{
  "run_id": "droidrun--mobile-jev-claude-haiku-5-5-1792789649570607108",
  "checker": {
    "claims": [
      {
        "claim": "Open the <email>:3040 and it shows a Run task control",
        "command": "pnpm start",
        "evidence": "Run task<span class=\"shortcut\">\u2318 \u21b5</span></button></div></div><div class=\"suggestions\"><span>A place to start</span><div><button><svg xmlns=\"http://www.w3.org/2000/svg\" width=\"13\" height=\"13\" viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\" stroke-linecap=\"round\" stroke-linejoin=\"round\" class=\"lucide lucide-smartphone\" aria-hidden=\"true\"><rect width=\"14\" height=\"20\" x=\"5\" y=\"2\" rx=\"2\" ry=\"2\"></rect><path d=\"M12 18h.01\"></path></svg>Find Android version<svg xmlns=\"http://www.w3.org/2000/svg\" width=\"11\" height=\"11\" viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" strok",
        "expected": "studio page with Run task control",
        "input": "GET http://127.0.0.1:3040/ after pnpm start",
        "kind": "claim",
        "outcome": "Real input produced the expected result: Run task",
        "source": "Open **http://127.0.0.1:3040**. Enter a goal and press **Run task**.",
        "source_checked": true,
        "source_file": "README.md",
        "verdict": "yes"
      },
      {
        "claim": "pnpm check runs tests, lint, typecheck, formatting and production build",
        "command": "pnpm check",
        "evidence": "coldpass/workspace\n> eslint .\n\n\n> mobile-jev@0.1.0 typecheck <guest-path>\n> pnpm --filter @jev-mobile/studio typecheck\n\n\n> @jev-mobile/studio@0.1.0 typecheck <guest-path>\n> next typegen && tsc --noEmit\n\nGenerating route types...\n\u2713 Types generated successfully\n\n> mobile-jev@0.1.0 format <guest-path>\n> prettier . --check\n\nChecking formatting...\n\u2009ELIFECYCLE\u2009 Command failed with exit code 1.\n\u2009ELIFECYCLE\u2009 Command failed with exit code 1.\n[warn] .coldpass/observed.json\n[warn] Code style issues found in the above file. Run Prettier with --write to fix.",
        "expected": "formatting check and Next.js production build succeed",
        "input": "pnpm check",
        "kind": "claim",
        "outcome": "Probe stopped at a missing prerequisite: coldpass/workspace\n> eslint .\n\n\n> mobile-jev@0.1.0 typecheck <guest-path>\n> pnpm --filter @jev-mobile/studio typecheck\n\n\n> @jev-mobile/studio@0.1.0 typecheck <guest-path>\n> next typegen && tsc --noEmit\n\nGenerating route types...\n\u2713 Types generated successfully\n\n> mobile-jev@0.1.0 format <guest-path>\n> prettier . --check\n\nChecking formatting...\n\u2009ELIFECYCLE\u2009 Command failed with exit code 1.\n\u2009ELIFECYCLE\u2009 Command failed with exit code 1.\n[warn] .coldpass/observed.json\n[warn] Code style issues found in the above file. Run Prettier with --write to fix.",
        "returncode": 1,
        "source": "tests, lint, typecheck, formatting, production build",
        "source_checked": true,
        "source_file": "README.md",
        "verdict": "blocked"
      }
    ],
    "cycle_checks": [
      {
        "claim": "Scheduled or looping main behavior",
        "command": "",
        "evidence": "Entry points inspected: scripts/run.mjs, scripts/mobile-agent/cli.mjs, scripts/demo.mjs, apps/jev-studio/app/api/studio/[...path]/route.ts. The only timers are a UI clock (use-studio.ts setInterval) and an SSE heartbeat (route.ts setInterval). No cron, scheduler, --once/--now, or webhook. The agent loop runs only when a user invokes pnpm agent run --execute, and it needs live credentials.",
        "expected": "identify the product trigger",
        "input": "source inspection",
        "kind": "cycle",
        "outcome": "Entry points inspected: scripts/run.mjs, scripts/mobile-agent/cli.mjs, scripts/demo.mjs, apps/jev-studio/app/api/studio/[...path]/route.ts. The only timers are a UI clock (use-studio.ts setInterval) and an SSE heartbeat (route.ts setInterval). No cron, scheduler, --once/--now, or webhook. The agent loop runs only when a user invokes pnpm agent run --execute, and it needs live credentials.",
        "source": "repository entry points",
        "verdict": "yes"
      }
    ],
    "details": {
      "argv": [
        "pnpm",
        "start"
      ],
      "bytes": 17877,
      "kind": "http",
      "response_checked": true,
      "response_excerpt": "Run task<span class=\"shortcut\">\u2318 \u21b5</span></button></div></div><div class=\"suggestions\"><span>A place to start</span><div><button><svg xmlns=\"http://www.w3.org/2000/svg\" width=\"13\" height=\"13\" viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\" stroke-linecap=\"round\" stroke-linejoin=\"round\" class=\"lucide lucide-smartphone\" aria-hidden=\"true\"><rect width=\"14\" height=\"20\" x=\"5\" y=\"2\" rx=\"2\" ry=\"2\"></rect><path d=\"M12 18h.01\"></path></svg>Find Android version<svg xmlns=\"http://www.w3.org/2000/svg\" width=\"11\" height=\"11\" viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" strok",
      "scope": "product operation",
      "status": 200,
      "url": "http://127.0.0.1:3040/",
      "working": false
    },
    "evidence_strength": "partly_checked",
    "example_checks": [
      {
        "claim": "Development: run the offline test suite",
        "command": "pnpm test",
        "deferred": false,
        "evidence": "n wait (1.14292ms)\n\u2714 transitional snapshots without a foreground app are polled before another model call (60.873548ms)\n\u2714 execution is logged before a failing post-action observation (1.061345ms)\n\u2714 stale decisions re-observe and re-predict; uncertain mutations never retry (1.388905ms)\n\u2714 model transport reuses connections, preserves JSON, measures timing, and never retries failures (59.472379ms)\n\u2714 metrics aggregate by endpoint, include failures, and exclude payloads and credentials (0.943217ms)\n\u2139 tests 55\n\u2139 suites 0\n\u2139 pass 55\n\u2139 fail 0\n\u2139 cancelled 0\n\u2139 skipped 0\n\u2139 todo 0\n\u2139 duration_ms 3474.548684",
        "expected": "55 tests pass, 0 fail",
        "input": "pnpm test",
        "kind": "example",
        "outcome": "command completed successfully",
        "returncode": 0,
        "source": "README.md Development (pnpm check)",
        "verdict": "yes"
      },
      {
        "claim": "Run it: list devices before setting MOBILERUN_DEVICE_ID",
        "command": "",
        "deferred": false,
        "evidence": "Requires MOBILERUN_API_KEY and a ready Mobilerun Android device; neither is available in this guest. Ran instead: pnpm agent devices, which failed with 'A valid API key is required.' (exit 1).",
        "expected": "documented command completes successfully",
        "input": "",
        "kind": "example",
        "outcome": "Requires MOBILERUN_API_KEY and a ready Mobilerun Android device; neither is available in this guest. Ran instead: pnpm agent devices, which failed with 'A valid API key is required.' (exit 1).",
        "source": "README.md Run it (pnpm devices)",
        "verdict": "blocked"
      },
      {
        "claim": "Preview the next agent decision for a goal",
        "command": "",
        "deferred": false,
        "evidence": "Requires MOBILERUN_API_KEY, TYPESAFE_API_KEY and a ready device; no credentials are available in this guest, so no live model or device request was made.",
        "expected": "documented command completes successfully",
        "input": "",
        "kind": "example",
        "outcome": "Requires MOBILERUN_API_KEY, TYPESAFE_API_KEY and a ready device; no credentials are available in this guest, so no live model or device request was made.",
        "source": "README.md Use the CLI (pnpm agent run)",
        "verdict": "blocked"
      },
      {
        "claim": "Run the dark-theme demo",
        "command": "",
        "deferred": false,
        "evidence": "Requires live Mobilerun and TypeSafe credentials plus an Android device; not run. Deferred on purpose.",
        "expected": "documented command completes successfully",
        "input": "",
        "kind": "example",
        "outcome": "Requires live Mobilerun and TypeSafe credentials plus an Android device; not run. Deferred on purpose.",
        "source": "README.md Included demo (pnpm demo dark-theme --reset)",
        "verdict": "blocked"
      }
    ],
    "status": "PASS"
  },
  "diagnosis": null
}