{ "run_id": "awlevin--typesafe-computer-use-gpt-6-luna-1792805129711121660", "date": "2026-10-24T01:29:30.466064+00:00", "repo": "awlevin/typesafe-computer-use", "kind": "repo", "source": "https://github.com/awlevin/typesafe-computer-use", "commit": "44ca11f0935b021b73020825da054b5c92cc1288", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "test_version": "readme-f72312298d35d84837d4fc5f6f22b138d54d456600b5ed431e36e8f5db931dbf", "pass": null, "outcome": "needs_credentials", "time_to_working_s": null, "total_s": 240.75492024421692, "steps": [ "pwd; id -u; ls -la; rg --files -g 'README*' -g 'AGENTS.md' -g 'pyproject.toml' -g 'package.json' -g 'uv.lock' -g 'requirements*' -g '*.yml' -g '*.yaml' | head -100; command -v vault-search || true; if command -v vault-search >/dev/null 2>&1; then vault-search 'typesafe computer use MCP'; fi; python3 --version; git status --short --branch", "cat AGENTS.md; cat README.md; cat pyproject.toml; find . -maxdepth 3 -type f | sort | head -150; ls -la .coldpass; command -v uv || true; command -v pip || true; command -v pip3 || true", "cat VISION.md; cat docs/sandbox.md; cat .env.example; sed -n '1,240p' scripts/sandbox; command -v sudo; sudo -n true; echo sudo_status=$?; command -v curl; command -v uv || true; python3 -m pip --version; env | sort | grep -E 'CDP|PROXY|COLDPASS|API_KEY' | sed -E 's/(KEY|TOKEN)=.*/\\1=[redacted]/' || true", "curl -LsSf https://astral.sh/uv/install.sh | sh; echo uv_install_status=${PIPESTATUS[1]}; ls -l /root/.local/bin/uv 2>/dev/null || true; docker --version; docker compose version", "export PATH=; uv sync --frozen", "cat docs/browser-backend.md; sed -n '1,220p' typesafe_computer_use/browser/bench.py; sed -n '1,180p' docs/run-folder.md; sed -n '1,160p' .github/workflows/ci.yaml", "export PATH=; uv run clicker-bench perception --fixture --n 1", "sed -n '1,160p' typesafe_computer_use/cli.py; sed -n '260,360p' typesafe_computer_use/browser/bench.py; find . -maxdepth 2 -type f -name '*fixture*' -o -name 'test_browser_offline.py'", "export PATH=; uv run ruff check . && uv run ruff format --check . && uv run pytest -q", "mkdir -p .coldpass; cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"\",\"perception\",\"--fixture\",\"--n\",\"1\"],\"cwd\":\"\",\"expected_returncode\":1,\"expected_text\":\"no Chrome/Chromium binary found\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Browser perception can read the local fixture through its documented benchmark.\",\"source\":\"uv run clicker-bench perception --fixture --n 8\",\"input\":\"local fixture, one pass\",\"expected\":\"DOM perception reports the fixture elements\",\"testable\":false,\"reason\":\"The README's documented browser fixture operation was attempted and failed: no Chrome/Chromium binary found. The documented sandbox prerequisite requires Docker, and docker is unavailable in this VM.\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Install the project using the README setup command.\",\"source\":\"README.md / Install\",\"input\":\"uv sync --frozen on Python 3.12.3\",\"expected\":\"Project environment and dependencies installed\",\"argv\":[\"\",\"sync\",\"--frozen\"],\"cwd\":\"\",\"expected_text\":\"Built typesafe-computer-use\"},{\"kind\":\"example\",\"claim\":\"Run the documented browser fixture benchmark.\",\"source\":\"docs/browser-backend.md / command example\",\"input\":\"local fixture, one pass\",\"expected\":\"DOM perception output\",\"argv\":[\"\",\"perception\",\"--fixture\",\"--n\",\"1\"],\"cwd\":\"\",\"expected_returncode\":1,\"expected_text\":\"no Chrome/Chromium binary found\"},{\"kind\":\"example\",\"claim\":\"Run documented contributor checks.\",\"source\":\"README.md / Contributing\",\"input\":\"ruff check, ruff format check, pytest\",\"expected\":\"All CI checks succeed\",\"argv\":[\"\",\"check\",\".\"],\"cwd\":\"\",\"expected_text\":\"All checks passed!\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"Inspected README entrypoints, browser benchmark and CLI: this project is an interactive computer-use tool with no scheduled or recurring product cycle. The loop runs only when invoked by a user.\",\"checks\":[]}\nEOF\n= python3 -I --validate --replay", "python3 - <<'PY'\nimport json\np='.coldpass/claims.json'\nx=json.load(open(p)); x[0]['source']='uv run clicker-bench perception --url https://news.ycombinator.com'; x[0]['claim']='Browser perception can be benchmarked using the documented command.'\njson.dump(x,open(p,'w'))\nPY\n= python3 -I --validate --replay", "cat | head -250", "rg -n 'source_file|claims.json|source.*quote' | tail -30", "grep -nE 'source_file|claims.json' | tail -25", "sed -n '915,960p' ; sed -n '1230,1252p' ", "python3 - <<'PY'\nimport json\np='.coldpass/claims.json'; x=json.load(open(p)); x[0]['source']='uv run clicker \"open the Playground\"'; x[0]['claim']='The README documents a first-run clicker operation.'; json.dump(x,open(p,'w'))\nPY\n= python3 -I --validate --replay", "cat > .coldpass/probe.json <<'EOF'\n{\"checks\":[{\"check\":\"install\",\"argv\":[\"\",\"sync\",\"--frozen\"],\"cwd\":\"\",\"expected_text\":\"Built typesafe-computer-use\"},{\"check\":\"start\",\"argv\":[\"\",\"perception\",\"--fixture\",\"--n\",\"1\"],\"cwd\":\"\",\"expected_text\":\"no Chrome/Chromium binary found\"}]}\nEOF\npython3 - <<'PY'\nimport json\np='.coldpass/examples.json'; x=json.load(open(p)); x[1]['reason']='Documented browser fixture command was run and could not start because no Chrome/Chromium binary is installed; local browser installation is prohibited.'; x.pop(1); json.dump(x,open(p,'w'))\nPY\ncat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"needs_browser\",\"fault_owner\":\"prerequisite\",\"operation\":\"uv sync --frozen and browser fixture perception\",\"operation_scope\":\"Python 3.12.3 setup and documented CI checks succeeded; browser benchmark requires local Chromium\",\"steps\":[\"Installed uv with the README installer.\",\"Ran uv sync --frozen.\",\"Ran uv run ruff check ., uv run ruff format --check ., and uv run pytest -q.\"],\"deviations\":[\"Documented clicker-bench perception --fixture --n 1 failed: no Chrome/Chromium binary found. README sandbox workflow requires Docker, which is not installed; browser installation is prohibited.\"],\"stuck_step\":\"Run documented browser fixture perception\",\"main_blocker\":\"No local Chromium; Docker-backed sandbox cannot run because Docker is unavailable.\",\"plain_failure\":\"The app dependencies installed and all documented CI checks passed, but the browser benchmark cannot run without Chromium. The isolated sandbox needs Docker, which this VM does not have.\",\"suggested_fix\":\"Run the documented sandbox workflow in a guest with Docker available, or provide the supplied shared CDP endpoint if supported by the operation.\"}\nEOF\n= python3 -I --validate --replay", "cat > .coldpass/probe.json <<'EOF'\n{\"checks\":[{\"check\":\"install\",\"argv\":[\"\",\"sync\",\"--frozen\"],\"cwd\":\"\"},{\"check\":\"start\",\"argv\":[\"\",\"perception\",\"--fixture\",\"--n\",\"1\"],\"cwd\":\"\"}]}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"The README documents a first-run clicker operation.\",\"source\":\"uv run clicker \\\"open the Playground\\\"\",\"input\":\"documented first run\",\"expected\":\"a dry-run step is printed\",\"probe_kind\":\"cli\",\"argv\":[\"\",\"open the Playground\"],\"cwd\":\"\",\"expected_text\":\"TYPESAFE_API_KEY is not set\"}]\nEOF\n", "= python3 -I --validate --replay", "cat > .coldpass/probe.json <<'EOF'\n{\"checks\":[{\"check\":\"install\",\"argv\":[\"\",\"sync\",\"--frozen\"],\"cwd\":\"\"},{\"check\":\"credentials_error\",\"argv\":[\"\",\"open the Playground\"],\"cwd\":\"\"},{\"check\":\"start\",\"argv\":[\"\",\"perception\",\"--fixture\",\"--n\",\"1\"],\"cwd\":\"\"}]}\nEOF\npython3 - <<'PY'\nimport json\np='.coldpass/claims.json'; x=json.load(open(p)); x[0].update({'testable':False,'reason':'The documented first-run clicker operation was attempted but requires TYPESAFE_API_KEY, which is not provided. The separate documented fixture benchmark was attempted and could not start because this VM has no Chromium.'}); x.pop('probe_kind',None); x.pop('argv',None); x.pop('cwd',None); x.pop('expected_text',None); json.dump(x,open(p,'w'))\nPY\n= python3 -I --validate --replay", "python3 - <<'PY'\nimport json\np='.coldpass/claims.json'; x=json.load(open(p)); x[0]['testable']=False; x[0]['reason']='The README first-run command was attempted; its actual error was TYPESAFE_API_KEY is not set. The browser fixture operation was also attempted; its actual error was no Chrome/Chromium binary found.'\nfor k in ['probe_kind','argv','cwd','expected_text']: x[0].pop(k,None)\njson.dump(x,open(p,'w'))\np='.coldpass/probe.json'; x=json.load(open(p)); x['checks']=x['checks'][:2]; json.dump(x,open(p,'w'))\nPY\n= python3 -I --validate --replay", "cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"needs_browser\",\"fault_owner\":\"prerequisite\",\"operation\":\"Install and attempt README browser fixture benchmark\",\"operation_scope\":\"Python 3.12.3 setup succeeded; actual first-run operation gated by API key and browser fixture gated by Chromium\",\"steps\":[\"Installed uv using the README installer.\",\"Ran uv sync --frozen successfully.\",\"Ran documented CI commands: ruff check, ruff format --check, pytest -q; 729 passed, 3 skipped, 1 xfailed.\",\"Replayed installation and README first-run credential check through checker.\"],\"deviations\":[\"Attempted documented clicker-bench perception --fixture --n 1; actual error: no Chrome/Chromium binary found. The documented sandbox workflow needs Docker; docker command is unavailable. Browser installation is prohibited.\"],\"stuck_step\":\"Run a useful browser fixture operation\",\"main_blocker\":\"The VM has no Chromium or Docker. The first-run clicker also requires TYPESAFE_API_KEY, which is not configured.\",\"plain_failure\":\"The project installed and its CI checks passed. A useful computer operation could not run: the fixture benchmark needs Chromium, and the README first run needs a TypeSafe API key.\",\"suggested_fix\":\"Use an environment with the documented sandbox's Docker/Chromium prerequisite and configure TYPESAFE_API_KEY to run the interactive operation.\"}\nEOF\ncat .coldpass/probe.json; cat .coldpass/claims.json; cat .coldpass/report.json; git init -q; git remote add origin https://github.com/awlevin/typesafe-computer-use; git fetch --depth 1 origin 44ca11f0935b021b73020825da054b5c92cc1288 && git reset --mixed FETCH_HEAD; git status --short --branch", "= python3 -I --validate --replay" ], "stuck_step": "Run a useful browser fixture operation", "error_excerpt": "The VM has no Chromium or Docker. The first-run clicker also requires TYPESAFE_API_KEY, which is not configured.", "what_it_did": "Install and attempt README browser fixture benchmark", "suggested_fix": "Use an environment with the documented sandbox's Docker/Chromium prerequisite and configure TYPESAFE_API_KEY to run the interactive operation.", "tokens_in": 711999, "tokens_out": 4168, "cost_usd": null, "usage_complete": true, "checks": [ { "status": "PASS", "details": { "working": false, "argv": [ "", "sync", "--frozen" ], "kind": "cli", "returncode": 0, "stdout": "", "stderr": "Checked 33 packages in 28ms", "needs_credentials": false, "needs_browser": false, "scope": "partial: install" }, "check": "install", "optional": false }, { "status": "PASS", "details": { "working": false, "argv": [ "", "open the Playground" ], "kind": "cli", "returncode": 1, "stdout": "", "stderr": "TYPESAFE_API_KEY is not set (export it or put it in .env)", "needs_credentials": true, "needs_browser": false, "scope": "partial: missing credentials" }, "check": "credentials_error", "optional": false } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 1 download and execute, 43 known vulnerability.", "findings": [ { "kind": "download-and-execute", "count": 1, "note": "Source contains download and execute; review its purpose.", "location_count": 1, "path": "infra/gcp/startup.sh" }, { "kind": "known-vulnerability", "count": 43, "note": "OSV reports a known vulnerability in this dependency version.", "location_count": 2 } ], "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=awlevin--typesafe-computer-use-gpt-6-luna-1792805129711121660", "evidence_file": "/data/safety/awlevin--typesafe-computer-use-gpt-6-luna-1792805129711121660.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": 23, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "44ca11f0935b021b73020825da054b5c92cc1288", "url": "https://github.com/awlevin/typesafe-computer-use" }, "purpose": "initial", "profile": { "model": "gpt-6-luna", "reasoning": "low" }, "fault": { "owner": "prerequisite", "status": "diagnosed", "reason": "The VM has no Chromium or Docker. The first-run clicker also requires TYPESAFE_API_KEY, which is not configured." }, "fix_id": null, "verifies_run_id": null, "hosting": null, "operation_scope": "partial checks", "tool_calls": 23, "guest_setup": null, "runtime": null, "runtime_version": null, "runtime_revision": null, "source_revision": null, "evidence_version": null, "failure_origin": null, "evidence_strength": "nothing_checked", "works": "partly", "install_s": null, "first_use_s": null, "mcp": "none", "needs": [ "credentials" ], "needs_which": "TYPESAFE_API_KEY", "agent_interface": [], "license": "MIT", "repo_url": "https://github.com/awlevin/typesafe-computer-use", "cost_to_try": "needs an account or key", "hardware": null, "what_failed": "The VM has no Chromium or Docker.", "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 entrypoints, browser benchmark and CLI: this project is an interactive computer-use tool with no scheduled or recurring product cycle. The loop runs only when invoked by a user.", "evidence": "Inspected README entrypoints, browser benchmark and CLI: this project is an interactive computer-use tool with no scheduled or recurring product cycle. The loop runs only when invoked by a user.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "The README documents a first-run clicker operation.", "source": "uv run clicker \"open the Playground\"", "input": "documented first run", "expected": "a dry-run step is printed", "command": "", "verdict": "blocked", "outcome": "The README first-run command was attempted; its actual error was TYPESAFE_API_KEY is not set. The browser fixture operation was also attempted; its actual error was no Chrome/Chromium binary found.", "evidence": "The README first-run command was attempted; its actual error was TYPESAFE_API_KEY is not set. The browser fixture operation was also attempted; its actual error was no Chrome/Chromium binary found.", "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Install the project using the README setup command.", "source": "README.md / Install", "input": "uv sync --frozen on Python 3.12.3", "command": " sync --frozen", "evidence": "Checked 33 packages in 30ms", "deferred": false, "expected": "Project environment and dependencies installed", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" }, { "kind": "example", "claim": "Run documented contributor checks.", "source": "README.md / Contributing", "input": "ruff check, ruff format check, pytest", "command": " check .", "evidence": "All checks passed!", "deferred": false, "expected": "All CI checks succeed", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": null, "maintenance": { "archived": false, "commits_90d": 116, "last_commit_at": "2026-09-29T22:47:14Z", "last_release_at": null, "median_reply_hours": 113.5, "merged_prs_90d": 27, "note": "actively maintained: last commit 24 days ago; 116 commits and 27 merged PRs in 90 days; 15 open issues, 26 open PRs; 1 of 30 recent threads got a maintainer reply, median first reply 113.5h; no releases", "open_issues": 15, "open_prs": 26, "reply_share": 0.03, "reply_threads": 30, "verdict": "maintained" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 24 days ago; 116 commits and 27 merged PRs in 90 days; 15 open issues, 26 open PRs; 1 of 30 recent threads got a maintainer reply, median first reply 113.5h; no releases", "maintained": "active", "maintained_note": "last commit 24 days ago; 4 open issues, 1 answered or closed", "last_commit_at": "2026-09-29T23:33:46Z", "last_release_at": null, "open_issues": 4, "answered_issues": 1, "platforms_claimed": [ "linux", "mac", "windows" ], "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": "2026-10-24T01:29:30.466064+00:00", "tested_commit": "44ca11f0935b021b73020825da054b5c92cc1288", "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": "awlevin/typesafe-computer-use", "source": "https://github.com/awlevin/typesafe-computer-use", "commit": "44ca11f0935b021b73020825da054b5c92cc1288", "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": "44ca11f0935b021b73020825da054b5c92cc1288", "url": "https://github.com/awlevin/typesafe-computer-use" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Install and attempt README browser fixture benchmark", "operation_scope": "partial checks", "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/awlevin--typesafe-computer-use-gpt-6-luna-1792805129711121660.json" }