timothy/ersatztv
1
0
Fork 0
Code Issues 51 Pull Requests 5 Actions Packages Projects Releases 9 Wiki Activity

fix(916): cross-family state is per round, and the orchestrator reads cross_family before a verdict

Browse Source 
A substitute that failed in round one said nothing about the tree that lands
after round two, yet the flag was sticky and doomed the run; the xfamily
string was never reset either, so clearing the stickiness alone would have let
a stale "substitute ALSO failed" sentence into the PR body. Both reset at the
top of review(). The harness runner is round-aware (ran per round, its own
counter reset) and a two-round case pins the fix; restoring the sticky flag
reddens it in both scripts. Step 4 of the mechanics page tells the referee to
read cross_family, not only error, before posting on a rubric-class PR.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015QqCpYFsKgnAnx6jVwrKiV
This commit is contained in:
timothy
2026-09-05 13:48:15 +02:00
co-authored by Claude Fable 5.1
parent 595c819de1
commit b1d5fbefcb
4 changed files with 29 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
web/scripts/orchestration-workflow-loop.test.mjs
+16 -2
View File
@@ -50,12 +50,14 @@ function run(script, args, { reviewRounds, landOverrides = {}, postRebase = null
calls.push({ label, prompt, opts });
if (label.startsWith('impl:') || label.startsWith('fix:#')) return { done: true, summary: '', verified: '', left: '', commits: IMPL_COMMITS, head_sha: 'aaaaaaa' };
if (label.startsWith('review:codex:')) {
lensesReturned = 0;
lensesReturnedWhenRunnerStarted.push(lensesReturned);
return { verdict: 'merge', findings: [], ran: false };
const spec = reviewRounds[round] || {};
return { verdict: 'merge', findings: [], ran: spec.runnerRan === true };
}
if (label.startsWith('review:fallback:')) {
lensesReturnedWhenFallbackStarted.push(lensesReturned);
if (fallbackNull) return null;
if (fallbackNull === true || (Array.isArray(fallbackNull) && fallbackNull.includes(round))) return null;
const spec = reviewRounds[round - 1] || { findings: [] };
return { verdict: 'merge', findings: spec.findings };
}
@@ -175,6 +177,18 @@ describe.each(cases)('%s review loop', (name, args) => {
expect(result.error).toMatch(/^the post-rebase review round produced no reviews/);
});
it('a substitute failure in round one does not doom a run whose landing round had a real cross-family review', async () => {
const rubricArgs = { ...args, risk: 'rubric' };
const { result, calls } = await run(script, rubricArgs, {
reviewRounds: [{ findings: [finding('should-fix')] }, { findings: [], runnerRan: true }],
fallbackNull: [1],
});
expect(result.error).toBeUndefined();
expect(result.cross_family).toBe('codex');
expect(finisherPrompt(calls)).not.toContain('substitute ALSO failed');
expect(calls.filter((c) => c.label.startsWith('review:codex:')).length).toBe(2);
});
it('a rubric round whose runner and substitute both fail is an error, never a landed PR', async () => {
const rubricArgs = { ...args, risk: 'rubric' };
const { result, calls } = await run(script, rubricArgs, { reviewRounds: [{ findings: [] }], fallbackNull: true });