mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-07 17:28:23 +01:00
test: repair seeded workflow delivery and completion evidence
This commit is contained in:
Garry Tan committed
1 parent
12faead463
commit
a6eaafacb8
28 files changed
+3824
-72
No files matched your search
@@ -0,0 +1,80 @@
|
||||
import { expect, test } from 'bun:test';
|
||||
import { findNativeAutoDecision } from './helpers/native-auto-decide';
|
||||
import captured from './fixtures/auto-decide-saved-ai.json';
|
||||
const clone=()=>structuredClone(captured) as any;
|
||||
const decision=(f=clone())=>findNativeAutoDecision(f.transcript,f.tools,f.options);
|
||||
const message=(f:any)=>f.transcript.assistantMessages.find((m:any)=>m.text.includes('Auto-decided'));
|
||||
|
||||
test('actual saved mode preference annotation is a completed native auto-decision',()=>{
|
||||
const f=clone(), result=decision(f);
|
||||
expect(result).not.toBeNull();
|
||||
expect(result!.option).toBe('HOLD SCOPE');
|
||||
expect(message(f).text).toContain(result!.annotation);
|
||||
expect(f.transcript.calls).toEqual([]);
|
||||
});
|
||||
|
||||
test('saved preference is bound to this invoked skill and an agreeing current mode',()=>{
|
||||
for(const change of [
|
||||
(s:string)=>s.replace('`plan-ceo-review-mode`','`plan-design-review-mode`'),
|
||||
(s:string)=>s.replace('`plan-ceo-review-mode`','`plan-ceo-review-routing`'),
|
||||
(s:string)=>s.replace('**Review mode: HOLD SCOPE.**','**Review mode: SCOPE EXPANSION.**'),
|
||||
(s:string)=>s.replace('**Review mode: HOLD SCOPE.**\n\n',''),
|
||||
(s:string)=>s.replace('"Select review mode"','"Select report folder"'),
|
||||
(s:string)=>s.replace('(your saved preference on','(a proposed preference on'),
|
||||
(s:string)=>s.replace('Change with /plan-tune.',''),
|
||||
(s:string)=>s.replace('Auto-decided','I will auto-decide'),
|
||||
]) {const f=clone();message(f).text=change(message(f).text);expect(decision(f)).toBeNull();}
|
||||
});
|
||||
|
||||
test('prefixed examples, quotations and hypothetical notices do not assert a current choice',()=>{
|
||||
for(const change of [
|
||||
(s:string)=>'Example:\n\n'+s,
|
||||
(s:string)=>'```text\n'+s+'\n```',
|
||||
(s:string)=>s.split('\n').map(l=>'> '+l).join('\n'),
|
||||
(s:string)=>s.replace('Heads-up from the preamble: unshipped work on this branch','Heads-up from the preamble: a hypothetical example'),
|
||||
(s:string)=>s.replace('Auto-decided "Select',' Auto-decided "Select'),
|
||||
(s:string)=>s.replace('Auto-decided "Select','If approved, Auto-decided "Select'),
|
||||
]) {const f=clone();message(f).text=change(message(f).text);expect(decision(f)).toBeNull();}
|
||||
});
|
||||
|
||||
test('failed loads, foreign sessions, actual questions and later withdrawals retain precedence',()=>{
|
||||
for(const mutate of [
|
||||
(f:any)=>{f.options.sessionId='foreign';},
|
||||
(f:any)=>{const use=f.tools.find((t:any)=>t.kind==='use'&&t.name==='Skill');f.tools.find((t:any)=>t.kind==='result'&&t.toolUseId===use.toolUseId).isError=true;},
|
||||
(f:any)=>{f.transcript.calls.push({sessionId:f.options.sessionId,toolUseId:'actual-question'});},
|
||||
(f:any)=>{f.options.now=Date.parse(message(f).timestamp)-1;},
|
||||
(f:any)=>{message(f).text+='\n\nCorrection: I withdraw this decision.';},
|
||||
(f:any)=>{message(f).text+='\n\n**Review mode: SCOPE EXPANSION.**';},
|
||||
]) {const f=clone();mutate(f);expect(decision(f)).toBeNull();}
|
||||
});
|
||||
|
||||
import { E2E_TOUCHFILES } from './helpers/touchfiles-data';
|
||||
test('new evidence inputs retain every native observation caller',()=>{
|
||||
const owners=['plan-ceo-review-plan-mode','plan-eng-review-plan-mode','plan-design-review-plan-mode','plan-devex-review-plan-mode','plan-mode-no-op','auto-decide-preserved','conductor-prose'];
|
||||
for(const file of ['test/auto-decide-saved-ai.test.ts','test/fixtures/auto-decide-saved-ai.json','test/fixtures/auto-decide-retry-ai.json'])
|
||||
expect(Object.entries(E2E_TOUCHFILES).filter(([,paths])=>paths.includes(file)).map(([name])=>name)).toEqual(owners);
|
||||
});
|
||||
|
||||
import retry from './fixtures/auto-decide-retry-ai.json';
|
||||
test('actual retry mode-decision heading retains its own annotation, excluding prior foreign text',()=>{
|
||||
const f:any=structuredClone(retry), actual=decision(f);
|
||||
expect(actual).not.toBeNull();expect(actual!.sessionId).toBe(f.options.sessionId);
|
||||
expect(actual!.option).toBe('HOLD SCOPE');
|
||||
expect(actual!.annotation).toContain('(your preference)');
|
||||
const own=f.transcript.assistantMessages.filter((m:any)=>m.sessionId===f.options.sessionId);
|
||||
f.transcript.assistantMessages=f.transcript.assistantMessages.filter((m:any)=>m.sessionId!==f.options.sessionId);
|
||||
expect(decision(f)).toBeNull();expect(own.length).toBeGreaterThan(0);
|
||||
});
|
||||
|
||||
test('retry heading cannot supply a hypothetical, different decision, or withdrawn selection',()=>{
|
||||
for(const change of [
|
||||
(s:string)=>'Example:\n\n'+s,
|
||||
(s:string)=>s.replace('Review mode for the deterministic','Review mode for the hypothetical'),
|
||||
(s:string)=>s.replace('D1 — Review mode','D1 — Report destination'),
|
||||
(s:string)=>s.replace('Auto-decided "Review mode:', 'Auto-decided "Report destination:'),
|
||||
(s:string)=>s.replace('→ **HOLD SCOPE**','→ **Save a file**'),
|
||||
(s:string)=>s+'\n\nCorrection: I withdraw this selection.',
|
||||
(s:string)=>s+'\n\n**Review mode: SCOPE EXPANSION.**',
|
||||
(s:string)=>s.replace('Heads-up from gstack: there is unshipped work on this branch','Heads-up from gstack: here is an example'),
|
||||
]) {const f:any=structuredClone(retry),m=f.transcript.assistantMessages.find((m:any)=>m.sessionId===f.options.sessionId&&m.text.includes('Auto-decided'));m.text=change(m.text);expect(decision(f)).toBeNull();}
|
||||
});
|
||||
@@ -0,0 +1,102 @@
|
||||
import { afterEach, expect, test } from 'bun:test';
|
||||
import * as fs from 'node:fs';
|
||||
import * as os from 'node:os';
|
||||
import * as path from 'node:path';
|
||||
import captured from './fixtures/autoplan-edit-prefix-ai.json';
|
||||
import { autoplanArtifactPermissionInput, pendingAutoplanArtifactPermissionInput, autoplanArtifactMenuKey } from './helpers/autoplan-artifact-permission';
|
||||
import type { NativePublicToolEvent } from './helpers/plan-count-transcript';
|
||||
import { E2E_TOUCHFILES, selectTests } from './helpers/touchfiles';
|
||||
|
||||
const roots: string[] = [];
|
||||
afterEach(() => { for (const root of roots.splice(0)) fs.rmSync(root, { recursive: true, force: true }); });
|
||||
function replay() {
|
||||
const root = fs.mkdtempSync(path.join(os.tmpdir(), 'autoplan-edit-prefix-')); roots.push(root);
|
||||
const cwd = path.join(root, path.basename(captured.cwd)), ownedStateRoot = path.join(root, 'home', '.gstack');
|
||||
const events = structuredClone(captured.events) as NativePublicToolEvent[];
|
||||
const latest = events.find(e => e.kind === 'use' && e.toolUseId === captured.pending.toolUseId)!
|
||||
const original = latest.input!.file_path as string, file = original.replace(captured.ownedStateRoot, ownedStateRoot);
|
||||
fs.mkdirSync(cwd, { recursive: true }); fs.mkdirSync(path.dirname(file), { recursive: true }); fs.writeFileSync(file, captured.before);
|
||||
const time = new Date(Date.parse(latest.timestamp) - 1000); fs.utimesSync(file, time, time);
|
||||
for (const event of events) if (event.input?.file_path === original) event.input.file_path = file;
|
||||
const context = { cwd, ownedStateRoot, commandStartedAt: Date.parse(events[0]!.timestamp) - 1,
|
||||
now: Date.parse(captured.viewportCapturedAt), viewportCapturedAt: Date.parse(captured.viewportCapturedAt), transcriptStatus: 'ready', publicTools: events };
|
||||
const viewport = captured.viewport.replace(/^ …[^\n]+$/m, ' …' + path.relative(ownedStateRoot, file));
|
||||
const header = viewport.lastIndexOf('\n● Update(') + 1;
|
||||
return { root, file, current: latest, context, viewport, prefix: viewport.slice(0, header), panel: viewport.slice(header) };
|
||||
}
|
||||
const pick = (r: ReturnType<typeof replay>, seen = new Set<string>()) => autoplanArtifactPermissionInput(r.viewport, r.context, seen);
|
||||
|
||||
test('the exact retained prior diff output does not hide the current published owned edit', () => {
|
||||
const r = replay();
|
||||
expect(r.prefix.split('\n')).toHaveLength(17);
|
||||
expect(pick(r)).toEqual({ input: '1\r', signature: r.current.sessionId + ':' + r.current.toolUseId, file: r.file });
|
||||
r.viewport = r.panel;
|
||||
expect(pick(r)?.input).toBe('1\r');
|
||||
});
|
||||
|
||||
test('completed diff rows are ignored only before one complete current native panel', () => {
|
||||
for (const prefix of [' 1 +Previous completed output\n\n', ' +cropped prior row\n 2 +next prior row\n +wrapped row\n\n', ' 1 -Old value\n 1 +New value\n\n']) {
|
||||
const r = replay(); r.viewport = prefix + r.panel; expect(pick(r)?.input).toBe('1\r');
|
||||
}
|
||||
});
|
||||
|
||||
test('competing headers, previous panels, misleading prose and quotes remain rejected', () => {
|
||||
for (const prefix of [
|
||||
'● Update(/tmp/foreign.md)\n\n',
|
||||
'● Update(~/.gstack/projects/gstack-autoplan-chain-9599im/ceo-plans/2026-09-10-user-dashboard.md)\n ⎿ Added 1 line\n\n',
|
||||
' Edit file\n /tmp/foreign.md\n────────\n',
|
||||
'Example:\n', '> quoted output\n', '```diff\n 1 +quoted\n```\n',
|
||||
]) { const r = replay(); r.viewport = prefix + r.viewport; expect(pick(r)).toBeNull(); }
|
||||
const priorPanel = replay(); priorPanel.viewport = priorPanel.panel + '\n' + priorPanel.panel; expect(pick(priorPanel)).toBeNull();
|
||||
});
|
||||
|
||||
test('malformed completed-output gutters cannot become a panel delimiter', () => {
|
||||
for (const prefix of [' 1 +wrong indent\n', ' 0 +zero line\n', ' 9007199254740992 +unsafe line\n', ' 1 +row\n +short wrap\n', ' 1 +row\n -wrong kind\n', ' +only a cropped fragment\n']) {
|
||||
const r = replay(); r.viewport = prefix + r.panel; expect(pick(r)).toBeNull();
|
||||
}
|
||||
});
|
||||
|
||||
test('the complete current header, exact target, menu and requested replacement remain binding', () => {
|
||||
for (const change of [
|
||||
(r: ReturnType<typeof replay>) => { r.viewport = r.viewport.replace('● Update(~/.gstack/', '● Update(/foreign/'); },
|
||||
(r: ReturnType<typeof replay>) => { r.viewport = r.viewport.replace(/^ …[^\n]+$/m, ' …projects/sibling/ceo-plans/2026-09-10-user-dashboard.md'); },
|
||||
(r: ReturnType<typeof replay>) => { r.viewport = r.viewport.replace(' Edit file', ' Read file'); },
|
||||
(r: ReturnType<typeof replay>) => { r.viewport = r.viewport.replace('❯ 1. Yes', '❯ 2. Yes'); },
|
||||
(r: ReturnType<typeof replay>) => { r.viewport = r.viewport.replace('3. No', '3. Maybe'); },
|
||||
(r: ReturnType<typeof replay>) => { r.viewport += '\nDo another action.'; },
|
||||
(r: ReturnType<typeof replay>) => { r.current.input!.new_string = 'Unrelated replacement'; },
|
||||
(r: ReturnType<typeof replay>) => { fs.writeFileSync(r.file, 'Unrelated current file'); },
|
||||
]) { const r = replay(); change(r); expect(pick(r)).toBeNull(); }
|
||||
});
|
||||
|
||||
test('seen, completed, foreign or superseded native requests cannot borrow the valid panel', () => {
|
||||
const once = replay(), granted = pick(once)!;
|
||||
expect(pick(once, new Set([granted.signature]))).toBeNull();
|
||||
for (const change of [
|
||||
(r: ReturnType<typeof replay>) => { const e = r.current; r.context.publicTools.push({ kind: 'result', sessionId: e.sessionId, toolUseId: e.toolUseId, timestamp: new Date(r.context.now).toISOString(), isError: false }); },
|
||||
(r: ReturnType<typeof replay>) => { r.current.sessionId = 'foreign'; },
|
||||
(r: ReturnType<typeof replay>) => { r.current.name = 'Write'; },
|
||||
(r: ReturnType<typeof replay>) => { r.current.input!.file_path = r.file + '.foreign'; },
|
||||
(r: ReturnType<typeof replay>) => { r.context.publicTools.find(e => e.kind === 'result')!.isError = true; },
|
||||
(r: ReturnType<typeof replay>) => { const e = structuredClone(r.current); e.toolUseId = 'newer-edit'; r.context.publicTools.push(e); },
|
||||
]) { const r = replay(); change(r); expect(pick(r)).toBeNull(); }
|
||||
});
|
||||
|
||||
test('metadata fallback uses the same panel boundary while published inputs stay authoritative', () => {
|
||||
const r = replay(), current = r.current;
|
||||
const pending = { source: 'pre_tool_use' as const, tool: 'Edit' as const, sessionId: current.sessionId, toolUseId: current.toolUseId, timestamp: captured.pending.timestamp, file: r.file };
|
||||
expect(pendingAutoplanArtifactPermissionInput(r.viewport, { ...r.context, pending }, new Set())).toBeNull();
|
||||
// Synthetic missing-publication projection; actual AI request was published.
|
||||
r.context.publicTools = r.context.publicTools.filter(e => e.toolUseId !== current.toolUseId);
|
||||
const context = { ...r.context, pending };
|
||||
expect(pendingAutoplanArtifactPermissionInput(r.viewport, context, new Set())?.input).toBe('1\r');
|
||||
expect(pendingAutoplanArtifactPermissionInput(r.viewport, context, new Set([autoplanArtifactMenuKey(r.viewport)]))).toBeNull();
|
||||
expect(pendingAutoplanArtifactPermissionInput(r.viewport, { ...context, viewportCapturedAt: Date.parse(pending.timestamp) - 1 }, new Set())).toBeNull();
|
||||
r.viewport = 'Example:\n' + r.viewport;
|
||||
expect(pendingAutoplanArtifactPermissionInput(r.viewport, context, new Set())).toBeNull();
|
||||
});
|
||||
|
||||
test('the exact prefix fixture and controls select only Autoplan', () => {
|
||||
for (const file of ['test/autoplan-edit-prefix-ai.test.ts', 'test/fixtures/autoplan-edit-prefix-ai.json'])
|
||||
expect(selectTests([file], E2E_TOUCHFILES, []).selected).toEqual(['autoplan-chain-pty']);
|
||||
});
|
||||
@@ -0,0 +1,104 @@
|
||||
import { expect, test } from 'bun:test';
|
||||
import { ceoFirstReviewAUQ, ceoStep0Boundary, nativePlanCallFingerprint, planCountQuestionPhase } from './helpers/claude-pty-runner';
|
||||
import captured from './fixtures/ceo-section-choice-ai.json';
|
||||
import { E2E_TOUCHFILES } from './helpers/touchfiles-data';
|
||||
|
||||
function call(index = 4): any {
|
||||
const source = structuredClone(captured.calls[index]!);
|
||||
return { sessionId: source.sessionId, toolUseId: source.toolUseId, questions: source.questions,
|
||||
answered: true, failed: false, unansweredQuestionIndices: [], answeredAt: source.answeredAt,
|
||||
answers: Object.fromEntries(source.questions.map((q, i) => [q.question, source.answers[i]])) };
|
||||
}
|
||||
const fp = (c: any) => nativePlanCallFingerprint(c, 0, true);
|
||||
function edit(c: any, change: (text: string) => string) {
|
||||
const q = c.questions[0], answer = c.answers[q.question];
|
||||
q.question = change(q.question); c.answers = { [q.question]: answer };
|
||||
}
|
||||
|
||||
test('exact captured section choices start review; preceding actual setup does not', () => {
|
||||
let started = false; const classified: boolean[] = [];
|
||||
for (let i = 0; i < captured.calls.length; i++) {
|
||||
const question = fp(call(i));
|
||||
expect(ceoFirstReviewAUQ(question)).toBe(captured.calls[i]!.expectedFirstReview);
|
||||
const phase = planCountQuestionPhase(question, started, ceoStep0Boundary, ceoFirstReviewAUQ);
|
||||
started = phase.reviewStarted; classified.push(phase.preReview);
|
||||
}
|
||||
expect(classified).toEqual([true, true, true, true, false, false, false, false, false]);
|
||||
});
|
||||
|
||||
test('an offered alternative and a quoted historical withdrawal retain current review identity', () => {
|
||||
const alternative = call(); alternative.answers[alternative.questions[0].question] = alternative.questions[0].options[1].label;
|
||||
expect(ceoFirstReviewAUQ(fp(alternative))).toBe(true);
|
||||
const quoted = call(); edit(quoted, s => s + '\nHistorical quote: "This issue has been resolved."');
|
||||
expect(ceoFirstReviewAUQ(fp(quoted))).toBe(true);
|
||||
});
|
||||
|
||||
test.each([
|
||||
['pending', (c: any) => { c.answered = false; }],
|
||||
['failed', (c: any) => { c.failed = true; }],
|
||||
['unanswered index', (c: any) => { c.unansweredQuestionIndices = [0]; }],
|
||||
['missing session', (c: any) => { c.sessionId = ''; }],
|
||||
['missing tool id', (c: any) => { c.toolUseId = ''; }],
|
||||
['unoffered answer', (c: any) => { c.answers[c.questions[0].question] = 'Not offered'; }],
|
||||
['missing answer', (c: any) => { c.answers = {}; }],
|
||||
['mixed packet', (c: any) => { c.questions.push(structuredClone(c.questions[0])); }],
|
||||
['multi-select', (c: any) => { c.questions[0].multiSelect = true; }],
|
||||
['duplicate options', (c: any) => { c.questions[0].options[1] = structuredClone(c.questions[0].options[0]); }],
|
||||
['missing description', (c: any) => { c.questions[0].options[1].description = ''; }],
|
||||
['option identity', (c: any) => { c.questions[0].options[1].label = '1B) Other'; }],
|
||||
['section mismatch', (c: any) => edit(c, s => s.replace('Section 1 Architecture.', 'Section 2 Architecture.'))],
|
||||
['recommendation mismatch', (c: any) => edit(c, s => s.replace('Recommendation: A', 'Recommendation: B'))],
|
||||
['missing stakes', (c: any) => edit(c, s => s.replace(/^Stakes if we pick wrong:.*$/m, ''))],
|
||||
['duplicate assessment', (c: any) => edit(c, s => s + '\nELI10: A second competing assessment.')],
|
||||
['quoted assessment', (c: any) => edit(c, s => s.replace(/^ELI10: (.+)$/m, 'ELI10: "$1"'))],
|
||||
['fenced context', (c: any) => edit(c, s => s.replace(/^(Project\/branch\/task:.*)$/m, '```\n$1\n```'))],
|
||||
['Suppose assessment', (c: any) => edit(c, s => s.replace('ELI10: The plan', 'ELI10: Suppose the plan'))],
|
||||
['single quoted assessment', (c: any) => edit(c, s => s.replace(/^ELI10: (.+)$/m, "ELI10: '$1'"))],
|
||||
['current withdrawal', (c: any) => edit(c, s => s + '\nThis issue is withdrawn.')],
|
||||
['completed withdrawal', (c: any) => edit(c, s => s + '\nWe have withdrawn this finding.')],
|
||||
['conditional assessment', (c: any) => edit(c, s => s.replace('ELI10: The plan', 'ELI10: If the plan'))],
|
||||
['withdrawn issue', (c: any) => edit(c, s => s + '\nWe withdraw this finding.')],
|
||||
['resolved issue', (c: any) => edit(c, s => s + '\nThis issue has been resolved.')],
|
||||
['administrative report', (c: any) => edit(c, s => s.replace(/^.*\n/, '1A — Should the completed review report be saved?\n'))],
|
||||
['setup header', (c: any) => { c.questions[0].header = 'Setup'; }],
|
||||
['borrowed qid', (c: any) => edit(c, s => s + '\n<gstack-qid:plan-ceo-review-example>')],
|
||||
])('rejects %s despite numbered review prose', (_name, mutate) => {
|
||||
const c = call(); mutate(c); expect(ceoFirstReviewAUQ(fp(c))).toBe(false);
|
||||
});
|
||||
|
||||
test('fingerprints cannot borrow another native call or its options', () => {
|
||||
const original = fp(call());
|
||||
expect(ceoFirstReviewAUQ({ ...original, signature: 'other:tool' })).toBe(false);
|
||||
expect(ceoFirstReviewAUQ({ ...original, nativeCall: undefined })).toBe(false);
|
||||
expect(ceoFirstReviewAUQ({ ...original, options: original.options.slice(1) })).toBe(false);
|
||||
});
|
||||
|
||||
test('the regression inputs belong to the existing paid CEO case', () => {
|
||||
expect(E2E_TOUCHFILES['plan-ceo-finding-count']).toContain('test/ceo-section-choice-ai.test.ts');
|
||||
expect(E2E_TOUCHFILES['plan-ceo-finding-count']).toContain('test/fixtures/ceo-section-choice-ai.json');
|
||||
});
|
||||
|
||||
test('coherent finished-note destination is administrative, despite matching section and choice', () => {
|
||||
const c = call(), q = c.questions[0];
|
||||
q.header = 'Destination';
|
||||
q.question = '1A — Which storage location should hold these notes?\nProject/branch/task: main, Stripe payment webhook plan, Section 1 Architecture.\nELI10: The review is finished; these notes can be saved in either folder for convenience.\nStakes if we pick wrong: People may have to look in a second folder.\nRecommendation: A because the existing folder is easier to find.';
|
||||
q.options = [{label:'A) Save beside the plan',description:'Keeps the finished notes together.'},{label:'B) Save in another folder',description:'Keeps finished notes separate.'}];
|
||||
c.answers = {[q.question]: q.options[0].label};
|
||||
expect(ceoFirstReviewAUQ(fp(c))).toBe(false);
|
||||
});
|
||||
|
||||
test('conditional stakes remain valid when the assessment asserts the current gap', () => {
|
||||
const c = call(); edit(c, s => s.replace('Stakes if we pick wrong:', 'Stakes if we pick wrong: Suppose there were an issue.'));
|
||||
expect(ceoFirstReviewAUQ(fp(c))).toBe(true);
|
||||
});
|
||||
|
||||
test('negated gaps and administrative missing fields cannot borrow review identity', () => {
|
||||
const negated = call(); edit(negated, s => s.replace(/^ELI10: .+$/m, 'ELI10: The transaction order is not unspecified. The plan guarantees commit before email.'));
|
||||
expect(ceoFirstReviewAUQ(fp(negated))).toBe(false);
|
||||
const admin = call(), q = admin.questions[0];
|
||||
q.header = 'Destination';
|
||||
q.question = '1A — Which storage location should hold these notes?\nProject/branch/task: main, Stripe payment webhook plan, Section 1 Architecture.\nELI10: These finished notes have a missing storage location.\nStakes if we pick wrong: People may look in the wrong folder.\nRecommendation: A because a notes folder is easy to find.';
|
||||
q.options = [{label:'A) Add a notes folder',description:'Save the finished notes together.'},{label:'B) Use the existing folder',description:'No new folder.'}];
|
||||
admin.answers = {[q.question]: q.options[0].label};
|
||||
expect(ceoFirstReviewAUQ(fp(admin))).toBe(false);
|
||||
});
|
||||
@@ -0,0 +1,132 @@
|
||||
import { expect, test } from 'bun:test';
|
||||
import captured from './fixtures/design-first-issue-ai.json';
|
||||
import { isDesignCountFirstReview, isDesignCountSetup } from './helpers/design-count-review';
|
||||
import { designStep0Boundary, planCountQuestionPhase } from './helpers/claude-pty-runner';
|
||||
|
||||
const findings = captured.calls.filter(row => row.ordinal >= 3 && row.ordinal <= 7);
|
||||
test.each(findings)('actual completed Design D$ordinal starts review', ({ fingerprint }) => {
|
||||
expect(isDesignCountFirstReview(fingerprint)).toBe(true);
|
||||
expect(planCountQuestionPhase(fingerprint, false, designStep0Boundary, isDesignCountFirstReview, isDesignCountSetup)).toMatchObject({ preReview: false, reviewStarted: true });
|
||||
});
|
||||
|
||||
function first(): any { return structuredClone(findings[0]!.fingerprint); }
|
||||
function question(fp: any, text: string) {
|
||||
const call = fp.nativeCall, old = call.questions[0].question;
|
||||
call.questions[0].question = text;
|
||||
call.answers = { [text]: call.answers[old] };
|
||||
}
|
||||
function options(fp: any, change: (q: any) => void) {
|
||||
const call = fp.nativeCall, q = call.questions[0];
|
||||
change(q);
|
||||
fp.options = q.options.map((o: any, i: number) => ({ index: i + 1, label: o.label }));
|
||||
call.answers = { [q.question]: q.options[0].label };
|
||||
}
|
||||
|
||||
test('actual routing, learnings and future typography TODO do not start a design review', () => {
|
||||
for (const row of captured.calls.filter(row => [1, 2, 9].includes(row.ordinal)))
|
||||
expect(isDesignCountFirstReview(row.fingerprint)).toBe(false);
|
||||
});
|
||||
|
||||
test('any offered answer and menu order can resolve a substantive finding', () => {
|
||||
for (const row of findings) {
|
||||
for (const option of row.fingerprint.nativeCall.questions[0]!.options) {
|
||||
const fp: any = structuredClone(row.fingerprint);
|
||||
fp.nativeCall.answers = { [fp.nativeCall.questions[0].question]: option.label };
|
||||
expect(isDesignCountFirstReview(fp)).toBe(true);
|
||||
}
|
||||
const fp: any = structuredClone(row.fingerprint);
|
||||
options(fp, q => q.options.reverse());
|
||||
expect(isDesignCountFirstReview(fp)).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
test('native completion, request identity, current answers and aligned menu are required', () => {
|
||||
for (const change of [
|
||||
(f: any) => { delete f.nativeCall; },
|
||||
(f: any) => { f.nativeCall.answered = false; },
|
||||
(f: any) => { f.nativeCall.failed = true; },
|
||||
(f: any) => { f.nativeCall.sessionId = 'foreign'; },
|
||||
(f: any) => { f.nativeCall.toolUseId = 'stale-request'; },
|
||||
(f: any) => { f.nativeQuestionIndex = 1; },
|
||||
(f: any) => { f.nativeCall.unansweredQuestionIndices = [0]; },
|
||||
(f: any) => { f.nativeCall.answers = {}; },
|
||||
(f: any) => { f.nativeCall.answers[f.nativeCall.questions[0].question] = 'not offered'; },
|
||||
(f: any) => { f.nativeCall.questions[0].question += '\nCorrection: this is a new question.'; },
|
||||
(f: any) => { f.nativeCall.answeredAt = 'invalid'; },
|
||||
(f: any) => { f.nativeCall.questions.push(structuredClone(f.nativeCall.questions[0])); },
|
||||
(f: any) => { f.nativeCall.questions[0].multiSelect = true; },
|
||||
(f: any) => { f.options.reverse(); },
|
||||
(f: any) => { f.nativeCall.questions[0].header = 'Issue 7'; },
|
||||
]) { const fp = first(); change(fp); expect(isDesignCountFirstReview(fp)).toBe(false); }
|
||||
});
|
||||
|
||||
test('numbered issue and all choice identifiers agree without depending on D numbering', () => {
|
||||
const fp = first(); question(fp, fp.nativeCall.questions[0].question.replace('D3 —', 'D27:'));
|
||||
expect(isDesignCountFirstReview(fp)).toBe(true);
|
||||
for (const change of [
|
||||
(q: any) => { q.options[0].label = q.options[0].label.replace('1A:', '2A:'); },
|
||||
(q: any) => { q.options[1].label = q.options[0].label; },
|
||||
]) { const f = first(); options(f, change); expect(isDesignCountFirstReview(f)).toBe(false); }
|
||||
});
|
||||
|
||||
test('a design Issue heading cannot borrow review content for setup, navigation or future work', () => {
|
||||
for (const title of [
|
||||
'Should we run outside design voices now?',
|
||||
'How should we configure design review routing?',
|
||||
'What review should run after the design review?',
|
||||
'Should we record an app-wide typography TODO?',
|
||||
'What type scale will form labels use after a future redesign?',
|
||||
]) {
|
||||
const fp = first(); question(fp, fp.nativeCall.questions[0].question.replace(/Issue 1: [^\n]+/, `Issue 1: ${title}`));
|
||||
expect(isDesignCountFirstReview(fp)).toBe(false);
|
||||
}
|
||||
for (const replacement of ['PLAN.md onboarding', 'PLAN.md post-review TODO', 'PLAN.md engineering review']) {
|
||||
const fp = first(); question(fp, fp.nativeCall.questions[0].question.replace('PLAN.md design review', replacement));
|
||||
expect(isDesignCountFirstReview(fp)).toBe(false);
|
||||
}
|
||||
});
|
||||
|
||||
test('quoted, hypothetical and withdrawn declarations cannot start the phase', () => {
|
||||
for (const change of [
|
||||
(text: string) => `Example: ${text}`,
|
||||
(text: string) => `\`\`\`text\n${text}\n\`\`\``,
|
||||
(text: string) => text.replace('ELI10: ', 'ELI10: Example only: '),
|
||||
(text: string) => `${text}\nCorrection: that question was hypothetical and is withdrawn.`,
|
||||
(text: string) => text.replace('How should Save', 'If we later proceed, how should Save'),
|
||||
]) { const fp = first(); question(fp, change(fp.nativeCall.questions[0].question)); expect(isDesignCountFirstReview(fp)).toBe(false); }
|
||||
});
|
||||
|
||||
test('concrete design conformance and an opposed current violation belong to different offered choices', () => {
|
||||
for (const change of [
|
||||
(q: any) => { q.options.forEach((o: any) => { o.description = 'This is an available option.'; }); },
|
||||
(q: any) => { q.options[0].description = '✅ Example only: ' + q.options[0].description; },
|
||||
(q: any) => { q.options[2].description = 'No current design gap remains.'; },
|
||||
(q: any) => { q.options[0].label = '1A: Run primary review (recommended)'; },
|
||||
]) { const fp = first(); options(fp, change); expect(isDesignCountFirstReview(fp)).toBe(false); }
|
||||
});
|
||||
|
||||
import { E2E_TOUCHFILES, selectTests } from './helpers/touchfiles';
|
||||
test('the new exact public fixture and controls select only the design count workflow', () => {
|
||||
for (const path of ['test/design-first-issue-ai.test.ts', 'test/fixtures/design-first-issue-ai.json'])
|
||||
expect(selectTests([path], E2E_TOUCHFILES, []).selected).toEqual(['plan-design-finding-count']);
|
||||
});
|
||||
|
||||
test('the assessment asserts a current defect, preserving conditional stakes and quoted history', () => {
|
||||
for (const change of [
|
||||
(s: string) => s.replace('ELI10: The header', 'ELI10: Suppose the header'),
|
||||
(s: string) => s.replace(/^ELI10: (.+)$/m, "ELI10: '$1'"),
|
||||
(s: string) => s.replace(/^ELI10: (.+)$/m, 'ELI10: "$1"'),
|
||||
(s: string) => s.replace('\nStakes if we pick wrong:', ' This issue is withdrawn.\nStakes if we pick wrong:'),
|
||||
(s: string) => s.replace('\nStakes if we pick wrong:', ' We have resolved this finding.\nStakes if we pick wrong:'),
|
||||
]) { const fp = first(); question(fp, change(fp.nativeCall.questions[0].question)); expect(isDesignCountFirstReview(fp)).toBe(false); }
|
||||
const conditional = first(); question(conditional, conditional.nativeCall.questions[0].question.replace('Stakes if we pick wrong:', 'Stakes if we pick wrong: If we leave this unchanged,'));
|
||||
expect(isDesignCountFirstReview(conditional)).toBe(true);
|
||||
const history = first(); question(history, history.nativeCall.questions[0].question.replace('\nStakes if we pick wrong:', ' The old report claimed "We have resolved this finding.", but that claim was wrong.\nStakes if we pick wrong:'));
|
||||
expect(isDesignCountFirstReview(history)).toBe(true);
|
||||
});
|
||||
|
||||
test('an explicit no-current-issue assessment cannot borrow the offered fixes', () => {
|
||||
const fp = first();
|
||||
question(fp, fp.nativeCall.questions[0].question.replace(/^ELI10: .+$/m, 'ELI10: The header shows four clearly differentiated buttons. DESIGN.md is fully followed. No current issue remains.'));
|
||||
expect(isDesignCountFirstReview(fp)).toBe(false);
|
||||
});
|
||||
@@ -0,0 +1,197 @@
|
||||
import { expect, test } from 'bun:test';
|
||||
import fixture from './fixtures/eng-declared-regression-ai.json';
|
||||
import { evaluateEngSeedCoverage } from './helpers/eng-seeded-coverage';
|
||||
import type { PlanCountTranscript } from './helpers/plan-count-transcript';
|
||||
import { E2E_TOUCHFILES, selectTests } from './helpers/touchfiles';
|
||||
|
||||
const transcript = fixture.transcript as PlanCountTranscript;
|
||||
const { start, end } = fixture.provenance.window;
|
||||
const plan = [
|
||||
'## Tests\n\n### CRITICAL regression (mandatory, regression rule)\n\n' + fixture.mandatory,
|
||||
'## Implementation Tasks\n\n' + fixture.task,
|
||||
'## Verification\n\n' + fixture.verification,
|
||||
fixture.reviewReport,
|
||||
].join('\n\n');
|
||||
const evaluate = (text = plan, native = transcript) => evaluateEngSeedCoverage(native, text, start, end);
|
||||
const retryPlan = [
|
||||
'## Architecture\n\n' + fixture.retry.legacyHeading + '\n\n' + fixture.retry.legacy,
|
||||
'## Tests\n\n' + fixture.retry.heading + '\n\n' + fixture.retry.mandatory,
|
||||
'## Implementation Tasks\n\n' + fixture.retry.task,
|
||||
fixture.retry.reviewReport,
|
||||
].join('\n\n');
|
||||
const evaluateRetry = (text = retryPlan) => evaluateEngSeedCoverage(fixture.retry.transcript as PlanCountTranscript,
|
||||
text, fixture.retry.provenance.window.start, fixture.retry.provenance.window.end);
|
||||
|
||||
test('actual mandatory suite, numbered task and unchanged baseline bind legacy regression', () => {
|
||||
const result = evaluate();
|
||||
expect(Object.keys(result.decisions)).toHaveLength(4);
|
||||
expect(result.missing).toEqual([]);
|
||||
expect(result.regression).toBe('plan');
|
||||
expect(result.ok).toBe(true);
|
||||
expect(fixture.provenance.retrospectivePass).toBe(false);
|
||||
});
|
||||
|
||||
test('retry same-fixture contract compares new behavior with the unchanged legacy release oracle', () => {
|
||||
const result = evaluateRetry();
|
||||
expect(result.missing).toEqual([]);
|
||||
expect(result.regression).toBe('plan');
|
||||
expect(result.ok).toBe(true);
|
||||
expect(fixture.retry.provenance.retrospectivePass).toBe(false);
|
||||
});
|
||||
|
||||
test('retry requires an unchanged legacy release oracle and actual result parity', () => {
|
||||
for (const text of [
|
||||
retryPlan.replace(fixture.retry.legacy, ''),
|
||||
retryPlan.replace('stays callable and unchanged this release', 'will be rewritten this release'),
|
||||
retryPlan.replace('stays callable and unchanged this release', 'might stay callable and unchanged this release'),
|
||||
retryPlan.replace('- A tenant-keyed flag', 'If approved:\n\n- A tenant-keyed flag'),
|
||||
retryPlan.replace('- A tenant-keyed flag', 'Unless rejected.\n\n- A tenant-keyed flag'),
|
||||
retryPlan.replace('- A tenant-keyed flag', 'Proposed baseline:\n\n- A tenant-keyed flag'),
|
||||
retryPlan.replace('legacyAuthFlow()` stays callable', 'newAuthFlow()` stays callable'),
|
||||
retryPlan.replace('Run each fixture', 'Run different fixtures'),
|
||||
retryPlan.replace('and assert identical `Session` shape on success', 'and document different `Session` shape on success'),
|
||||
retryPlan.replace('identical error code on failure', 'similar error code on failure'),
|
||||
retryPlan.replace('through `legacyAuthFlow()` and', 'through `newAuthFlow()` and'),
|
||||
retryPlan.replace('AuthBroker.authenticate()', 'NewBroker.authenticate()'),
|
||||
retryPlan.replace('and AuthBroker, identical', 'and NewBroker, identical'),
|
||||
retryPlan.replace('identical Session / error codes', 'identical OtherResponse / error codes'),
|
||||
retryPlan.replace('Files: src/auth/authFlow.contract.test.ts', 'Files: src/auth/other.contract.test.ts'),
|
||||
retryPlan.replace('suite green on both paths', 'suite green on the new path'),
|
||||
retryPlan.replace(fixture.retry.task, ''),
|
||||
retryPlan.replace('This test\nis also the gate', 'This optional test\nis also the gate'),
|
||||
]) { expect(text).not.toBe(retryPlan); expect(evaluateRetry(text).regression, text).toBeUndefined(); }
|
||||
});
|
||||
|
||||
test('retry proposals and current withdrawals cannot supply parity coverage', () => {
|
||||
for (const text of [
|
||||
retryPlan.replace(fixture.retry.mandatory, 'If approved, ' + fixture.retry.mandatory),
|
||||
retryPlan.replace(fixture.retry.mandatory, '"' + fixture.retry.mandatory + '"'),
|
||||
retryPlan.replace(fixture.retry.mandatory, '```\n' + fixture.retry.mandatory + '\n```'),
|
||||
retryPlan.replace(fixture.retry.mandatory, fixture.retry.mandatory + '\nThis test is withdrawn.'),
|
||||
retryPlan.replace(fixture.retry.task, fixture.retry.task + '\nT4 is no longer required.'),
|
||||
retryPlan.replace(fixture.retry.legacy, fixture.retry.legacy + '\nCorrection: legacyAuthFlow() is changed this release.'),
|
||||
retryPlan.replace(fixture.retry.legacy, fixture.retry.legacy.split('\n').map(line => '> ' + line).join('\n')),
|
||||
'# Hypothetical example\n\n' + retryPlan,
|
||||
'# Proposed work\n\n' + retryPlan,
|
||||
]) { expect(text).not.toBe(retryPlan); expect(evaluateRetry(text).regression, text).toBeUndefined(); }
|
||||
});
|
||||
|
||||
test('consistent retry identities and unrelated negative outcomes retain parity evidence', () => {
|
||||
for (const text of [
|
||||
retryPlan.replaceAll('AuthBroker', 'SessionBroker').replaceAll('Session', 'Reply'),
|
||||
retryPlan.replaceAll('authFlow.contract.test.ts', 'loginFlow.contract.test.js').replaceAll('T4', 'T14'),
|
||||
retryPlan.replace(fixture.retry.task, fixture.retry.task + '\n - Verify revoked tokens are rejected.'),
|
||||
retryPlan.replace(fixture.retry.legacy, fixture.retry.legacy + '\nRejected alternatives stay documented.'),
|
||||
]) expect(evaluateRetry(text).regression).toBe('plan');
|
||||
});
|
||||
|
||||
for (const prefix of [
|
||||
'# Source\n\n',
|
||||
'An unproven hypothesis.\n\n',
|
||||
'The following is a hypothetical example.\n\n',
|
||||
'The following is source material only, not the current reviewed plan.\n\n',
|
||||
'# Current reviewed plan\n\nThe following sections reproduce source material only; they are not requirements of this plan.\n\n',
|
||||
]) {
|
||||
test('first and retry evidence retain enclosing source frame: ' + prefix.trim(), () => {
|
||||
expect(evaluate(prefix + plan).regression).toBeUndefined();
|
||||
expect(evaluateRetry(prefix + retryPlan).regression).toBeUndefined();
|
||||
});
|
||||
}
|
||||
|
||||
test('declaration wording and task identity can vary without changing the required baseline', () => {
|
||||
for (const text of [
|
||||
plan.replaceAll('T4', 'T12'),
|
||||
plan.replace('capture current', 'pin existing'),
|
||||
plan.replace('is added as a critical', 'is required as a mandatory'),
|
||||
plan.replace('auth/legacy tests — ', 'core/auth — '),
|
||||
plan.replace('wrong-audience, wrong-issuer,', 'wrong-audience, wrong-issuer, malformed,'),
|
||||
plan.replace(fixture.task, fixture.task + '\n - Verify expired and revoked tokens are rejected.'),
|
||||
plan.replace(fixture.mandatory, fixture.mandatory + '\nKeep a record of rejected alternatives.'),
|
||||
'# Historical example\n\nA proposed suite was discussed.\n\n# Current reviewed plan\n\n' + plan,
|
||||
]) expect(evaluate(text).regression, text).toBe('plan');
|
||||
});
|
||||
|
||||
test('declaration, task, target and original baseline cannot lend each other missing evidence', () => {
|
||||
for (const text of [
|
||||
plan.replace(fixture.mandatory, ''),
|
||||
plan.replace(fixture.task, ''),
|
||||
plan.replace(fixture.verification, ''),
|
||||
plan.replace('suite (T4)', 'suite (T5)'),
|
||||
plan.replace('against the untouched', 'against the rewritten'),
|
||||
plan.replace('first and commit it green. This is the baseline.', 'after rollout and document it.'),
|
||||
plan.replace('capture current', 'describe future'),
|
||||
plan.replace('is\nthe oracle the new path is compared to', 'is documentation the new path links to'),
|
||||
plan.replace('characterization test suite** for `legacyAuthFlow()`', 'characterization test suite** for `newAuthFlow()`'),
|
||||
plan.replace('suite for `legacyAuthFlow()` prior behavior', 'suite for `newAuthFlow()` prior behavior'),
|
||||
plan.replace('untouched `legacyAuthFlow()`', 'untouched `newAuthFlow()`'),
|
||||
]) { expect(text).not.toBe(plan); expect(evaluate(text).regression, text).toBeUndefined(); }
|
||||
});
|
||||
|
||||
test('proposals, future work, conditional and quoted declarations are not required coverage', () => {
|
||||
for (const text of [
|
||||
plan.replace('is added as a critical', 'will be added as a critical'),
|
||||
plan.replace('is added as a critical', 'might be added as a critical'),
|
||||
plan.replace('is added as a critical', 'is not added as a critical'),
|
||||
plan.replace(fixture.mandatory, 'If approved, ' + fixture.mandatory),
|
||||
plan.replace(fixture.mandatory, 'Example: ' + fixture.mandatory),
|
||||
plan.replace(fixture.mandatory, 'An unproven hypothesis. ' + fixture.mandatory),
|
||||
plan.replace(fixture.mandatory, '"' + fixture.mandatory + '"'),
|
||||
plan.replace(fixture.mandatory, "'" + fixture.mandatory + "'"),
|
||||
plan.replace(fixture.mandatory, fixture.mandatory.split('\n').map(line => '> ' + line).join('\n')),
|
||||
plan.replace(fixture.mandatory, '```\n' + fixture.mandatory + '\n```'),
|
||||
'# Hypothetical example\n\n' + plan,
|
||||
'# Quoted source\n\n' + plan,
|
||||
'# Proposed work\n\n' + plan,
|
||||
plan.replace('## Verification\n\n1. Run', '## Verification\n\n1. If approved, run'),
|
||||
]) { expect(text).not.toBe(plan); expect(evaluate(text).regression, text).toBeUndefined(); }
|
||||
});
|
||||
|
||||
test('withdrawal of the owned suite, task or baseline prevents credit', () => {
|
||||
for (const [from, addition] of [
|
||||
[fixture.mandatory, 'This suite is withdrawn.'],
|
||||
[fixture.mandatory, 'The characterization suite is not required.'],
|
||||
[fixture.mandatory, 'Do not run the suite.'],
|
||||
[fixture.task, 'Correction: T4 is cancelled.'],
|
||||
[fixture.task, 'This task is deferred.'],
|
||||
[fixture.verification, 'Correction: T4 is cancelled.'],
|
||||
[fixture.verification, 'Skip the characterization suite.'],
|
||||
]) expect(evaluate(plan.replace(from!, from + '\n' + addition)).regression, addition).toBeUndefined();
|
||||
});
|
||||
|
||||
test('the required suite cannot replace completed distinct native decisions or final report', () => {
|
||||
for (let index = 0; index < transcript.calls.length; index++) {
|
||||
const native = structuredClone(transcript);
|
||||
native.calls.splice(index, 1);
|
||||
expect(evaluate(plan, native).ok).toBe(false);
|
||||
expect(evaluate(plan, native).missing).toHaveLength(1);
|
||||
}
|
||||
for (const mutate of [
|
||||
(native: PlanCountTranscript) => { native.calls[0]!.failed = true; },
|
||||
(native: PlanCountTranscript) => { native.calls[0]!.answeredAt = new Date(start - 1).toISOString(); },
|
||||
(native: PlanCountTranscript) => { native.calls[0]!.sessionId = 'foreign-session'; },
|
||||
(native: PlanCountTranscript) => { native.calls.push(structuredClone(native.calls[0]!)); },
|
||||
]) {
|
||||
const native = structuredClone(transcript); mutate(native);
|
||||
expect(evaluate(plan, native).ok).toBe(false);
|
||||
}
|
||||
expect(evaluate(plan.replace(fixture.reviewReport, '')).problems).toContain('final review report absent or empty');
|
||||
});
|
||||
|
||||
test('public declaration still requires the existing owned time and session interval', () => {
|
||||
const native = structuredClone(transcript);
|
||||
native.assistantMessages = [{ sessionId: native.calls[0]!.sessionId, timestamp: new Date(start).toISOString(), text: plan }];
|
||||
expect(evaluate(fixture.reviewReport, native).regression).toBe('public-narration');
|
||||
native.assistantMessages[0]!.timestamp = new Date(start - 1).toISOString();
|
||||
expect(evaluate(fixture.reviewReport, native).regression).toBeUndefined();
|
||||
native.assistantMessages[0]!.timestamp = new Date(end + 1).toISOString();
|
||||
expect(evaluate(fixture.reviewReport, native).regression).toBeUndefined();
|
||||
native.assistantMessages[0]!.timestamp = new Date(start).toISOString();
|
||||
native.assistantMessages[0]!.sessionId = 'foreign-session';
|
||||
expect(evaluate(fixture.reviewReport, native).regression).toBeUndefined();
|
||||
});
|
||||
|
||||
test('new declaration evidence registers only the two existing engineering count owners', () => {
|
||||
for (const file of ['test/eng-declared-regression-ai.test.ts', 'test/fixtures/eng-declared-regression-ai.json']) {
|
||||
expect(selectTests([file], E2E_TOUCHFILES, []).selected.sort()).toEqual(['plan-eng-finding-count', 'plan-eng-multi-finding-batching']);
|
||||
}
|
||||
});
|
||||
@@ -0,0 +1,177 @@
|
||||
import { expect, test } from 'bun:test';
|
||||
import * as fs from 'node:fs';
|
||||
import * as os from 'node:os';
|
||||
import * as path from 'node:path';
|
||||
import { pathToFileURL } from 'node:url';
|
||||
import fixture from './fixtures/eng-seeded-completion-ai.json';
|
||||
import { classifyVisible, extractPlanFilePath } from './helpers/claude-pty-runner';
|
||||
import * as predicates from './helpers/claude-pty-runner';
|
||||
import { selectTests, E2E_TOUCHFILES } from './helpers/touchfiles';
|
||||
|
||||
const gate = '─────\nClaude has written up a plan and is ready to execute. Would you like to proceed?\n❯ 1. Yes, and use auto mode\n2. Yes, manually approve edits\n3. Tell Claude what to change';
|
||||
const compactGate = 'Exit plan mode?\nClaude wants to exit plan mode\n❯ 1. Yes, and switch to default (ask each time) for this session\n2. No';
|
||||
const question = 'Which runner should the plan use?\nA) Use the built-in runner\nB) Build a custom runner\nRecommendation: A because it avoids duplicate scheduling logic.\nReply with A or B.';
|
||||
const classify = (history: string, currentScreen: string) => classifyVisible(history, { strictPlanWrites: true, currentScreen });
|
||||
|
||||
test('historical TODO excerpt supplies no current seeded completion or plan file', () => {
|
||||
expect(classifyVisible(fixture.visibleReadExcerpt, { strictPlanWrites: true })?.outcome).toBe('plan_ready');
|
||||
expect(extractPlanFilePath(fixture.visibleReadExcerpt)).toBeNull();
|
||||
expect(classify(fixture.visibleReadExcerpt, fixture.visibleReadExcerpt)).toBeNull();
|
||||
expect(classify(fixture.visibleReadExcerpt, fixture.reconstructedScreen)).toBeNull();
|
||||
expect(classify(fixture.visibleReadExcerpt, '')).toBeNull();
|
||||
});
|
||||
|
||||
test('only a complete current native approval panel establishes seeded plan_ready', () => {
|
||||
for (const current of [gate, compactGate]) {
|
||||
expect(classify(fixture.visibleReadExcerpt + '\n' + current, current)?.outcome).toBe('plan_ready');
|
||||
for (const invalid of [
|
||||
'', 'Still reviewing the draft.', current + '\nStill reviewing the draft.',
|
||||
current.split('\n').slice(0, -1).join('\n'), current.replace('❯', ''),
|
||||
current.replace(/2\.[^\n]+/, '2. Approve another action'),
|
||||
'Example:\n' + current, '```text\n' + current, current.split('\n').map(line => '> ' + line).join('\n'),
|
||||
]) expect(classify(fixture.visibleReadExcerpt + '\n' + current, invalid), invalid).toBeNull();
|
||||
}
|
||||
});
|
||||
|
||||
test('ignoring old completion text preserves a genuine current question and stronger failure outcomes', () => {
|
||||
for (const history of [fixture.visibleReadExcerpt, gate, compactGate]) {
|
||||
expect(classify(history + '\n' + question, question)?.outcome).toBe('asked');
|
||||
}
|
||||
expect(classify(fixture.visibleReadExcerpt + '\n' + question, fixture.visibleReadExcerpt + '\n' + question)?.outcome).toBe('asked');
|
||||
expect(classify('⏺ Write(/tmp/.claude/plans/review.md)\n' + gate, gate)?.outcome).toBe('wrote_findings_before_asking');
|
||||
expect(classify('⏺ Write(/tmp/implementation.ts)\n' + fixture.visibleReadExcerpt, '')?.outcome).toBe('silent_write');
|
||||
// Callers which do not opt into the current viewport retain their contract.
|
||||
expect(classifyVisible('The item is ready to execute.')?.outcome).toBe('plan_ready');
|
||||
expect(classifyVisible(question)?.outcome).toBe('asked');
|
||||
});
|
||||
|
||||
test('real PTY waits past old TODO, stale, partial and mismatched panels but accepts the current gate', async () => {
|
||||
const scenarios = [
|
||||
{ name: 'todo', initial: fixture.visibleReadExcerpt, expected: 'asked' },
|
||||
{ name: 'stale', initial: gate + '\u001b[2J\u001b[HStill reviewing the draft.', expected: 'asked' },
|
||||
{ name: 'partial', initial: gate.split('\n').slice(0, -1).join('\n'), expected: 'asked' },
|
||||
{ name: 'mismatch', initial: gate.replace('3. Tell Claude what to change', '3. Delete the draft'), expected: 'asked' },
|
||||
{ name: 'complete', initial: gate, expected: 'plan_ready' },
|
||||
{ name: 'cursorless-timeout', initial: gate.replace('❯ ', ''), expected: 'timeout' },
|
||||
];
|
||||
const results = await Promise.allSettled(scenarios.map(async scenario => {
|
||||
const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'seeded-completion-'));
|
||||
const cli = path.join(dir, 'fake-claude'), working = path.join(dir, 'repo');
|
||||
fs.mkdirSync(working);
|
||||
fs.writeFileSync(cli, `#!/usr/bin/env bun
|
||||
const fs = require('node:fs');
|
||||
fs.writeFileSync(process.env.COMPLETION_ARGV, JSON.stringify(process.argv.slice(2)));
|
||||
let sent = false;
|
||||
const render = text => process.stdout.write('\\x1b[2J\\x1b[H' + text.replace(/\\n/g, '\\r\\n'));
|
||||
process.stdin.on('data', chunk => {
|
||||
if (sent || !chunk.toString().includes('/plan-eng-review')) return;
|
||||
sent = true;
|
||||
fs.writeFileSync(process.env.COMPLETION_PHASE, 'initial');
|
||||
render(${JSON.stringify(scenario.initial)});
|
||||
if (${JSON.stringify(scenario.expected)} === 'asked') setTimeout(() => {
|
||||
fs.writeFileSync(process.env.COMPLETION_PHASE, 'question');
|
||||
render(${JSON.stringify(question)});
|
||||
}, 4500);
|
||||
});
|
||||
setInterval(() => {}, 1000);
|
||||
`, { mode: 0o755 });
|
||||
try {
|
||||
const runner = pathToFileURL(path.join(import.meta.dir, 'helpers/claude-pty-runner.ts')).href;
|
||||
const childFile = path.join(dir, 'observe.ts');
|
||||
fs.writeFileSync(childFile, `import { runPlanSkillObservation, resolveClaudeBinary } from ${JSON.stringify(runner)};
|
||||
if (resolveClaudeBinary() !== process.env.BROWSE_TERMINAL_BINARY) throw new Error('Fake CLI resolution failed');
|
||||
const obs = await runPlanSkillObservation({ skillName: 'plan-eng-review', inPlanMode: true,
|
||||
initialPlanContent: '# Plan: Completion regression\\n\\nReview the existing draft.',
|
||||
cwd: ${JSON.stringify(working)}, timeoutMs: 12000,
|
||||
env: { COMPLETION_ARGV: process.env.COMPLETION_ARGV, COMPLETION_PHASE: process.env.COMPLETION_PHASE } });
|
||||
console.log(JSON.stringify(obs));
|
||||
`);
|
||||
// Only this isolated child receives the executable override; it verifies
|
||||
// the resolver before the real PTY launch, so no provider can be invoked.
|
||||
const child = Bun.spawn([process.execPath, childFile], { cwd: process.cwd(),
|
||||
env: { ...process.env, BROWSE_TERMINAL_BINARY: cli,
|
||||
COMPLETION_ARGV: path.join(dir, 'argv.json'), COMPLETION_PHASE: path.join(dir, 'phase.txt'),
|
||||
EVALS_RUN_ID: 'seeded-completion-fake', GSTACK_EVAL_DIR: path.join(dir, 'evidence') },
|
||||
stdout: 'pipe', stderr: 'pipe' });
|
||||
const [stdout, stderr, exitCode] = await Promise.all([
|
||||
new Response(child.stdout).text(), new Response(child.stderr).text(), child.exited,
|
||||
]);
|
||||
expect(exitCode, stderr).toBe(0);
|
||||
const obs = JSON.parse(stdout.trim().split('\n').at(-1)!);
|
||||
expect(obs.outcome, scenario.name).toBe(scenario.expected);
|
||||
expect(fs.readFileSync(path.join(dir, 'phase.txt'), 'utf8'), scenario.name).toBe(scenario.expected === 'asked' ? 'question' : 'initial');
|
||||
expect(obs.planFile).toBeUndefined();
|
||||
expect(obs.scopeGateAutoSelectObserved).toBe(false);
|
||||
const args = JSON.parse(fs.readFileSync(path.join(dir, 'argv.json'), 'utf8'));
|
||||
expect(args.filter((arg: string) => arg === '--session-id')).toHaveLength(1);
|
||||
expect(args).toContain('--permission-mode'); expect(args).toContain('plan');
|
||||
const saved = JSON.parse(fs.readFileSync(path.join(obs.artifactDir, 'observation.json'), 'utf8'));
|
||||
expect(saved.scopeSessionId).toBe(args[args.indexOf('--session-id') + 1]);
|
||||
expect(saved.scopeGateAutoSelectObserved).toBe(false);
|
||||
} finally { fs.rmSync(dir, { recursive: true, force: true }); }
|
||||
}));
|
||||
for (let i = 0; i < results.length; i++) {
|
||||
const result = results[i]!;
|
||||
expect(result.status, `${scenarios[i]!.name}: ${result.status === 'rejected' ? String(result.reason) : 'complete'}`).toBe('fulfilled');
|
||||
}
|
||||
}, 45000);
|
||||
|
||||
async function mockedObservation(frames: string[], verdict: 'waiting' | 'working', seeded = true) {
|
||||
// Execute the unchanged observer function with its real classifiers, a
|
||||
// synthetic clock/session, and a stubbed judge. No CLI or judge is launched.
|
||||
const source = fs.readFileSync(path.join(import.meta.dir, 'helpers/claude-pty-runner.ts'), 'utf8');
|
||||
const start = source.indexOf('export async function runPlanSkillObservation(');
|
||||
const end = source.indexOf('\n// ─', start);
|
||||
expect(start).toBeGreaterThan(0); expect(end).toBeGreaterThan(start);
|
||||
const executable = source.slice(start, end).replace('export async function', 'async function') + '\nreturn runPlanSkillObservation;';
|
||||
const js = new Bun.Transpiler({ loader: 'ts' }).transformSync(executable);
|
||||
let clock = 0, tick = -1, closed = 0, judged = 0;
|
||||
const current = () => frames[Math.min(Math.max(tick, 0), frames.length - 1)]!;
|
||||
const args: Record<string, unknown> = {
|
||||
path, process: { cwd: () => '/synthetic-owned' }, Date: { now: () => clock }, randomUUID: () => 'owned',
|
||||
Bun: { sleep: async (ms: number) => { if (ms === 2000) { tick++; clock += tick === 0 && frames.length > 1 ? 2000 : 61000; } else clock += ms; } },
|
||||
launchClaudePty: async () => ({ send: () => {}, mark: () => 0, exited: () => false,
|
||||
visibleSince: current, rawOutput: current, currentScreen: async () => current(), hermeticConfigDir: null,
|
||||
close: async () => { closed++; } }),
|
||||
createPlanCountSnapshotWriter: () => () => ({}), logPtySnapshot: () => {},
|
||||
isProseAUQVisible: predicates.isProseAUQVisible, isPlanReadyVisible: predicates.isPlanReadyVisible,
|
||||
isScopeGateQuestionVisible: predicates.isScopeGateQuestionVisible,
|
||||
isScopeGateAutoSelectVisible: predicates.isScopeGateAutoSelectVisible,
|
||||
classifyVisible, extractPlanFilePath, findNativeAutoDecision: () => null,
|
||||
judgePtyState: () => { judged++; return { state: verdict, reasoning: 'synthetic current-frame verdict' }; },
|
||||
};
|
||||
const run = new Function(...Object.keys(args), js)(...Object.values(args));
|
||||
const obs = await run({ skillName: 'plan-eng-review', timeoutMs: 70000,
|
||||
...(seeded ? { initialPlanContent: '# Plan: Required draft' } : {}) });
|
||||
expect(closed).toBe(1);
|
||||
return { obs, judged };
|
||||
}
|
||||
|
||||
for (const [name, current] of [
|
||||
['cursorless approval', gate.replace('❯ ', '')],
|
||||
['partial approval', gate.split('\n').slice(0, -1).join('\n')],
|
||||
] as const) test(`rejected seeded ${name} cannot gain prose or judge waiting credit`, async () => {
|
||||
const { obs, judged } = await mockedObservation([current], 'waiting');
|
||||
expect(judged).toBeGreaterThan(0);
|
||||
expect(obs.outcome).toBe('timeout');
|
||||
expect(obs.proseAUQEverObserved).toBe(false); expect(obs.waitingEverObserved).toBe(false);
|
||||
});
|
||||
|
||||
test('rejected completion does not erase a genuine earlier question or change unseeded behavior', async () => {
|
||||
const prior = question + '\nDo you want to create draft.md?\n❯ 1. Yes\n2. No\nEsc to cancel · Tab to amend';
|
||||
expect(predicates.isProseAUQVisible(prior)).toBe(true);
|
||||
expect(classifyVisible(prior)).toBeNull();
|
||||
const { obs } = await mockedObservation([prior, gate.replace('❯ ', '')], 'working');
|
||||
expect(obs.outcome).toBe('asked'); expect(obs.proseAUQEverObserved).toBe(true);
|
||||
expect(obs.waitingEverObserved).toBe(false);
|
||||
const unseeded = await mockedObservation([gate.replace('❯ ', '')], 'waiting', false);
|
||||
expect(unseeded.obs.outcome).toBe('plan_ready'); expect(unseeded.judged).toBe(0);
|
||||
});
|
||||
|
||||
test('completion evidence dependencies select exactly the seeded observation owners', () => {
|
||||
const owners = ['plan-ceo-review-plan-mode', 'plan-eng-review-plan-mode', 'plan-design-review-plan-mode',
|
||||
'plan-devex-review-plan-mode', 'plan-mode-no-op', 'auto-decide-preserved', 'conductor-prose'].sort();
|
||||
for (const file of ['test/eng-seeded-completion-ai.test.ts', 'test/fixtures/eng-seeded-completion-ai.json']) {
|
||||
expect(selectTests([file], E2E_TOUCHFILES).selected.sort()).toEqual(owners);
|
||||
}
|
||||
});
|
||||
+454
@@ -0,0 +1,454 @@
|
||||
{
|
||||
"transcript": {
|
||||
"status": "ready",
|
||||
"calls": [],
|
||||
"assistantMessages": [
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"text": "I'll invoke the `/plan-ceo-review` skill against the draft plan.",
|
||||
"timestamp": "2026-09-10T04:21:58.556Z"
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"text": "Running the preamble first, then a light system audit so the mode question is grounded in the actual listing code.",
|
||||
"timestamp": "2026-09-10T04:22:10.706Z"
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"text": "Found the relevant code paths. Running the question-tuning check for the mode question and handling the onboarding markers, then I'll present the mode decision.",
|
||||
"timestamp": "2026-09-10T04:23:41.654Z"
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"text": "Heads-up from the preamble: unshipped work on this branch, so `/review` then `/ship` when you're ready. Also, gstack follows the **Boil the Ocean** principle: do the complete thing when AI makes the marginal cost near zero. Read more at https://garryslist.org/posts/boil-the-ocean if you'd like.\n\n**Review mode: HOLD SCOPE.**\n\nAuto-decided \"Select review mode\" \u2192 HOLD SCOPE (your saved preference on `plan-ceo-review-mode`). Change with /plan-tune.\n\nWhy this mode fits the draft:\n\n- **It is a correctness fix to an existing path, not a new capability.** Skill listings should not change order between machines or filesystems. The context default for bug fixes and refactors is HOLD SCOPE.\n- **The draft already states its invariants.** Membership, aliases, metadata and text/JSON formats stay unchanged. The review's job is to make those invariants bulletproof, not to widen them.\n- **The codebase confirms the problem is real.** The census helper enumerates skills with no sort at all. The context-bill code sorts with the default code-point comparator, so a mixed-case name like `Zeta` lands before `alpha`. Both are places the deep review should pin with tests.\n\nWhat I deliberately left open for the later invocation, at your request:\n\n1. **The implementation approach decision** (a shared case-insensitive comparator versus per-site sorts). The skill requires your explicit approval there before the deep review.\n2. **Which listing path the draft means.** The census helper, the context-bill CLI, or both. This changes the file list.\n3. **Onboarding prompts** (continuous checkpoint feature, cross-project learnings) and the Office Hours offer. Their markers are untouched, so they will fire again next healthy run.\n\nThe plan file at `.claude/plans/please-review-the-following-melodic-kernighan.md` records the mode, the audit findings with file and line references, and the three open items. I have not called ExitPlanMode since the review workflow is paused rather than complete.\n\nSTATUS: DONE. No durable learnings this session.",
|
||||
"timestamp": "2026-09-10T04:24:41.750Z"
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"text": "I'll invoke the /plan-ceo-review skill against your draft plan.",
|
||||
"timestamp": "2026-09-10T04:32:12.533Z"
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"text": "Running the skill preamble and base-branch detection first.",
|
||||
"timestamp": "2026-09-10T04:32:27.444Z"
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"text": "Base branch is `main`. Checking your question-tuning preference for the mode question before I render it.",
|
||||
"timestamp": "2026-09-10T04:33:00.854Z"
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"text": "Heads-up from gstack: there is unshipped work on this branch, so `/review` then `/ship` when you get to it.\n\n**D1 \u2014 Review mode for the deterministic skill-list ordering draft**\n\nAuto-decided \"Review mode: push scope up, cherry-pick expansions, hold scope, or cut to minimum?\" \u2192 **HOLD SCOPE** (your preference). Change with /plan-tune.\n\nWhy HOLD SCOPE is the recommendation the auto-decide landed on:\n\n- **The draft is a determinism fix to an existing path,** not a new capability. The skill's context defaults map bug fixes and refactors to HOLD SCOPE.\n- **The draft already draws hard boundaries.** Membership, aliases, metadata, and text/JSON formats stay unchanged. That is a hold-scope posture written into the plan itself.\n- **The value is in rigor, not ambition.** The interesting questions are locale-independent comparison for mixed-case names, whether the sort happens once at the listing path or leaks into other enumerators, and how the tests force differing directory order. Those are HOLD SCOPE questions.\n\nSkipped in this invocation, per your request:\n\n- **Office Hours offer and onboarding prompts.** The preamble fired two one-time setup prompts. I did not answer or mark them, so they re-fire on your next healthy run.\n- **Approach selection (0C-bis).** The skill normally wants an approved implementation approach before mode selection. Since you asked for only the mode decision, this is still pending. Expect it as the first question when you run the substantive review.\n- **The 11-section deep review and plan file.** Not started. No plan file was written, so there is no review report and I did not exit plan mode.\n\nNo durable learnings this session.\n\nNext: when you are ready, re-run `/plan-ceo-review` with the draft. Tell it \"HOLD SCOPE already selected\" so it skips D1 and goes straight to approach selection and the deep review.",
|
||||
"timestamp": "2026-09-10T04:33:46.197Z"
|
||||
}
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:22:00.757Z",
|
||||
"toolUseId": "toolu_01D1z8pVbfkEeHZGgi6JdPZk",
|
||||
"kind": "use",
|
||||
"name": "Skill",
|
||||
"input": {
|
||||
"skill": "plan-ceo-review",
|
||||
"args": "Draft: deterministic skill-list ordering. Users compare skill listings in scripts and reviews. Make the existing listing path sort registered skill names deterministically before rendering them. Keep skill membership, aliases, metadata and text/JSON output formats unchanged. Cover mixed-case names and differing directory enumeration order with tests. Review-mode decision only for this invocation."
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:22:02.528Z",
|
||||
"toolUseId": "toolu_01D1z8pVbfkEeHZGgi6JdPZk",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:22:12.591Z",
|
||||
"toolUseId": "toolu_01B89LH3gWatoKLbFjkW1duv",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "_SS=\"$HOME/.claude/skills/gstack/bin/gstack-skill-start\"\n[ -x \"$_SS\" ] || _SS=\".claude/skills/gstack/bin/gstack-skill-start\"\n\"$_SS\" --skill \"plan-ceo-review\" --model \"claude\" --parent-pid \"$PPID\" \\\n || echo \"SKILL_START: unavailable \u2014 stale install; run ./setup or /gstack-upgrade (preamble degraded, continue the user's task)\"",
|
||||
"description": "Run gstack skill-start preamble"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:22:15.395Z",
|
||||
"toolUseId": "toolu_01B89LH3gWatoKLbFjkW1duv",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:22:42.272Z",
|
||||
"toolUseId": "toolu_011L1hSC8vSZLDVGpfiokh1h",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "git remote get-url origin 2>/dev/null; echo \"---LOG\"; git log --oneline -15; echo \"---STAT\"; git diff main --stat 2>/dev/null | tail -5; echo \"---STASH\"; git stash list | head; echo \"---DESIGN\"; SLUG=$(~/.claude/skills/gstack/browse/bin/remote-slug 2>/dev/null || basename \"$(git rev-parse --show-toplevel 2>/dev/null || pwd)\"); BRANCH=$(git rev-parse --abbrev-ref HEAD 2>/dev/null | tr '/' '-'); echo \"SLUG=$SLUG BRANCH=$BRANCH\"; ls -t ~/.gstack/projects/$SLUG/*-design-*.md 2>/dev/null | head -1; ls -t docs/designs/*.md 2>/dev/null | head -3; ls -t ~/.gstack/projects/$SLUG/*-$BRANCH-ceo-handoff-*.md 2>/dev/null | head -1 || echo NO_HANDOFF; echo \"---LEARN\"; ~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo unset; ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 5 2>/dev/null | head -20",
|
||||
"description": "System audit: remote, log, diff, stash, design doc, learnings"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:22:43.881Z",
|
||||
"toolUseId": "toolu_011L1hSC8vSZLDVGpfiokh1h",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:22:54.173Z",
|
||||
"toolUseId": "toolu_01Jpe19C6Qy7iLjhxsVVFZEM",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "cd /home/vercel-sandbox/gstack; ls bin | grep -i -E \"skill|list|catalog|census|route\" ; echo \"---GREP\"; grep -rl -i -E \"list.*skills|skills.*list|listSkills|skill-list|skills list\" --include=*.ts --include=*.sh --include=*.tmpl bin scripts lib _gstack-command setup 2>/dev/null | grep -v node_modules | head -30; echo \"---TODOS\"; grep -n -i -E \"sort|order|determin|listing\" TODOS.md | head -20",
|
||||
"description": "Locate skill listing code and related TODOs"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:22:54.300Z",
|
||||
"toolUseId": "toolu_01Jpe19C6Qy7iLjhxsVVFZEM",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:06.413Z",
|
||||
"toolUseId": "toolu_013RE2TjYQMdqe8nLecHC4vw",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "cd /home/vercel-sandbox/gstack; grep -n -E '\"(skill:check|skill:list|skills|list|catalog|context-bill)[^\"]*\":' package.json; echo \"---REGISTRY\"; grep -rn -i -E \"registered skill|registeredSkills|skill registry|SKILL_REGISTRY|listRegistered|registerSkill\" --include=*.ts --include=*.sh scripts lib bin test/helpers 2>/dev/null | grep -v node_modules | head -15; echo \"---READDIR\"; grep -rn -E \"readdirSync\\(\" scripts/gen-skill-docs.ts scripts/skill-check.ts scripts/skill-health.ts test/helpers/skill-census.ts lib/*.ts 2>/dev/null | head -20; echo \"---JSON\"; grep -rln -E \"\\-\\-json\" bin scripts --include=* 2>/dev/null | head -20",
|
||||
"description": "Find skill enumeration and JSON-listing code"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:06.508Z",
|
||||
"toolUseId": "toolu_013RE2TjYQMdqe8nLecHC4vw",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:13.375Z",
|
||||
"toolUseId": "toolu_013Ee9LJJQ8R1fR2sQFPGwkj",
|
||||
"kind": "use",
|
||||
"name": "Read",
|
||||
"input": {
|
||||
"file_path": "/home/vercel-sandbox/gstack/test/helpers/skill-census.ts",
|
||||
"offset": 40,
|
||||
"limit": 50
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:13.401Z",
|
||||
"toolUseId": "toolu_013Ee9LJJQ8R1fR2sQFPGwkj",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:14.737Z",
|
||||
"toolUseId": "toolu_01BU2xpwy4uMyx1Xp4quu9bj",
|
||||
"kind": "use",
|
||||
"name": "Read",
|
||||
"input": {
|
||||
"file_path": "/home/vercel-sandbox/gstack/lib/context-bill.ts",
|
||||
"offset": 195,
|
||||
"limit": 30
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:14.759Z",
|
||||
"toolUseId": "toolu_01BU2xpwy4uMyx1Xp4quu9bj",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:16.384Z",
|
||||
"toolUseId": "toolu_013aumciUHw2Bqjaaq27g1EV",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "cd /home/vercel-sandbox/gstack; grep -n -E \"json|text|format|\\.sort\\(|localeCompare\" lib/context-bill.ts | head -30; echo \"---BIN\"; grep -n -E \"json|sort|format\" bin/gstack-context-bill | head -15; echo \"---SKILLCHECK\"; grep -n -E \"json|\\.sort\\(\" scripts/skill-check.ts | head",
|
||||
"description": "Check output formats and sorting in listing candidates"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:16.450Z",
|
||||
"toolUseId": "toolu_013aumciUHw2Bqjaaq27g1EV",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:26.286Z",
|
||||
"toolUseId": "toolu_015mJBMXZtpHKA6hWxDwTo8j",
|
||||
"kind": "use",
|
||||
"name": "Read",
|
||||
"input": {
|
||||
"file_path": "/home/vercel-sandbox/gstack/lib/context-bill.ts",
|
||||
"offset": 335,
|
||||
"limit": 50
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:26.306Z",
|
||||
"toolUseId": "toolu_015mJBMXZtpHKA6hWxDwTo8j",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:28.306Z",
|
||||
"toolUseId": "toolu_01H7ZHzRW7U18u8zh3L6yKFH",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "cd /home/vercel-sandbox/gstack; grep -n -E \"json|JSON|renderText|function render|function format\" bin/gstack-context-bill.ts bin/gstack-context-bill 2>/dev/null | head -20; ls bin | grep context-bill; echo \"---TESTS\"; ls test | grep -i -E \"context-bill|census|catalog\"; echo \"---GBRAIN\"; grep -n -E \"\\.skills\\b|skills:\" lib/context-bill.ts | head -10",
|
||||
"description": "Find context-bill CLI output formats and tests"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:28.376Z",
|
||||
"toolUseId": "toolu_01H7ZHzRW7U18u8zh3L6yKFH",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:45.519Z",
|
||||
"toolUseId": "toolu_01BHQiS1mU8LZfxsWwFbGADs",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "cd /home/vercel-sandbox/gstack; grep -n -i -E \"plan-ceo-review.*(mode|scope)|ceo.*mode\" ~/.claude/skills/gstack/scripts/question-registry.ts | head -5; echo \"---CHECK\"; printf '%s' \"Select review mode (expansion/selective/hold/reduction) for deterministic skill-list ordering plan\" | ~/.claude/skills/gstack/bin/gstack-question-preference --check \"plan-ceo-review-mode-selection\" --summary-stdin 2>&1 | head -5; echo \"---MARKERS\"; touch \"/tmp/gstack-paid-shard-pNXtSA/tmp/gstack-auto-decide-w2UU3e/.completeness-intro-seen\" && echo \"lake-intro marker touched\"",
|
||||
"description": "Question-tuning check and lake-intro marker"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:47.061Z",
|
||||
"toolUseId": "toolu_01BHQiS1mU8LZfxsWwFbGADs",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:53.288Z",
|
||||
"toolUseId": "toolu_01Fz4MuCGi9tb8sPCq6SswEB",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "cd /home/vercel-sandbox/gstack; printf '%s' \"Select review mode (expansion/selective/hold/reduction) for deterministic skill-list ordering plan\" | ~/.claude/skills/gstack/bin/gstack-question-preference --check \"plan-ceo-review-mode\" --summary-stdin 2>&1 | head -3",
|
||||
"description": "Re-run tuning check with registered question id"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:54.770Z",
|
||||
"toolUseId": "toolu_01Fz4MuCGi9tb8sPCq6SswEB",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:24:12.317Z",
|
||||
"toolUseId": "toolu_01YHaTDadr9x4vFfuus4vamb",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "cd /home/vercel-sandbox/gstack; ~/.claude/skills/gstack/bin/gstack-question-log '{\"skill\":\"plan-ceo-review\",\"question_id\":\"plan-ceo-review-mode\",\"question_summary\":\"Select review mode for deterministic skill-list ordering plan\",\"category\":\"routing\",\"door_type\":\"two-way\",\"options_count\":4,\"user_choice\":\"C\",\"recommended\":\"C\",\"session_id\":\"634003-1789014135-1db98f5a\"}' 2>/dev/null && echo \"question logged\" || echo \"question-log unavailable\"; ~/.claude/skills/gstack/bin/gstack-skill-end --skill \"plan-ceo-review\" --outcome success --session-id \"634003-1789014135-1db98f5a\" --tel-start \"1789014135\" --used-browse no --error-message \"\" --failed-step \"\" 2>/dev/null && echo \"telemetry ok\" || echo \"telemetry skipped\"",
|
||||
"description": "Log auto-decided mode question and run skill-end telemetry"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:24:14.288Z",
|
||||
"toolUseId": "toolu_01YHaTDadr9x4vFfuus4vamb",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:24:26.317Z",
|
||||
"toolUseId": "toolu_01EVSYPhAqVAdZhoeTZ9bU1r",
|
||||
"kind": "use",
|
||||
"name": "Write",
|
||||
"input": {
|
||||
"file_path": "/tmp/gstack-paid-shard-pNXtSA/tmp/gstack-hermetic-633854-8JWnVY/with-skills/.claude/plans/please-review-the-following-melodic-kernighan.md",
|
||||
"content": "# Plan: deterministic skill-list ordering (CEO review \u2014 mode decision only)\n\n## Context\n\nUsers compare skill listings in scripts and reviews. Today the ordering of\nregistered skill names depends on directory enumeration order and, where a\nsort exists, on JavaScript's default code-point sort (uppercase before\nlowercase). The draft plan makes the existing listing path sort registered\nskill names deterministically before rendering, keeping membership, aliases,\nmetadata and text/JSON output formats unchanged, with tests for mixed-case\nnames and differing enumeration order.\n\nThis invocation covered ONLY the /plan-ceo-review mode decision, at the\nuser's request. Office Hours, onboarding/setup prompts, the implementation\napproach decision (0C-bis), and the 11-section deep review are deferred to a\nlater invocation.\n\n## System audit (light, for mode grounding)\n\n- Branch `edinburgh-v1`, clean tree, far ahead of `main` (633 files); no stash.\n- No per-branch design doc, no CEO handoff note.\n- Skill enumeration paths found in the repo:\n - `test/helpers/skill-census.ts:63` \u2014 `readdirSync` with NO sort; registry\n is a `Set`, so insertion order follows enumeration order.\n - `lib/context-bill.ts:382` \u2014 `findSkillDirs` returns `out.sort()`\n (code-point sort on full paths; mixed case orders `Z` before `a`).\n - `lib/context-bill.ts:461` \u2014 `diffBills` sorts merged skill names with the\n default comparator (same mixed-case caveat).\n - `scripts/skill-check.ts:101` \u2014 `readdirSync(hostDir).sort()`.\n- Related tests: `test/skill-census.test.ts`, `test/context-bill.test.ts`,\n `test/catalog-budget.test.ts`.\n\n## Review mode decision\n\n**Mode: HOLD SCOPE** (auto-decided from the user's saved preference on\n`plan-ceo-review-mode`; change with /plan-tune).\n\nWhy HOLD SCOPE: this is a small correctness fix / refactor to an existing\npath, with explicit invariants (membership, aliases, metadata, formats\nunchanged). The context-dependent default for bug fixes and refactors is\nHOLD SCOPE. The value is in rigor: a single shared comparator, mixed-case\nand enumeration-order tests, and no silent behavior change in text or JSON\noutput.\n\n## Open before the substantive review\n\n1. 0C-bis implementation approaches (minimal vs shared comparator helper)\n still need an explicit approval.\n2. Confirm which listing path the draft means (\"the existing listing path\"):\n the census helper, the context-bill CLI, or both.\n3. Deep review per `sections/review-sections.md`, then the\n `## GSTACK REVIEW REPORT` section.\n"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:24:26.395Z",
|
||||
"toolUseId": "toolu_01EVSYPhAqVAdZhoeTZ9bU1r",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"timestamp": "2026-09-10T04:32:13.463Z",
|
||||
"toolUseId": "toolu_01TjWu1RBRGNXRWZ47Yro3ZT",
|
||||
"kind": "use",
|
||||
"name": "Skill",
|
||||
"input": {
|
||||
"skill": "plan-ceo-review"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"timestamp": "2026-09-10T04:32:14.680Z",
|
||||
"toolUseId": "toolu_01TjWu1RBRGNXRWZ47Yro3ZT",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"timestamp": "2026-09-10T04:32:29.695Z",
|
||||
"toolUseId": "toolu_01YWrQccueekQXWmbEqyiRfV",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "_SS=\"$HOME/.claude/skills/gstack/bin/gstack-skill-start\"\n[ -x \"$_SS\" ] || _SS=\".claude/skills/gstack/bin/gstack-skill-start\"\n\"$_SS\" --skill \"plan-ceo-review\" --model \"claude\" --parent-pid \"$PPID\" \\\n || echo \"SKILL_START: unavailable \u2014 stale install; run ./setup or /gstack-upgrade (preamble degraded, continue the user's task)\"",
|
||||
"description": "Run gstack skill-start preamble"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"timestamp": "2026-09-10T04:32:31.475Z",
|
||||
"toolUseId": "toolu_01YWrQccueekQXWmbEqyiRfV",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"timestamp": "2026-09-10T04:32:48.387Z",
|
||||
"toolUseId": "toolu_01G8mYVmSDWTrxTxuTBS8qbU",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "git remote get-url origin 2>/dev/null; echo \"---PR---\"; gh pr view --json baseRefName -q .baseRefName 2>&1 | head -2; echo \"---DEFAULT---\"; gh repo view --json defaultBranchRef -q .defaultBranchRef.name 2>&1 | head -2; echo \"---SYMREF---\"; git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||'; git rev-parse --verify origin/main >/dev/null 2>&1 && echo \"origin/main exists\"",
|
||||
"description": "Detect platform and base branch"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"timestamp": "2026-09-10T04:32:49.956Z",
|
||||
"toolUseId": "toolu_01Mn1fJWAVFxQKg4c9nDCTFz",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "git log --oneline -8; echo \"---STASH---\"; git stash list | head -3; echo \"---DIFF vs main---\"; git diff main --stat 2>/dev/null | tail -3",
|
||||
"description": "Quick system audit: log, stash, diff"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"timestamp": "2026-09-10T04:32:50.104Z",
|
||||
"toolUseId": "toolu_01G8mYVmSDWTrxTxuTBS8qbU",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"timestamp": "2026-09-10T04:32:50.377Z",
|
||||
"toolUseId": "toolu_01Mn1fJWAVFxQKg4c9nDCTFz",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"timestamp": "2026-09-10T04:32:51.506Z",
|
||||
"toolUseId": "toolu_01SA5VsDgqehzwJQMweeZNKi",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "grep -n -i \"mode\\|ceo\" \"$HOME/.claude/skills/gstack/scripts/question-registry.ts\" 2>/dev/null | head -20",
|
||||
"description": "Find question_id for CEO mode selection"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"timestamp": "2026-09-10T04:32:51.542Z",
|
||||
"toolUseId": "toolu_01SA5VsDgqehzwJQMweeZNKi",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"timestamp": "2026-09-10T04:32:52.860Z",
|
||||
"toolUseId": "toolu_01ATJDNJ62fCiTEdmPJ7qm4N",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "grep -rn -i \"skill.*list\\|listSkills\\|list-skills\\|skills list\" --include=*.ts --include=*.sh -l bin setup lib scripts 2>/dev/null | head -15",
|
||||
"description": "Locate the skill-listing code path the draft targets"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"timestamp": "2026-09-10T04:32:52.908Z",
|
||||
"toolUseId": "toolu_01ATJDNJ62fCiTEdmPJ7qm4N",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"timestamp": "2026-09-10T04:33:01.877Z",
|
||||
"toolUseId": "toolu_01Bwwgt4wwfrmyJDS7ZQMrpy",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "printf '%s' \"Review mode for deterministic skill-list ordering draft: expansion, selective expansion, hold scope, or reduction\" | \"$HOME/.claude/skills/gstack/bin/gstack-question-preference\" --check \"plan-ceo-review-mode\" --summary-stdin 2>&1",
|
||||
"description": "Check question-tuning preference for mode question"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"timestamp": "2026-09-10T04:33:03.484Z",
|
||||
"toolUseId": "toolu_01Bwwgt4wwfrmyJDS7ZQMrpy",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"timestamp": "2026-09-10T04:33:28.691Z",
|
||||
"toolUseId": "toolu_016K5grRiHEAyfUEUpX3dNxE",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "\"$HOME/.claude/skills/gstack/bin/gstack-question-log\" '{\"skill\":\"plan-ceo-review\",\"question_id\":\"plan-ceo-review-mode\",\"question_summary\":\"Review mode for deterministic skill-list ordering draft\",\"category\":\"routing\",\"door_type\":\"two-way\",\"options_count\":4,\"user_choice\":\"C\",\"recommended\":\"C\",\"session_id\":\"656632-1789014751-94b2b37a\"}' 2>&1 || true",
|
||||
"description": "Log auto-decided mode question"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"timestamp": "2026-09-10T04:33:30.094Z",
|
||||
"toolUseId": "toolu_016K5grRiHEAyfUEUpX3dNxE",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
}
|
||||
],
|
||||
"options": {
|
||||
"skillName": "plan-ceo-review",
|
||||
"sessionId": "a836788b-1676-4ac3-a39d-bb86b873bf03",
|
||||
"commandStartedAt": 1789014725874,
|
||||
"now": 1789015327103
|
||||
}
|
||||
}
|
||||
+291
@@ -0,0 +1,291 @@
|
||||
{
|
||||
"transcript": {
|
||||
"status": "ready",
|
||||
"calls": [],
|
||||
"assistantMessages": [
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"text": "I'll invoke the `/plan-ceo-review` skill against the draft plan.",
|
||||
"timestamp": "2026-09-10T04:21:58.556Z"
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"text": "Running the preamble first, then a light system audit so the mode question is grounded in the actual listing code.",
|
||||
"timestamp": "2026-09-10T04:22:10.706Z"
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"text": "Found the relevant code paths. Running the question-tuning check for the mode question and handling the onboarding markers, then I'll present the mode decision.",
|
||||
"timestamp": "2026-09-10T04:23:41.654Z"
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"text": "Heads-up from the preamble: unshipped work on this branch, so `/review` then `/ship` when you're ready. Also, gstack follows the **Boil the Ocean** principle: do the complete thing when AI makes the marginal cost near zero. Read more at https://garryslist.org/posts/boil-the-ocean if you'd like.\n\n**Review mode: HOLD SCOPE.**\n\nAuto-decided \"Select review mode\" \u2192 HOLD SCOPE (your saved preference on `plan-ceo-review-mode`). Change with /plan-tune.\n\nWhy this mode fits the draft:\n\n- **It is a correctness fix to an existing path, not a new capability.** Skill listings should not change order between machines or filesystems. The context default for bug fixes and refactors is HOLD SCOPE.\n- **The draft already states its invariants.** Membership, aliases, metadata and text/JSON formats stay unchanged. The review's job is to make those invariants bulletproof, not to widen them.\n- **The codebase confirms the problem is real.** The census helper enumerates skills with no sort at all. The context-bill code sorts with the default code-point comparator, so a mixed-case name like `Zeta` lands before `alpha`. Both are places the deep review should pin with tests.\n\nWhat I deliberately left open for the later invocation, at your request:\n\n1. **The implementation approach decision** (a shared case-insensitive comparator versus per-site sorts). The skill requires your explicit approval there before the deep review.\n2. **Which listing path the draft means.** The census helper, the context-bill CLI, or both. This changes the file list.\n3. **Onboarding prompts** (continuous checkpoint feature, cross-project learnings) and the Office Hours offer. Their markers are untouched, so they will fire again next healthy run.\n\nThe plan file at `.claude/plans/please-review-the-following-melodic-kernighan.md` records the mode, the audit findings with file and line references, and the three open items. I have not called ExitPlanMode since the review workflow is paused rather than complete.\n\nSTATUS: DONE. No durable learnings this session.",
|
||||
"timestamp": "2026-09-10T04:24:41.750Z"
|
||||
}
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:22:00.757Z",
|
||||
"toolUseId": "toolu_01D1z8pVbfkEeHZGgi6JdPZk",
|
||||
"kind": "use",
|
||||
"name": "Skill",
|
||||
"input": {
|
||||
"skill": "plan-ceo-review",
|
||||
"args": "Draft: deterministic skill-list ordering. Users compare skill listings in scripts and reviews. Make the existing listing path sort registered skill names deterministically before rendering them. Keep skill membership, aliases, metadata and text/JSON output formats unchanged. Cover mixed-case names and differing directory enumeration order with tests. Review-mode decision only for this invocation."
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:22:02.528Z",
|
||||
"toolUseId": "toolu_01D1z8pVbfkEeHZGgi6JdPZk",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:22:12.591Z",
|
||||
"toolUseId": "toolu_01B89LH3gWatoKLbFjkW1duv",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "_SS=\"$HOME/.claude/skills/gstack/bin/gstack-skill-start\"\n[ -x \"$_SS\" ] || _SS=\".claude/skills/gstack/bin/gstack-skill-start\"\n\"$_SS\" --skill \"plan-ceo-review\" --model \"claude\" --parent-pid \"$PPID\" \\\n || echo \"SKILL_START: unavailable \u2014 stale install; run ./setup or /gstack-upgrade (preamble degraded, continue the user's task)\"",
|
||||
"description": "Run gstack skill-start preamble"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:22:15.395Z",
|
||||
"toolUseId": "toolu_01B89LH3gWatoKLbFjkW1duv",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:22:42.272Z",
|
||||
"toolUseId": "toolu_011L1hSC8vSZLDVGpfiokh1h",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "git remote get-url origin 2>/dev/null; echo \"---LOG\"; git log --oneline -15; echo \"---STAT\"; git diff main --stat 2>/dev/null | tail -5; echo \"---STASH\"; git stash list | head; echo \"---DESIGN\"; SLUG=$(~/.claude/skills/gstack/browse/bin/remote-slug 2>/dev/null || basename \"$(git rev-parse --show-toplevel 2>/dev/null || pwd)\"); BRANCH=$(git rev-parse --abbrev-ref HEAD 2>/dev/null | tr '/' '-'); echo \"SLUG=$SLUG BRANCH=$BRANCH\"; ls -t ~/.gstack/projects/$SLUG/*-design-*.md 2>/dev/null | head -1; ls -t docs/designs/*.md 2>/dev/null | head -3; ls -t ~/.gstack/projects/$SLUG/*-$BRANCH-ceo-handoff-*.md 2>/dev/null | head -1 || echo NO_HANDOFF; echo \"---LEARN\"; ~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo unset; ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 5 2>/dev/null | head -20",
|
||||
"description": "System audit: remote, log, diff, stash, design doc, learnings"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:22:43.881Z",
|
||||
"toolUseId": "toolu_011L1hSC8vSZLDVGpfiokh1h",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:22:54.173Z",
|
||||
"toolUseId": "toolu_01Jpe19C6Qy7iLjhxsVVFZEM",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "cd /home/vercel-sandbox/gstack; ls bin | grep -i -E \"skill|list|catalog|census|route\" ; echo \"---GREP\"; grep -rl -i -E \"list.*skills|skills.*list|listSkills|skill-list|skills list\" --include=*.ts --include=*.sh --include=*.tmpl bin scripts lib _gstack-command setup 2>/dev/null | grep -v node_modules | head -30; echo \"---TODOS\"; grep -n -i -E \"sort|order|determin|listing\" TODOS.md | head -20",
|
||||
"description": "Locate skill listing code and related TODOs"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:22:54.300Z",
|
||||
"toolUseId": "toolu_01Jpe19C6Qy7iLjhxsVVFZEM",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:06.413Z",
|
||||
"toolUseId": "toolu_013RE2TjYQMdqe8nLecHC4vw",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "cd /home/vercel-sandbox/gstack; grep -n -E '\"(skill:check|skill:list|skills|list|catalog|context-bill)[^\"]*\":' package.json; echo \"---REGISTRY\"; grep -rn -i -E \"registered skill|registeredSkills|skill registry|SKILL_REGISTRY|listRegistered|registerSkill\" --include=*.ts --include=*.sh scripts lib bin test/helpers 2>/dev/null | grep -v node_modules | head -15; echo \"---READDIR\"; grep -rn -E \"readdirSync\\(\" scripts/gen-skill-docs.ts scripts/skill-check.ts scripts/skill-health.ts test/helpers/skill-census.ts lib/*.ts 2>/dev/null | head -20; echo \"---JSON\"; grep -rln -E \"\\-\\-json\" bin scripts --include=* 2>/dev/null | head -20",
|
||||
"description": "Find skill enumeration and JSON-listing code"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:06.508Z",
|
||||
"toolUseId": "toolu_013RE2TjYQMdqe8nLecHC4vw",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:13.375Z",
|
||||
"toolUseId": "toolu_013Ee9LJJQ8R1fR2sQFPGwkj",
|
||||
"kind": "use",
|
||||
"name": "Read",
|
||||
"input": {
|
||||
"file_path": "/home/vercel-sandbox/gstack/test/helpers/skill-census.ts",
|
||||
"offset": 40,
|
||||
"limit": 50
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:13.401Z",
|
||||
"toolUseId": "toolu_013Ee9LJJQ8R1fR2sQFPGwkj",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:14.737Z",
|
||||
"toolUseId": "toolu_01BU2xpwy4uMyx1Xp4quu9bj",
|
||||
"kind": "use",
|
||||
"name": "Read",
|
||||
"input": {
|
||||
"file_path": "/home/vercel-sandbox/gstack/lib/context-bill.ts",
|
||||
"offset": 195,
|
||||
"limit": 30
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:14.759Z",
|
||||
"toolUseId": "toolu_01BU2xpwy4uMyx1Xp4quu9bj",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:16.384Z",
|
||||
"toolUseId": "toolu_013aumciUHw2Bqjaaq27g1EV",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "cd /home/vercel-sandbox/gstack; grep -n -E \"json|text|format|\\.sort\\(|localeCompare\" lib/context-bill.ts | head -30; echo \"---BIN\"; grep -n -E \"json|sort|format\" bin/gstack-context-bill | head -15; echo \"---SKILLCHECK\"; grep -n -E \"json|\\.sort\\(\" scripts/skill-check.ts | head",
|
||||
"description": "Check output formats and sorting in listing candidates"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:16.450Z",
|
||||
"toolUseId": "toolu_013aumciUHw2Bqjaaq27g1EV",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:26.286Z",
|
||||
"toolUseId": "toolu_015mJBMXZtpHKA6hWxDwTo8j",
|
||||
"kind": "use",
|
||||
"name": "Read",
|
||||
"input": {
|
||||
"file_path": "/home/vercel-sandbox/gstack/lib/context-bill.ts",
|
||||
"offset": 335,
|
||||
"limit": 50
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:26.306Z",
|
||||
"toolUseId": "toolu_015mJBMXZtpHKA6hWxDwTo8j",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:28.306Z",
|
||||
"toolUseId": "toolu_01H7ZHzRW7U18u8zh3L6yKFH",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "cd /home/vercel-sandbox/gstack; grep -n -E \"json|JSON|renderText|function render|function format\" bin/gstack-context-bill.ts bin/gstack-context-bill 2>/dev/null | head -20; ls bin | grep context-bill; echo \"---TESTS\"; ls test | grep -i -E \"context-bill|census|catalog\"; echo \"---GBRAIN\"; grep -n -E \"\\.skills\\b|skills:\" lib/context-bill.ts | head -10",
|
||||
"description": "Find context-bill CLI output formats and tests"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:28.376Z",
|
||||
"toolUseId": "toolu_01H7ZHzRW7U18u8zh3L6yKFH",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:45.519Z",
|
||||
"toolUseId": "toolu_01BHQiS1mU8LZfxsWwFbGADs",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "cd /home/vercel-sandbox/gstack; grep -n -i -E \"plan-ceo-review.*(mode|scope)|ceo.*mode\" ~/.claude/skills/gstack/scripts/question-registry.ts | head -5; echo \"---CHECK\"; printf '%s' \"Select review mode (expansion/selective/hold/reduction) for deterministic skill-list ordering plan\" | ~/.claude/skills/gstack/bin/gstack-question-preference --check \"plan-ceo-review-mode-selection\" --summary-stdin 2>&1 | head -5; echo \"---MARKERS\"; touch \"/tmp/gstack-paid-shard-pNXtSA/tmp/gstack-auto-decide-w2UU3e/.completeness-intro-seen\" && echo \"lake-intro marker touched\"",
|
||||
"description": "Question-tuning check and lake-intro marker"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:47.061Z",
|
||||
"toolUseId": "toolu_01BHQiS1mU8LZfxsWwFbGADs",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:53.288Z",
|
||||
"toolUseId": "toolu_01Fz4MuCGi9tb8sPCq6SswEB",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "cd /home/vercel-sandbox/gstack; printf '%s' \"Select review mode (expansion/selective/hold/reduction) for deterministic skill-list ordering plan\" | ~/.claude/skills/gstack/bin/gstack-question-preference --check \"plan-ceo-review-mode\" --summary-stdin 2>&1 | head -3",
|
||||
"description": "Re-run tuning check with registered question id"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:23:54.770Z",
|
||||
"toolUseId": "toolu_01Fz4MuCGi9tb8sPCq6SswEB",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:24:12.317Z",
|
||||
"toolUseId": "toolu_01YHaTDadr9x4vFfuus4vamb",
|
||||
"kind": "use",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "cd /home/vercel-sandbox/gstack; ~/.claude/skills/gstack/bin/gstack-question-log '{\"skill\":\"plan-ceo-review\",\"question_id\":\"plan-ceo-review-mode\",\"question_summary\":\"Select review mode for deterministic skill-list ordering plan\",\"category\":\"routing\",\"door_type\":\"two-way\",\"options_count\":4,\"user_choice\":\"C\",\"recommended\":\"C\",\"session_id\":\"634003-1789014135-1db98f5a\"}' 2>/dev/null && echo \"question logged\" || echo \"question-log unavailable\"; ~/.claude/skills/gstack/bin/gstack-skill-end --skill \"plan-ceo-review\" --outcome success --session-id \"634003-1789014135-1db98f5a\" --tel-start \"1789014135\" --used-browse no --error-message \"\" --failed-step \"\" 2>/dev/null && echo \"telemetry ok\" || echo \"telemetry skipped\"",
|
||||
"description": "Log auto-decided mode question and run skill-end telemetry"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:24:14.288Z",
|
||||
"toolUseId": "toolu_01YHaTDadr9x4vFfuus4vamb",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:24:26.317Z",
|
||||
"toolUseId": "toolu_01EVSYPhAqVAdZhoeTZ9bU1r",
|
||||
"kind": "use",
|
||||
"name": "Write",
|
||||
"input": {
|
||||
"file_path": "/tmp/gstack-paid-shard-pNXtSA/tmp/gstack-hermetic-633854-8JWnVY/with-skills/.claude/plans/please-review-the-following-melodic-kernighan.md",
|
||||
"content": "# Plan: deterministic skill-list ordering (CEO review \u2014 mode decision only)\n\n## Context\n\nUsers compare skill listings in scripts and reviews. Today the ordering of\nregistered skill names depends on directory enumeration order and, where a\nsort exists, on JavaScript's default code-point sort (uppercase before\nlowercase). The draft plan makes the existing listing path sort registered\nskill names deterministically before rendering, keeping membership, aliases,\nmetadata and text/JSON output formats unchanged, with tests for mixed-case\nnames and differing enumeration order.\n\nThis invocation covered ONLY the /plan-ceo-review mode decision, at the\nuser's request. Office Hours, onboarding/setup prompts, the implementation\napproach decision (0C-bis), and the 11-section deep review are deferred to a\nlater invocation.\n\n## System audit (light, for mode grounding)\n\n- Branch `edinburgh-v1`, clean tree, far ahead of `main` (633 files); no stash.\n- No per-branch design doc, no CEO handoff note.\n- Skill enumeration paths found in the repo:\n - `test/helpers/skill-census.ts:63` \u2014 `readdirSync` with NO sort; registry\n is a `Set`, so insertion order follows enumeration order.\n - `lib/context-bill.ts:382` \u2014 `findSkillDirs` returns `out.sort()`\n (code-point sort on full paths; mixed case orders `Z` before `a`).\n - `lib/context-bill.ts:461` \u2014 `diffBills` sorts merged skill names with the\n default comparator (same mixed-case caveat).\n - `scripts/skill-check.ts:101` \u2014 `readdirSync(hostDir).sort()`.\n- Related tests: `test/skill-census.test.ts`, `test/context-bill.test.ts`,\n `test/catalog-budget.test.ts`.\n\n## Review mode decision\n\n**Mode: HOLD SCOPE** (auto-decided from the user's saved preference on\n`plan-ceo-review-mode`; change with /plan-tune).\n\nWhy HOLD SCOPE: this is a small correctness fix / refactor to an existing\npath, with explicit invariants (membership, aliases, metadata, formats\nunchanged). The context-dependent default for bug fixes and refactors is\nHOLD SCOPE. The value is in rigor: a single shared comparator, mixed-case\nand enumeration-order tests, and no silent behavior change in text or JSON\noutput.\n\n## Open before the substantive review\n\n1. 0C-bis implementation approaches (minimal vs shared comparator helper)\n still need an explicit approval.\n2. Confirm which listing path the draft means (\"the existing listing path\"):\n the census helper, the context-bill CLI, or both.\n3. Deep review per `sections/review-sections.md`, then the\n `## GSTACK REVIEW REPORT` section.\n"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"timestamp": "2026-09-10T04:24:26.395Z",
|
||||
"toolUseId": "toolu_01EVSYPhAqVAdZhoeTZ9bU1r",
|
||||
"kind": "result",
|
||||
"isError": false
|
||||
}
|
||||
],
|
||||
"options": {
|
||||
"skillName": "plan-ceo-review",
|
||||
"sessionId": "bd12c284-1989-47ed-9ffb-548b3d75a3ad",
|
||||
"commandStartedAt": 1789014113697,
|
||||
"now": 1789014714476
|
||||
}
|
||||
}
|
||||
+53
@@ -0,0 +1,53 @@
|
||||
{
|
||||
"sourceCommit": "12faead4636b97305348e25fc12258a56fcf6868",
|
||||
"provenance": {
|
||||
"path": ".context/ship-source-ai-delta-paid-20260910-v1/autoplan-edit-prefix-evidence-v1/public-tools.json",
|
||||
"sha256": "e49a7b02986840f0e76466076d54b21d001bfc8ad94213258f24c19bdf968b91",
|
||||
"projection": "Successful same-file use/result metadata plus exact current Edit request; unrelated events remain in context proof."
|
||||
},
|
||||
"cwd": "/tmp/gstack-paid-shard-Am4ci8/tmp/gstack-autoplan-chain-9599im",
|
||||
"ownedStateRoot": "/tmp/gstack-paid-shard-Am4ci8/tmp/gstack-hermetic-592891-MJaePo/skill-home-31EPP8/.gstack",
|
||||
"viewportCapturedAt": "2026-09-10T04:27:38.073Z",
|
||||
"viewport": " +r this plan. \n 80 +- Latency remedies, in order: if endpoint p95 > 300 ms for two consecutive stages, first add the per-me\n +mber predicate cache (a performance fix, exempt from the feature gate below); if still over, switch to \n +alternative B' (three parallel calls). The 600 ms guardrail is separate and triggers rollback, not reme\n +diation. \n 81 +- Gate: no new dashboard features (including the separately planned dark mode and personalization) unti\n +l the cohort metric has been read against control at the 25% stage. Performance remediation is exempt f\n +rom this gate. \n 82 +- Refresh semantics: SUCCESS and EMPTY panels enter REFRESHING (content stays visible); an ERROR panel \n +returns to LOADING on Refresh or Retry. \n 83 + \n 84 +## Spec review record \n 85 +Three adversarial review rounds (scores 7/10 \u2192 8/10 \u2192 8/10; 21 issues raised, 21 fixed in-document). Th\n +e loop hit its 3-iteration cap with the round-3 issues fixed inline above; no unresolved reviewer conce\n +rns remain. \n\n\u25cf Update(~/.gstack/projects/gstack-autoplan-chain-9599im/ceo-plans/2026-09-10-user-dashboard.md)\n\n\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\n Edit file\n \u2026-592891-MJaePo/skill-home-31EPP8/.gstack/projects/gstack-autoplan-chain-9599im/ceo-plans/2026-09-10-user-dashboard.md\n\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\n 55 - Client analytics events: dashboard_viewed, dashboard_panel_state (ERROR/EMPTY only), dashboard_quick_action_click\n ed, dashboard_mark_all_read, dashboard_view_all_clicked, dashboard_refresh_clicked\n 56 \n 57 ## Deferred to TODOS.md\n 58 -All deferrals wait until the cohort metric has been read against control (see Gate below), then: \n 58 +Feature deferrals wait until the cohort metric has been read against control (see Gate below); the predicate cache \n +is a performance remedy and is exempt: \n 59 - Unread badge in global nav (P2)\n 60 - Smart-redirect experiment cohort for single-action members (P2)\n 61 - Real-time notification/activity updates via SSE (P3, infra decision)\n\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\u254c\n Do you want to make this edit to 2Line truncated
|
||||
"before": "---\nstatus: ACTIVE\n---\n# CEO Plan: User Dashboard Page\nGenerated by /plan-ceo-review (via /autoplan) on 2026-09-10\nBranch: main | Mode: SELECTIVE EXPANSION\nRepo: gstack-autoplan-chain-9599im (fixture; no remote)\n\n## Baseline scope (unchanged from the source plan)\n- `/dashboard` page rendered after login, with three panels: QuickActions, NotificationsPanel, ActivityFeed\n- One aggregate endpoint `GET /api/dashboard` returning a top-level `fetchedAt` (server time of the response) plus one result per panel (`{ ok: true, data } | { ok: false, error }`), so one panel failing never blanks the page\n- \"Mark all as read\" behind a confirm dialog built on the existing dialog primitive\n- A toast primitive (new, built as a shared app-level component, success feedback only)\n- Canonical panel states, used everywhere in this record: LOADING (skeleton), EMPTY, ERROR, SUCCESS, REFRESHING (a SUCCESS or EMPTY panel re-fetching while its previous content stays visible). A shared `PanelFrame` component owns the chrome for all five; each panel supplies only its SUCCESS rendering.\n- Tailwind tokens; mobile-first sm/md/lg\n- Out of scope, from the source plan: dark mode, personalization (separate plans)\n\n## Vision\n\n### North star (12-month direction, NOT this release)\nThe dashboard that already knows what you were doing. The hero is the one eligible\n\"resume\" action, huge and one Tab away. Notifications are ranked by urgency and can be\ncleared per item. Activity streams in live. Nothing the member needs after login is\nmore than one click away, and nothing they don't need takes up space.\n\n### 10x within this release's constraints\nThe source plan forbids new mutation APIs and new infrastructure, so per-item read and\nlive streaming are deferred (E9 below, and the per-item read API in the deferred list).\nThe 10x lever available now is hierarchy: QuickActions first, Notifications second,\nActivity third, at every breakpoint. The per-panel result envelope and the shared\n`PanelFrame` are the widget contract that lets every later panel plug in without\nre-deciding its states.\n\n## Scope Decisions\n\n| # | Proposal | Effort | Decision | Reasoning |\n|---|----------|--------|----------|-----------|\n| E1 | \"Updated Xm ago\" + Refresh in page header | S | ACCEPTED | Uses the top-level `fetchedAt` of the aggregate response; Refresh puts panels into REFRESHING; makes staleness visible |\n| E2 | Notification rows deep-link to their target | S | ACCEPTED | Route targets exist per contracts; link only. The row stays unread after the member returns, until \"Mark all as read\" (intentional: no per-item read API in this release) |\n| E3 | `<time datetime>` relative + absolute-on-hover timestamps | S | ACCEPTED | Accessibility policy; trivial |\n| E4 | \"View all\" links per panel into existing full pages | S | ACCEPTED | Existing pages own older-page navigation |\n| E5 | Optimistic mark-all-read with rollback | S | ACCEPTED | Idempotent snapshot-bounded API makes it safe; on failure the unread markers are restored and an error message renders inline inside the notifications panel (persistent, screen-reader visible); the toast is used for success only |\n| E6 | Keyboard shortcut to first quick action | S | DEFERRED | Single-key shortcuts need a11y design first |\n| E7 | Unread badge in global nav | M | DEFERRED | Outside blast radius (global nav) |\n| E8 | Smart post-login redirect experiment cohort | M | DEFERRED | Run after the cohort metric is read |\n| E9 | Real-time updates (SSE) | L | DEFERRED | New infrastructure |\n| E10 | Six named client analytics events | S | ACCEPTED | The source plan's contracts require \"exposure and interaction instrumentation\" in general; this decision names the concrete events (listed below) |\n\n## Accepted Scope (added to this plan)\n- Page header with \"Updated Xm ago\" (from the aggregate response's top-level `fetchedAt`) and a Refresh control that moves panels to REFRESHING without clearing content\n- Notification rows link to their target route when one is present; the row remains unread until \"Mark all as read\"\n- `<time datetime>` timestamps, relative text with absolute on hover\n- \"View all activity\" and \"View all notifications\" links into the existing pages\n- Optimistic mark-all-read with full rollback; failure message inline in the panel, success via toast\n- Client analytics events: dashboard_viewed, dashboard_panel_state (ERROR/EMPTY only), dashboard_quick_action_clicked, dashboard_mark_all_read, dashboard_view_all_clicked, dashboard_refresh_clicked\n\n## Deferred to TODOS.md\nAll deferrals wait until the cohort metric has been read against control (see Gate below), then:\n- Unread badge in global nav (P2)\n- Smart-redirect experiment cohort for single-action members (P2)\n- Real-time notification/activity updates via SSE (P3, infra decision)\n- Keyboard shortcut to first quick action (P3, after a11y review)\n- QuickActions predicate cache, 30s per memLine truncated
|
||||
"events": [
|
||||
{
|
||||
"sessionId": "06788c5a-af8b-4a56-a97e-0ed1efd56f81",
|
||||
"timestamp": "2026-09-10T04:23:46.290Z",
|
||||
"kind": "use",
|
||||
"toolUseId": "toolu_014fVm5J1Kj6Qqjn9qXWxec1",
|
||||
"name": "Edit",
|
||||
"input": {
|
||||
"file_path": "/tmp/gstack-paid-shard-Am4ci8/tmp/gstack-hermetic-592891-MJaePo/skill-home-31EPP8/.gstack/projects/gstack-autoplan-chain-9599im/ceo-plans/2026-09-10-user-dashboard.md"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "06788c5a-af8b-4a56-a97e-0ed1efd56f81",
|
||||
"timestamp": "2026-09-10T04:23:48.545Z",
|
||||
"toolUseId": "toolu_018TVtFH38vSPzawATsGhrU3",
|
||||
"kind": "use",
|
||||
"name": "Edit",
|
||||
"input": {
|
||||
"replace_all": false,
|
||||
"file_path": "/tmp/gstack-paid-shard-Am4ci8/tmp/gstack-hermetic-592891-MJaePo/skill-home-31EPP8/.gstack/projects/gstack-autoplan-chain-9599im/ceo-plans/2026-09-10-user-dashboard.md",
|
||||
"old_string": "All deferrals wait until the cohort metric has been read against control (see Gate below), then:",
|
||||
"new_string": "Feature deferrals wait until the cohort metric has been read against control (see Gate below); the predicate cache is a performance remedy and is exempt:"
|
||||
}
|
||||
},
|
||||
{
|
||||
"sessionId": "06788c5a-af8b-4a56-a97e-0ed1efd56f81",
|
||||
"timestamp": "2026-09-10T04:23:50.325Z",
|
||||
"kind": "result",
|
||||
"toolUseId": "toolu_014fVm5J1Kj6Qqjn9qXWxec1",
|
||||
"isError": false
|
||||
}
|
||||
],
|
||||
"pending": {
|
||||
"source": "pre_tool_use",
|
||||
"sessionId": "06788c5a-af8b-4a56-a97e-0ed1efd56f81",
|
||||
"toolUseId": "toolu_018TVtFH38vSPzawATsGhrU3",
|
||||
"tool": "Edit",
|
||||
"file": "/tmp/gstack-paid-shard-Am4ci8/tmp/gstack-hermetic-592891-MJaePo/skill-home-31EPP8/.gstack/projects/gstack-autoplan-chain-9599im/ceo-plans/2026-09-10-user-dashboard.md",
|
||||
"timestamp": "2026-09-10T04:23:50.390Z"
|
||||
}
|
||||
}
|
||||
+264
@@ -0,0 +1,264 @@
|
||||
{
|
||||
"sourceCommit": "12faead4636b97305348e25fc12258a56fcf6868",
|
||||
"sourceProjectionSHA256": "e07c4689f60afe88b7695e085c97fcc834a737777928a3aeddc4e0779cfd9e91",
|
||||
"calls": [
|
||||
{
|
||||
"sessionId": "686b732f-ce5b-47d9-bd3c-3d59e0fcf536",
|
||||
"toolUseId": "toolu_01V5tht3FfJYqPt7SAJ4LZzp",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D0 \u2014 Add gstack skill routing rules to CLAUDE.md?\nProject/branch/task: plan-count-W42Czh on main, reviewing the Stripe payment webhook plan.\nELI10: gstack works best when your project's CLAUDE.md includes skill routing rules, so that requests like \"review this diff\" automatically reach the right skill. This is a one-time setup prompt per project. Note: plan mode is active, so if you pick A the CLAUDE.md edit and commit happen after the review, once plan mode exits.\nStakes if we pick wrong: Low either way; skills still work when invoked manually.\nRecommendation: A because routing rules make skill invocation automatic with no downside.\nNote: options differ in kind, not coverage \u2014 no completeness score.\nNet: convenience of auto-routing versus keeping CLAUDE.md untouched.",
|
||||
"header": "Routing",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "Add routing rules (recommended)",
|
||||
"description": "\u2705 Requests auto-route to the right gstack skill without typing slash commands. \u2705 Teammates get the same routing since CLAUDE.md is committed. \u274c Adds a section to CLAUDE.md and a commit after plan mode exits."
|
||||
},
|
||||
{
|
||||
"label": "No thanks, manual",
|
||||
"description": "\u2705 CLAUDE.md stays exactly as it is in this fixture repo. \u2705 Skills remain fully usable via explicit /skill-name invocation. \u274c You must remember which skill to call for each task."
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answers": [
|
||||
"Add routing rules (recommended)"
|
||||
],
|
||||
"answeredAt": "2026-09-10T04:06:48.672Z",
|
||||
"expectedFirstReview": false
|
||||
},
|
||||
{
|
||||
"sessionId": "686b732f-ce5b-47d9-bd3c-3d59e0fcf536",
|
||||
"toolUseId": "toolu_01URnAwJxvsGLw5TeD8KfGby",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D1 \u2014 Enable cross-project learnings search?\nProject/branch/task: plan-count-W42Czh on main, Stripe webhook plan review.\nELI10: gstack can search learnings saved from your other projects on this machine to spot patterns that apply here. Everything stays local; no data leaves the machine. Good for solo developers; skip if you work across client codebases where cross-contamination matters.\nStakes if we pick wrong: Low. Either way, this project's own learnings still get searched.\nRecommendation: A because local-only pattern reuse compounds review quality with no privacy cost for a single developer.\nNote: options differ in kind, not coverage \u2014 no completeness score.\nNet: broader pattern recall versus strict per-project isolation.",
|
||||
"header": "Learnings",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "Enable cross-project (recommended)",
|
||||
"description": "\u2705 Past learnings from any local project inform this and future reviews. \u2705 Stays entirely on this machine, nothing is uploaded. \u274c Learnings from unrelated client codebases could surface where they do not apply."
|
||||
},
|
||||
{
|
||||
"label": "Project-scoped only",
|
||||
"description": "\u2705 Strict isolation; only this repo's learnings are ever consulted. \u2705 Safe default for consultants juggling multiple client codebases. \u274c Loses cross-pollination of pitfalls already solved elsewhere."
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answers": [
|
||||
"Enable cross-project (recommended)"
|
||||
],
|
||||
"answeredAt": "2026-09-10T04:07:08.751Z",
|
||||
"expectedFirstReview": false
|
||||
},
|
||||
{
|
||||
"sessionId": "686b732f-ce5b-47d9-bd3c-3d59e0fcf536",
|
||||
"toolUseId": "toolu_01MNF5u8T857AeX1on7THBqA",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D2 \u2014 Which implementation structure should the handler use?\nProject/branch/task: main, Stripe payment webhook plan (HOLD SCOPE review).\nELI10: The plan adds a new StripePaymentWebhookHandler class but says it bypasses the existing WebhookDispatcher for a \"clean namespace.\" The plan also says the handler runs inside the existing signature, dedup, and lock guards. If those guards live in or behind the dispatcher, bypassing it silently drops them. The structural question is where the new class plugs in.\nStakes if we pick wrong: A second routing path can lose dedup or locking on real payments, or drift when the guards change; nobody notices until a duplicate or unlocked update lands.\nRecommendation: B because it achieves the dedicated-class goal while reusing the existing routing and guards by construction, with the smallest correct diff and no speculative service layer.\nCompleteness: A=4/10, B=8/10, C=9/10\nNet: literal plan text with a parallel entry point, versus one dispatcher-routed class, versus that plus a service split that pays off only once a second payment event exists.",
|
||||
"header": "Structure",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "B) Register in WebhookDispatcher (recommended)",
|
||||
"description": "Completeness 8/10. (human: ~2h / CC: ~15min) \u2705 Guard chain (signature, dedup, per-user lock, ownership) wraps the handler automatically. \u2705 One routing table to read; handler testable through the dispatcher's existing test harness. \u274c Handler owns lookup/update/notify, so unit tests need a DB fixture or repository double."
|
||||
},
|
||||
{
|
||||
"label": "A) Standalone handler, as written",
|
||||
"description": "Completeness 4/10. (human: ~1h / CC: ~10min) \u2705 Fewest files touched; matches the current plan text literally. \u2705 No change to WebhookDispatcher registration. \u274c Two routing paths for Stripe events; must independently prove every guard still wraps it and re-prove on every guard change."
|
||||
},
|
||||
{
|
||||
"label": "C) Dispatcher + PaymentSuccessService",
|
||||
"description": "Completeness 9/10. (human: ~4h / CC: ~25min) \u2705 Domain logic unit-testable without HTTP or the dispatcher. \u2705 Ready-made seam for a second payment event type later. \u274c Second new class for one event type today, a premature abstraction until a second consumer exists."
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answers": [
|
||||
"B) Register in WebhookDispatcher (recommended)"
|
||||
],
|
||||
"answeredAt": "2026-09-10T04:09:22.850Z",
|
||||
"expectedFirstReview": false
|
||||
},
|
||||
{
|
||||
"sessionId": "686b732f-ce5b-47d9-bd3c-3d59e0fcf536",
|
||||
"toolUseId": "toolu_01SUpnsqV3dyC5GytaLkqBgu",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D3 \u2014 What is the per-order fetch in the handler for?\nProject/branch/task: main, Stripe payment webhook plan (HOLD SCOPE).\nELI10: The Performance section says each webhook looks up the user, then fetches each order in a loop, but nothing in the plan says what the orders are used for. The implementer will have to guess, and the guess decides whether this is a read for the email, a write that must sit inside the payment transaction, or dead work. I cannot see your domain, so this is your call.\nStakes if we pick wrong: Orders that should be marked paid stay unpaid, or the handler does N extra queries per webhook for nothing and slows toward Stripe's 10-second timeout.\nRecommendation: A because the notification email is the only other consumer of user data in the plan, and a read-only batch is the least risky interpretation; correct me if orders must change state.\nNote: options differ in kind, not coverage \u2014 no completeness score.\nNet: read-for-email versus write-in-transaction versus no consumer at all.",
|
||||
"header": "Orders loop",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "A) Orders feed the email (recommended)",
|
||||
"description": "\u2705 Read-only; one batched SELECT by user_id, no transactional coupling with the payment update. \u2705 Failure of the read can share the notification rescue path without affecting payment state. \u274c If orders also need a status change, that write is silently missing."
|
||||
},
|
||||
{
|
||||
"label": "B) Orders must be marked paid too",
|
||||
"description": "\u2705 Order state stays consistent with the user payment status in one transaction. \u2705 Single batched UPDATE ... WHERE user_id = ? AND payment_intent_id = ? under the existing lock. \u274c Widens the transaction and the idempotency surface; must define which orders belong to this PaymentIntent."
|
||||
},
|
||||
{
|
||||
"label": "C) No consumer, drop the loop",
|
||||
"description": "\u2705 Removes N queries per webhook and the whole N+1 finding. \u2705 Smallest handler; nothing to test for orders. \u274c If a downstream feature relied on this fetch, it disappears without a trace."
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answers": [
|
||||
"A) Orders feed the email (recommended)"
|
||||
],
|
||||
"answeredAt": "2026-09-10T04:11:20.976Z",
|
||||
"expectedFirstReview": false
|
||||
},
|
||||
{
|
||||
"sessionId": "686b732f-ce5b-47d9-bd3c-3d59e0fcf536",
|
||||
"toolUseId": "toolu_01RdWLfMent2nPdCr4JMNqvc",
|
||||
"questions": [
|
||||
{
|
||||
"question": "1A \u2014 Should the notification email be sent only after the user update commits?\nProject/branch/task: main, Stripe payment webhook plan (HOLD SCOPE), Section 1 Architecture.\nELI10: The plan says the user update and the email both happen inline, but not in which order relative to the database commit. If the email goes out while the transaction is still open and the commit then fails, the customer gets a \"you're paid\" email for a payment we did not record, and Stripe's retry sends a second one. Sequencing the send after the commit means the email only ever describes committed state.\nStakes if we pick wrong: Phantom confirmation emails and duplicate emails on retry, discovered by customers before on-call.\nRecommendation: A because \"explicit over clever\" applies: make the order commit, then read orders, then send, and assert that order in a test.\nCompleteness: A=10/10, B=3/10\nNet: a fixed, tested ordering versus leaving the ordering to the implementer.",
|
||||
"header": "Email order",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "A) Commit first, then email (recommended)",
|
||||
"description": "Completeness 10/10. (human: ~30min / CC: ~5min) \u2705 Email content always reflects committed payment state; a failed commit sends nothing. \u2705 Test asserts the mail client is not invoked when the update raises before commit. \u274c Adds one explicit ordering constraint the handler comment must document."
|
||||
},
|
||||
{
|
||||
"label": "B) Leave ordering unspecified",
|
||||
"description": "Completeness 3/10. (human: 0 / CC: 0) \u2705 No change to the plan text. \u2705 Implementer keeps freedom to structure the method. \u274c A phantom confirmation email on commit failure becomes possible and untested."
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answers": [
|
||||
"A) Commit first, then email (recommended)"
|
||||
],
|
||||
"answeredAt": "2026-09-10T04:12:08.732Z",
|
||||
"expectedFirstReview": true
|
||||
},
|
||||
{
|
||||
"sessionId": "686b732f-ce5b-47d9-bd3c-3d59e0fcf536",
|
||||
"toolUseId": "toolu_016DTtpSCTFdSYzdo71ajPpD",
|
||||
"questions": [
|
||||
{
|
||||
"question": "2A \u2014 How should the handler treat a failure on the email leg after the payment is committed?\nProject/branch/task: main, Stripe payment webhook plan (HOLD SCOPE), Section 2 Error map.\nELI10: Today the plan has no error handling on the email. Any mail provider hiccup becomes a 500, and Stripe redelivers the whole payment event for up to 72 hours. The payment is already saved, so each redelivery is a blind replay that your own runbook forbids, plus another email attempt. The mail client already reports failures to a dashboard and alert, and the runbook already retries only the notification. The handler just needs to let that machinery work instead of fighting it.\nStakes if we pick wrong: Payment replays on every mail blip, alert storms, duplicate emails, and on-call unable to tell a failed payment from a failed email.\nRecommendation: A because it names each exception, keeps the failure visible through the existing alert and traces, and matches the runbook's \"retry only the notification\" rule.\nCompleteness: A=10/10, B=6/10, C=2/10\nNet: named rescue with structured warning versus retry-then-rescue in the request path versus leaving the 500.",
|
||||
"header": "Email rescue",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "A) Rescue named mail errors, warn, return 200 (recommended)",
|
||||
"description": "Completeness 10/10. (human: ~1h / CC: ~10min) \u2705 Rescues MailDeliveryError, MailTimeoutError, MailRateLimited, MailRenderError and the post-commit orders-read error by name; logs one structured warning with event_id, user_id, payment_intent_id, exception class. \u2705 Event completes; failure visible via mail failure-rate alert and outcome trace; test asserts user paid + 200 + warning when mail raises. \u274c Notification retry stays manual through the existing runbook procedure."
|
||||
},
|
||||
{
|
||||
"label": "B) Retry email once inline, then rescue",
|
||||
"description": "Completeness 6/10. (human: ~1.5h / CC: ~15min) \u2705 Transient provider blips self-heal without on-call. \u2705 Same named rescue and warning as A on the second failure. \u274c Adds mail latency twice inside Stripe's ~10s response budget and duplicates the mail client's own retry semantics if it has them."
|
||||
},
|
||||
{
|
||||
"label": "C) Keep the plan: no handling, propagate",
|
||||
"description": "Completeness 2/10. (human: 0 / CC: 0) \u2705 No new code in the handler. \u2705 Stripe retries do eventually resend the email. \u274c Every retry replays a committed payment, violating the runbook; alert storms; duplicate emails."
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answers": [
|
||||
"A) Rescue named mail errors, warn, return 200 (recommended)"
|
||||
],
|
||||
"answeredAt": "2026-09-10T04:12:56.538Z",
|
||||
"expectedFirstReview": true
|
||||
},
|
||||
{
|
||||
"sessionId": "686b732f-ce5b-47d9-bd3c-3d59e0fcf536",
|
||||
"toolUseId": "toolu_013TjkzQXpnKEStB6Sp4N7Wk",
|
||||
"questions": [
|
||||
{
|
||||
"question": "3A \u2014 How should the handler look up the user from params.userId?\nProject/branch/task: main, Stripe payment webhook plan (HOLD SCOPE), Section 3 Security.\nELI10: The plan pastes the user ID string straight into a SQL fragment. Your own contract says that string arrives unsanitized, may contain punctuation and Unicode, and that a valid Stripe signature does not make it SQL-safe. A customer whose ID contains an apostrophe breaks the query, gets a 500, and Stripe retries the same broken event for 72 hours while alerts fire. A hostile value in PaymentIntent metadata does worse. Bound parameters make the string data, never code.\nStakes if we pick wrong: Arbitrary SQL against the users table in the worst case, and a guaranteed poison-event alert loop for ordinary IDs in the common case.\nRecommendation: A because parameterized queries through the existing DB client are the tried-and-true fix, cost a few lines, and the follow-on queries keyed by the internal primary key close the orders-scoping threat too.\nCompleteness: A=10/10, B=5/10, C=1/10\nNet: bound parameter plus internal-key follow-ons versus escaping the string versus the plan as written.",
|
||||
"header": "SQL lookup",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "A) Bound parameter via existing DB client (recommended)",
|
||||
"description": "Completeness 10/10. (human: ~1h / CC: ~10min) \u2705 userId is passed as a bound value; update and orders read use the looked-up internal primary key. \u2705 Tests cover O'Brien, SQL-metacharacter, Unicode, 255-char, and missing IDs with zero DB errors; a DB error here still propagates to 500 as retained. \u274c Requires the DB client to expose a parameterized lookup helper, or adding one small one."
|
||||
},
|
||||
{
|
||||
"label": "B) Escape/quote the string before interpolating",
|
||||
"description": "Completeness 5/10. (human: ~30min / CC: ~5min) \u2705 Blocks the obvious apostrophe breakage. \u2705 Keeps the raw-fragment shape the plan describes. \u274c Escaping is driver- and encoding-specific; Unicode and multibyte edge cases have a history of bypasses, and it still deviates from the existing client pattern."
|
||||
},
|
||||
{
|
||||
"label": "C) Keep raw SQL fragment as written",
|
||||
"description": "Completeness 1/10. (human: 0 / CC: 0) \u2705 No change to the plan text. \u2705 Nothing new to review. \u274c Injection vector plus a deterministic 72-hour poison-event loop for any ID containing a quote."
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answers": [
|
||||
"A) Bound parameter via existing DB client (recommended)"
|
||||
],
|
||||
"answeredAt": "2026-09-10T04:13:38.302Z",
|
||||
"expectedFirstReview": true
|
||||
},
|
||||
{
|
||||
"sessionId": "686b732f-ce5b-47d9-bd3c-3d59e0fcf536",
|
||||
"toolUseId": "toolu_018xNjhW6LMGGnhTSwrnzTbr",
|
||||
"questions": [
|
||||
{
|
||||
"question": "4A \u2014 Should the handler suppress the email when the user row already carries this PaymentIntent?\nProject/branch/task: main, Stripe payment webhook plan (HOLD SCOPE), Section 4 async ordering.\nELI10: The dedup guard only skips deliveries whose completion marker was written. If the email goes out and then the marker write fails, Stripe retries, the guard sees no marker, and the handler runs again. The user update is idempotent so the row is fine, but the customer gets a second \"you're paid\" email. The lookup already returns the row, so the handler can see that this PaymentIntent was recorded before and skip the send, using data that already exists.\nStakes if we pick wrong: Duplicate confirmation emails on every bookkeeping hiccup, and support tickets asking whether they were charged twice.\nRecommendation: A because it closes the only remaining duplicate-email schedule with zero new storage, and logs the suppression so on-call can see it happened.\nCompleteness: A=10/10, B=7/10, C=2/10\nNet: reuse the row as the sent-signal versus a mail-provider idempotency key versus accepting duplicates.",
|
||||
"header": "Dup email",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "A) Skip email if row already has this PI (recommended)",
|
||||
"description": "Completeness 10/10. (human: ~45min / CC: ~10min) \u2705 Lookup result already exposes payment_status and payment_intent_id; no new table or marker. \u2705 Structured info log on suppression with event_id and payment_intent_id; test asserts exactly one mail call across two runs with the marker absent. \u274c A row that was already paid by the same PI before this handler ever ran also suppresses the email, which is the correct behavior but worth a comment."
|
||||
},
|
||||
{
|
||||
"label": "B) Pass payment_intent_id as mail idempotency key",
|
||||
"description": "Completeness 7/10. (human: ~1h / CC: ~10min) \u2705 Provider-side dedup even if two handler runs both attempt the send. \u2705 No handler branching on row state. \u274c Depends on the shared mail client and provider supporting idempotency keys, which the plan does not establish; still counts as a delivery attempt in the failure-rate metric."
|
||||
},
|
||||
{
|
||||
"label": "C) Accept occasional duplicate emails",
|
||||
"description": "Completeness 2/10. (human: 0 / CC: 0) \u2705 No new code. \u2705 Window is narrow (marker write must fail right after a successful send). \u274c A stated correctness gap left unhandled and untested; duplicates surface as customer confusion."
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answers": [
|
||||
"A) Skip email if row already has this PI (recommended)"
|
||||
],
|
||||
"answeredAt": "2026-09-10T04:14:30.132Z",
|
||||
"expectedFirstReview": true
|
||||
},
|
||||
{
|
||||
"sessionId": "686b732f-ce5b-47d9-bd3c-3d59e0fcf536",
|
||||
"toolUseId": "toolu_01EWhQ5zbtnibLPsdNMpSM9B",
|
||||
"questions": [
|
||||
{
|
||||
"question": "6A \u2014 Should automated tests for the handler land in this branch, replacing \"None planned\"?\nProject/branch/task: main, Stripe payment webhook plan (HOLD SCOPE), Section 6 Tests.\nELI10: The plan says no tests, the existing integration suite will catch regressions. That suite has never heard of this handler, so it cannot fail when the handler is wrong. The manual staging replay checks one happy path by hand. Every fix agreed so far (commit before email, named mail rescue, bound-parameter lookup, duplicate-email suppression) is a behavior that only an automated assertion keeps true after the next refactor.\nStakes if we pick wrong: The SQL, email, and duplicate fixes silently regress; the first signal is a customer or an alert storm, not a red build.\nRecommendation: A because well-tested code is your stated non-negotiable, the suite is ~15 minutes of CC time, and the staging replay stays as the manual gate it already is.\nCompleteness: A=10/10, B=6/10, C=1/10\nNet: full unit plus integration matrix now, versus happy-path integration only, versus the plan as written.",
|
||||
"header": "Tests",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "A) Full matrix in this branch (recommended)",
|
||||
"description": "Completeness 10/10. (human: ~1 day / CC: ~15min) \u2705 Unit tests with a mail double for every named rescue and the ordering assertion; DB-backed integration tests for routing, SQL-metacharacter and Unicode IDs, unknown user, zero orders, one-query orders read, duplicate suppression, and the two-delivery lock schedule. \u2705 Red build is the first signal for any regression of 1A/2A/3A/4A. \u274c Concurrency test needs controlled pause/release points to avoid flakiness."
|
||||
},
|
||||
{
|
||||
"label": "B) Happy-path integration tests only",
|
||||
"description": "Completeness 6/10. (human: ~2h / CC: ~5min) \u2705 Proves routing, lookup, update, and one email end to end. \u2705 Small, fast, no doubles. \u274c Leaves the SQL-metacharacter, mail-error, ordering, and duplicate cases unasserted; those are exactly the bugs this review found."
|
||||
},
|
||||
{
|
||||
"label": "C) Keep \"None planned\"",
|
||||
"description": "Completeness 1/10. (human: 0 / CC: 0) \u2705 Nothing to write or maintain. \u2705 Manual staging replay still runs before broad enablement. \u274c Contradicts the stated engineering preference; regressions in a payment path reach production first."
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answers": [
|
||||
"A) Full matrix in this branch (recommended)"
|
||||
],
|
||||
"answeredAt": "2026-09-10T04:15:26.080Z",
|
||||
"expectedFirstReview": true
|
||||
}
|
||||
]
|
||||
}
|
||||
+441
@@ -0,0 +1,441 @@
|
||||
{
|
||||
"sourceCommit": "12faead4636b97305348e25fc12258a56fcf6868",
|
||||
"sourceObservation": {
|
||||
"path": "/home/vercel-sandbox/gstack/.context/ship-source-ai-delta-paid-20260910-v1/design-first-finding-evidence-v1/observation.json",
|
||||
"sha256": "2ad38e3c492bdb15907b4c6e59c76d91b2bf26936b7496688f0a5affae7f6eed",
|
||||
"bytes": 86983
|
||||
},
|
||||
"capture": {
|
||||
"skill": "plan-design-review",
|
||||
"runId": "ship-source-ai-delta-paid-20260910-v1-3",
|
||||
"cwd": "/tmp/gstack-paid-shard-UTP2FK/tmp/gstack-plan-count-XQbt40",
|
||||
"claudeConfigDir": "/tmp/gstack-paid-shard-UTP2FK/tmp/gstack-hermetic-593109-2sknO2/with-skills/.claude",
|
||||
"at": "2026-09-10T04:16:41.573Z"
|
||||
},
|
||||
"calls": [
|
||||
{
|
||||
"ordinal": 1,
|
||||
"fingerprint": {
|
||||
"signature": "ba2c03f0-6d75-4f7e-8140-d3fd03cfdbcf:toolu_01DRVrppFnbqJYBSwvwCSGvA",
|
||||
"promptSnippet": "Routing D1 \u2014 Add gstack skill routing rules to this project's CLAUDE.md? Project/branch/task: gstack-plan-count-XQbt40 on main, one-time gstack onboarding before the PLAN.md design review. ELI10: gstack works best when your project's CLAUDE",
|
||||
"options": [
|
||||
{
|
||||
"index": 1,
|
||||
"label": "Add routing rules to CLAUDE.md (recommended)"
|
||||
},
|
||||
{
|
||||
"index": 2,
|
||||
"label": "No thanks, I'll invoke skills manually"
|
||||
}
|
||||
],
|
||||
"observedAtMs": 58214,
|
||||
"preReview": true,
|
||||
"nativeCall": {
|
||||
"sessionId": "ba2c03f0-6d75-4f7e-8140-d3fd03cfdbcf",
|
||||
"toolUseId": "toolu_01DRVrppFnbqJYBSwvwCSGvA",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D1 \u2014 Add gstack skill routing rules to this project's CLAUDE.md?\nProject/branch/task: gstack-plan-count-XQbt40 on main, one-time gstack onboarding before the PLAN.md design review.\nELI10: gstack works best when your project's CLAUDE.md includes skill routing rules, so plain requests like \"review this diff\" or \"why is this failing\" route to the matching skill automatically instead of you typing the slash command. This is a one-time prompt per project. Plan mode is active, so if you say yes the CLAUDE.md edit and commit happen after plan mode exits, not now.\nStakes if we pick wrong: Without routing you invoke every skill by hand; with routing you get automatic skill dispatch you may not have wanted.\nRecommendation: A because routing rules make the skill suite discoverable with zero ongoing cost.\nNote: options differ in kind, not coverage \u2014 no completeness score.\nNet: automatic skill dispatch vs. fully manual invocation.",
|
||||
"header": "Routing",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "Add routing rules to CLAUDE.md (recommended)",
|
||||
"description": "\u2705 Requests like \"ship this\" or \"review the plan\" route to the right skill without remembering slash names\n\u2705 Applies to every future session in this repo, one small append to CLAUDE.md\n\u274c Adds a routing section to a checked-in file; deferred until plan mode exits (human: ~2 min / CC: ~10 sec)"
|
||||
},
|
||||
{
|
||||
"label": "No thanks, I'll invoke skills manually",
|
||||
"description": "\u2705 CLAUDE.md stays exactly as it is, nothing committed to the fixture repo\n\u2705 You keep full control over when a skill runs; nothing fires implicitly\n\u274c Every skill needs an explicit slash command; the prompt is suppressed until you re-enable it via gstack-config"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answered": true,
|
||||
"failed": false,
|
||||
"answers": {
|
||||
"D1 \u2014 Add gstack skill routing rules to this project's CLAUDE.md?\nProject/branch/task: gstack-plan-count-XQbt40 on main, one-time gstack onboarding before the PLAN.md design review.\nELI10: gstack works best when your project's CLAUDE.md includes skill routing rules, so plain requests like \"review this diff\" or \"why is this failing\" route to the matching skill automatically instead of you typing the slash command. This is a one-time prompt per project. Plan mode is active, so if you say yes the CLAUDE.md edit and commit happen after plan mode exits, not now.\nStakes if we pick wrong: Without routing you invoke every skill by hand; with routing you get automatic skill dispatch you may not have wanted.\nRecommendation: A because routing rules make the skill suite discoverable with zero ongoing cost.\nNote: options differ in kind, not coverage \u2014 no completeness score.\nNet: automatic skill dispatch vs. fully manual invocation.": "Add routing rules to CLAUDE.md (recommended)"
|
||||
},
|
||||
"unansweredQuestionIndices": [],
|
||||
"answeredAt": "2026-09-10T04:06:43.138Z"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"ordinal": 2,
|
||||
"fingerprint": {
|
||||
"signature": "ba2c03f0-6d75-4f7e-8140-d3fd03cfdbcf:toolu_01U2GkcaXuVnsnGGRqmrHAmf",
|
||||
"promptSnippet": "Learnings D2 \u2014 Enable cross-project learnings search for gstack? Project/branch/task: gstack-plan-count-XQbt40 on main, one-time gstack setting before the PLAN.md design passes. ELI10: gstack records small lessons after each session (projec",
|
||||
"options": [
|
||||
{
|
||||
"index": 1,
|
||||
"label": "Enable cross-project learnings (recommended)"
|
||||
},
|
||||
{
|
||||
"index": 2,
|
||||
"label": "Keep learnings project-scoped only"
|
||||
}
|
||||
],
|
||||
"observedAtMs": 202103,
|
||||
"preReview": true,
|
||||
"nativeCall": {
|
||||
"sessionId": "ba2c03f0-6d75-4f7e-8140-d3fd03cfdbcf",
|
||||
"toolUseId": "toolu_01U2GkcaXuVnsnGGRqmrHAmf",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D2 \u2014 Enable cross-project learnings search for gstack?\nProject/branch/task: gstack-plan-count-XQbt40 on main, one-time gstack setting before the PLAN.md design passes.\nELI10: gstack records small lessons after each session (project quirks, pitfalls). This setting decides whether reviews in this repo may also search lessons saved from your other projects on this machine. Everything stays local; no data leaves the machine. It helps solo developers reuse patterns; it is a concern if you work across client codebases that must not cross-contaminate.\nStakes if we pick wrong: Either you miss reusable lessons from other repos, or a lesson from one client's codebase surfaces while reviewing another's.\nRecommendation: A because this is a single-developer sandbox with no client separation concern.\nNote: options differ in kind, not coverage \u2014 no completeness score.\nNet: broader recall vs. strict per-project isolation.",
|
||||
"header": "Learnings",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "Enable cross-project learnings (recommended)",
|
||||
"description": "\u2705 Reviews can surface pitfalls and patterns already learned in your other local repos\n\u2705 Compounding: every session on this machine makes later sessions smarter\n\u274c Lessons from unrelated codebases could appear where they do not apply"
|
||||
},
|
||||
{
|
||||
"label": "Keep learnings project-scoped only",
|
||||
"description": "\u2705 Strict isolation: nothing from another repo ever appears in this project's reviews\n\u2705 Safe default when you work on multiple client codebases\n\u274c Each project starts cold; shared pitfalls must be rediscovered per repo"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answered": true,
|
||||
"failed": false,
|
||||
"answers": {
|
||||
"D2 \u2014 Enable cross-project learnings search for gstack?\nProject/branch/task: gstack-plan-count-XQbt40 on main, one-time gstack setting before the PLAN.md design passes.\nELI10: gstack records small lessons after each session (project quirks, pitfalls). This setting decides whether reviews in this repo may also search lessons saved from your other projects on this machine. Everything stays local; no data leaves the machine. It helps solo developers reuse patterns; it is a concern if you work across client codebases that must not cross-contaminate.\nStakes if we pick wrong: Either you miss reusable lessons from other repos, or a lesson from one client's codebase surfaces while reviewing another's.\nRecommendation: A because this is a single-developer sandbox with no client separation concern.\nNote: options differ in kind, not coverage \u2014 no completeness score.\nNet: broader recall vs. strict per-project isolation.": "Enable cross-project learnings (recommended)"
|
||||
},
|
||||
"unansweredQuestionIndices": [],
|
||||
"answeredAt": "2026-09-10T04:09:07.019Z"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"ordinal": 3,
|
||||
"fingerprint": {
|
||||
"signature": "ba2c03f0-6d75-4f7e-8140-d3fd03cfdbcf:toolu_011W4vKp1KpSsVfiLgDLV9E9",
|
||||
"promptSnippet": "Issue 1 D3 \u2014 Issue 1: How should Save be distinguished from Reset, Cancel, and Export? Project/branch/task: gstack-plan-count-XQbt40 on main, PLAN.md design review, Pass 1 Information Architecture. ELI10: The header shows four buttons that ",
|
||||
"options": [
|
||||
{
|
||||
"index": 1,
|
||||
"label": "1A: Save filled primary, others ghost (recommended)"
|
||||
},
|
||||
{
|
||||
"index": 2,
|
||||
"label": "1B: Save primary, Export outlined secondary, Reset/Cancel ghost"
|
||||
},
|
||||
{
|
||||
"index": 3,
|
||||
"label": "1C: Leave all four buttons identical"
|
||||
}
|
||||
],
|
||||
"observedAtMs": 242227,
|
||||
"preReview": true,
|
||||
"nativeCall": {
|
||||
"sessionId": "ba2c03f0-6d75-4f7e-8140-d3fd03cfdbcf",
|
||||
"toolUseId": "toolu_011W4vKp1KpSsVfiLgDLV9E9",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D3 \u2014 Issue 1: How should Save be distinguished from Reset, Cancel, and Export?\nProject/branch/task: gstack-plan-count-XQbt40 on main, PLAN.md design review, Pass 1 Information Architecture.\nELI10: The header shows four buttons that look exactly alike. Users scan, they do not read, so the first glance has nothing that says \"this is the one you want\". Someone who just edited their email may hover between Save, Reset, and Cancel and pick wrong, which on Reset or Cancel means a confirmation dialog they did not want. DESIGN.md already says Save is the only filled primary button and the other three are neutral ghost buttons.\nStakes if we pick wrong: Users hesitate at the moment of commitment, or hit Reset/Cancel by mistake; the page reads as assembled rather than designed.\nRecommendation: 1A because DESIGN.md already prescribes the exact treatment and it makes Save the one visual anchor on the page (Principle 2: every screen has a hierarchy).\nCompleteness: 1A=10/10, 1B=7/10, 1C=3/10\nNet: exact design-system conformance vs. a three-tier hierarchy DESIGN.md does not define vs. leaving the gap open.",
|
||||
"header": "Issue 1",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "1A: Save filled primary, others ghost (recommended)",
|
||||
"description": "\u2705 Save is the only filled #1d4ed8 button with white text; Reset, Cancel, Export are neutral ghost buttons, exactly per DESIGN.md\n\u2705 One visual anchor; DOM/tab order and 44px targets unchanged, so no accessibility retest beyond contrast (human: ~1h / CC: ~5min)\n\u274c Export loses visual weight even though some users come to the page just to download"
|
||||
},
|
||||
{
|
||||
"label": "1B: Save primary, Export outlined secondary, Reset/Cancel ghost",
|
||||
"description": "\u2705 Three tiers: commit, download, destructive-ish, giving Export a bit more presence\n\u2705 Save is still the single filled anchor\n\u274c Adds an outlined button style DESIGN.md does not define, so it is a new token decision (human: ~2h / CC: ~10min)"
|
||||
},
|
||||
{
|
||||
"label": "1C: Leave all four buttons identical",
|
||||
"description": "\u2705 Zero styling work; nothing new to verify\n\u2705 Keeps the current look users have already seen\n\u274c Ships the documented violation; no primary action; litmus check 2 stays failed"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answered": true,
|
||||
"failed": false,
|
||||
"answers": {
|
||||
"D3 \u2014 Issue 1: How should Save be distinguished from Reset, Cancel, and Export?\nProject/branch/task: gstack-plan-count-XQbt40 on main, PLAN.md design review, Pass 1 Information Architecture.\nELI10: The header shows four buttons that look exactly alike. Users scan, they do not read, so the first glance has nothing that says \"this is the one you want\". Someone who just edited their email may hover between Save, Reset, and Cancel and pick wrong, which on Reset or Cancel means a confirmation dialog they did not want. DESIGN.md already says Save is the only filled primary button and the other three are neutral ghost buttons.\nStakes if we pick wrong: Users hesitate at the moment of commitment, or hit Reset/Cancel by mistake; the page reads as assembled rather than designed.\nRecommendation: 1A because DESIGN.md already prescribes the exact treatment and it makes Save the one visual anchor on the page (Principle 2: every screen has a hierarchy).\nCompleteness: 1A=10/10, 1B=7/10, 1C=3/10\nNet: exact design-system conformance vs. a three-tier hierarchy DESIGN.md does not define vs. leaving the gap open.": "1A: Save filled primary, others ghost (recommended)"
|
||||
},
|
||||
"unansweredQuestionIndices": [],
|
||||
"answeredAt": "2026-09-10T04:09:47.149Z"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"ordinal": 4,
|
||||
"fingerprint": {
|
||||
"signature": "ba2c03f0-6d75-4f7e-8140-d3fd03cfdbcf:toolu_01M52vsQMYt9bjoBfqJhH3aU",
|
||||
"promptSnippet": "Issue 5 D4 \u2014 Issue 5: What does the user see while Save is pending for 2-5 seconds? Project/branch/task: gstack-plan-count-XQbt40 on main, PLAN.md design review, Pass 2 Interaction States. ELI10: After clicking Save, nothing changes on scre",
|
||||
"options": [
|
||||
{
|
||||
"index": 1,
|
||||
"label": "5A: Spinner + \u201cSaving\u2026\u201d inside disabled Save (recommended)"
|
||||
},
|
||||
{
|
||||
"index": 2,
|
||||
"label": "5B: InlineStatus text \u201cSaving\u2026\u201d only, no spinner"
|
||||
},
|
||||
{
|
||||
"index": 3,
|
||||
"label": "5C: Full-form skeleton or overlay while saving"
|
||||
}
|
||||
],
|
||||
"observedAtMs": 277337,
|
||||
"preReview": true,
|
||||
"nativeCall": {
|
||||
"sessionId": "ba2c03f0-6d75-4f7e-8140-d3fd03cfdbcf",
|
||||
"toolUseId": "toolu_01M52vsQMYt9bjoBfqJhH3aU",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D4 \u2014 Issue 5: What does the user see while Save is pending for 2-5 seconds?\nProject/branch/task: gstack-plan-count-XQbt40 on main, PLAN.md design review, Pass 2 Interaction States.\nELI10: After clicking Save, nothing changes on screen for up to five seconds. People assume the click did not register, click again, or leave. The plan already disables repeat submissions, but a disabled button with no other change just looks broken. DESIGN.md already defines the pending pattern: a small spinner beside the word \"Saving\u2026\" inside the disabled Save button, aria-busy=true, and a non-animated fallback for reduced-motion users. Export already uses this exact pattern.\nStakes if we pick wrong: Users lose trust at the exact moment they commit their data; screen reader users get no pending announcement.\nRecommendation: 5A because it is the established pattern Export already uses and it keeps the user's edited fields fully visible (Principle 9: trust is earned at the pixel level).\nCompleteness: 5A=10/10, 5B=6/10, 5C=5/10\nNet: reuse the existing pending pattern vs. text-only feedback vs. hiding the form behind a skeleton.",
|
||||
"header": "Issue 5",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "5A: Spinner + \u201cSaving\u2026\u201d inside disabled Save (recommended)",
|
||||
"description": "\u2705 Exact DESIGN.md pattern, already implemented for Export, so it is reuse not new work (human: ~1h / CC: ~5min)\n\u2705 aria-busy=true plus the visible label change gives sighted and screen reader users the same signal; reduced-motion users get a static indicator\n\u274c Spinner lives only in the button; a user scrolled down to Notifications may not see it"
|
||||
},
|
||||
{
|
||||
"label": "5B: InlineStatus text \u201cSaving\u2026\u201d only, no spinner",
|
||||
"description": "\u2705 The live region announces the pending state wherever the user is on the page\n\u2705 No animation at all, so reduced-motion is trivially satisfied\n\u274c Deviates from the DESIGN.md pending pattern and leaves the Save button itself looking merely disabled (human: ~1h / CC: ~5min)"
|
||||
},
|
||||
{
|
||||
"label": "5C: Full-form skeleton or overlay while saving",
|
||||
"description": "\u2705 Impossible to miss; also blocks edits during the atomic save\n\u2705 Reuses the existing loading skeleton component\n\u274c Hides the values the user just typed, feels like a page reload, and is not the DESIGN.md pattern (human: ~3h / CC: ~15min)"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answered": true,
|
||||
"failed": false,
|
||||
"answers": {
|
||||
"D4 \u2014 Issue 5: What does the user see while Save is pending for 2-5 seconds?\nProject/branch/task: gstack-plan-count-XQbt40 on main, PLAN.md design review, Pass 2 Interaction States.\nELI10: After clicking Save, nothing changes on screen for up to five seconds. People assume the click did not register, click again, or leave. The plan already disables repeat submissions, but a disabled button with no other change just looks broken. DESIGN.md already defines the pending pattern: a small spinner beside the word \"Saving\u2026\" inside the disabled Save button, aria-busy=true, and a non-animated fallback for reduced-motion users. Export already uses this exact pattern.\nStakes if we pick wrong: Users lose trust at the exact moment they commit their data; screen reader users get no pending announcement.\nRecommendation: 5A because it is the established pattern Export already uses and it keeps the user's edited fields fully visible (Principle 9: trust is earned at the pixel level).\nCompleteness: 5A=10/10, 5B=6/10, 5C=5/10\nNet: reuse the existing pending pattern vs. text-only feedback vs. hiding the form behind a skeleton.": "5A: Spinner + \u201cSaving\u2026\u201d inside disabled Save (recommended)"
|
||||
},
|
||||
"unansweredQuestionIndices": [],
|
||||
"answeredAt": "2026-09-10T04:10:22.269Z"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"ordinal": 5,
|
||||
"fingerprint": {
|
||||
"signature": "ba2c03f0-6d75-4f7e-8140-d3fd03cfdbcf:toolu_016A6vzTEdsNaW8QDyaBPuPf",
|
||||
"promptSnippet": "Issue 4 D5 \u2014 Issue 4: What type scale should form labels and section headings use? Project/branch/task: gstack-plan-count-XQbt40 on main, PLAN.md design review, Pass 4 AI Slop Risk (flat-type-hierarchy). ELI10: Labels on the form are set in",
|
||||
"options": [
|
||||
{
|
||||
"index": 1,
|
||||
"label": "4A: 16px labels/body/helper, 20px section headings (recommended)"
|
||||
},
|
||||
{
|
||||
"index": 2,
|
||||
"label": "4B: Keep three sizes but define roles (14 helper, 16 label, 18 heading)"
|
||||
},
|
||||
{
|
||||
"index": 3,
|
||||
"label": "4C: Leave label sizes as they are"
|
||||
}
|
||||
],
|
||||
"observedAtMs": 368189,
|
||||
"preReview": true,
|
||||
"nativeCall": {
|
||||
"sessionId": "ba2c03f0-6d75-4f7e-8140-d3fd03cfdbcf",
|
||||
"toolUseId": "toolu_016A6vzTEdsNaW8QDyaBPuPf",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D5 \u2014 Issue 4: What type scale should form labels and section headings use?\nProject/branch/task: gstack-plan-count-XQbt40 on main, PLAN.md design review, Pass 4 AI Slop Risk (flat-type-hierarchy).\nELI10: Labels on the form are set in three different sizes (14, 16, 18px) with no rule behind which gets which. Three sizes doing one job reads as noise, and the 14px ones fall below the 16px body-text floor that keeps text readable for everyone. DESIGN.md defines exactly two roles: 16px for body, labels, and helper text, 20px for the Profile and Notifications headings.\nStakes if we pick wrong: Small labels stay hard to read on phones; the page keeps the \"assembled, not designed\" feel; a future engineer inherits an undefined scale.\nRecommendation: 4A because two roles are what DESIGN.md prescribes and they give a real hierarchy: headings clearly above everything else, everything else equal (Principle 3: specificity over vibes).\nCompleteness: 4A=10/10, 4B=5/10, 4C=3/10\nNet: the design-system scale vs. a documented three-size scale that keeps sub-16px text vs. leaving it undefined.",
|
||||
"header": "Issue 4",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "4A: 16px labels/body/helper, 20px section headings (recommended)",
|
||||
"description": "\u2705 Exactly the two DESIGN.md type roles; nothing on the form drops below 16px (human: ~1h / CC: ~5min)\n\u2705 Headings become the only larger text, so scanning by headline works and litmus check 3 stays YES\n\u274c Helper text at the same size as labels loses a subtle secondary cue; weight or color must carry it"
|
||||
},
|
||||
{
|
||||
"label": "4B: Keep three sizes but define roles (14 helper, 16 label, 18 heading)",
|
||||
"description": "\u2705 Codifies what exists today, so minimal visual change for returning users\n\u2705 Gives helper text a distinct size cue\n\u274c Contradicts DESIGN.md and keeps 14px text below the 16px readability floor (human: ~1h / CC: ~5min)"
|
||||
},
|
||||
{
|
||||
"label": "4C: Leave label sizes as they are",
|
||||
"description": "\u2705 No styling work now\n\u2705 Nothing to re-verify visually\n\u274c Ships the documented violation with an undefined scale and sub-16px labels"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answered": true,
|
||||
"failed": false,
|
||||
"answers": {
|
||||
"D5 \u2014 Issue 4: What type scale should form labels and section headings use?\nProject/branch/task: gstack-plan-count-XQbt40 on main, PLAN.md design review, Pass 4 AI Slop Risk (flat-type-hierarchy).\nELI10: Labels on the form are set in three different sizes (14, 16, 18px) with no rule behind which gets which. Three sizes doing one job reads as noise, and the 14px ones fall below the 16px body-text floor that keeps text readable for everyone. DESIGN.md defines exactly two roles: 16px for body, labels, and helper text, 20px for the Profile and Notifications headings.\nStakes if we pick wrong: Small labels stay hard to read on phones; the page keeps the \"assembled, not designed\" feel; a future engineer inherits an undefined scale.\nRecommendation: 4A because two roles are what DESIGN.md prescribes and they give a real hierarchy: headings clearly above everything else, everything else equal (Principle 3: specificity over vibes).\nCompleteness: 4A=10/10, 4B=5/10, 4C=3/10\nNet: the design-system scale vs. a documented three-size scale that keeps sub-16px text vs. leaving it undefined.": "4A: 16px labels/body/helper, 20px section headings (recommended)"
|
||||
},
|
||||
"unansweredQuestionIndices": [],
|
||||
"answeredAt": "2026-09-10T04:11:53.107Z"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"ordinal": 6,
|
||||
"fingerprint": {
|
||||
"signature": "ba2c03f0-6d75-4f7e-8140-d3fd03cfdbcf:toolu_01L3HDrnJUYBNKCbz234QRtg",
|
||||
"promptSnippet": "Issue 2 D6 \u2014 Issue 2: What vertical spacing rhythm should the form use? Project/branch/task: gstack-plan-count-XQbt40 on main, PLAN.md design review, Pass 5 Design System Alignment. ELI10: Gaps between sections are 24px in one place, 32px i",
|
||||
"options": [
|
||||
{
|
||||
"index": 1,
|
||||
"label": "2A: 8px base: sections 32, field groups 24, label-to-input 8 (recommended)"
|
||||
},
|
||||
{
|
||||
"index": 2,
|
||||
"label": "2B: Uniform 24px between everything"
|
||||
},
|
||||
{
|
||||
"index": 3,
|
||||
"label": "2C: Leave spacing as it is"
|
||||
}
|
||||
],
|
||||
"observedAtMs": 404843,
|
||||
"preReview": true,
|
||||
"nativeCall": {
|
||||
"sessionId": "ba2c03f0-6d75-4f7e-8140-d3fd03cfdbcf",
|
||||
"toolUseId": "toolu_01L3HDrnJUYBNKCbz234QRtg",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D6 \u2014 Issue 2: What vertical spacing rhythm should the form use?\nProject/branch/task: gstack-plan-count-XQbt40 on main, PLAN.md design review, Pass 5 Design System Alignment.\nELI10: Gaps between sections are 24px in one place, 32px in another, and 16px in a third. Spacing is how users know what belongs together (Gestalt proximity): a bigger gap says \"new section\", a smaller gap says \"this label belongs to this input\". Random gaps blur that grouping, so the eye cannot tell where Profile ends and Notifications begins. DESIGN.md defines an 8px base: 32px between sections, 24px between field groups, 8px from a label to its input.\nStakes if we pick wrong: Grouping stays ambiguous; the form reads as unfinished; each new field gets its own guessed margin.\nRecommendation: 2A because DESIGN.md already defines the scale and three distinct steps encode the three levels of grouping the form actually has (Principle 2: hierarchy; Gestalt proximity).\nCompleteness: 2A=10/10, 2B=6/10, 2C=3/10\nNet: the three-step design-system scale vs. one flat gap everywhere vs. leaving it inconsistent.",
|
||||
"header": "Issue 2",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "2A: 8px base: sections 32, field groups 24, label-to-input 8 (recommended)",
|
||||
"description": "\u2705 Exactly the DESIGN.md scale; every gap on the form maps to one of three named values (human: ~1h / CC: ~5min)\n\u2705 Section, field, and label grouping each get a distinct step, so proximity does the work without borders or cards\n\u274c Requires auditing every existing margin on the form, including the header action group and InlineStatus"
|
||||
},
|
||||
{
|
||||
"label": "2B: Uniform 24px between everything",
|
||||
"description": "\u2705 Simplest possible rule; one value to remember and verify\n\u2705 Still consistent, so the random-gap problem disappears\n\u274c Flattens section vs. field grouping (monotonous-spacing) and contradicts the DESIGN.md scale (human: ~30min / CC: ~3min)"
|
||||
},
|
||||
{
|
||||
"label": "2C: Leave spacing as it is",
|
||||
"description": "\u2705 No layout work now\n\u2705 No risk of shifting content users are used to\n\u274c Ships the documented violation; grouping stays ambiguous"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answered": true,
|
||||
"failed": false,
|
||||
"answers": {
|
||||
"D6 \u2014 Issue 2: What vertical spacing rhythm should the form use?\nProject/branch/task: gstack-plan-count-XQbt40 on main, PLAN.md design review, Pass 5 Design System Alignment.\nELI10: Gaps between sections are 24px in one place, 32px in another, and 16px in a third. Spacing is how users know what belongs together (Gestalt proximity): a bigger gap says \"new section\", a smaller gap says \"this label belongs to this input\". Random gaps blur that grouping, so the eye cannot tell where Profile ends and Notifications begins. DESIGN.md defines an 8px base: 32px between sections, 24px between field groups, 8px from a label to its input.\nStakes if we pick wrong: Grouping stays ambiguous; the form reads as unfinished; each new field gets its own guessed margin.\nRecommendation: 2A because DESIGN.md already defines the scale and three distinct steps encode the three levels of grouping the form actually has (Principle 2: hierarchy; Gestalt proximity).\nCompleteness: 2A=10/10, 2B=6/10, 2C=3/10\nNet: the three-step design-system scale vs. one flat gap everywhere vs. leaving it inconsistent.": "2A: 8px base: sections 32, field groups 24, label-to-input 8 (recommended)"
|
||||
},
|
||||
"unansweredQuestionIndices": [],
|
||||
"answeredAt": "2026-09-10T04:12:29.762Z"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"ordinal": 7,
|
||||
"fingerprint": {
|
||||
"signature": "ba2c03f0-6d75-4f7e-8140-d3fd03cfdbcf:toolu_01FpBzXVgEECyAaNDUCYP6pi",
|
||||
"promptSnippet": "Issue 3 D7 \u2014 Issue 3: How should the error message meet WCAG AA contrast? Project/branch/task: gstack-plan-count-XQbt40 on main, PLAN.md design review, Pass 6 Responsive & Accessibility. ELI10: The error message is red text on light pink at",
|
||||
"options": [
|
||||
{
|
||||
"index": 1,
|
||||
"label": "3A: #991b1b text on #fef2f2 surface, icon + explicit text (recommended)"
|
||||
},
|
||||
{
|
||||
"index": 2,
|
||||
"label": "3B: Darken the red on the current pink until it measures 4.5:1"
|
||||
},
|
||||
{
|
||||
"index": 3,
|
||||
"label": "3C: Leave the error styling as it is"
|
||||
}
|
||||
],
|
||||
"observedAtMs": 441491,
|
||||
"preReview": false,
|
||||
"nativeCall": {
|
||||
"sessionId": "ba2c03f0-6d75-4f7e-8140-d3fd03cfdbcf",
|
||||
"toolUseId": "toolu_01FpBzXVgEECyAaNDUCYP6pi",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D7 \u2014 Issue 3: How should the error message meet WCAG AA contrast?\nProject/branch/task: gstack-plan-count-XQbt40 on main, PLAN.md design review, Pass 6 Responsive & Accessibility.\nELI10: The error message is red text on light pink at about 3:1 contrast. WCAG AA requires 4.5:1 for text this size, so people with low vision or a dim phone screen may not be able to read the one message that tells them why their save failed. DESIGN.md defines the tokens: text #991b1b on surface #fef2f2 (about 7.6:1, passes AA and AAA) with an icon and explicit wording, so the state never depends on color alone.\nStakes if we pick wrong: The failure message is unreadable for the users most likely to need it; the page fails an accessibility audit.\nRecommendation: 3A because the DESIGN.md pair clears AA with room to spare and the icon plus text satisfy the never-color-alone rule (Principle 7: accessibility is not optional).\nCompleteness: 3A=10/10, 3B=6/10, 3C=3/10\nNet: the design-system error tokens vs. an ad hoc darker red on the current pink vs. leaving it below AA.",
|
||||
"header": "Issue 3",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "3A: #991b1b text on #fef2f2 surface, icon + explicit text (recommended)",
|
||||
"description": "\u2705 Exactly the DESIGN.md error tokens; measured contrast about 7.6:1, clearing AA (4.5:1) and AAA (7:1) (human: ~1h / CC: ~5min)\n\u2705 Icon plus explicit wording means the state is readable without color, for colorblind users and screen readers alike\n\u274c Every existing error surface (field errors, ErrorSummary, inline retry area) must be re-checked against the new pair"
|
||||
},
|
||||
{
|
||||
"label": "3B: Darken the red on the current pink until it measures 4.5:1",
|
||||
"description": "\u2705 Smallest visual change from what users see today\n\u2705 Meets the AA floor once measured\n\u274c Introduces a color pair DESIGN.md does not define and leaves the icon/explicit-text rule unaddressed (human: ~1h / CC: ~5min)"
|
||||
},
|
||||
{
|
||||
"label": "3C: Leave the error styling as it is",
|
||||
"description": "\u2705 No styling work now\n\u2705 Nothing to re-measure\n\u274c Ships a known WCAG AA failure on the most important message on the page"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answered": true,
|
||||
"failed": false,
|
||||
"answers": {
|
||||
"D7 \u2014 Issue 3: How should the error message meet WCAG AA contrast?\nProject/branch/task: gstack-plan-count-XQbt40 on main, PLAN.md design review, Pass 6 Responsive & Accessibility.\nELI10: The error message is red text on light pink at about 3:1 contrast. WCAG AA requires 4.5:1 for text this size, so people with low vision or a dim phone screen may not be able to read the one message that tells them why their save failed. DESIGN.md defines the tokens: text #991b1b on surface #fef2f2 (about 7.6:1, passes AA and AAA) with an icon and explicit wording, so the state never depends on color alone.\nStakes if we pick wrong: The failure message is unreadable for the users most likely to need it; the page fails an accessibility audit.\nRecommendation: 3A because the DESIGN.md pair clears AA with room to spare and the icon plus text satisfy the never-color-alone rule (Principle 7: accessibility is not optional).\nCompleteness: 3A=10/10, 3B=6/10, 3C=3/10\nNet: the design-system error tokens vs. an ad hoc darker red on the current pink vs. leaving it below AA.": "3A: #991b1b text on #fef2f2 surface, icon + explicit text (recommended)"
|
||||
},
|
||||
"unansweredQuestionIndices": [],
|
||||
"answeredAt": "2026-09-10T04:13:06.407Z"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"ordinal": 9,
|
||||
"fingerprint": {
|
||||
"signature": "ba2c03f0-6d75-4f7e-8140-d3fd03cfdbcf:toolu_016CKwnTbAj4y3ZBB45CT5pB",
|
||||
"promptSnippet": "TODO D9 \u2014 Deferred debt TODO: replace the app-wide system-ui font with a chosen typeface? Project/branch/task: gstack-plan-count-XQbt40 on main, PLAN.md design review, post-pass TODO proposal. ELI10: The form inherits the app's font, system",
|
||||
"options": [
|
||||
{
|
||||
"index": 1,
|
||||
"label": "A: Add to TODOS.md (recommended)"
|
||||
},
|
||||
{
|
||||
"index": 2,
|
||||
"label": "B: Skip, system-ui is intentional for this app"
|
||||
},
|
||||
{
|
||||
"index": 3,
|
||||
"label": "C: Choose a typeface in this PR"
|
||||
}
|
||||
],
|
||||
"observedAtMs": 521371,
|
||||
"preReview": false,
|
||||
"nativeCall": {
|
||||
"sessionId": "ba2c03f0-6d75-4f7e-8140-d3fd03cfdbcf",
|
||||
"toolUseId": "toolu_016CKwnTbAj4y3ZBB45CT5pB",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D9 \u2014 Deferred debt TODO: replace the app-wide system-ui font with a chosen typeface?\nProject/branch/task: gstack-plan-count-XQbt40 on main, PLAN.md design review, post-pass TODO proposal.\nELI10: The form inherits the app's font, system-ui, which means \"whatever the operating system uses\". The design checklist treats that as the \"gave up on typography\" signal because the product has no typographic voice of its own. This plan correctly keeps it: swapping fonts on one settings page would make that page look foreign, and DESIGN.md currently mandates system-ui. The question is only whether to record an app-wide typeface decision as future debt.\nWhat: Evaluate one chosen body/UI typeface app-wide and update DESIGN.md. Why: give the product a typographic voice instead of the OS default. Pros: stronger brand presence on every screen. Cons: app-wide change, font loading cost, DESIGN.md revision, visual regression across all pages. Context: flagged in Pass 4 of this review; explicitly out of scope for this form update. Depends on: /design-consultation and a DESIGN.md revision. TODOS.md does not exist yet and cannot be created in plan mode, so option A records the item in this plan and writes TODOS.md after plan mode exits.\nStakes if we pick wrong: Either the debt is forgotten, or time goes into an app-wide font change nobody asked for.\nRecommendation: A because it costs nothing now and keeps an explicit design decision from being lost, while B is a fully defensible choice for a native-feeling settings surface.\nNote: options differ in kind, not coverage \u2014 no completeness score.\nNet: record the debt vs. accept system-ui as intentional vs. widen this PR.",
|
||||
"header": "TODO",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "A: Add to TODOS.md (recommended)",
|
||||
"description": "\u2705 The typeface question becomes an explicit, findable decision with its context preserved\n\u2705 Zero work in this PR; the settings form ships unchanged\n\u274c Creates a TODOS.md file after plan mode exits; another item to triage later"
|
||||
},
|
||||
{
|
||||
"label": "B: Skip, system-ui is intentional for this app",
|
||||
"description": "\u2705 Native OS type is a legitimate choice for an OPERATE surface; nothing to track\n\u2705 No new files, no future triage\n\u274c The decision stays implicit; a future reviewer will raise it again"
|
||||
},
|
||||
{
|
||||
"label": "C: Choose a typeface in this PR",
|
||||
"description": "\u2705 Resolves the slop flag now rather than later\n\u2705 The settings form ships with the final type voice\n\u274c Contradicts the plan's explicit no-visual-exploration constraint and touches every page (human: ~2 days / CC: ~1h)"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answered": true,
|
||||
"failed": false,
|
||||
"answers": {
|
||||
"D9 \u2014 Deferred debt TODO: replace the app-wide system-ui font with a chosen typeface?\nProject/branch/task: gstack-plan-count-XQbt40 on main, PLAN.md design review, post-pass TODO proposal.\nELI10: The form inherits the app's font, system-ui, which means \"whatever the operating system uses\". The design checklist treats that as the \"gave up on typography\" signal because the product has no typographic voice of its own. This plan correctly keeps it: swapping fonts on one settings page would make that page look foreign, and DESIGN.md currently mandates system-ui. The question is only whether to record an app-wide typeface decision as future debt.\nWhat: Evaluate one chosen body/UI typeface app-wide and update DESIGN.md. Why: give the product a typographic voice instead of the OS default. Pros: stronger brand presence on every screen. Cons: app-wide change, font loading cost, DESIGN.md revision, visual regression across all pages. Context: flagged in Pass 4 of this review; explicitly out of scope for this form update. Depends on: /design-consultation and a DESIGN.md revision. TODOS.md does not exist yet and cannot be created in plan mode, so option A records the item in this plan and writes TODOS.md after plan mode exits.\nStakes if we pick wrong: Either the debt is forgotten, or time goes into an app-wide font change nobody asked for.\nRecommendation: A because it costs nothing now and keeps an explicit design decision from being lost, while B is a fully defensible choice for a native-feeling settings surface.\nNote: options differ in kind, not coverage \u2014 no completeness score.\nNet: record the debt vs. accept system-ui as intentional vs. widen this PR.": "A: Add to TODOS.md (recommended)"
|
||||
},
|
||||
"unansweredQuestionIndices": [],
|
||||
"answeredAt": "2026-09-10T04:14:26.288Z"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
+315
@@ -0,0 +1,315 @@
|
||||
{
|
||||
"sourceHead": "12faead4636b97305348e25fc12258a56fcf6868",
|
||||
"provenance": {
|
||||
"proof": ".context/ship-source-ai-delta-paid-20260910-v1/eng-first-regression-ledger-v1/proof.json",
|
||||
"proofSha256": "f6b6357218bfe8759698ca86b09dd0cfc2779824c64403a10d94fd3c08a16c1f",
|
||||
"reportSha256": "49d0f65e3d3544b312b2b25565b1f6413b0bc6efcefdbf1124b44a8c777d15af",
|
||||
"observationSha256": "22d665ff9c67f9de93885bcd4048721b6b2f34ac780974ca9050706696a4a42b",
|
||||
"reportSource": "Exact public Write167 / successful acknowledgment173; original report file later cleaned",
|
||||
"projection": "Four exact completed decision calls; three exact noncontiguous report blocks plus final report; assistant narration omitted",
|
||||
"window": {
|
||||
"start": 1789013856644,
|
||||
"end": 1789014573164,
|
||||
"note": "Conservative retained-call interval; original caller start timestamp was not retained."
|
||||
},
|
||||
"actualOutcome": "plan_ready",
|
||||
"actualFailure": "mandatory legacy regression coverage absent",
|
||||
"retrospectivePass": false
|
||||
},
|
||||
"transcript": {
|
||||
"status": "ready",
|
||||
"calls": [
|
||||
{
|
||||
"sessionId": "38d7bd5f-6064-40c7-8a8e-d84a05d0079a",
|
||||
"toolUseId": "toolu_01Vs1iEsnQPLEo5meRnjmvyy",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D4 \u2014 Reduce scope to the classes the plan actually motivates, or proceed with all 4 new classes across 12 files?\nProject/branch/task: main, PLAN.md Multi-tenant Auth Refactor, Step 0 complexity gate.\nELI10: The plan adds four new classes but only explains two of them. AuthBroker and SessionMint are the new services, and AuthCache is a thin wrapper over a cache adapter you already have. TokenStore and RequestPolicy appear only in the file-count line (PLAN.md:35) with no job described. Every unexplained class is surface area that has to be tested, reviewed, and kept in sync with the existing adapter. The question is whether to build all four now or land the two motivated ones plus the facade and add the rest when a concrete need shows up.\nStakes if we pick wrong: Overbuild and you carry two classes nobody can explain in code review, with a real chance TokenStore duplicates the adapter's tenant-keyed storage. Underbuild and you come back for a second PR if TokenStore or RequestPolicy turn out to be load-bearing.\nRecommendation: A because the plan text gives TokenStore and RequestPolicy zero responsibilities, and the existing adapter already owns token storage and invalidation. Fewer moving parts, same stated goal, and the eng preference for engineered-enough over premature abstraction.\nCompleteness: A=9/10, B=10/10, C=6/10\nNet: three classes you can defend in review versus four where two are speculative.",
|
||||
"header": "Scope",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "A) Reduce: 3 classes, ~8 files (recommended)",
|
||||
"description": "\u2705 Keeps AuthBroker, SessionMint, and the AuthCache facade; defers TokenStore and RequestPolicy until the plan states what they do (human: ~3 days / CC: ~1 hr)\n\u2705 Removes the likely overlap between TokenStore and the existing tenant-keyed adapter before it is written\n\u274c If RequestPolicy is secretly required for multi-tenant routing, it lands in a follow-up PR instead of this one"
|
||||
},
|
||||
{
|
||||
"label": "B) Proceed as-is: 4 classes, 12 files",
|
||||
"description": "\u2705 Nothing deferred; whatever TokenStore and RequestPolicy were meant to do ships in one PR (human: ~5 days / CC: ~2 hr)\n\u2705 Single review cycle instead of two if the extra classes really are needed\n\u274c Two classes with no written responsibility, so reviewers and tests have nothing to check them against"
|
||||
},
|
||||
{
|
||||
"label": "C) Reduce further: drop AuthCache facade too",
|
||||
"description": "\u2705 Smallest possible diff; both services call the existing adapter directly (human: ~2 days / CC: ~45 min)\n\u2705 No new cache surface, so no facade drift from the adapter it wraps\n\u274c Both services must re-implement whatever service-facing shaping the facade was going to centralize, a DRY hit"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answered": true,
|
||||
"failed": false,
|
||||
"answers": {
|
||||
"D4 \u2014 Reduce scope to the classes the plan actually motivates, or proceed with all 4 new classes across 12 files?\nProject/branch/task: main, PLAN.md Multi-tenant Auth Refactor, Step 0 complexity gate.\nELI10: The plan adds four new classes but only explains two of them. AuthBroker and SessionMint are the new services, and AuthCache is a thin wrapper over a cache adapter you already have. TokenStore and RequestPolicy appear only in the file-count line (PLAN.md:35) with no job described. Every unexplained class is surface area that has to be tested, reviewed, and kept in sync with the existing adapter. The question is whether to build all four now or land the two motivated ones plus the facade and add the rest when a concrete need shows up.\nStakes if we pick wrong: Overbuild and you carry two classes nobody can explain in code review, with a real chance TokenStore duplicates the adapter's tenant-keyed storage. Underbuild and you come back for a second PR if TokenStore or RequestPolicy turn out to be load-bearing.\nRecommendation: A because the plan text gives TokenStore and RequestPolicy zero responsibilities, and the existing adapter already owns token storage and invalidation. Fewer moving parts, same stated goal, and the eng preference for engineered-enough over premature abstraction.\nCompleteness: A=9/10, B=10/10, C=6/10\nNet: three classes you can defend in review versus four where two are speculative.": "A) Reduce: 3 classes, ~8 files (recommended)"
|
||||
},
|
||||
"unansweredQuestionIndices": [],
|
||||
"answeredAt": "2026-09-10T04:20:14.567Z"
|
||||
},
|
||||
{
|
||||
"sessionId": "38d7bd5f-6064-40c7-8a8e-d84a05d0079a",
|
||||
"toolUseId": "toolu_015M9Aq4LXnMuEUoygXrgXxX",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D5 \u2014 Issue 1 [P1] (confidence 8/10) PLAN.md:19-20 \u2014 AuthBroker and SessionMint share a module-level mutable AuthCache and both write to it. How should the shared cache be wired?\nProject/branch/task: main, PLAN.md Multi-tenant Auth Refactor, Section 1 Architecture.\nELI10: Right now the plan exports one cache object from a module and has two services reach for it and change it. That means nobody owns it: test files stomp on each other's cache state, two writers can interleave on the same tenant key with no coordination (PLAN.md:10 says the adapter does not serialize mutations), and a future third caller can mutate it from anywhere without a reviewer noticing. Passing the cache into each service's constructor from one composition point keeps a single instance in production while making every dependency visible and every test isolated.\nStakes if we pick wrong: Keep the global and a SessionMint write racing an AuthBroker revocation can leave a revoked token cached for a suspended tenant, a cross-tenant security incident that no unit test can reproduce because the tests share the same global.\nRecommendation: A because it is Layer 1 practice for Node.js services, costs a constructor parameter per service, and satisfies explicit-over-clever. It also makes the write-ownership rule enforceable in code.\nCompleteness: A=10/10, B=7/10, C=3/10\nNet: one composition root and two constructor parameters versus an invisible global that every test and every future caller can corrupt.",
|
||||
"header": "Issue 1",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "1A) Inject + single writer (recommended)",
|
||||
"description": "\u2705 AuthCache passed by constructor from one composition root; AuthBroker is the only writer, SessionMint reads and requests invalidation through AuthBroker, so there is no two-writer race by construction (human: ~4 hr / CC: ~20 min)\n\u2705 Tests construct a fresh in-memory adapter per case; no cross-test leakage and the concurrency claim is testable with an interleaving test\n\u274c SessionMint gains a dependency on AuthBroker (or a narrow invalidation interface) rather than on the cache directly"
|
||||
},
|
||||
{
|
||||
"label": "1B) Inject, keep two writers",
|
||||
"description": "\u2705 Constructor injection fixes test isolation and hidden coupling with the same cheap change (human: ~2 hr / CC: ~10 min)\n\u2705 Neither service needs to know about the other; both depend only on the AuthCache interface\n\u274c The unserialized two-writer race on a shared tenant key stays; you must document key-scoped idempotency and still cannot prove ordering"
|
||||
},
|
||||
{
|
||||
"label": "1C) Keep module-level global",
|
||||
"description": "\u2705 Zero plan changes and no constructor churn (human: 0 / CC: 0)\n\u2705 Matches whatever the current codebase already does for other shared modules\n\u274c Test isolation, hidden coupling, and the write race all stay; a revoked token surviving in cache is a silent cross-tenant failure"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answered": true,
|
||||
"failed": false,
|
||||
"answers": {
|
||||
"D5 \u2014 Issue 1 [P1] (confidence 8/10) PLAN.md:19-20 \u2014 AuthBroker and SessionMint share a module-level mutable AuthCache and both write to it. How should the shared cache be wired?\nProject/branch/task: main, PLAN.md Multi-tenant Auth Refactor, Section 1 Architecture.\nELI10: Right now the plan exports one cache object from a module and has two services reach for it and change it. That means nobody owns it: test files stomp on each other's cache state, two writers can interleave on the same tenant key with no coordination (PLAN.md:10 says the adapter does not serialize mutations), and a future third caller can mutate it from anywhere without a reviewer noticing. Passing the cache into each service's constructor from one composition point keeps a single instance in production while making every dependency visible and every test isolated.\nStakes if we pick wrong: Keep the global and a SessionMint write racing an AuthBroker revocation can leave a revoked token cached for a suspended tenant, a cross-tenant security incident that no unit test can reproduce because the tests share the same global.\nRecommendation: A because it is Layer 1 practice for Node.js services, costs a constructor parameter per service, and satisfies explicit-over-clever. It also makes the write-ownership rule enforceable in code.\nCompleteness: A=10/10, B=7/10, C=3/10\nNet: one composition root and two constructor parameters versus an invisible global that every test and every future caller can corrupt.": "1A) Inject + single writer (recommended)"
|
||||
},
|
||||
"unansweredQuestionIndices": [],
|
||||
"answeredAt": "2026-09-10T04:20:48.675Z"
|
||||
},
|
||||
{
|
||||
"sessionId": "38d7bd5f-6064-40c7-8a8e-d84a05d0079a",
|
||||
"toolUseId": "toolu_014j8ZPhGxWomRacLoYdwtmf",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D7 \u2014 Issue 3 [P1] (confidence 8/10) PLAN.md:23-24 \u2014 validateAndDispatch() is 60 lines with three nested try/catch blocks and each catch swallows a different error class. How should error handling be restructured?\nProject/branch/task: main, PLAN.md Multi-tenant Auth Refactor, Section 2 Code Quality.\nELI10: Three nested try/catch blocks that each swallow an error mean a failed token check, a failed policy lookup, or a failed dispatch can all turn into 'nothing happened'. In auth, a swallowed error is the worst outcome: the user either gets silently denied with no reason or, worse, falls through to a code path that treats missing data as valid. Splitting the function into three named steps with one error boundary that maps each error class to an explicit outcome (deny with reason, retry, or rethrow) makes every failure visible and every branch testable.\nStakes if we pick wrong: A swallowed IDP error on a revocation check can let a revoked session through; a swallowed policy error can deny a whole tenant with no log line to debug from.\nRecommendation: A because swallowing is never acceptable in an auth path, and three small pure functions plus one boundary is both DRY and explicit. Each error class then has exactly one place where its handling is decided.\nCompleteness: A=10/10, B=6/10, C=2/10\nNet: three 15-line functions with one visible error map versus one 60-line function that can fail silently three different ways.",
|
||||
"header": "Issue 3",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "3A) Decompose + single error boundary (recommended)",
|
||||
"description": "\u2705 Split into validateToken, resolvePolicy, dispatch; one outer boundary maps TokenError, PolicyError, DispatchError to explicit deny/retry/rethrow with a log line and metric each (human: ~4 hr / CC: ~20 min)\n\u2705 Each step is unit-testable alone and the error map is one table-driven test; no error class can be silently dropped\n\u274c Touches the dispatch entry point that the per-tenant flag from Issue 2 also lives in, so sequence this refactor first"
|
||||
},
|
||||
{
|
||||
"label": "3B) Keep shape, log in each catch",
|
||||
"description": "\u2705 Minimal diff; add a structured log and metric inside each existing catch (human: ~1 hr / CC: ~5 min)\n\u2705 Failures become visible in logs without changing control flow\n\u274c Still three nested blocks in one 60-line function; swallow-then-continue semantics remain and are still hard to test per branch"
|
||||
},
|
||||
{
|
||||
"label": "3C) Leave as-is",
|
||||
"description": "\u2705 No change to a function that presumably works today (human: 0 / CC: 0)\n\u2705 No risk of altering control flow in the dispatch path\n\u274c Three silent failure modes in the auth path persist and the new AuthBroker path inherits them"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answered": true,
|
||||
"failed": false,
|
||||
"answers": {
|
||||
"D7 \u2014 Issue 3 [P1] (confidence 8/10) PLAN.md:23-24 \u2014 validateAndDispatch() is 60 lines with three nested try/catch blocks and each catch swallows a different error class. How should error handling be restructured?\nProject/branch/task: main, PLAN.md Multi-tenant Auth Refactor, Section 2 Code Quality.\nELI10: Three nested try/catch blocks that each swallow an error mean a failed token check, a failed policy lookup, or a failed dispatch can all turn into 'nothing happened'. In auth, a swallowed error is the worst outcome: the user either gets silently denied with no reason or, worse, falls through to a code path that treats missing data as valid. Splitting the function into three named steps with one error boundary that maps each error class to an explicit outcome (deny with reason, retry, or rethrow) makes every failure visible and every branch testable.\nStakes if we pick wrong: A swallowed IDP error on a revocation check can let a revoked session through; a swallowed policy error can deny a whole tenant with no log line to debug from.\nRecommendation: A because swallowing is never acceptable in an auth path, and three small pure functions plus one boundary is both DRY and explicit. Each error class then has exactly one place where its handling is decided.\nCompleteness: A=10/10, B=6/10, C=2/10\nNet: three 15-line functions with one visible error map versus one 60-line function that can fail silently three different ways.": "3A) Decompose + single error boundary (recommended)"
|
||||
},
|
||||
"unansweredQuestionIndices": [],
|
||||
"answeredAt": "2026-09-10T04:21:36.850Z"
|
||||
},
|
||||
{
|
||||
"sessionId": "38d7bd5f-6064-40c7-8a8e-d84a05d0079a",
|
||||
"toolUseId": "toolu_01VRvWUm73ScjhfBbGaGbrXq",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D9 \u2014 Issue 5 [P2] (confidence 8/10) PLAN.md:31-32 \u2014 Token validation makes 5 sequential IDP calls; the plan says 'Promise.all trivially'. How should the parallelization be done?\nProject/branch/task: main, PLAN.md Multi-tenant Auth Refactor, Section 4 Performance.\nELI10: Five calls in a row means login latency is the sum of five network round trips. Running them at once cuts that to the slowest single call. But 'just wrap in Promise.all' is not the whole story: Promise.all rejects on the first failure and leaves the other four requests running in the background, and none of the calls has a timeout today. For auth, fail-fast is correct (all five checks must pass), so Promise.all is the right primitive, but each call needs a timeout and the losers need to be cancelled so a slow IDP does not pile up open connections under load.\nStakes if we pick wrong: Bare Promise.all with no timeout means one hung IDP endpoint hangs every login indefinitely; allSettled would let a login proceed with a failed check unless you add aggregation logic that fail-fast already gives you.\nRecommendation: A because all five checks are required for a valid token, so fail-fast semantics match the domain, and adding an AbortController plus per-call timeout is a few lines that turns a latency win into a resilience win too.\nCompleteness: A=10/10, B=7/10, C=6/10\nNet: parallel with cancellation and timeouts versus parallel with dangling requests and no upper bound on login time.",
|
||||
"header": "Issue 5",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "5A) Promise.all + shared AbortController + per-call timeout (recommended)",
|
||||
"description": "\u2705 All five run in parallel, first failure aborts the rest, every call bounded by a timeout mapped to TokenError for the Issue 3 error boundary (human: ~3 hr / CC: ~15 min)\n\u2705 Login latency drops from sum-of-five to max-of-one and a hung IDP degrades to a clear timeout instead of a hang\n\u274c Requires the IDP client to accept an abort signal; if it does not, wrap it once in a small adapter"
|
||||
},
|
||||
{
|
||||
"label": "5B) Bare Promise.all as planned",
|
||||
"description": "\u2705 One-line change that gets the full latency win (human: ~30 min / CC: ~2 min)\n\u2705 Fail-fast semantics already match 'all checks must pass'\n\u274c No timeout and no cancellation: a slow IDP hangs login and losing requests keep running after the first rejection"
|
||||
},
|
||||
{
|
||||
"label": "5C) Promise.allSettled + aggregate",
|
||||
"description": "\u2705 Every call completes so you get a full picture of which checks failed for diagnostics (human: ~2 hr / CC: ~10 min)\n\u2705 No dangling requests since all settle before you proceed\n\u274c Login waits for the slowest call even when the first one already failed; you re-implement fail-fast by hand in the aggregation"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answered": true,
|
||||
"failed": false,
|
||||
"answers": {
|
||||
"D9 \u2014 Issue 5 [P2] (confidence 8/10) PLAN.md:31-32 \u2014 Token validation makes 5 sequential IDP calls; the plan says 'Promise.all trivially'. How should the parallelization be done?\nProject/branch/task: main, PLAN.md Multi-tenant Auth Refactor, Section 4 Performance.\nELI10: Five calls in a row means login latency is the sum of five network round trips. Running them at once cuts that to the slowest single call. But 'just wrap in Promise.all' is not the whole story: Promise.all rejects on the first failure and leaves the other four requests running in the background, and none of the calls has a timeout today. For auth, fail-fast is correct (all five checks must pass), so Promise.all is the right primitive, but each call needs a timeout and the losers need to be cancelled so a slow IDP does not pile up open connections under load.\nStakes if we pick wrong: Bare Promise.all with no timeout means one hung IDP endpoint hangs every login indefinitely; allSettled would let a login proceed with a failed check unless you add aggregation logic that fail-fast already gives you.\nRecommendation: A because all five checks are required for a valid token, so fail-fast semantics match the domain, and adding an AbortController plus per-call timeout is a few lines that turns a latency win into a resilience win too.\nCompleteness: A=10/10, B=7/10, C=6/10\nNet: parallel with cancellation and timeouts versus parallel with dangling requests and no upper bound on login time.": "5A) Promise.all + shared AbortController + per-call timeout (recommended)"
|
||||
},
|
||||
"unansweredQuestionIndices": [],
|
||||
"answeredAt": "2026-09-10T04:23:03.192Z"
|
||||
}
|
||||
],
|
||||
"assistantMessages": []
|
||||
},
|
||||
"mandatory": "`legacyAuthFlow()` is existing behavior being modified, and PLAN.md:14-16\nstates no test asserts compatibility with its prior behavior. A\n**characterization test suite** for `legacyAuthFlow()` is added as a critical\nrequirement: capture current response shape, headers, cookies, cache effects,\nand error responses for valid, expired, revoked, wrong-audience, wrong-issuer,\nand suspended-tenant inputs. This suite runs against the flag-OFF path and is\nthe oracle the new path is compared to during rollout.",
|
||||
"task": "- [ ] **T4 (P1, human: ~1d / CC: ~30min)** \u2014 auth/legacy tests \u2014 **CRITICAL regression:** characterization suite for `legacyAuthFlow()` prior behavior\n - Surfaced by: Test review regression rule \u2014 PLAN.md:27-28, 14-16 no regression test for rewritten legacy flow\n - Files: auth/__tests__/legacyAuthFlow.characterization.test\n - Verify: suite green against flag-OFF path before and after refactor",
|
||||
"verification": "1. Run the characterization suite (T4) against the untouched `legacyAuthFlow()` first and commit it green. This is the baseline.",
|
||||
"reviewReport": "## GSTACK REVIEW REPORT\n\n| Review | Trigger | Why | Runs | Status | Findings |\n|--------|---------|-----|------|--------|----------|\n| CEO Review | `/plan-ceo-review` | Scope & strategy | 0 | \u2014 | \u2014 |\n| Outside Review | codex via `/plan-eng-review` | Independent 2nd opinion | 1 | disabled | codex_reviews=disabled; no outside coverage |\n| Eng Review | `/plan-eng-review` | Architecture & tests (required) | 1 | clean | 28 issues (5 findings + 23 test gaps), 0 critical gaps, SCOPE_REDUCED |\n| Design Review | `/plan-design-review` | UI/UX gaps | 0 | \u2014 | \u2014 |\n| DX Review | `/plan-devex-review` | Developer experience gaps | 0 | \u2014 | \u2014 |\n\n**OUTSIDE COVERAGE:** provider codex, phase plan-review, status disabled (user config `codex_reviews=disabled`), no findings. Native review only; no outside model coverage. Re-enable with `gstack-config set codex_reviews enabled`.\n\n**VERDICT:** ENG CLEARED \u2014 ready to implement. Backend-only auth change, no UI scope; design review not applicable. CEO review optional (refactor, not a product change).\n\nNO UNRESOLVED DECISIONS\n",
|
||||
"retry": {
|
||||
"provenance": {
|
||||
"proof": ".context/ship-source-ai-delta-paid-20260910-v1/eng-retry-regression-ledger-v1/proof.json",
|
||||
"proofSha256": "440cfe55e0bf12105b906e6c7c78bea67cabcd07e10ccfe93fc9e59bc779b0ea",
|
||||
"reportSha256": "d6491cf54d09c4975d169a251f39b4cd35cdc6148b0b9af2b1309a143b6a7f69",
|
||||
"observationSha256": "653ec66de6e2a7feb2c86b3ba15c411d9bc3b7be84a0171085b8a5baa620cde5",
|
||||
"reportSource": "Exact observer-retained public Write159 / successful acknowledgment165; native/report temporary files cleaned",
|
||||
"projection": "Four exact completed calls and two exact noncontiguous report blocks plus final report; narration omitted",
|
||||
"window": {
|
||||
"start": 1789014617709,
|
||||
"end": 1789015182938,
|
||||
"note": "Conservative retained-call interval; original caller start not retained"
|
||||
},
|
||||
"actualOutcome": "plan_ready",
|
||||
"actualFailure": "mandatory legacy regression coverage absent",
|
||||
"retrospectivePass": false
|
||||
},
|
||||
"transcript": {
|
||||
"status": "ready",
|
||||
"calls": [
|
||||
{
|
||||
"sessionId": "46259e9c-41ce-49a9-9835-e58c2127bafd",
|
||||
"toolUseId": "toolu_01ETm5Logu7z2giNJrDn5Cch",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D4 \u2014 Complexity check triggered: 4 new classes across 12 files. Reduce scope or proceed as-is?\nProject/branch/task: main branch, PLAN.md Multi-tenant Auth Refactor, Step 0 scope gate.\nELI10: The plan adds four new classes (TokenStore, SessionMint, AuthCache, RequestPolicy) plus AuthBroker, touching 12 files (PLAN.md:35-36). The existing cache adapter already stores tokens keyed by tenant, evicts, and invalidates (PLAN.md:7-13), so TokenStore looks like a second token store next to the first. RequestPolicy has no stated behavior beyond a policy decision, which is usually typed config plus one pure function, not a class. Every extra class is a second place a 3am on-call engineer has to look when a tenant's token is stale.\nStakes if we pick wrong: over-build means two token stores that can disagree on validity; under-build means we cut a class that had a real reason to exist that the plan did not state.\nRecommendation: A because the adapter already owns token storage and the plan gives TokenStore and RequestPolicy no responsibility that justifies a class; AuthBroker, SessionMint, and AuthCache-as-injected-seam carry the actual goal.\nNote: options differ in kind, not coverage \u2014 no completeness score.\nNet: fewer moving parts and one source of truth for tokens vs keeping the plan's original decomposition.",
|
||||
"header": "Scope",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "Reduce: cut TokenStore + RequestPolicy class (recommended)",
|
||||
"description": "(human: ~1 day less / CC: ~10 min less) \u2705 One token store: the existing adapter behind AuthCache; no second cache that can disagree on validity. \u2705 RequestPolicy becomes a typed config object plus a pure evaluate() function, trivially unit-testable. \u2705 Drops to 2-3 new classes and roughly 8-9 files. \u274c If TokenStore held state the adapter cannot (e.g. refresh-token secrets), that need must be re-stated and re-planned."
|
||||
},
|
||||
{
|
||||
"label": "Proceed as-is with 4 classes",
|
||||
"description": "(human: ~3 days / CC: ~45 min) \u2705 Keeps whatever unstated reasons the author had for each class. \u2705 No re-planning before the review continues. \u274c Two token-holding components (adapter + TokenStore) and a class for what is likely config; more surface for the tests and the on-call engineer."
|
||||
},
|
||||
{
|
||||
"label": "Reduce further: also drop AuthCache facade",
|
||||
"description": "(human: ~1.5 days less / CC: ~15 min less) \u2705 Services inject the existing adapter directly; smallest possible diff, one fewer indirection. \u2705 Existing adapter tests already cover the store the services talk to. \u274c Loses the seam where tenant-scoped or service-facing helpers would live; if the adapter API is wide, both services re-implement the same wrapping (DRY hit)."
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answered": true,
|
||||
"failed": false,
|
||||
"answers": {
|
||||
"D4 \u2014 Complexity check triggered: 4 new classes across 12 files. Reduce scope or proceed as-is?\nProject/branch/task: main branch, PLAN.md Multi-tenant Auth Refactor, Step 0 scope gate.\nELI10: The plan adds four new classes (TokenStore, SessionMint, AuthCache, RequestPolicy) plus AuthBroker, touching 12 files (PLAN.md:35-36). The existing cache adapter already stores tokens keyed by tenant, evicts, and invalidates (PLAN.md:7-13), so TokenStore looks like a second token store next to the first. RequestPolicy has no stated behavior beyond a policy decision, which is usually typed config plus one pure function, not a class. Every extra class is a second place a 3am on-call engineer has to look when a tenant's token is stale.\nStakes if we pick wrong: over-build means two token stores that can disagree on validity; under-build means we cut a class that had a real reason to exist that the plan did not state.\nRecommendation: A because the adapter already owns token storage and the plan gives TokenStore and RequestPolicy no responsibility that justifies a class; AuthBroker, SessionMint, and AuthCache-as-injected-seam carry the actual goal.\nNote: options differ in kind, not coverage \u2014 no completeness score.\nNet: fewer moving parts and one source of truth for tokens vs keeping the plan's original decomposition.": "Reduce: cut TokenStore + RequestPolicy class (recommended)"
|
||||
},
|
||||
"unansweredQuestionIndices": [],
|
||||
"answeredAt": "2026-09-10T04:32:24.356Z"
|
||||
},
|
||||
{
|
||||
"sessionId": "46259e9c-41ce-49a9-9835-e58c2127bafd",
|
||||
"toolUseId": "toolu_01HQ688pYVMztonScLEhZTDR",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D5 \u2014 Issue 1: AuthBroker and SessionMint both mutate a module-level global AuthCache with no serialization. How should the cache be owned?\nProject/branch/task: main branch, PLAN.md Multi-tenant Auth Refactor, Architecture review.\nELI10: Both new services import the same cache object from a module and write to it (PLAN.md:19-20), and the plan says nothing serializes those writes (PLAN.md:10). Two writers on one shared object is how a token minted for tenant A lands under tenant B's key, or a revocation gets overwritten by a stale mint a few milliseconds later. A module-level global also means tests share state across files and you cannot swap in a fake without hacking the module cache.\nStakes if we pick wrong: cross-tenant token leakage or a revoked session staying valid, which in auth is a security incident, not a bug.\nRecommendation: 1A because a single writer plus constructor injection removes the race by design instead of by lock, matches your explicit-over-clever and well-tested preferences, and costs minutes with CC.\nCompleteness: A=10/10, B=7/10, C=2/10\nNet: eliminate the race structurally vs paper over it with a lock vs accept a latent auth race.",
|
||||
"header": "Issue 1",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "1A: Inject AuthCache; AuthBroker sole writer (recommended)",
|
||||
"description": "(human: ~1 day / CC: ~15 min) Completeness 10/10. \u2705 One writer: SessionMint returns a minted session and AuthBroker commits it via one write-through method (putIfAbsent / compare-and-set on tenant key + policy version). \u2705 Constructor injection from one composition root makes every test a fresh instance with a fake adapter; no module-cache hacks. \u2705 Contract test proves two concurrent mints for the same tenant key yield exactly one cache entry. \u274c SessionMint's public shape changes from 'mutate cache' to 'return value', so its callers need the broker in the loop."
|
||||
},
|
||||
{
|
||||
"label": "1B: Keep module export, add per-tenant-key mutex",
|
||||
"description": "(human: ~half day / CC: ~10 min) Completeness 7/10. \u2705 Smallest change to the plan's current shape; both services keep writing. \u2705 Serializes writes per tenant key so revoke-then-mint ordering is preserved. \u274c Lock is a runtime guard, not a design boundary; a third writer added later is one forgotten import away from the same race. \u274c Global still leaks state across tests and hides the dependency."
|
||||
},
|
||||
{
|
||||
"label": "1C: Do nothing, keep as planned",
|
||||
"description": "(human: 0 / CC: 0) Completeness 2/10. \u2705 No change to the plan or its file count. \u2705 If the runtime is truly single-threaded and every write is synchronous, the race window may be tiny. \u274c 'Tiny' is not 'zero' across await points in token validation, and the plan already says mutations are not serialized."
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answered": true,
|
||||
"failed": false,
|
||||
"answers": {
|
||||
"D5 \u2014 Issue 1: AuthBroker and SessionMint both mutate a module-level global AuthCache with no serialization. How should the cache be owned?\nProject/branch/task: main branch, PLAN.md Multi-tenant Auth Refactor, Architecture review.\nELI10: Both new services import the same cache object from a module and write to it (PLAN.md:19-20), and the plan says nothing serializes those writes (PLAN.md:10). Two writers on one shared object is how a token minted for tenant A lands under tenant B's key, or a revocation gets overwritten by a stale mint a few milliseconds later. A module-level global also means tests share state across files and you cannot swap in a fake without hacking the module cache.\nStakes if we pick wrong: cross-tenant token leakage or a revoked session staying valid, which in auth is a security incident, not a bug.\nRecommendation: 1A because a single writer plus constructor injection removes the race by design instead of by lock, matches your explicit-over-clever and well-tested preferences, and costs minutes with CC.\nCompleteness: A=10/10, B=7/10, C=2/10\nNet: eliminate the race structurally vs paper over it with a lock vs accept a latent auth race.": "1A: Inject AuthCache; AuthBroker sole writer (recommended)"
|
||||
},
|
||||
"unansweredQuestionIndices": [],
|
||||
"answeredAt": "2026-09-10T04:33:18.686Z"
|
||||
},
|
||||
{
|
||||
"sessionId": "46259e9c-41ce-49a9-9835-e58c2127bafd",
|
||||
"toolUseId": "toolu_01M4AHaLz6DYBcwq4aY2QLDv",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D7 \u2014 Issue 3: validateAndDispatch() nests three try/catch blocks that each swallow an error class. How should it be restructured?\nProject/branch/task: main branch, PLAN.md Multi-tenant Auth Refactor, Code quality review.\nELI10: One 60-line function does validation and dispatch with three nested try/catch blocks, and each catch swallows a different error class (PLAN.md:23-24). Swallowing means the function keeps going as if nothing failed. In an auth path that can mean a token that failed a check still gets dispatched, and the only trace is a log line nobody reads. Splitting it into small stages with one explicit result type makes every failure visible, typed, and testable.\nStakes if we pick wrong: silent auth failures that look like success from the outside, and a function nobody wants to touch.\nRecommendation: 3A because explicit typed outcomes beat clever catch-and-continue, each stage becomes a pure unit with its own tests, and it is a 15-minute job with CC.\nCompleteness: A=10/10, B=6/10, C=2/10\nNet: explicit failure surface and testable stages vs a smaller edit that keeps the swallowing shape.",
|
||||
"header": "Issue 3",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "3A: Split into stages, one typed error boundary (recommended)",
|
||||
"description": "(human: ~half day / CC: ~15 min) Completeness 10/10. \u2705 validateToken(), resolvePolicy(), dispatch() as separate functions, each returning a typed Result (ok | AuthError subtype) instead of throwing into a swallowing catch. \u2705 One boundary at the top maps every AuthError to an explicit response or rethrow with tenant context; nothing is swallowed. \u2705 Each stage gets a test per success and per error class; 3 error classes = at least 3 negative tests. \u274c More small functions and a Result type; slightly larger diff than an in-place patch."
|
||||
},
|
||||
{
|
||||
"label": "3B: Keep one function, stop swallowing",
|
||||
"description": "(human: ~1 hour / CC: ~5 min) Completeness 6/10. \u2705 Minimal diff: each catch rethrows a typed AuthError with context instead of swallowing. \u2705 No new types or file moves. \u274c Still 60 lines with three nesting levels; hard to test each branch in isolation. \u274c The next person adding a fourth check will add a fourth nested try/catch."
|
||||
},
|
||||
{
|
||||
"label": "3C: Leave as-is",
|
||||
"description": "(human: 0 / CC: 0) Completeness 2/10. \u2705 Zero risk of breaking whatever the swallowing currently hides. \u2705 No effort. \u274c Auth failures stay silent; the plan itself calls this out as a smell and the refactor is the natural moment to fix it."
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answered": true,
|
||||
"failed": false,
|
||||
"answers": {
|
||||
"D7 \u2014 Issue 3: validateAndDispatch() nests three try/catch blocks that each swallow an error class. How should it be restructured?\nProject/branch/task: main branch, PLAN.md Multi-tenant Auth Refactor, Code quality review.\nELI10: One 60-line function does validation and dispatch with three nested try/catch blocks, and each catch swallows a different error class (PLAN.md:23-24). Swallowing means the function keeps going as if nothing failed. In an auth path that can mean a token that failed a check still gets dispatched, and the only trace is a log line nobody reads. Splitting it into small stages with one explicit result type makes every failure visible, typed, and testable.\nStakes if we pick wrong: silent auth failures that look like success from the outside, and a function nobody wants to touch.\nRecommendation: 3A because explicit typed outcomes beat clever catch-and-continue, each stage becomes a pure unit with its own tests, and it is a 15-minute job with CC.\nCompleteness: A=10/10, B=6/10, C=2/10\nNet: explicit failure surface and testable stages vs a smaller edit that keeps the swallowing shape.": "3A: Split into stages, one typed error boundary (recommended)"
|
||||
},
|
||||
"unansweredQuestionIndices": [],
|
||||
"answeredAt": "2026-09-10T04:34:09.004Z"
|
||||
},
|
||||
{
|
||||
"sessionId": "46259e9c-41ce-49a9-9835-e58c2127bafd",
|
||||
"toolUseId": "toolu_01C6LEfWUSZynnZvSJvjvCXb",
|
||||
"questions": [
|
||||
{
|
||||
"question": "D9 \u2014 Issue 5: Token validation makes 5 sequential IDP calls. How should they be parallelized, and what happens when one fails?\nProject/branch/task: main branch, PLAN.md Multi-tenant Auth Refactor, Performance review.\nELI10: Every login waits for five identity-provider round trips one after another (PLAN.md:31-32). Running them at once cuts that wait to roughly the slowest single call. The catch is failure semantics: Promise.all rejects on the first failure but leaves the other four requests running, and you need to decide whether a partial result is ever usable for validation. For auth it is not: every check must pass, so fail-fast is correct, but the in-flight calls should be cancelled and the failure typed so it lands in the Issue 3 error boundary instead of a swallowed catch.\nStakes if we pick wrong: either users wait 5x longer than needed, or a partial failure produces a confusing aggregate error and orphaned requests hammer the IDP during an outage.\nRecommendation: 5A because validation needs all five results, fail-fast is the right semantics, and adding an AbortController plus one shared timeout is a few lines that also protect the IDP when it is degraded.\nCompleteness: A=10/10, B=8/10, C=1/10\nNet: fast, bounded, cancellable validation vs bare Promise.all vs the current 5x latency.",
|
||||
"header": "Issue 5",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{
|
||||
"label": "5A: Promise.all + AbortController + shared timeout, typed failure (recommended)",
|
||||
"description": "(human: ~half day / CC: ~10 min) Completeness 10/10. \u2705 Latency drops from sum-of-five to max-of-one on the login hot path. \u2705 First failure aborts the other four via one AbortSignal and surfaces as a typed IdpValidationError with which check failed, feeding the Issue 3 boundary. \u2705 Tests: all succeed, one rejects (others aborted), one times out, IDP 5xx. \u274c Slightly more code than a one-line Promise.all; needs the IDP client to accept an AbortSignal."
|
||||
},
|
||||
{
|
||||
"label": "5B: Bare Promise.all",
|
||||
"description": "(human: ~30 min / CC: ~3 min) Completeness 8/10. \u2705 Same latency win with a one-line change. \u2705 Fail-fast semantics match 'all checks must pass'. \u274c Remaining four requests keep running after the first rejection; during an IDP incident that multiplies load on a struggling dependency. \u274c No shared deadline, so one hung call hangs the login."
|
||||
},
|
||||
{
|
||||
"label": "5C: Leave sequential",
|
||||
"description": "(human: 0 / CC: 0) Completeness 1/10. \u2705 Simplest possible control flow and error attribution. \u2705 Lowest instantaneous load on the IDP. \u274c Users pay five round trips on every login; the plan itself calls the calls independent."
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"answered": true,
|
||||
"failed": false,
|
||||
"answers": {
|
||||
"D9 \u2014 Issue 5: Token validation makes 5 sequential IDP calls. How should they be parallelized, and what happens when one fails?\nProject/branch/task: main branch, PLAN.md Multi-tenant Auth Refactor, Performance review.\nELI10: Every login waits for five identity-provider round trips one after another (PLAN.md:31-32). Running them at once cuts that wait to roughly the slowest single call. The catch is failure semantics: Promise.all rejects on the first failure but leaves the other four requests running, and you need to decide whether a partial result is ever usable for validation. For auth it is not: every check must pass, so fail-fast is correct, but the in-flight calls should be cancelled and the failure typed so it lands in the Issue 3 error boundary instead of a swallowed catch.\nStakes if we pick wrong: either users wait 5x longer than needed, or a partial failure produces a confusing aggregate error and orphaned requests hammer the IDP during an outage.\nRecommendation: 5A because validation needs all five results, fail-fast is the right semantics, and adding an AbortController plus one shared timeout is a few lines that also protect the IDP when it is degraded.\nCompleteness: A=10/10, B=8/10, C=1/10\nNet: fast, bounded, cancellable validation vs bare Promise.all vs the current 5x latency.": "5A: Promise.all + AbortController + shared timeout, typed failure (recommended)"
|
||||
},
|
||||
"unansweredQuestionIndices": [],
|
||||
"answeredAt": "2026-09-10T04:35:15.424Z"
|
||||
}
|
||||
],
|
||||
"assistantMessages": []
|
||||
},
|
||||
"heading": "### CRITICAL: regression contract test for legacyAuthFlow() (iron rule, no decision needed)",
|
||||
"mandatory": "The rewrite modifies existing behavior with no covering test (PLAN.md:27-28). Add\n`src/auth/authFlow.contract.test.ts`: a fixture table of (tenant, token, policy) cases\ncovering valid token, expired token, wrong audience, wrong issuer, policy deny, revoked token,\nsuspended tenant. Run each fixture through `legacyAuthFlow()` and `AuthBroker.authenticate()`\nand assert identical `Session` shape on success and identical error code on failure. This test\nis also the gate for flipping any tenant's flag and for TODO 1 removal.",
|
||||
"task": "- [ ] **T4 (P1, human: ~half day / CC: ~15 min)** \u2014 Tests \u2014 CRITICAL regression contract test: same fixtures through legacyAuthFlow() and AuthBroker, identical Session / error codes\n - Surfaced by: Test review \u2014 iron regression rule, PLAN.md:27-28\n - Files: src/auth/authFlow.contract.test.ts\n - Verify: contract suite green on both paths",
|
||||
"reviewReport": "## GSTACK REVIEW REPORT\n\n### Suppressed findings (confidence < 7)\n\n- `[P3] (confidence: 5/10) PLAN.md:31-32` \u2014 Some of the five IDP calls may fetch cacheable issuer metadata (discovery/JWKS). Unverifiable without the IDP client; captured as TODO 2 rather than a finding.\n\n| Review | Trigger | Why | Runs | Status | Findings |\n|--------|---------|-----|------|--------|----------|\n| CEO Review | `/plan-ceo-review` | Scope & strategy | 0 | \u2014 | \u2014 |\n| Outside Review | codex via `/plan-eng-review` (host: claude) | Independent 2nd opinion | 1 | disabled | outside_status: disabled, phase: plan-review, no findings (not run) |\n| Eng Review | `/plan-eng-review` | Architecture & tests (required) | 1 | clean (PLAN) | 5 issues, 0 critical gaps |\n| Design Review | `/plan-design-review` | UI/UX gaps | 0 | \u2014 | \u2014 |\n| DX Review | `/plan-devex-review` | Developer experience gaps | 0 | \u2014 | \u2014 |\n\n**OUTSIDE COVERAGE:** provider codex, phase plan-review, outside_status disabled (codex_reviews=disabled), no native fallback dispatched, no findings. Missing outside coverage is not counted as clean.\n\n**VERDICT:** ENG CLEARED \u2014 ready to implement (eng review clean; CEO/Design/DX not run, optional for a backend auth refactor).\n\nNO UNRESOLVED DECISIONS\n",
|
||||
"legacyHeading": "### Issue 2 (D6, chose 2A): Per-tenant flag routes legacy vs AuthBroker",
|
||||
"legacy": "PLAN.md:27-28 rewrote `legacyAuthFlow()` in place with no rollback path. Auth is the one\npath where a bad deploy locks every tenant out, so the cutover is a strangler fig:\n\n- A tenant-keyed flag `auth.useBroker[tenantId]` (default off) selects the path at the\n login entry point. `legacyAuthFlow()` stays callable and unchanged this release.\n- Rollout: one internal tenant, soak one release, widen. Rollback is a config flip.\n- Removal of the legacy path and the flag is TODO 1 below, triggered by 100% of tenants on\n the new path for one release."
|
||||
}
|
||||
}
|
||||
+20
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"sourceHead": "12faead4636b97305348e25fc12258a56fcf6868",
|
||||
"evidence": {
|
||||
"path": ".context/ship-source-ai-delta-paid-20260910-v1/eng-plan-mode-diagnosis-ledger-v1/seeded-first-terminal.visible.log",
|
||||
"sha256": "c9abe6c170ea3ba44fc5d3493c510f508b77c91392d9e398a63d99f4edb02db9",
|
||||
"sessionId": "6f83f040-b1b5-4318-a6ab-c60de84f263b",
|
||||
"startCharacter": 37930,
|
||||
"endCharacter": 38080,
|
||||
"note": "Exact historical TODO excerpt from the first seeded attempt; current screen variants in tests are synthetic. Full retained raw/visible history remains in context; no paid pass is inferred."
|
||||
},
|
||||
"visibleReadExcerpt": "--timings/--shard once the repo unpins Bun 1.3.13.CIandthismachinearenowonBun1.4.0,sothatunpinhas\n already happened and the item is ready to execute.",
|
||||
"reconstructedScreen": " 1. Existing code already solves this. bun run test already routes through scripts/test-free-shards.ts (1,631 lines),\n which runs N concurrent shard processes, packs files by recorded durations (LPT), classifies every byte of child\n output through scripts/test-strict-output.ts, kills wedged shards by process group, and serves the CI matrix via\n --shards M --shard i. The paid suite has the same in scripts/test-paid-shards.ts. Both share runShardChild. All\n four files the plan would duplicate have pinning tests today (test/test-free-shards.test.ts, \n test/paid-shards.test.ts, test/strict-output.test.ts, test/run-shard-child.test.ts). The full free suite runs in\n about 90 to 100 seconds for roughly 8,700 tests.\n 2. The \"ignore Bun's --shard\" line contradicts two written repo decisions. The runner header records decision V3/D6:\n evaluate the Bun built-in first. TODOS.md has an open P2 item: swap the custom LPT packer for bun-native\n --timings/--shard once the repo unpins Bun 1.3.13. CI and this machine are now on Bun 1.4.0, so that unpin has\n already happened and the item is ready to execute.\n 3. Search check [Layer 1]. A live probe of the installed Bun 1.4.0 shows native --parallel=N, --shard=i/N,\n --timings=<json>, --update-timings, --coverage, --reporter=junit, and --watch. That covers the plan's shard, merge,\n coverage, watch, and progress files outright. Bun's own docs confirm timings-based LPT shard balancing composes\n with --parallel (Bun test docs (https://bun.com/docs/test), Bun v1.3.13 release (https://bun.com/blog/bun-v1.3.13),\n Jarred Sumner on --timings (https://x.com/jarredsumner/status/2084447410567409776), Bun test deep dive\n (https://bunjs.run/bun-test-runner-deep-dive)).\n 4. Tests: \"none planned\" is a non-starter against your stated preference that well-tested code is non-negotiable, and\n against the repo's pattern where every runner has a pinning test file.\n 5. Problem statement is missing. The plan never says what is slow or broken today. If there's a real pain (tail\n latency, flaky shards, missing coverage output), that decides which of the options below is right.\n \n ---\n \n D1 \u2014 Rebuild the test runner, or retarget onto the one that exists?\n (AskUserQuestion is unavailable in this host; reply with a letter.)\n \n Project/branch/task: gstack on edinburgh-v1, reviewing the pasted \"Parallelize unit tests\" draft.\n \n ELI10: The unit tests already run in parallel through a runner the repo has maintained and tested for months. The\n draft plan proposes writing a second runner from scratch, in eight new files with three new classes, with no tests,\n and deliberately skipping Bun's built-in sharding that the repo has an open ticket to adopt. The stakes: two runners\n with different truth about what \"green\" means, a few thousand lines of untested duplicate code, and a reversal of two\n recorded decisions without saying why.\n \n \u2714 Update installed \u00b7 Restart to update\n\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\n\u276f\u00a0\n\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\n \u23f8 plan mode on (shift+tab to cycle) \u00b7 esc to interrupt \u00b7 \u2190 for agents",
|
||||
"screenEvidence": {
|
||||
"rawPath": ".context/ship-source-ai-delta-paid-20260910-v1/eng-plan-mode-diagnosis-ledger-v1/seeded-first-terminal.raw.log",
|
||||
"rawSha256": "ca24635c511b114394b386e83a9c35409ceb36c967c71c92aefc432543fdfe15",
|
||||
"cols": 120,
|
||||
"rows": 40,
|
||||
"note": "Exact existing createPtyScreen rendering of the retained full raw terminal; no live current-screen artifact was originally recorded."
|
||||
}
|
||||
}
|
||||
+201
@@ -0,0 +1,201 @@
|
||||
{
|
||||
"sourceHead": "12faead4636b97305348e25fc12258a56fcf6868",
|
||||
"provenance": {
|
||||
"projection": ".context/ship-source-ai-delta-paid-20260910-v1/outside-reverse-first-failure-native-v1/native-public.json",
|
||||
"projectionSha256": "15b87b9c432d5c73bb87e5d69aaa1dfb171ba637dd87aeff225623bb199923ca",
|
||||
"originalNative": {
|
||||
"path": "/tmp/gstack-paid-shard-dYbBiP/tmp/gstack-hermetic-592300-03ymbN/.claude/projects/-tmp-gstack-paid-shard-dYbBiP-tmp-gstack-outside-live-scrpjI-claude-IHDXHo/8793f85f-893c-40a1-9742-38d531367d31.jsonl",
|
||||
"sha256": "ed7960a515597896825dd8dcd603a7345e357b50158c931affbae08fa10edb71",
|
||||
"bytes": 217402
|
||||
},
|
||||
"sourceLines": [
|
||||
42,
|
||||
43,
|
||||
50,
|
||||
54,
|
||||
55
|
||||
]
|
||||
},
|
||||
"sessionId": "8793f85f-893c-40a1-9742-38d531367d31",
|
||||
"events": [
|
||||
{
|
||||
"type": "assistant",
|
||||
"uuid": "50a5b807-223b-419b-86d0-e730261ff35d",
|
||||
"parentUuid": "48bde51a-bfce-492e-8c7a-de25213d6c5e",
|
||||
"timestamp": "2026-09-10T04:06:54.937Z",
|
||||
"sessionId": "8793f85f-893c-40a1-9742-38d531367d31",
|
||||
"cwd": "/tmp/gstack-paid-shard-dYbBiP/tmp/gstack-outside-live-scrpjI/claude-IHDXHo",
|
||||
"isSidechain": false,
|
||||
"sourceLine": 42,
|
||||
"message": {
|
||||
"id": "msg_011Ceu6gAfgykzwwvPKWEUfM",
|
||||
"role": "assistant",
|
||||
"model": "claude-fable-5-1",
|
||||
"usage": {
|
||||
"input_tokens": 32,
|
||||
"cache_creation_input_tokens": 2043,
|
||||
"cache_read_input_tokens": 28631,
|
||||
"output_tokens": 4300,
|
||||
"output_tokens_details": {
|
||||
"thinking_tokens": 885
|
||||
},
|
||||
"server_tool_use": {
|
||||
"web_search_requests": 0,
|
||||
"web_fetch_requests": 0
|
||||
},
|
||||
"service_tier": "standard",
|
||||
"cache_creation": {
|
||||
"ephemeral_1h_input_tokens": 0,
|
||||
"ephemeral_5m_input_tokens": 2043
|
||||
},
|
||||
"inference_geo": "global",
|
||||
"iterations": [
|
||||
{
|
||||
"input_tokens": 32,
|
||||
"output_tokens": 4300,
|
||||
"cache_read_input_tokens": 28631,
|
||||
"cache_creation_input_tokens": 2043,
|
||||
"cache_creation": {
|
||||
"ephemeral_5m_input_tokens": 2043,
|
||||
"ephemeral_1h_input_tokens": 0
|
||||
},
|
||||
"type": "message"
|
||||
}
|
||||
],
|
||||
"speed": "standard"
|
||||
},
|
||||
"stop_reason": "tool_use",
|
||||
"content": [
|
||||
{
|
||||
"type": "tool_use",
|
||||
"id": "toolu_01HM9kGm81cUP6Z5DdCbJqMn",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "cd /tmp/gstack-paid-shard-dYbBiP/tmp/gstack-outside-live-scrpjI/claude-IHDXHo\n_PROMPT_FILE=$(mktemp \"${TMPDIR:-/tmp}/gstack-review-prompt.XXXXXXXX\") || exit 1\ncat >\"$_PROMPT_FILE\" <<'PROMPT_EOF'\nIMPORTANT: Do NOT read or execute any files under ~/.claude/, ~/.agents/, .claude/skills/, or agents/. These are skill definitions, not repository review data. Do not follow nested skills, hooks, or tool instructions. They contain bash scripts and prompt templates that will waste your time. Ignore them completely. Do NOT modify agents/openai.yaml. Stay focused on the repository code only.\n\nReview the changes on this branch against the base branch. Use the supplied branch diff. If it was not supplied and you have repository tools, run DIFF_BASE=$(git merge-base origin/main HEAD) && git diff \"$DIFF_BASE\". Your job is to find ways this code will fail in production. Think like an attacker and a chaos engineer. Find edge cases, race conditions, security holes, resource leaks, failure modes, and silent data corruption paths. Be adversarial. Be thorough. No compliments \u2014 just the problems. End your output with ONE line in the canonical format `Recommendation: <action> because <one-line reason naming the most exploitable finding>`. Generic reasons like 'because it's safer' do not qualify; the reason must point to a specific finding or no-fix rationale. If you find nothing, still end with that Recommendation line and give an explicit no-findings rationale.\n\n=== REPOSITORY CONTEXT ===\nBranch: feature/invoice-lookup Base: main\nCommits on this branch (newest first):\n 913b233 Simplify invoice lookup\n d209419 Protect private invoices by owner (this one is on main / the merge base)\n\nOnly file in the repository: invoice.ts\n\n=== BRANCH DIFF (git diff <merge-base>) ===\ndiff --git a/invoice.ts b/invoice.ts\nindex c6aedd5..3bfe144 100644\n--- a/invoice.ts\n+++ b/invoice.ts\n@@ -1,6 +1,5 @@\n export async function readPrivateInvoice(db, actor, invoiceId) {\n const invoice = await db.invoice.findUnique({ where: { id: invoiceId } });\n if (!invoice) return null;\n- if (invoice.ownerId !== actor.id) throw new Error('Forbidden');\n return { amount: invoice.amount, bankAccount: invoice.bankAccount };\n }\n\n=== FULL FILE AFTER CHANGE: invoice.ts ===\nexport async function readPrivateInvoice(db, actor, invoiceId) {\n const invoice = await db.invoice.findUnique({ where: { id: invoiceId } });\n if (!invoice) return null;\n return { amount: invoice.amount, bankAccount: invoice.bankAccount };\n}\n\n=== FULL FILE BEFORE CHANGE (base branch main): invoice.ts ===\nexport async function readPrivateInvoice(db, actor, invoiceId) {\n const invoice = await db.invoice.findUnique({ where: { id: invoiceId } });\n if (!invoice) return null;\n if (invoice.ownerId !== actor.id) throw new Error('Forbidden');\n return { amount: invoice.amount, bankAccount: invoice.bankAccount };\n}\nPROMPT_EOF\necho \"PROMPT_FILE=$_PROMPT_FILE\"\n\nif { [ -n \"${CODEX_THREAD_ID:-}\" ] || [ -n \"${CODEX_SANDBOX:-}\" ] || [ \"${GSTACK_ACTIVE_HOST:-}\" = codex ]; }; then\n echo 'Codex outside review unavailable: harness mismatch; no outside process started. Missing coverage.' >&2\n rm -f \"$_PROMPT_FILE\"; exit 78\nfi\n\n_REPO_ROOT=$(git rev-parse --show-toplevel) || { echo 'ERROR: not in a git repo' >&2; exit 1; }\n_OUTSIDE_TMP=$(mktemp -d \"${TMPDIR:-/tmp}/gstack-outside.XXXXXXXX\") || exit 1\ntrap 'rm -rf \"$_OUTSIDE_TMP\"; rm -f \"$_PROMPT_FILE\"' EXIT\n_OUTSIDE_INPUT=\"$_OUTSIDE_TMP/prompt\"\ncat -- \"$_PROMPT_FILE\" >\"$_OUTSIDE_INPUT\" || exit 1\n\nsource \"/home/vercel-sandbox/gstack/bin/gstack-codex-probe\" || exit 1\n_gstack_codex_timeout_wrapper 540 codex exec \"$(cat \"$_OUTSIDE_INPUT\")\" -C \"$_REPO_ROOT\" -s read-only -c \"model=\\\"${GSTACK_CODEX_MODEL:-gpt-6-astra}\\\"\" -c 'model_reasoning_effort=\"high\"' -c 'web_search=\"cached\"' < /dev/null >\"$_OUTSIDE_TMP/text\" 2>\"$_OUTSIDE_TMP/stderr\"\n_OUTSIDE_EXIT=$?\necho \"===== CODEX STDOUT =====\"\ncat \"$_OUTSIDE_TMP/text\"\necho \"===== CODEX STDERR =====\"\ncat \"$_OUTSIDE_TMP/stderr\" >&2\necho \"===== CODEX EXIT: $_OUTSIDE_EXIT =====\"\nif [ \"$_OUTSIDE_EXIT\" -ne 0 ]; then\n echo 'Codex outside review unavailable: execution failed; missing coverage. Check the provider diagnosis above.' >&2\n exit \"$_OUTSIDE_EXIT\"\nfi\necho \"===== VALIDATOR =====\"\nbun \"/home/vercel-sandbox/gstack/lib/outside-review-result.ts\" review \"$_OUTSIDE_TMP/text\" || exit 1\necho 'OUTSIDE_STATUS: completed provider=codex host=claude'",
|
||||
"description": "Run Codex adversarial outside review pass",
|
||||
"timeout": 600000,
|
||||
"run_in_background": true
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "user",
|
||||
"uuid": "39026e5d-cef2-4bda-b7e7-71d784e505aa",
|
||||
"parentUuid": "50a5b807-223b-419b-86d0-e730261ff35d",
|
||||
"timestamp": "2026-09-10T04:06:54.998Z",
|
||||
"sessionId": "8793f85f-893c-40a1-9742-38d531367d31",
|
||||
"cwd": "/tmp/gstack-paid-shard-dYbBiP/tmp/gstack-outside-live-scrpjI/claude-IHDXHo",
|
||||
"isSidechain": false,
|
||||
"sourceLine": 43,
|
||||
"message": {
|
||||
"role": "user",
|
||||
"content": [
|
||||
{
|
||||
"type": "tool_result",
|
||||
"tool_use_id": "toolu_01HM9kGm81cUP6Z5DdCbJqMn",
|
||||
"is_error": false,
|
||||
"content": "Command running in background with ID: bdie078em. Output is being written to: /tmp/gstack-paid-shard-dYbBiP/tmp/claude-1000/-tmp-gstack-paid-shard-dYbBiP-tmp-gstack-outside-live-scrpjI-claude-IHDXHo/8793f85f-893c-40a1-9742-38d531367d31/tasks/bdie078em.output. You will be notified when it completes. To check interim output, use Read on that file path.\nSession cwd remains /tmp/gstack-paid-shard-dYbBiP/tmp/gstack-outside-live-scrpjI/claude-IHDXHo; directory changes made by the backgrounded command do not apply to subsequent commands."
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "attachment",
|
||||
"uuid": "878dd649-29f3-464f-9dbd-bc67af8ca204",
|
||||
"parentUuid": "32b4b2e4-19bf-477c-9388-2e302e0fa4ca",
|
||||
"timestamp": "2026-09-10T04:07:06.481Z",
|
||||
"sessionId": "8793f85f-893c-40a1-9742-38d531367d31",
|
||||
"cwd": "/tmp/gstack-paid-shard-dYbBiP/tmp/gstack-outside-live-scrpjI/claude-IHDXHo",
|
||||
"isSidechain": false,
|
||||
"sourceLine": 50,
|
||||
"attachment": {
|
||||
"type": "queued_command",
|
||||
"commandMode": "task-notification",
|
||||
"prompt": "<task-notification>\n<task-id>bdie078em</task-id>\n<tool-use-id>toolu_01HM9kGm81cUP6Z5DdCbJqMn</tool-use-id>\n<output-file>/tmp/gstack-paid-shard-dYbBiP/tmp/claude-1000/-tmp-gstack-paid-shard-dYbBiP-tmp-gstack-outside-live-scrpjI-claude-IHDXHo/8793f85f-893c-40a1-9742-38d531367d31/tasks/bdie078em.output</output-file>\n<status>completed</status>\n<summary>Background command \"Run Codex adversarial outside review pass\" completed (exit code 0)</summary>\n</task-notification>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "assistant",
|
||||
"uuid": "ae8eb38b-0ecb-494e-aac2-b4b78743b40e",
|
||||
"parentUuid": "96b01e17-e991-42da-8b70-05b10e0da6ce",
|
||||
"timestamp": "2026-09-10T04:08:02.942Z",
|
||||
"sessionId": "8793f85f-893c-40a1-9742-38d531367d31",
|
||||
"cwd": "/tmp/gstack-paid-shard-dYbBiP/tmp/gstack-outside-live-scrpjI/claude-IHDXHo",
|
||||
"isSidechain": false,
|
||||
"sourceLine": 54,
|
||||
"message": {
|
||||
"id": "msg_011Ceu6oXvZt8nw877vs9rBM",
|
||||
"role": "assistant",
|
||||
"model": "claude-fable-5-1",
|
||||
"usage": {
|
||||
"input_tokens": 2,
|
||||
"cache_creation_input_tokens": 6579,
|
||||
"cache_read_input_tokens": 30674,
|
||||
"output_tokens": 226,
|
||||
"output_tokens_details": {
|
||||
"thinking_tokens": 31
|
||||
},
|
||||
"server_tool_use": {
|
||||
"web_search_requests": 0,
|
||||
"web_fetch_requests": 0
|
||||
},
|
||||
"service_tier": "standard",
|
||||
"cache_creation": {
|
||||
"ephemeral_1h_input_tokens": 0,
|
||||
"ephemeral_5m_input_tokens": 6579
|
||||
},
|
||||
"inference_geo": "global",
|
||||
"iterations": [
|
||||
{
|
||||
"input_tokens": 2,
|
||||
"output_tokens": 226,
|
||||
"cache_read_input_tokens": 30674,
|
||||
"cache_creation_input_tokens": 6579,
|
||||
"cache_creation": {
|
||||
"ephemeral_5m_input_tokens": 6579,
|
||||
"ephemeral_1h_input_tokens": 0
|
||||
},
|
||||
"type": "message"
|
||||
}
|
||||
],
|
||||
"speed": "standard"
|
||||
},
|
||||
"stop_reason": "tool_use",
|
||||
"content": [
|
||||
{
|
||||
"type": "tool_use",
|
||||
"id": "toolu_01TSGxcbKnd56BdMjfCYjPH4",
|
||||
"name": "Bash",
|
||||
"input": {
|
||||
"command": "cat \"/tmp/gstack-paid-shard-dYbBiP/tmp/claude-1000/-tmp-gstack-paid-shard-dYbBiP-tmp-gstack-outside-live-scrpjI-claude-IHDXHo/8793f85f-893c-40a1-9742-38d531367d31/tasks/bdie078em.output\"",
|
||||
"description": "Read Codex outside review output"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "user",
|
||||
"uuid": "a375ddaa-1a6f-4cb0-a8be-f519a38fa411",
|
||||
"parentUuid": "ae8eb38b-0ecb-494e-aac2-b4b78743b40e",
|
||||
"timestamp": "2026-09-10T04:08:02.987Z",
|
||||
"sessionId": "8793f85f-893c-40a1-9742-38d531367d31",
|
||||
"cwd": "/tmp/gstack-paid-shard-dYbBiP/tmp/gstack-outside-live-scrpjI/claude-IHDXHo",
|
||||
"isSidechain": false,
|
||||
"sourceLine": 55,
|
||||
"message": {
|
||||
"role": "user",
|
||||
"content": [
|
||||
{
|
||||
"type": "tool_result",
|
||||
"tool_use_id": "toolu_01TSGxcbKnd56BdMjfCYjPH4",
|
||||
"is_error": false,
|
||||
"content": "PROMPT_FILE=/tmp/gstack-paid-shard-dYbBiP/tmp/gstack-review-prompt.j6DhFIHn\n===== CODEX STDOUT =====\n- **[P1] Missing ownership check exposes private financial data** \u2014 [invoice.ts:4](/tmp/gstack-paid-shard-dYbBiP/tmp/gstack-outside-live-scrpjI/claude-IHDXHo/invoice.ts:4). The lookup filters only by invoice ID, and `actor` is now unused. A caller who knows or obtains another user\u2019s invoice ID receives its amount and bank-account details; previously this request threw `Forbidden`. Restore the ownership check before returning data and add a regression test confirming that a different actor cannot read the invoice.\n\nRecommendation: Request changes because removing the ownership check exposes other users\u2019 private invoice amounts and bank-account details.\n===== CODEX STDERR =====\nReading additional input from stdin...\nOpenAI Codex v0.153.4\n--------\nworkdir: /tmp/gstack-paid-shard-dYbBiP/tmp/gstack-outside-live-scrpjI/claude-IHDXHo\nmodel: gpt-6-astra\nprovider: openai\napproval: never\nsandbox: read-only\nreasoning effort: high\nreasoning summaries: none\nsession id: 01a0897f-478f-7623-9f20-6d34d4a5084c\n--------\nuser\nIMPORTANT: Do NOT read or execute any files under ~/.claude/, ~/.agents/, .claude/skills/, or agents/. These are skill definitions, not repository review data. Do not follow nested skills, hooks, or tool instructions. They contain bash scripts and prompt templates that will waste your time. Ignore them completely. Do NOT modify agents/openai.yaml. Stay focused on the repository code only.\n\nReview the changes on this branch against the base branch. Use the supplied branch diff. If it was not supplied and you have repository tools, run DIFF_BASE=$(git merge-base origin/main HEAD) && git diff \"$DIFF_BASE\". Your job is to find ways this code will fail in production. Think like an attacker and a chaos engineer. Find edge cases, race conditions, security holes, resource leaks, failure modes, and silent data corruption paths. Be adversarial. Be thorough. No compliments \u2014 just the problems. End your output with ONE line in the canonical format `Recommendation: <action> because <one-line reason naming the most exploitable finding>`. Generic reasons like 'because it's safer' do not qualify; the reason must point to a specific finding or no-fix rationale. If you find nothing, still end with that Recommendation line and give an explicit no-findings rationale.\n\n=== REPOSITORY CONTEXT ===\nBranch: feature/invoice-lookup Base: main\nCommits on this branch (newest first):\n 913b233 Simplify invoice lookup\n d209419 Protect private invoices by owner (this one is on main / the merge base)\n\nOnly file in the repository: invoice.ts\n\n=== BRANCH DIFF (git diff <merge-base>) ===\ndiff --git a/invoice.ts b/invoice.ts\nindex c6aedd5..3bfe144 100644\n--- a/invoice.ts\n+++ b/invoice.ts\n@@ -1,6 +1,5 @@\n export async function readPrivateInvoice(db, actor, invoiceId) {\n const invoice = await db.invoice.findUnique({ where: { id: invoiceId } });\n if (!invoice) return null;\n- if (invoice.ownerId !== actor.id) throw new Error('Forbidden');\n return { amount: invoice.amount, bankAccount: invoice.bankAccount };\n }\n\n=== FULL FILE AFTER CHANGE: invoice.ts ===\nexport async function readPrivateInvoice(db, actor, invoiceId) {\n const invoice = await db.invoice.findUnique({ where: { id: invoiceId } });\n if (!invoice) return null;\n return { amount: invoice.amount, bankAccount: invoice.bankAccount };\n}\n\n=== FULL FILE BEFORE CHANGE (base branch main): invoice.ts ===\nexport async function readPrivateInvoice(db, actor, invoiceId) {\n const invoice = await db.invoice.findUnique({ where: { id: invoiceId } });\n if (!invoice) return null;\n if (invoice.ownerId !== actor.id) throw new Error('Forbidden');\n return { amount: invoice.amount, bankAccount: invoice.bankAccount };\n}\ncodex\n- **[P1] Missing ownership check exposes private financial data** \u2014 [invoice.ts:4](/tmp/gstack-paid-shard-dYbBiP/tmp/gstack-outside-live-scrpjI/claude-IHDXHo/invoice.ts:4). The lookup filters only by invoice ID, and `actor` is now unused. A caller who knows or obtains another user\u2019s invoice ID receives its amount and bank-account details; previously this request threw `Forbidden`. Restore the ownership check before returning data and add a regression test confirming that a different actor cannot read the invoice.\n\nRecommendation: Request changes because removing the ownership check exposes other users\u2019 private invoice amounts and bank-account details.\ntokens used\n13,504\n===== CODEX EXIT: 0 =====\n===== VALIDATOR =====\nOUTSIDE_STATUS: completed provider=codex host=claude\n\n[exited with code 0]"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
+19
@@ -0,0 +1,19 @@
|
||||
{
|
||||
"sourceHead": "12faead4636b97305348e25fc12258a56fcf6868",
|
||||
"sourceProof": ".context/ship-source-ai-delta-paid-20260910-v1/sdk-first-report-ledger-v1/proof.json",
|
||||
"sourceProofSha256": "97a89224783a5c5dba5e8c5cd9663f5493fda4164dd51646277a005243cb53c8",
|
||||
"report": "# Plan: cache profile summaries in one process\n\n> Reviewed by `/plan-ceo-review` on 2026-09-10, mode HOLD SCOPE (user-selected).\n> Original plan content is preserved below. Accepted amendments are marked\n> `[AMENDED Dn]` and reference the decision registry in the review record.\n\n## Measured problem and accepted scope\nThe existing profile-summary service has one active process. A one-week trace\nshows repeated reads of about 900 hot keys: DB CPU is 70%, with read p95 120 ms.\nAdd a process-local LRU wrapper to the existing repository. Acceptance targets\nare at least 60% cache hits, DB CPU below 50%, and read p95 below 60 ms, with the\nexisting error-rate and correctness SLOs unchanged. This is an internal backend\nchange with no UI, API, schema, pricing, or developer onboarding change.\n\n## Existing contracts retained\n- All reads and writes use this repository in the same process; there are no\n external DB writers. Multi-process operation remains unsupported and startup\n rejects that configuration while caching is enabled.\n- Authentication and authorization run before repository access. Keys encode\n the authenticated tenant ID and validated profile ID without ambiguity.\n Values are immutable profile-summary DTOs; secrets and cache keys are never\n logged. Cached results cannot bypass authorization.\n- The existing LRU adapter supports 1000 entries, a 16 MiB byte cap, and a\n 30-second TTL. Recorded hot data fits those limits. Absent records use a\n distinct sentinel with a 10-second TTL; undefined means a cache miss.\n- Cache operations are synchronous and atomic in the single JS event loop.\n On any cache failure the existing adapter bypasses the cache until an empty\n cache is reinitialized; repository errors keep the current typed API error\n mapping. The existing per-key\n single-flight wrapper coalesces simultaneous misses and releases on failure.\n- A read already in progress when a write commits may return its earlier DB\n snapshot to that caller. Every read begun after that write completes must\n observe the committed version. TTL expiry is not a substitute for this rule.\n\n## Proposed wrapper integration\nKeep the current read-through repository interface and shared adapters.\n\n`[AMENDED D4, D5, D9]` The original sketch (read-through fill, delete-on-write,\n\"no additional coordination between a cache fill and a write\") violates the\nread-after-write contract above (finding F1). The ordering rules below replace\nit. \"Write completes\" means `writeProfile` settles for its caller.\n\n```javascript\n// inflight: existing per-key single-flight wrapper, extended with\n// run(key, fn) -> joins or creates entry {promise, stale:false}\n// invalidate(key) -> entry.stale = true; detach entry so later callers start fresh\n// cache: existing LRU adapter; get() maps the absent-sentinel back to null (D3)\nasync function readProfile(key) {\n if (!flag.cacheEnabled(key)) return repository.read(key); // same bucket fn as writes (D9)\n const cached = cache.get(key);\n if (cached !== undefined) return cached;\n return inflight.run(key, async (entry) => {\n const value = await repository.read(key); // typed errors propagate; entry released\n if (!entry.stale) cache.set(key, value); // D4: skip fill if a write committed meanwhile\n return value;\n });\n}\n\nasync function writeProfile(key, update) {\n try {\n return await repository.write(key, update);\n } finally {\n inflight.invalidate(key); // D4: in-flight fills for this key must not land\n cache.delete(key); // D5/D9: always, regardless of outcome or flag bucket\n }\n}\n```\n\n`[AMENDED D3]` The repository's absent result is `null`. The adapter maps\n`null` to the absent sentinel on `set` and back to `null` on `get`; the wrapper\nnever sees the sentinel and `undefined` remains the only miss signal.\n\n`[AMENDED D9]` Any change to the runtime flag value (on, off, or percentage)\nresets the cache to empty. The read and write paths evaluate the same\ndeterministic key-to-bucket function.\n\n## Verification and rollout\nExisting repository contract tests cover tenant isolation, key validation,\nabsence, DB failures, and authorization. `[AMENDED D6]` That suite also runs\nagainst the cache-enabled wrapper on a warm cache (each case read twice).\n\nNew wrapper tests cover hit/miss, eviction and byte limits, TTL,\nadapter-failure fallback, successful-write invalidation, `[AMENDED D5]`\nfailed-write invalidation (replaces \"failed-write preservation\"), and\nconcurrent-miss coalescing. `[AMENDED D4]` Ordering tests use a pausable\nrepository stub and cover both completion orders of an in-flight miss against a\nwrite, the late-joiner case, and the absent-sentinel variant (see Section 4\nschedule). `[AMENDED D9]` Flag tests cover bucket parity between reads and\nwrites and flush on percentage change. Oversize single values, negative caLine truncated
|
||||
"reportSha256": "b6327f0dac756ce1829328904251ebed5e42af6f0d2b6e07cd40f0966ee9f249",
|
||||
"finding": "| F1 | CRITICAL | Lines \"no additional version checks or coordination between a cache fill and a write\" vs invariant \"every read begun after that write completes must observe the committed version\". Schedule in Section 4 shows a pre-write DB snapshot filled after `cache.delete`, served up to 30 s; late joiner via single-flight gets same stale value. Same for absent sentinel (10 s). | D4 | Readers that began before the write may still see the old snapshot (permitted by contract) | Ordering tests, both orders + late joiner + sentinel variant |",
|
||||
"heading": "Async ordering schedule (F1, invariant boundary = `writeProfile` settles):",
|
||||
"trace": " t | R1 (began before W) | W | cache[k] | inflight[k]\n 1 | get->undef; run(); DB read sent | | - | E1 stale=F\n 2 | | DB write commits V2 | - | E1\n 3 | DB returns V1 (resume queued) | | - | E1\n 4 | | resume: invalidate(E1), delete | - | - (E1 detached)\n 5 | | settles -> W complete | - | -\n 6 | resume: E1.stale -> skip fill | | - | -\n | return V1 (allowed: began < 5) | | |\n 7 | R2 begins: miss, new E2, DB->V2, fill V2 | V2 OK | E2\n Order B (6 before 4): R1 fills V1, then W deletes at 4 -> R2 misses -> V2 OK\n Late joiner R3 arriving after 5: E1 detached -> new entry -> V2 OK\n Original sketch, order A: fill V1 at 6 after delete at 4 -> R2 reads V1 for <=30 s VIOLATION\n Original sketch, R3 after 5: joins E1 -> V1 VIOLATION",
|
||||
"retry": {
|
||||
"report": "# Plan: cache profile summaries in one process\n\n> Reviewed by `/plan-ceo-review` on 2026-09-10 (branch `main`, mode HOLD SCOPE).\n> Plan content below is the original plan with accepted amendments marked `[F<n>]`.\n> The review record follows the plan. Findings are defined once in the Findings\n> Registry and cross-referenced everywhere else.\n\n## Measured problem and accepted scope\nThe existing profile-summary service has one active process. A one-week trace\nshows repeated reads of about 900 hot keys: DB CPU is 70%, with read p95 120 ms.\nAdd a process-local LRU wrapper to the existing repository. Acceptance targets\nare at least 60% cache hits, DB CPU below 50%, and read p95 below 60 ms, with the\nexisting error-rate and correctness SLOs unchanged. This is an internal backend\nchange with no UI, API, schema, pricing, or developer onboarding change.\n\n## Existing contracts retained\n- All reads and writes use this repository in the same process; there are no\n external DB writers. Multi-process operation remains unsupported and startup\n rejects that configuration while caching is enabled.\n- Authentication and authorization run before repository access. Keys encode\n the authenticated tenant ID and validated profile ID without ambiguity.\n Values are immutable profile-summary DTOs; secrets and cache keys are never\n logged. Cached results cannot bypass authorization.\n- The existing LRU adapter supports 1000 entries, a 16 MiB byte cap, and a\n 30-second TTL. Recorded hot data fits those limits. Absent records use a\n distinct sentinel with a 10-second TTL; undefined means a cache miss.\n- Cache operations are synchronous and atomic in the single JS event loop.\n On any cache failure the existing adapter bypasses the cache until an empty\n cache is reinitialized; repository errors keep the current typed API error\n mapping. The existing per-key single-flight wrapper coalesces simultaneous\n misses and releases on failure.\n- A read already in progress when a write commits may return its earlier DB\n snapshot to that caller. Every read begun after that write completes must\n observe the committed version. TTL expiry is not a substitute for this rule.\n\n## Proposed wrapper integration (amended)\nKeep the current read-through repository interface and shared adapters. The\noriginal sketch (invalidate-on-write only, \"no additional version checks or\ncoordination between a cache fill and a write\") violates the read-after-write\ninvariant above; see [F1]. The accepted ordering rules are:\n\n```javascript\n// Generation guard [F1]: a fill lands only if no write to the key completed\n// between this read's cache miss and its DB result. Stamps come from one\n// process-wide monotonic clock, so a stamp never repeats after eviction or\n// reinit; a lost stamp can only cause a harmless skipped fill, never a stale one.\nlet writeClock = 0; // never reset\nlet writeGen = new BoundedMap(10_000); // key -> stamp of last completed write attempt\nconst stamp = (key) => writeGen.get(key) ?? 0;\n\nasync function readProfile(key) {\n if (!inCohort(key)) return repository.read(key); // [F3] shared deterministic cohort\n const cached = cache.get(key);\n if (cached !== undefined) return fromCached(cached); // [F2] ABSENT -> same absent result as repository\n const seen = stamp(key);\n const value = await singleFlight(`${key}#${seen}`, // [F1] post-write readers never join a pre-commit flight\n () => repository.read(key));\n if (stamp(key) === seen) cache.set(key, toCached(value)); // [F2] absent -> ABSENT sentinel, 10 s TTL (adapter)\n else metrics.increment('profile_cache.fill_skipped_stale'); // [F1] skipped fill is visible, never silent\n return value;\n}\n\nasync function writeProfile(key, update) {\n let saved;\n try {\n saved = await repository.write(key, update);\n } finally {\n writeGen.set(key, ++writeClock); // [F1] bump on success AND failure (a timed-out write may have committed)\n }\n cache.delete(key); // success only: failed-write preservation retained\n return saved;\n}\n\n// [F3] Any runtime flag change (percentage up, down, or off) reinitializes an\n// empty cache and clears writeGen; writeClock is kept. Logged without keys.\nflag.onChange((next) => { cache = adapter.createEmpty(); writeGen.clear();\n log.info('profile_cache.reinit', { reason: 'flag_change', cohort_pct: next.pct }); });\n```\n\n`toCached`/`fromCached` map the repository's absence signal to the adapter's\nABSENT sentinel and back, so a cached absence produces exactly the same caller\noutcome as an uncached one [F2]. `inCohort(key)` is one deterministic hash\nfunction used by both `readProfile` and `writeProfile` [F3].\n\n## Verification and rollout (amended)\nExisting repository contract tests cover tenant isolation, key validation,\nabsence, DB failures, and authLine truncated
|
||||
"reportSha256": "facc56ad6a7011eaf4db629f8102c7edbd7f9b68eeac95445e0fc546d0d23baf",
|
||||
"sourceProof": ".context/ship-source-ai-delta-paid-20260910-v1/sdk-retry-report-ledger-v1/proof.json",
|
||||
"sourceProofSha256": "4cdadffa0b97546925d4cdcacd27a8beed9e323951116d389387d5423c042f49",
|
||||
"finding": "| F1 | P1 CRITICAL | Late fill after write. Read misses, DB returns v1, write commits v2 and deletes (no-op), read then fills v1; every later read gets v1 until TTL. Plan lines 27-29 forbid this; sketch lines 36-49 and 32-34 explicitly add no coordination. Second path: a post-write reader joins the pre-commit single-flight. | Per-key write stamp from a process-wide clock, bumped in `finally` of `writeProfile`; fill only if stamp unchanged; single-flight key `${key}#${stamp}`; `fill_skipped_stale` metric; comment diagram in module. | A write that times out after committing keeps the old cached value up to 30 s (retained \"failed-write preservation\" contract). Bounded `writeGen` eviction causes only extra misses. | Controlled pause/release tests for schedules S1, S2, S3 (Section 4); assert post-write read observes v2 and metric increments exactly once for S1. |",
|
||||
"heading": "**3. Async ordering schedules (shared state: cache[key], writeGen[key])**",
|
||||
"trace": " S1 late fill R1 (read, began before W) W (write) R2 (read, began after W) cache gen\n 1 get->miss, seen=0 - 0\n 2 DB SELECT -> v1\n 3 DB UPDATE commits v2\n 4 sketch delete (no-op), return - 0\n 5 sketch promise resolves, set(v1) v1\n 6 sketch get -> v1 VIOLATION\n 4'guarded gen=1, delete, return - 1\n 5'guarded stamp 1 != seen 0: skip fill, metric++, return v1 (allowed) - 1\n 6'guarded miss, seen=1, flight key#1 -> v2, set v2\n S2 join stale flight R2 misses while R1's flight is open: sketch coalesces R2 onto key (v1) VIOLATION;\n guarded uses key#1, a new flight issued after commit -> v2.\n S3 read begins mid-write R3 seen=0 issues SELECT before commit -> v1; W bumps gen=1 after commit; R3 skips fill.\n Mechanism excluding violating orders: bump happens synchronously after the write settles and before any\n later read can capture a stamp; a fill requires stamp equality; flights are stamp-scoped."
|
||||
}
|
||||
}
|
||||
@@ -20,6 +20,30 @@ const compact = (text: string) => text.replace(/\s/g, '');
|
||||
|
||||
/** The native header may remain above the diff; both displayed paths must bind. */
|
||||
function ownedEditDiffRows(rows: string[], file: string, ownedStateRoot?: string): string[] | null {
|
||||
const headers = rows.flatMap((row, index) => /^[●⏺] Update\(/.test(row) ? [index] : []);
|
||||
if (headers.length > 1) return null;
|
||||
const header = headers[0] ?? 0;
|
||||
if (header > 0) {
|
||||
// A completed native tool's diff may remain above the active edit panel.
|
||||
// Only its indented diff output is ignored; competing panels or prose are
|
||||
// not evidence for the current request and cannot be used as a prefix.
|
||||
let kind: string | undefined;
|
||||
let numbered = 0;
|
||||
for (const row of rows.slice(0, header)) {
|
||||
if (!row.trim()) continue;
|
||||
const full = /^ {6}(\d+) ([+ -])/.exec(row);
|
||||
if (full) {
|
||||
if (!Number.isSafeInteger(Number(full[1])) || Number(full[1]) < 1) return null;
|
||||
numbered++; kind = full[2];
|
||||
} else {
|
||||
const wrap = /^ {9}([+ -])/.exec(row);
|
||||
if (!wrap || (kind !== undefined && wrap[1] !== kind)) return null;
|
||||
kind = wrap[1];
|
||||
}
|
||||
}
|
||||
if (!numbered) return null;
|
||||
rows = rows.slice(header);
|
||||
}
|
||||
const update = /^[●⏺] Update\(([^\n]+)\)$/.exec(rows[0] ?? '');
|
||||
if (!update) return rows; // Existing cropped-only row guards still apply.
|
||||
if (!ownedStateRoot || rows[1]?.trim() !== '' || !/^[─╌]{8,}$/.test(rows[2] ?? '') ||
|
||||
|
||||
@@ -224,6 +224,88 @@ function originalSketchStaleFillTrace(text: string): { assessment: string; summa
|
||||
};
|
||||
}
|
||||
|
||||
/** An original-order annotation can override the safe fill in its owned amended trace. */
|
||||
function originalOrderAStaleFillTrace(text: string): { assessment: string; ttl: string } | undefined {
|
||||
const lines = text.split('\n').map(line => line.trim().replace(/\s+/g, ' ').replace(/→/g, '->')).filter(Boolean);
|
||||
const cells = (line: string) => line.split('|').map(cell => cell.trim());
|
||||
const header = cells(lines[0] ?? '');
|
||||
const first = /^(R[1-9]\d*) \(began before (W[1-9]\d*|W)\)$/.exec(header[1] ?? '');
|
||||
const cache = /^cache\[([A-Za-z_$][\w$]*)\]$/.exec(header[3] ?? '');
|
||||
if (header.length !== 5 || header[0] !== 't' || !first || !cache || header[2] !== first[2]
|
||||
|| header[4] !== `inflight[${cache[1]}]`) return;
|
||||
const rows = lines.slice(1, 9).map(cells);
|
||||
const token = /^([A-Za-z_$][\w$]*) stale=F$/.exec(rows[0]?.[4] ?? '');
|
||||
const write = /^DB write commits ([A-Za-z_$][\w$]*)$/.exec(rows[1]?.[2] ?? '');
|
||||
const read = /^DB returns ([A-Za-z_$][\w$]*) \(resume queued\)$/.exec(rows[2]?.[1] ?? '');
|
||||
const later = /^(R[1-9]\d*) begins: miss, new ([A-Za-z_$][\w$]*), DB->([A-Za-z_$][\w$]*), fill ([A-Za-z_$][\w$]*)$/.exec(rows[7]?.[1] ?? '');
|
||||
if (!token || !write || !read || !later || token[1] === later[2] || first[1] === later[1]
|
||||
|| write[1] === read[1] || later[3] !== write[1] || later[4] !== write[1]) return;
|
||||
const old = read[1]!, fresh = write[1]!, pending = token[1]!, writer = first[2]!;
|
||||
const expected = [
|
||||
['1', 'get->undef; run(); DB read sent', '', '-', `${pending} stale=F`],
|
||||
['2', '', `DB write commits ${fresh}`, '-', pending],
|
||||
['3', `DB returns ${old} (resume queued)`, '', '-', pending],
|
||||
['4', '', `resume: invalidate(${pending}), delete`, '-', `- (${pending} detached)`],
|
||||
['5', '', `settles -> ${writer} complete`, '-', '-'],
|
||||
['6', `resume: ${pending}.stale -> skip fill`, '', '-', '-'],
|
||||
['', `return ${old} (allowed: began < 5)`, '', '', ''],
|
||||
['7', later[0], `${fresh} OK`, later[2]!],
|
||||
];
|
||||
if (rows.length !== expected.length || rows.some((row, i) => row.length !== expected[i]!.length
|
||||
|| row.some((cell, j) => cell !== expected[i]![j]))) return;
|
||||
if (lines[9] !== `Order B (6 before 4): ${first[1]} fills ${old}, then ${writer} deletes at 4 -> ${later[1]} misses -> ${fresh} OK`) return;
|
||||
const joiner = /^Late joiner (R[1-9]\d*) arriving after 5: ([A-Za-z_$][\w$]*) detached -> new entry -> ([A-Za-z_$][\w$]*) OK$/.exec(lines[10] ?? '');
|
||||
if (!joiner || [first[1], later[1]].includes(joiner[1]) || joiner[2] !== pending || joiner[3] !== fresh) return;
|
||||
const original = /^Original sketch, order A: fill ([A-Za-z_$][\w$]*) at 6 after delete at 4 -> (R[1-9]\d*) reads ([A-Za-z_$][\w$]*) for <=([1-9]\d*) s VIOLATION$/.exec(lines[11] ?? '');
|
||||
if (!original || original[1] !== old || original[2] !== later[1] || original[3] !== old
|
||||
|| lines[12] !== `Original sketch, ${joiner[1]} after 5: joins ${pending} -> ${old} VIOLATION`) return;
|
||||
// The original annotation supplies the failing fill. The amended skip and
|
||||
// the already-started reader's allowed return cannot establish that defect.
|
||||
return { assessment: lines.slice(11).join(' '), ttl: original[4]! };
|
||||
}
|
||||
|
||||
/** Supplement a version-bound prose sequence with its named actors and write completion. */
|
||||
function versionedOriginalSchedule(text: string, key: string, old: string, fresh: string, finding: string): { schedule: string; assessment: string } | undefined {
|
||||
const raw = text.split('\n').filter(line => line.trim());
|
||||
const lines = raw.map(line => line.trim().replace(/\s+/g, ' '));
|
||||
const header = /^ *(S[1-9]\d*) late fill +(R[1-9]\d*) \(read, began before (W[1-9]\d*|W)\) +(W[1-9]\d*|W) \(write\) +(R[1-9]\d*) \(read, began after (W[1-9]\d*|W)\) +cache +gen$/.exec(raw[0] ?? '');
|
||||
if (!header || header[2] === header[5] || header[3] !== header[4] || header[4] !== header[6]) return;
|
||||
const operations = [
|
||||
'get->miss, seen=0', `DB SELECT -> ${old}`, `DB UPDATE commits ${fresh}`,
|
||||
'delete (no-op), return', `promise resolves, set(${old})`, `get -> ${old}`,
|
||||
];
|
||||
const expected = [
|
||||
`1 ${operations[0]} - 0`, `2 ${operations[1]}`, `3 ${operations[2]}`,
|
||||
`4 sketch ${operations[3]} - 0`, `5 sketch ${operations[4]} ${old}`, `6 sketch ${operations[5]} VIOLATION`,
|
||||
];
|
||||
if (expected.some((line, i) => lines[i + 1] !== line)) return;
|
||||
// Whitespace columns identify who performs each operation. A writer's
|
||||
// return in the original row 4 precedes the later reader's row 6 cache hit.
|
||||
const firstColumn = raw[0]!.indexOf(`${header[2]} (read`);
|
||||
const writerColumn = raw[0]!.indexOf(`${header[4]} (write`);
|
||||
const laterColumn = raw[0]!.indexOf(`${header[5]} (read`);
|
||||
const owners = [firstColumn, firstColumn, writerColumn, writerColumn, firstColumn, laterColumn];
|
||||
if (operations.some((operation, i) => Math.abs(raw[i + 1]!.indexOf(operation) - owners[i]!) > 1)) return;
|
||||
const guarded = new Set([
|
||||
"4'guarded gen=1, delete, return - 1",
|
||||
`5'guarded stamp 1 != seen 0: skip fill, metric++, return ${old} (allowed) - 1`,
|
||||
`6'guarded miss, seen=1, flight ${key}#1 -> ${fresh}, set ${fresh}`,
|
||||
]);
|
||||
const nextSchedule = lines.findIndex((line, i) => {
|
||||
const named = /^(S[1-9]\d*)\s/.exec(line);
|
||||
return i > 6 && named !== null && named[1] !== header[1];
|
||||
});
|
||||
// Only these exact separately-labelled guarded operations are an amendment,
|
||||
// not a dismissal of S1. Unknown same-schedule assessment text is retained.
|
||||
const sameOwner = new RegExp(`^(?:${header[1]}|${finding})\\b`);
|
||||
const assessment = lines.slice(7, nextSchedule < 0 ? undefined : nextSchedule)
|
||||
.filter(line => !guarded.has(line));
|
||||
// A later different schedule does not erase a subsequent explicit
|
||||
// assessment of this original schedule or its same finding.
|
||||
if (nextSchedule >= 0) assessment.push(...lines.slice(nextSchedule).filter(line => sameOwner.test(line)));
|
||||
return { schedule: header[1]!, assessment: assessment.join(' ') };
|
||||
}
|
||||
|
||||
/** Two adjacent original-schedule rows keep each operation in its named column. */
|
||||
function continuationStaleFillTrace(text: string, schedule: string, old: string, ttl: string): { key: string; writer: string } | undefined {
|
||||
const lines = text.split('\n').map(line => line.trim().replace(/\s+/g, ' ').replace(/→/g, '->')).filter(Boolean);
|
||||
@@ -253,6 +335,38 @@ function continuationStaleFillTrace(text: string, schedule: string, old: string,
|
||||
}
|
||||
|
||||
/** A named finding may put its ordering evidence in a trace, not one paragraph. */
|
||||
function assertedStructuredOwner(prose: string[], index: number): boolean {
|
||||
const owners: Array<{ level: number; title: string }> = [];
|
||||
for (const line of prose.slice(0, index + 1)) {
|
||||
const heading = /^(#{1,6})\s+(.+)$/.exec(line);
|
||||
if (!heading) continue;
|
||||
while (owners.length && owners.at(-1)!.level >= heading[1]!.length) owners.pop();
|
||||
owners.push({ level: heading[1]!.length, title: heading[2]! });
|
||||
}
|
||||
return !owners.some(owner => /\b(?:hypothetical|example|quoted|historical|template|source)\b/i.test(owner.title));
|
||||
}
|
||||
|
||||
/** A same-ID assessment survives intervening diagrams and named assessment headings. */
|
||||
function structuredFindingAssessment(prose: string[], finding: number, traceEnd: number, ids: string[]): string[] {
|
||||
const assessment: string[] = [];
|
||||
const sameId = new RegExp(`^(?:${ids.join('|')})\\b`);
|
||||
const ownsHeading = new RegExp(`\\b(?:${ids.join('|')})\\b`);
|
||||
let followingTrace = false, namedAssessment = false;
|
||||
for (let i = finding + 1; i < prose.length; i++) {
|
||||
const line = prose[i]!;
|
||||
if (i === traceEnd + 1) followingTrace = true;
|
||||
if (/^#{1,6}\s/.test(line)) {
|
||||
namedAssessment = ownsHeading.test(line);
|
||||
followingTrace = false;
|
||||
} else if (/^\||^[FSDA][1-9]\d*\b/.test(line) && !sameId.test(line)) {
|
||||
followingTrace = false;
|
||||
namedAssessment = false;
|
||||
}
|
||||
if (assertedStructuredOwner(prose, i) && (sameId.test(line) || namedAssessment || followingTrace)) assessment.push(line);
|
||||
}
|
||||
return assessment;
|
||||
}
|
||||
|
||||
function hasStructuredStaleFillFinding(report: string): boolean {
|
||||
const lines = report.split('\n');
|
||||
const prose = lines.map(() => '');
|
||||
@@ -274,6 +388,74 @@ function hasStructuredStaleFillFinding(report: string): boolean {
|
||||
// closing delimiter. They cannot supply an asserted prose violation.
|
||||
if (!fence && !/^\s*>/.test(line) && !/^(?: {4}|\t)/.test(line)) prose[i] = line;
|
||||
}
|
||||
for (const trace of traces) {
|
||||
let heading = trace.start - 1;
|
||||
while (heading >= 0 && !prose[heading]!.trim()) heading--;
|
||||
const identity = /^Async ordering schedule \((F[1-9]\d*), invariant boundary = `writeProfile` settles\):$/.exec(prose[heading] ?? '');
|
||||
if (!identity || !assertedStructuredOwner(prose, heading)) continue;
|
||||
const framed = (line: string) => !line || /^(?:\||#{1,6}\s)/.test(line);
|
||||
let previous = heading - 1;
|
||||
while (previous >= 0 && !lines[previous]!.trim()) previous--;
|
||||
if (!framed(prose[previous] ?? '') || (!prose[previous] && previous >= 0 && !traces.some(other => other.end === previous))) continue;
|
||||
const findings = prose.slice(0, heading).map((line, index) => ({ index, cells: line.split('|').map(cell => cell.trim()) }))
|
||||
.filter(({ cells }) => cells.length === 8 && cells[0] === '' && cells[1] === identity[1] && cells[2] === 'CRITICAL');
|
||||
if (findings.length !== 1) continue;
|
||||
const finding = findings[0]!;
|
||||
if (!assertedStructuredOwner(prose, finding.index)) continue;
|
||||
let registryHeading = finding.index - 1;
|
||||
while (registryHeading >= 0 && !/^#{1,6}\s/.test(prose[registryHeading]!)) registryHeading--;
|
||||
if (!/^#{1,6} Findings registry$/.test(prose[registryHeading] ?? '')
|
||||
|| prose.slice(registryHeading + 1, finding.index).some(line => line.trim() && !/^\|/.test(line))) continue;
|
||||
const prefix = prose.slice(0, registryHeading).filter(line => line.trim()).at(-1) ?? '';
|
||||
const priorSection = prose.slice(0, registryHeading).filter(line => /^#{1,6}\s/.test(line)).at(-1) ?? '';
|
||||
const closesDecisions = /^Lake Score: [0-9]+\/[0-9]+ coverage-scored decisions \([A-Z0-9, -]+\) chose the complete option\.$/.test(prefix)
|
||||
&& /^#{1,6} Decision registry\b/.test(priorSection);
|
||||
if (!framed(prefix) && !closesDecisions) continue;
|
||||
const citation = /^Lines "no additional version checks or coordination between a cache fill and a write" vs invariant "every read begun after that write completes must observe the committed version"\. Schedule in Section [1-9]\d* shows a pre-write DB snapshot filled after `cache\.delete`, served up to ([1-9]\d*) s;/.exec(finding.cells[3] ?? '');
|
||||
const ordered = originalOrderAStaleFillTrace(trace.text);
|
||||
if (!citation || !ordered || citation[1] !== ordered.ttl) continue;
|
||||
const assessment = structuredFindingAssessment(prose, finding.index, trace.end, [identity[1]!]);
|
||||
const registry = [...finding.cells];
|
||||
// This exact residual allowance refers only to readers begun before W,
|
||||
// matching R1 in the validated header, never to the later R2 cache hit.
|
||||
if (registry[5] === 'Readers that began before the write may still see the old snapshot (permitted by contract)') {
|
||||
registry[5] = 'Allowed by contract: the original reader returns its earlier value.';
|
||||
}
|
||||
const context = [registry.join(' | '), ordered.assessment, ...assessment].join(' ');
|
||||
if (new RegExp(`\\b${identity[1]}\\s+(?:is|was|remains)\\s+(?:impossible|rejected|dismissed|withdrawn)\\b`, 'i').test(context)
|
||||
|| /\b(?:(?:this|that|the|original)\s+(?:trace|schedule|scenario|execution|sequence)|this|that|it)\s+(?:is|was|remains)\s+impossible\b/i.test(context)) continue;
|
||||
const claim = `Concurrent cache read fills an old value after the write committed and invalidated the same key. A new reader receives that stale value, which violates the read-after-write contract. ${context}`;
|
||||
if (hasProseStaleFillFinding(claim)) return true;
|
||||
}
|
||||
for (const trace of traces) {
|
||||
let heading = trace.start - 1;
|
||||
while (heading >= 0 && !prose[heading]!.trim()) heading--;
|
||||
const shared = /^\*\*[1-9]\d*\. Async ordering schedules \(shared state: cache\[([A-Za-z_$][\w$]*)\], writeGen\[([A-Za-z_$][\w$]*)\]\)\*\*$/.exec(prose[heading] ?? '');
|
||||
if (!shared || shared[1] !== shared[2] || !assertedStructuredOwner(prose, heading)) continue;
|
||||
const framed = (line: string) => !line || /^(?:\||#{1,6}\s|\*\*[0-9]+[A-Z]?\b)/.test(line);
|
||||
let previous = heading - 1;
|
||||
while (previous >= 0 && !lines[previous]!.trim()) previous--;
|
||||
if (!framed(prose[previous] ?? '') || (!prose[previous] && previous >= 0 && !traces.some(other => other.end === previous))) continue;
|
||||
const findings = prose.slice(0, heading).map((line, index) => ({ index, cells: line.split('|').map(cell => cell.trim()) }))
|
||||
.filter(({ cells }) => cells.length === 8 && cells[0] === '' && /^F[1-9]\d*$/.test(cells[1] ?? '') && /^P[0-3] CRITICAL$/.test(cells[2] ?? ''));
|
||||
for (const finding of findings) {
|
||||
if (!assertedStructuredOwner(prose, finding.index) || findings.filter(other => other.cells[1] === finding.cells[1]).length !== 1) continue;
|
||||
let registryHeading = finding.index - 1;
|
||||
while (registryHeading >= 0 && !/^#{1,6}\s/.test(prose[registryHeading]!)) registryHeading--;
|
||||
if (!/^#{1,6} Findings Registry$/.test(prose[registryHeading] ?? '')
|
||||
|| !framed(prose.slice(0, registryHeading).filter(line => line.trim()).at(-1) ?? '')) continue;
|
||||
const sequence = /^Late fill after write\. Read misses, DB returns ([A-Za-z][\w.-]*), write commits ([A-Za-z][\w.-]*) and deletes \(no-op\), read then fills ([A-Za-z][\w.-]*); every later read gets ([A-Za-z][\w.-]*) until TTL\.(?=\s|$)/.exec(finding.cells[3] ?? '');
|
||||
if (!sequence || sequence[1] === sequence[2] || sequence[1] !== sequence[3] || sequence[1] !== sequence[4]) continue;
|
||||
const ordered = versionedOriginalSchedule(trace.text, shared[1]!, sequence[1]!, sequence[2]!, finding.cells[1]!);
|
||||
if (!ordered || !new RegExp(`\\bschedules?\\s+${ordered.schedule}(?=[, .]|$)`).test(finding.cells[6] ?? '')) continue;
|
||||
const assessment = structuredFindingAssessment(prose, finding.index, trace.end, [finding.cells[1]!, ordered.schedule]);
|
||||
const context = [finding.cells.join(' | '), ordered.assessment, ...assessment].join(' ');
|
||||
if (new RegExp(`\\b(?:${finding.cells[1]}|${ordered.schedule})\\s+(?:is|was|remains)\\s+(?:impossible|rejected|dismissed|withdrawn)\\b`, 'i').test(context)
|
||||
|| /\b(?:(?:this|that|the|original)\s+(?:trace|schedule|scenario|execution|sequence)|this|that|it)\s+(?:is|was|remains)\s+impossible\b/i.test(context)) continue;
|
||||
const claim = `Concurrent cache read fills an old value after the write committed and invalidated the same key. A new reader receives that stale value, which violates the read-after-write contract. ${context}`;
|
||||
if (hasProseStaleFillFinding(claim)) return true;
|
||||
}
|
||||
}
|
||||
for (const trace of traces) {
|
||||
let heading = trace.start - 1;
|
||||
while (heading >= 0 && !/^#{1,6}\s/.test(prose[heading]!)) heading--;
|
||||
|
||||
@@ -31,6 +31,7 @@ import { withHermeticSkillRuntime } from './hermetic-skill-runtime';
|
||||
import { createPlanCountFixture } from './plan-count-fixture';
|
||||
import { createPlanCountSnapshotWriter } from './plan-count-artifacts';
|
||||
import { nativeSeededPlanSelection } from './plan-scope-selection';
|
||||
import { readPlanFloorTarget, type PlanFloorTargetDelivery } from './plan-floor-target';
|
||||
import { findNativeAutoDecision, type NativeAutoDecision } from './native-auto-decide';
|
||||
import { readPlanCountTranscript, unresolvedPlanQuestionCalls, type NativePlanQuestionCall, type PlanCountTranscript, type NativePublicToolEvent } from './plan-count-transcript';
|
||||
import { createPendingExitRecorder, withPendingExit, isCurrentPlanApprovalScreen } from './plan-count-pending-exit';
|
||||
@@ -101,7 +102,7 @@ export interface ClaudePtyOptions {
|
||||
/** Terminal size. Default 120x40. Plan-mode UI lays out cleanly at this size. */
|
||||
cols?: number;
|
||||
rows?: number;
|
||||
/** Opt in only when input targeting needs the actual VT viewport. */
|
||||
/** Opt in when input targeting or completion needs the actual VT viewport. */
|
||||
observeScreen?: boolean;
|
||||
/** Count-only pending identity; the hook never approves or changes native tools. */
|
||||
observePlanReady?: boolean;
|
||||
@@ -999,6 +1000,8 @@ export function classifyVisible(
|
||||
* where zero-findings → write plan → plan_ready is legitimate.
|
||||
*/
|
||||
strictPlanWrites?: boolean;
|
||||
/** Seeded observations require the complete native approval panel in this owned viewport. */
|
||||
currentScreen?: string;
|
||||
},
|
||||
): ClassifyResult {
|
||||
// Silent-write detection: any Write/Edit tool render that targets a path
|
||||
@@ -1048,10 +1051,20 @@ export function classifyVisible(
|
||||
};
|
||||
}
|
||||
if (isPlanReadyVisible(visible)) {
|
||||
return {
|
||||
outcome: 'plan_ready',
|
||||
summary: 'skill ran end-to-end and emitted plan-mode "Ready to execute" confirmation',
|
||||
};
|
||||
if (opts?.currentScreen === undefined || isCurrentPlanApprovalScreen(opts.currentScreen)) {
|
||||
return {
|
||||
outcome: 'plan_ready',
|
||||
summary: 'skill ran end-to-end and emitted plan-mode "Ready to execute" confirmation',
|
||||
};
|
||||
}
|
||||
// Historical TODO prose and stale approval menus cannot finish a seeded
|
||||
// review. The viewport may corroborate an existing question, never add one.
|
||||
const current = opts.currentScreen;
|
||||
// A streaming or mismatched native approval panel is not an AUQ either.
|
||||
if (/Claude (?:has written up a plan|wants to exit plan mode)|Exit plan mode\?/i.test(current) ||
|
||||
!(isNumberedOptionListVisible(visible) && isNumberedOptionListVisible(current) ||
|
||||
isProseAUQVisible(visible) && isProseAUQVisible(current))) return null;
|
||||
visible = current;
|
||||
}
|
||||
if (isNumberedOptionListVisible(visible)) {
|
||||
// Permission dialogs render numbered lists too. Skip them — the
|
||||
@@ -2248,6 +2261,38 @@ function ceoParenthesizedIssueBrief(q: NativePlanQuestionCall['questions'][numbe
|
||||
labels.some(label => label![2]!.toUpperCase() === recommendations[0]![2]!.toUpperCase());
|
||||
}
|
||||
|
||||
/** A section-numbered option brief remains a review decision when qids are omitted. */
|
||||
function ceoSectionChoiceBrief(q: NativePlanQuestionCall['questions'][number], title: string): boolean {
|
||||
const identity = /^([1-9]\d*)([A-Z])\s*[—–-]\s*(?:What|How|Which|Should)\b[^\n?]+\?$/i.exec(title);
|
||||
if (!identity || /\b(?:hypothetical|example|template|report|summary|archive|routing|setup|completion|next review|completed review)\b/i.test(title)) return false;
|
||||
const prose = q.question
|
||||
.replace(/```[\s\S]*?(?:```|$)|~~~[\s\S]*?(?:~~~|$)/g, '')
|
||||
.replace(/^(?:\s*>| {4}|\t).*$/gm, '')
|
||||
.replace(/"(?:[^"\\]|\\.)*"|“[^”]*”|`[^`]*`/g, '""');
|
||||
const field = (name: string) => [...prose.matchAll(new RegExp('^' + name + ':\\s*(.+)$', 'gm'))];
|
||||
const contexts = field('Project/branch/task'), explanations = field('ELI10');
|
||||
const stakes = field('Stakes if we pick wrong'), recommendations = field('Recommendation');
|
||||
if ([contexts, explanations, stakes, recommendations].some(rows => rows.length !== 1)) return false;
|
||||
const section = /(?:^|[,;]\s*)Section ([1-9]\d*) [a-z][a-z -]*\.$/i.exec(contexts[0]![1]!);
|
||||
const recommended = /^([A-Z])\b/i.exec(recommendations[0]![1]!);
|
||||
if (section?.[1] !== identity[1] || recommended?.[1]?.toUpperCase() !== identity[2]!.toUpperCase() ||
|
||||
[explanations[0]![1]!, stakes[0]![1]!].some(text => !/\w/.test(text) || /^["'‘“`]/.test(text.trim())) ||
|
||||
/^(?:if|unless|whether|suppose|imagine|example|template|hypothetical|historical|quoted)\b/i.test(explanations[0]![1]!.trim())) return false;
|
||||
// Neither an administrative recap nor a withdrawn assessment starts review.
|
||||
if (/\b(?:no (?:(?:current|unresolved) )?(?:defect|gap|issue|problem)|(?:this|that|the) (?:issue|finding|gap|problem|defect)\s+(?:is|was|has been)\s+(?:(?:already|now)\s+)?(?:resolved|fixed|closed|withdrawn|retracted)|(?:I|we)\s+(?:(?:have|has)\s+)?(?:withdraw|withdrawn|retract|retracted|resolve|resolved)\s+(?:this|that|the)\s+(?:finding|issue|question))\b/i.test(prose)) return false;
|
||||
const explanation = explanations[0]![1]!;
|
||||
// A section/choice number is identity, not proof of a review issue. The
|
||||
// current assessment must state a correctness gap, with a substantive
|
||||
// offered change; administrative storage choices satisfy neither condition.
|
||||
const currentGap = /\bno\s+(?:error handling|tests?|checks?|validation|coordination)\b|\bbut not in which order\b|\bpastes?\b[^.!?]*\bstraight into a SQL fragment\b|\bcustomer gets a second\b/i.test(explanation);
|
||||
const amendment = q.options.some(option => /^(?:commit|rescue|bound parameter|skip email|full matrix)\b/i.test(option.label.replace(/^[A-Z][):.]\s*/i, '')));
|
||||
if (!currentGap || !amendment) return false;
|
||||
const labels = q.options.map(option => /^([A-Z])[):.]\s*\S/i.exec(option.label));
|
||||
return q.options.length >= 2 && q.options.every((option, i) => Boolean(option.description?.trim()) && labels[i]) &&
|
||||
new Set(labels.map(label => label![1]!.toUpperCase())).size === labels.length &&
|
||||
labels.some(label => label![1]!.toUpperCase() === recommended![1]!.toUpperCase());
|
||||
}
|
||||
|
||||
function nativeExplicitCeoFinding(fp: AskUserQuestionFingerprint, allowQuestionId = false): boolean {
|
||||
const call = fp.nativeCall;
|
||||
// QUESTION_TUNING=false omits qid injection. Accept an explicit Finding
|
||||
@@ -2267,6 +2312,7 @@ function nativeExplicitCeoFinding(fp: AskUserQuestionFingerprint, allowQuestionI
|
||||
if (allowQuestionId && ((q.question.match(/<gstack-qid/gi)?.length ?? 0) !== 1 ||
|
||||
!/<gstack-qid:\s*(?:plan-)?ceo-(?:review-)?[a-z0-9-]+\s*>/i.test(q.question))) return false;
|
||||
const title = q.question.split('\n')[0]!.replace(/\s*<gstack-qid:[^>]+>\s*$/i, '');
|
||||
if (!allowQuestionId && ceoSectionChoiceBrief(q, title)) return true;
|
||||
// The issue identity is separate from the decision counter and section
|
||||
// numbering. A completed "Issue 2" choice and "Finding 2.1" choice carry
|
||||
// the same review evidence as the already-supported numbered findings.
|
||||
@@ -3186,6 +3232,7 @@ export async function runPlanSkillObservation(opts: {
|
||||
env: opts.env,
|
||||
model: opts.model,
|
||||
seedSkills: true,
|
||||
observeScreen: !!opts.initialPlanContent,
|
||||
});
|
||||
|
||||
try {
|
||||
@@ -3274,9 +3321,16 @@ export async function runPlanSkillObservation(opts: {
|
||||
};
|
||||
}
|
||||
|
||||
const classified = classifyVisible(visible, {
|
||||
strictPlanWrites: !!opts.initialPlanContent,
|
||||
currentScreen: opts.initialPlanContent ? await session.currentScreen() : undefined,
|
||||
});
|
||||
const pendingSeededCompletion = !!opts.initialPlanContent &&
|
||||
isPlanReadyVisible(visible) && classified === null;
|
||||
|
||||
// Cheap surface-tracking: did the model ever surface a prose AUQ in
|
||||
// this tick's recent buffer? Track once-true (high water).
|
||||
if (!proseAUQEverObserved && isProseAUQVisible(visible)) {
|
||||
if (!proseAUQEverObserved && !pendingSeededCompletion && isProseAUQVisible(visible)) {
|
||||
proseAUQEverObserved = true;
|
||||
logPtySnapshot(visible, {
|
||||
testName: opts.skillName,
|
||||
@@ -3308,9 +3362,6 @@ export async function runPlanSkillObservation(opts: {
|
||||
if (!tokensObserved[t] && visible.includes(t)) tokensObserved[t] = true;
|
||||
}
|
||||
|
||||
const classified = classifyVisible(visible, {
|
||||
strictPlanWrites: !!opts.initialPlanContent,
|
||||
});
|
||||
if (classified) {
|
||||
const obs: PlanSkillObservation = {
|
||||
...classified,
|
||||
@@ -3354,7 +3405,7 @@ export async function runPlanSkillObservation(opts: {
|
||||
lastJudgeAt = Date.now();
|
||||
logPtySnapshot(visible, { testName: opts.skillName, elapsedMs: elapsed, tag: 'judge-tick' });
|
||||
lastJudgeVerdict = judgePtyState(visible, { testName: opts.skillName });
|
||||
if (lastJudgeVerdict.state === 'waiting') {
|
||||
if (lastJudgeVerdict.state === 'waiting' && !pendingSeededCompletion) {
|
||||
waitingEverObserved = true;
|
||||
return {
|
||||
outcome: 'asked',
|
||||
@@ -3903,6 +3954,8 @@ export async function runPlanSkillCounting(opts: {
|
||||
export interface PlanSkillFloorObservation {
|
||||
/** True iff a review-phase AUQ render was observed. */
|
||||
auqObserved: boolean;
|
||||
/** Owned native acknowledgment of the exact seeded target command. */
|
||||
targetDelivery?: PlanFloorTargetDelivery;
|
||||
outcome:
|
||||
| 'auq_observed'
|
||||
| 'plan_ready'
|
||||
@@ -3923,11 +3976,11 @@ export interface PlanSkillFloorObservation {
|
||||
export async function runPlanSkillFloorCheck(opts: {
|
||||
/** Skill name, e.g. 'plan-eng-review'. Used for diagnostic strings only. */
|
||||
skillName: string;
|
||||
/** Slash command to send alone, e.g. '/plan-eng-review'. */
|
||||
/** Slash command; the owned PLAN.md target is supplied in the same submission. */
|
||||
slashCommand: string;
|
||||
/** Plan content sent as a follow-up message ~3s after the slash command. */
|
||||
/** Complete request seeded in an isolated project before the command starts. */
|
||||
followUpPrompt: string;
|
||||
/** Working directory. Default process.cwd(). */
|
||||
/** Installation cwd retained for caller compatibility; review uses an owned seeded project. */
|
||||
cwd?: string;
|
||||
/** Total budget. Default 600000 (10 min). Tests exit early on AUQ. */
|
||||
timeoutMs?: number;
|
||||
@@ -3939,21 +3992,40 @@ export async function runPlanSkillFloorCheck(opts: {
|
||||
const startedAt = Date.now();
|
||||
const timeoutMs = opts.timeoutMs ?? 600_000;
|
||||
|
||||
const session = await launchClaudePty({
|
||||
permissionMode: 'plan',
|
||||
cwd: opts.cwd,
|
||||
timeoutMs: timeoutMs + 60_000,
|
||||
env: opts.env,
|
||||
model: opts.model,
|
||||
seedSkills: true,
|
||||
});
|
||||
const fixture = createPlanCountFixture(opts.followUpPrompt);
|
||||
const sessionId = randomUUID();
|
||||
let session: ClaudePtySession;
|
||||
try {
|
||||
session = await launchClaudePty({
|
||||
permissionMode: 'plan',
|
||||
cwd: fixture.cwd,
|
||||
timeoutMs: timeoutMs + 60_000,
|
||||
env: { ...opts.env, ...fixture.env },
|
||||
model: opts.model,
|
||||
seedSkills: true,
|
||||
extraArgs: ['--session-id', sessionId],
|
||||
});
|
||||
} catch (error) {
|
||||
fixture.cleanup();
|
||||
throw error;
|
||||
}
|
||||
|
||||
try {
|
||||
await Bun.sleep(8000); // boot grace + auto-trust handler window
|
||||
const since = session.mark();
|
||||
session.send(`${opts.slashCommand}\r`);
|
||||
await Bun.sleep(3000);
|
||||
session.send(`${opts.followUpPrompt}\r`);
|
||||
const commandStartedAt = Date.now();
|
||||
session.send(`${opts.slashCommand} PLAN.md\r`);
|
||||
const deliveryOptions = { seed: opts.followUpPrompt, sessionId,
|
||||
slashCommand: opts.slashCommand, startedAt: commandStartedAt };
|
||||
let targetDelivery = readPlanFloorTarget(session.hermeticConfigDir, fixture.cwd,
|
||||
{ ...deliveryOptions, now: Date.now() });
|
||||
const saveSnapshot = createPlanCountSnapshotWriter();
|
||||
const finish = (observation: PlanSkillFloorObservation): PlanSkillFloorObservation => {
|
||||
const artifacts = saveSnapshot({ skillName: opts.skillName, cwd: fixture.cwd,
|
||||
claudeConfigDir: session.hermeticConfigDir, raw: session.rawOutput(),
|
||||
visible: session.visibleSince(since), observation: { ...observation, targetDelivery, commandStartedAt } });
|
||||
return { ...observation, targetDelivery, ...artifacts };
|
||||
};
|
||||
|
||||
const start = Date.now();
|
||||
let lastJudgeAt = 0;
|
||||
@@ -3977,22 +4049,28 @@ export async function runPlanSkillFloorCheck(opts: {
|
||||
}
|
||||
|
||||
if (session.exited()) {
|
||||
return {
|
||||
return finish({
|
||||
auqObserved: false,
|
||||
outcome: 'exited',
|
||||
summary: `claude exited (code=${session.exitCode()}) before any AUQ render`,
|
||||
evidence: visible.slice(-3000),
|
||||
elapsedMs: Date.now() - startedAt,
|
||||
};
|
||||
});
|
||||
}
|
||||
if (visible.includes('Unknown command:')) {
|
||||
return {
|
||||
return finish({
|
||||
auqObserved: false,
|
||||
outcome: 'exited',
|
||||
summary: `claude rejected ${opts.slashCommand} as unknown command`,
|
||||
evidence: visible.slice(-3000),
|
||||
elapsedMs: Date.now() - startedAt,
|
||||
};
|
||||
});
|
||||
}
|
||||
|
||||
if (targetDelivery.status !== 'ready') {
|
||||
targetDelivery = readPlanFloorTarget(session.hermeticConfigDir, fixture.cwd,
|
||||
{ ...deliveryOptions, now: Date.now() });
|
||||
if (targetDelivery.status !== 'ready') continue;
|
||||
}
|
||||
|
||||
// Success: ANY non-permission numbered-option list is an AUQ render —
|
||||
@@ -4029,13 +4107,13 @@ export async function runPlanSkillFloorCheck(opts: {
|
||||
!isPermissionDialogVisible(tail) &&
|
||||
!gateIsActiveRender
|
||||
) {
|
||||
return {
|
||||
return finish({
|
||||
auqObserved: true,
|
||||
outcome: 'auq_observed',
|
||||
summary: 'agent rendered an AskUserQuestion (floor met)',
|
||||
evidence: visible.slice(-3000),
|
||||
elapsedMs: Date.now() - startedAt,
|
||||
};
|
||||
});
|
||||
}
|
||||
|
||||
// LLM judge fallback: same shape as runPlanSkillObservation. After 60s
|
||||
@@ -4054,13 +4132,13 @@ export async function runPlanSkillFloorCheck(opts: {
|
||||
// must NOT satisfy the floor — same active-render exclusion as the
|
||||
// regex path.
|
||||
if (lastJudgeVerdict.state === 'waiting' && !gateIsActiveRender) {
|
||||
return {
|
||||
return finish({
|
||||
auqObserved: true,
|
||||
outcome: 'auq_observed',
|
||||
summary: `LLM judge: ${lastJudgeVerdict.reasoning} (state=waiting after ${Math.round(elapsed / 1000)}s; floor met)`,
|
||||
evidence: visible.slice(-3000),
|
||||
elapsedMs: Date.now() - startedAt,
|
||||
};
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4071,13 +4149,13 @@ export async function runPlanSkillFloorCheck(opts: {
|
||||
const target = m[1] ?? '';
|
||||
const sanctioned = SANCTIONED_WRITE_SUBSTRINGS.some((s) => target.includes(s));
|
||||
if (!sanctioned && !isNumberedOptionListVisible(visible)) {
|
||||
return {
|
||||
return finish({
|
||||
auqObserved: false,
|
||||
outcome: 'silent_write',
|
||||
summary: `Write/Edit to ${target} fired before any AskUserQuestion`,
|
||||
evidence: visible.slice(-3000),
|
||||
elapsedMs: Date.now() - startedAt,
|
||||
};
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4089,24 +4167,26 @@ export async function runPlanSkillFloorCheck(opts: {
|
||||
// (claude's actual "Ready to execute" confirmation) is the reliable
|
||||
// terminal signal for "agent finished without asking."
|
||||
if (isPlanReadyVisible(visible)) {
|
||||
return {
|
||||
return finish({
|
||||
auqObserved: false,
|
||||
outcome: 'plan_ready',
|
||||
summary: 'agent reached plan_ready without firing any AskUserQuestion',
|
||||
evidence: visible.slice(-3000),
|
||||
elapsedMs: Date.now() - startedAt,
|
||||
};
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
return {
|
||||
return finish({
|
||||
auqObserved: false,
|
||||
outcome: 'timeout',
|
||||
summary: `no AUQ render and no terminal outcome within ${timeoutMs}ms`,
|
||||
summary: targetDelivery.status === 'ready'
|
||||
? `no AUQ render and no terminal outcome within ${timeoutMs}ms`
|
||||
: `seeded target delivery unavailable within ${timeoutMs}ms: ${targetDelivery.reason ?? targetDelivery.status}`,
|
||||
evidence: session.visibleSince(since).slice(-3000),
|
||||
elapsedMs: Date.now() - startedAt,
|
||||
};
|
||||
});
|
||||
} finally {
|
||||
await session.close();
|
||||
try { await session.close(); } finally { fixture.cleanup(); }
|
||||
}
|
||||
}
|
||||
@@ -92,12 +92,57 @@ function ordinaryDesignIssue(fp: AskUserQuestionFingerprint): boolean {
|
||||
return opposed.length > 0 && !!(repair || primaryRepair);
|
||||
}
|
||||
|
||||
/** A design-system choice can name the gap without using an imperative repair verb. */
|
||||
function designSystemChoiceIssue(fp: AskUserQuestionFingerprint): boolean {
|
||||
const call = fp.nativeCall;
|
||||
if (!call || call.answered !== true || call.failed !== false || !call.sessionId || !call.toolUseId ||
|
||||
call.questions.length !== 1 || !Array.isArray(call.unansweredQuestionIndices) || call.unansweredQuestionIndices.length ||
|
||||
fp.signature !== `${call.sessionId}:${call.toolUseId}` ||
|
||||
(fp.nativeQuestionIndex !== undefined && fp.nativeQuestionIndex !== 0) ||
|
||||
!call.answeredAt || !Number.isFinite(Date.parse(call.answeredAt))) return false;
|
||||
const q = call.questions[0]!;
|
||||
const lines = q.question.trim().split('\n');
|
||||
const issue = /^(?:D[1-9]\d*\s*[—–:-]\s*)?Issue ([1-9]\d*): (.+)\?$/.exec(lines[0]!);
|
||||
if (!issue || q.header.trim() !== `Issue ${issue[1]}` || lines.length !== 7 ||
|
||||
!/^Project\/branch\/task: [^\n,]+ on [^\n,]+, PLAN\.md design review, Pass [1-7] [A-Za-z][A-Za-z &()-]+\.$/.test(lines[1]!) ||
|
||||
!/^ELI10: \S/.test(lines[2]!) || !/\bDESIGN\.md\b/.test(lines[2]!) ||
|
||||
!/^Stakes if we pick wrong: \S/.test(lines[3]!) || !/^Recommendation: \S/.test(lines[4]!) ||
|
||||
!/^Completeness: \S/.test(lines[5]!) || !/^Net: \S/.test(lines[6]!) ||
|
||||
/<gstack-qid:|```|^ELI10: (?:Example|Hypothetical|Quoted)\b/im.test(q.question) || q.multiSelect ||
|
||||
q.options.length < 2 || q.options.length > 4 || new Set(q.options.map(o => o.label)).size !== q.options.length ||
|
||||
!q.options.every(o => new RegExp(`^${issue[1]}[A-Z]: \\S`).test(o.label)) ||
|
||||
fp.options.length !== q.options.length || !fp.options.every((o, i) => o.index === i + 1 && o.label === q.options[i]!.label) ||
|
||||
!q.options.some(o => o.label === call.answers?.[q.question])) return false;
|
||||
// These are current visual/interaction choices, not reviewer participation or next-step routing.
|
||||
const subjects = [
|
||||
/^How should [A-Z][A-Za-z0-9 _/-]{0,79} be distinguished from [A-Z][A-Za-z0-9 ,/_-]{0,119}$/,
|
||||
/^What does the user see while [A-Z][A-Za-z0-9 _/-]{0,79} is pending for [1-9]\d*(?:[-–][1-9]\d*)? seconds$/,
|
||||
/^What type scale should (?:form )?labels(?: and section headings)? use$/,
|
||||
/^What vertical spacing rhythm should the form use$/,
|
||||
/^How should (?:the )?error message meet WCAG AA contrast$/,
|
||||
];
|
||||
const subject = subjects.findIndex(pattern => pattern.test(issue[2]!));
|
||||
if (subject < 0) return false;
|
||||
const assessments = [/^ELI10: The header shows\b/, /^ELI10: After clicking\b/,
|
||||
/^ELI10: Labels on the form are set\b/, /^ELI10: Gaps between sections are\b/, /^ELI10: The error message is\b/];
|
||||
if (!assessments[subject]!.test(lines[2]!) ||
|
||||
/(?:^|[.!?]\s+)(?:This (?:issue|finding) (?:is|has been) (?:withdrawn|resolved|closed)|We have (?:resolved|closed|withdrawn) this (?:issue|finding)|No current (?:issue|finding|gap|defect|violation) (?:remains|exists))\b/i.test(lines[2]!.slice(7))) return false;
|
||||
const control = /^How should (.+) be distinguished from /.exec(issue[2]!)?.[1];
|
||||
const concrete = [new RegExp(`^${control}\\b[^\\n]*\\b(?:filled|ghost|outlined|primary)\\b`, 'i'),
|
||||
/^(?:Spinner|InlineStatus|Static indicator)\b/i, /^[1-9]\d*px\b/i, /^[1-9]\d*px\b/i, /^#[0-9a-f]{6}\b/i][subject]!;
|
||||
const conforming = q.options.filter(o => concrete.test(o.label.replace(/^[1-9]\d*[A-Z]: /, '')) &&
|
||||
(/^✅ Exact(?:ly)? (?:the (?:two )?)?DESIGN\.md\b/.test(o.description ?? '') ||
|
||||
(subject === 0 && new RegExp(`^✅ ${control} is [^\\n]+\\bexactly per DESIGN\\.md\\b`).test(o.description ?? ''))));
|
||||
return conforming.some(choice => q.options.some(o => o !== choice &&
|
||||
/^❌ (?:Ships (?:the documented violation|a known WCAG AA failure)\b|Deviates from the DESIGN\.md\b)/m.test(o.description ?? '')));
|
||||
}
|
||||
|
||||
/** A completed finding can start the passes when the caller already supplied the focus. */
|
||||
export function isDesignCountFirstReview(fp: AskUserQuestionFingerprint): boolean {
|
||||
const call = fp.nativeCall;
|
||||
if (!call?.answered || call.failed) return false;
|
||||
if (isDesignCountSetup(fp)) return false;
|
||||
if (numberedVisualHierarchyFinding(fp) || ordinaryDesignIssue(fp)) return true;
|
||||
if (numberedVisualHierarchyFinding(fp) || ordinaryDesignIssue(fp) || designSystemChoiceIssue(fp)) return true;
|
||||
if (designFirstReviewAUQ(fp)) return true;
|
||||
return call.questions.some(q => {
|
||||
if (!call.answers?.[q.question] || q.options.length < 2) return false;
|
||||
|
||||
@@ -64,7 +64,80 @@ function requiredLegacyCharacterization(task: string): boolean {
|
||||
&& !/\bno\s+(?:(?:regression|characterization)\s+)?(?:tests?|fixtures?)\s+(?:are\s+)?(?:needed|required)\b/i.test(text);
|
||||
}
|
||||
|
||||
/** Required suites bind a numbered task to an untouched legacy baseline or parity oracle. */
|
||||
function declaredLegacyCharacterization(text: string): boolean {
|
||||
const sections: Array<{ title: string; body: string[]; asserted: boolean }> = [];
|
||||
const owners: Array<{ level: number; asserted: boolean }> = [];
|
||||
let preamble = '', sourcePreamble = false;
|
||||
const sourceFrame = (body: string) => /\b(?:(?:hypothetical|historical) example|unproven hypothesis|(?:source|quoted) (?:material|text) only|(?:are|is) not requirements? of this plan)\b/i.test(body.replace(/\s+/g, ' '));
|
||||
for (const line of prose(text).split('\n')) {
|
||||
const heading = /^(#{1,6})\s+(.+)$/.exec(line);
|
||||
if (heading) {
|
||||
while (owners.length && owners.at(-1)!.level >= heading[1]!.length) owners.pop();
|
||||
if (/^Current reviewed plan$/i.test(heading[2]!) && owners.length === 0) sourcePreamble = false;
|
||||
const asserted = !sourcePreamble && owners.every(owner => owner.asserted)
|
||||
&& !/\b(?:source|example|hypothetical|proposed|optional|quoted|historical|template|unproven)\b/i.test(heading[2]!);
|
||||
owners.push({ level: heading[1]!.length, asserted });
|
||||
sections.push({ title: heading[2]!, body: [], asserted });
|
||||
} else if (sections.length) {
|
||||
const section = sections.at(-1)!;
|
||||
section.body.push(line);
|
||||
if (sourceFrame(section.body.join(' '))) section.asserted = owners.at(-1)!.asserted = false;
|
||||
} else {
|
||||
preamble += ' ' + line;
|
||||
sourcePreamble = sourceFrame(preamble);
|
||||
}
|
||||
}
|
||||
const current = sections.filter(section => section.asserted);
|
||||
const mandatory = current.filter(section => /^CRITICAL regression \(mandatory, regression rule\)$/i.test(section.title));
|
||||
const declaration = /^legacyAuthFlow(?:\(\))? is (?:existing|current) behavior being (?:modified|refactored)\b[^!?]{0,240}\.\s+(?:A|The) characterization test suite for legacyAuthFlow(?:\(\))? is (?:added|required) as a (?:critical|mandatory) requirement:\s*(?:capture|pin|record) (?:current|existing|prior)\b[^.!?]{1,400}\.\s+This suite runs against the flag-OFF path and is the oracle the new path is compared to during rollout\./i;
|
||||
const withdrawn = (body: string, task?: string) => new RegExp(
|
||||
`\\b(?:${task ? `${task}|` : ''}(?:this|the|that)\\s+(?:(?:characterization|regression|contract)\\s+)?(?:suite|task|test|requirement)|(?:characterization|regression)\\s+(?:suite|tests?))\\s+(?:(?:is|was|has been)\\s+)?(?:(?:not|no longer)\\s+(?:required|needed)|cancelled|canceled|withdrawn|rejected|deferred|optional)\\b`, 'i').test(body)
|
||||
|| /\b(?:do not|never|skip|defer|cancel|withdraw)\s+(?:run(?:ning)?\s+)?(?:the|this)\s+(?:characterization\s+)?suite\b/i.test(body);
|
||||
const declared = mandatory.some(section => {
|
||||
const body = section.body.join(' ').replace(/\s+/g, ' ').trim();
|
||||
const claim = declaration.exec(body)?.[0];
|
||||
return claim && !/["“”]|\b(?:maybe|might|could|if|unless|optional|hypothetical|unproven)\b/i.test(claim)
|
||||
&& !withdrawn(body);
|
||||
});
|
||||
if (declared) for (const section of current.filter(s => s.title === 'Implementation Tasks')) {
|
||||
const tasks = section.body.join('\n').split(/\n(?=-\s)/);
|
||||
for (const task of tasks) {
|
||||
const match = /^\s*-\s+(?:\[[ xX]\]\s*)?(T[1-9]\d*)(?:\s+\([^\n)]*\))?\s+[—–:-]\s+(?:[A-Za-z][\w-]*(?:\/[A-Za-z][\w-]*)+(?:\s+tests)?\s+[—–]\s+)?CRITICAL regression:\s+characterization suite for legacyAuthFlow(?:\(\))? prior behavior[\t ]*(?:\n|$)/i.exec(task);
|
||||
if (!match || withdrawn(task, match[1])) continue;
|
||||
const baseline = new RegExp(`^[1-9]\\d*\\. Run the characterization suite \\(${match[1]}\\) against the untouched legacyAuthFlow(?:\\(\\))? first and commit it green\\. This is the baseline\\.`, 'i');
|
||||
if (current.some(s => s.title === 'Verification' && baseline.test(s.body.join(' ').replace(/\s+/g, ' ').trim())
|
||||
&& !withdrawn(s.body.join(' '), match[1]))) return true;
|
||||
}
|
||||
}
|
||||
for (const section of current.filter(s => /^CRITICAL: regression contract test for legacyAuthFlow\(\) \(iron rule, no decision needed\)$/.test(s.title))) {
|
||||
const body = section.body.join(' ').replace(/\s+/g, ' ').trim();
|
||||
const parity = /^The rewrite modifies existing behavior with no covering test \([^)]{1,120}\)\. Add ([A-Za-z][\w/-]*\.contract\.test\.[jt]s): a fixture table of \(tenant, token, policy\) cases covering [^.!?]{1,300}\. Run each fixture through legacyAuthFlow\(\) and ([A-Za-z][\w]*)\.authenticate\(\) and assert identical ([A-Za-z][\w]*) shape on success and identical error code on failure\. This test is also the gate for flipping any tenant's flag and for TODO [1-9]\d* removal\./.exec(body);
|
||||
if (!parity || withdrawn(body) || /["“”]|\b(?:maybe|might|could|if|unless|optional|hypothetical|unproven)\b/i.test(parity[0])) continue;
|
||||
const unchanged = current.some(s => {
|
||||
if (!s.title.endsWith(`: Per-tenant flag routes legacy vs ${parity[2]}`)
|
||||
|| !/^Issue [1-9]\d* \(D[1-9]\d*, chose [1-9]\d*[A-D]\): /.test(s.title)) return false;
|
||||
const body = s.body.join('\n');
|
||||
const release = /(?:^|\n)- A tenant-keyed flag [A-Za-z][\w.]*\[tenantId\] \(default off\) selects the path at the\s+login entry point\. legacyAuthFlow\(\) stays callable and unchanged this release\./.exec(body);
|
||||
const prefix = release ? body.slice(0, release.index).trim().split(/\n\s*\n/).at(-1) ?? '' : '';
|
||||
return Boolean(release) && !/^(?:if|unless|maybe|perhaps|proposed|optional)\b/i.test(prefix)
|
||||
&& !/\blegacyAuthFlow(?:\(\))?\s+(?:(?:is|was|will be|has been)\s+)?(?:changed|modified|rewritten|removed|withdrawn|not unchanged|no longer unchanged)\b/i.test(s.body.join(' '));
|
||||
});
|
||||
if (!unchanged) continue;
|
||||
for (const tasks of current.filter(s => s.title === 'Implementation Tasks')) {
|
||||
for (const task of tasks.body.join('\n').split(/\n(?=-\s)/)) {
|
||||
const match = /^\s*-\s+(?:\[[ xX]\]\s*)?(T[1-9]\d*)(?:\s+\([^\n)]*\))?\s+[—–:-]\s+Tests\s+[—–]\s+CRITICAL regression contract test: same fixtures through legacyAuthFlow\(\) and ([A-Za-z][\w]*), identical ([A-Za-z][\w]*) \/ error codes[\t ]*(?:\n|$)/.exec(task);
|
||||
if (!match || match[2] !== parity[2] || match[3] !== parity[3] || withdrawn(task, match[1])) continue;
|
||||
const files = /^\s+- Files: ([^\n]+)$/m.exec(task);
|
||||
if (files?.[1] === parity[1] && /^\s+- Verify: contract suite green on both paths[\t ]*$/m.test(task)) return true;
|
||||
}
|
||||
}
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
function regressionEvidence(text: string): boolean {
|
||||
if (declaredLegacyCharacterization(text)) return true;
|
||||
return prose(text).split(/\n\s*\n|\n(?=\s*[-#])/).some(block => {
|
||||
let task = block.trim().replace(/^[-+]\s+(?:\[[ xX]\]\s*)?/, '');
|
||||
const numbered = /^T\d+(?:\s*\([^\n)]*\))?\s*[—–:-]\s*/.exec(task);
|
||||
|
||||
@@ -10,7 +10,7 @@ export interface NativeAutoDecision {
|
||||
}
|
||||
|
||||
const plain = (text: string) => text.replace(/\*\*([^*]+)\*\*/g, '$1').trim();
|
||||
const annotationLine = /^Auto-decided ([^\r\n→]{1,240}) → ([^\r\n→]{1,200}) \(your preference\)\. Change with \/plan-tune\.$/;
|
||||
const annotationLine = /^Auto-decided ([^\r\n→]{1,240}) → ([^\r\n→]{1,200}) \(your (?:preference|saved preference on `([a-z][a-z0-9-]*)`)\)\. Change with \/plan-tune\.$/;
|
||||
|
||||
/** Asserted prose only; later quoted examples cannot retract a current decision. */
|
||||
function publicProse(text: string): string {
|
||||
@@ -41,23 +41,34 @@ function withdrawn(text: string, option: string): boolean {
|
||||
return [...prose.matchAll(/^Review mode:\s*([^\n.]+)\.?$/gmi)].some(m => plain(m[1]!).toLowerCase() !== option.toLowerCase());
|
||||
}
|
||||
|
||||
function assertedAnnotation(text: string): RegExpExecArray | null {
|
||||
function assertedAnnotation(text: string, skillName: string): RegExpExecArray | null {
|
||||
const paragraphs = text.replace(/^(?:[ \t]*\r?\n)+|(?:\r?\n[ \t]*)+$/g, '').split(/\r?\n\s*\r?\n/);
|
||||
let index = 0;
|
||||
// A preamble notice is independent of the immediately following current
|
||||
// mode declaration. No arbitrary source/example prefix is skipped.
|
||||
if (/^Heads-up from gstack: this branch has unshipped work\. Run `\/review` then `\/ship` when you're ready\.$/.test(paragraphs[0] ?? '')) index++;
|
||||
const preambleNotice = "Heads-up from the preamble: unshipped work on this branch, so `/review` then `/ship` when you're ready. Also, gstack follows the **Boil the Ocean** principle: do the complete thing when AI makes the marginal cost near zero. Read more at https://garryslist.org/posts/boil-the-ocean if you'd like.";
|
||||
const decisionNotice = "Heads-up from gstack: there is unshipped work on this branch, so `/review` then `/ship` when you get to it.";
|
||||
if (/^Heads-up from gstack: this branch has unshipped work\. Run `\/review` then `\/ship` when you're ready\.$/.test(paragraphs[0] ?? '') || paragraphs[0] === preambleNotice || paragraphs[0] === decisionNotice) index++;
|
||||
const mode = /^\*\*Review mode:\s*([^*\n.]+)\.\*\*$/.exec(paragraphs[index] ?? '');
|
||||
if (mode) index++;
|
||||
if (index && !mode) return null;
|
||||
const decisionHeading = /^\*\*D[1-9]\d* [—–-] Review mode for the ([^*\n]+) draft\*\*$/.exec(paragraphs[index] ?? '');
|
||||
if (decisionHeading && /\b(?:example|hypothetical|historical|previous|quoted)\b/i.test(decisionHeading[1]!)) return null;
|
||||
if (mode || decisionHeading) index++;
|
||||
if (index && !mode && !decisionHeading) return null;
|
||||
const paragraph = paragraphs[index];
|
||||
if (!paragraph || /^(?: {4}|\t)/.test(paragraph) || paragraph.includes('\n')) return null;
|
||||
const match = annotationLine.exec(paragraph);
|
||||
if (!match || !plain(match[1]!) || !plain(match[2]!)) return null;
|
||||
if (decisionHeading && (!/^"Review mode:[^"]+\?"$/.test(match[1]!) ||
|
||||
!/^(?:HOLD SCOPE|SCOPE EXPANSION|SELECTIVE EXPANSION|SCOPE REDUCTION)$/.test(plain(match[2]!)))) return null;
|
||||
// The printed skill template is not a concrete observed choice.
|
||||
if (/<[^>\r\n]+>/.test(match[1]!) || /<[^>\r\n]+>/.test(match[2]!)) return null;
|
||||
// A named saved preference belongs to the invoked skill's mode, and its
|
||||
// concrete choice must agree with the adjacent current mode declaration.
|
||||
if (match[3] && (match[3] !== `${skillName}-mode` || !mode ||
|
||||
!/^(?:HOLD SCOPE|SCOPE EXPANSION|SELECTIVE EXPANSION|SCOPE REDUCTION)$/.test(plain(match[2]!)))) return null;
|
||||
if (mode && (plain(mode[1]!).toLowerCase() !== plain(match[2]!).toLowerCase() ||
|
||||
!/^(?:review mode|"Review mode:[^"]+\?")$/i.test(match[1]!))) return null;
|
||||
(!/^(?:review mode|"Review mode:[^"]+\?")$/i.test(match[1]!) &&
|
||||
!(match[3] && /^"Select review mode"$/.test(match[1]!))))) return null;
|
||||
return match;
|
||||
}
|
||||
|
||||
@@ -84,7 +95,7 @@ export function findNativeAutoDecision(
|
||||
const loadedAt = at(results[0]!.timestamp);
|
||||
for (const message of messages) {
|
||||
if (at(message.timestamp) < loadedAt) continue;
|
||||
const match = assertedAnnotation(message.text);
|
||||
const match = assertedAnnotation(message.text, opts.skillName);
|
||||
if (!match) continue;
|
||||
const option = plain(match[2]!);
|
||||
const current = messages.filter(m => at(m.timestamp) >= at(message.timestamp)).map(m => m.text).join('\n\n');
|
||||
|
||||
@@ -47,6 +47,13 @@ function completedTaskRead(text: string): string | null {
|
||||
return /(?:^|\n)\[exited with code 0\]\s*$/.test(output) ? output : null;
|
||||
}
|
||||
|
||||
/** A literal cat cannot replace, truncate or redirect the acknowledged task file. */
|
||||
function literalTaskCat(command: string, outputFile: string): boolean {
|
||||
if (!/^\/[A-Za-z0-9_./-]+$/.test(outputFile)) return false;
|
||||
return ['', '-- '].some(option => [outputFile, `"${outputFile}"`, `'${outputFile}'`]
|
||||
.some(file => command.trim() === `cat ${option}${file}`));
|
||||
}
|
||||
|
||||
export function claudeOutsideExecutions(transcript: unknown[]): OutsideExecution[] {
|
||||
const calls = new Map<string, { command?: string; name: string; input: any; session: string | null }>();
|
||||
const tasks = new Map<string, {
|
||||
@@ -77,7 +84,14 @@ export function claudeOutsideExecutions(transcript: unknown[]): OutsideExecution
|
||||
const call = calls.get(block.tool_use_id)!;
|
||||
const output = toolText(block.content);
|
||||
if (call.name === 'Bash' && typeof call.command === 'string') {
|
||||
const acknowledgment = /^Command running in background with ID: ([a-zA-Z0-9_-]+)\. Output is being written to: ([^\r\n]+)\. You will be notified when it completes\. To check interim output, use Read on that file path\.$/.exec(output);
|
||||
const readTask = [...tasks.values()].find(task => call.session === task.session &&
|
||||
sessionIdentity(event) === task.session && literalTaskCat(call.command!, task.outputFile));
|
||||
if (readTask) {
|
||||
const complete = block.is_error !== true && /(?:^|\n)\[exited with code 0\]\s*$/.test(output);
|
||||
readTask.outputs.push({ toolUseId: block.tool_use_id, output, complete });
|
||||
continue;
|
||||
}
|
||||
const acknowledgment = /^Command running in background with ID: ([a-zA-Z0-9_-]+)\. Output is being written to: ([^\r\n]+)\. You will be notified when it completes\. To check interim output, use Read on that file path\.(?:\nSession cwd remains (\/[^;\r\n]+); directory changes made by the backgrounded command do not apply to subsequent commands\.)?$/.exec(output);
|
||||
if (!acknowledgment) {
|
||||
const existing = tasks.get(block.tool_use_id);
|
||||
if (existing) {
|
||||
@@ -96,6 +110,7 @@ export function claudeOutsideExecutions(transcript: unknown[]): OutsideExecution
|
||||
results.push({ command: call.command, output, succeeded: false, background });
|
||||
const existing = tasks.get(block.tool_use_id);
|
||||
if (block.is_error === true || !call.session || sessionIdentity(event) !== call.session ||
|
||||
(acknowledgment[3] && typeof event.cwd === 'string' && acknowledgment[3] !== event.cwd) ||
|
||||
!outputFile!.endsWith(`/tasks/${taskId}.output`) || !outputFile!.startsWith('/')) {
|
||||
if (existing) existing.failed = true;
|
||||
continue;
|
||||
|
||||
@@ -0,0 +1,65 @@
|
||||
import * as fs from 'node:fs';
|
||||
import * as path from 'node:path';
|
||||
import { createHash } from 'node:crypto';
|
||||
|
||||
export interface PlanFloorTargetDelivery {
|
||||
status: 'missing' | 'ready' | 'error';
|
||||
reason?: string;
|
||||
sessionId: string;
|
||||
command: string;
|
||||
targetPath: string;
|
||||
targetSha256: string;
|
||||
acknowledgedAt?: string;
|
||||
}
|
||||
|
||||
/** The first owned native user command must name the already-seeded plan. */
|
||||
export function readPlanFloorTarget(configDir: string | null, cwd: string, opts: {
|
||||
seed: string; sessionId: string; slashCommand: string; startedAt: number; now: number;
|
||||
}): PlanFloorTargetDelivery {
|
||||
const delivery: PlanFloorTargetDelivery = {
|
||||
status: 'missing', sessionId: opts.sessionId, command: `${opts.slashCommand} PLAN.md`,
|
||||
targetPath: path.join(cwd, 'PLAN.md'), targetSha256: createHash('sha256').update(opts.seed).digest('hex'),
|
||||
};
|
||||
try {
|
||||
if (!configDir || !/^[\da-f-]{36}$/i.test(opts.sessionId) || !/^\/[\w-]+$/.test(opts.slashCommand) ||
|
||||
!Number.isFinite(opts.startedAt) || !Number.isFinite(opts.now) || opts.now < opts.startedAt) return delivery;
|
||||
if (!fs.lstatSync(delivery.targetPath).isFile() || fs.readFileSync(delivery.targetPath, 'utf8') !== opts.seed) {
|
||||
return { ...delivery, status: 'error', reason: 'Owned seed plan is missing or changed' };
|
||||
}
|
||||
const projects = path.join(configDir, 'projects');
|
||||
if (!fs.existsSync(projects)) return delivery;
|
||||
if (!fs.lstatSync(projects).isDirectory()) throw Error('Native project root is not a directory');
|
||||
const dirs = fs.readdirSync(projects, { withFileTypes: true }).filter(dir => dir.isDirectory());
|
||||
if (dirs.length > 128) throw Error('Too many native project directories');
|
||||
const files = dirs.map(dir => path.join(projects, dir.name, `${opts.sessionId}.jsonl`)).filter(file => fs.existsSync(file));
|
||||
if (files.length === 0) return delivery;
|
||||
if (files.length !== 1 || !fs.lstatSync(files[0]!).isFile()) throw Error('Ambiguous or nonregular native session');
|
||||
if (fs.statSync(files[0]!).size > 32 * 1024 * 1024) throw Error('Native session exceeds 32 MiB');
|
||||
const raw = fs.readFileSync(files[0]!, 'utf8');
|
||||
const expected = `<command-message>${opts.slashCommand.slice(1)}</command-message>\n` +
|
||||
`<command-name>${opts.slashCommand}</command-name>\n<command-args>PLAN.md</command-args>`;
|
||||
for (const line of raw.slice(0, raw.lastIndexOf('\n') + 1).split('\n')) {
|
||||
if (!line.trim()) continue;
|
||||
const record = JSON.parse(line), at = Date.parse(record.timestamp ?? '');
|
||||
if (record.type !== 'user' || record.isSidechain !== false || record.cwd !== cwd ||
|
||||
record.sessionId !== opts.sessionId || record.parent_tool_use_id || record.message?.role !== 'user' ||
|
||||
!Number.isFinite(at) || at < opts.startedAt || at > opts.now) continue;
|
||||
const content = record.message.content;
|
||||
const text = typeof content === 'string' ? content : Array.isArray(content) && content.length === 1 &&
|
||||
content[0]?.type === 'text' && typeof content[0].text === 'string' ? content[0].text : undefined;
|
||||
if (text === undefined) {
|
||||
if (Array.isArray(content) && content.some(block => block?.type === 'text')) {
|
||||
return { ...delivery, status: 'error', reason: 'First owned native user text was not one target command' };
|
||||
}
|
||||
continue; // Tool-result-only user envelopes are not submitted commands.
|
||||
}
|
||||
// A later queued target cannot repair a skill that already started bare.
|
||||
return text === expected
|
||||
? { ...delivery, status: 'ready', acknowledgedAt: record.timestamp }
|
||||
: { ...delivery, status: 'error', reason: 'First owned native user input did not name the seeded plan' };
|
||||
}
|
||||
return delivery;
|
||||
} catch (error) {
|
||||
return { ...delivery, status: 'error', reason: error instanceof Error ? error.message : String(error) };
|
||||
}
|
||||
}
|
||||
@@ -100,17 +100,22 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
|
||||
// include question-tuning.ts and generate-ask-user-format.ts because the
|
||||
// AUTO_DECIDE preamble injection lives there and changes can flip the
|
||||
// regression test outcome between 'asked' and 'auto_decided'.
|
||||
'plan-ceo-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/skill-e2e-plan-ceo-plan-mode.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/helpers/plan-scope-selection.ts', 'test/plan-scope-selection.test.ts', 'test/helpers/native-auto-decide.ts', 'test/native-auto-decide.test.ts', 'test/native-auto-decide-pty.test.ts', 'test/fixtures/native-auto-decide-ag.json'],
|
||||
'plan-eng-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-eng-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/skill-e2e-plan-eng-plan-mode.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/helpers/plan-scope-selection.ts', 'test/plan-scope-selection.test.ts', 'test/fixtures/design-plan-scope-ag.json', 'test/helpers/native-auto-decide.ts', 'test/native-auto-decide.test.ts', 'test/native-auto-decide-pty.test.ts', 'test/fixtures/native-auto-decide-ag.json'],
|
||||
'plan-design-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-design-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/skill-e2e-plan-design-plan-mode.test.ts', 'test/skill-e2e-design.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/helpers/plan-scope-selection.ts', 'test/plan-scope-selection.test.ts', 'test/fixtures/design-plan-scope-ag.json', 'test/helpers/native-auto-decide.ts', 'test/native-auto-decide.test.ts', 'test/native-auto-decide-pty.test.ts', 'test/fixtures/native-auto-decide-ag.json'],
|
||||
'plan-devex-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/skill-e2e-plan-devex-plan-mode.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/helpers/plan-scope-selection.ts', 'test/plan-scope-selection.test.ts', 'test/helpers/native-auto-decide.ts', 'test/native-auto-decide.test.ts', 'test/native-auto-decide-pty.test.ts', 'test/fixtures/native-auto-decide-ag.json'],
|
||||
'plan-ceo-review-plan-mode': [
|
||||
'test/auto-decide-saved-ai.test.ts', 'test/fixtures/auto-decide-saved-ai.json', 'test/fixtures/auto-decide-retry-ai.json','bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/skill-e2e-plan-ceo-plan-mode.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/helpers/plan-scope-selection.ts', 'test/plan-scope-selection.test.ts', 'test/helpers/native-auto-decide.ts', 'test/native-auto-decide.test.ts', 'test/native-auto-decide-pty.test.ts', 'test/fixtures/native-auto-decide-ag.json', 'test/eng-seeded-completion-ai.test.ts', 'test/fixtures/eng-seeded-completion-ai.json', 'test/helpers/plan-count-pending-exit.ts', 'test/plan-count-pending-exit.test.ts', 'test/helpers/pty-screen.ts', 'test/pty-screen.test.ts', 'test/pty-screen-session.test.ts', 'test/fixtures/pty-screen/**'],
|
||||
'plan-eng-review-plan-mode': [
|
||||
'test/auto-decide-saved-ai.test.ts', 'test/fixtures/auto-decide-saved-ai.json', 'test/fixtures/auto-decide-retry-ai.json','bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-eng-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/skill-e2e-plan-eng-plan-mode.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/helpers/plan-scope-selection.ts', 'test/plan-scope-selection.test.ts', 'test/fixtures/design-plan-scope-ag.json', 'test/helpers/native-auto-decide.ts', 'test/native-auto-decide.test.ts', 'test/native-auto-decide-pty.test.ts', 'test/fixtures/native-auto-decide-ag.json', 'test/eng-seeded-completion-ai.test.ts', 'test/fixtures/eng-seeded-completion-ai.json', 'test/helpers/plan-count-pending-exit.ts', 'test/plan-count-pending-exit.test.ts', 'test/helpers/pty-screen.ts', 'test/pty-screen.test.ts', 'test/pty-screen-session.test.ts', 'test/fixtures/pty-screen/**'],
|
||||
'plan-design-review-plan-mode': [
|
||||
'test/auto-decide-saved-ai.test.ts', 'test/fixtures/auto-decide-saved-ai.json', 'test/fixtures/auto-decide-retry-ai.json','bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-design-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/skill-e2e-plan-design-plan-mode.test.ts', 'test/skill-e2e-design.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/helpers/plan-scope-selection.ts', 'test/plan-scope-selection.test.ts', 'test/fixtures/design-plan-scope-ag.json', 'test/helpers/native-auto-decide.ts', 'test/native-auto-decide.test.ts', 'test/native-auto-decide-pty.test.ts', 'test/fixtures/native-auto-decide-ag.json', 'test/eng-seeded-completion-ai.test.ts', 'test/fixtures/eng-seeded-completion-ai.json', 'test/helpers/plan-count-pending-exit.ts', 'test/plan-count-pending-exit.test.ts', 'test/helpers/pty-screen.ts', 'test/pty-screen.test.ts', 'test/pty-screen-session.test.ts', 'test/fixtures/pty-screen/**'],
|
||||
'plan-devex-review-plan-mode': [
|
||||
'test/auto-decide-saved-ai.test.ts', 'test/fixtures/auto-decide-saved-ai.json', 'test/fixtures/auto-decide-retry-ai.json','bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/skill-e2e-plan-devex-plan-mode.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/helpers/plan-scope-selection.ts', 'test/plan-scope-selection.test.ts', 'test/helpers/native-auto-decide.ts', 'test/native-auto-decide.test.ts', 'test/native-auto-decide-pty.test.ts', 'test/fixtures/native-auto-decide-ag.json', 'test/eng-seeded-completion-ai.test.ts', 'test/fixtures/eng-seeded-completion-ai.json', 'test/helpers/plan-count-pending-exit.ts', 'test/plan-count-pending-exit.test.ts', 'test/helpers/pty-screen.ts', 'test/pty-screen.test.ts', 'test/pty-screen-session.test.ts', 'test/fixtures/pty-screen/**'],
|
||||
// Covers ceo (preamble misfire) + eng/design (scope-gate bypass must not
|
||||
// fire outside plan mode) + the named-target exception case. 4 PTY runs;
|
||||
// in CI these run CONCURRENT with the rest of the pty-plan-smoke suite
|
||||
// (--max-concurrency + --retry 1), so worst-case cost is ~2x a single
|
||||
// pass of each, sharing the API budget with sibling tests — not the
|
||||
// sequential ~+10min a local read suggests.
|
||||
'plan-mode-no-op': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/preamble.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/skill-e2e-plan-mode-no-op.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/helpers/plan-scope-selection.ts', 'test/plan-scope-selection.test.ts', 'test/helpers/native-auto-decide.ts', 'test/native-auto-decide.test.ts', 'test/native-auto-decide-pty.test.ts', 'test/fixtures/native-auto-decide-ag.json'],
|
||||
'plan-mode-no-op': [
|
||||
'test/auto-decide-saved-ai.test.ts', 'test/fixtures/auto-decide-saved-ai.json', 'test/fixtures/auto-decide-retry-ai.json','bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/preamble.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/skill-e2e-plan-mode-no-op.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/helpers/plan-scope-selection.ts', 'test/plan-scope-selection.test.ts', 'test/helpers/native-auto-decide.ts', 'test/native-auto-decide.test.ts', 'test/native-auto-decide-pty.test.ts', 'test/fixtures/native-auto-decide-ag.json', 'test/eng-seeded-completion-ai.test.ts', 'test/fixtures/eng-seeded-completion-ai.json', 'test/helpers/plan-count-pending-exit.ts', 'test/plan-count-pending-exit.test.ts', 'test/helpers/pty-screen.ts', 'test/pty-screen.test.ts', 'test/pty-screen-session.test.ts', 'test/fixtures/pty-screen/**'],
|
||||
|
||||
// v1.21+ AskUserQuestion-blocked regression tests — Conductor launches
|
||||
// claude with `--disallowedTools AskUserQuestion --permission-mode default`
|
||||
@@ -128,12 +133,14 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
|
||||
// written a never-ask preference, AUQ should still auto-decide rather than
|
||||
// surfacing the question. Touches the question-tuning + preference
|
||||
// infrastructure plus the resolvers that own the AUTO_DECIDE preamble.
|
||||
'auto-decide-preserved': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'bin/gstack-session-kind', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'plan-ceo-review/**', 'bin/gstack-question-preference', 'bin/gstack-config', 'bin/gstack-slug', 'hosts/claude/hooks/question-preference-hook.ts', 'hosts/claude/hooks/spawned-directive.ts', 'lib/is-conductor.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/skill-e2e-auto-decide-preserved.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/helpers/native-auto-decide.ts', 'test/native-auto-decide.test.ts', 'test/native-auto-decide-pty.test.ts', 'test/fixtures/native-auto-decide-ag.json'],
|
||||
'auto-decide-preserved': [
|
||||
'test/auto-decide-saved-ai.test.ts', 'test/fixtures/auto-decide-saved-ai.json', 'test/fixtures/auto-decide-retry-ai.json','bin/gstack-skill-start', 'bin/gstack-skill-end', 'bin/gstack-session-kind', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'plan-ceo-review/**', 'bin/gstack-question-preference', 'bin/gstack-config', 'bin/gstack-slug', 'hosts/claude/hooks/question-preference-hook.ts', 'hosts/claude/hooks/spawned-directive.ts', 'lib/is-conductor.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/skill-e2e-auto-decide-preserved.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/helpers/native-auto-decide.ts', 'test/native-auto-decide.test.ts', 'test/native-auto-decide-pty.test.ts', 'test/fixtures/native-auto-decide-ag.json', 'test/eng-seeded-completion-ai.test.ts', 'test/fixtures/eng-seeded-completion-ai.json', 'test/helpers/plan-count-pending-exit.ts', 'test/plan-count-pending-exit.test.ts', 'test/helpers/pty-screen.ts', 'test/pty-screen.test.ts', 'test/pty-screen-session.test.ts', 'test/fixtures/pty-screen/**'],
|
||||
|
||||
// Conductor → prose decision brief (Conductor signal makes prose the default;
|
||||
// the PreToolUse hook denies the flaky tool). Touches the resolver that owns
|
||||
// the Conductor rule, the preamble signal, the hook, and the detection helper.
|
||||
'conductor-prose': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'bin/gstack-session-kind', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble.ts', 'plan-eng-review/**', 'hosts/claude/hooks/question-preference-hook.ts', 'hosts/claude/hooks/spawned-directive.ts', 'lib/is-conductor.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/skill-e2e-conductor-prose.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/helpers/native-auto-decide.ts', 'test/native-auto-decide.test.ts', 'test/native-auto-decide-pty.test.ts', 'test/fixtures/native-auto-decide-ag.json'],
|
||||
'conductor-prose': [
|
||||
'test/auto-decide-saved-ai.test.ts', 'test/fixtures/auto-decide-saved-ai.json', 'test/fixtures/auto-decide-retry-ai.json','bin/gstack-skill-start', 'bin/gstack-skill-end', 'bin/gstack-session-kind', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble.ts', 'plan-eng-review/**', 'hosts/claude/hooks/question-preference-hook.ts', 'hosts/claude/hooks/spawned-directive.ts', 'lib/is-conductor.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/skill-e2e-conductor-prose.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/helpers/native-auto-decide.ts', 'test/native-auto-decide.test.ts', 'test/native-auto-decide-pty.test.ts', 'test/fixtures/native-auto-decide-ag.json', 'test/eng-seeded-completion-ai.test.ts', 'test/fixtures/eng-seeded-completion-ai.json', 'test/helpers/plan-count-pending-exit.ts', 'test/plan-count-pending-exit.test.ts', 'test/helpers/pty-screen.ts', 'test/pty-screen.test.ts', 'test/pty-screen-session.test.ts', 'test/fixtures/pty-screen/**'],
|
||||
|
||||
// Real-PTY E2E batch (#6 new tests on the harness).
|
||||
// Each one tests behavior the SDK harness can't observe (rendered TTY,
|
||||
@@ -148,21 +155,21 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
|
||||
'tpa-absent-darwin': ['scripts/resolvers/third-party-actions.ts', 'ship/SKILL.md.tmpl', 'ship/sections/apple-release.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/helpers/session-runner.ts', 'test/skill-e2e-third-party-actions.test.ts', 'test/helpers/third-party-actions.ts'],
|
||||
'tpa-apple-ban': ['scripts/resolvers/third-party-actions.ts', 'ship/SKILL.md.tmpl', 'ship/sections/apple-release.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/helpers/session-runner.ts', 'test/skill-e2e-third-party-actions.test.ts', 'test/helpers/third-party-actions.ts'],
|
||||
'ship-section-loading': ['ship/**', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/session-runner-tools.test.ts', 'test/skill-e2e-ship-section-loading.test.ts'],
|
||||
'plan-ceo-section-loading': ['plan-ceo-review/**', 'test/skill-ceo-section-ordering.test.ts', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/session-runner-tools.test.ts', 'test/helpers/ceo-section-loading-fixture.ts', 'test/ceo-section-loading-fixture.test.ts', 'test/skill-e2e-plan-ceo-review-section-loading.test.ts', 'test/fixtures/ceo-section-loading-l-report.md', 'test/fixtures/ceo-section-loading-q-report.md', 'test/fixtures/ceo-section-r-rejected-report.md', 'test/fixtures/ceo-section-s-trace-report.md', 'test/fixtures/ceo-section-u-report.md', 'test/fixtures/ceo-section-y-report.md', 'test/fixtures/ceo-section-aa-report.md', 'test/sdk-stale-table-ad-v3.test.ts', 'test/fixtures/sdk-stale-table-ad-v3.json', 'test/sdk-ordering-ae.test.ts', 'test/fixtures/sdk-ordering-ae.json', 'test/sdk-columnar-af.test.ts', 'test/fixtures/sdk-columnar-af.json', 'test/sdk-order-b-ag.test.ts', 'test/fixtures/sdk-order-b-ag.json', 'test/sdk-schedule-continuation-ah.test.ts', 'test/fixtures/sdk-schedule-continuation-ah.json'],
|
||||
'plan-ceo-section-loading': ['plan-ceo-review/**', 'test/skill-ceo-section-ordering.test.ts', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/session-runner-tools.test.ts', 'test/helpers/ceo-section-loading-fixture.ts', 'test/ceo-section-loading-fixture.test.ts', 'test/skill-e2e-plan-ceo-review-section-loading.test.ts', 'test/fixtures/ceo-section-loading-l-report.md', 'test/fixtures/ceo-section-loading-q-report.md', 'test/fixtures/ceo-section-r-rejected-report.md', 'test/fixtures/ceo-section-s-trace-report.md', 'test/fixtures/ceo-section-u-report.md', 'test/fixtures/ceo-section-y-report.md', 'test/fixtures/ceo-section-aa-report.md', 'test/sdk-stale-table-ad-v3.test.ts', 'test/fixtures/sdk-stale-table-ad-v3.json', 'test/sdk-ordering-ae.test.ts', 'test/fixtures/sdk-ordering-ae.json', 'test/sdk-columnar-af.test.ts', 'test/fixtures/sdk-columnar-af.json', 'test/sdk-order-b-ag.test.ts', 'test/fixtures/sdk-order-b-ag.json', 'test/sdk-schedule-continuation-ah.test.ts', 'test/fixtures/sdk-schedule-continuation-ah.json', 'test/sdk-original-order-ai.test.ts', 'test/fixtures/sdk-original-order-ai.json'],
|
||||
// Data-driven behavioral guard for the 'plan'/'prompt' carves (eng, design,
|
||||
// devex, office-hours + future PR2 carves). One file iterating CARVE_GUARDS;
|
||||
// the selector sets GSTACK_CARVE_SKILL=<name> to scope cost to the changed
|
||||
// skill (D-CODEX A). Touching the registry/helper or sections.ts runs all.
|
||||
'carve-section-loading': ['scripts/resolvers/composition.ts', 'test/autoplan-review-discovery.test.ts', 'test/autoplan-phase-order.test.ts', 'design-html/**', 'design-shotgun/**', 'qa/**', 'browse/**', 'retro/**', 'autoplan/**', 'spec/**', 'setup-gbrain/**', 'review/**', 'codex/**', 'land-and-deploy/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'office-hours/**', 'document-release/**', 'design-consultation/**', 'cso/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/session-runner-tools.test.ts', 'test/carve-section-loading.test.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/autoplan-snapshot.test.ts', 'test/autoplan-init.test.ts', 'test/autoplan-obligations.test.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json'],
|
||||
'autoplan-chain-pty': ['scripts/resolvers/composition.ts', 'test/autoplan-review-discovery.test.ts', 'test/autoplan-phase-order.test.ts', 'autoplan/**', 'plan-ceo-review/**', 'plan-design-review/**', 'plan-eng-review/**', 'plan-devex-review/**', 'test/fixtures/plans/autoplan-dashboard.md', 'test/autoplan-chain-fixture.test.ts', 'test/helpers/plan-count-fixture.ts', 'test/plan-count-fixture.test.ts', 'test/plan-count-prerequisite-n.test.ts', 'test/fixtures/ceo-prerequisite-n-call.json', 'bin/gstack-config', 'test/helpers/claude-pty-runner.ts', 'test/plan-count-native-input.test.ts', 'test/helpers/pty-screen.ts', 'test/pty-screen.test.ts', 'test/pty-screen-session.test.ts', 'test/fixtures/pty-screen/**', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/helpers/autoplan-setup-question.ts', 'test/autoplan-setup-question.test.ts', 'test/helpers/autoplan-phase-observer.ts', 'test/autoplan-phase-observer.test.ts', 'test/helpers/plan-count-transcript.ts', 'test/autoplan-public-narration.test.ts', 'test/fixtures/autoplan-public-narration-ad.json', 'test/plan-count-transcript.test.ts', 'test/helpers/plan-count-artifacts.ts', 'test/plan-count-artifacts.test.ts', 'test/skill-e2e-autoplan-chain.test.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/autoplan-snapshot.test.ts', 'test/autoplan-init.test.ts', 'test/autoplan-obligations.test.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/plan-count-checkbox.test.ts', 'test/fixtures/ceo-checkbox-l.screen.txt', 'test/helpers/eval-budgets.ts', 'test/autoplan-eval-budget.test.ts', 'test/eval-budgets-policy.test.ts', 'test/eval-detach-timeout-floor.test.ts', 'scripts/test-paid-shards.ts', '.github/workflows/evals-periodic.yml', 'test/fixtures/autoplan-routing-n-screen.txt', 'test/autoplan-routing-o.test.ts', 'test/fixtures/autoplan-routing-o-screen.txt', 'test/autoplan-setup-packet-o.test.ts', 'test/fixtures/autoplan-setup-packet-o-screen.txt', 'test/fixtures/autoplan-setup-packet-o-call.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'test/fixtures/autoplan-setup-z-packet.json', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/helpers/autoplan-method-read-audit.ts', 'test/autoplan-method-read-audit.test.ts', 'test/fixtures/autoplan-method-read-aa-events.json', 'test/autoplan-routing-manual-skills.test.ts', 'test/fixtures/autoplan-routing-manual-skills-ac.json', 'test/helpers/plan-count-pending-question.ts', 'test/autoplan-pending-question.test.ts', 'test/plan-pending-question-pty.test.ts', 'test/pending-question-completion.test.ts', 'test/fixtures/pending-question-completion-ad.json', 'test/fixtures/autoplan-setup-ad-v2-packet.json', 'test/helpers/autoplan-artifact-permission.ts', 'test/autoplan-artifact-permission.test.ts', 'test/fixtures/autoplan-artifact-permission-ad-v3.json', 'scripts/resolvers/testing.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/autoplan-artifact-recorder.test.ts', 'test/autoplan-pending-artifact.test.ts', 'test/fixtures/autoplan-pending-artifact-ae.json', 'test/autoplan-edit-header-ag.test.ts', 'test/fixtures/autoplan-edit-header-ag.json'],
|
||||
'autoplan-chain-pty': ['scripts/resolvers/composition.ts', 'test/autoplan-review-discovery.test.ts', 'test/autoplan-phase-order.test.ts', 'autoplan/**', 'plan-ceo-review/**', 'plan-design-review/**', 'plan-eng-review/**', 'plan-devex-review/**', 'test/fixtures/plans/autoplan-dashboard.md', 'test/autoplan-chain-fixture.test.ts', 'test/helpers/plan-count-fixture.ts', 'test/plan-count-fixture.test.ts', 'test/plan-count-prerequisite-n.test.ts', 'test/fixtures/ceo-prerequisite-n-call.json', 'bin/gstack-config', 'test/helpers/claude-pty-runner.ts', 'test/plan-count-native-input.test.ts', 'test/helpers/pty-screen.ts', 'test/pty-screen.test.ts', 'test/pty-screen-session.test.ts', 'test/fixtures/pty-screen/**', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/helpers/autoplan-setup-question.ts', 'test/autoplan-setup-question.test.ts', 'test/helpers/autoplan-phase-observer.ts', 'test/autoplan-phase-observer.test.ts', 'test/helpers/plan-count-transcript.ts', 'test/autoplan-public-narration.test.ts', 'test/fixtures/autoplan-public-narration-ad.json', 'test/plan-count-transcript.test.ts', 'test/helpers/plan-count-artifacts.ts', 'test/plan-count-artifacts.test.ts', 'test/skill-e2e-autoplan-chain.test.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/autoplan-snapshot.test.ts', 'test/autoplan-init.test.ts', 'test/autoplan-obligations.test.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/plan-count-checkbox.test.ts', 'test/fixtures/ceo-checkbox-l.screen.txt', 'test/helpers/eval-budgets.ts', 'test/autoplan-eval-budget.test.ts', 'test/eval-budgets-policy.test.ts', 'test/eval-detach-timeout-floor.test.ts', 'scripts/test-paid-shards.ts', '.github/workflows/evals-periodic.yml', 'test/fixtures/autoplan-routing-n-screen.txt', 'test/autoplan-routing-o.test.ts', 'test/fixtures/autoplan-routing-o-screen.txt', 'test/autoplan-setup-packet-o.test.ts', 'test/fixtures/autoplan-setup-packet-o-screen.txt', 'test/fixtures/autoplan-setup-packet-o-call.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'test/fixtures/autoplan-setup-z-packet.json', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/helpers/autoplan-method-read-audit.ts', 'test/autoplan-method-read-audit.test.ts', 'test/fixtures/autoplan-method-read-aa-events.json', 'test/autoplan-routing-manual-skills.test.ts', 'test/fixtures/autoplan-routing-manual-skills-ac.json', 'test/helpers/plan-count-pending-question.ts', 'test/autoplan-pending-question.test.ts', 'test/plan-pending-question-pty.test.ts', 'test/pending-question-completion.test.ts', 'test/fixtures/pending-question-completion-ad.json', 'test/fixtures/autoplan-setup-ad-v2-packet.json', 'test/helpers/autoplan-artifact-permission.ts', 'test/autoplan-artifact-permission.test.ts', 'test/fixtures/autoplan-artifact-permission-ad-v3.json', 'scripts/resolvers/testing.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/autoplan-artifact-recorder.test.ts', 'test/autoplan-pending-artifact.test.ts', 'test/fixtures/autoplan-pending-artifact-ae.json', 'test/autoplan-edit-header-ag.test.ts', 'test/fixtures/autoplan-edit-header-ag.json', 'test/autoplan-edit-prefix-ai.test.ts', 'test/fixtures/autoplan-edit-prefix-ai.json'],
|
||||
|
||||
// Per-finding AskUserQuestion count + review-report-at-bottom assertion.
|
||||
// Each test drives its skill end-to-end; touchfiles include preamble +
|
||||
// completion-status resolvers because they affect question cadence and
|
||||
// terminal output (the regression surface this test catches).
|
||||
'plan-ceo-finding-count': ['bin/gstack-config', 'bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'test/skill-ceo-section-ordering.test.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/claude-pty-runner.ts', 'test/plan-count-native-input.test.ts', 'test/helpers/pty-screen.ts', 'test/pty-screen.test.ts', 'test/pty-screen-session.test.ts', 'test/fixtures/pty-screen/**', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/claude-pty-runner.unit.test.ts', 'test/plan-count-completion.test.ts', 'test/plan-count-dx-handoff.test.ts', 'test/fixtures/devex-handoff-n-call.json', 'test/helpers/ceo-completion-handoff.ts', 'test/ceo-completion-handoff.test.ts', 'test/ceo-count-s-terminals.test.ts', 'test/fixtures/ceo-count-s-paired.json', 'test/fixtures/ceo-completion-handoff-calls.json', 'test/fixtures/ceo-completion-handoff-j-calls.json', 'test/fixtures/ceo-completion-handoff-k-calls.json', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/helpers/plan-count-transcript.ts', 'test/autoplan-public-narration.test.ts', 'test/fixtures/autoplan-public-narration-ad.json', 'test/helpers/plan-count-pending-exit.ts', 'test/plan-count-pending-exit.test.ts', 'test/plan-count-transcript.test.ts', 'test/helpers/plan-count-artifacts.ts', 'test/plan-count-artifacts.test.ts', 'test/helpers/eval-store.ts', 'test/helpers/plan-count-fixture.ts', 'test/plan-count-fixture.test.ts', 'test/plan-count-timeout.test.ts', 'test/plan-count-navigation-r.test.ts', 'test/plan-count-prerequisite-n.test.ts', 'test/fixtures/ceo-prerequisite-n-call.json', 'test/skill-e2e-plan-ceo-finding-count.test.ts', 'test/ceo-completion-handoff-l.test.ts', 'test/fixtures/ceo-completion-handoff-l-calls.json', 'test/ceo-completion-handoff-m.test.ts', 'test/fixtures/ceo-completion-handoff-m-call.json', 'test/fixtures/devex-review-l-calls.json', 'test/plan-count-checkbox.test.ts', 'test/fixtures/ceo-checkbox-l.screen.txt', 'test/fixtures/ceo-handoff-n-calls.json', 'test/ceo-completion-handoff-o.test.ts', 'test/fixtures/ceo-completion-handoff-o-call.json', 'test/plan-count-empty-review.test.ts', 'test/fixtures/ceo-count-s-distinct.json', 'test/fixtures/plan-count-design-questionless-report.md', 'test/plan-count-dx-handoff-o.test.ts', 'test/fixtures/devex-handoff-o-call.json', 'test/helpers/ceo-approach-pick.ts', 'test/ceo-approach-pick.test.ts', 'test/fixtures/ceo-approach-q-call.json', 'test/fixtures/ceo-approach-r-call.json', 'test/fixtures/ceo-approach-r-distinct-call.json', 'test/fixtures/ceo-approach-q-paired-call.json', 'test/fixtures/ceo-completion-handoff-q-call.json', 'test/fixtures/ceo-completion-handoff-r-calls.json', 'test/fixtures/ceo-completion-handoff-t-call.json', 'test/helpers/plan-count-file-permission.ts', 'test/plan-count-file-permission.test.ts', 'test/fixtures/plan-count-edit-permission-t.json', 'test/plan-count-preview-footer.test.ts', 'test/fixtures/ceo-preview-u-call.json', 'test/fixtures/ceo-preview-u-screen.txt', 'test/fixtures/ceo-completion-handoff-u-call.json', 'test/fixtures/ceo-completion-handoff-v-call.json', 'test/fixtures/design-preview-v-screen.txt', 'test/plan-count-owned-permission.test.ts', 'test/fixtures/plan-count-owned-permission-v.json', 'test/fixtures/ceo-questionless-w-native.json', 'test/plan-count-ceo-body-finding.test.ts', 'test/fixtures/ceo-count-w-paired.json', 'test/fixtures/ceo-completion-handoff-w-call.json', 'test/fixtures/ceo-approach-y-call.json', 'test/fixtures/ceo-approach-y-screen.txt', 'test/ceo-handoff-y.test.ts', 'test/fixtures/ceo-handoff-y-call.json', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/fixtures/ceo-handoff-z-call.json', 'test/fixtures/ceo-approach-aa-call.json', 'test/review-handoffs-aa.test.ts', 'test/fixtures/review-handoff-aa-ceo.json', 'test/fixtures/review-handoff-aa-dx.json', 'test/helpers/ceo-mode-option.ts', 'test/ceo-count-mode.test.ts', 'test/fixtures/ceo-count-mode-ab-call.json', 'test/ceo-count-ac.test.ts', 'test/fixtures/ceo-count-ac-calls.json', 'test/fixtures/ceo-count-ac-later-calls.json', 'test/plan-count-permission-ac.test.ts', 'test/fixtures/plan-count-permission-ac.json', 'test/fixtures/plan-count-permission-ad.json', 'test/fixtures/plan-count-permission-ae.json', 'test/ceo-count-ad-v2.test.ts', 'test/fixtures/ceo-count-ad-v2.json', 'test/fixtures/plan-count-permission-target-ad-v2.json', 'test/fixtures/ceo-finding-alias-af.json', 'test/fixtures/ceo-numbered-brief-af.json', 'test/ceo-contract-assertions-ag.test.ts', 'test/fixtures/ceo-contract-assertions-ag.json', 'test/fixtures/ceo-contract-assertions-ag-retry.json', 'test/fixtures/plan-count-permission-ah.json', 'test/ceo-parenthesized-issue-ah.test.ts', 'test/fixtures/ceo-parenthesized-issue-ah.json'],
|
||||
'plan-eng-finding-count': ['bin/gstack-config', 'bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-eng-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/claude-pty-runner.ts', 'test/plan-count-native-input.test.ts', 'test/helpers/pty-screen.ts', 'test/pty-screen.test.ts', 'test/pty-screen-session.test.ts', 'test/fixtures/pty-screen/**', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/claude-pty-runner.unit.test.ts', 'test/plan-count-completion.test.ts', 'test/plan-count-dx-handoff.test.ts', 'test/fixtures/devex-handoff-n-call.json', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/helpers/plan-count-transcript.ts', 'test/autoplan-public-narration.test.ts', 'test/fixtures/autoplan-public-narration-ad.json', 'test/helpers/plan-count-pending-exit.ts', 'test/plan-count-pending-exit.test.ts', 'test/plan-count-transcript.test.ts', 'test/helpers/plan-count-artifacts.ts', 'test/plan-count-artifacts.test.ts', 'test/helpers/eval-store.ts', 'test/helpers/plan-count-fixture.ts', 'test/plan-count-fixture.test.ts', 'test/plan-count-timeout.test.ts', 'test/plan-count-navigation-r.test.ts', 'test/plan-count-prerequisite-n.test.ts', 'test/fixtures/ceo-prerequisite-n-call.json', 'test/skill-e2e-plan-eng-finding-count.test.ts', 'test/fixtures/devex-review-l-calls.json', 'test/plan-count-checkbox.test.ts', 'test/fixtures/ceo-checkbox-l.screen.txt', 'test/plan-count-empty-review.test.ts', 'test/fixtures/ceo-count-s-distinct.json', 'test/fixtures/plan-count-design-questionless-report.md', 'test/plan-count-dx-handoff-o.test.ts', 'test/fixtures/devex-handoff-o-call.json', 'test/eng-devex-s-count.test.ts', 'test/fixtures/eng-devex-s-first-calls.json', 'test/fixtures/eng-devex-s-retry-calls.json', 'test/helpers/plan-count-file-permission.ts', 'test/plan-count-file-permission.test.ts', 'test/fixtures/plan-count-edit-permission-t.json', 'test/eng-first-review-t.test.ts', 'test/fixtures/eng-batching-t-calls.json', 'test/plan-count-preview-footer.test.ts', 'test/fixtures/ceo-preview-u-call.json', 'test/fixtures/ceo-preview-u-screen.txt', 'test/fixtures/design-preview-v-screen.txt', 'test/plan-count-owned-permission.test.ts', 'test/fixtures/plan-count-owned-permission-v.json', 'test/fixtures/ceo-questionless-w-native.json', 'test/eng-scope-y.test.ts', 'test/fixtures/eng-scope-y-calls.json', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/eng-binding-z.test.ts', 'test/fixtures/eng-binding-z-calls.json', 'test/eng-binding-retry-z.test.ts', 'test/fixtures/eng-binding-retry-z-calls.json', 'test/plan-count-permission-ac.test.ts', 'test/fixtures/plan-count-permission-ac.json', 'test/fixtures/plan-count-permission-ad.json', 'test/fixtures/plan-count-permission-ae.json', 'test/fixtures/plan-count-permission-target-ad-v2.json', 'test/helpers/eng-completion-handoff.ts', 'test/eng-count-ad-v2.test.ts', 'test/fixtures/eng-count-ad-v2.json', 'test/helpers/eng-seeded-coverage.ts', 'test/eng-seeded-coverage.test.ts', 'test/eng-seeded-packet-ae.test.ts', 'test/fixtures/eng-seeded-packet-ae.json', 'test/eng-first-category-af.test.ts', 'test/fixtures/eng-first-category-af.json', 'test/eng-regression-pinning-ag.test.ts', 'test/fixtures/eng-regression-pinning-ag.json', 'test/fixtures/plan-count-permission-ah.json', 'test/eng-next-handoff-ah.test.ts', 'test/fixtures/eng-next-handoff-ah.json'],
|
||||
'plan-design-finding-count': ['bin/gstack-config', 'bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-design-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/claude-pty-runner.ts', 'test/plan-count-native-input.test.ts', 'test/helpers/pty-screen.ts', 'test/pty-screen.test.ts', 'test/pty-screen-session.test.ts', 'test/fixtures/pty-screen/**', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/claude-pty-runner.unit.test.ts', 'test/plan-count-completion.test.ts', 'test/plan-count-dx-handoff.test.ts', 'test/fixtures/devex-handoff-n-call.json', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/helpers/plan-count-transcript.ts', 'test/autoplan-public-narration.test.ts', 'test/fixtures/autoplan-public-narration-ad.json', 'test/helpers/plan-count-pending-exit.ts', 'test/plan-count-pending-exit.test.ts', 'test/plan-count-transcript.test.ts', 'test/helpers/plan-count-artifacts.ts', 'test/plan-count-artifacts.test.ts', 'test/helpers/eval-store.ts', 'test/helpers/plan-count-fixture.ts', 'test/plan-count-fixture.test.ts', 'test/plan-count-timeout.test.ts', 'test/plan-count-navigation-r.test.ts', 'test/plan-count-prerequisite-n.test.ts', 'test/fixtures/ceo-prerequisite-n-call.json', 'test/helpers/design-count-review.ts', 'test/design-count-review.test.ts', 'test/fixtures/design-review-j-calls.json', 'test/helpers/design-count-outside.ts', 'test/design-count-outside.test.ts', 'test/skill-e2e-plan-design-finding-count.test.ts', 'test/fixtures/design-review-l-calls.json', 'test/design-completion-handoff.test.ts', 'test/fixtures/design-handoff-l-calls.json', 'test/fixtures/devex-review-l-calls.json', 'test/plan-count-checkbox.test.ts', 'test/fixtures/ceo-checkbox-l.screen.txt', 'test/fixtures/design-review-n-calls.json', 'test/design-completion-handoff-scored.test.ts', 'test/fixtures/design-handoff-n-calls.json', 'test/fixtures/design-handoff-q-calls.json', 'test/plan-count-empty-review.test.ts', 'test/fixtures/ceo-count-s-distinct.json', 'test/fixtures/plan-count-design-questionless-report.md', 'test/plan-count-dx-handoff-o.test.ts', 'test/fixtures/devex-handoff-o-call.json', 'test/helpers/plan-count-file-permission.ts', 'test/plan-count-file-permission.test.ts', 'test/fixtures/plan-count-edit-permission-t.json', 'test/plan-count-preview-footer.test.ts', 'test/fixtures/ceo-preview-u-call.json', 'test/fixtures/ceo-preview-u-screen.txt', 'test/design-completion-handoff-u.test.ts', 'test/fixtures/design-handoff-u-calls.json', 'test/fixtures/design-preview-v-screen.txt', 'test/plan-count-owned-permission.test.ts', 'test/fixtures/plan-count-owned-permission-v.json', 'test/fixtures/ceo-questionless-w-native.json', 'test/helpers/design-artifact-question.ts', 'test/design-artifact-question.test.ts', 'test/fixtures/design-artifacts-w-calls.json', 'test/fixtures/design-outside-y-calls.json', 'test/fixtures/design-boundaries-y-calls.json', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/fixtures/design-gap-z-calls.json', 'test/plan-count-permission-ac.test.ts', 'test/fixtures/plan-count-permission-ac.json', 'test/fixtures/plan-count-permission-ad.json', 'test/fixtures/plan-count-permission-ae.json', 'test/fixtures/plan-count-permission-target-ad-v2.json', 'test/design-count-ad-v2.test.ts', 'test/fixtures/design-count-ad-v2.json', 'test/design-first-decision-af.test.ts', 'test/fixtures/design-first-decision-af.json', 'test/fixtures/design-first-decision-af-retry.json', 'test/fixtures/plan-count-permission-ah.json'],
|
||||
'plan-ceo-finding-count': ['bin/gstack-config', 'bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'test/skill-ceo-section-ordering.test.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/claude-pty-runner.ts', 'test/plan-count-native-input.test.ts', 'test/helpers/pty-screen.ts', 'test/pty-screen.test.ts', 'test/pty-screen-session.test.ts', 'test/fixtures/pty-screen/**', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/claude-pty-runner.unit.test.ts', 'test/plan-count-completion.test.ts', 'test/plan-count-dx-handoff.test.ts', 'test/fixtures/devex-handoff-n-call.json', 'test/helpers/ceo-completion-handoff.ts', 'test/ceo-completion-handoff.test.ts', 'test/ceo-count-s-terminals.test.ts', 'test/fixtures/ceo-count-s-paired.json', 'test/fixtures/ceo-completion-handoff-calls.json', 'test/fixtures/ceo-completion-handoff-j-calls.json', 'test/fixtures/ceo-completion-handoff-k-calls.json', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/helpers/plan-count-transcript.ts', 'test/autoplan-public-narration.test.ts', 'test/fixtures/autoplan-public-narration-ad.json', 'test/helpers/plan-count-pending-exit.ts', 'test/plan-count-pending-exit.test.ts', 'test/plan-count-transcript.test.ts', 'test/helpers/plan-count-artifacts.ts', 'test/plan-count-artifacts.test.ts', 'test/helpers/eval-store.ts', 'test/helpers/plan-count-fixture.ts', 'test/plan-count-fixture.test.ts', 'test/plan-count-timeout.test.ts', 'test/plan-count-navigation-r.test.ts', 'test/plan-count-prerequisite-n.test.ts', 'test/fixtures/ceo-prerequisite-n-call.json', 'test/skill-e2e-plan-ceo-finding-count.test.ts', 'test/ceo-completion-handoff-l.test.ts', 'test/fixtures/ceo-completion-handoff-l-calls.json', 'test/ceo-completion-handoff-m.test.ts', 'test/fixtures/ceo-completion-handoff-m-call.json', 'test/fixtures/devex-review-l-calls.json', 'test/plan-count-checkbox.test.ts', 'test/fixtures/ceo-checkbox-l.screen.txt', 'test/fixtures/ceo-handoff-n-calls.json', 'test/ceo-completion-handoff-o.test.ts', 'test/fixtures/ceo-completion-handoff-o-call.json', 'test/plan-count-empty-review.test.ts', 'test/fixtures/ceo-count-s-distinct.json', 'test/fixtures/plan-count-design-questionless-report.md', 'test/plan-count-dx-handoff-o.test.ts', 'test/fixtures/devex-handoff-o-call.json', 'test/helpers/ceo-approach-pick.ts', 'test/ceo-approach-pick.test.ts', 'test/fixtures/ceo-approach-q-call.json', 'test/fixtures/ceo-approach-r-call.json', 'test/fixtures/ceo-approach-r-distinct-call.json', 'test/fixtures/ceo-approach-q-paired-call.json', 'test/fixtures/ceo-completion-handoff-q-call.json', 'test/fixtures/ceo-completion-handoff-r-calls.json', 'test/fixtures/ceo-completion-handoff-t-call.json', 'test/helpers/plan-count-file-permission.ts', 'test/plan-count-file-permission.test.ts', 'test/fixtures/plan-count-edit-permission-t.json', 'test/plan-count-preview-footer.test.ts', 'test/fixtures/ceo-preview-u-call.json', 'test/fixtures/ceo-preview-u-screen.txt', 'test/fixtures/ceo-completion-handoff-u-call.json', 'test/fixtures/ceo-completion-handoff-v-call.json', 'test/fixtures/design-preview-v-screen.txt', 'test/plan-count-owned-permission.test.ts', 'test/fixtures/plan-count-owned-permission-v.json', 'test/fixtures/ceo-questionless-w-native.json', 'test/plan-count-ceo-body-finding.test.ts', 'test/fixtures/ceo-count-w-paired.json', 'test/fixtures/ceo-completion-handoff-w-call.json', 'test/fixtures/ceo-approach-y-call.json', 'test/fixtures/ceo-approach-y-screen.txt', 'test/ceo-handoff-y.test.ts', 'test/fixtures/ceo-handoff-y-call.json', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/fixtures/ceo-handoff-z-call.json', 'test/fixtures/ceo-approach-aa-call.json', 'test/review-handoffs-aa.test.ts', 'test/fixtures/review-handoff-aa-ceo.json', 'test/fixtures/review-handoff-aa-dx.json', 'test/helpers/ceo-mode-option.ts', 'test/ceo-count-mode.test.ts', 'test/fixtures/ceo-count-mode-ab-call.json', 'test/ceo-count-ac.test.ts', 'test/fixtures/ceo-count-ac-calls.json', 'test/fixtures/ceo-count-ac-later-calls.json', 'test/plan-count-permission-ac.test.ts', 'test/fixtures/plan-count-permission-ac.json', 'test/fixtures/plan-count-permission-ad.json', 'test/fixtures/plan-count-permission-ae.json', 'test/ceo-count-ad-v2.test.ts', 'test/fixtures/ceo-count-ad-v2.json', 'test/fixtures/plan-count-permission-target-ad-v2.json', 'test/fixtures/ceo-finding-alias-af.json', 'test/fixtures/ceo-numbered-brief-af.json', 'test/ceo-contract-assertions-ag.test.ts', 'test/fixtures/ceo-contract-assertions-ag.json', 'test/fixtures/ceo-contract-assertions-ag-retry.json', 'test/fixtures/plan-count-permission-ah.json', 'test/ceo-parenthesized-issue-ah.test.ts', 'test/fixtures/ceo-parenthesized-issue-ah.json', 'test/ceo-section-chLine truncated
|
||||
'plan-eng-finding-count': ['bin/gstack-config', 'bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-eng-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/claude-pty-runner.ts', 'test/plan-count-native-input.test.ts', 'test/helpers/pty-screen.ts', 'test/pty-screen.test.ts', 'test/pty-screen-session.test.ts', 'test/fixtures/pty-screen/**', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/claude-pty-runner.unit.test.ts', 'test/plan-count-completion.test.ts', 'test/plan-count-dx-handoff.test.ts', 'test/fixtures/devex-handoff-n-call.json', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/helpers/plan-count-transcript.ts', 'test/autoplan-public-narration.test.ts', 'test/fixtures/autoplan-public-narration-ad.json', 'test/helpers/plan-count-pending-exit.ts', 'test/plan-count-pending-exit.test.ts', 'test/plan-count-transcript.test.ts', 'test/helpers/plan-count-artifacts.ts', 'test/plan-count-artifacts.test.ts', 'test/helpers/eval-store.ts', 'test/helpers/plan-count-fixture.ts', 'test/plan-count-fixture.test.ts', 'test/plan-count-timeout.test.ts', 'test/plan-count-navigation-r.test.ts', 'test/plan-count-prerequisite-n.test.ts', 'test/fixtures/ceo-prerequisite-n-call.json', 'test/skill-e2e-plan-eng-finding-count.test.ts', 'test/fixtures/devex-review-l-calls.json', 'test/plan-count-checkbox.test.ts', 'test/fixtures/ceo-checkbox-l.screen.txt', 'test/plan-count-empty-review.test.ts', 'test/fixtures/ceo-count-s-distinct.json', 'test/fixtures/plan-count-design-questionless-report.md', 'test/plan-count-dx-handoff-o.test.ts', 'test/fixtures/devex-handoff-o-call.json', 'test/eng-devex-s-count.test.ts', 'test/fixtures/eng-devex-s-first-calls.json', 'test/fixtures/eng-devex-s-retry-calls.json', 'test/helpers/plan-count-file-permission.ts', 'test/plan-count-file-permission.test.ts', 'test/fixtures/plan-count-edit-permission-t.json', 'test/eng-first-review-t.test.ts', 'test/fixtures/eng-batching-t-calls.json', 'test/plan-count-preview-footer.test.ts', 'test/fixtures/ceo-preview-u-call.json', 'test/fixtures/ceo-preview-u-screen.txt', 'test/fixtures/design-preview-v-screen.txt', 'test/plan-count-owned-permission.test.ts', 'test/fixtures/plan-count-owned-permission-v.json', 'test/fixtures/ceo-questionless-w-native.json', 'test/eng-scope-y.test.ts', 'test/fixtures/eng-scope-y-calls.json', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/eng-binding-z.test.ts', 'test/fixtures/eng-binding-z-calls.json', 'test/eng-binding-retry-z.test.ts', 'test/fixtures/eng-binding-retry-z-calls.json', 'test/plan-count-permission-ac.test.ts', 'test/fixtures/plan-count-permission-ac.json', 'test/fixtures/plan-count-permission-ad.json', 'test/fixtures/plan-count-permission-ae.json', 'test/fixtures/plan-count-permission-target-ad-v2.json', 'test/helpers/eng-completion-handoff.ts', 'test/eng-count-ad-v2.test.ts', 'test/fixtures/eng-count-ad-v2.json', 'test/helpers/eng-seeded-coverage.ts', 'test/eng-seeded-coverage.test.ts', 'test/eng-seeded-packet-ae.test.ts', 'test/fixtures/eng-seeded-packet-ae.json', 'test/eng-first-category-af.test.ts', 'test/fixtures/eng-first-category-af.json', 'test/eng-regression-pinning-ag.test.ts', 'test/fixtures/eng-regression-pinning-ag.json', 'test/fixtures/plan-count-permission-ah.json', 'test/eng-next-handoff-ah.test.ts', 'test/fixtures/eng-next-handoff-ah.json', 'test/eng-declared-regression-ai.test.ts', 'test/fixtures/eng-declared-regression-ai.json'],
|
||||
'plan-design-finding-count': ['bin/gstack-config', 'bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-design-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/claude-pty-runner.ts', 'test/plan-count-native-input.test.ts', 'test/helpers/pty-screen.ts', 'test/pty-screen.test.ts', 'test/pty-screen-session.test.ts', 'test/fixtures/pty-screen/**', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/claude-pty-runner.unit.test.ts', 'test/plan-count-completion.test.ts', 'test/plan-count-dx-handoff.test.ts', 'test/fixtures/devex-handoff-n-call.json', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/helpers/plan-count-transcript.ts', 'test/autoplan-public-narration.test.ts', 'test/fixtures/autoplan-public-narration-ad.json', 'test/helpers/plan-count-pending-exit.ts', 'test/plan-count-pending-exit.test.ts', 'test/plan-count-transcript.test.ts', 'test/helpers/plan-count-artifacts.ts', 'test/plan-count-artifacts.test.ts', 'test/helpers/eval-store.ts', 'test/helpers/plan-count-fixture.ts', 'test/plan-count-fixture.test.ts', 'test/plan-count-timeout.test.ts', 'test/plan-count-navigation-r.test.ts', 'test/plan-count-prerequisite-n.test.ts', 'test/fixtures/ceo-prerequisite-n-call.json', 'test/helpers/design-count-review.ts', 'test/design-count-review.test.ts', 'test/fixtures/design-review-j-calls.json', 'test/helpers/design-count-outside.ts', 'test/design-count-outside.test.ts', 'test/skill-e2e-plan-design-finding-count.test.ts', 'test/fixtures/design-review-l-calls.json', 'test/design-completion-handoff.test.ts', 'test/fixtures/design-handoff-l-calls.json', 'test/fixtures/devex-review-l-calls.json', 'test/plan-count-checkbox.test.ts', 'test/fixtures/ceo-checkbox-l.screen.txt', 'test/fixtures/design-review-n-calls.json', 'test/design-completion-handoff-scored.test.ts', 'test/fixtures/design-handoff-n-calls.json', 'test/fixtures/design-handoff-q-calls.json', 'test/plan-count-empty-review.test.ts', 'test/fixtures/ceo-count-s-distinct.json', 'test/fixtures/plan-count-design-questionless-report.md', 'test/plan-count-dx-handoff-o.test.ts', 'test/fixtures/devex-handoff-o-call.json', 'test/helpers/plan-count-file-permission.ts', 'test/plan-count-file-permission.test.ts', 'test/fixtures/plan-count-edit-permission-t.json', 'test/plan-count-preview-footer.test.ts', 'test/fixtures/ceo-preview-u-call.json', 'test/fixtures/ceo-preview-u-screen.txt', 'test/design-completion-handoff-u.test.ts', 'test/fixtures/design-handoff-u-calls.json', 'test/fixtures/design-preview-v-screen.txt', 'test/plan-count-owned-permission.test.ts', 'test/fixtures/plan-count-owned-permission-v.json', 'test/fixtures/ceo-questionless-w-native.json', 'test/helpers/design-artifact-question.ts', 'test/design-artifact-question.test.ts', 'test/fixtures/design-artifacts-w-calls.json', 'test/fixtures/design-outside-y-calls.json', 'test/fixtures/design-boundaries-y-calls.json', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/fixtures/design-gap-z-calls.json', 'test/plan-count-permission-ac.test.ts', 'test/fixtures/plan-count-permission-ac.json', 'test/fixtures/plan-count-permission-ad.json', 'test/fixtures/plan-count-permission-ae.json', 'test/fixtures/plan-count-permission-target-ad-v2.json', 'test/design-count-ad-v2.test.ts', 'test/fixtures/design-count-ad-v2.json', 'test/design-first-decision-af.test.ts', 'test/fixtures/design-first-decision-af.json', 'test/fixtures/design-first-decision-af-retry.json', 'test/fixtures/plan-count-permission-ah.json', 'test/design-first-issue-ai.test.ts', 'test/fixtures/design-first-issue-ai.json'],
|
||||
'plan-devex-finding-count': ['bin/gstack-config', 'bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-devex-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/claude-pty-runner.ts', 'test/plan-count-native-input.test.ts', 'test/helpers/pty-screen.ts', 'test/pty-screen.test.ts', 'test/pty-screen-session.test.ts', 'test/fixtures/pty-screen/**', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/claude-pty-runner.unit.test.ts', 'test/plan-count-completion.test.ts', 'test/plan-count-dx-handoff.test.ts', 'test/fixtures/devex-handoff-n-call.json', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/helpers/plan-count-transcript.ts', 'test/autoplan-public-narration.test.ts', 'test/fixtures/autoplan-public-narration-ad.json', 'test/helpers/plan-count-pending-exit.ts', 'test/plan-count-pending-exit.test.ts', 'test/plan-count-transcript.test.ts', 'test/helpers/plan-count-artifacts.ts', 'test/plan-count-artifacts.test.ts', 'test/helpers/eval-store.ts', 'test/helpers/plan-count-fixture.ts', 'test/plan-count-fixture.test.ts', 'test/plan-count-timeout.test.ts', 'test/plan-count-navigation-r.test.ts', 'test/plan-count-prerequisite-n.test.ts', 'test/fixtures/ceo-prerequisite-n-call.json', 'test/helpers/devex-count-fixture.ts', 'test/devex-count-fixture.test.ts', 'test/skill-e2e-plan-devex-finding-count.test.ts', 'test/fixtures/dx-prerequisite-r-call.json', 'test/fixtures/devex-review-l-calls.json', 'test/plan-count-checkbox.test.ts', 'test/fixtures/ceo-checkbox-l.screen.txt', 'test/fixtures/devex-review-n-calls.json', 'test/plan-count-empty-review.test.ts', 'test/fixtures/ceo-count-s-distinct.json', 'test/fixtures/plan-count-design-questionless-report.md', 'test/devex-output-o.test.ts', 'test/fixtures/devex-review-o-calls.json', 'test/fixtures/devex-output-o-retry-call.json', 'test/devex-setup-remedy-o.test.ts', 'test/fixtures/devex-review-o-retry-calls.json', 'test/plan-count-dx-handoff-o.test.ts', 'test/fixtures/devex-handoff-o-call.json', 'test/eng-devex-s-count.test.ts', 'test/fixtures/eng-devex-s-first-calls.json', 'test/fixtures/eng-devex-s-retry-calls.json', 'test/fixtures/devex-review-t-calls.json', 'test/helpers/plan-count-file-permission.ts', 'test/plan-count-file-permission.test.ts', 'test/fixtures/plan-count-edit-permission-t.json', 'test/plan-count-preview-footer.test.ts', 'test/fixtures/ceo-preview-u-call.json', 'test/fixtures/ceo-preview-u-screen.txt', 'test/fixtures/devex-count-u-calls.json', 'test/fixtures/devex-count-u-retry-calls.json', 'test/fixtures/devex-empathy-v-calls.json', 'test/fixtures/devex-handoff-v-call.json', 'test/fixtures/design-preview-v-screen.txt', 'test/plan-count-owned-permission.test.ts', 'test/fixtures/plan-count-owned-permission-v.json', 'test/fixtures/ceo-questionless-w-native.json', 'test/fixtures/devex-count-y-calls.json', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/fixtures/devex-count-z-calls.json', 'test/fixtures/devex-handoff-z-call.json', 'test/review-handoffs-aa.test.ts', 'test/fixtures/review-handoff-aa-ceo.json', 'test/fixtures/review-handoff-aa-dx.json', 'test/devex-empathy-ab.test.ts', 'test/fixtures/devex-empathy-ab-calls.json', 'test/devex-ac-accounting.test.ts', 'test/fixtures/devex-ac-first-attempt-calls.json', 'test/plan-count-permission-ac.test.ts', 'test/fixtures/plan-count-permission-ac.json', 'test/fixtures/plan-count-permission-ad.json', 'test/fixtures/plan-count-permission-ae.json', 'test/fixtures/plan-count-permission-target-ad-v2.json', 'test/devex-reconfirmation-ad-v2.test.ts', 'test/fixtures/devex-reconfirmation-ad-v2.json', 'test/plan-count-history.test.ts', 'test/helpers/devex-seed-coverage.ts', 'test/devex-seed-coverage.test.ts', 'test/fixtures/devex-seed-coverage-ad-v3.json', 'test/fixtures/plan-count-permission-ah.json'],
|
||||
|
||||
// Gate-tier reviewCount-floor counterparts. Catch the May 2026 transcript
|
||||
@@ -170,17 +177,17 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
|
||||
// review-phase AskUserQuestion). Uses runPlanSkillFloorCheck — minimal
|
||||
// "did agent fire ANY AUQ?" observer that exits early on first non-permission
|
||||
// numbered-option render. ~1-3 min typical wall time per test, ~$2-6 total.
|
||||
'plan-eng-finding-floor': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-eng-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-eng-finding-floor.test.ts', 'test/eng-first-review-t.test.ts', 'test/fixtures/eng-batching-t-calls.json', 'test/eng-scope-y.test.ts', 'test/fixtures/eng-scope-y-calls.json', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/eng-binding-z.test.ts', 'test/fixtures/eng-binding-z-calls.json', 'test/eng-binding-retry-z.test.ts', 'test/fixtures/eng-binding-retry-z-calls.json'],
|
||||
'plan-ceo-finding-floor': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-ceo-finding-floor.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt'],
|
||||
'plan-design-finding-floor': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-design-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-design-finding-floor.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt'],
|
||||
'plan-devex-finding-floor': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-devex-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-devex-finding-floor.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt'],
|
||||
'plan-eng-finding-floor': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-eng-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-eng-finding-floor.test.ts', 'test/eng-first-review-t.test.ts', 'test/fixtures/eng-batching-t-calls.json', 'test/eng-scope-y.test.ts', 'test/fixtures/eng-scope-y-calls.json', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/eng-binding-z.test.ts', 'test/fixtures/eng-binding-z-calls.json', 'test/eng-binding-retry-z.test.ts', 'test/fixtures/eng-binding-retry-z-calls.json', 'test/helpers/plan-floor-target.ts', 'test/plan-floor-target.test.ts', 'test/helpers/plan-count-fixture.ts', 'test/plan-count-fixture.test.ts', 'test/helpers/plan-count-artifacts.ts', 'test/plan-count-artifacts.test.ts'],
|
||||
'plan-ceo-finding-floor': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-ceo-finding-floor.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/helpers/plan-floor-target.ts', 'test/plan-floor-target.test.ts', 'test/helpers/plan-count-fixture.ts', 'test/plan-count-fixture.test.ts', 'test/helpers/plan-count-artifacts.ts', 'test/plan-count-artifacts.test.ts'],
|
||||
'plan-design-finding-floor': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-design-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-design-finding-floor.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/helpers/plan-floor-target.ts', 'test/plan-floor-target.test.ts', 'test/helpers/plan-count-fixture.ts', 'test/plan-count-fixture.test.ts', 'test/helpers/plan-count-artifacts.ts', 'test/plan-count-artifacts.test.ts'],
|
||||
'plan-devex-finding-floor': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-devex-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-devex-finding-floor.test.ts', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/helpers/plan-floor-target.ts', 'test/plan-floor-target.test.ts', 'test/helpers/plan-count-fixture.ts', 'test/plan-count-fixture.test.ts', 'test/helpers/plan-count-artifacts.ts', 'test/plan-count-artifacts.test.ts'],
|
||||
|
||||
// Multi-finding batching regression — periodic tier complement to the
|
||||
// gate-tier finding-floor. Catches the May 2026 transcript shape where
|
||||
// a model fires one AUQ then batches the rest into a "## Decisions to
|
||||
// confirm" plan write. runPlanSkillFloorCheck cannot detect that shape
|
||||
// (it exits on first AUQ); runPlanSkillCounting can.
|
||||
'plan-eng-multi-finding-batching': ['bin/gstack-config', 'bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-eng-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/plan-count-native-input.test.ts', 'test/helpers/pty-screen.ts', 'test/pty-screen.test.ts', 'test/pty-screen-session.test.ts', 'test/fixtures/pty-screen/**', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/claude-pty-runner.unit.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/helpers/plan-count-transcript.ts', 'test/autoplan-public-narration.test.ts', 'test/fixtures/autoplan-public-narration-ad.json', 'test/helpers/plan-count-pending-exit.ts', 'test/plan-count-pending-exit.test.ts', 'test/plan-count-transcript.test.ts', 'test/helpers/plan-count-artifacts.ts', 'test/plan-count-artifacts.test.ts', 'test/helpers/eval-store.ts', 'test/helpers/plan-count-fixture.ts', 'test/plan-count-fixture.test.ts', 'test/plan-count-timeout.test.ts', 'test/plan-count-navigation-r.test.ts', 'test/plan-count-prerequisite-n.test.ts', 'test/fixtures/ceo-prerequisite-n-call.json', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-eng-multi-finding-batching.test.ts', 'test/plan-count-checkbox.test.ts', 'test/fixtures/ceo-checkbox-l.screen.txt', 'test/eng-devex-s-count.test.ts', 'test/fixtures/eng-devex-s-first-calls.json', 'test/fixtures/eng-devex-s-retry-calls.json', 'test/helpers/plan-count-file-permission.ts', 'test/plan-count-file-permission.test.ts', 'test/fixtures/plan-count-edit-permission-t.json', 'test/eng-first-review-t.test.ts', 'test/fixtures/eng-batching-t-calls.json', 'test/plan-count-preview-footer.test.ts', 'test/fixtures/ceo-preview-u-call.json', 'test/fixtures/ceo-preview-u-screen.txt', 'test/fixtures/design-preview-v-screen.txt', 'test/plan-count-owned-permission.test.ts', 'test/fixtures/plan-count-owned-permission-v.json', 'test/fixtures/ceo-questionless-w-native.json', 'test/eng-scope-y.test.ts', 'test/fixtures/eng-scope-y-calls.json', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/eng-binding-z.test.ts', 'test/fixtures/eng-binding-z-calls.json', 'test/eng-binding-retry-z.test.ts', 'test/fixtures/eng-binding-retry-z-calls.json', 'test/plan-count-permission-ac.test.ts', 'test/fixtures/plan-count-permission-ac.json', 'test/fixtures/plan-count-permission-ad.json', 'test/fixtures/plan-count-permission-ae.json', 'test/fixtures/plan-count-permission-target-ad-v2.json', 'test/eng-count-ad-v2.test.ts', 'test/fixtures/eng-count-ad-v2.json', 'test/eng-first-category-af.test.ts', 'test/fixtures/eng-first-category-af.json', 'test/eng-regression-pinning-ag.test.ts', 'test/fixtures/eng-regression-pinning-ag.json', 'test/fixtures/plan-count-permission-ah.json'],
|
||||
'plan-eng-multi-finding-batching': ['bin/gstack-config', 'bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-eng-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/plan-count-native-input.test.ts', 'test/helpers/pty-screen.ts', 'test/pty-screen.test.ts', 'test/pty-screen-session.test.ts', 'test/fixtures/pty-screen/**', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/claude-pty-runner.unit.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/helpers/plan-count-transcript.ts', 'test/autoplan-public-narration.test.ts', 'test/fixtures/autoplan-public-narration-ad.json', 'test/helpers/plan-count-pending-exit.ts', 'test/plan-count-pending-exit.test.ts', 'test/plan-count-transcript.test.ts', 'test/helpers/plan-count-artifacts.ts', 'test/plan-count-artifacts.test.ts', 'test/helpers/eval-store.ts', 'test/helpers/plan-count-fixture.ts', 'test/plan-count-fixture.test.ts', 'test/plan-count-timeout.test.ts', 'test/plan-count-navigation-r.test.ts', 'test/plan-count-prerequisite-n.test.ts', 'test/fixtures/ceo-prerequisite-n-call.json', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-eng-multi-finding-batching.test.ts', 'test/plan-count-checkbox.test.ts', 'test/fixtures/ceo-checkbox-l.screen.txt', 'test/eng-devex-s-count.test.ts', 'test/fixtures/eng-devex-s-first-calls.json', 'test/fixtures/eng-devex-s-retry-calls.json', 'test/helpers/plan-count-file-permission.ts', 'test/plan-count-file-permission.test.ts', 'test/fixtures/plan-count-edit-permission-t.json', 'test/eng-first-review-t.test.ts', 'test/fixtures/eng-batching-t-calls.json', 'test/plan-count-preview-footer.test.ts', 'test/fixtures/ceo-preview-u-call.json', 'test/fixtures/ceo-preview-u-screen.txt', 'test/fixtures/design-preview-v-screen.txt', 'test/plan-count-owned-permission.test.ts', 'test/fixtures/plan-count-owned-permission-v.json', 'test/fixtures/ceo-questionless-w-native.json', 'test/eng-scope-y.test.ts', 'test/fixtures/eng-scope-y-calls.json', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/eng-binding-z.test.ts', 'test/fixtures/eng-binding-z-calls.json', 'test/eng-binding-retry-z.test.ts', 'test/fixtures/eng-binding-retry-z-calls.json', 'test/plan-count-permission-ac.test.ts', 'test/fixtures/plan-count-permission-ac.json', 'test/fixtures/plan-count-permission-ad.json', 'test/fixtures/plan-count-permission-ae.json', 'test/fixtures/plan-count-permission-target-ad-v2.json', 'test/eng-count-ad-v2.test.ts', 'test/fixtures/eng-count-ad-v2.json', 'test/eng-first-category-af.test.ts', 'test/fixtures/eng-first-category-af.json', 'test/eng-regression-pinning-ag.test.ts', 'test/fixtures/eng-regression-pinning-ag.json', 'test/fixtures/plan-count-permission-ah.json', 'test/eng-declared-regression-ai.test.ts', 'test/fixtures/eng-declared-regression-ai.json'],
|
||||
'plan-ceo-split-overflow': ['bin/gstack-config', 'plan-ceo-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'bin/gstack-question-preference', 'test/helpers/claude-pty-runner.ts', 'test/plan-count-native-input.test.ts', 'test/helpers/pty-screen.ts', 'test/pty-screen.test.ts', 'test/pty-screen-session.test.ts', 'test/fixtures/pty-screen/**', 'test/helpers/hermetic-skill-runtime.ts', 'test/hermetic-skill-runtime.test.ts', 'test/helpers/claude-pty-runner.unit.test.ts', 'test/helpers/pty-trust-dialog.ts', 'test/pty-trust-dialog.test.ts', 'test/helpers/plan-count-transcript.ts', 'test/autoplan-public-narration.test.ts', 'test/fixtures/autoplan-public-narration-ad.json', 'test/helpers/plan-count-pending-exit.ts', 'test/plan-count-pending-exit.test.ts', 'test/plan-count-transcript.test.ts', 'test/helpers/plan-count-artifacts.ts', 'test/plan-count-artifacts.test.ts', 'test/helpers/eval-store.ts', 'test/helpers/plan-count-fixture.ts', 'test/plan-count-fixture.test.ts', 'test/plan-count-timeout.test.ts', 'test/plan-count-navigation-r.test.ts', 'test/plan-count-prerequisite-n.test.ts', 'test/fixtures/ceo-prerequisite-n-call.json', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-ceo-split-overflow.test.ts', 'test/plan-count-checkbox.test.ts', 'test/fixtures/ceo-checkbox-l.screen.txt', 'test/helpers/plan-count-file-permission.ts', 'test/plan-count-file-permission.test.ts', 'test/fixtures/plan-count-edit-permission-t.json', 'test/plan-count-owned-permission.test.ts', 'test/fixtures/plan-count-owned-permission-v.json', 'test/fixtures/ceo-questionless-w-native.json', 'test/plan-count-truncated-question.test.ts', 'test/fixtures/ceo-approach-z-call.json', 'test/fixtures/ceo-approach-z-screen.txt', 'test/plan-count-permission-ac.test.ts', 'test/fixtures/plan-count-permission-ac.json', 'test/fixtures/plan-count-permission-ad.json', 'test/fixtures/plan-count-permission-ae.json', 'test/fixtures/plan-count-permission-target-ad-v2.json', 'test/fixtures/plan-count-permission-ah.json'],
|
||||
'brain-privacy-gate': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'scripts/resolvers/preamble/generate-brain-sync-block.ts', 'scripts/resolvers/preamble.ts', 'bin/gstack-brain-sync', 'bin/gstack-artifacts-init', 'bin/gstack-config', 'test/helpers/agent-sdk-runner.ts', 'test/skill-e2e-brain-privacy-gate.test.ts'],
|
||||
|
||||
@@ -290,6 +297,7 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
|
||||
'scripts/gen-skill-docs.ts', 'scripts/resolvers/index.ts', 'scripts/resolvers/outside-voice.ts',
|
||||
'scripts/resolvers/constants.ts', 'scripts/resolvers/review.ts',
|
||||
'bin/gstack-codex-probe', 'lib/outside-review-result.ts', 'test/helpers/session-runner.ts',
|
||||
'test/outside-background-ai.test.ts', 'test/fixtures/outside-background-ai.json',
|
||||
'test/helpers/skill-fixture.ts', 'test/helpers/outside-voice-fixture.ts', 'test/outside-voice-fixture.test.ts', 'test/helpers/outside-voice-evidence.ts', 'test/outside-voice-evidence.test.ts', 'test/outside-voice-async.test.ts', 'test/fixtures/outside-async-task-m-events.json', 'test/skill-e2e-outside-voice.test.ts',
|
||||
],
|
||||
|
||||
|
||||
@@ -0,0 +1,103 @@
|
||||
import { describe, expect, test } from 'bun:test';
|
||||
import { claudeOutsideExecutions, foundInvoiceAuthorizationDefect, outsideExecutionTranscript } from './helpers/outside-voice-evidence';
|
||||
import captured from './fixtures/outside-background-ai.json';
|
||||
|
||||
const events = () => structuredClone(captured.events) as any[];
|
||||
const block = (input: any[], index: number) => input[index].message.content[0];
|
||||
const outputFile = /<output-file>([^<]+)<\/output-file>/.exec(captured.events[2].attachment!.prompt!)![1]!;
|
||||
const finding = 'The missing invoice owner authorization check allows another user to access the invoice.';
|
||||
const detected = (input: any[]) => foundInvoiceAuthorizationDefect(claudeOutsideExecutions(input), 'codex');
|
||||
|
||||
function rejects(mutations: Array<(input: any[]) => void>) {
|
||||
for (const mutate of mutations) {
|
||||
const input = events();
|
||||
mutate(input);
|
||||
expect(detected(input)).toBe(false);
|
||||
}
|
||||
}
|
||||
|
||||
describe('native completed outside task read through literal Bash cat', () => {
|
||||
test('the exact five public events retain the completed Codex finding', () => {
|
||||
expect(captured.events).toHaveLength(5);
|
||||
const executions = claudeOutsideExecutions(events());
|
||||
expect(foundInvoiceAuthorizationDefect(executions, 'codex')).toBe(true);
|
||||
const completed = outsideExecutionTranscript(executions, 'codex').filter(row => row.succeeded);
|
||||
expect(completed).toHaveLength(1);
|
||||
expect(completed[0]!.background).toEqual({
|
||||
toolUseId: block(events(), 0).id, taskId: 'bdie078em', outputFile,
|
||||
outputToolUseId: block(events(), 3).id, completion: 'task_notification',
|
||||
});
|
||||
expect(completed[0]!.output).toContain('Missing ownership check exposes private financial data');
|
||||
});
|
||||
|
||||
test('equivalent literal quoting and optional cat delimiter keep exact path ownership', () => {
|
||||
for (const path of [outputFile, `'${outputFile}'`, `"${outputFile}"`]) {
|
||||
for (const delimiter of ['', '-- ']) {
|
||||
const input = events();
|
||||
block(input, 3).input.command = `cat ${delimiter}${path}`;
|
||||
expect(detected(input)).toBe(true);
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
test('completion requires the owned launch, acknowledgment, native notice and paired output', () => {
|
||||
rejects([
|
||||
e => { e.splice(0, 1); }, e => { e.splice(1, 1); }, e => { e.splice(2, 1); },
|
||||
e => { e.splice(3, 1); }, e => { e.pop(); },
|
||||
e => { block(e, 1).is_error = true; },
|
||||
e => { block(e, 4).tool_use_id = 'foreign-output'; },
|
||||
e => { e[2].attachment.prompt = e[2].attachment.prompt.replace('<task-id>bdie078em', '<task-id>other'); },
|
||||
e => { e[2].attachment.prompt = e[2].attachment.prompt.replace(block(e, 0).id, 'foreign-launch'); },
|
||||
e => { e[2].attachment.prompt = e[2].attachment.prompt.replace(outputFile, outputFile + '.other'); },
|
||||
e => { e[2].attachment.prompt = e[2].attachment.prompt.replace('<status>completed', '<status>failed'); },
|
||||
e => { e[2].attachment.prompt = e[2].attachment.prompt.replace('(exit code 0)', '(exit code 1)'); },
|
||||
e => { e.unshift(e.splice(2, 1)[0]); },
|
||||
e => { const notice = e.splice(2, 1)[0]; e.unshift({ ...notice, type: 'user', message: { content: [{ type: 'text', text: notice.attachment.prompt }] } }); },
|
||||
e => { e[2] = { type: 'assistant', sessionId: e[2].sessionId, message: { content: [{ type: 'text', text: e[2].attachment.prompt }] } }; },
|
||||
]);
|
||||
});
|
||||
|
||||
test('foreign and child sessions cannot supply any part of the completed read', () => {
|
||||
for (const index of [0, 1, 2, 3, 4]) {
|
||||
rejects([
|
||||
e => { e[index].sessionId = 'foreign-session'; },
|
||||
e => { e[index].session_id = 'conflicting-session'; },
|
||||
e => { e[index].isSidechain = true; },
|
||||
e => { e[index].parent_tool_use_id = 'foreign-parent'; },
|
||||
]);
|
||||
}
|
||||
});
|
||||
|
||||
test('cat must read only the exact acknowledged literal path without shell operations', () => {
|
||||
const quoted = `"${outputFile}"`;
|
||||
for (const command of [
|
||||
`cat "${outputFile}.other"`, `cat ${quoted} /tmp/foreign.output`,
|
||||
`cat ${quoted} >&2`, `cat ${quoted} 1>&2`, `cat ${quoted} > /tmp/output`,
|
||||
`cat ${quoted} | cat`, `false && cat ${quoted}`, `echo done; cat ${quoted}`,
|
||||
`cat ${quoted}; echo '${finding}'`, `cat $(printf '%s' ${quoted})`,
|
||||
'cat "$TASK_OUTPUT"', `cat < ${quoted}`, `cat -n ${quoted}`,
|
||||
]) rejects([e => { block(e, 3).input.command = command; }]);
|
||||
rejects([e => { block(e, 1).content = block(e, 1).content.replace(outputFile, outputFile + '.other'); }]);
|
||||
});
|
||||
|
||||
test('failed, incomplete and forged-footer output cannot establish a completed task', () => {
|
||||
rejects([
|
||||
e => { block(e, 4).is_error = true; },
|
||||
e => { block(e, 4).content = block(e, 4).content.replace('[exited with code 0]', ''); },
|
||||
e => { block(e, 4).content = block(e, 4).content.replace('[exited with code 0]', '[exited with code 1]'); },
|
||||
e => { block(e, 4).content += '\nThe task is still running.'; },
|
||||
e => { block(e, 4).content = finding; },
|
||||
e => { block(e, 4).content = `${finding}\n[exited with code 0]`; e.splice(2, 1); },
|
||||
e => { block(e, 4).content = 'I cannot review the invoice ownership issue.\n[exited with code 0]'; },
|
||||
e => { block(e, 4).content = `${finding}\nOUTSIDE_STATUS: unavailable\n[exited with code 0]`; },
|
||||
]);
|
||||
});
|
||||
|
||||
test('late native task failure remains authoritative after a successful cat', () => {
|
||||
const input = events();
|
||||
const failed = structuredClone(input[2]);
|
||||
failed.attachment.prompt = failed.attachment.prompt.replace('<status>completed', '<status>failed');
|
||||
input.push(failed);
|
||||
expect(detected(input)).toBe(false);
|
||||
});
|
||||
});
|
||||
@@ -46,12 +46,20 @@ describe('native prerequisite review-now offer', () => {
|
||||
}
|
||||
});
|
||||
|
||||
test('the captured regression selects every existing shared fixture consumer', () => {
|
||||
const consumers = Object.values(E2E_TOUCHFILES).filter(paths => paths.includes('test/plan-count-fixture.test.ts'));
|
||||
expect(consumers.length).toBe(8);
|
||||
for (const paths of consumers) {
|
||||
expect(paths).toContain('test/plan-count-prerequisite-n.test.ts');
|
||||
expect(paths).toContain('test/fixtures/ceo-prerequisite-n-call.json');
|
||||
test('the captured prerequisite regression selects its exact counting and mode consumers', () => {
|
||||
// Floor checks also seed a plan, but never pick a prerequisite answer.
|
||||
const expected = [
|
||||
'autoplan-chain-pty', 'plan-ceo-finding-count', 'plan-ceo-mode-routing',
|
||||
'plan-ceo-split-overflow', 'plan-design-finding-count', 'plan-devex-finding-count',
|
||||
'plan-eng-finding-count', 'plan-eng-multi-finding-batching',
|
||||
].sort();
|
||||
for (const dependency of ['test/plan-count-prerequisite-n.test.ts', 'test/fixtures/ceo-prerequisite-n-call.json']) {
|
||||
const consumers = Object.entries(E2E_TOUCHFILES).filter(([, paths]) => paths.includes(dependency));
|
||||
expect(consumers.map(([name]) => name).sort()).toEqual(expected);
|
||||
for (const [, paths] of consumers) {
|
||||
expect(paths).toContain('test/helpers/plan-count-fixture.ts');
|
||||
expect(paths).toContain('test/plan-count-fixture.test.ts');
|
||||
}
|
||||
}
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,145 @@
|
||||
import { expect, test } from 'bun:test';
|
||||
import * as fs from 'node:fs';
|
||||
import * as os from 'node:os';
|
||||
import * as path from 'node:path';
|
||||
import { pathToFileURL } from 'node:url';
|
||||
import { readPlanFloorTarget } from './helpers/plan-floor-target';
|
||||
import { selectTests, E2E_TOUCHFILES } from './helpers/touchfiles';
|
||||
|
||||
const ROOT = path.resolve(import.meta.dir, '..');
|
||||
const SID = '11111111-2222-3333-4444-555555555555';
|
||||
const START = Date.parse('2026-09-10T04:46:45Z');
|
||||
const SEED = '# Plan: Marketing landing page\n\nThe primary CTA has the same weight as Learn more.';
|
||||
const COMMAND = '<command-message>plan-design-review</command-message>\n<command-name>/plan-design-review</command-name>\n<command-args>PLAN.md</command-args>';
|
||||
function fixture() {
|
||||
const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'floor-target-'));
|
||||
const cwd = path.join(dir, 'project'), config = path.join(dir, 'config');
|
||||
fs.mkdirSync(cwd); fs.writeFileSync(path.join(cwd, 'PLAN.md'), SEED);
|
||||
const journal = path.join(config, 'projects', 'owned', SID + '.jsonl');
|
||||
fs.mkdirSync(path.dirname(journal), { recursive: true });
|
||||
const row = { type: 'user', isSidechain: false, cwd, sessionId: SID, timestamp: new Date(START + 1).toISOString(), message: { role: 'user', content: COMMAND } };
|
||||
const write = (rows: unknown[], newline = true) => fs.writeFileSync(journal, rows.map(x => JSON.stringify(x)).join('\n') + (newline ? '\n' : ''));
|
||||
const options = { seed: SEED, sessionId: SID, slashCommand: '/plan-design-review', startedAt: START, now: START + 100 };
|
||||
return { dir, cwd, config, journal, row, write, options, check: () => readPlanFloorTarget(config, cwd, options), cleanup: () => fs.rmSync(dir, { recursive: true, force: true }) };
|
||||
}
|
||||
|
||||
test('owned native command acknowledgment binds exact target, session and submitted bytes', () => {
|
||||
const f = fixture();
|
||||
try {
|
||||
expect(f.check().status).toBe('missing');
|
||||
f.write([f.row]);
|
||||
expect(f.check()).toMatchObject({ status: 'ready', command: '/plan-design-review PLAN.md', targetPath: path.join(f.cwd, 'PLAN.md'), sessionId: SID, acknowledgedAt: f.row.timestamp });
|
||||
f.write([{ ...f.row, message: { role: 'user', content: [{ type: 'text', text: COMMAND }] } }]);
|
||||
expect(f.check().status).toBe('ready');
|
||||
} finally { f.cleanup(); }
|
||||
});
|
||||
|
||||
test('foreign, child, stale, future, quoted, tool and wrong-target records cannot acknowledge delivery', () => {
|
||||
const f = fixture();
|
||||
try {
|
||||
for (const row of [
|
||||
{ ...f.row, cwd: f.cwd + '-foreign' }, { ...f.row, sessionId: 'foreign' },
|
||||
{ ...f.row, isSidechain: true }, { ...f.row, parent_tool_use_id: 'parent-tool' },
|
||||
{ ...f.row, timestamp: new Date(START - 1).toISOString() },
|
||||
{ ...f.row, timestamp: new Date(START + 101).toISOString() },
|
||||
{ ...f.row, type: 'assistant', message: { role: 'assistant', content: COMMAND } },
|
||||
{ ...f.row, message: { role: 'user', content: '> ' + COMMAND } },
|
||||
{ ...f.row, message: { role: 'user', content: COMMAND.replace('PLAN.md', 'OTHER.md') } },
|
||||
{ ...f.row, message: { role: 'user', content: [{ type: 'tool_result', tool_use_id: 'read', content: COMMAND }] } },
|
||||
]) { f.write([row]); expect(f.check().status, JSON.stringify(row)).not.toBe('ready'); }
|
||||
} finally { f.cleanup(); }
|
||||
});
|
||||
|
||||
test('the actual bare invocation cannot be repaired by a later queued target', () => {
|
||||
const f = fixture();
|
||||
try {
|
||||
const bare = '<command-message>plan-design-review</command-message>\n<command-name>/plan-design-review</command-name>';
|
||||
f.write([{ ...f.row, message: { role: 'user', content: bare } }, { ...f.row, timestamp: new Date(START + 2).toISOString() }]);
|
||||
expect(f.check().status).toBe('error');
|
||||
f.write([{ ...f.row, message: { role: 'user', content: [{ type: 'text', text: bare }, { type: 'text', text: 'Started without a target.' }] } }, f.row]);
|
||||
expect(f.check().status).toBe('error');
|
||||
f.write([{ ...f.row, message: { role: 'user', content: [{ type: 'tool_result', tool_use_id: 'read', content: bare }] } }, f.row]);
|
||||
expect(f.check().status).toBe('ready');
|
||||
f.write([f.row], false); expect(f.check().status).toBe('missing');
|
||||
f.write([f.row]);
|
||||
const other = path.join(f.config, 'projects', 'other'); fs.mkdirSync(other); fs.copyFileSync(f.journal, path.join(other, SID + '.jsonl'));
|
||||
expect(f.check().status).toBe('error');
|
||||
} finally { f.cleanup(); }
|
||||
});
|
||||
|
||||
test('changed or linked plan, invalid clock, linked journal and oversized source are unavailable', () => {
|
||||
const f = fixture();
|
||||
try {
|
||||
f.write([f.row]); fs.writeFileSync(path.join(f.cwd, 'PLAN.md'), SEED + ' changed'); expect(f.check().status).toBe('error');
|
||||
fs.writeFileSync(path.join(f.cwd, 'PLAN.md'), SEED);
|
||||
for (const now of [NaN, Infinity, START - 1]) expect(readPlanFloorTarget(f.config, f.cwd, { ...f.options, now }).status).not.toBe('ready');
|
||||
fs.renameSync(path.join(f.cwd, 'PLAN.md'), path.join(f.cwd, 'real.md')); fs.symlinkSync('real.md', path.join(f.cwd, 'PLAN.md')); expect(f.check().status).toBe('error');
|
||||
fs.unlinkSync(path.join(f.cwd, 'PLAN.md')); fs.renameSync(path.join(f.cwd, 'real.md'), path.join(f.cwd, 'PLAN.md'));
|
||||
const real = f.journal + '.real'; fs.renameSync(f.journal, real); fs.symlinkSync(real, f.journal); expect(f.check().status).toBe('error');
|
||||
fs.unlinkSync(f.journal); fs.renameSync(real, f.journal); fs.truncateSync(f.journal, 32 * 1024 * 1024 + 1); expect(f.check().status).toBe('error');
|
||||
} finally { f.cleanup(); }
|
||||
});
|
||||
|
||||
test('new delivery helper and controls select all four existing floor owners', () => {
|
||||
for (const file of ['test/helpers/plan-floor-target.ts', 'test/plan-floor-target.test.ts']) {
|
||||
expect(selectTests([file], E2E_TOUCHFILES).selected.sort()).toEqual(['plan-ceo-finding-floor', 'plan-design-finding-floor', 'plan-devex-finding-floor', 'plan-eng-finding-floor']);
|
||||
}
|
||||
});
|
||||
|
||||
test('real fake CLI sees seed before command; missing acknowledgment and scope menu never satisfy floor', async () => {
|
||||
const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'floor-delivery-pty-'));
|
||||
try {
|
||||
const cli = path.join(dir, 'fake-claude'), worker = path.join(dir, 'worker.ts'), output = path.join(dir, 'results.json');
|
||||
fs.writeFileSync(cli, `#!/usr/bin/env bun
|
||||
const fs = require('node:fs'), path = require('node:path');
|
||||
const args = process.argv.slice(2), id = args[args.indexOf('--session-id') + 1];
|
||||
const record = value => fs.appendFileSync(process.env.FLOOR_RECORD, JSON.stringify(value)+'\\n');
|
||||
record({type:'startup',pid:process.pid,cwd:process.cwd(),argv:args,plan:fs.readFileSync('PLAN.md','utf8'),context:fs.readFileSync('CLAUDE.md','utf8')});
|
||||
if (process.stdin.isTTY) process.stdin.setRawMode(true);
|
||||
let started=false;
|
||||
process.stdin.on('data', chunk => {
|
||||
const input=chunk.toString(); record({type:'input',input}); if(started)return; started=true;
|
||||
const mode=process.env.FLOOR_MODE;
|
||||
if(mode!=='missing') {
|
||||
const root=path.join(process.env.CLAUDE_CONFIG_DIR,'projects','owned'); fs.mkdirSync(root,{recursive:true});
|
||||
const content=${JSON.stringify(COMMAND)};
|
||||
const row={type:'user',isSidechain:false,cwd:mode==='foreign'?process.cwd()+'-foreign':process.cwd(),sessionId:id,timestamp:new Date().toISOString(),message:{role:'user',content}};
|
||||
fs.writeFileSync(path.join(root,id+'.jsonl'),JSON.stringify(row)+'\\n');
|
||||
}
|
||||
process.stdout.write(mode==='scope'?'What should I review?\\n❯ 1. Current branch diff\\n 2. A plan or design doc\\n':'Finding 1: CTA hierarchy is unclear.\\n❯ 1. Emphasize the primary CTA\\n 2. Keep equal weight\\n');
|
||||
});
|
||||
process.on('SIGINT',()=>{record({type:'closed'});process.exit(0)});
|
||||
process.stdin.resume();
|
||||
`);
|
||||
fs.chmodSync(cli, 0o755);
|
||||
fs.writeFileSync(worker, `
|
||||
import {runPlanSkillFloorCheck} from ${JSON.stringify(pathToFileURL(path.join(ROOT, 'test/helpers/claude-pty-runner.ts')).href)};
|
||||
import fs from 'node:fs';
|
||||
const modes=['ready','missing','foreign','scope'];
|
||||
const results=await Promise.all(modes.map(async mode=>({mode,observation:await runPlanSkillFloorCheck({skillName:'plan-design-review',slashCommand:'/plan-design-review',followUpPrompt:${JSON.stringify(SEED)},cwd:${JSON.stringify(ROOT)},timeoutMs:2500,model:'claude-fable-5-1',env:{FLOOR_MODE:mode,FLOOR_RECORD:${JSON.stringify(dir)}+'/'+mode+'.jsonl'}})})));
|
||||
fs.writeFileSync(${JSON.stringify(output)},JSON.stringify(results));
|
||||
`);
|
||||
const child = Bun.spawn([process.execPath, worker], { cwd: ROOT,
|
||||
env: { ...process.env, BROWSE_TERMINAL_BINARY: cli, EVALS_HERMETIC: '1', GSTACK_EVAL_DIR: path.join(dir, 'artifacts'), EVALS_RUN_ID: 'floor-delivery-test' }, stdout: 'pipe', stderr: 'pipe' });
|
||||
const killer = setTimeout(() => child.kill('SIGKILL'), 25000);
|
||||
try {
|
||||
const [exit, stdout, stderr] = await Promise.all([child.exited, new Response(child.stdout).text(), new Response(child.stderr).text()]);
|
||||
expect(exit, stdout + stderr).toBe(0);
|
||||
for (const result of JSON.parse(fs.readFileSync(output, 'utf8'))) {
|
||||
const events = fs.readFileSync(path.join(dir, result.mode + '.jsonl'), 'utf8').trim().split('\n').map(line => JSON.parse(line));
|
||||
const startup = events[0];
|
||||
expect(startup.plan).toBe(SEED); expect(startup.context).toContain(SEED); expect(startup.cwd).not.toBe(ROOT);
|
||||
expect(startup.argv[startup.argv.indexOf('--permission-mode') + 1]).toBe('plan');
|
||||
expect(startup.argv[startup.argv.indexOf('--model') + 1]).toBe('claude-fable-5-1');
|
||||
expect(events.filter(e => e.type === 'input').map(e => e.input).join('')).toBe('/plan-design-review PLAN.md\r');
|
||||
expect(events.at(-1).type).toBe('closed'); expect(fs.existsSync(startup.cwd)).toBe(false);
|
||||
expect(() => process.kill(startup.pid, 0)).toThrow();
|
||||
expect(result.observation.auqObserved).toBe(result.mode === 'ready');
|
||||
expect(result.observation.outcome).toBe(result.mode === 'ready' ? 'auq_observed' : 'timeout');
|
||||
expect(result.observation.targetDelivery.status).toBe(['ready','scope'].includes(result.mode) ? 'ready' : 'missing');
|
||||
const retained=JSON.parse(fs.readFileSync(path.join(result.observation.artifactDir,'observation.json'),'utf8'));
|
||||
expect(retained.targetDelivery).toEqual(result.observation.targetDelivery);
|
||||
}
|
||||
} finally { clearTimeout(killer); }
|
||||
} finally { fs.rmSync(dir, { recursive: true, force: true }); }
|
||||
}, 30000);
|
||||
@@ -0,0 +1,143 @@
|
||||
import { describe, expect, test } from 'bun:test';
|
||||
import { hasStaleFillRaceFinding } from './helpers/ceo-section-loading-fixture';
|
||||
import captured from './fixtures/sdk-original-order-ai.json';
|
||||
|
||||
const compact = () => `### Findings registry\n\n${captured.finding}\n\n${captured.heading}\n\`\`\`\n${captured.trace}\n\`\`\``;
|
||||
const rejects = (changes: Array<[string, string]>) => {
|
||||
for (const [before, after] of changes) {
|
||||
expect(compact()).toContain(before);
|
||||
expect(hasStaleFillRaceFinding(compact().replace(before, after))).toBe(false);
|
||||
}
|
||||
};
|
||||
|
||||
describe('asserted original order beside an amended cache schedule', () => {
|
||||
test('exact completed report and its owned finding/schedule show the original late-fill violation', () => {
|
||||
expect(hasStaleFillRaceFinding(captured.report)).toBe(true);
|
||||
expect(hasStaleFillRaceFinding(compact())).toBe(true);
|
||||
});
|
||||
|
||||
test('amended behavior or the original caller allowance cannot replace the original stale-fill evidence', () => {
|
||||
const original = 'Original sketch, order A: fill V1 at 6 after delete at 4 -> R2 reads V1 for <=30 s VIOLATION';
|
||||
rejects([
|
||||
[original, ''], [original, 'Not ' + original], [original, '> ' + original],
|
||||
[original, '"' + original + '"'], [original, 'If ' + original],
|
||||
[original, original.replace('VIOLATION', 'PERMITTED')],
|
||||
[original, original.replace('R2 reads', 'R1 reads')],
|
||||
[original, original.replace('fill V1', 'skip fill V1')],
|
||||
[original, original.replace('after delete at 4', 'before delete at 4')],
|
||||
]);
|
||||
});
|
||||
|
||||
test('reader, writer, cache key, versions and completion order must all refer to the same execution', () => {
|
||||
rejects([
|
||||
['inflight[k]', 'inflight[foreign]'], ['R1 (began before W)', 'R1 (began after W)'],
|
||||
['DB write commits V2', 'DB write commits V1'], ['DB returns V1', 'DB returns V2'],
|
||||
['resume: invalidate(E1), delete', 'resume: invalidate(E9), delete'],
|
||||
['settles -> W complete', 'settles -> W pending'],
|
||||
['resume: E1.stale -> skip fill', 'resume: E9.stale -> skip fill'],
|
||||
['7 | R2 begins:', '4.5 | R2 begins:'], ['R2 reads V1 for', 'R2 reads V2 for'],
|
||||
['fill V1 at 6 after delete at 4', 'fill V1 at 3 after delete at 4'],
|
||||
['cache[k]', 'cache[foreign]'],
|
||||
]);
|
||||
});
|
||||
|
||||
test('the current finding owns the trace and must independently assert the invariant violation', () => {
|
||||
rejects([
|
||||
['schedule (F1,', 'schedule (F2,'], ['| F1 | CRITICAL |', '| F2 | CRITICAL |'],
|
||||
['| F1 | CRITICAL |', '| F1 | LOW |'],
|
||||
['Schedule in Section 4 shows', 'A hypothetical Schedule in Section 4 shows'],
|
||||
['filled after `cache.delete`', 'filled before `cache.delete`'],
|
||||
['every read begun after that write completes must observe the committed version', 'earlier values are accepted for later readers'],
|
||||
]);
|
||||
expect(hasStaleFillRaceFinding(compact().replace(captured.finding, captured.finding + '\n' + captured.finding))).toBe(false);
|
||||
});
|
||||
|
||||
test('source and hypothetical framing cannot supply the assertion', () => {
|
||||
for (const prefix of ['An unproven hypothesis.', 'Historical example only.', 'The following is a hypothetical example.']) {
|
||||
expect(hasStaleFillRaceFinding(prefix + '\n' + compact())).toBe(false);
|
||||
expect(hasStaleFillRaceFinding(compact().replace(captured.heading, prefix + '\n' + captured.heading))).toBe(false);
|
||||
}
|
||||
expect(hasStaleFillRaceFinding(compact().split('\n').map(line => '> ' + line).join('\n'))).toBe(false);
|
||||
expect(hasStaleFillRaceFinding('````text\n' + compact() + '\n````')).toBe(false);
|
||||
expect(hasStaleFillRaceFinding(compact().replace('### Findings registry', '### Quoted source'))).toBe(false);
|
||||
});
|
||||
|
||||
test('same-finding direct and quoted withdrawals remain authoritative inside or after the trace', () => {
|
||||
for (const withdrawal of ['F1 is withdrawn.', 'F1 is rejected.', 'The original schedule is impossible.', 'There is no stale-fill race.', 'Rejected: "There is no stale-fill race."']) {
|
||||
expect(hasStaleFillRaceFinding(compact() + '\n\n' + withdrawal)).toBe(false);
|
||||
expect(hasStaleFillRaceFinding(compact().replace(captured.trace, captured.trace + '\n' + withdrawal))).toBe(false);
|
||||
expect(hasStaleFillRaceFinding(compact().replace('Ordering tests, both orders + late joiner + sentinel variant', withdrawal))).toBe(false);
|
||||
}
|
||||
expect(hasStaleFillRaceFinding(compact().replace('Readers that began before the write may still see the old snapshot (permitted by contract)', 'Later readers may see old snapshots; this stale-fill behavior is accepted.'))).toBe(false);
|
||||
});
|
||||
|
||||
test('unrelated sections and consistently renamed identities do not change valid evidence', () => {
|
||||
expect(hasStaleFillRaceFinding('### Prior example\nHistorical example only.\n\n### Current review\n' + compact())).toBe(true);
|
||||
expect(hasStaleFillRaceFinding(compact() + '\n\n### Other finding\nF2 is rejected.')).toBe(true);
|
||||
const renamed = compact().replaceAll('R1', 'R7').replaceAll('R2', 'R8').replaceAll('R3', 'R9')
|
||||
.replaceAll('V1', 'oldSnapshot').replaceAll('V2', 'newSnapshot').replaceAll('E1', 'pendingA').replaceAll('E2', 'pendingB')
|
||||
.replaceAll('[k]', '[profileKey]').replace(/\bW\b/g, 'W2');
|
||||
expect(hasStaleFillRaceFinding(renamed)).toBe(true);
|
||||
});
|
||||
|
||||
test('owning source headings and same-finding assessments survive intervening structure', () => {
|
||||
for (const heading of ['## Hypothetical example', '## Quoted source', '## Historical example only']) {
|
||||
expect(hasStaleFillRaceFinding(heading + '\n' + compact())).toBe(false);
|
||||
}
|
||||
expect(hasStaleFillRaceFinding(compact().replace(captured.heading,
|
||||
'F1 is rejected.\n\nUnrelated diagram:\n```\nA -> B\n```\n\n' + captured.heading))).toBe(false);
|
||||
expect(hasStaleFillRaceFinding(compact() + '\n\n### Assessment of F1\nF1 is rejected.')).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
const retry = () => `## Findings Registry\n\n${captured.retry.finding}\n\n${captured.retry.heading}\n\`\`\`\n${captured.retry.trace}\n\`\`\``;
|
||||
describe('version-labelled original prose with its owned schedule', () => {
|
||||
test('the exact retry and compact evidence require the original sequence, not amended prevention', () => {
|
||||
expect(hasStaleFillRaceFinding(captured.retry.report)).toBe(true);
|
||||
expect(hasStaleFillRaceFinding(retry())).toBe(true);
|
||||
});
|
||||
|
||||
test('each version and shared key must agree, with write completion before the later reader', () => {
|
||||
for (const [before, after] of [
|
||||
['DB returns v1', 'DB returns v2'], ['write commits v2 and', 'write commits v1 and'],
|
||||
['read then fills v1;', 'read then fills v2;'], ['every later read gets v1', 'every later read gets v2'],
|
||||
['write commits v2 and', 'write commits v3 and'], ['writeGen[key]', 'writeGen[foreign]'],
|
||||
['cache[key]', 'cache[foreign]'], ['R2 (read, began after W)', 'R2 (read, began before W)'],
|
||||
['delete (no-op), return', 'delete (no-op), pending'], ['DB SELECT -> v1', 'DB SELECT -> v2'],
|
||||
['DB UPDATE commits v2', 'DB UPDATE commits v3'], ['promise resolves, set(v1)', 'promise resolves, set(v2)'],
|
||||
['get -> v1 VIOLATION', 'get -> v2 VIOLATION'], ['6 sketch', '3 sketch'],
|
||||
['3 DB UPDATE commits v2', '3 DB UPDATE commits v2'],
|
||||
]) {
|
||||
expect(retry()).toContain(before);
|
||||
expect(hasStaleFillRaceFinding(retry().replace(before, after))).toBe(false);
|
||||
}
|
||||
expect(hasStaleFillRaceFinding(retry().replace(captured.retry.trace, captured.retry.trace.split('\n').filter(line => !/\b[456] sketch\b/.test(line)).join('\n')))).toBe(false);
|
||||
});
|
||||
|
||||
test('conditional, quoted, obsolete or withdrawn evidence cannot become a current finding', () => {
|
||||
for (const prefix of ['An unproven hypothesis.', 'Historical example only.', 'The following is a hypothetical example.']) {
|
||||
expect(hasStaleFillRaceFinding(prefix + '\n' + retry())).toBe(false);
|
||||
expect(hasStaleFillRaceFinding(retry().replace('Late fill after write.', prefix + ' Late fill after write.'))).toBe(false);
|
||||
}
|
||||
for (const heading of ['## Hypothetical example', '## Quoted source', '## Historical example only']) {
|
||||
expect(hasStaleFillRaceFinding(heading + '\n' + retry().replace('## Findings Registry', '### Findings Registry'))).toBe(false);
|
||||
}
|
||||
for (const withdrawal of ['F1 is rejected.', 'S1 is withdrawn.', 'The original schedule is impossible.', 'There is no stale-fill race.', 'Rejected: "There is no stale-fill race."']) {
|
||||
expect(hasStaleFillRaceFinding(retry() + '\n\n' + withdrawal)).toBe(false);
|
||||
expect(hasStaleFillRaceFinding(retry() + '\n\n### Assessment of F1\n' + withdrawal)).toBe(false);
|
||||
expect(hasStaleFillRaceFinding(retry().replace(' S2 join stale flight', withdrawal + '\n S2 join stale flight'))).toBe(false);
|
||||
}
|
||||
for (const withdrawal of ['S1 is withdrawn.', 'F1 is rejected.']) {
|
||||
expect(hasStaleFillRaceFinding(retry().replace(captured.retry.trace, captured.retry.trace + '\n' + withdrawal))).toBe(false);
|
||||
}
|
||||
expect(hasStaleFillRaceFinding(retry().split('\n').map(line => '> ' + line).join('\n'))).toBe(false);
|
||||
expect(hasStaleFillRaceFinding('````\n' + retry() + '\n````')).toBe(false);
|
||||
expect(hasStaleFillRaceFinding(retry().replace('Late fill after write.', 'If a late fill happens after write.'))).toBe(false);
|
||||
});
|
||||
|
||||
test('consistent versions and independent later findings remain valid', () => {
|
||||
expect(hasStaleFillRaceFinding(retry().replaceAll('v1', 'v7').replaceAll('v2', 'v8').replaceAll('[key]', '[profileKey]').replaceAll('key#1', 'profileKey#1'))).toBe(true);
|
||||
expect(hasStaleFillRaceFinding('## Prior example\nHistorical only.\n\n## Current review\n' + retry().replace('## Findings Registry', '### Findings Registry'))).toBe(true);
|
||||
expect(hasStaleFillRaceFinding(retry() + '\n\n### Other finding\nF9 is rejected.')).toBe(true);
|
||||
});
|
||||
});
|
||||
Reference in new issue
Block a user