mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-09 14:09:47 +08:00
99833de9f4
Every test case in skill-e2e-plan-{eng,ceo,design,devex}-plan-mode.test.ts
that produces a plan file now asserts ## GSTACK REVIEW REPORT is the last
## section. The {{PLAN_FILE_REVIEW_REPORT}} resolver mandated this contract;
nothing tested it until now.
Plan-eng additionally gains a third test case: STOP gate fires when seeded
plan forces Step 0 findings. Combines the new initialPlanContent runner
option with --disallowedTools AskUserQuestion to force the Conductor
MCP-variant path through mcp__*__AskUserQuestion. Asserts outcome NOT in
{wrote_findings_before_asking, auto_decided, silent_write, exited, timeout}
and that plan_ready outcomes carry a ## Decisions section.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
75 lines
2.8 KiB
TypeScript
75 lines
2.8 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,
|
|
planFileHasDecisionsSection,
|
|
assertReportAtBottomIfPlanWritten,
|
|
} 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);
|
|
assertReportAtBottomIfPlanWritten(obs);
|
|
}, 360_000);
|
|
|
|
// v1.21+ regression: see skill-e2e-plan-ceo-plan-mode.test.ts for the
|
|
// contract. Pass envelope is ['asked', 'plan_ready']; failure signals
|
|
// are 'auto_decided' (AUTO_DECIDE without opt-in) plus the standard
|
|
// silent_write/exited/timeout.
|
|
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 === 'auto_decided' ||
|
|
obs.outcome === 'silent_write' ||
|
|
obs.outcome === 'exited' ||
|
|
obs.outcome === 'timeout'
|
|
) {
|
|
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}`,
|
|
);
|
|
}
|
|
if (obs.outcome === 'plan_ready') {
|
|
if (!obs.planFile || !planFileHasDecisionsSection(obs.planFile)) {
|
|
throw new Error(
|
|
`plan-devex-review AskUserQuestion-blocked regression: plan_ready without a "## Decisions" section in ${obs.planFile ?? '<no plan file detected>'} — Step 0 was silently skipped.\n` +
|
|
`--- evidence (last 2KB visible) ---\n${obs.evidence}`,
|
|
);
|
|
}
|
|
}
|
|
expect(['asked', 'plan_ready']).toContain(obs.outcome);
|
|
assertReportAtBottomIfPlanWritten(obs);
|
|
}, 360_000);
|
|
});
|