mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-02 03:35:09 +02:00
Garry Tan
aaf2668103
Conductor launches Claude Code with --disallowedTools AskUserQuestion
--permission-mode default --permission-prompt-tool stdio (verified by
inspecting the live conductor claude process via ps -p ... -o args=).
Native AskUserQuestion is removed from the model's tool registry; without
fallback guidance the plan-mode skills (plan-ceo-review, plan-eng-review,
plan-design-review, plan-devex-review, autoplan, office-hours) silently
proceed and never surface decisions to the user.
Adds 6 gate-tier real-PTY regression cases:
- 4 inline test cases inside the existing plan-X-review-plan-mode.test
files, each exercising the same skill with extraArgs ['--disallowedTools',
'AskUserQuestion'] and asserting outcome === 'asked'. plan-design-review
keeps the ['asked', 'plan_ready'] envelope (legitimate short-circuit on
no-UI-scope) but explicitly fails on 'auto_decided'.
- 2 standalone test files for autoplan + office-hours (which had no prior
plan-mode test). autoplan asserts the FIRST non-auto-decided gate fires
(Phase 1 premise confirmation) — autoplan auto-decides intermediate
questions BY DESIGN.
Touchfile entries:
- autoplan-auto-mode + office-hours-auto-mode added to E2E_TOUCHFILES +
E2E_TIERS (gate)
- existing plan-X-review-plan-mode entries gain question-tuning.ts and
generate-ask-user-format.ts touchfile deps so AUTO_DECIDE-related
resolver changes correctly invalidate the regression tests
- touchfiles.test.ts count updated 18 -> 19 to cover the autoplan
touchfile dependency on plan-ceo-review/**
Filenames retain `auto-mode` for branch-history continuity. Auto-mode (the
AUTO_DECIDE preamble path when QUESTION_TUNING=true) is a related but
distinct silencing mechanism; both share the same fix surface in the
preamble.
These tests are expected to FAIL on this branch until the fix lands. The
failure is the receipt for the regression.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
56 lines
2.1 KiB
TypeScript
56 lines
2.1 KiB
TypeScript
/**
|
|
* plan-devex-review plan-mode smoke (gate, paid, real-PTY).
|
|
*
|
|
* See test/skill-e2e-plan-ceo-plan-mode.test.ts for the shared assertion
|
|
* contract. Exercises the same contract against /plan-devex-review.
|
|
*/
|
|
|
|
import { describe, test, expect } from 'bun:test';
|
|
import { runPlanSkillObservation } from './helpers/claude-pty-runner';
|
|
|
|
const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
|
|
const describeE2E = shouldRun ? describe : describe.skip;
|
|
|
|
describeE2E('plan-devex-review plan-mode smoke (gate)', () => {
|
|
test('reaches a terminal outcome (asked or plan_ready) without silent writes', async () => {
|
|
const obs = await runPlanSkillObservation({
|
|
skillName: 'plan-devex-review',
|
|
inPlanMode: true,
|
|
timeoutMs: 300_000,
|
|
});
|
|
|
|
if (obs.outcome === 'silent_write' || obs.outcome === 'exited' || obs.outcome === 'timeout') {
|
|
throw new Error(
|
|
`plan-devex-review plan-mode smoke FAILED: outcome=${obs.outcome}\n` +
|
|
`summary: ${obs.summary}\n` +
|
|
`elapsed: ${obs.elapsedMs}ms\n` +
|
|
`--- evidence (last 2KB visible) ---\n${obs.evidence}`,
|
|
);
|
|
}
|
|
expect(['asked', 'plan_ready']).toContain(obs.outcome);
|
|
}, 360_000);
|
|
|
|
// v1.21+ regression: see skill-e2e-plan-ceo-plan-mode.test.ts for the
|
|
// contract. plan-devex-review's Step 0 always issues a persona-mode
|
|
// AskUserQuestion before scoring, so 'asked' is the only pass when
|
|
// AskUserQuestion is --disallowedTools.
|
|
test('AskUserQuestion surfaces when --disallowedTools AskUserQuestion is set', async () => {
|
|
const obs = await runPlanSkillObservation({
|
|
skillName: 'plan-devex-review',
|
|
inPlanMode: true,
|
|
extraArgs: ['--disallowedTools', 'AskUserQuestion'],
|
|
timeoutMs: 300_000,
|
|
});
|
|
|
|
if (obs.outcome !== 'asked') {
|
|
throw new Error(
|
|
`plan-devex-review AskUserQuestion-blocked regression: outcome=${obs.outcome}\n` +
|
|
`summary: ${obs.summary}\n` +
|
|
`elapsed: ${obs.elapsedMs}ms\n` +
|
|
`--- evidence (last 2KB visible) ---\n${obs.evidence}`,
|
|
);
|
|
}
|
|
expect(obs.outcome).toEqual('asked');
|
|
}, 360_000);
|
|
});
|