mini-code-agent-langgraph 0.4.0

What's Changed

• [codex] Add transactional agent runtime and Windows support by @wusuiling-if in #8
• [codex] harden sandbox boundaries and add capability probes by @wusuiling-if in #6

Full Changelog: v0.3.2...v0.4.0

mini-code-agent-langgraph 0.3.2

0.3.2 tightens the trust boundary around verified patches and documents a CI-verified release path.

Highlights

• Recognized zero-test runs fail closed by default; --allow-zero-tests is an explicit weakening flag.
• mca run now requires an explicit model and authoritative test command, while chat without a test command stays in read-only /ask mode.
• The deterministic offline policy suite covers 11 cases: nine verified submissions and two expected refusals, with zero unexpected submissions and zero unrelated changes.
• GitHub Actions, dependency review, CodeQL, pinned actions, dual dependency audits, protected main, and protected release tags harden the supply chain.

The 11/11 result measures offline runtime-policy conformance with scripted local decisions. It does not measure model quality, autonomous repair ability, provider behavior, real-world task success, or SWE-bench performance.

Install and try without an API key

python -m pip install mini-code-agent-langgraph==0.3.2
mca demo

Run mca demo on macOS, Linux, or WSL2. Native Windows supports informational CLI and configuration paths only.

• PyPI 0.3.2
• Changelog
• Security policy

Technical feedback

• Launch notes and technical feedback

mini-code-agent-langgraph 0.3.1

What's Changed

• [codex] prepare public 0.3.1 release by @wusuiling-if in #1

New Contributors

• @wusuiling-if made their first contribution in #1

Full Changelog: https://github.com/wusuiling-if/mini-code-agent-langgraph/commits/v0.3.1