This release fixes issues for SREs watching stability and regressions.
✓ No known CVEs patched in this version
Affected surfaces
Summary
AI summaryFixed infinite restart loop when switching embedding models by correctly detecting dimension mismatches.
Full changelog
Bug Fix
The _heal_dimension_mismatch() guard used not probe["embeddings"][0] which raises ValueError on NumPy arrays ("truth value of an array with more than one element is ambiguous"). This silenced the heal logic, leaving the stale collection in place, and every subsequent upsert/query crashed with:
chromadb.errors.InvalidArgumentError: Collection expecting embedding with dimension of 384, got 1024
This caused an infinite restart loop when switching embedding models (e.g. from all-MiniLM-L6-v2 to BAAI/bge-m3).
Fix
Replaced boolean coercion with explicit None/len() checks so the dimension mismatch is properly detected and the collection recreated automatically.
Update
curl -sSL https://raw.githubusercontent.com/dl4rce/flaiwheel/main/scripts/install.sh | bash
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About dl4rce/flaiwheel
Self-hosted memory and governance layer for AI coding agents. 28 MCP tools with structured knowledge capture, hybrid search (semantic + BM25 + cross-encoder reranking), behavioral documentation nudges, cold-start codebase analyzer, and git-native storage. Single Docker container, zero cloud dependencies.
Related context
Beta — feedback welcome: [email protected]