{ "run_id": "glmn-ai--neurosquad-cli-gpt-6-luna-1792812263493151626", "date": "2026-10-24T03:31:34.034076+00:00", "repo": "glmn-ai/neurosquad-cli", "kind": "repo", "source": "https://github.com/glmn-ai/neurosquad-cli", "commit": "a91269f31cd4c4dc91b0cecee40a32654e20ec02", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "test_version": "readme-f72312298d35d84837d4fc5f6f22b138d54d456600b5ed431e36e8f5db931dbf", "pass": true, "outcome": "pass", "time_to_working_s": 389.8453124560183, "total_s": 430.54086542129517, "steps": [ "pwd; rg --files -g 'README*' -g 'AGENTS.md' -g 'package.json' -g 'pyproject.toml' -g 'requirements*.txt' -g 'Makefile' -g 'uv.lock' -g 'package-lock.json' -g 'pnpm-lock.yaml' -g 'yarn.lock' -g '*.toml' -g '*.json' | head -100; vault-search 'neurosquad-cli README operation' 2>&1 | head -80; cat 2>/dev/null | head -80", "ls -la; find .. -name AGENTS.md -o -iname 'README*' | head -80", "cat README.md; cat package.json; python3 --version; node --version; npm --version", "id -u; ls -la .coldpass; curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash -; sudo apt-get install -y nodejs", "npm install -g neurosquad", "npx --yes neurosquad ls --json", "npm install && npm run build && npm run release:smoke", "sudo apt-get install -y build-essential python3-dev && npm install && npm run build && npm run release:smoke", "cd /tmp && npx --yes neurosquad@0.6.0 ls --json", "cd /tmp && npx --yes neurosquad@0.6.0 run --name coldpass-agent -- node -e 'console.log(\"NEUROSQUAD_OPERATION_OK\")' && npx --yes neurosquad@0.6.0 ls --json && npx --yes neurosquad@0.6.0 down", "cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"npx\",\"--yes\",\"neurosquad@0.6.0\",\"run\",\"--name\",\"coldpass-agent\",\"--\",\"node\",\"-e\",\"console.log('NEUROSQUAD_OPERATION_OK')\"],\"cwd\":\"/tmp\",\"expected_text\":\"started coldpass-agent\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Run any command as an agent\",\"source\":\"`nsq run -- npm run dev # any command, as an agent`\",\"input\":\"node -e console.log('NEUROSQUAD_OPERATION_OK')\",\"expected\":\"starts an agent\",\"probe_kind\":\"cli\",\"argv\":[\"npx\",\"--yes\",\"neurosquad@0.6.0\",\"run\",\"--name\",\"coldpass-claim\",\"--\",\"node\",\"-e\",\"console.log('NEUROSQUAD_OPERATION_OK')\"],\"expected_text\":\"started coldpass-claim\",\"cwd\":\"/tmp\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Run command agent and list status\",\"source\":\"README.md / Quick start; Commands\",\"input\":\"node command printing marker\",\"expected\":\"agent appears then exits\",\"argv\":[\"bash\",\"-lc\",\"cd /tmp && npx --yes neurosquad@0.6.0 run --name coldpass-example -- node -e 'console.log(\\\"EXAMPLE_OK\\\")' && npx --yes neurosquad@0.6.0 ls --json && npx --yes neurosquad@0.6.0 down\"],\"cwd\":\"/tmp\",\"expected_text\":\"coldpass-example\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"README entry points provide interactive dashboard and persistent daemon commands; no scheduled cycle or loop is documented.\"}\nEOF\n= python3 -I --validate --replay", "python3 - <<'PY'\np='.coldpass/claims.json'\ns=open(p).read().replace('`nsq run -- npm run dev # any command, as an agent`','nsq run [--name n] -- any command')\nopen(p,'w').write(s)\nPY\n= python3 -I --validate --replay", "cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Run an arbitrary command under nsq and inspect agent status\",\"operation_scope\":\"Node.js 22.23.4 with native build prerequisites; npm-installed dependencies and packaged CLI smoke test\",\"steps\":[\"Installed Node.js 22.23.4 using the NodeSource Node 22 setup script and apt.\",\"Installed build-essential and python3-dev after npm install required make for node-pty's native build.\",\"npm install\",\"npm run build\",\"npm run release:smoke\",\"From /tmp: npx --yes neurosquad@0.6.0 run --name coldpass-agent -- node -e 'console.log(\\\"NEUROSQUAD_OPERATION_OK\\\")'; npx --yes neurosquad@0.6.0 ls --json; npx --yes neurosquad@0.6.0 down\"],\"deviations\":[\"The initial documented global npm install failed with EACCES; used the documented npx installation method.\",\"Initial npm install failed because make was absent; installed documented native-build prerequisites and retried.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\nEOF" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Run an arbitrary command under nsq and inspect agent status", "suggested_fix": null, "tokens_in": 448715, "tokens_out": 1935, "cost_usd": null, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "npx", "--yes", "neurosquad@0.6.0", "run", "--name", "coldpass-agent", "--", "node", "-e", "console.log('NEUROSQUAD_OPERATION_OK')" ], "kind": "cli", "returncode": 0, "stdout": "started coldpass-agent-3 (command) in /tmp\nnsq attach coldpass-agent-3 \u00b7 nsq (dashboard)", "stderr": "", "needs_credentials": false, "needs_browser": false, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 1 connection review, 1 download and execute, 6 encoded blob, 1 outside write, 3 sensitive read. 5 static matches retained as context.", "expected": "Reviewed as expected for a test run: npm built the package inside its global install folder; opened pseudo-terminals; read only test files inside the test workspace or its temporary folders; resolver address lookups that send no data.", "findings": [ { "kind": "connection-review", "count": 1, "note": "Repository processes attempted these non-loopback connections; proxies can hide the final hostname.", "location_count": 2, "process_count": 2 }, { "kind": "download-and-execute", "count": 1, "note": "Source contains download and execute; review its purpose.", "location_count": 1, "path": "packaging/install/install.sh" }, { "kind": "encoded-blob", "count": 6, "note": "Source contains encoded blob; review its purpose.", "location_count": 1, "path": "packages/tui-theme/src/logos.generated.ts" }, { "kind": "outside-write", "count": 1, "note": "Repository processes attempted these writes outside documented output/cache paths.", "location_count": 1, "path": "/usr/bin/python3", "process_count": 1, "processes": [ { "executable": "/usr/bin/node", "owner": "repo", "path": "/usr/bin/python3", "pid": "8756", "source": "npm lifecycle" } ] }, { "kind": "sensitive-read", "count": 3, "note": "A repository process attempted to read this sensitive path.", "location_count": 3, "process_count": 16 } ], "context": [ { "kind": "hardcoded-secret", "count": 5, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 1, "path": "apps/cli/src/daemon/approvals.test.ts" } ], "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=glmn-ai--neurosquad-cli-gpt-6-luna-1792812263493151626", "evidence_file": "/data/safety/glmn-ai--neurosquad-cli-gpt-6-luna-1792812263493151626.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": 13, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "a91269f31cd4c4dc91b0cecee40a32654e20ec02", "url": "https://github.com/glmn-ai/neurosquad-cli" }, "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": 13, "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/glmn-ai/neurosquad-cli", "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": "README entry points provide interactive dashboard and persistent daemon commands; no scheduled cycle or loop is documented.", "evidence": "README entry points provide interactive dashboard and persistent daemon commands; no scheduled cycle or loop is documented.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "Run any command as an agent", "source": "nsq run [--name n] -- any command", "input": "node -e console.log('NEUROSQUAD_OPERATION_OK')", "expected": "starts an agent", "command": "npx --yes neurosquad@0.6.0 run --name coldpass-claim -- node -e 'console.log('\"'\"'NEUROSQUAD_OPERATION_OK'\"'\"')'", "verdict": "yes", "outcome": "Real input produced the expected result: started coldpass-claim", "evidence": "started coldpass-claim-2 (command) in /tmp\nnsq attach coldpass-claim-2 \u00b7 nsq (dashboard)\n", "returncode": 0, "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Run command agent and list status", "source": "README.md / Quick start; Commands", "input": "node command printing marker", "command": "bash -lc 'cd /tmp && npx --yes neurosquad@0.6.0 run --name coldpass-example -- node -e '\"'\"'console.log(\"EXAMPLE_OK\")'\"'\"' && npx --yes neurosquad@0.6.0 ls --json && npx --yes neurosquad@0.6.0 down'", "evidence": " \"-e\",\n \"console.log('NEUROSQUAD_OPERATION_OK')\"\n ],\n \"createdAt\": 1792812663394,\n \"running\": false,\n \"status\": \"exited\",\n \"statusAt\": 1792812663489\n },\n {\n \"id\": \"1172b088-5ac5-4b12-99cb-5b6737b394e3\",\n \"name\": \"coldpass-example-2\",\n \"harness\": \"command\",\n \"workspace\": \"/tmp\",\n \"cwd\": \"/tmp\",\n \"command\": [\n \"node\",\n \"-e\",\n \"console.log(\\\"EXAMPLE_OK\\\")\"\n ],\n \"createdAt\": 1792812666139,\n \"running\": false,\n \"status\": \"exited\",\n \"statusAt\": 1792812666225\n }\n]\nstopped the nsq daemon and its agents (they resume with `nsq up`)", "deferred": false, "expected": "agent appears then exits", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": "yes", "maintenance": { "archived": false, "commits_90d": 66, "last_commit_at": "2026-10-13T14:19:21Z", "last_release_at": "2026-10-13T14:29:10Z", "median_reply_hours": null, "merged_prs_90d": 65, "note": "actively maintained: last commit 10 days ago; 66 commits and 65 merged PRs in 90 days; 0 open issues, 2 open PRs; 0 of 1 recent threads got a maintainer reply; latest release 2026-10-13", "open_issues": 0, "open_prs": 2, "reply_share": 0.0, "reply_threads": 1, "verdict": "maintained" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 10 days ago; 66 commits and 65 merged PRs in 90 days; 0 open issues, 2 open PRs; 0 of 1 recent threads got a maintainer reply; latest release 2026-10-13", "maintained": "active", "maintained_note": "last commit 4 days ago", "last_commit_at": "2026-10-19T07:36:39Z", "last_release_at": "2026-10-13T14:29:10Z", "open_issues": null, "answered_issues": null, "platforms_claimed": [ "linux", "mac", "windows" ], "topic": "agent-harness", "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": "2026-10-24T03:31:34.034076+00:00", "tested_commit": "a91269f31cd4c4dc91b0cecee40a32654e20ec02", "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": "glmn-ai/neurosquad-cli", "source": "https://github.com/glmn-ai/neurosquad-cli", "commit": "a91269f31cd4c4dc91b0cecee40a32654e20ec02", "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": "a91269f31cd4c4dc91b0cecee40a32654e20ec02", "url": "https://github.com/glmn-ai/neurosquad-cli" }, "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 an arbitrary command under nsq and inspect agent status", "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/glmn-ai--neurosquad-cli-gpt-6-luna-1792812263493151626.json" }