This release fixes issues for SREs watching stability and regressions.
✓ No known CVEs patched in this version
Affected surfaces
Summary
AI summaryInstaller now warms up the SentenceTransformerEmbeddingFunction before running analyze_codebase.
Full changelog
Root cause
SentenceTransformerEmbeddingFunction (ChromaDB) lazy-loads model weights on the first embed call — not at container startup. The /health endpoint returns 200 as soon as the web server process starts, which is long before the model is ready. The previous 90-second retry loop in v3.9.4 kept calling analyze_codebase() but the model never loaded because nothing had triggered it yet.
Fix
The installer now explicitly warms up the model before calling analyze_codebase():
- Calls
search_docs("warmup")via MCP - Polls every 5s until it returns a valid result (up to 3 minutes)
- This forces the lazy-load of the embedding model
- Then calls
analyze_codebase()— model is guaranteed to be ready
Upgrade
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]