{"version":"2.1.234","anchor":"plugin-eval-reference-rewritten-around-a-tighter-sandbox","canonical_anchor":"plugin-eval-reference-rewritten-around-a-tighter-sandbox","heading":"Plugin eval reference rewritten around a tighter sandbox","tier":"notice","area":"Plugin Evals","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.234\/e\/plugin-eval-reference-rewritten-around-a-tighter-sandbox","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.234","markdown":"### Plugin eval reference rewritten around a tighter sandbox\n\nPlugin eval runs now happen in a tighter sandbox with their own git repo and home directory.\n\n**What**\n\nThe bundled reference for `claude plugin eval` describes a redesigned sandbox: the working directory sits inside the sandbox home, an empty git repository at the sandbox home root stops git from walking up into your real repo, and the child process is started with `--setting-sources user` and the prompt passed on stdin instead of the command line. Enterprise managed settings are called out as the one policy that still applies inside a run.\n\n**Details**\n\n- Adds exit code 143 for a run killed by SIGTERM, and an `auth_failed` reason for a partial run.\n- Per-plugin failure codes appear under the suite's plugin list, and individual cases can carry advisories.\n- Image and binary grading moved from \"upcoming\" to shipped.\n- This is documentation text; the eval harness itself remains early-access gated.\n\n**Evidence**\n\n`--setting-sources user`\n\n- Area: Plugin Evals\n- Names: `claude plugin eval`\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 2\/5"}