This release includes 2 breaking changes for platform teams planning a safe upgrade.
✓ No known CVEs patched in this version
Topics
+4 more
Affected surfaces
Summary
AI summaryUpdates All Servers, mcp-qwen — Full Rewrite, and mcp-openai across a mixed release.
Full changelog
What's Changed
mcp-qwen — Full Rewrite
exec()→spawn()+ stdin prompt delivery (no shell injection risk)QWEN_AUTH_TYPEenv var for OAuth support (qwen-oauth)- 5 error detection patterns:
AUTH_NOT_CONFIGURED,QUOTA_EXCEEDED,AUTH_EXPIRED,MODEL_NOT_AVAILABLE,TIMEOUT
mcp-openai
- Default timeout increased 90s → 180s for complex prompts
All Servers
- Version bumped to 2.0.0
Documentation
- setup-qwen: OAuth as recommended auth method,
selectedTypefix - setup-openai: updated timeout, minimal config tips
- architecture: updated error patterns and timeout table
- README: added Changelog section, updated auth descriptions
- config examples: added
QWEN_AUTH_TYPE, removed hardcoded model
AI Concilium Skill
- Added Qwen auth troubleshooting entries
Full Changelog: https://github.com/spyrae/claude-concilium/compare/v0.1.0...v2.0.0
Breaking Changes
- `exec()` replaced by `spawn()` with stdin prompt delivery in mcp-qwen
- Default timeout for mcp-openai increased from 90 s to 180 s
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 spyrae/claude-concilium
Multi-agent AI consultation framework for Claude Code. Three MCP servers wrapping CLI tools (Codex, Gemini, Qwen) for parallel code review and problem-solving with fallback chains and error detection. Includes ready-to-use Claude Code skill.
Related context
Beta — feedback welcome: [email protected]