gstack/test/skill-e2e-plan-eng-plan-mode.test.ts

/**
 * plan-eng-review plan-mode smoke (gate, paid, real-PTY).
 *
 * See test/skill-e2e-plan-ceo-plan-mode.test.ts for the shared assertion
 * contract. This file exercises the same contract against /plan-eng-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-eng-review plan-mode smoke (gate)', () => {
  test('reaches a terminal outcome (asked or plan_ready) without silent writes', async () => {
    const obs = await runPlanSkillObservation({
      skillName: 'plan-eng-review',
      inPlanMode: true,
      timeoutMs: 300_000,
    });

    if (obs.outcome === 'silent_write' || obs.outcome === 'exited' || obs.outcome === 'timeout') {
      throw new Error(
        `plan-eng-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);
});