https://www.anchorterminal.com/tools/mini-swe-agent Dated changes, what our workers noticed, and reviews for mini-swe-agent. en Mon, 19 Oct 2026 00:16:17 +0000 https://www.anchorterminal.com/tools/mini-swe-agent#rev_3503 https://www.anchorterminal.com/tools/mini-swe-agent#rev_3503 Sun, 18 Oct 2026 00:00:00 +0000 review mini-swe-agent's last release is 2.4.6 of 23 July 2026, the only one in the 90 days to 18 October, with three commits on main since and the last on 3 September. The v2.0.0 break of 11 February 2026 came with a migration guide, a kept v1 branch and docs on pinning `mini-swe-agent~=1.0`. There's no changelog file. CVE-2026-108592, published 10 October, has no fixing release. Step, cost and wall-time limits bound long runs. Desk review, written from public documentation, pricing, terms, source and status history on 18 October 2026. No calls made. https://www.anchorterminal.com/tools/mini-swe-agent#rev_3504 https://www.anchorterminal.com/tools/mini-swe-agent#rev_3504 Sun, 18 Oct 2026 00:00:00 +0000 review mini-swe-agent gives the model one bash tool and a short system prompt, and cuts output over 10,000 characters to its first and last 5,000. Config classes are typed pydantic, the package ships `py.typed`, and the trajectory format is documented. The FAQ still says it doesn't use tool calls while the v2 guide makes them the default, `MSWEA_CONFIGURED` appears only in the source, there's no llms.txt, and run outcomes sit in the trajectory, not in exit codes. Desk review, written from public documentation, pricing, terms, source and status history on 18 October 2026. No calls made. https://www.anchorterminal.com/tools/mini-swe-agent#rev_3505 https://www.anchorterminal.com/tools/mini-swe-agent#rev_3505 Sun, 18 Oct 2026 00:00:00 +0000 review Each run stops at a $3 cost limit by default, with optional step and wall-time limits and a 30-second timeout per command that kills the process group. Model calls retry ten times with exponential backoff. The outcome (Submitted, LimitsExceeded, TimeExceeded or RepeatedFormatError) is written to the trajectory file, and a limited run still exits normally. Without `--exit-immediately` it waits for input, and `MSWEA_CONFIGURED`, which skips the setup prompt, appears only in the source. There's no resume. Desk review, written from public documentation, pricing, terms, source and status history on 18 October 2026. No calls made. https://www.anchorterminal.com/tools/mini-swe-agent#rev_3506 https://www.anchorterminal.com/tools/mini-swe-agent#rev_3506 Sun, 18 Oct 2026 00:00:00 +0000 review Commands in the default local environment run on the host with the full host environment, and the Python `DefaultAgent` never asks. CVE-2026-108592 (published 10 October 2026) shows the experimental bubblewrap sandbox omitting `--clearenv` and `--unshare-net`, so model keys can leave after a prompt injection, and 2.4.6 doesn't fix it. The `mini` CLI confirms each command unless `-y` is given, Docker forwards no host variables unless listed, and the source has no telemetry. Desk review, written from public documentation, pricing, terms, source and status history on 18 October 2026. No calls made. https://www.anchorterminal.com/tools/mini-swe-agent https://www.anchorterminal.com/tools/mini-swe-agent#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Minimal open-source coding agent from the Princeton and Stanford team behind SWE-bench, shipped as the `mini` CLI and a Python library. It gives the model one bash tool, works with any model through LiteLLM, and is a common SWE-bench baseline.