Skip to content

Commit e1583eb

Browse files
committed
test(cli): classify the field-patch target check as validate-only in the build/validate parity roster
Claude-Session: https://claude.ai/code/session_01FEkQ5nSMgkteiemkoN31vf Co-authored-by: Claude <noreply@anthropic.com>
1 parent bcbb3c1 commit e1583eb

1 file changed

Lines changed: 7 additions & 1 deletion

File tree

‎packages/cli/test/validate-build-gate-parity.test.ts‎

Lines changed: 7 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -241,7 +241,13 @@ const BUILD_ONLY_GATES: Readonly<Record<string, string>> = {
241241
* empty, because it is the only honest place the closed roster has for the
242242
* next validate-only gate.
243243
*/
244-
const VALIDATE_ONLY_GATES: Readonly<Record<string, string>> = {};
244+
const VALIDATE_ONLY_GATES: Readonly<Record<string, string>> = {
245+
findFieldPatchTargetRefusals:
246+
'[ADR-0146 D10, second rule] An object extension\'s `fieldPatches` naming a field or option value its ' +
247+
'in-stack target lacks, judged by the marketplace install door\'s own `fieldPatchTargetRefusals`. Wired ' +
248+
'where the rollout card asked for it (`os validate` and the install door); `os build` still emits such an ' +
249+
'artifact, which the install door then refuses — the build-side gap, reported rather than closed here.',
250+
};
245251

246252
/**
247253
* Everything else the two commands call, and the reason each one is NOT an

0 commit comments

Comments
 (0)