CalvinBackup/gstack
1
0 Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-10-11 21:49:00 +02:00
Code Issues Packages Projects Releases Wiki Activity

test(autoplan-dual-voice): unwrap Claude Code 2.1.284 subagent hand-back frames; accept read-only probe diagnostics; record before asserting

Browse Source 
Census run 36626737820: the native CEO report arrived framed and indented, so
its INPUT line never matched, and the model's exact probe plus two variable
echoes was not canonical. A column-zero line inside a frame, command
substitution, backticks, redirects, assignments, CODEX_MODE echoes and output
line-count mismatches stay rejected. The failure now records before asserting.
This commit is contained in:
garrytan committed 2026-09-29 20:48:37 +00:00
1 parent 3fc05932b7
commit d05d161713
3 files changed
+57 -7
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

test/skill-e2e-autoplan-dual-voice.test.ts
+4 -4
View File
@@ -240,14 +240,14 @@ ${principles}${preflight}${dual}`, { mode: 0o444, flag: 'wx' });
ownedRoots: [workDir, stateDir], cwd: workDir, activePlan, methodologySha256,
commands: loadAutoplanDualCommandContract(ROOT),
});
expect(evidence.claudeVoiceFired, evidence.reasons.join('; ')).toBe(true);
expect(evidence.codexVoiceFired || evidence.codexUnavailable, evidence.reasons.join('; ')).toBe(true);
expect(evidence.reviewDispatched).toBe(true);
logCost('autoplan-dual-voice', result);
recordE2E(evalCollector, 'autoplan-dual-voice', 'Autoplan dual-voice E2E', result, {
passed: evidence.claudeVoiceFired && (evidence.codexVoiceFired || evidence.codexUnavailable) && evidence.reviewDispatched,
...(evidence.reasons.length ? { error: evidence.reasons.join('; ') } : {}),
});
expect(evidence.claudeVoiceFired, evidence.reasons.join('; ')).toBe(true);
expect(evidence.codexVoiceFired || evidence.codexUnavailable, evidence.reasons.join('; ')).toBe(true);
expect(evidence.reviewDispatched).toBe(true);
},
630_000, // per-test timeout slightly > spawn timeout so cleanup can run
);