{ "run_id": "Shoberman2--openWorld-gpt-6-luna-1792776529685851743", "date": "2026-10-23T17:47:39.532162+00:00", "repo": "Shoberman2/openWorld", "kind": "repo", "source": "https://github.com/Shoberman2/openWorld", "commit": "969b75b698359477a96c81d3277aa2752c199ab1", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "test_version": "readme-f72312298d35d84837d4fc5f6f22b138d54d456600b5ed431e36e8f5db931dbf", "pass": true, "outcome": "pass", "time_to_working_s": 1080.4959940240951, "total_s": 1129.8462793827057, "steps": [ "pwd; ls -la; rg --files -g 'README*' -g 'AGENTS.md' -g 'pyproject.toml' -g 'requirements*.txt' -g 'package.json' -g 'Makefile' -g '*.yml' -g '*.yaml' | head -100; vault-search 'openWorld MCP world simulation README tools'", "cat README.md; cat package.json; find . -name AGENTS.md -o -name '*.md'", "node --version; npm --version; id -u; git status --short; ls -la .coldpass; python3 --version; git init; git remote add origin https://github.com/Shoberman2/openWorld; git fetch --depth 1 origin 969b75b698359477a96c81d3277aa2752c199ab1; git reset --mixed FETCH_HEAD", "sudo -n apt-get update && sudo -n apt-get install -y nodejs npm; node --version; npm --version", "curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -n bash -; sudo -n apt-get install -y nodejs; node --version; npm --version; npm install", "sed -n '1,240p' server/index.ts; rg -n 'app\\.(get|post)|router\\.(get|post)' server; sed -n '1,160p' client/vite.config.ts; git status --short", "tail -100 server/index.ts; grep -n \"start\\|app.get\" server/index.ts | tail -30; cat > /tmp/noop <<'EOF'\nEOF\n", "npm run build && npm run typecheck", "PORT=4317 OPENWORLD_HOME= OPENWORLD_FAKE_AGENTS=1 OPENWORLD_DRY_PR=1 OPENWORLD_DRY_GITHUB=1 npm start > 2>&1 & echo $! > ; for i in $(seq 1 40); do curl -fsS http://localhost:4317/ -o && break; sleep 1; done; head -c 180 ; curl -sS -D - http://localhost:4317/api/me; kill $(cat ); sleep 1; cat ", "cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"http\",\"argv\":[\"npm\",\"start\"],\"cwd\":\"\",\"url\":\"http://localhost:4317/api/me\",\"env\":{\"PORT\":\"4317\",\"OPENWORLD_HOME\":\"\",\"OPENWORLD_FAKE_AGENTS\":\"1\",\"OPENWORLD_DRY_PR\":\"1\",\"OPENWORLD_DRY_GITHUB\":\"1\"},\"expected_text\":\"\\\"connected\\\":false\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"The world works straight away with no accounts at all.\",\"source\":\"The world works straight away with no accounts at all.\",\"input\":\"GET /api/me with no account credentials\",\"expected\":\"connected is false while the server provides app API data\",\"probe_kind\":\"http\",\"argv\":[\"npm\",\"start\"],\"url\":\"http://localhost:4317/api/me\",\"env\":{\"PORT\":\"4317\",\"OPENWORLD_HOME\":\"\",\"OPENWORLD_FAKE_AGENTS\":\"1\",\"OPENWORLD_DRY_PR\":\"1\",\"OPENWORLD_DRY_GITHUB\":\"1\"},\"expected_text\":\"\\\"connected\\\":false\",\"cwd\":\"\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"README Quick start production entrypoint serves the OpenWorld client\",\"source\":\"README.md / Quick start: npm start builds the client once and serves everything on http://localhost:4317.\",\"input\":\"npm install then npm start; GET /\",\"expected\":\"HTML page title OpenWorld HQ\",\"argv\":[\"npm\",\"start\"],\"cwd\":\"\",\"env\":{\"PORT\":\"4317\",\"OPENWORLD_HOME\":\"\",\"OPENWORLD_FAKE_AGENTS\":\"1\",\"OPENWORLD_DRY_PR\":\"1\",\"OPENWORLD_DRY_GITHUB\":\"1\"},\"expected_text\":\"OpenWorld HQ\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"The product has schedules and background schedule ticks, but no user-triggerable periodic cycle was exercised; server/index.ts starts the HTTP application and installs background schedule handling. Ordinary useful behavior is served through HTTP endpoints.\",\"checks\":[]}\nEOF\nmkdir -p .coldpass; = python3 -I --validate --replay", "ps aux | grep -E '[n]ode|[t]sx'; fuser -n tcp 4317 2>/dev/null || true; kill $(cat ) 2>/dev/null || true; pkill -f 'tsx --env-file-if-exists=.env server/index.ts' || true", "ps aux | grep -E '[n]ode|[t]sx'; fuser -n tcp 4317 2>/dev/null || true", "sed -i 's/4317/43817/g' .coldpass/probe.json .coldpass/claims.json .coldpass/examples.json; sed -i 's/\"PORT\":\"4317\"/\"PORT\":\"43817\"/g' .coldpass/probe.json .coldpass/claims.json .coldpass/examples.json; = python3 -I --validate --replay", "python3 - <<'PY'\nimport json\np='.coldpass/examples.json'\nx=json.load(open(p)); x[0]={'kind':'example','claim':'README Quick start build command produces client assets','source':'README.md / Quick start: npm start builds the client once and serves everything on http://localhost:4317.','input':'npm run build','expected':'Vite production assets generated','argv':['npm','run','build'],'cwd':'','env':{},'expected_text':'built in'}\njson.dump(x,open(p,'w'))\nPY\n= python3 -I --validate --replay", "cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Installed dependencies, built the client, started the production app, and read its account API response.\",\"operation_scope\":\"Node.js 22.23.4; no GitHub or AI credentials required for this local API operation.\",\"steps\":[\"Installed Node.js 22 using the NodeSource apt repository after Ubuntu's node package was below the README requirement.\",\"Ran npm install; the documented postinstall fetched Xbot.glb and Soldier.glb.\",\"Ran npm run build and npm run typecheck successfully.\",\"Ran the documented npm start entrypoint and observed GET /api/me return connected:false without credentials.\",\"Validated probe, README claim, cycle inventory, and build example with the coldpass checker replay.\"],\"deviations\":[\"Initial Ubuntu nodejs/npm setup installed Node 18.19.1 and removed npm while upgrading; replaced it with Node.js 22.23.4 through NodeSource. The documented app install then succeeded.\",\"The first evidence replay's example collided with an already running server; the next run timed out because npm start remains a server process. Replaced that example with the README-documented npm run build, which replays successfully.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\nEOF\n= python3 -I --validate --replay; ps aux | grep -E '[n]ode|[t]sx'" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Installed dependencies, built the client, started the production app, and read its account API response.", "suggested_fix": null, "tokens_in": 616923, "tokens_out": 2345, "cost_usd": null, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "npm", "start" ], "kind": "http", "status": 200, "bytes": 171, "url": "http://localhost:43817/api/me", "response_checked": true, "response_excerpt": "\"connected\":false,\"login\":null,\"name\":null,\"avatarUrl\":null,\"claudeAvailable\":false,\"tokenSource\":null,\"agentsReady\":false,\"hidePrivate\":false,\"hidePrivateFromEnv\":false}", "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 1 connection review, 2 download and execute.", "expected": "Reviewed as expected for a test run: 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": 1, "path": "104.17.207.5:443", "process_count": 1, "processes": [ { "address": "104.17.207.5:443", "executable": "/usr/bin/node", "owner": "repo", "pid": "13491", "source": "" } ] }, { "kind": "download-and-execute", "count": 2, "note": "Source contains download and execute; review its purpose.", "location_count": 1, "path": "server/providers/grok.ts" } ], "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=Shoberman2--openWorld-gpt-6-luna-1792776529685851743", "evidence_file": "/data/safety/Shoberman2--openWorld-gpt-6-luna-1792776529685851743.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": 15, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "969b75b698359477a96c81d3277aa2752c199ab1", "url": "https://github.com/Shoberman2/openWorld" }, "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": 15, "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": [ "api" ], "license": "MIT", "repo_url": "https://github.com/Shoberman2/openWorld", "cost_to_try": "free", "hardware": "GPU", "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": "The product has schedules and background schedule ticks, but no user-triggerable periodic cycle was exercised; server/index.ts starts the HTTP application and installs background schedule handling. Ordinary useful behavior is served through HTTP endpoints.", "evidence": "The product has schedules and background schedule ticks, but no user-triggerable periodic cycle was exercised; server/index.ts starts the HTTP application and installs background schedule handling. Ordinary useful behavior is served through HTTP endpoints.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "The world works straight away with no accounts at all.", "source": "The world works straight away with no accounts at all.", "input": "GET /api/me with no account credentials", "expected": "connected is false while the server provides app API data", "command": "npm start", "verdict": "yes", "outcome": "Real input produced the expected result: \"connected\":false", "evidence": "\"connected\":false,\"login\":null,\"name\":null,\"avatarUrl\":null,\"claudeAvailable\":false,\"tokenSource\":null,\"agentsReady\":false,\"hidePrivate\":false,\"hidePrivateFromEnv\":false}", "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "README Quick start build command produces client assets", "source": "README.md / Quick start: npm start builds the client once and serves everything on http://localhost:4317.", "input": "npm run build", "command": "npm run build", "evidence": "l 1.61 kB \u2502 gzip: 0.70 kB\nclient/dist/assets/tilemap.worker-B0geajbE.js 21.76 kB\nclient/dist/assets/worker-BYabsMYE.js 221.42 kB\nclient/dist/assets/index-BTWetR7H.css 92.39 kB \u2502 gzip: 19.50 kB\nclient/dist/assets/index-iDACb_V9.js 1,947.01 kB \u2502 gzip: 632.66 kB\n\n\u2713 built in 1.03s\n\u001b[33m[INEFFECTIVE_DYNAMIC_IMPORT] \u001b[0mclient/src/ui/settings.ts is dynamically imported by client/src/ui/agentPick.ts but also statically imported by client/src/landing/index.ts, client/src/main.ts, dynamic import will not move module into another chunk.", "deferred": false, "expected": "Vite production assets generated", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": "yes", "maintenance": { "archived": false, "commits_90d": 10, "last_commit_at": "2026-10-22T22:30:23Z", "last_release_at": null, "median_reply_hours": null, "merged_prs_90d": 0, "note": "actively maintained: last commit 0 days ago; 10 commits and 0 merged PRs in 90 days; 0 open issues, 0 open PRs; no releases", "open_issues": 0, "open_prs": 0, "reply_share": null, "reply_threads": 0, "verdict": "maintained" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 0 days ago; 10 commits and 0 merged PRs in 90 days; 0 open issues, 0 open PRs; no releases", "maintained": "active", "maintained_note": "last commit 0 days ago", "last_commit_at": "2026-10-22T22:37:41Z", "last_release_at": null, "open_issues": null, "answered_issues": null, "platforms_claimed": [ "linux", "mac", "windows" ], "topic": "agent-harness", "agent_interfaces": [ { "interface": "api", "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": "2026-10-23T17:47:39.532162+00:00", "tested_commit": "969b75b698359477a96c81d3277aa2752c199ab1", "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": "Shoberman2/openWorld", "source": "https://github.com/Shoberman2/openWorld", "commit": "969b75b698359477a96c81d3277aa2752c199ab1", "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": "969b75b698359477a96c81d3277aa2752c199ab1", "url": "https://github.com/Shoberman2/openWorld" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Installed dependencies, built the client, started the production app, and read its account API response.", "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/Shoberman2--openWorld-gpt-6-luna-1792776529685851743.json" }