embed via a local embedding model (or the configured LLM provider's embedding endpoint)
- Store embeddings in
.lex/index.db (sqlite-vec or similar)
- On query: embed query, ANN search, return top_k
The index should be lazily rebuilt when source files change (compare mtime or SigId against stored hash).
Dependencies
- Check if lex-llm exposes an embedding API (
prov.embed(text) -> Vec[Float])
- If not, file a companion ticket in lex-llm
Acceptance
semantic_search "validate A2A envelope" returns relevant functions- Available to explore, plan, review agents
- Index rebuild is incremental (unchanged files not re-embedded)
Problem
All navigation is grep + glob — pattern matching on names. On a large codebase, explore/plan quality is capped because the agent cannot find functions by semantic intent (e.g. "functions that validate A2A envelopes").
Design
New tool:
semantic_searchEach result: file path, function name, SigId, relevance score, one-line summary.
Implementation requires:
.lexfiles, extract function signatures + docstrings +examples {}blocks, embed via a local embedding model (or the configured LLM provider's embedding endpoint).lex/index.db(sqlite-vec or similar)The index should be lazily rebuilt when source files change (compare mtime or SigId against stored hash).
Dependencies
prov.embed(text) -> Vec[Float])Acceptance
semantic_search "validate A2A envelope"returns relevant functions