{"version":"2.1.251","anchor":"how-the-evaluation-subprocess-environment-is-assembled","canonical_anchor":"how-the-evaluation-subprocess-environment-is-assembled","heading":"How the evaluation subprocess environment is assembled","tier":"internal","area":"Plugin Eval","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.251\/e\/how-the-evaluation-subprocess-environment-is-assembled","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.251","markdown":"### How the evaluation subprocess environment is assembled\n\nThe confined-evaluation flag is injected into eval child processes, confirming it's harness plumbing not a setting.\n\n**What**\n\nThe confined-evaluation variable is written directly into a spawned child's environment, next to the artifact stub directory and an internal feature-flag override variable, confirming it is harness plumbing rather than a configuration key.\n\n**Details**\n\n- Reaches file hard-link checks, artifact read locking, plan-mode denial forcing and subprocess environment construction.\n- No settings file or config lookup reads it.\n\n**Evidence**\n\n`v.CLAUDE_CODE_EVAL_CONFINED = \"1\"`\n\n- Area: Plugin Eval\n- Names: `CLAUDE_CODE_EVAL_CONFINED`\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 3\/5"}