This release includes breaking changes for platform teams planning a safe upgrade.
Published 1mo
AI Agents & Assistants
✓ No known CVEs patched
✓ No known CVEs patched in this version
Topics
agent-harness
agent-isolation
agentic
ai-agents
ai-coding
ai-tools
+14 more
aider
claude-code
code-provenance
codex
coding-assistant
cursor
developer-tools
gemini-cli
git
git-worktree
llm-agents
python
vcs
worktree
Summary
AI summaryWrapped agent CLI now recreates the default memory‑policy file before importing agent memory or building context.
Full changelog
0.37.0
This release moves self-repair into the path users actually run every day: wrapped agent CLI execution.
- Wrapped agent runs now recreate the default
.ait/memory-policy.jsonbefore importing agent memory or building context. - Direct
claude,codex, andaiderwrapper invocations keep repo memory governance in place even if the policy file was removed. - Runner tests now cover wrapper-path self repair for memory policy creation and agent-memory import.
Validation:
.venv/bin/pytest -q-> 248 passed, 4 subtests passed.venv/bin/python -m compileall -q src testsgit diff --check.venv/bin/python -m build.venv/bin/python -m twine check dist/*- Clean wheel smoke that invoked
.ait/bin/claudedirectly and verified policy recreation, agent-memory import, attempt-memory creation, and workspace output
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 Ait
All releases →Related context
Related tools
Earlier breaking changes
- v0.55.52 Keep the built-in claude-code reviewer pinned to the local claude -p CLI even when repository policy defines a conflicting command override.
Beta — feedback welcome: [email protected]