This release fixes issues for SREs watching stability and regressions.
Published 18d
AI Agents & Assistants
✓ No known CVEs patched
✓ No known CVEs patched in this version
Topics
agent
agent-framework
autonomous-agent
autonomous-agents
claude
computer-use
+9 more
llms
mcp
model-context-protocol
openai
openclaw
llm
reliability
ucp
universal-commerce-protocol
Summary
AI summaryFixed chat and messages handling to tolerate trailing junk in tool arguments and reset the task on retry.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Bugfix | Medium |
tolerate trailing junk in tool args and reset task on retry tolerate trailing junk in tool args and reset task on retry Source: llm_adapter@2026-05-21 Confidence: high |
— |
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
Related context
Related tools
Beta — feedback welcome: [email protected]