{ "run_id": "lucasmartins-ai--lookacrawler-claude-haiku-5-5-1793112925327966549", "date": "2026-10-27T14:58:39.251505+00:00", "repo": "lucasmartins-ai/lookacrawler", "kind": "mcp", "source": "https://github.com/lucasmartins-ai/lookacrawler", "commit": "bc5ce110f8b52b00a474343105c40c0de0d86fb9", "model": "claude-haiku-5-5", "model_version": "claude-haiku-5-5", "test_version": "readme-d5b140d3c0f8b95c2dd6fe6fc381a303cacb92679582c22317d8e78b572f0cf2", "pass": true, "outcome": "pass", "time_to_working_s": 155.30855936800072, "total_s": 193.92343878746033, "steps": [ "pwd; ls -la; id -u; python3 --version; cat README.md 2>/dev/null | head -c 6000; echo; echo CDP=$CDP_URL; curl -s -m 10 -i $CDP_URL/json/version | head -20", "cd ; sed -n '1,400p' README.md | tail -c +6000 | head -c 7500", "cd ; cat package.json; ls .coldpass; which bun node npm; ls .github/workflows 2>/dev/null; git status 2>&1 | head -2", "node --version; npm --version; (curl -fsSL https://bun.sh/install | bash) 2>&1 | tail -5; ls ~/.bun/bin 2>/dev/null", "export PATH=$HOME/.bun/bin:$PATH; bun --version; cd && bun install 2>&1 | tail -15", "export PATH=$HOME/.bun/bin:$PATH; cd && timeout 120 bun run cli.ts extract https://example.com --mode fast 2>&1 | head -40; echo EXIT=${PIPESTATUS[0]}", "export PATH=$HOME/.bun/bin:$PATH; cd && timeout 600 bun test 2>&1 | tail -15", "cd ; grep -n \"registerTool\\|server.tool(\" index.ts | head -30; grep -n -A12 \"name: \\\"extract_web_content\\\"\\|'extract_web_content'\\|\\\"extract_web_content\\\"\" index.ts | head -40", "cd ; sed -n 50,75p index.ts", "echo HOME=$HOME; command -v bun; cd ; export PATH=$HOME/.bun/bin:$PATH; { echo '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"initialize\",\"params\":{\"protocolVersion\":\"2024-11-05\",\"capabilities\":{},\"clientInfo\":{\"name\":\"t\",\"version\":\"1\"}}}'; echo '{\"jsonrpc\":\"2.0\",\"method\":\"notifications/initialized\"}'; echo '{\"jsonrpc\":\"2.0\",\"id\":2,\"method\":\"tools/call\",\"params\":{\"name\":\"extract_web_content\",\"arguments\":{\"url\":\"https://example.com\",\"mode\":\"fast\"}}}'; } | timeout 120 bun run index.ts 2>/dev/null | tail -c 1200", "ls -la ; cd ; grep -rn -i \"setInterval\\|cron\\|--once\\|--now\\|schedule\" --include=*.ts . | grep -v node_modules | grep -v test | head -20; grep -n -i \"cron\\|schedul\\|--once\\|webhook\" README.md | head", "cd ; B=; timeout 120 $B run cli.ts intent \"Procuro um sof\u00e1 at\u00e9 R$ 2.500\" 2>&1 | head -c 1500; echo; echo ---; timeout 120 $B run cli.ts antislop \"No cen\u00e1rio atual, uma solu\u00e7\u00e3o revolucion\u00e1ria\" 2>&1 | head -c 1500; echo; echo ---; timeout 200 $B run cli.ts map https://example.com --max-urls 5 2>&1 | head -c 1200; echo EXIT=$?", "cd && cat > claims.json <<'EOF'\n[\n {\"kind\":\"claim\",\"claim\":\"CLI extracts a page to Markdown\",\"source\":\"bun run cli.ts extract https://news.ycombinator.com --mode fast\",\"input\":\"https://example.com\",\"expected\":\"Markdown text of the page\",\"probe_kind\":\"cli\",\"argv\":[\"\",\"run\",\"cli.ts\",\"extract\",\"https://example.com\",\"--mode\",\"fast\"],\"stdin\":\"\",\"expected_text\":\"documentation examples\",\"cwd\":\"\",\"env\":{}},\n {\"kind\":\"claim\",\"claim\":\"MCP server exposes extract_web_content tool\",\"source\":\"**Tools:** `extract_web_content`, `crawl_website`, `map_website`\",\"input\":\"https://example.com\",\"expected\":\"Markdown text returned by the tool\",\"probe_kind\":\"mcp\",\"argv\":[\"\",\"run\",\"index.ts\"],\"tool\":\"extract_web_content\",\"arguments\":{\"url\":\"https://example.com\",\"mode\":\"fast\"},\"expected_text\":\"documentation examples\",\"cwd\":\"\",\"env\":{}},\n {\"kind\":\"claim\",\"claim\":\"CLI scores buying intent of a text\",\"source\":\"bun run cli.ts intent \\\"Procuro um sof\u00e1 at\u00e9 R$ 2.500\\\"\",\"input\":\"Procuro um sof\u00e1 at\u00e9 R$ 2.500\",\"expected\":\"JSON with isLead true\",\"probe_kind\":\"cli\",\"argv\":[\"\",\"run\",\"cli.ts\",\"intent\",\"Procuro um sof\u00e1 at\u00e9 R$ 2.500\"],\"stdin\":\"\",\"expected_text\":\"\\\"isLead\\\": true\",\"cwd\":\"\",\"env\":{}}\n]\nEOF\npython3 -I -c \"import json;json.load(open('claims.json'));print('ok')\"", "cd && cat > probe.json <<'EOF'\n{\"kind\":\"mcp\",\"argv\":[\"\",\"run\",\"index.ts\"],\"cwd\":\"\",\"tool\":\"extract_web_content\",\"arguments\":{\"url\":\"https://example.com\",\"mode\":\"fast\"},\"expected_text\":\"documentation examples\",\"env\":{}}\nEOF\ncat > examples.json <<'EOF'\n[\n {\"kind\":\"example\",\"claim\":\"Extract a page to Markdown from the CLI\",\"source\":\"README.md: Quick Start & CLI Usage\",\"input\":\"https://example.com --mode fast\",\"expected\":\"Markdown text of the page\",\"argv\":[\"\",\"run\",\"cli.ts\",\"extract\",\"https://example.com\",\"--mode\",\"fast\"],\"cwd\":\"\",\"env\":{},\"expected_text\":\"documentation examples\"},\n {\"kind\":\"example\",\"claim\":\"Discover sitemaps for a domain\",\"source\":\"README.md: Quick Start & CLI Usage\",\"input\":\"https://example.com --max-urls 5\",\"expected\":\"JSON listing the host and sitemaps found\",\"argv\":[\"\",\"run\",\"cli.ts\",\"map\",\"https://example.com\",\"--max-urls\",\"5\"],\"cwd\":\"\",\"env\":{},\"expected_text\":\"https://example.com/sitemap.xml\"},\n {\"kind\":\"example\",\"claim\":\"Lint copy for AI slop\",\"source\":\"README.md: Quick Start & CLI Usage\",\"input\":\"No cen\u00e1rio atual, uma solu\u00e7\u00e3o revolucion\u00e1ria\",\"expected\":\"JSON with isSlop true\",\"argv\":[\"\",\"run\",\"cli.ts\",\"antislop\",\"No cen\u00e1rio atual, uma solu\u00e7\u00e3o revolucion\u00e1ria\"],\"cwd\":\"\",\"env\":{},\"expected_text\":\"\\\"isSlop\\\": true\"}\n]\nEOF\ncat > cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"Entry points inspected (cli.ts, index.ts, package.json scripts, README). No cron, scheduler, --once/--now, or webhook loop is documented. The only long-running items are the MCP stdio/SSE server (serve) and the Maps daemon (daemon start), which are request servers rather than scheduled cycles. setInterval in browser-manager.ts is an idle browser sweeper, not a product cycle.\",\"checks\":[]}\nEOF\nfor f in probe.json examples.json cycles.json; do python3 -I -c \"import json,sys;json.load(open('$f'));print('$f ok')\"; done", "cd && cat > report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Run the LookaCrawler CLI extract command and the extract_web_content MCP tool against a real page\",\"operation_scope\":\"Pinned commit bc5ce110f8b52b00a474343105c40c0de0d86fb9 in a fresh Ubuntu VM; Bun 1.4.4 runtime; public internet access to example.com. Google Maps engine (maps/gtm/intel/daemon) not built and not exercised.\",\"steps\":[\"curl -fsSL https://bun.sh/install | bash\",\"bun install (in )\",\"bun run cli.ts extract https://example.com --mode fast\",\"bun test (372 tests: 369 pass, 3 skip, 0 fail)\",\"bun run index.ts (stdio MCP) tools/call extract_web_content {url: https://example.com}\"],\"deviations\":[\"README says Bun 1.1+ but does not name an installer; installed Bun 1.4.4 with the official bun.sh install script (curl|sh), which put bun in ; bun was not on PATH so saved argv uses that absolute path.\",\"Workspace is not a git repository; no git metadata was needed for the operation.\",\"Maps engine (go build, build:maps) skipped: not required for extract/CLI/MCP operations and needs Go 1.26+.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":\"None for the tested operations. Note: bun is not on PATH after the curl installer; add it to PATH or use an absolute path.\"}\nEOF\npython3 -I -c \"import json;json.load(open('report.json'));print('ok')\"; cd && = python3 -I --validate --replay 2>&1 | tail -60" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Run the LookaCrawler CLI extract command and the extract_web_content MCP tool against a real page", "suggested_fix": null, "tokens_in": 320324, "tokens_out": 8887, "cost_usd": 0.0138653, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "", "run", "index.ts" ], "kind": "mcp", "serverInfo": { "name": "lookacrawler", "version": "1.1.2" }, "tools": [ "extract_web_content", "batch_extract_web_content", "extract_structured_data", "map_website", "crawl_website", "extract_contacts", "search_places", "discover_local_leads", "deep_enrich_lead", "lint_anti_slop", "lookup_social_profile", "search_social_intent", "audit_company_website", "analyze_competitors", "generate_growth_plan", "gtm_pipeline_run" ], "tool_schema_bytes": 20651, "tool_result": { "content": [ { "type": "text", "text": "> [!NOTE] This content was retrieved from local cache.\n\nThis domain is for use in documentation examples without needing permission. This is not a service; avoid relying on it for testing and monitoring purposes." } ] }, "tool_result_checked": true, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 1 connection review, 93 known vulnerability, 1 sensitive read.", "expected": "Reviewed as expected for a test run: attempted writes that failed, so nothing was written; 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": 25, "process_count": 7 }, { "kind": "known-vulnerability", "count": 93, "note": "OSV reports a known vulnerability in this dependency version.", "location_count": 15 }, { "kind": "sensitive-read", "count": 1, "note": "A repository process attempted to read this sensitive path.", "location_count": 1, "file_kind": "package registry login", "process_count": 1, "processes": [ { "created_in_run": false, "executable": "", "owner": "repo", "path": "", "pid": "2064", "source": "", "succeeded": false, "syscall": "openat", "trace": "5.trace" } ] } ], "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=lucasmartins-ai--lookacrawler-claude-haiku-5-5-1793112925327966549", "evidence_file": "/data/safety/lucasmartins-ai--lookacrawler-claude-haiku-5-5-1793112925327966549.json.gz" }, "agent_execution": "native_agent", "agent_runtime": "claude-code", "agent_runtime_version": "2.1.310 (Claude Code)", "tool_transport": "mcp-assigned-vm", "platform": "linux", "reasoning": "low", "service_tier": null, "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": "bc5ce110f8b52b00a474343105c40c0de0d86fb9", "url": "https://github.com/lucasmartins-ai/lookacrawler" }, "purpose": "initial", "profile": { "model": "claude-haiku-5-5", "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": "local", "needs": [], "needs_which": null, "agent_interface": [ "mcp" ], "license": "MIT", "repo_url": "https://github.com/lucasmartins-ai/lookacrawler", "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": "Entry points inspected (cli.ts, index.ts, package.json scripts, README). No cron, scheduler, --once/--now, or webhook loop is documented. The only long-running items are the MCP stdio/SSE server (serve) and the Maps daemon (daemon start), which are request servers rather than scheduled cycles. setInterval in browser-manager.ts is an idle browser sweeper, not a product cycle.", "evidence": "Entry points inspected (cli.ts, index.ts, package.json scripts, README). No cron, scheduler, --once/--now, or webhook loop is documented. The only long-running items are the MCP stdio/SSE server (serve) and the Maps daemon (daemon start), which are request servers rather than scheduled cycles. setInterval in browser-manager.ts is an idle browser sweeper, not a product cycle.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "CLI extracts a page to Markdown", "source": "bun run cli.ts extract https://news.ycombinator.com --mode fast", "input": "https://example.com", "expected": "Markdown text of the page", "command": " run cli.ts extract https://example.com --mode fast", "verdict": "yes", "outcome": "Real input produced the expected result: documentation examples", "evidence": "documentation examples without needing permission. This is not a service; avoid relying on it for testing and monitoring purposes.\n", "returncode": 0, "source_checked": true, "source_file": "README.md" }, { "kind": "claim", "claim": "MCP server exposes extract_web_content tool", "source": "**Tools:** `extract_web_content`, `crawl_website`, `map_website`", "input": "{\"tool\": \"extract_web_content\", \"arguments\": {\"url\": \"https://example.com\", \"mode\": \"fast\"}}", "expected": "Markdown text returned by the tool", "command": " run index.ts tools/call {\"tool\": \"extract_web_content\", \"arguments\": {\"url\": \"https://example.com\", \"mode\": \"fast\"}}", "verdict": "yes", "outcome": "Real input produced the expected result: documentation examples", "evidence": "documentation examples without needing permission. This is not a service; avoid relying on it for testing and monitoring purposes.\"}]}", "source_checked": true, "source_file": "README.md" }, { "kind": "claim", "claim": "CLI scores buying intent of a text", "source": "bun run cli.ts intent \"Procuro um sof\u00e1 at\u00e9 R$ 2.500\"", "input": "Procuro um sof\u00e1 at\u00e9 R$ 2.500", "expected": "JSON with isLead true", "command": " run cli.ts intent 'Procuro um sof\u00e1 at\u00e9 R$ 2.500'", "verdict": "yes", "outcome": "Real input produced the expected result: \"isLead\": true", "evidence": "\"isLead\": true,\n \"score\": 85,\n \"matched\": [\n \"procuro\"\n ],\n \"region\": null,\n \"budget\": 2500\n}\n", "returncode": 0, "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Extract a page to Markdown from the CLI", "source": "README.md: Quick Start & CLI Usage", "input": "https://example.com --mode fast", "command": " run cli.ts extract https://example.com --mode fast", "evidence": "This domain is for use in documentation examples without needing permission. This is not a service; avoid relying on it for testing and monitoring purposes.", "deferred": false, "expected": "Markdown text of the page", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" }, { "kind": "example", "claim": "Discover sitemaps for a domain", "source": "README.md: Quick Start & CLI Usage", "input": "https://example.com --max-urls 5", "command": " run cli.ts map https://example.com --max-urls 5", "evidence": "{\n \"host\": \"example.com\",\n \"sitemapsFound\": [\n \"https://example.com/sitemap.xml\"\n ],\n \"totalDiscovered\": 0,\n \"urls\": []\n}", "deferred": false, "expected": "JSON listing the host and sitemaps found", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" }, { "kind": "example", "claim": "Lint copy for AI slop", "source": "README.md: Quick Start & CLI Usage", "input": "No cen\u00e1rio atual, uma solu\u00e7\u00e3o revolucion\u00e1ria", "command": " run cli.ts antislop 'No cen\u00e1rio atual, uma solu\u00e7\u00e3o revolucion\u00e1ria'", "evidence": "ed_word\",\n \"matched\": \"No cen\u00e1rio atual\",\n \"rule\": \"Abertura clich\u00ea de IA (throat-clearing)\",\n \"suggestion\": \"V\u00e1 direto ao ponto ou ao fato concreto\",\n \"index\": 0\n },\n {\n \"category\": \"banned_word\",\n \"matched\": \"revolucion\u00e1ria\",\n \"rule\": \"Hip\u00e9rbole vazia sem dados comprobat\u00f3rios\",\n \"suggestion\": \"Descreva o resultado espec\u00edfico em n\u00fameros ou tempo economizado\",\n \"index\": 30\n }\n ],\n \"metrics\": {\n \"wordCount\": 6,\n \"concreteNumbersCount\": 0,\n \"sentencesCount\": 1,\n \"averageSentenceLength\": 6,\n \"hasConcreteGrounding\": false\n }\n}", "deferred": false, "expected": "JSON with isSlop true", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": "yes", "maintenance": { "last_commit_at": "2026-10-19T23:21:27Z", "commits_90d": 47, "merged_prs_90d": 19, "open_issues": 1, "open_prs": 2, "reply_share": 0.1, "reply_threads": 10, "median_reply_hours": 161.8, "last_release_at": "2026-10-11T06:48:28Z", "archived": false, "verdict": "maintained", "note": "actively maintained: last commit 7 days ago; 47 commits and 19 merged PRs in 90 days; 1 open issues, 2 open PRs; 1 of 10 recent threads got a maintainer reply, median first reply 161.8h; latest release 2026-10-11" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 7 days ago; 47 commits and 19 merged PRs in 90 days; 1 open issues, 2 open PRs; 1 of 10 recent threads got a maintainer reply, median first reply 161.8h; latest release 2026-10-11", "maintained": "active", "maintained_note": "last commit 7 days ago; 1 open issues, 1 answered or closed", "last_commit_at": "2026-10-19T23:21:29Z", "last_release_at": "2026-10-11T06:48:28Z", "open_issues": 1, "answered_issues": 1, "platforms_claimed": [ "linux" ], "topic": "mcp-server", "agent_interfaces": [ { "interface": "mcp", "evidence": "independent checker", "observed": true, "operation_checked": true }, { "interface": "cli", "evidence": "README metadata", "observed": false, "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": { "tool_count": 16, "schema_bytes": 20651, "tokens_approx": 5163, "estimate_method": "ceil(compact UTF-8 tools/list JSON bytes / 4)", "scope": "returned tools/list page only; excludes client framing and tool results" }, "tested_at": "2026-10-27T14:58:39.251505+00:00", "tested_commit": "bc5ce110f8b52b00a474343105c40c0de0d86fb9", "tested_with": { "agent": "claude-code", "agent_version": "2.1.310 (Claude Code)", "model": "claude-haiku-5-5", "model_route": "claude-haiku-5-5", "reasoning": "low", "os": "linux", "backend": "hyperv", "transport": "mcp-assigned-vm" }, "setup_identity": { "repo": "lucasmartins-ai/lookacrawler", "source": "https://github.com/lucasmartins-ai/lookacrawler", "commit": "bc5ce110f8b52b00a474343105c40c0de0d86fb9", "source_revision": null, "os": "linux", "architecture": null, "backend": "hyperv", "model": "claude-haiku-5-5", "model_version": "claude-haiku-5-5", "agent_execution": "native_agent", "agent_runtime": "claude-code", "agent_runtime_version": "2.1.310 (Claude Code)", "tool_transport": "mcp-assigned-vm", "runtime": null, "runtime_version": null, "runtime_revision": null, "sandbox_source": null, "guest_setup": null, "source_pin": { "commit": "bc5ce110f8b52b00a474343105c40c0de0d86fb9", "url": "https://github.com/lucasmartins-ai/lookacrawler" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": null, "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Run the LookaCrawler CLI extract command and the extract_web_content MCP tool against a real page", "operation_scope": "product operation", "hosting": null, "kind": "mcp", "test_version": "readme-d5b140d3c0f8b95c2dd6fe6fc381a303cacb92679582c22317d8e78b572f0cf2", "evidence_version": null }, "other_model": null, "other_run_id": null, "models_agree": null, "furthest_model": null, "transcript_url": "/transcripts/lucasmartins-ai--lookacrawler-claude-haiku-5-5-1793112925327966549.txt", "report_url": "/reports/lucasmartins-ai--lookacrawler-claude-haiku-5-5-1793112925327966549.json" }