This release adds 2 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+4 more
Summary
AI summaryAdded outputSchema for health, memory.search, and memory.write tools.
Full changelog
Summary
Tool-definition quality and server-coherence hardening for Glama scoring.
What changed
- Added explicit
outputSchemaforhealth,memory.search, andmemory.writeMCP tools. - Added
structuredContentin MCP tool-call responses, alongside JSON text payloads. - Strengthened tool descriptions for behavior, auth/error posture, parameter interactions, and usage context.
- Tightened tool input schemas (
additionalProperties: false) for clearer contracts. - Added README section documenting the Glama-lite MCP tool contract and scope.
Why
Glama rubric still reported residual gaps in Tool Definition Quality and Server Coherence after the first metadata pass.
Included PR
- https://github.com/sheawinkler/ContextLattice/pull/143
Deterministic target
- Commit:
5f27a8f3d5cf1d6555cacff7ff891518958f373d
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 sheawinkler/ContextLattice
Private-by-default memory and context layer for agents with Go/Rust runtime, staged retrieval across fused data backends, and long-horizon context continuity.
Related context
Related tools
Beta — feedback welcome: [email protected]