{ "run_id": "digitalsamba--claude-code-video-toolkit-gpt-6-luna-1792765432443167202", "date": "2026-10-23T14:53:54.608343+00:00", "repo": "digitalsamba/claude-code-video-toolkit", "kind": "repo", "source": "https://github.com/digitalsamba/claude-code-video-toolkit", "commit": "da3f474c1230d161be1384ef97aec27f73b11636", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "test_version": "readme-f72312298d35d84837d4fc5f6f22b138d54d456600b5ed431e36e8f5db931dbf", "pass": true, "outcome": "pass", "time_to_working_s": 1746.676242867019, "total_s": 1802.1651520729065, "steps": [ "pwd; rg --files -g 'README*' -g 'AGENTS.md' -g 'pyproject.toml' -g 'package.json' -g 'Makefile' -g 'requirements*.txt' -g 'uv.lock' -g 'p3-models.md' -g '*.yml' -g '*.yaml' | head -100; git status --short --branch; git rev-parse HEAD 2>/dev/null; python3 --version; id -u; command -v vault-search || true", "ls -la; find .. -name AGENTS.md -o -name README.md -o -name README.rst | head -100; cat 2>/dev/null || true; find /home -path '*/skills/i-have-adhd/SKILL.md' -o -path '*/skills/ponytail/SKILL.md' -o -path '*/skills/p3-mode/SKILL.md' 2>/dev/null | head", "cat AGENTS.md; sed -n '1,240p' README.md", "command -v vault-search && vault-search 'claude code video toolkit README operations' || true; command -v uv || true; node --version 2>/dev/null || true; sed -n '1,200p' examples/hello-world/package.json; cat .python-version; find . -maxdepth 2 -name package.json -print; rg || true; grep -nE 'Using with Codex|npm run render|uv sync|tests|schedule|cycle' README.md", "sed -n '360,410p' README.md; cat pyproject.toml; cat .coldpass/* 2>/dev/null || true; command -v sudo; sudo -n true; echo sudo_rc:$?; command -v curl; env | grep -E 'PROXY|proxy' | sed 's/=.*$/=/'", "sudo -n apt-get update && sudo -n apt-get install -y nodejs npm ffmpeg; curl -LsSf https://astral.sh/uv/install.sh | sh; export PATH=\"$HOME/.local/bin:$PATH\"; uv sync", "node --version; npm --version; ffmpeg -version | head -1; export PATH=\"$HOME/.local/bin:$PATH\"; cd examples/hello-world && npm install && npm run render", "mkdir -p .coldpass examples/hello-world/out; rm -f examples/hello-world/out/video.mp4; cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"npm\",\"run\",\"render\"],\"cwd\":\"\",\"expected_file\":\"\",\"expected_text\":\"ftyp\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"The hello-world example renders an MP4 without API keys.\",\"source\":\"No API keys needed \u2014 outputs an MP4 immediately.\",\"input\":\"npm run render in examples/hello-world\",\"expected\":\"out/video.mp4 is a rendered MP4\",\"probe_kind\":\"cli\",\"argv\":[\"npm\",\"run\",\"render\"],\"expected_file\":\"\",\"expected_text\":\"ftyp\",\"cwd\":\"\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Render the documented no-key hello-world video\",\"source\":\"README.md / Quick Start\",\"input\":\"cd examples/hello-world && npm install && npm run render\",\"expected\":\"out/video.mp4\",\"argv\":[\"npm\",\"run\",\"render\"],\"cwd\":\"\",\"expected_text\":\"+ out/video.mp4\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"Inspected README entrypoints and package scripts: the toolkit provides interactive agent workflows and one-shot render commands, with no product scheduler or cycle trigger.\",\"checks\":[]}\nEOF\n= python3 -I --validate --replay", "sed -n '1,120p' examples/hello-world/package.json; sed -n '1,100p' examples/hello-world/src/index.ts; mkdir -p .coldpass; cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"npm\",\"run\",\"render\",\"--\",\"--output\",\"out/replay.mp4\"],\"cwd\":\"\",\"expected_file\":\"\",\"expected_text\":\"ftyp\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"The hello-world example renders an MP4 without API keys.\",\"source\":\"No API keys needed \u2014 outputs an MP4 immediately.\",\"input\":\"npm run render in examples/hello-world\",\"expected\":\"out/replay-claim.mp4 is a rendered MP4\",\"probe_kind\":\"cli\",\"argv\":[\"npm\",\"run\",\"render\",\"--\",\"--output\",\"out/replay-claim.mp4\"],\"expected_file\":\"\",\"expected_text\":\"ftyp\",\"cwd\":\"\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Render the documented no-key hello-world video\",\"source\":\"README.md / Quick Start\",\"input\":\"cd examples/hello-world && npm install && npm run render\",\"expected\":\"out/video.mp4\",\"argv\":[\"npm\",\"run\",\"render\"],\"cwd\":\"\",\"expected_text\":\"out/video.mp4\"}]\nEOF\n= python3 -I --validate --replay", "sed -n '1,260p' | grep -n -A20 -B10 'expected_file'", "ls -la ; grep -R -n 'expected_file must match\\|expected_file' | head", "cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"npx\",\"remotion\",\"render\",\"src/index.ts\",\"SprintReview\",\"\"],\"cwd\":\"\",\"expected_file\":\"\",\"expected_text\":\"ftyp\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"The hello-world example renders an MP4 without API keys.\",\"source\":\"No API keys needed \u2014 outputs an MP4 immediately.\",\"input\":\"Render SprintReview\",\"expected\":\"MP4 file generated\",\"probe_kind\":\"cli\",\"argv\":[\"npx\",\"remotion\",\"render\",\"src/index.ts\",\"SprintReview\",\"\"],\"expected_file\":\"\",\"expected_text\":\"ftyp\",\"cwd\":\"\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Run documented hello-world render\",\"source\":\"README.md / Quick Start\",\"input\":\"npm run render\",\"expected\":\"out/video.mp4\",\"argv\":[\"npm\",\"run\",\"render\"],\"cwd\":\"\",\"expected_text\":\"out/video.mp4\"}]\nEOF\n= python3 -I --validate --replay", "cat | sed -n '730,785p'", "cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"npx\",\"remotion\",\"render\",\"src/index.ts\",\"SprintReview\",\"--out\",\"\"],\"cwd\":\"\",\"expected_file\":\"\",\"expected_text\":\"ftyp\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"The hello-world example renders an MP4 without API keys.\",\"source\":\"No API keys needed \u2014 outputs an MP4 immediately.\",\"input\":\"Render SprintReview\",\"expected\":\"MP4 file generated\",\"probe_kind\":\"cli\",\"argv\":[\"npx\",\"remotion\",\"render\",\"src/index.ts\",\"SprintReview\",\"--out\",\"\"],\"expected_file\":\"\",\"expected_text\":\"ftyp\",\"cwd\":\"\"}]\nEOF\n= python3 -I --validate --replay", "cat .coldpass/probe.json; cat .coldpass/claims.json", "cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"npx\",\"remotion\",\"render\",\"src/index.ts\",\"SprintReview\",\"--out=\"],\"cwd\":\"\",\"expected_file\":\"\",\"expected_text\":\"ftyp\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"The hello-world example renders an MP4 without API keys.\",\"source\":\"No API keys needed \u2014 outputs an MP4 immediately.\",\"input\":\"Render SprintReview\",\"expected\":\"MP4 file generated\",\"probe_kind\":\"cli\",\"argv\":[\"npx\",\"remotion\",\"render\",\"src/index.ts\",\"SprintReview\",\"--out=\"],\"expected_file\":\"\",\"expected_text\":\"ftyp\",\"cwd\":\"\"}]\nEOF\n= python3 -I --validate --replay", "cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"npm\",\"run\",\"render\"],\"cwd\":\"\",\"expected_text\":\"out/video.mp4\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"The hello-world example renders an MP4 without API keys.\",\"source\":\"No API keys needed \u2014 outputs an MP4 immediately.\",\"input\":\"Render SprintReview\",\"expected\":\"out/video.mp4 rendered\",\"probe_kind\":\"cli\",\"argv\":[\"npm\",\"run\",\"render\"],\"expected_text\":\"out/video.mp4\",\"cwd\":\"\"}]\nEOF\ncat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Render hello-world Remotion video\",\"operation_scope\":\"README Quick Start no-key MP4 example\",\"steps\":[\"Installed Node.js/npm and FFmpeg with apt.\",\"Installed uv and ran uv sync on Python 3.12.3.\",\"Ran cd examples/hello-world && npm install && npm run render; generated 1.1 MB out/video.mp4.\"],\"deviations\":[\"Git metadata was absent; source snapshot used as supplied.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\nEOF\n= python3 -I --validate --replay" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Render hello-world Remotion video", "suggested_fix": null, "tokens_in": 941614, "tokens_out": 5056, "cost_usd": null, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "npm", "run", "render" ], "kind": "cli", "returncode": 0, "stdout": "Rendered 437/750, time remaining: 24s\nRendered 438/750, time remaining: 24s\nRendered 439/750, time remaining: 24s\nRendered 440/750, time remaining: 24s\nRendered 441/750, time remaining: 23s\nRendered 442/750, time remaining: 23s\nRendered 443/750, time remaining: 23s\nRendered 444/750, time remaining: 23s\nRendered 445/750, time remaining: 23s\nRendered 446/750, time remaining: 23s\nRendered 447/750, time remaining: 23s\nRendered 448/750, time remaining: 23s\n[excerpt truncated]", "stderr": "", "needs_credentials": false, "needs_browser": false, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 1 connection review, 206 known vulnerability, 1 outside write, 1 sensitive read.", "findings": [ { "kind": "connection-review", "count": 1, "note": "Repository processes attempted these non-loopback connections; proxies can hide the final hostname.", "location_count": 1, "path": "2001:4860:4860::8888:443", "process_count": 1, "processes": [ { "address": "2001:4860:4860::8888:443", "executable": "/proc/self/exe", "owner": "repo", "pid": "11877", "source": "npm lifecycle" } ] }, { "kind": "known-vulnerability", "count": 195, "note": "OSV reports a known vulnerability in this dependency version.", "location_count": 15 }, { "kind": "outside-write", "count": 1, "note": "Repository processes attempted these writes outside documented output/cache paths.", "location_count": 1, "path": "/dev/udmabuf", "process_count": 1, "processes": [ { "executable": "/proc/self/exe", "owner": "repo", "path": "/dev/udmabuf", "pid": "11866", "source": "npm lifecycle" } ] }, { "kind": "sensitive-read", "count": 1, "note": "A repository process attempted to read this sensitive path.", "location_count": 1, "path": "/tmp/puppeteer_dev_chrome_profile-5KQgkK/Default/Cookies", "process_count": 1, "processes": [ { "created_in_run": true, "executable": "/proc/self/exe", "owner": "repo", "path": "/tmp/puppeteer_dev_chrome_profile-5KQgkK/Default/Cookies", "pid": "11876", "source": "npm lifecycle", "succeeded": true, "syscall": "openat", "trace": "16.trace" } ] } ], "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=digitalsamba--claude-code-video-toolkit-gpt-6-luna-1792765432443167202", "evidence_file": "/data/safety/digitalsamba--claude-code-video-toolkit-gpt-6-luna-1792765432443167202.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": 17, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "da3f474c1230d161be1384ef97aec27f73b11636", "url": "https://github.com/digitalsamba/claude-code-video-toolkit" }, "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": 17, "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/digitalsamba/claude-code-video-toolkit", "cost_to_try": "free", "hardware": "GPU", "what_failed": null, "local_or_hosted": "both", "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 entrypoints and package scripts: the toolkit provides interactive agent workflows and one-shot render commands, with no product scheduler or cycle trigger.", "evidence": "Inspected README entrypoints and package scripts: the toolkit provides interactive agent workflows and one-shot render commands, with no product scheduler or cycle trigger.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "The hello-world example renders an MP4 without API keys.", "source": "No API keys needed \u2014 outputs an MP4 immediately.", "input": "Render SprintReview", "expected": "out/video.mp4 rendered", "command": "npm run render", "verdict": "yes", "outcome": "Real input produced the expected result: out/video.mp4", "evidence": "out/video.mp4\n\nBundling 6%\nBundling 22%\nBundling 61%\nBundling 69%\nBundling 74%\nBundling 80%\nBundling 85%\nBundling 90%\nBundling 95%\nBundling 100%\nGetting composition\nComposition SprintReview\nCodec h264\nOutput out/video.mp4\nConcurrency 1x\nRendered 0/750\nRendered 1/750, time remaining: 6m 20s\nRendered 2/750, time remaining: 3m 39s\nRendered 3/750, time remaining: 2m 42s\nRendered 4/750, time remaining: 2m 14s\nRendered 5/750, time remaining: 1m 57s\nRendered 6/750, time remaining: 1m 47s\nRendered 7/750, time remaining: 1m 39s\nRendered 8/750, time remaini", "returncode": 0, "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Run documented hello-world render", "source": "README.md / Quick Start", "input": "npm run render", "command": "npm run render", "evidence": "dered 740/750, time remaining: 0s\nRendered 741/750, time remaining: 0s\nRendered 742/750, time remaining: 0s\nRendered 743/750, time remaining: 0s\nRendered 744/750, time remaining: 0s\nRendered 745/750, time remaining: 0s\nRendered 746/750, time remaining: 0s\nRendered 747/750, time remaining: 0s\nRendered 748/750, time remaining: 0s\nRendered 749/750, time remaining: 0s\nRendered 750/750\nEncoded 28/750\nEncoded 103/750\nEncoded 167/750\nEncoded 243/750\nEncoded 322/750\nEncoded 384/750\nEncoded 450/750\nEncoded 525/750\nEncoded 593/750\nEncoded 674/750\nEncoded 750/750\n\u25cb out/video.mp4 1.1 MB", "deferred": false, "expected": "out/video.mp4", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": "yes", "maintenance": { "archived": false, "commits_90d": 129, "last_commit_at": "2026-10-21T23:00:50Z", "last_release_at": "2026-10-21T21:35:04Z", "median_reply_hours": 190.8, "merged_prs_90d": 57, "note": "actively maintained: last commit 1 days ago; 129 commits and 57 merged PRs in 90 days; 2 open issues, 1 open PRs; 15 of 17 recent threads got a maintainer reply, median first reply 190.8h; latest release 2026-10-21", "open_issues": 2, "open_prs": 1, "reply_share": 0.88, "reply_threads": 17, "verdict": "maintained" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 1 days ago; 129 commits and 57 merged PRs in 90 days; 2 open issues, 1 open PRs; 15 of 17 recent threads got a maintainer reply, median first reply 190.8h; latest release 2026-10-21", "maintained": "active", "maintained_note": "last commit 1 days ago; 0 open issues, 2 answered or closed", "last_commit_at": "2026-10-21T23:00:50Z", "last_release_at": "2026-10-21T21:35:04Z", "open_issues": 0, "answered_issues": 2, "platforms_claimed": [ "linux", "mac", "windows" ], "topic": "browser-automation", "agent_interfaces": [ { "interface": "mcp", "evidence": "README metadata", "observed": false, "operation_checked": false }, { "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": "2026-10-23T14:53:54.608343+00:00", "tested_commit": "da3f474c1230d161be1384ef97aec27f73b11636", "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": "digitalsamba/claude-code-video-toolkit", "source": "https://github.com/digitalsamba/claude-code-video-toolkit", "commit": "da3f474c1230d161be1384ef97aec27f73b11636", "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": "da3f474c1230d161be1384ef97aec27f73b11636", "url": "https://github.com/digitalsamba/claude-code-video-toolkit" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Render hello-world Remotion video", "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/digitalsamba--claude-code-video-toolkit-gpt-6-luna-1792765432443167202.json" }