{ "run_id": "OrionArchitekton--schemafit-gpt-6-luna-1793019056556387304", "date": "2026-10-26T12:52:26.788302+00:00", "repo": "OrionArchitekton/schemafit", "kind": "repo", "source": "https://github.com/OrionArchitekton/schemafit", "commit": "13fb6a43fd0e8890b9b594e035ac57f5b441e78d", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "test_version": "readme-a17389bda4cc696f9601c0c4ff1b2c16e23bfa1d907883b715ccdd9e92ddec56", "pass": true, "outcome": "pass", "time_to_working_s": 69.51188125298359, "total_s": 90.23187708854675, "steps": [ "pwd; ls -la; sed -n '1,240p' README.md; python3 --version; id -u", "rg --files schemafit; cat pyproject.toml; rg -n \"schemafit lint|schemafit demo|drift-mock\" README.md", "python3 -m venv /tmp/schemafit-venv && /tmp/schemafit-venv/bin/python -m pip install -e . && /tmp/schemafit-venv/bin/schemafit demo", "sed -n '1,160p' fixtures/drift-mock-bad.json; mkdir -p .coldpass; /tmp/schemafit-venv/bin/schemafit lint fixtures/drift-mock-bad.json --provider cohere --live-verify", "cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"/tmp/schemafit-venv/bin/schemafit\",\"lint\",\"fixtures/drift-mock-bad.json\",\"--provider\",\"cohere\",\"--live-verify\"],\"cwd\":\"\",\"expected_returncode\":1,\"expected_text\":\"cohere-drift\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Live-verify mock drift detection reports a cohere-drift finding\",\"source\":\"Proofs include `schemafit lint fixtures/drift-mock-bad.json --provider cohere --live-verify`\",\"input\":\"fixtures/drift-mock-bad.json with provider cohere in mock mode\",\"expected\":\"cohere-drift finding\",\"probe_kind\":\"cli\",\"argv\":[\"/tmp/schemafit-venv/bin/schemafit\",\"lint\",\"fixtures/drift-mock-bad.json\",\"--provider\",\"cohere\",\"--live-verify\"],\"expected_text\":\"cohere-drift\",\"expected_returncode\":1,\"cwd\":\"\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Run the documented offline self-check\",\"source\":\"README.md / Install\",\"input\":\"schemafit demo\",\"expected\":\"PROOF_OK\",\"argv\":[\"/tmp/schemafit-venv/bin/schemafit\",\"demo\"],\"cwd\":\"\",\"expected_text\":\"PROOF_OK\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"Inspected README usage, CI and shipped entry points: schemafit is a one-shot static linter/repair CLI; no product scheduler, loop, webhook, or cycle trigger is documented.\",\"checks\":[]}\nEOF\n", "= python3 -I --validate --replay", "python3 - <<'PY'\np='.coldpass/claims.json'\ns=open(p).read().replace('\"source\":\"Proofs include `schemafit lint fixtures/drift-mock-bad.json --provider cohere --live-verify`\"','\"source\":\"Proofs include `schemafit lint fixtures/drift-mock-bad.json --provider cohere --live-verify` (exit 1 + `cohere-drift`).\"')\nopen(p,'w').write(s)\nPY\n= python3 -I --validate --replay", "sed -n '150,205p' README.md", "cat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Mock mode performs a deterministic network-free verification\",\"source\":\"deterministic, network-free client modeled on the static rule pack\",\"input\":\"schemafit lint fixtures/drift-mock-bad.json --provider cohere --live-verify\",\"expected\":\"cohere-drift\",\"probe_kind\":\"cli\",\"argv\":[\"/tmp/schemafit-venv/bin/schemafit\",\"lint\",\"fixtures/drift-mock-bad.json\",\"--provider\",\"cohere\",\"--live-verify\"],\"expected_text\":\"cohere-drift\",\"expected_returncode\":1,\"cwd\":\"\"}]\nEOF\n", "= python3 -I --validate --replay", "cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Run schemafit demo and lint a fixture with mock live verification\",\"operation_scope\":\"Python 3.12.3 virtual environment; local offline CLI\",\"steps\":[\"python3 -m venv /tmp/schemafit-venv\",\"/tmp/schemafit-venv/bin/python -m pip install -e .\",\"/tmp/schemafit-venv/bin/schemafit demo\",\"/tmp/schemafit-venv/bin/schemafit lint fixtures/drift-mock-bad.json --provider cohere --live-verify\"],\"deviations\":[],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\nEOF" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Run schemafit demo and lint a fixture with mock live verification", "suggested_fix": null, "tokens_in": 184439, "tokens_out": 1571, "cost_usd": null, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "/tmp/schemafit-venv/bin/schemafit", "lint", "fixtures/drift-mock-bad.json", "--provider", "cohere", "--live-verify" ], "kind": "cli", "returncode": 1, "stdout": "[cohere] FAIL: 1 error(s), 0 warning(s)\n ERROR # (cohere-drift)\n Rule-pack drift detected for cohere: live verification rejected the schema but static pack had no violations. Pack may lag provider docs (client=mock): modeled from the static rule pack (no network, no key)\n ref: https://docs.cohere.com/docs/structured-outputs\n[cohere] LIVE-VERIFY confirmed_by_provider=False client=mock (modeled from the static rule pack (no network, no key))", "stderr": "", "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=OrionArchitekton--schemafit-gpt-6-luna-1793019056556387304", "evidence_file": "/data/safety/OrionArchitekton--schemafit-gpt-6-luna-1793019056556387304.json.gz" }, "agent_execution": "native_agent", "agent_runtime": "codex", "agent_runtime_version": "codex-cli 0.163.0", "tool_transport": "mcp-assigned-vm", "platform": "linux", "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "native_tool_calls": 11, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "13fb6a43fd0e8890b9b594e035ac57f5b441e78d", "url": "https://github.com/OrionArchitekton/schemafit" }, "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": 11, "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": "MIT", "repo_url": "https://github.com/OrionArchitekton/schemafit", "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 README usage, CI and shipped entry points: schemafit is a one-shot static linter/repair CLI; no product scheduler, loop, webhook, or cycle trigger is documented.", "evidence": "Inspected README usage, CI and shipped entry points: schemafit is a one-shot static linter/repair CLI; no product scheduler, loop, webhook, or cycle trigger is documented.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "Mock mode performs a deterministic network-free verification", "source": "deterministic, network-free client modeled on the static rule pack", "input": "schemafit lint fixtures/drift-mock-bad.json --provider cohere --live-verify", "expected": "cohere-drift", "command": "/tmp/schemafit-venv/bin/schemafit lint fixtures/drift-mock-bad.json --provider cohere --live-verify", "verdict": "yes", "outcome": "Real input produced the expected result: cohere-drift", "evidence": "cohere-drift)\n Rule-pack drift detected for cohere: live verification rejected the schema but static pack had no violations. Pack may lag provider docs (client=mock): modeled from the static rule pack (no network, no key)\n ref: https://docs.cohere.com/docs/structured-outputs\n[cohere] LIVE-VERIFY confirmed_by_provider=False client=mock (modeled from the static rule pack (no network, no key))\n", "returncode": 1, "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Run the documented offline self-check", "source": "README.md / Install", "input": "schemafit demo", "command": "/tmp/schemafit-venv/bin/schemafit demo", "evidence": "== schemafit demo ==\nPROVIDER=anthropic INPUT=demo-bad VIOLATIONS=5 EXIT=1\nVIOLATION_PATH=#/properties/age/maximum (keyword: maximum -> rejected by anthropic)\n--- after `schemafit repair --provider anthropic` --- VIOLATIONS=0 EXIT=0 auto_fixed=5\nMULTI: openai=PASS anthropic=FAIL gemini=PASS mistral=PASS cohere=FAIL\nNOTE: gemini portability warnings=1 (version-sensitive, non-failing)\nPROOF_OK", "deferred": false, "expected": "PROOF_OK", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": "yes", "maintenance": { "archived": false, "commits_90d": 1, "last_commit_at": "2026-10-24T20:41:08Z", "last_release_at": "2026-10-24T21:19:36Z", "median_reply_hours": null, "merged_prs_90d": 1, "note": "actively maintained: last commit 1 days ago; 1 commits and 1 merged PRs in 90 days; 0 open issues, 0 open PRs; latest release 2026-10-24", "open_issues": 0, "open_prs": 0, "reply_share": null, "reply_threads": 0, "verdict": "maintained" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 1 days ago; 1 commits and 1 merged PRs in 90 days; 0 open issues, 0 open PRs; latest release 2026-10-24", "maintained": "active", "maintained_note": "last commit 1 days ago", "last_commit_at": "2026-10-24T20:45:47Z", "last_release_at": "2026-10-24T21:19:36Z", "open_issues": null, "answered_issues": null, "platforms_claimed": [ "linux" ], "topic": "mcp-server", "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": "2026-10-26T12:52:26.788302+00:00", "tested_commit": "13fb6a43fd0e8890b9b594e035ac57f5b441e78d", "tested_with": { "agent": "codex", "agent_version": "codex-cli 0.163.0", "model": "gpt-6-luna", "model_route": "gpt-6-luna", "reasoning": "low", "os": "linux", "backend": "hyperv", "transport": "mcp-assigned-vm" }, "setup_identity": { "repo": "OrionArchitekton/schemafit", "source": "https://github.com/OrionArchitekton/schemafit", "commit": "13fb6a43fd0e8890b9b594e035ac57f5b441e78d", "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 0.163.0", "tool_transport": "mcp-assigned-vm", "runtime": null, "runtime_version": null, "runtime_revision": null, "sandbox_source": null, "guest_setup": null, "source_pin": { "commit": "13fb6a43fd0e8890b9b594e035ac57f5b441e78d", "url": "https://github.com/OrionArchitekton/schemafit" }, "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 schemafit demo and lint a fixture with mock live verification", "operation_scope": "product operation", "hosting": null, "kind": "repo", "test_version": "readme-a17389bda4cc696f9601c0c4ff1b2c16e23bfa1d907883b715ccdd9e92ddec56", "evidence_version": null }, "other_model": null, "other_run_id": null, "models_agree": null, "furthest_model": null, "transcript_url": "/transcripts/OrionArchitekton--schemafit-gpt-6-luna-1793019056556387304.txt", "report_url": "/reports/OrionArchitekton--schemafit-gpt-6-luna-1793019056556387304.json" }