CalvinBackup/gstack
1
0 Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-10-04 18:36:54 +02:00
Code Issues Packages Projects Releases Wiki Activity

test: move the full office-hours workflow to marathon; add a periodic design-draft checkpoint

Browse Source 
The full startup workflow runs 1–3 real spec-review rounds (~280s each) and
hit its 1200s capture in run 36385945043 at finalize. Review depth is the
product's loop, so the case cannot fit a blocking lane without cutting
rounds. It is now marathon tier with every assertion unchanged.

skill-e2e-office-hours-design-draft.test.ts (periodic) runs the same fixed
interview only through the Write that creates the design (269s in that run)
and applies the full validator's design-draft checks, the required section
reads and the launch/foreign-skill-read guards. validateOfficeHoursDesignDraft
is extracted from validateOfficeHoursCompletion, which still applies it.

Selection: office-hours-design-draft is registered periodic; the marathon-only
file is already excluded from the gate and periodic plans by the B5 planner
rule. Tier-alignment regexes and the valid-tier check accept 'marathon'.
A type-only cast in plan-scope-selection.test.ts removes a diagnostic whose
union print order made the ratchet identity unstable; baseline tightened.
This commit is contained in:
garrytan committed 2026-09-29 15:29:46 +00:00
1 parent a41cdb7d7d
commit 4973f96d98
12 files changed
+180 -57
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

test/helpers/office-hours-completion.ts
+44 -27
View File
@@ -91,6 +91,49 @@ function assignmentBody(markdown: string): string {
|| '';
}
/**
* Design-draft phase of the fixed fixture: the repo design carries every
* required section and an Assignment, and an independent Agent/Task opinion on
* RosterCheck preceded the Write that created it. The full workflow validator
* applies these same checks; the focused design-draft capture applies them alone.
*/
export function validateOfficeHoursDesignDraft(
evidence: Pick<OfficeHoursCompletionEvidence, 'designPath' | 'designContent' | 'toolCalls'>,
label = 'Office-hours design draft',
): { designPath: string; repoPath: string; firstDesignWrite: number } {
const fail = (message: string): never => { throw new Error(`${label}: ${message}`); };
if (evidence.designContent === null) fail(`repo design is missing: ${evidence.designPath}`);
const design = evidence.designContent!;
for (const [section, names] of [
['Problem Statement', ['problem statement']],
['Recommended Approach', ['recommended approach']],
['Success Criteria', ['success criteria']],
['What I noticed about how you think', ['what i noticed about how you think']],
] as const) {
if (!substantive(sectionBody(design, [...names]))) fail(`repo design lacks substantive ${section}`);
}
if (!substantive(assignmentBody(design))) fail('repo design lacks a concrete Assignment');
// A cold-read opinion before the design exists is not the required spec
// review. The fixture promises an available Agent, so require an attempt
// that names this design even when the review subsequently fails.
const designPath = evidence.designPath.replace(/\\/g, '/');
const repoPath = designPath.match(/(?:^|\/)(docs\/designs\/[^/]+\.md)$/)?.[1] ?? designPath;
const firstDesignWrite = evidence.toolCalls.findIndex(call => {
const writtenPath = String(call.input?.file_path ?? '').replace(/\\/g, '/').replace(/^\.\//, '');
return call.tool === 'Write' && (writtenPath === designPath || writtenPath === repoPath);
});
if (firstDesignWrite === -1) fail('no observed Write created the repo design');
const opinion = evidence.toolCalls.slice(0, firstDesignWrite).some(call => {
if (!['Agent', 'Task'].includes(call.tool)) return false;
const prompt = `${String(call.input?.description ?? '')}\n${String(call.input?.prompt ?? '')}`;
return /\bRosterCheck\b/i.test(prompt)
&& /\b(?:review|challenge|opinion|critique|perspective|steelman|advisor)\b|\bcold.read\b/i.test(prompt);
});
if (!opinion) fail('no independent Agent/Task opinion on RosterCheck preceded the repo design Write');
return { designPath, repoPath, firstDesignWrite };
}
export function validateOfficeHoursCompletion(evidence: OfficeHoursCompletionEvidence): OfficeHoursReviewEvidence | null {
const fail = (message: string): never => { throw new Error(`Office-hours completion: ${message}`); };
if (evidence.exitReason !== 'success') fail(`execution failed: ${evidence.exitReason}`);
@@ -111,34 +154,8 @@ export function validateOfficeHoursCompletion(evidence: OfficeHoursCompletionEvi
if (statuses.length !== 1 || statuses[0].trim().toUpperCase() !== 'APPROVED') {
fail('repo design is not marked Status: APPROVED');
}
for (const [label, names] of [
['Problem Statement', ['problem statement']],
['Recommended Approach', ['recommended approach']],
['Success Criteria', ['success criteria']],
['What I noticed about how you think', ['what i noticed about how you think']],
] as const) {
if (!substantive(sectionBody(design, [...names]))) fail(`repo design lacks substantive ${label}`);
}
if (!substantive(assignmentBody(design))) fail('repo design lacks a concrete Assignment');
const { designPath, repoPath, firstDesignWrite } = validateOfficeHoursDesignDraft(evidence, 'Office-hours completion');
if (!substantive(assignmentBody(evidence.output))) fail('REPORT.md lacks the Assignment');
// A cold-read opinion before the design exists is not the required spec
// review. The fixture promises an available Agent, so require an attempt
// that names this design even when the review subsequently fails.
const designPath = evidence.designPath.replace(/\\/g, '/');
const repoPath = designPath.match(/(?:^|\/)(docs\/designs\/[^/]+\.md)$/)?.[1] ?? designPath;
const firstDesignWrite = evidence.toolCalls.findIndex(call => {
const writtenPath = String(call.input?.file_path ?? '').replace(/\\/g, '/').replace(/^\.\//, '');
return call.tool === 'Write' && (writtenPath === designPath || writtenPath === repoPath);
});
if (firstDesignWrite === -1) fail('no observed Write created the repo design');
const opinion = evidence.toolCalls.slice(0, firstDesignWrite).some(call => {
if (!['Agent', 'Task'].includes(call.tool)) return false;
const prompt = `${String(call.input?.description ?? '')}\n${String(call.input?.prompt ?? '')}`;
return /\bRosterCheck\b/i.test(prompt)
&& /\b(?:review|challenge|opinion|critique|perspective|steelman|advisor)\b|\bcold.read\b/i.test(prompt);
});
if (!opinion) fail('no independent Agent/Task opinion on RosterCheck preceded the repo design Write');
const reviews = evidence.toolCalls.slice(firstDesignWrite + 1).filter(call => {
if (!['Agent', 'Task'].includes(call.tool)) return false;
const prompt = String(call.input?.prompt ?? '').replace(/\\/g, '/');