{ "run_id": "stablyai--orca-gpt-6-luna-1792788872369838558", "date": "2026-10-23T21:07:19.174376+00:00", "repo": "stablyai/orca", "kind": "repo", "source": "https://github.com/stablyai/orca", "commit": "2847bbe9e81ea8d94f0e42560aa981b3fccd4614", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "test_version": "readme-f72312298d35d84837d4fc5f6f22b138d54d456600b5ed431e36e8f5db931dbf", "pass": null, "outcome": "unverified", "time_to_working_s": null, "total_s": 766.8045129776001, "steps": [ "pwd; id -u; rg --files -g 'README*' -g 'AGENTS.md' -g 'pyproject.toml' -g 'package.json' -g 'requirements*.txt' -g 'Dockerfile' -g 'Makefile' -g '.github/workflows/**' -g 'setup.py' -g 'uv.lock' | head -100; ls -la", "cat AGENTS.md; cat README.md; cat package.json; python3 --version; node --version; npm --version; command -v pnpm || true; ls -la .coldpass", "cat .github/CONTRIBUTING.md; find -maxdepth 3 -type f -print 2>/dev/null | head; which sudo; sudo -n true; uname -a; command -v apt-get; command -v curl; git status --short; git rev-parse HEAD; sed -n '1,140p' .github/workflows/ci.yml 2>/dev/null", "pwd", "git init; git remote add origin https://github.com/stablyai/orca; git fetch --depth 1 origin 2847bbe9e81ea8d94f0e42560aa981b3fccd4614; git reset --mixed FETCH_HEAD; git rev-parse HEAD; cat config/.bun-version; env | sort | grep -Ei 'proxy|cdp|browser|coldpass'", "set -e; curl -fsSL https://deb.nodesource.com/setup_24.x | sudo -E bash -; sudo -n apt-get install -y nodejs; corepack enable; corepack prepare --activate; curl -fsSL https://bun.sh/install | bash;", "sudo -n corepack enable; corepack prepare --activate; curl -fsSL https://bun.sh/install | bash; node --version; pnpm --version; --version; cat config/.bun-version", "sudo -n apt-get install -y unzip; curl -fsSL https://bun.sh/install | bash; --version", "false", "export PATH=; export NODE_USE_ENV_PROXY=1; export CI=1; pnpm install", "sudo -n apt-get install -y build-essential python3 make g++ pkg-config libsecret-1-dev libx11-dev; export PATH=; export NODE_USE_ENV_PROXY=1; export CI=1; pnpm install", "sudo -n apt-get install -y libgtk-3-0t64 libnss3 libxss1 libasound2t64 libxtst6 libx11-xcb1 libxkbfile1 libnotify4 libgbm1 libdrm2 libxshmfence1 libxrandr2 libxdamage1 libxcomposite1 libxfixes3 libxrender1 libxext6 libglib2.0-0t64 libatk1.0-0t64 libcups2t64 libdbus-1-3 libpango-1.0-0 libatk-bridge2.0-0t64 libatspi2.0-0t64 libxkbcommon0 libxkbcommon-x11-0 xvfb; export PATH=; export NODE_USE_ENV_PROXY=1; export ORCA_BACKGROUND_LAUNCH=1; export ORCA_DEV_MAIN_SOURCEMAPS=0; pnpm dev > 2>&1 & echo $! > ; sleep 50; cat ; ps -p $(cat ) -o pid,stat,cmd; find /tmp -maxdepth 3 -iname '*cdp*' -o -iname '*browser*' | head -40", "cat ; ps aux | grep -E 'electron|orca|vite' | grep -v grep; curl -sS http://127.0.0.1:9371/json/list || true; find -maxdepth 3 -type f | grep -Ei 'cdp|browser' | head -50; mkdir -p .coldpass", "tail -80 ; ps -ef | grep -E 'electron|electron-vite|vite.*dev' | grep -v grep; curl -sS --max-time 3 http://127.0.0.1:9371/json/list; ls -l ", "ps -ef | grep -E 'electron|electron-vite|vite.*dev' | grep -v grep; tail -25 ; ls -l out/main out/preload out/renderer 2>/dev/null; find out -maxdepth 2 -type f | head", "find -maxdepth 2 -type f -printf '%p %s\\n' | head -30; pgrep -af electron; pgrep -af 'pnpm dev|run-electron-vite-dev'", "sed -n '1,240p' config/scripts/run-electron-vite-dev.mjs; sed -n '1,160p' electron.vite.config.ts", "kill -TERM 11631 11933 12082 12090 2>/dev/null || true; pgrep -af 'electron-vite|pnpm dev' | grep -v coldpass || true; mkdir -p .coldpass; python3 - <<'PY'\nimport json\nroot=''\njson.dump({\"kind\":\"cli\",\"argv\":[\"pnpm\",\"dev\"],\"cwd\":root,\"env\":{\"PATH\":\"\",\"NODE_USE_ENV_PROXY\":\"1\",\"ORCA_BACKGROUND_LAUNCH\":\"1\",\"ORCA_DEV_MAIN_SOURCEMAPS\":\"0\"},\"checks\":[{\"check\":\"install\",\"argv\":[\"pnpm\",\"install\"],\"cwd\":root,\"expected_text\":\"Done in 33.2s using pnpm v12.14.0\"},{\"check\":\"start\",\"argv\":[\"pnpm\",\"dev\"],\"cwd\":root,\"expected_text\":\"Remote debugging on http://127.0.0.1:9371\"},{\"check\":\"credentials_error\",\"argv\":[\"pnpm\",\"dev\"],\"cwd\":root,\"expected_text\":\"command exceeded the attempt ceiling\"}]},open(root+'/.coldpass/probe.json','w'),indent=2)\njson.dump([{\"kind\":\"claim\",\"claim\":\"Orca is an AI orchestrator for parallel agents in worktrees.\",\"source\":\"Run Codex, ClaudeCode, OpenCode or Pi side-by-side \u2014 each in its own worktree, tracked in one place.\",\"testable\":False,\"reason\":\"The documented desktop app launch started compilation but did not produce the app process or CDP endpoint during the observed attempt; no UI result was available.\"}],open(root+'/.coldpass/claims.json','w'),indent=2)\njson.dump([],open(root+'/.coldpass/examples.json','w'),indent=2)\njson.dump({\"detected\":False,\"reason\":\"Inspected README and documented desktop entry points; no product scheduling or recurring cycle described. Orca is launched as an interactive desktop application.\",\"checks\":[]},open(root+'/.coldpass/cycles.json','w'),indent=2)\nPY\nmkdir -p .coldpass", "= python3 -I --validate --replay; ls -l /inputs/coldpass-preflight.py 2>/dev/null", "python3 - <<'PY'\nimport json\np='.coldpass/probe.json'; d=json.load(open(p)); d['kind']='cli'; d.pop('checks',None); d['stays_running']=True; d['expected_text']='Remote debugging on http://127.0.0.1:9371'; json.dump(d,open(p,'w'),indent=2)\nPY\n= python3 -I --validate --replay", "python3 - <<'PY'\nimport json\np='.coldpass/report.json'\nr={\"outcome\":\"blocked\",\"fault_owner\":\"prerequisite\",\"operation\":\"pnpm dev\",\"operation_scope\":\"Documented Orca desktop development launch on Linux, with Node 24, pnpm 12.14.0, Bun 1.4.4, and Linux desktop runtime libraries installed.\",\"steps\":[\"Initialized Git metadata and fetched/reset to 2847bbe9e81ea8d94f0e42560aa981b3fccd4614.\",\"Installed Node 24.22.1, pnpm 12.14.0, Bun 1.4.4, Python 3.12.3, native build tools, and Electron runtime libraries.\",\"Ran pnpm install successfully.\",\"Ran documented pnpm dev with ORCA_BACKGROUND_LAUNCH=1; compilation completed, but no Electron process or CDP endpoint became available.\"],\"deviations\":[\"Initial pnpm install failed because native node-pty compilation could not find make; installing build-essential and development headers resolved it.\",\"Bun installer initially reported missing unzip; installed unzip and Bun successfully.\",\"Documented app launch output included Remote debugging on http://127.0.0.1:9371, but polling found no listener and electron-vite remained compiling; no real UI operation could be checked.\"],\"stuck_step\":\"Launch/render the desktop app and check a useful UI action through CDP.\",\"main_blocker\":\"After dependencies and Electron runtime packages were installed, pnpm dev stalled during electron-vite build; it emitted no desktop process, and the advertised CDP endpoint refused connections.\",\"plain_failure\":\"The app dependencies installed, but the development launch did not finish starting Orca, so its desktop behavior could not be exercised.\",\"suggested_fix\":\"Investigate why electron-vite development compilation does not progress beyond transforming 8629 modules in this guest, then rerun pnpm dev and verify the app through the configured CDP endpoint.\"}\njson.dump(r,open(p,'w'),indent=2)\nPY\n= python3 -I --validate --replay" ], "stuck_step": "Launch/render the desktop app and check a useful UI action through CDP.", "error_excerpt": "After dependencies and Electron runtime packages were installed, pnpm dev stalled during electron-vite build; it emitted no desktop process, and the advertised CDP endpoint refused connections.", "what_it_did": "pnpm dev", "suggested_fix": "Investigate why electron-vite development compilation does not progress beyond transforming 8629 modules in this guest, then rerun pnpm dev and verify the app through the configured CDP endpoint.", "tokens_in": 1198521, "tokens_out": 3550, "cost_usd": null, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": false, "argv": [ "pnpm", "dev" ], "kind": "cli", "returncode": 0, "stdout": "$ pnpm run build:packages && pnpm run ensure:electron-runtime && node config/scripts/run-electron-vite-dev.mjs\n$ pnpm --filter @orca/process-host build\n$ tsx --conditions=orca-source scripts/build-dist.mjs\n$ node config/scripts/ensure-native-runtime.mjs --runtime=electron\n[orca-dev] Prepared wrapper in \n[orca-dev] Instance: workspace @ master\n[orca-dev] Background launch: window stays off screen; automate through CDP\n[orca-dev] Remote debugging on http://127.0.0.1:9371\n[orca-dev] Web client bundle missing; skipping pairing web build. Run `pnpm run build:web` or set ORCA_DEV_WEB_PREPARE=1 when you need browser pairing.", "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 encoded execution, 258 hardcoded secret, 7 known vulnerability, 1 outside write. 48 static matches retained as context.", "findings": [ { "kind": "connection-review", "count": 1, "note": "Repository processes attempted these non-loopback connections; proxies can hide the final hostname.", "location_count": 13, "process_count": 7 }, { "kind": "encoded-execution", "count": 1, "note": "Source contains encoded execution; review its purpose.", "location_count": 1, "path": "src/main/wsl-bash-command.ts" }, { "kind": "hardcoded-secret", "count": 238, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 70 }, { "kind": "known-vulnerability", "count": 7, "note": "OSV reports a known vulnerability in this dependency version.", "location_count": 3 }, { "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": "10302", "source": "" } ] } ], "context": [ { "kind": "download-and-execute", "count": 2, "note": "Source contains download and execute; review its purpose.", "location_count": 2 }, { "kind": "encoded-blob", "count": 2, "note": "Source contains encoded blob; review its purpose.", "location_count": 2 }, { "kind": "encoded-execution", "count": 2, "note": "Source contains encoded execution; review its purpose.", "location_count": 2 }, { "kind": "hardcoded-secret", "count": 41, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 27 } ], "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=stablyai--orca-gpt-6-luna-1792788872369838558", "evidence_file": "/data/safety/stablyai--orca-gpt-6-luna-1792788872369838558.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": 21, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "2847bbe9e81ea8d94f0e42560aa981b3fccd4614", "url": "https://github.com/stablyai/orca" }, "purpose": "initial", "profile": { "model": "gpt-6-luna", "reasoning": "low" }, "fault": { "owner": "prerequisite", "status": "diagnosed", "reason": "After dependencies and Electron runtime packages were installed, pnpm dev stalled during electron-vite build; it emitted no desktop process, and the advertised CDP endpoint refused connections." }, "fix_id": null, "verifies_run_id": null, "hosting": null, "operation_scope": "product operation", "tool_calls": 21, "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/stablyai/orca", "cost_to_try": null, "hardware": null, "what_failed": "After dependencies and Electron runtime packages were installed, pnpm dev stalled during electron-vite build; it emitted no desktop process, and the advertised CDP endpoint refused connections.", "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 and documented desktop entry points; no product scheduling or recurring cycle described. Orca is launched as an interactive desktop application.", "evidence": "Inspected README and documented desktop entry points; no product scheduling or recurring cycle described. Orca is launched as an interactive desktop application.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "Orca is an AI orchestrator for parallel agents in worktrees.", "source": "Run Codex, ClaudeCode, OpenCode or Pi side-by-side \u2014 each in its own worktree, tracked in one place.", "input": "", "expected": "", "command": "", "verdict": "blocked", "outcome": "The documented desktop app launch started compilation but did not produce the app process or CDP endpoint during the observed attempt; no UI result was available.", "evidence": "The documented desktop app launch started compilation but did not produce the app process or CDP endpoint during the observed attempt; no UI result was available.", "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [], "does_what_it_says": null, "maintenance": { "archived": false, "commits_90d": 8670, "last_commit_at": "2026-10-23T20:15:45Z", "last_release_at": "2026-10-21T07:25:23Z", "median_reply_hours": null, "merged_prs_90d": 8732, "note": "actively maintained: last commit 0 days ago; 8670 commits and 8732 merged PRs in 90 days; 4420 open issues, 4377 open PRs; latest release 2026-10-21", "open_issues": 4420, "open_prs": 4377, "reply_share": null, "reply_threads": 0, "verdict": "maintained" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 0 days ago; 8670 commits and 8732 merged PRs in 90 days; 4420 open issues, 4377 open PRs; latest release 2026-10-21", "maintained": "active", "maintained_note": "last commit 0 days ago; 3 open issues, 0 answered or closed", "last_commit_at": "2026-10-23T20:18:25Z", "last_release_at": "2026-10-21T07:25:23Z", "open_issues": 3, "answered_issues": 0, "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": "2026-10-23T21:07:19.174376+00:00", "tested_commit": "2847bbe9e81ea8d94f0e42560aa981b3fccd4614", "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": "stablyai/orca", "source": "https://github.com/stablyai/orca", "commit": "2847bbe9e81ea8d94f0e42560aa981b3fccd4614", "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": "2847bbe9e81ea8d94f0e42560aa981b3fccd4614", "url": "https://github.com/stablyai/orca" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "pnpm dev", "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/stablyai--orca-gpt-6-luna-1792788872369838558.json" }