test: wire assertReportAtBottomIfPlanWritten into 4 plan-mode E2E tests + add seeded-plan STOP-gate case

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>
This commit is contained in:
Garry Tan
2026-05-03 20:08:27 -07:00
parent ece2650d4f
commit 99833de9f4
4 changed files with 102 additions and 4 deletions

View File

@@ -10,7 +10,10 @@
*/
import { describe, test, expect } from 'bun:test';
import { runPlanSkillObservation, planFileHasDecisionsSection } from './helpers/claude-pty-runner';
import {
runPlanSkillObservation,
assertReportAtBottomIfPlanWritten,
} from './helpers/claude-pty-runner';
const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
const describeE2E = shouldRun ? describe : describe.skip;
@@ -32,6 +35,7 @@ describeE2E('plan-design-review plan-mode smoke (gate)', () => {
);
}
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
@@ -68,5 +72,6 @@ describeE2E('plan-design-review plan-mode smoke (gate)', () => {
// Other plan-mode skills require the decisions section under
// --disallowedTools; design is the special case.
expect(['asked', 'plan_ready']).toContain(obs.outcome);
assertReportAtBottomIfPlanWritten(obs);
}, 360_000);
});