mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-16 18:05:31 +02:00
* feat: add a restricted and supervised Claude Code runner Preserve configured authentication and models while enforcing tool access, strict completion JSON, bounded output and process cleanup. Cover argv, failure handling, session metadata and Windows process containment. * feat: route outside reviews by harness and migrate wrapper installs Use Claude Code from Codex and Codex from other supported hosts, with shared invocation rendering, positive gate validation and per-phase provenance. Rename /claude to /claude-code, repair managed shared and copied installations safely, and generate native Kiro skills. Add installed-workflow, failure-injection and live cross-harness regression coverage. * test: recognize CEO mode labels without terminal spacing The paid workflow rendered SCOPEEXPANSION at option 4, but its driver required a literal space. Match the leading mode title without cursor-spacing artifacts and ignore adjacent preview text. Preserve missing-target failures and downstream posture assertions. * test: isolate plan-count fixtures before starting review workflows Seed the complete test plan in a private git repository before launching Claude, so a bare slash command cannot review the live workspace while a delayed fixture message remains queued. Preserve count thresholds, parsers and budgets. Add initial-context and installed-discovery tests, and retain startup/terminal diagnostics on failed evaluations. * test: stabilize review fixtures and Claude eval startup Preserve source boundaries in workflow judge inputs, isolate CEO mode plans, and wait for interactive trust input readiness. Keep startup failure evidence and retain existing models, budgets, and assertions. Co-Authored-By: OpenAI Codex <noreply@openai.com> * test: classify collapsed review modes and isolate seeded findings Keep review questions out of the setup count when terminal cursor positioning removes spaces. State existing webhook safeguards so the five-finding control measures its seeded defects without accidental extra security and concurrency gaps. Preserve question bands and the paired control. Co-Authored-By: OpenAI Codex <noreply@openai.com> * test: isolate browser daemon state across free shards Co-Authored-By: OpenAI Codex <noreply@openai.com> * test: stabilize native review counting and interactive navigation Co-Authored-By: OpenAI Codex <noreply@openai.com> * chore: prepare v1.82.0.0 release Co-Authored-By: OpenAI Codex <noreply@openai.com> * fix: eliminate browser and process-cleanup test flakes Pin every CI surface to Bun 1.4.0 to avoid extra-stdio finalizers closing reused live sockets. Add an isolated GC/listener regression that fails on Bun 1.3.13, and prevent coordinated rollback to an affected CI runtime. Check renderer cleanup against the render's own staging directory so concurrent renders cannot invalidate the assertion. Make the no-pgrep process-tree walk tolerate disappearing /proc entries, and synchronize its test fixture through child readiness and pipe EOF instead of sleeps. Validation: 9,157 passed, 31 skipped, zero failures across 556 files with retries disabled. Build, all-host generation freshness, and skill checks passed. All three races have failing-before/passing-after regressions. * fix: count completed native review questions in evals * fix: drive review navigation from confirmed native choices * fix: require complete section-loading eval reports * test: isolate telemetry HTTP transport from local assertions * fix: keep review input on the active native question * test: let tunnel revocation daemon choose an available port * test: allocate available ports for pairing and watchdog fixtures * fix: stabilize planning eval navigation and phase reporting * test: isolate installed runtime paths in planning evals * test: stabilize review evidence and concurrent refresh fixtures * fix: resolve design findings before editing the plan * fix: honor and persist disabled outside plan reviews * fix: preserve planning decisions and terminal evidence Load installed host reviews at autoplan phase entry and wait for completed reviewers and saved artifacts. Reuse approved remedies while preserving individual finding decisions. Drive interactive evals from the current terminal viewport, bind native questions across scrolling, and require complete native report evidence. Cover captured stale menus, permission lifecycles, setup classification, and disabled-review tool availability with deterministic regressions. Advance release metadata and the upgrade migration to the unclaimed 1.83.0.0 slot. * fix: drive native review questions and preserve current plans Use the native single-choice keyboard protocol and current terminal viewport, with per-question navigation inside packets and completed-call coverage. Keep permissions, multi-select menus, and Submit controls distinct. Send Autoplan reviewers the amended implementation plan, keep its review record separate, and supply retained application contracts in the chain fixture. Clarify individual DevEx decisions and complete CEO fix options; use one active plan destination for the section-loading report. * fix: preserve complete plan-review decisions * fix: recognize native plan dialogs and reviewer controls * fix: preserve review decisions and phase completion * fix: recognize completed reviews without losing findings * fix: preserve review continuity and native eval completion * test: fix native review completion and eval retry isolation * test: handle native review menus and complete eval fixtures * test: fix native review setup, completion, and isolation failures * test: limit native skill discovery to runtime assets * fix: bind Autoplan reviews to full ordered phase inputs * test: fix planning eval routing, counting, and timeout handling * chore: advance queued release to v1.84.0.0 * fix: preserve complete review inputs and planning decisions * fix: reconcile review approvals and preserve phase obligations * fix: preserve review obligations and unblock eval permissions Carry recorded Autoplan requirements into blind phase inputs, require Eng review approvals before exit, and exercise combined asynchronous flows in CEO reviews. Correct native finding and handoff classification and unblock repeated report edits using scoped request identities. * fix: retain plan requirements and complete native review dialogs * fix: complete native review prompts and retain plan references * fix: preserve review inputs and classify native eval evidence * fix: check competing completion orders in CEO reviews * fix: recognize review decisions and require phase methodology Require the current phase methodology before Autoplan snapshots. Correct substantive decision, closed handoff, and cache-finding classification, and honor the recommended implementation approach in native review dialogs. Add captured-transcript regressions without changing review thresholds, provider models, retries, or deadlines. * test: bind native review decisions and close completed handoffs * fix: complete review dialogs and verify methodology delivery * fix: preserve review evidence and unblock native eval prompts * fix: handle native review question completions * fix: recognize native review narration and controls * fix: count native review decisions and isolate eval fixtures * test: verify seeded review coverage and current artifact permissions * test: isolate model and brain-aware skill renders * fix: repair native workflow evaluation and clarify review steps * fix: stabilize workflow eval evidence and review guidance * test: repair native workflow observation and fixture isolation * fix: recognize completed workflow evidence and owned skill reads * test: repair seeded workflow delivery and completion evidence * test: recognize current review evidence across native forms * test: handle native review variants and permission redraws * fix: honor review preferences and recognize native eval evidence * test: recognize completed review decisions and queued permissions * test: match current review contracts and partial-line edits * test: recognize completed workflow evidence and bounded human waits * fix: preserve review entry gates and native eval interactions * fix: recognize native workflow evidence and preserve review gates * test: recognize current review evidence and preconfigure workflow fixtures * test: recognize completed review findings and scoped artifact permissions * fix: stabilize native workflow review and permission evidence * fix: recognize current review evidence and scoped edit confirmations Clarify Design and engineering review entry instructions and Design scoring. Recognize required legacy coverage and public Autoplan completion recaps. Bind the pending Edit confirmation to its exact file, ordered digest, and one-request approval when a preceding command display remains visible. Keep reviews within their existing size limits and preserve scope gates when extracting workflow fixtures from either supported preamble header. Keep failure outcomes, review thresholds, provider choices, and eval budgets. * fix: recover review workflow progress and eval evidence * fix: recognize valid review evidence and scope selection * test: fix review evidence parsing and repeated artifact prompts * test: recognize valid review decisions and pending native cards * fix(plan-eng-review): keep final navigation consistent with approved tasks * test: recognize valid review evidence and bind legacy diff requests * fix: stabilize review eval evidence and harness repair guidance * docs: update project documentation for v1.85.0.0 Co-Authored-By: OpenAI Codex <noreply@openai.com> * test: fix Windows CI fixtures and credential scan Rebase captured JSON values and filesystem evidence using the appropriate path convention. Compile native fake CLIs on Windows and synchronize pipe holder readiness, with cleanup retained when assertions fail. Assemble synthetic credential fixtures at runtime so the added-line scan keeps enforcing the same gate without flagging its own rejection controls. Discover generated skills directly for the empty-find regression check, avoiding a recursive scan through saved evaluation artifacts and dependencies. * fix: preserve source renders on Windows Compare canonical generator paths using native separators so an output sidecar pointing at the source cannot overwrite its skill or metadata. Keep the regression fixture isolated from the real checkout and expose freshness diagnostics before asserting subprocess status. Detach Windows drain-test pipe holders from the fake provider's automatic child cleanup while preserving the enclosing runner job and its assertions. * fix: clarify outside review fallback and CEO decisions Render one applicable own-harness fallback path and retain native review, disabled policy, and missing-coverage semantics. Align report field names and mode labels, and make the existing per-cut scope approval explicit. Regenerate skill outputs and keep the workflow judge's model, thresholds, and retry policy unchanged. * chore: move release to free version slot (v1.86.0.0) PR #2852 now claims v1.85.0.0. Align the release metadata and rename migration so upgrades from that version still receive it. Co-Authored-By: OpenAI Codex <noreply@openai.com> * fix: include engineering review prerequisites and restore branch context * fix: recognize coverage diagrams and clarify design review instructions * fix: preserve file identities and join Windows test processes --------- Co-authored-by: OpenAI Codex <noreply@openai.com>
118 lines
8.2 KiB
TypeScript
118 lines
8.2 KiB
TypeScript
import { describe, expect, test } from 'bun:test';
|
|
import * as fs from 'node:fs';
|
|
import * as os from 'node:os';
|
|
import * as path from 'node:path';
|
|
import { hasNativePostAnswerCeoPosture, nativeCeoModeAnswer } from './helpers/ceo-mode-option';
|
|
import { readPlanCountTranscript, type NativePublicToolEvent } from './helpers/plan-count-transcript';
|
|
import { E2E_TOUCHFILES, selectTests } from './helpers/touchfiles';
|
|
import captured from './fixtures/ceo-mode-posture-ad.json';
|
|
|
|
const patterns = {
|
|
'HOLD SCOPE': /\b(rigor|bulletproof|hold\s*scope|maximum\s+rigor)\b/i,
|
|
'SCOPE EXPANSION': /\b(expansion|10x|delight|dream|cathedral|opt[\s-]?in)\b/i,
|
|
};
|
|
function replay(index: number, change?: (rows: any[]) => void) {
|
|
const item = captured.cases[index]!;
|
|
const rows = structuredClone(item.records);
|
|
change?.(rows);
|
|
const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'ceo-posture-ad-'));
|
|
const project = path.join(dir, 'projects', 'owned');
|
|
fs.mkdirSync(project, {recursive:true});
|
|
fs.writeFileSync(path.join(project, item.process.sessionId+'.jsonl'), rows.map(row=>JSON.stringify(row)).join('\n')+'\n');
|
|
const events: NativePublicToolEvent[]=[];
|
|
try { return {item, transcript:readPlanCountTranscript(dir,item.process.cwd,event=>events.push(event)),events}; }
|
|
finally { fs.rmSync(dir,{recursive:true,force:true}); }
|
|
}
|
|
function matches(e: ReturnType<typeof replay>) {
|
|
const mode=e.item.mode as keyof typeof patterns;
|
|
return hasNativePostAnswerCeoPosture(e.transcript,mode,patterns[mode],e.item.selectedAt,e.events);
|
|
}
|
|
function rebind(e: ReturnType<typeof replay>) {
|
|
const decision=e.transcript.calls[1]!;
|
|
e.events[2]!.input={questions:decision.questions};
|
|
decision.answers={[decision.questions[0]!.question]:decision.questions[0]!.options[0]!.label};
|
|
}
|
|
|
|
for (const index of [0,1]) describe(`${captured.cases[index]!.mode} actual completed mode application`,()=>{
|
|
test('the exact mode answer and concrete scope decision supply posture without finalized prose',()=>{
|
|
const e=replay(index);
|
|
expect(e.item.actualFailure.state).toBe('failed');
|
|
expect(e.transcript.calls.map(call=>call.toolUseId)).toEqual([e.item.modeToolUseId,e.item.decisionToolUseId]);
|
|
expect(nativeCeoModeAnswer(e.transcript,e.item.mode as keyof typeof patterns,e.item.selectedAt)?.toolUseId).toBe(e.item.modeToolUseId);
|
|
expect(e.transcript.assistantMessages.every(message=>Date.parse(message.timestamp)<e.item.selectedAt)).toBe(true);
|
|
expect(matches(e)).toBe(true);
|
|
expect(hasNativePostAnswerCeoPosture(e.transcript,e.item.mode as keyof typeof patterns,patterns[e.item.mode as keyof typeof patterns],e.item.selectedAt)).toBe(false);
|
|
});
|
|
test.each(['wrong selected mode','pending mode','failed mode','answer before selection','pending decision','failed decision',
|
|
'foreign session','pre-mode request','reply before request','reply before selection','reply timestamp mismatch','wrong tool','missing request','missing reply','failed public reply','duplicate request','duplicate reply',
|
|
'request mismatch','unknown answer','extra question','extra option','multiselect','quoted decision','fenced decision',
|
|
'mere mode mention','extra obligation','extra imperative','option imperative'])('%s cannot supply posture',failure=>{
|
|
const e=replay(index);const [mode,decision]=e.transcript.calls;const q=decision!.questions[0]!;
|
|
switch(failure){
|
|
case 'wrong selected mode':mode!.answers![mode!.questions[0]!.question]=index===0?'SCOPE EXPANSION':'HOLD SCOPE';break;
|
|
case 'pending mode':mode!.answered=false;break;
|
|
case 'failed mode':mode!.failed=true;break;
|
|
case 'answer before selection':mode!.answeredAt=new Date(e.item.selectedAt-1).toISOString();break;
|
|
case 'pending decision':decision!.answered=false;break;
|
|
case 'failed decision':decision!.failed=true;break;
|
|
case 'foreign session':decision!.sessionId=e.events[2]!.sessionId=e.events[3]!.sessionId='foreign';break;
|
|
case 'pre-mode request':e.events[2]!.timestamp=e.events[0]!.timestamp;break;
|
|
case 'reply before request':decision!.answeredAt=e.events[3]!.timestamp=new Date(Date.parse(e.events[2]!.timestamp)-1).toISOString();break;
|
|
case 'reply before selection':decision!.answeredAt=e.events[3]!.timestamp=new Date(e.item.selectedAt-1).toISOString();break;
|
|
case 'reply timestamp mismatch':e.events[3]!.timestamp=new Date(Date.parse(decision!.answeredAt!)+1).toISOString();break;
|
|
case 'wrong tool':e.events[2]!.name='Read';break;
|
|
case 'missing request':e.events.splice(2,1);break;
|
|
case 'missing reply':e.events.splice(3,1);break;
|
|
case 'failed public reply':e.events[3]!.isError=true;break;
|
|
case 'duplicate request':e.events.push({...e.events[2]!});break;
|
|
case 'duplicate reply':e.events.push({...e.events[3]!});break;
|
|
case 'request mismatch':e.events[2]!.input={questions:[]};break;
|
|
case 'unknown answer':decision!.answers![q.question]='Unrecognized';break;
|
|
case 'extra question':decision!.questions.push({...structuredClone(q),header:'Also',question:'Also remove the CI gate?'});rebind(e);break;
|
|
case 'extra option':q.options.push({label:'Remove the CI gate',description:'A separate obligation.'});rebind(e);break;
|
|
case 'multiselect':q.multiSelect=true;rebind(e);break;
|
|
case 'quoted decision':q.question=q.question.split('\n').map(line=>'> '+line).join('\n');rebind(e);break;
|
|
case 'fenced decision':q.question='```text\n'+q.question+'\n```';rebind(e);break;
|
|
case 'mere mode mention':q.question=`D6 — Continue the review?\nSelected ${e.item.mode}.`;rebind(e);break;
|
|
case 'extra obligation':q.question+=' Also, should we remove the CI gate?';rebind(e);break;
|
|
case 'extra imperative':q.question+=' Also remove the CI gate.';rebind(e);break;
|
|
case 'option imperative':q.options[0]!.description+=' Please remove the CI gate.';rebind(e);break;
|
|
}
|
|
expect(matches(e),failure).toBe(false);
|
|
});
|
|
test.each(['Delete the CI gate.', 'Ship the new endpoint now.', 'After that, disable authentication.'])('an instruction appended after the final comparison is not part of the scope brief: %s', extra=>{
|
|
const e=replay(index);const q=e.transcript.calls[1]!.questions[0]!;
|
|
q.question+=' '+extra;rebind(e);expect(matches(e)).toBe(false);
|
|
});
|
|
test('foreign, sidechain, missing and failed native records do not become completed evidence',()=>{
|
|
for(const change of [(rows:any[])=>{rows[3].cwd='/foreign';},(rows:any[])=>{rows[3].isSidechain=true;},
|
|
(rows:any[])=>{rows.pop();},(rows:any[])=>{rows[4].message.content[0].is_error=true;}]) expect(matches(replay(index,change))).toBe(false);
|
|
});
|
|
});
|
|
|
|
test('HOLD requires the explicit out-of-scope deferral and its selected defer answer',()=>{
|
|
for(const change of [(q:any)=>{q.question=q.question.replace('Under HOLD SCOPE, keep or defer','Under HOLD SCOPE, automatically add');},
|
|
(q:any)=>{q.question=q.question.replace('not in the plan text','required by the plan text');},
|
|
(q:any)=>{q.question=q.question.replace('pure additions, not repairs to meet a stated invariant','repairs needed to meet a stated invariant');},
|
|
(q:any)=>{q.options[0].label='Keep all three (recommended)';},
|
|
(q:any)=>{q.options[1].label='Remove CI gate';}]){
|
|
const e=replay(0);change(e.transcript.calls[1]!.questions[0]);rebind(e);expect(matches(e)).toBe(false);
|
|
}
|
|
const e=replay(0);const q=e.transcript.calls[1]!.questions[0]!;
|
|
e.transcript.calls[1]!.answers={[q.question]:q.options[1]!.label};expect(matches(e)).toBe(false);
|
|
});
|
|
|
|
test('completed expansion decisions require application of the selected mode',()=>{
|
|
for(const change of [(q:any)=>{q.question='D6 — Continue the review?\nSelected SCOPE EXPANSION.';},
|
|
(q:any)=>{q.question=q.question.replace('SCOPE EXPANSION mode','SELECTIVE EXPANSION mode');},
|
|
(q:any)=>{q.question=q.question.replace('SCOPE EXPANSION mode','HOLD SCOPE mode');},
|
|
(q:any)=>{q.options[1].label='Enable telemetry';}]){
|
|
const e=replay(1);change(e.transcript.calls[1]!.questions[0]);rebind(e);expect(matches(e)).toBe(false);
|
|
}
|
|
});
|
|
|
|
test('the new replay controls and fixture select the actual periodic mode-routing caller',()=>{
|
|
for(const file of ['test/ceo-mode-posture-ad.test.ts','test/fixtures/ceo-mode-posture-ad.json'])
|
|
expect(selectTests([file],E2E_TOUCHFILES,[]).selected).toEqual(['plan-ceo-mode-routing']);
|
|
});
|