This release keeps dependencies and maintenance posture current for teams operating this tool.
✓ No known CVEs patched in this version
Topics
+8 more
Summary
AI summaryMinor fixes and improvements.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
Adds deterministic session capture and crash recovery. Adds deterministic session capture and crash recovery. Source: llm_adapter@2026-06-09 Confidence: high |
— |
| Feature | Medium |
Adds transcript-tail parser with thinking-fallback logic. Adds transcript-tail parser with thinking-fallback logic. Source: llm_adapter@2026-06-09 Confidence: high |
— |
| Refactor | Low |
Reconciles main branch to published v4.7.5, removing orphaned local‑only release. Reconciles main branch to published v4.7.5, removing orphaned local‑only release. Source: llm_adapter@2026-06-09 Confidence: high |
— |
Full changelog
What's Changed
- Reconcile main to published v4.7.5 (orphaned local-only release) by @infracore in https://github.com/delimit-ai/delimit-mcp-server/pull/118
- LED-1705: deterministic session capture + crash recovery (v4.7.6) by @infracore in https://github.com/delimit-ai/delimit-mcp-server/pull/119
- LED-1713: transcript-tail parser thinking-fallback (folds into 4.7.6) by @infracore in https://github.com/delimit-ai/delimit-mcp-server/pull/120
- docs(changelog): 4.7.6 + retroactive 4.7.5 by @infracore in https://github.com/delimit-ai/delimit-mcp-server/pull/121
Full Changelog: https://github.com/delimit-ai/delimit-mcp-server/compare/v4.7.3...v4.7.6
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 delimit-ai/delimit
API governance server that detects breaking changes in OpenAPI specs. Diffs two spec versions, applies configurable policy rules (strict/default/relaxed), and returns structured pass/fail verdicts. 23 change types, 10 breaking. Supports OpenAPI 3.0, 3.1, and Swagger 2.0.
Related context
Beta — feedback welcome: [email protected]