- Scope dedupe key to label::relativePath in mergeMultiCollectionResults
so same file in different projects is not collapsed
- Compute embedding once in searchMultipleCollections via internal
searchChunksWithVector helper (avoids N redundant API calls)
- Compare base project hashes (not branch-suffixed names) when skipping
duplicate linked projects in resolveLinkedCollections
- Use path.resolve() for platform-neutral assertion in query-tools tests
- Update multi-collection-search tests for new cross-project dedup semantics
- query-tools.test.ts: 6 new tests for includeLinked parameter:
- omitted/false → calls searchChunks (not searchMultipleCollections)
- true → calls searchMultipleCollections via resolveLinkedCollections
- passes collections and args correctly
- project label appears in output
- no project tag when field absent
- multi-collection-search.test.ts: 1 new test for searchMultipleCollections
empty-input short-circuit (internal searchChunks calls cannot be mocked
from the same module — integration covered by query-tools tests)
Add searchMultipleCollections() and mergeMultiCollectionResults() to qdrant.ts.
Queries multiple Qdrant collections in parallel, merges results using Reciprocal
Rank Fusion (k=60), and deduplicates by relativePath (first collection wins).
Add optional 'project' field to SearchResult type for source attribution.
This is the shared foundation for linked projects (#20) and branch-aware
indexing (#19).
Refs: #19, #20
Giancarlo Erra