{"version":"2.1.248","anchor":"permission-prompts-say-whose-comment-is-being-acted-on","canonical_anchor":"permission-prompts-say-whose-comment-is-being-acted-on","heading":"Permission prompts say whose comment is being acted on","tier":"soon","area":"Artifacts","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.248\/e\/permission-prompts-say-whose-comment-is-being-acted-on","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.248","markdown":"### Permission prompts say whose comment is being acted on\n\nComment permission prompts can name whose comment it is, behind an artifact-comments env var.\n\n**What**\n\nPermission prompts for comment actions now name the comment's author in plain words, either inline as `your comment \"\u2026\"`, `Claude's comment \"\u2026\"`, `a viewer's comment \"\u2026\"` or `the comment \"\u2026\"`, or as a thread, for example `Claude's comment thread`. This only runs on the artifact comments path, behind the `tengu_teal_corbel` gate and the `CLAUDE_CODE_ARTIFACT_COMMENTS` environment variable.\n\n**Details**\n\n- The quoted excerpt is normalised before display: newlines and tabs collapse to spaces, double quotes become single quotes, and the text is truncated with an ellipsis at 120 characters.\n- A target is only built when the call has a tool-use id, the permission mode is not `dontAsk`, and prompt suppression is not set, so nothing is computed when no prompt would be shown.\n- The formatters are defined in this build; the exact line as rendered in the prompt is inferred from those definitions rather than read at the render site.\n\n**Evidence**\n\n`Claude's comment thread`\n\n- Flag `tengu_teal_corbel`: Off by default, switched on for this account (read for one account on one subscription tier against v2.1.248; this account: on, anonymous baseline: on, compiled default: off)\n- Area: Artifacts\n- Names: `CLAUDE_CODE_ARTIFACT_COMMENTS`\n- Tier: Nothing to try yet\n- Useful: 2\/5\n- Signal: 4\/5\n- Present in the build but not switched on"}