{
  "run_id": "loadn-ai--loadn-gpt-6-luna-1793190085090151963",
  "date": "2026-10-28T12:23:37.223467+00:00",
  "repo": "loadn-ai/loadn",
  "kind": "repo",
  "source": "https://github.com/loadn-ai/loadn",
  "commit": "544915ab78d0e0363b7bfb7b96cf07ebcbf1bf18",
  "model": "gpt-6-luna",
  "model_version": "gpt-6-luna",
  "test_version": "readme-604d73685be33b2939b2632791fb1de37972f659febb28a139c60d6e81057c18",
  "pass": true,
  "outcome": "pass",
  "time_to_working_s": 105.69985680399986,
  "total_s": 132.13327741622925,
  "steps": [
    "pwd && ls -la && rg --files -g 'README*' -g 'pyproject.toml' -g 'package.json' -g 'requirements*' -g 'Makefile' -g '*.md' | head -80",
    "cat README.md",
    "python3 --version && python3 -m pip --version && python3 -m venv /tmp/loadn-venv && /tmp/loadn-venv/bin/python -m pip install -e '.[dev]'",
    "python3 -m venv /tmp/loadn-run && /tmp/loadn-run/bin/pip install -e . && sed -n '1,240p' tests/test_cli.py && ls -la",
    "find tests -maxdepth 2 -type f | head -40; ls -la .coldpass; LOADN_PROVIDER=fake LOADN_FAKE_DIR=<guest-path> /tmp/loadn-run/bin/loadn -p --dangerously-skip-permissions 'say hello'",
    "mkdir -p .coldpass && cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"/tmp/loadn-run/bin/loadn\",\"-p\",\"--dangerously-skip-permissions\",\"say hello\"],\"cwd\":\"<guest-path>\",\"env\":{\"LOADN_PROVIDER\":\"fake\",\"LOADN_FAKE_DIR\":\"<guest-path>\"},\"expected_text\":\"\u6536\u5230\uff1asay hello\uff08fake\uff09\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[\n  {\"kind\":\"claim\",\"claim\":\"The fake provider replays control files from $LOADN_FAKE_DIR.\",\"source\":\"The fake provider (`LOADN_PROVIDER=fake`) replays control files from `$LOADN_FAKE_DIR`\",\"input\":\"say hello\",\"expected\":\"\u6536\u5230\uff1asay hello\uff08fake\uff09\",\"probe_kind\":\"cli\",\"argv\":[\"/tmp/loadn-run/bin/loadn\",\"-p\",\"--dangerously-skip-permissions\",\"say hello\"],\"env\":{\"LOADN_PROVIDER\":\"fake\",\"LOADN_FAKE_DIR\":\"<guest-path>\"},\"expected_text\":\"\u6536\u5230\uff1asay hello\uff08fake\uff09\",\"cwd\":\"<guest-path>\"}\n]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[\n  {\"kind\":\"example\",\"claim\":\"Use the fake provider for a one-shot headless turn.\",\"source\":\"README.md / Development setup\",\"input\":\"say hello\",\"expected\":\"fake provider response\",\"argv\":[\"/tmp/loadn-run/bin/loadn\",\"-p\",\"--dangerously-skip-permissions\",\"say hello\"],\"cwd\":\"<guest-path>\",\"env\":{\"LOADN_PROVIDER\":\"fake\",\"LOADN_FAKE_DIR\":\"<guest-path>\"},\"expected_text\":\"\u6536\u5230\uff1asay hello\uff08fake\uff09\"}\n]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"checks\":[],\"reason\":\"Inspected the README documented CLI entrypoints; no product scheduler or recurring cycle trigger is documented.\"}\nEOF",
    "<env-var>=<guest-path> python3 -I <guest-path> --validate --replay",
    "python3 - <<'PY'\np='.coldpass/claims.json'\ns=open(p).read().replace('The fake provider (`LOADN_PROVIDER=fake`) replays control files from `$LOADN_FAKE_DIR`','The fake provider (`LOADN_PROVIDER=fake`) replays control files from `$LOADN_FAKE_DIR` \u2014 the same protocol used by the end-to-end CLI tests.')\nopen(p,'w').write(s)\nPY\n<env-var>=<guest-path> python3 -I <guest-path> --validate --replay",
    "python3 - <<'PY'\nimport json\np='.coldpass/claims.json'; a=json.load(open(p)); a[0]['source']='The fake provider (`LOADN_PROVIDER=fake`) replays control files from `$LOADN_FAKE_DIR` \u2014 the same protocol used by the end-to-end CLI tests.'; a[0]['claim']='The fake provider replays control files from LOADN_FAKE_DIR.'; json.dump(a,open(p,'w'),ensure_ascii=False,indent=2)\nPY\n<env-var>=<guest-path> python3 -I <guest-path> --validate --replay",
    "python3 - <<'PY'\nr=open('README.md').read()\nneedle='The fake provider (`LOADN_PROVIDER=fake`)'\ni=r.index(needle); print(repr(r[i:i+160]))\nPY",
    "python3 - <<'PY'\nimport json\np='.coldpass/claims.json'; a=json.load(open(p)); a[0]['source']='The fake provider (`LOADN_PROVIDER=fake`) replays control files from\\n`$LOADN_FAKE_DIR` \u2014 the same protocol used by the end-to-end CLI tests.'; json.dump(a,open(p,'w'),ensure_ascii=False,indent=2)\nPY\n<env-var>=<guest-path> python3 -I <guest-path> --validate --replay",
    "cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Run a one-shot loadn CLI turn with the README fake provider setup\",\"operation_scope\":\"Python 3.12.3 in an isolated venv; editable repository install and fake provider using evals/fake control files\",\"steps\":[\"Read README.md; confirmed Python 3.10+ requirement and documented fake provider workflow.\",\"Created /tmp/loadn-run and installed the repository with pip install -e .; also installed dev extras in /tmp/loadn-venv.\",\"Ran loadn -p --dangerously-skip-permissions 'say hello' with LOADN_PROVIDER=fake and LOADN_FAKE_DIR=<guest-path>; observed '\u6536\u5230\uff1asay hello\uff08fake\uff09'.\",\"Validated and replayed probe, README claim, example, and cycle evidence successfully.\"],\"deviations\":[\"First claim validation attempt failed because the README source quote crossed a hard-wrapped line; corrected it to include the newline exactly.\",\"Grep logged that rg is unavailable and it is using its Python fallback; the requested CLI operation still succeeded.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\nEOF\nls -la .coldpass"
  ],
  "stuck_step": null,
  "error_excerpt": null,
  "what_it_did": "Run a one-shot loadn CLI turn with the README fake provider setup",
  "suggested_fix": null,
  "tokens_in": 244228,
  "tokens_out": 1853,
  "cost_usd": null,
  "usage_complete": true,
  "checks": [
    {
      "check": "operation",
      "status": "PASS",
      "details": {
        "working": true,
        "argv": [
          "/tmp/loadn-run/bin/loadn",
          "-p",
          "--dangerously-skip-permissions",
          "say hello"
        ],
        "kind": "cli",
        "returncode": 0,
        "stdout": "\u6536\u5230\uff1asay hello\uff08fake\uff09",
        "stderr": "2026-10-28 12:23:23,981 loadn.tools.grep WARNING rg \u4e0d\u53ef\u7528\u2014\u2014Grep \u8d70\u7eaf Python \u626b\u63cf\u515c\u5e95\uff08\u901f\u5ea6\u6162\uff0crg -g/--multiline \u53c2\u6570\u8bed\u4e49\u964d\u7ea7\uff1aglob \u4ecd\u751f\u6548\u3001multiline \u9010\u884c\u8fd1\u4f3c\uff09\n2026-10-28 12:23:24,027 loadn.core.models WARNING \u6a21\u578b 'fake' \u4e0d\u5728\u76ee\u5f55\uff08models.json\uff09\u2014\u2014\u7a97\u53e3\u6309\u4fdd\u5b88 128k \u4f30\u7b97\uff08\u8865\u76ee\u5f55\u53ef\u6d88\u9664\u672c\u544a\u8b66\uff09\n2026-10-28 12:23:24,027 loadn.core.cache_warmer INFO cache-warm \u4e0d\u53d1\uff1acache economics unavailable\uff08\u76ee\u5f55\u65e0\u4ef7\u683c\uff09",
        "needs_credentials": false,
        "needs_browser": false,
        "scope": "product operation"
      }
    }
  ],
  "safety": {
    "version": "z2x-1",
    "rules_version": "z2x-1",
    "summary": "Review signals: 17 known vulnerability. 5 static matches retained as context.",
    "expected": "Reviewed as expected for a test run: attempted writes that failed, so nothing was written.",
    "findings": [
      {
        "kind": "known-vulnerability",
        "count": 17,
        "note": "OSV reports a known vulnerability in this dependency version.",
        "location_count": 11
      }
    ],
    "context": [
      {
        "kind": "hardcoded-secret",
        "count": 5,
        "note": "Gitleaks found a possible hardcoded secret; value withheld.",
        "location_count": 4
      }
    ],
    "limitations": [
      "A short run cannot establish that code is safe.",
      "Connections show IP addresses; proxies can hide the final hostname.",
      "Tracing covers dispatched commands and their children, not the whole OS; guest root can interfere with tracing."
    ],
    "static": {
      "dependency_note": "OSV scanned supported lockfiles; unpinned dependencies and unsupported formats are outside this check."
    },
    "evidence_url": "/safety/?run=loadn-ai--loadn-gpt-6-luna-1793190085090151963",
    "evidence_file": "/data/safety/loadn-ai--loadn-gpt-6-luna-1793190085090151963.json.gz"
  },
  "agent_execution": "native_agent",
  "agent_runtime": "codex",
  "agent_runtime_version": "codex-cli 0.164.0",
  "tool_transport": "mcp-assigned-vm",
  "platform": "linux",
  "reasoning": "low",
  "service_tier": "standard",
  "resources": {
    "cpus": 2,
    "memory_mib": 4096,
    "disk_mib": 32768
  },
  "native_tool_calls": 12,
  "native_bundle": null,
  "architecture": null,
  "backend": "hyperv",
  "platform_details": {
    "backend": "hyperv",
    "os": "linux"
  },
  "platform_conflicts": null,
  "sandbox_source": null,
  "source_pin": {
    "commit": "544915ab78d0e0363b7bfb7b96cf07ebcbf1bf18",
    "url": "https://github.com/loadn-ai/loadn"
  },
  "purpose": "initial",
  "profile": {
    "model": "gpt-6-luna",
    "reasoning": "low"
  },
  "fault": {
    "owner": null,
    "status": "resolved",
    "reason": null
  },
  "fix_id": null,
  "verifies_run_id": null,
  "hosting": null,
  "operation_scope": "product operation",
  "tool_calls": 12,
  "guest_setup": null,
  "runtime": null,
  "runtime_version": null,
  "runtime_revision": null,
  "source_revision": null,
  "evidence_version": null,
  "failure_origin": null,
  "evidence_strength": "readme_checked",
  "works": "yes",
  "install_s": null,
  "first_use_s": null,
  "mcp": "none",
  "needs": [],
  "needs_which": null,
  "agent_interface": [
    "cli"
  ],
  "license": "Apache-2.0",
  "repo_url": "https://github.com/loadn-ai/loadn",
  "cost_to_try": "free",
  "hardware": null,
  "what_failed": null,
  "local_or_hosted": "local",
  "cycle_checks": [
    {
      "kind": "cycle",
      "claim": "Scheduled or looping main behavior",
      "source": "repository entry points",
      "input": "source inspection",
      "expected": "identify the product trigger",
      "verdict": "yes",
      "outcome": "Inspected the README documented CLI entrypoints; no product scheduler or recurring cycle trigger is documented.",
      "evidence": "Inspected the README documented CLI entrypoints; no product scheduler or recurring cycle trigger is documented.",
      "command": ""
    }
  ],
  "claims": [
    {
      "kind": "claim",
      "claim": "The fake provider replays control files from LOADN_FAKE_DIR.",
      "source": "The fake provider (`LOADN_PROVIDER=fake`) replays control files from\n`$LOADN_FAKE_DIR` \u2014 the same protocol used by the end-to-end CLI tests.",
      "input": "say hello",
      "expected": "\u6536\u5230\uff1asay hello\uff08fake\uff09",
      "command": "/tmp/loadn-run/bin/loadn -p --dangerously-skip-permissions 'say hello'",
      "verdict": "yes",
      "outcome": "Real input produced the expected result: \u6536\u5230\uff1asay hello\uff08fake\uff09",
      "evidence": "\u6536\u5230\uff1asay hello\uff08fake\uff09\n2026-10-28 12:23:27,228 loadn.tools.grep WARNING rg \u4e0d\u53ef\u7528\u2014\u2014Grep \u8d70\u7eaf Python \u626b\u63cf\u515c\u5e95\uff08\u901f\u5ea6\u6162\uff0crg -g/--multiline \u53c2\u6570\u8bed\u4e49\u964d\u7ea7\uff1aglob \u4ecd\u751f\u6548\u3001multiline \u9010\u884c\u8fd1\u4f3c\uff09\n2026-10-28 12:23:27,274 loadn.core.models WARNING \u6a21\u578b 'fake' \u4e0d\u5728\u76ee\u5f55\uff08models.json\uff09\u2014\u2014\u7a97\u53e3\u6309\u4fdd\u5b88 128k \u4f30\u7b97\uff08\u8865\u76ee\u5f55\u53ef\u6d88\u9664\u672c\u544a\u8b66\uff09\n2026-10-28 12:23:27,274 loadn.core.cache_warmer INFO cache-warm \u4e0d\u53d1\uff1acache economics unavailable\uff08\u76ee\u5f55\u65e0\u4ef7\u683c\uff09\n",
      "returncode": 0,
      "source_checked": true,
      "source_file": "README.md"
    }
  ],
  "claims_note": null,
  "example_checks": [
    {
      "kind": "example",
      "claim": "Use the fake provider for a one-shot headless turn.",
      "source": "README.md / Development setup",
      "input": "say hello",
      "command": "/tmp/loadn-run/bin/loadn -p --dangerously-skip-permissions 'say hello'",
      "evidence": "\u6536\u5230\uff1asay hello\uff08fake\uff09\n2026-10-28 12:23:30,469 loadn.tools.grep WARNING rg \u4e0d\u53ef\u7528\u2014\u2014Grep \u8d70\u7eaf Python \u626b\u63cf\u515c\u5e95\uff08\u901f\u5ea6\u6162\uff0crg -g/--multiline \u53c2\u6570\u8bed\u4e49\u964d\u7ea7\uff1aglob \u4ecd\u751f\u6548\u3001multiline \u9010\u884c\u8fd1\u4f3c\uff09\n2026-10-28 12:23:30,514 loadn.core.models WARNING \u6a21\u578b 'fake' \u4e0d\u5728\u76ee\u5f55\uff08models.json\uff09\u2014\u2014\u7a97\u53e3\u6309\u4fdd\u5b88 128k \u4f30\u7b97\uff08\u8865\u76ee\u5f55\u53ef\u6d88\u9664\u672c\u544a\u8b66\uff09\n2026-10-28 12:23:30,514 loadn.core.cache_warmer INFO cache-warm \u4e0d\u53d1\uff1acache economics unavailable\uff08\u76ee\u5f55\u65e0\u4ef7\u683c\uff09",
      "deferred": false,
      "expected": "fake provider response",
      "returncode": 0,
      "verdict": "yes",
      "outcome": "command completed successfully"
    }
  ],
  "does_what_it_says": "yes",
  "maintenance": {
    "archived": false,
    "commits_90d": 553,
    "last_commit_at": "2026-10-28T10:10:50Z",
    "last_release_at": "2026-10-28T10:11:07Z",
    "median_reply_hours": null,
    "merged_prs_90d": 0,
    "note": "actively maintained: last commit 0 days ago; 553 commits and 0 merged PRs in 90 days; 0 open issues, 10 open PRs; latest release 2026-10-28",
    "open_issues": 0,
    "open_prs": 10,
    "reply_share": null,
    "reply_threads": 0,
    "verdict": "maintained"
  },
  "maintenance_verdict": "maintained",
  "maintenance_note": "actively maintained: last commit 0 days ago; 553 commits and 0 merged PRs in 90 days; 0 open issues, 10 open PRs; latest release 2026-10-28",
  "maintained": "active",
  "maintained_note": "last commit 0 days ago",
  "last_commit_at": "2026-10-28T10:10:55Z",
  "last_release_at": "2026-10-28T10:11:07Z",
  "open_issues": null,
  "answered_issues": null,
  "platforms_claimed": [
    "linux",
    "mac",
    "windows"
  ],
  "topic": "agent-harness",
  "agent_interfaces": [
    {
      "interface": "cli",
      "evidence": "independent checker",
      "observed": true,
      "operation_checked": true
    }
  ],
  "agent_interfaces_note": "README metadata is a discovery hint, not pinned documentation proof. Observed interfaces were exercised in this run. An empty list means unknown.",
  "mcp_context": null,
  "tested_at": "2026-10-28T12:23:37.223467+00:00",
  "tested_commit": "544915ab78d0e0363b7bfb7b96cf07ebcbf1bf18",
  "tested_with": {
    "agent": "codex",
    "agent_version": "codex-cli 0.164.0",
    "model": "gpt-6-luna",
    "model_route": "gpt-6-luna",
    "reasoning": "low",
    "os": "linux",
    "backend": "hyperv",
    "transport": "mcp-assigned-vm"
  },
  "setup_identity": {
    "repo": "loadn-ai/loadn",
    "source": "https://github.com/loadn-ai/loadn",
    "commit": "544915ab78d0e0363b7bfb7b96cf07ebcbf1bf18",
    "source_revision": null,
    "os": "linux",
    "architecture": null,
    "backend": "hyperv",
    "model": "gpt-6-luna",
    "model_version": "gpt-6-luna",
    "agent_execution": "native_agent",
    "agent_runtime": "codex",
    "agent_runtime_version": "codex-cli 0.164.0",
    "tool_transport": "mcp-assigned-vm",
    "runtime": null,
    "runtime_version": null,
    "runtime_revision": null,
    "sandbox_source": null,
    "guest_setup": null,
    "source_pin": {
      "commit": "544915ab78d0e0363b7bfb7b96cf07ebcbf1bf18",
      "url": "https://github.com/loadn-ai/loadn"
    },
    "platform_details": {
      "os": "linux",
      "backend": "hyperv"
    },
    "platform_conflicts": null,
    "reasoning": "low",
    "service_tier": "standard",
    "resources": {
      "cpus": 2,
      "memory_mib": 4096,
      "disk_mib": 32768
    },
    "operation": "Run a one-shot loadn CLI turn with the README fake provider setup",
    "operation_scope": "product operation",
    "hosting": null,
    "kind": "repo",
    "test_version": "readme-604d73685be33b2939b2632791fb1de37972f659febb28a139c60d6e81057c18",
    "evidence_version": null
  },
  "other_model": null,
  "other_run_id": null,
  "models_agree": null,
  "furthest_model": null,
  "transcript_url": "/transcripts/loadn-ai--loadn-gpt-6-luna-1793190085090151963.txt",
  "report_url": "/reports/loadn-ai--loadn-gpt-6-luna-1793190085090151963.json"
}