This release fixes issues for SREs watching stability and regressions.
✓ No known CVEs patched in this version
Topics
+5 more
Summary
AI summaryFixed parseAnswers() to accept answers as objects or strings across six interview tools.
Full changelog
From Mira's Session 3 completion: flexible answers parsing.
Fixed
- All 6 interview tools now accept answers as objects or strings. MCP clients differ in serialization — some send
{"answers": "{\"key\":\"val\"}"}(string), others send{"answers": {"key":"val"}}(object). The newparseAnswers()helper handles both, plus plain text fallback. Eliminates theinvalid_jsonerrors agents were hitting when recording session answers.
Affected tools: brand_compile_messaging, brand_deepen_identity, brand_build_personas, brand_build_journey, brand_build_themes, brand_build_matrix.
This completes the feedback cycle from Mira's full 3-session test on Booth Beacon (Sessions 1-3 all complete, brand-runtime.json deployed to sub-agents in production).
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 Brand-System/brandsystem-mcp
Make your brand machine-readable. Extract brand identity (colors, fonts, logo, voice, visual rules) from any website via static CSS + rendered-page extraction, compile into DTCG tokens, brand runtime contracts, and interaction policies. 34 tools across 4 progressive sessions. Subscribable `brand://runtime` and `brand://policy` MCP resources. Content compliance scoring (0-100), pass/fail gate, and HTML/CSS preflight. Brandcode Studio connector for hosted brand sync.
Beta — feedback welcome: [email protected]