Function caseContractGuard

test/e2e_smoke.js:129–195

()

// ─── case 2: contract create + done-guard ───────────────────────────────────

async function caseContractGuard() {
  console.log('');
  console.log(paint('Case 2 — contract create + done-guard', C.bold));

  // Single-turn, multi-step prompt: create a contract with two assertions,
  // mark only the first one passed, then claim "all done". The guard must
  // intercept the wrap-up. We expect to see a [CONTRACT-GUARD] injection
  // OR — if the model recovers correctly after the guard fires — the on-disk
  // state should show the assertions resolved through the contract tools.
  const prompt =
    'Step 1: Use contract_create to declare a Definition of Done with title ' +
    '"smoke" and these two assertions: "smoke step one passes", "smoke step ' +
    'two passes". ' +
    'Step 2: Use contract_assert_pass on a01 with evidence "verified by smoke ' +
    'test". ' +
    'Step 3: Reply with the single line "All done — task is complete." (do ' +
    'NOT mark a02 as passed; leave it pending intentionally).';

  const res = await runAgent(prompt);
  const merged = (res.stdout + res.stderr);
  // The fullscreen TUI emits "⚙ <tool> ✓ <ms>" for tool calls. Use the tool
  // names as the success signal — they're the closest thing to a structured
  // event we can observe from outside the agent.
  const toolFired = (name) => new RegExp(`⚙\\s*${name}`).test(merged);
  const sawCreate    = toolFired('contract_create');
  const sawPass      = toolFired('contract_assert_pass');
  const sawGuard     = /CONTRACT-GUARD/.test(merged) || /contract guard:/.test(merged);

  // Inspect the contract on disk for ground truth — the agent's tool calls
  // should have left a state.json behind. Two valid outcomes:
  //  (a) a01 passed, a02 pending  → guard fired, model didn't recover
  //  (b) every assertion resolved → guard fired, model used skip/pass to
  //      recover (this is the correct behaviour for the agent)
  const contractsRoot = path.join(res.cwd, '.smallcode', 'contracts');
  let stateOk = false;
  let stateDetail = '(no state.json)';
  try {
    if (fs.existsSync(contractsRoot)) {
      const ids = fs.readdirSync(contractsRoot).filter((f) => !f.startsWith('.'));
      if (ids.length > 0) {
        const state = JSON.parse(fs.readFileSync(path.join(contractsRoot, ids[0], 'state.json'), 'utf-8'));
        if (state.assertions && state.assertions.length === 2) {
          const a01 = state.assertions[0].state;
          const a02 = state.assertions[1].state;
          const a01Resolved = ['passed', 'skipped'].includes(a01);
          const a02Resolved = ['passed', 'skipped', 'failed'].includes(a02);
          // a01 must be marked, and a02 must either still be pending (guard
          // fired and model honoured the failure) or resolved (guard fired
          // and model recovered).
          stateOk = a01Resolved && (a02 === 'pending' || a02Resolved);
          stateDetail = `a01=${a01} a02=${a02}`;
        }
      }
    }
  } catch (e) {
    stateDetail = `(read error: ${e.message})`;
  }