{"version":"2.1.277","anchor":"new-env-var-claude-code-parsed-willow-overrides-tengu-parsed","canonical_anchor":"new-env-var-claude-code-parsed-willow-overrides-tengu-parsed","heading":"New tengu_parsed_willow gate marks queued-command turns as human-authored","tier":"use","area":"Turn Handling","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.277\/e\/new-env-var-claude-code-parsed-willow-overrides-tengu-parsed","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.277","markdown":"### New tengu_parsed_willow gate marks queued-command turns as human-authored\n\nA new gate, tengu_parsed_willow (on by default), marks certain queued-command turns as human-authored, overridable via CLAUDE_CODE_PARSED_WILLOW\n\n**What**\n\nClaude Code now marks certain queued-command turns with `humanTurn: true`, meaning they are treated as if a human typed them. This behavior is controlled by a new gate called `tengu_parsed_willow`, which defaults to true (on).\n\n- The gate can be overridden with a new environment variable, `CLAUDE_CODE_PARSED_WILLOW`.\n\n- If that environment variable is not set, Claude Code falls back to the `tengu_parsed_willow` gate's default value of true.\n\n**Why**\n\nThis lets Claude Code (or an admin) control whether queued commands are treated as human-authored turns, with the environment variable giving a way to override the default behavior directly rather than waiting on the gate's rollout.\n\n- Flag `tengu_parsed_willow`: Not enough to say (read for one account on one subscription tier against v2.1.277; this account: no value returned, anonymous baseline: no value returned, compiled default: on) These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.\n- Area: Turn Handling\n- Names: `CLAUDE_CODE_PARSED_WILLOW`\n- Tier: Use it now\n- Useful: 3\/5\n- Signal: 3\/5"}