This release fixes issues for SREs watching stability and regressions.
✓ No known CVEs patched in this version
Affected surfaces
Summary
AI summaryInstaller now runs the analyzer directly inside the container instead of using an incorrect HTTP endpoint.
Full changelog
Root cause
The installer was calling curl -X POST http://localhost:8081/tools/analyze_codebase and http://localhost:8081/tools/search_docs — but port 8081 is the MCP SSE endpoint, not a REST API. Every call returned "Not Found", the JSON parser failed silently, and the result was always empty. This is why:
- v3.9.4: retry loop timed out after 90s
- v3.9.5: warm-up + analyze both timed out after 180s
The model was probably ready the whole time — the calls were just hitting the wrong protocol.
Fix
Replaced the entire HTTP approach with docker exec python3 -c "..." which runs the analyzer directly inside the container using the same Python code the MCP tool uses. No HTTP, no warm-up loop, no protocol issues.
Tested on a running container: completes in ~20 seconds, full report printed inline.
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]