{ "run_id": "langflow-ai--langflow-gpt-6-luna-1792852522388067991", "date": "2026-10-24T15:19:43.804462+00:00", "repo": "langflow-ai/langflow", "kind": "repo", "source": "https://github.com/langflow-ai/langflow", "commit": "aeb10d96bb2ea797696613af931e91ddf51f3320", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "test_version": "readme-20cd1bc4ab0be6730266a08d7400e342dd7d403c08aabf42aab2e51dc9b34ce0", "pass": null, "outcome": "unverified", "time_to_working_s": null, "total_s": 2661.416371822357, "steps": [ "pwd; rg --files -g 'README*' -g 'AGENTS.md' -g 'pyproject.toml' -g 'package.json' -g 'uv.lock' -g 'requirements*.txt' -g '.github/workflows/**' | head -100; git status --short --branch; python3 --version; id -u; vault-search 'langflow README setup MCP probe' 2>&1 | head -80; cat 2>&1 | head -80", "find .. -name AGENTS.md -o -iname 'README*' | head -100; ls -la | head -60", "cat AGENTS.md; cat README.md", "grep -n -E 'run_cli|make init|uv|langflow run|MCP|flow' Makefile README.md | head -80; command -v uv || true; command -v make; ls -la .coldpass; sed -n '1,100p' Makefile", "sed -n '240,265p' Makefile; command -v node || true; npm --version 2>&1; command -v sudo; sudo -n true 2>&1; ls /inputs/coldpass-preflight.py 2>&1; cat .env.example | head -20", "sudo -n apt-get update && sudo -n apt-get install -y curl make; curl -LsSf https://astral.sh/uv/install.sh | sh; ls -la 2>/dev/null; cat pyproject.toml | head -35", "sudo -n apt-get install -y nodejs npm; node --version 2>&1; npm --version 2>&1", "node --version; npm --version;", "curl -fsSL https://nodejs.org/dist/index.tab | head -2", "sudo -n npm install -g n; sudo -n n 22.12.0; node --version; npm --version", "make run_cli host=127.0.0.1 port=7860 open_browser=false", "sed -n '1,45p' Makefile.frontend; sed -n '1,70p' src/frontend/package.json; ls src/frontend | head; cd src/frontend && npm ci", "cd src/frontend && PUPPETEER_SKIP_DOWNLOAD=1 npm ci", "make run_cli host=127.0.0.1 port=7860 open_browser=false", "cat ; ls ;", "PATH= make run_cli host=127.0.0.1 port=7860 open_browser=false", "curl -fsSL https://nodejs.org/dist/index.tab | head -25", "sudo -n n 22.13.0; node --version;", "NODE_OPTIONS=--max-old-space-size=4096 PATH= make run_cli host=127.0.0.1 port=7860 open_browser=false", "find src/backend/base/langflow/frontend -maxdepth 2 -type f | head; ls src/frontend/build 2>/dev/null; rg -n 'list_flows|/api/v1/flows|GET.*flows' src/backend/base/langflow/api", "PATH= LANGFLOW_AUTO_LOGIN=true uv run langflow run --host 127.0.0.1 --port 7860 --no-open-browser > /tmp/lf.log 2>&1 & echo $! > /tmp/lf.pid; for i in $(seq 1 90); do curl -sS http://127.0.0.1:7860/api/v1/flows/ > /tmp/flowresponse && break; sleep 2; done; cat /tmp/lf.log; head -c 1500 /tmp/flowresponse; kill $(cat /tmp/lf.pid) 2>/dev/null || true; pkill -f 'langflow run' || true", "cat /tmp/lf.log 2>&1 | tail -80; cat /tmp/flowresponse 2>&1; ps aux | grep '[l]angflow'", "mkdir -p .coldpass; cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"make\",\"run_cli\",\"host=127.0.0.1\",\"port=7860\",\"open_browser=false\"],\"cwd\":\"\",\"env\":{\"PATH\":\"\",\"NODE_OPTIONS\":\"--max-old-space-size=4096\",\"PUPPETEER_SKIP_DOWNLOAD\":\"1\"},\"expected_returncode\":2,\"expected_text\":\"Killed\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Running the source checkout starts Langflow at its local web address.\",\"source\":\"From a fresh directory, run:\\n```shell\\nuv pip install langflow -U\\n```\\nThe latest Langflow package is installed.\\nFor more information, see [Install and run the Langflow OSS Python package](https://docs.langflow.org/get-started-installation#install-and-run-the-langflow-oss-python-package).\\n\\n#### Run\\n\\nOfficial release packages and tagged source archives disable automatic login by default. Set `LANGFLOW_SUPERUSER_PASSWORD` before starting Langflow, then sign in with the username `langflow` (or your configured `LANGFLOW_SUPERUSER`). Development branches retain automatic login by default. See [authentication configuration](https://docs.langflow.org/api-keys-and-authentication#start-a-langflow-server-with-authentication-enabled).\\n\\nTo start Langflow, run:\\n```shell\\nuv run langflow run\\n```\\n\\nLangflow starts at http://127.0.0.1:7860.\",\"input\":\"127.0.0.1:7860\",\"expected\":\"Langflow starts at http://127.0.0.1:7860.\",\"testable\":false,\"reason\":\"make run_cli installed dependencies but its frontend production build was killed by the guest memory limit; the CLI then failed because src/backend/base/langflow/frontend/index.html was not generated\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Run the source checkout using the documented Make target\",\"source\":\"README.md > Other install options > Run from source\",\"input\":\"host=127.0.0.1 port=7860 open_browser=false\",\"expected\":\"Starts the application\",\"argv\":[\"make\",\"run_cli\",\"host=127.0.0.1\",\"port=7860\",\"open_browser=false\"],\"cwd\":\"\",\"env\":{\"PATH\":\"\",\"NODE_OPTIONS\":\"--max-old-space-size=4096\",\"PUPPETEER_SKIP_DOWNLOAD\":\"1\"},\"expected_returncode\":2,\"expected_text\":\"Killed\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"README and product entrypoints inspected: Langflow is an interactive workflow builder/server; no built-in product scheduler cycle is exposed for this documented source launch\",\"checks\":[]}\nEOF\n", "= python3 -I --validate --replay", "python3 - <<'PY'\nimport json\np='.coldpass/claims.json'; d=json.load(open(p)); d[0]['source']='Langflow starts at http://127.0.0.1:7860.'; open(p,'w').write(json.dumps(d,indent=2))\nPY\n= python3 -I --validate --replay", "mkdir -p src/backend/base/langflow/frontend; cp -a src/frontend/build/. src/backend/base/langflow/frontend/ 2>/dev/null || true; ls src/backend/base/langflow/frontend/index.html;", "find src/frontend/build -type f | head -20; df -h /tmp; free -h", "NODE_OPTIONS=--max-old-space-size=3072 PATH= make run_cli host=127.0.0.1 port=7860 open_browser=false > /tmp/make.log 2>&1 & echo $! >/tmp/make.pid; for i in $(seq 1 180); do if curl -fsS http://127.0.0.1:7860/api/v1/flows/ >/tmp/flowresponse 2>/dev/null; then break; fi; sleep 2; done; tail -20 /tmp/make.log; head -c 500 /tmp/flowresponse 2>/dev/null; kill $(cat /tmp/make.pid) 2>/dev/null || true", "mkdir -p .coldpass; python3 - <<'PY'\nimport json\np='.coldpass/probe.json'; x=json.load(open(p)); x['expected_text']='Killed'; open(p,'w').write(json.dumps(x,indent=2))\np='.coldpass/examples.json'; x=json.load(open(p)); x[0]['expected_text']='Killed'; open(p,'w').write(json.dumps(x,indent=2))\np='.coldpass/report.json'; json.dump({'outcome':'blocked','fault_owner':'prerequisite','operation':'make run_cli','operation_scope':'Source checkout install, frontend build, and application launch','steps':['Installed make, uv 0.13.5, Node.js 22.13.0 and npm 10.9.2.','Installed frontend dependencies with PUPPETEER_SKIP_DOWNLOAD=1 to honor the no-browser-download constraint.','Ran README source command make run_cli host=127.0.0.1 port=7860 open_browser=false.'],'deviations':['Frontend builds were killed during Vite rendering/gzip under guest memory constraints despite increasing Node heap.','Checker replay confirmed make run_cli exits 2 with Killed; app launch and useful API call could not proceed.'],'stuck_step':'Frontend production build in make run_cli','main_blocker':'The guest memory limit kills the frontend production build before index.html is generated.','plain_failure':'Langflow could not start because the required frontend bundle build is killed by the guest memory limit.','suggested_fix':'Run make run_cli on a guest with enough memory to complete the Vite production build.'},open(p,'w'),indent=2)\nPY\n= python3 -I --validate --replay" ], "stuck_step": "Frontend production build in make run_cli", "error_excerpt": "The guest memory limit kills the frontend production build before index.html is generated.", "what_it_did": "make run_cli", "suggested_fix": "Run make run_cli on a guest with enough memory to complete the Vite production build.", "tokens_in": 1568341, "tokens_out": 3901, "cost_usd": null, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": false, "argv": [ "make", "run_cli", "host=127.0.0.1", "port=7860", "open_browser=false" ], "kind": "cli", "returncode": 2, "stdout": "Installing frontend dependencies\nInstalling backend dependencies\n==== Starting frontend build ====\nCurrent directory: $(pwd)\nChecking if src/frontend exists...\ntotal 940\ndrwxrwxr-x 12 ubuntu ubuntu 4096 Oct 24 14:55 .\ndrwxrwxr-x 8 ubuntu ubuntu 4096 Oct 24 14:35 ..\n-rw-rw-r-- 1 ubuntu ubuntu 317 Oct 24 14:35 .achecker.yml\n-rw-rw-r-- 1 ubuntu ubuntu 162 Oct 24 14:35 .biomeignore\n-rw-rw-r-- 1 ubuntu ubuntu 24 Oct 24 14:35 .dockerignore\ndrwxrwxr-x 2 ubuntu ubuntu 4096 Oct 24 14:35 .dspy_cache\n[excerpt truncated]", "stderr": "Checked 561 packages in 655ms\nmake: *** [Makefile.frontend:42: build_frontend] Error 1", "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 blob, 1265 hardcoded secret, 148 known vulnerability. 44 static matches retained as context.", "expected": "Reviewed as expected for a test run: apt refreshed its package lists; 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": 16, "process_count": 22 }, { "kind": "encoded-blob", "count": 1, "note": "Source contains encoded blob; review its purpose.", "location_count": 1, "path": "src/frontend/src/utils/styleUtils.ts" }, { "kind": "hardcoded-secret", "count": 1265, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 68 }, { "kind": "known-vulnerability", "count": 142, "note": "OSV reports a known vulnerability in this dependency version.", "location_count": 37 } ], "context": [ { "kind": "hardcoded-secret", "count": 44, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 21 } ], "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=langflow-ai--langflow-gpt-6-luna-1792852522388067991", "evidence_file": "/data/safety/langflow-ai--langflow-gpt-6-luna-1792852522388067991.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": 29, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "aeb10d96bb2ea797696613af931e91ddf51f3320", "url": "https://github.com/langflow-ai/langflow" }, "purpose": "test_rerun", "profile": { "model": "gpt-6-luna", "reasoning": "low" }, "fault": { "owner": "prerequisite", "status": "diagnosed", "reason": "The guest memory limit kills the frontend production build before index.html is generated." }, "fix_id": null, "verifies_run_id": "langflow-ai--langflow-gpt-6-luna-1792799059670329129", "hosting": null, "operation_scope": "product operation", "tool_calls": 29, "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/langflow-ai/langflow", "cost_to_try": null, "hardware": null, "what_failed": "The guest memory limit kills the frontend production build before index.html is generated.", "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 and product entrypoints inspected: Langflow is an interactive workflow builder/server; no built-in product scheduler cycle is exposed for this documented source launch", "evidence": "README and product entrypoints inspected: Langflow is an interactive workflow builder/server; no built-in product scheduler cycle is exposed for this documented source launch", "command": "" } ], "claims": [ { "kind": "claim", "claim": "Running the source checkout starts Langflow at its local web address.", "source": "Langflow starts at http://127.0.0.1:7860.", "input": "127.0.0.1:7860", "expected": "Langflow starts at http://127.0.0.1:7860.", "command": "", "verdict": "blocked", "outcome": "make run_cli installed dependencies but its frontend production build was killed by the guest memory limit; the CLI then failed because src/backend/base/langflow/frontend/index.html was not generated", "evidence": "make run_cli installed dependencies but its frontend production build was killed by the guest memory limit; the CLI then failed because src/backend/base/langflow/frontend/index.html was not generated", "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Run the source checkout using the documented Make target", "source": "README.md > Other install options > Run from source", "input": "host=127.0.0.1 port=7860 open_browser=false", "command": "make run_cli host=127.0.0.1 port=7860 open_browser=false", "evidence": "reStore.ts, dynamic import will not move module into another chunk.\n\n[plugin vite:reporter] \n(!) is dynamically imported by but also statically imported by , dynamic import will not move module into another chunk.\n\ncomputing gzip size...\nKilled\n\nBuild failed! Error output above \u261d\ufe0f\nChecked 561 packages in 1.21s\nmake: *** [Makefile.frontend:42: build_frontend] Error 1", "deferred": false, "expected": "Starts the application", "returncode": 2, "verdict": "no", "outcome": "command exited with code 2" } ], "does_what_it_says": null, "maintenance": { "archived": false, "commits_90d": 1033, "last_commit_at": "2026-10-22T20:37:39Z", "last_release_at": "2026-10-22T21:20:30Z", "median_reply_hours": 15.8, "merged_prs_90d": 904, "note": "actively maintained: last commit 0 days ago; 1033 commits and 904 merged PRs in 90 days; 206 open issues, 1015 open PRs; 5 of 11 recent threads got a maintainer reply, median first reply 15.8h; latest release 2026-10-22", "open_issues": 206, "open_prs": 1015, "reply_share": 0.45, "reply_threads": 11, "verdict": "maintained" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 0 days ago; 1033 commits and 904 merged PRs in 90 days; 206 open issues, 1015 open PRs; 5 of 11 recent threads got a maintainer reply, median first reply 15.8h; latest release 2026-10-22", "maintained": "active", "maintained_note": "last commit 0 days ago; 1 open issues, 2 answered or closed", "last_commit_at": "2026-10-23T19:18:10Z", "last_release_at": "2026-10-22T21:20:30Z", "open_issues": 1, "answered_issues": 2, "platforms_claimed": [ "mac", "windows" ], "topic": "agent-harness", "agent_interfaces": [ { "interface": "mcp", "evidence": "README metadata", "observed": false, "operation_checked": false }, { "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": "2026-10-24T15:19:43.804462+00:00", "tested_commit": "aeb10d96bb2ea797696613af931e91ddf51f3320", "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": "langflow-ai/langflow", "source": "https://github.com/langflow-ai/langflow", "commit": "aeb10d96bb2ea797696613af931e91ddf51f3320", "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": "aeb10d96bb2ea797696613af931e91ddf51f3320", "url": "https://github.com/langflow-ai/langflow" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "make run_cli", "operation_scope": "product operation", "hosting": null, "kind": "repo", "test_version": "readme-20cd1bc4ab0be6730266a08d7400e342dd7d403c08aabf42aab2e51dc9b34ce0", "evidence_version": null }, "transcript_url": null, "report_url": "/reports/langflow-ai--langflow-gpt-6-luna-1792852522388067991.json" }