{
  "run_id": "causaldyn--causal-hybrid-control-gpt-6-luna-1793115384598161725",
  "date": "2026-10-27T15:43:14.445672+00:00",
  "repo": "causaldyn/causal-hybrid-control",
  "kind": "repo",
  "source": "https://github.com/causaldyn/causal-hybrid-control",
  "commit": "0e6d129442c2d34a304df8e46e3c63be7faa9214",
  "model": "gpt-6-luna",
  "model_version": "gpt-6-luna",
  "test_version": "readme-38e6b13f3b13804effb95797e3466b1a1334da7a232d897cbc8965867f802605",
  "pass": true,
  "outcome": "pass",
  "time_to_working_s": 379.8561609190001,
  "total_s": 409.8474066257477,
  "steps": [
    "pwd && id -u && python3 --version && rg --files -g 'README*' -g 'pyproject.toml' -g 'requirements*.txt' -g 'package.json' -g 'Cargo.toml' -g 'go.mod' -g '.github/workflows/**' -g 'Makefile' -g 'Dockerfile' | head -80 && sed -n '1,240p' README.md",
    "ls -la | head -60 && find . -maxdepth 3 -type f | sort | head -100 && python3 -m pip --version && python3 -m pip install -e .",
    "python3 -m venv /tmp/chc-venv && /tmp/chc-venv/bin/python -m pip install -e .",
    "sed -n '1,220p' docs/quickstart.md 2>/dev/null || find docs -maxdepth 2 -iname '*quickstart*'; cat pyproject.toml | head -90; find scripts -maxdepth 2 -type f",
    "ls docs/quickstart.py docs/output/quickstart.txt; sed -n '1,220p' docs/quickstart.py",
    "JAX_ENABLE_X64=1 /tmp/chc-venv/bin/python docs/quickstart.py",
    "mkdir -p .coldpass && cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"/tmp/chc-venv/bin/python\",\"docs/quickstart.py\"],\"cwd\":\"<guest-path>\",\"env\":{\"JAX_ENABLE_X64\":\"1\"},\"expected_text\":\"Trustworthy prefix: 3 steps.\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Quickstart creates a schedule and reports its certificate for identified logs.\",\"source\":\"From a panel of logs to a schedule and its certificate, in one call.\",\"input\":\"docs/quickstart.py simulated panel\",\"expected\":\"Trustworthy prefix: 3 steps.\",\"probe_kind\":\"cli\",\"argv\":[\"/tmp/chc-venv/bin/python\",\"docs/quickstart.py\"],\"cwd\":\"<guest-path>\",\"env\":{\"JAX_ENABLE_X64\":\"1\"},\"expected_text\":\"Trustworthy prefix: 3 steps.\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Run the documented quickstart end to end.\",\"source\":\"docs/quickstart.md, Quickstart command\",\"input\":\"simulated panel generated by script\",\"expected\":\"Markdown prescription report with certificate\",\"argv\":[\"/tmp/chc-venv/bin/python\",\"docs/quickstart.py\"],\"cwd\":\"<guest-path>\",\"env\":{\"JAX_ENABLE_X64\":\"1\"},\"expected_text\":\"Trustworthy prefix: 3 steps.\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"Inspected README, docs/quickstart.py, scripts, and project entry points; this library runs a user invoked prescription call and exposes no product scheduler, recurring loop, or webhook trigger.\",\"checks\":[]}\nEOF\ncat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Run the documented causal prescription quickstart over simulated confounded panel logs.\",\"operation_scope\":\"Python 3.12.3 in an isolated venv; installed editable package and CPU JAX dependencies.\",\"steps\":[\"Read README installation and quickstart guidance.\",\"Created /tmp/chc-venv and installed package with pip install -e .\",\"Ran JAX_ENABLE_X64=1 /tmp/chc-venv/bin/python docs/quickstart.py; it emitted identified and nonidentified reports.\"],\"deviations\":[\"Initial system pip install -e . was rejected by Debian externally-managed-environment policy; repeated successfully in isolated venv.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\nEOF\n",
    "<env-var>=<guest-path> python3 -I <guest-path> --validate --replay"
  ],
  "stuck_step": null,
  "error_excerpt": null,
  "what_it_did": "Run the documented causal prescription quickstart over simulated confounded panel logs.",
  "suggested_fix": null,
  "tokens_in": 224856,
  "tokens_out": 1443,
  "cost_usd": null,
  "usage_complete": true,
  "checks": [
    {
      "check": "operation",
      "status": "PASS",
      "details": {
        "working": true,
        "argv": [
          "/tmp/chc-venv/bin/python",
          "docs/quickstart.py"
        ],
        "kind": "cli",
        "returncode": 0,
        "stdout": "# Prescription for `supply`\n\n## Decision\n\nStart: the mean (standard deviation) over 200 units of each unit's last logged state, from period 11: `supply` 0.02264 (0.5971), `wait` 0.02703 (0.323).\n\n| lever | active steps | first | last |\n|---|---|---|---|\n| `incentive` | 0-14 | +2 | +0.3368 |\n\nPlanned task cost: 2.15002.\n\n[excerpt truncated]",
        "stderr": "no schedule: no observed set identifies the effect",
        "needs_credentials": false,
        "needs_browser": false,
        "scope": "product operation"
      }
    }
  ],
  "safety": {
    "version": "z2x-1",
    "rules_version": "z2x-1",
    "summary": "No problems traced to this repository code in these checks.",
    "expected": "Reviewed as expected for a test run: attempted writes that failed, so nothing was written.",
    "findings": [],
    "context": [],
    "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=causaldyn--causal-hybrid-control-gpt-6-luna-1793115384598161725",
    "evidence_file": "/data/safety/causaldyn--causal-hybrid-control-gpt-6-luna-1793115384598161725.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": 8,
  "native_bundle": null,
  "architecture": null,
  "backend": "hyperv",
  "platform_details": {
    "backend": "hyperv",
    "os": "linux"
  },
  "platform_conflicts": null,
  "sandbox_source": null,
  "source_pin": {
    "commit": "0e6d129442c2d34a304df8e46e3c63be7faa9214",
    "url": "https://github.com/causaldyn/causal-hybrid-control"
  },
  "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": 8,
  "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/causaldyn/causal-hybrid-control",
  "cost_to_try": "free",
  "hardware": "GPU",
  "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 README, docs/quickstart.py, scripts, and project entry points; this library runs a user invoked prescription call and exposes no product scheduler, recurring loop, or webhook trigger.",
      "evidence": "Inspected README, docs/quickstart.py, scripts, and project entry points; this library runs a user invoked prescription call and exposes no product scheduler, recurring loop, or webhook trigger.",
      "command": ""
    }
  ],
  "claims": [
    {
      "kind": "claim",
      "claim": "Quickstart creates a schedule and reports its certificate for identified logs.",
      "source": "From a panel of logs to a schedule and its certificate, in one call.",
      "input": "docs/quickstart.py simulated panel",
      "expected": "Trustworthy prefix: 3 steps.",
      "command": "/tmp/chc-venv/bin/python docs/quickstart.py",
      "verdict": "yes",
      "outcome": "Real input produced the expected result: Trustworthy prefix: 3 steps.",
      "evidence": "Trustworthy prefix: 3 steps.**\n\n## Provenance\n\n- data sha256: `2f5ae7c0e4ef94c1...`\n- panel: chc 0.23.0, 2400 rows, x64=True, seed=0\n- run: on cpu (cpu), x64=True, fit in float64, solve in float64, seed=0, integrator=euler\n- settings: folds=2, degree=1, channel_degree=1, nuisance_degree=2, nuisance_knots=auto, ridge=1e-06, steps=10000, tolerance=0.5, hold_constraints=False, max_levers=none\n- versions: causal-hybrid-control 0.23.0, jax 0.12.0.1, jaxlib 0.12.0.1, numpy 2.5.4, scipy 1.18.1\n\n# Prescription for `supply`\n\n## Decision\n\nStart: the mean (standard deviation) over 200 units of each unit'",
      "returncode": 0,
      "source_checked": true,
      "source_file": "README.md"
    }
  ],
  "claims_note": null,
  "example_checks": [
    {
      "kind": "example",
      "claim": "Run the documented quickstart end to end.",
      "source": "docs/quickstart.md, Quickstart command",
      "input": "simulated panel generated by script",
      "command": "/tmp/chc-venv/bin/python docs/quickstart.py",
      "evidence": "er: not run\n- regret bound on the fitted model: not evaluated\n\n**Trustworthy prefix: 0 steps.**\n\n## Provenance\n\n- data sha256: `2f5ae7c0e4ef94c1...`\n- panel: chc 0.23.0, 2400 rows, x64=True, seed=0\n- run: on cpu (cpu), x64=True, fit in float64, no solve, seed=0, integrator=euler\n- settings: folds=2, degree=1, channel_degree=1, nuisance_degree=2, nuisance_knots=auto, ridge=1e-06, steps=10000, tolerance=0.5, hold_constraints=False, max_levers=none\n- versions: causal-hybrid-control 0.23.0, jax 0.12.0.1, jaxlib 0.12.0.1, numpy 2.5.4, scipy 1.18.1\n\nno schedule: no observed set identifies the effect",
      "deferred": false,
      "expected": "Markdown prescription report with certificate",
      "returncode": 0,
      "verdict": "yes",
      "outcome": "command completed successfully"
    }
  ],
  "does_what_it_says": "yes",
  "maintenance": {
    "archived": false,
    "commits_90d": 896,
    "last_commit_at": "2026-10-27T13:43:34Z",
    "last_release_at": "2026-10-27T14:37:23Z",
    "median_reply_hours": null,
    "merged_prs_90d": 22,
    "note": "actively maintained: last commit 0 days ago; 896 commits and 22 merged PRs in 90 days; 0 open issues, 6 open PRs; latest release 2026-10-27",
    "open_issues": 0,
    "open_prs": 6,
    "reply_share": null,
    "reply_threads": 0,
    "verdict": "maintained"
  },
  "maintenance_verdict": "maintained",
  "maintenance_note": "actively maintained: last commit 0 days ago; 896 commits and 22 merged PRs in 90 days; 0 open issues, 6 open PRs; latest release 2026-10-27",
  "maintained": "active",
  "maintained_note": "last commit 0 days ago",
  "last_commit_at": "2026-10-27T13:43:48Z",
  "last_release_at": "2026-10-27T14:37:23Z",
  "open_issues": null,
  "answered_issues": null,
  "platforms_claimed": [
    "linux"
  ],
  "topic": "other",
  "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": "2026-10-27T15:43:14.445672+00:00",
  "tested_commit": "0e6d129442c2d34a304df8e46e3c63be7faa9214",
  "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": "causaldyn/causal-hybrid-control",
    "source": "https://github.com/causaldyn/causal-hybrid-control",
    "commit": "0e6d129442c2d34a304df8e46e3c63be7faa9214",
    "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": "0e6d129442c2d34a304df8e46e3c63be7faa9214",
      "url": "https://github.com/causaldyn/causal-hybrid-control"
    },
    "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 the documented causal prescription quickstart over simulated confounded panel logs.",
    "operation_scope": "product operation",
    "hosting": null,
    "kind": "repo",
    "test_version": "readme-38e6b13f3b13804effb95797e3466b1a1334da7a232d897cbc8965867f802605",
    "evidence_version": null
  },
  "other_model": null,
  "other_run_id": null,
  "models_agree": null,
  "furthest_model": null,
  "transcript_url": "/transcripts/causaldyn--causal-hybrid-control-gpt-6-luna-1793115384598161725.txt",
  "report_url": "/reports/causaldyn--causal-hybrid-control-gpt-6-luna-1793115384598161725.json"
}