mirror of
https://github.com/garrytan/gstack.git
synced 2026-06-21 17:20:02 +02:00
Garry Tan
af5f066186
The first re-run after wiring the LLM judge revealed that the model also
emits a third surface I hadn't anticipated: a properly-formatted question
with options ("Pick A, B, or C in your reply") rendered as prose AND
followed by ExitPlanMode (outcome=plan_ready). The migrated tests only
accepted (## Decisions section) OR (BLOCKED string) — neither matched
this case, so the test failed even though the user clearly saw the
question.
Three valid surfaces now:
1. `## Decisions to confirm` section in plan file (legacy fallback path,
still valid through migration window)
2. `BLOCKED — AskUserQuestion` string in TTY (post-v1.28 BLOCKED rule)
3. Numbered/lettered options visible in TTY as prose (post-v1.28 prose
rendering — uses the existing isProseAUQVisible detector)
Also fixes assertReportAtBottomIfPlanWritten to be tolerant of:
- Missing files (path detected from TTY but file not persisted) — was
throwing ENOENT on plan_design_plan_mode and plan_ceo_plan_mode test 1
- 'asked' outcome (smoke test exited at first AUQ before the model
reached the report-writing step) — was throwing on the 1 fail in the
plan-eng-plan-mode --disallowedTools test
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
91 lines
3.8 KiB
TypeScript
91 lines
3.8 KiB
TypeScript
/**
|
|
* plan-design-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-design-review.
|
|
*
|
|
* Note: on no-UI-scope branches plan-design-review legitimately short-
|
|
* circuits to plan_ready without firing AskUserQuestion. Both 'asked' and
|
|
* 'plan_ready' are valid pass outcomes.
|
|
*/
|
|
|
|
import { describe, test, expect } from 'bun:test';
|
|
import {
|
|
runPlanSkillObservation,
|
|
assertReportAtBottomIfPlanWritten,
|
|
isProseAUQVisible,
|
|
} from './helpers/claude-pty-runner';
|
|
|
|
const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
|
|
const describeE2E = shouldRun ? describe : describe.skip;
|
|
|
|
describeE2E('plan-design-review plan-mode smoke (gate)', () => {
|
|
test('reaches a terminal outcome (asked or plan_ready) without silent writes', async () => {
|
|
const obs = await runPlanSkillObservation({
|
|
skillName: 'plan-design-review',
|
|
inPlanMode: true,
|
|
timeoutMs: 300_000,
|
|
});
|
|
|
|
if (obs.outcome === 'silent_write' || obs.outcome === 'exited' || obs.outcome === 'timeout') {
|
|
throw new Error(
|
|
`plan-design-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);
|
|
assertReportAtBottomIfPlanWritten(obs);
|
|
}, 360_000);
|
|
|
|
// v1.21+ regression: see skill-e2e-plan-ceo-plan-mode.test.ts for the
|
|
// contract. plan-design-review legitimately short-circuits on no-UI-scope
|
|
// branches, so this case has historically used a looser envelope.
|
|
//
|
|
// Post-v1.28 (forever-war fix), 'exited' is acceptable when BLOCKED is
|
|
// visible in the TTY (model correctly recognized the AUQ-unavailable
|
|
// failure mode and stopped). The legacy 'plan_ready' (with or without
|
|
// decisions section) and 'asked' paths remain valid pass outcomes.
|
|
//
|
|
// The discriminating regression signals are 'auto_decided' (AUTO_DECIDE
|
|
// preamble fired upstream), 'silent_write', 'timeout', or 'exited'
|
|
// without BLOCKED visible — all mean the user never saw a question they
|
|
// should have.
|
|
test('does not silently auto-decide when --disallowedTools AskUserQuestion is set', async () => {
|
|
const obs = await runPlanSkillObservation({
|
|
skillName: 'plan-design-review',
|
|
inPlanMode: true,
|
|
extraArgs: ['--disallowedTools', 'AskUserQuestion'],
|
|
timeoutMs: 300_000,
|
|
});
|
|
|
|
// Surface visibility check (same as ceo / autoplan migrations): user
|
|
// must SEE the question via BLOCKED string OR prose-rendered AUQ options.
|
|
const blockedVisible = /BLOCKED\s*[—-]\s*AskUserQuestion/i.test(obs.evidence);
|
|
const proseAUQVisible = isProseAUQVisible(obs.evidence);
|
|
const surfaceVisible = blockedVisible || proseAUQVisible;
|
|
|
|
if (
|
|
obs.outcome === 'auto_decided' ||
|
|
obs.outcome === 'silent_write' ||
|
|
obs.outcome === 'timeout'
|
|
) {
|
|
throw new Error(
|
|
`plan-design-review AskUserQuestion-blocked regression: outcome=${obs.outcome}\n` +
|
|
`summary: ${obs.summary}\n` +
|
|
`elapsed: ${obs.elapsedMs}ms\n` +
|
|
`--- evidence (last 2KB visible) ---\n${obs.evidence}`,
|
|
);
|
|
}
|
|
if (obs.outcome === 'exited' && !surfaceVisible) {
|
|
throw new Error(
|
|
`plan-design-review AskUserQuestion-blocked regression: outcome=exited without any visible question surface (no BLOCKED string, no prose-rendered AUQ options). Model quit silently.\n` +
|
|
`--- evidence (last 2KB visible) ---\n${obs.evidence}`,
|
|
);
|
|
}
|
|
expect(['asked', 'plan_ready', 'exited']).toContain(obs.outcome);
|
|
assertReportAtBottomIfPlanWritten(obs);
|
|
}, 360_000);
|
|
});
|