{ "run_id": "RomanSlack--jev-drone-gpt-6-luna-1792790853700451182", "date": "2026-10-23T21:31:01.029612+00:00", "repo": "RomanSlack/jev-drone", "kind": "repo", "source": "https://github.com/RomanSlack/jev-drone", "commit": "974b47378c14c6dcf7d11f7c813fba0f5f4d8b6a", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "test_version": "readme-f72312298d35d84837d4fc5f6f22b138d54d456600b5ed431e36e8f5db931dbf", "pass": null, "outcome": "unverified", "time_to_working_s": null, "total_s": 207.3291244506836, "steps": [ "cd && pwd && rg --files -g 'README*' -g 'AGENTS.md' -g 'pyproject.toml' -g 'requirements*.txt' -g 'package.json' -g 'Makefile' -g 'setup.py' -g 'tox.ini' | head -80 && cat 2>/dev/null; vault-search 'jev-drone repository README operation' 2>/dev/null || true", "cd && ls -la && find .. -name README.md -o -name AGENTS.md | head -60 && python3 --version && git status --short --branch", "cd && cat README.md && cat requirements.txt && cat setup.sh && cat site/AGENTS.md", "cd && cat .env.example && sed -n '1,240p' run.py && sed -n '1,200p' replay.py && ls -la .coldpass && id -u && command -v sudo || true", "cd && sudo -n apt-get update && sudo -n apt-get install -y git python3-venv libglfw3 libgl1-mesa-glx libegl1", "cd && sudo -n apt-get install -y git python3-venv libglfw3 libgl1 libegl1 && ./setup.sh", "cd && MUJOCO_GL=egl .venv/bin/python run.py --no-jev --fast --seconds 1 --seeds 0", "cd && sed -n '240,520p' run.py && sed -n '1,160p' tactics.py && ls -la assets .venv/bin/python", "cd && mkdir -p .coldpass && cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"\",\"run.py\",\"--no-jev\",\"--fast\",\"--seconds\",\"1\",\"--seeds\",\"0\"],\"cwd\":\"\",\"env\":{\"MUJOCO_GL\":\"egl\"},\"expected_text\":\"\\\"collisions\\\": 0\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[\n {\"kind\":\"claim\",\"claim\":\"The no-Jev ablation can execute a flight and reports collision metrics.\",\"source\":\".venv/bin/python run.py --no-jev --fast --seconds 65 --seeds 0 1 2 # ablation (free)\",\"input\":\"one second, seed 0\",\"expected\":\"flight metrics with zero collisions\",\"probe_kind\":\"cli\",\"argv\":[\"\",\"run.py\",\"--no-jev\",\"--fast\",\"--seconds\",\"1\",\"--seeds\",\"0\"],\"expected_text\":\"\\\"collisions\\\": 0\",\"cwd\":\"\",\"env\":{\"MUJOCO_GL\":\"egl\"}},\n {\"kind\":\"claim\",\"claim\":\"The Jev enabled flight requires an API key.\",\"source\":\"cp .env.example .env # then put your key in it\",\"testable\":false,\"reason\":\"No API key was supplied; run.py raises RuntimeError: set TYPESAFE_API_KEY (see .env.example).\"}\n]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[\n {\"kind\":\"example\",\"claim\":\"Documented no-Jev ablation flight\",\"source\":\"README.md, Run it\",\"input\":\"seed 0, one simulated second, fast mode, EGL\",\"expected\":\"JSON flight metrics with zero collisions\",\"argv\":[\"\",\"run.py\",\"--no-jev\",\"--fast\",\"--seconds\",\"1\",\"--seeds\",\"0\"],\"cwd\":\"\",\"env\":{\"MUJOCO_GL\":\"egl\"},\"expected_text\":\"\\\"collisions\\\": 0\"},\n {\"kind\":\"example\",\"claim\":\"Jev engaged flight\",\"source\":\"README.md, Run it\",\"reason\":\"Requires TYPESAFE_API_KEY from Typesafe; no credential supplied. The README instructions cp .env.example .env and add key cannot be completed without it.\"}\n]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"Inspected run.py episode loop and CLI entry point. The README describes finite episode simulations started by run.py; it has no product scheduler, cron, webhook, or recurring cycle.\",\"checks\":[]}\nEOF\n= python3 -I --validate --replay", "cd && cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"README setup and no-Jev flight simulation\",\"operation_scope\":\"Installed README requirements in Python 3.12.3 venv, fetched Skydio X2 model, and replayed a one-second documented ablation flight with EGL. The flight completed with zero collisions and 100% target visibility.\",\"steps\":[\"sudo -n apt-get install -y git python3-venv libglfw3 libgl1 libegl1\",\"./setup.sh\",\"MUJOCO_GL=egl .venv/bin/python run.py --no-jev --fast --seconds 1 --seeds 0\"],\"deviations\":[\"An initial apt install command failed because libgl1-mesa-glx has no Ubuntu 24.04 package candidate; installed libgl1 instead, then setup succeeded.\",\"The Jev enabled flight could not be run: README requires adding a Typesafe API key to .env, and none was supplied. The documented no-Jev ablation was exercised.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\nEOF\n" ], "stuck_step": " run.py --no-jev --fast --seconds 1 --seeds 0", "error_excerpt": "The saved checks do not fully confirm documented product behavior.", "what_it_did": "README setup and no-Jev flight simulation", "suggested_fix": "Keep the partial evidence and check the documented behavior with real input and expected output.", "tokens_in": 226216, "tokens_out": 1822, "cost_usd": null, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": false, "argv": [ "", "run.py", "--no-jev", "--fast", "--seconds", "1", "--seeds", "0" ], "kind": "cli", "returncode": 0, "stdout": "{\"seed\": 0, \"jev\": false, \"collisions\": 0, \"target_visible_pct\": 100.0, \"mean_standoff_m\": 5.07, \"max_standoff_m\": 5.26, \"final_gap_m\": 5.17, \"distance_flown_m\": 0.8, \"steps_jev_acted_pct\": 0.0, \"steps_reflex_pct\": 0.0, \"max_x_m\": 2.2, \"crossed_barrier\": false, \"crashed_at_s\": null, \"flew_s\": 1.0}", "stderr": "", "needs_credentials": false, "needs_browser": false, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 1 connection review, 82 known vulnerability, 1 outside write, 1 sensitive read.", "expected": "Reviewed as expected for a test run: a Python interpreter or package manager probed its own interpreter file under a system program folder.", "findings": [ { "kind": "connection-review", "count": 1, "note": "Repository processes attempted these non-loopback connections; proxies can hide the final hostname.", "location_count": 1, "path": "140.82.114.4:443", "process_count": 3 }, { "kind": "known-vulnerability", "count": 82, "note": "OSV reports a known vulnerability in this dependency version.", "location_count": 4 }, { "kind": "outside-write", "count": 1, "note": "Repository processes attempted these writes outside documented output/cache paths.", "location_count": 1, "path": "/dev/udmabuf", "process_count": 7 }, { "kind": "sensitive-read", "count": 1, "note": "A repository process attempted to read this sensitive path.", "location_count": 1, "file_kind": "saved web login", "process_count": 3 } ], "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=RomanSlack--jev-drone-gpt-6-luna-1792790853700451182", "evidence_file": "/data/safety/RomanSlack--jev-drone-gpt-6-luna-1792790853700451182.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": 10, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "974b47378c14c6dcf7d11f7c813fba0f5f4d8b6a", "url": "https://github.com/RomanSlack/jev-drone" }, "purpose": "initial", "profile": { "model": "gpt-6-luna", "reasoning": "low" }, "fault": { "owner": "unknown", "status": "pending", "reason": "The saved checks do not fully confirm documented product behavior." }, "fix_id": null, "verifies_run_id": null, "hosting": null, "operation_scope": "product operation", "tool_calls": 10, "guest_setup": null, "runtime": null, "runtime_version": null, "runtime_revision": null, "source_revision": null, "evidence_version": null, "failure_origin": null, "evidence_strength": "partly_checked", "works": "untested", "install_s": null, "first_use_s": null, "mcp": "none", "needs": [], "needs_which": null, "agent_interface": [ "cli" ], "license": "MIT", "repo_url": "https://github.com/RomanSlack/jev-drone", "cost_to_try": null, "hardware": null, "what_failed": "The saved checks do not fully confirm documented product behavior.", "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 run.py episode loop and CLI entry point. The README describes finite episode simulations started by run.py; it has no product scheduler, cron, webhook, or recurring cycle.", "evidence": "Inspected run.py episode loop and CLI entry point. The README describes finite episode simulations started by run.py; it has no product scheduler, cron, webhook, or recurring cycle.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "The no-Jev ablation can execute a flight and reports collision metrics.", "source": ".venv/bin/python run.py --no-jev --fast --seconds 65 --seeds 0 1 2 # ablation (free)", "input": "one second, seed 0", "expected": "flight metrics with zero collisions", "command": " run.py --no-jev --fast --seconds 1 --seeds 0", "verdict": "yes", "outcome": "Real input produced the expected result: \"collisions\": 0", "evidence": "\"collisions\": 0, \"target_visible_pct\": 100.0, \"mean_standoff_m\": 5.07, \"max_standoff_m\": 5.26, \"final_gap_m\": 5.17, \"distance_flown_m\": 0.8, \"steps_jev_acted_pct\": 0.0, \"steps_reflex_pct\": 0.0, \"max_x_m\": 2.2, \"crossed_barrier\": false, \"crashed_at_s\": null, \"flew_s\": 1.0}\n", "returncode": 0, "source_checked": true, "source_file": "README.md" }, { "kind": "claim", "claim": "The Jev enabled flight requires an API key.", "source": "cp .env.example .env # then put your key in it", "input": "", "expected": "", "command": "", "verdict": "blocked", "outcome": "No API key was supplied; run.py raises RuntimeError: set TYPESAFE_API_KEY (see .env.example).", "evidence": "No API key was supplied; run.py raises RuntimeError: set TYPESAFE_API_KEY (see .env.example).", "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Documented no-Jev ablation flight", "source": "README.md, Run it", "input": "seed 0, one simulated second, fast mode, EGL", "command": " run.py --no-jev --fast --seconds 1 --seeds 0", "evidence": "{\"seed\": 0, \"jev\": false, \"collisions\": 0, \"target_visible_pct\": 100.0, \"mean_standoff_m\": 5.07, \"max_standoff_m\": 5.26, \"final_gap_m\": 5.17, \"distance_flown_m\": 0.8, \"steps_jev_acted_pct\": 0.0, \"steps_reflex_pct\": 0.0, \"max_x_m\": 2.2, \"crossed_barrier\": false, \"crashed_at_s\": null, \"flew_s\": 1.0}", "deferred": false, "expected": "JSON flight metrics with zero collisions", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" }, { "kind": "example", "claim": "Jev engaged flight", "source": "README.md, Run it", "input": "", "command": "", "evidence": "Requires TYPESAFE_API_KEY from Typesafe; no credential supplied. The README instructions cp .env.example .env and add key cannot be completed without it.", "deferred": false, "expected": "documented command completes successfully", "verdict": "blocked", "outcome": "Requires TYPESAFE_API_KEY from Typesafe; no credential supplied. The README instructions cp .env.example .env and add key cannot be completed without it." } ], "does_what_it_says": "partly", "maintenance": { "archived": false, "commits_90d": 13, "last_commit_at": "2026-09-24T21:10:40Z", "last_release_at": null, "median_reply_hours": 23.4, "merged_prs_90d": 2, "note": "actively maintained: last commit 29 days ago; 13 commits and 2 merged PRs in 90 days; 1 open issues, 0 open PRs; 2 of 5 recent threads got a maintainer reply, median first reply 23.4h; no releases", "open_issues": 1, "open_prs": 0, "reply_share": 0.4, "reply_threads": 5, "verdict": "maintained" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 29 days ago; 13 commits and 2 merged PRs in 90 days; 1 open issues, 0 open PRs; 2 of 5 recent threads got a maintainer reply, median first reply 23.4h; no releases", "maintained": "active", "maintained_note": "last commit 29 days ago; 1 open issues, 2 answered or closed", "last_commit_at": "2026-09-24T21:10:40Z", "last_release_at": null, "open_issues": 1, "answered_issues": 2, "platforms_claimed": [ "linux" ], "topic": "agent-harness", "agent_interfaces": [ { "interface": "cli", "evidence": "independent checker", "observed": true, "operation_checked": false } ], "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": "2026-10-23T21:31:01.029612+00:00", "tested_commit": "974b47378c14c6dcf7d11f7c813fba0f5f4d8b6a", "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": "RomanSlack/jev-drone", "source": "https://github.com/RomanSlack/jev-drone", "commit": "974b47378c14c6dcf7d11f7c813fba0f5f4d8b6a", "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": "974b47378c14c6dcf7d11f7c813fba0f5f4d8b6a", "url": "https://github.com/RomanSlack/jev-drone" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "README setup and no-Jev flight simulation", "operation_scope": "product operation", "hosting": null, "kind": "repo", "test_version": "readme-f72312298d35d84837d4fc5f6f22b138d54d456600b5ed431e36e8f5db931dbf", "evidence_version": null }, "other_model": null, "other_run_id": null, "models_agree": null, "furthest_model": null, "transcript_url": null, "report_url": "/reports/RomanSlack--jev-drone-gpt-6-luna-1792790853700451182.json" }