{ "run_id": "LearningCircuit--local-deep-research-claude-haiku-5-5-1792761300474358264", "date": "2026-10-23T13:33:41.129117+00:00", "repo": "LearningCircuit/local-deep-research", "kind": "mcp", "source": "https://github.com/LearningCircuit/local-deep-research", "commit": "7c274b6f72355aeef9ef1a51396363414307534f", "model": "claude-haiku-5-5", "model_version": "claude-haiku-5-5", "test_version": "readme-bdc1b9b3c0d2673aef87e076d14084a8123ddcf09d520c1ee2e364a37c3f4bb9", "pass": true, "outcome": "pass", "time_to_working_s": 1017.3170533409575, "total_s": 1120.6547272205353, "steps": [ "cd && pwd && ls -la && id -u && python3 --version && cat /etc/os-release | head -3 && (git -C . rev-parse HEAD 2>&1 | head -1)", "cd && ls -la; test -f README.md && wc -l README.md && sed -n 1,200p README.md", "cd && sed -n 200,640p README.md | grep -n -i -E 'install|pip|python|run|\\$ |```|cli|--|pytest|test' | head -120; echo ---; grep -n -E 'requires-python|^version' pyproject.toml; cat .nvmrc", "cd && git init -q 2>&1; git remote add origin https://github.com/LearningCircuit/local-deep-research 2>&1; timeout 300 git fetch --depth 1 origin 7c274b6f72355aeef9ef1a51396363414307534f 2>&1 | tail -5; git reset --mixed FETCH_HEAD 2>&1 | tail -2; git rev-parse HEAD", "cd && sed -n 350,400p README.md", "cd && sed -n 400,430p README.md; echo ----; ls -la .coldpass; ls ; ls /inputs 2>&1", "mkdir -p && cd && python3 -m venv 2>&1 | tail -3; -V && cd && timeout 900 install -q \".[mcp]\" 2>&1 | tail -15; echo \"rc=$?\"; ls | grep -i ldr", "rm -rf ; sudo -n apt-get update -qq 2>&1 | tail -2; sudo -n DEBIAN_FRONTEND=noninteractive apt-get install -y -qq python3.12-venv 2>&1 | tail -3; cd && python3 -m venv && -V", "cd && timeout 1500 install \".[mcp]\" > 2>&1; echo \"rc=$?\"; tail -5 ; ls | grep -i ldr", "ls -la ; cd && ls docs | head -50; sed -n 1,80p docs/mcp-server.md 2>/dev/null | head -120", "mkdir -p && cat > <<'EOF'\nimport asyncio, sys, json\nfrom mcp import ClientSession, StdioServerParameters\nfrom mcp.client.stdio import stdio_client\nasync def main():\n tool = sys.argv[1]; args = json.loads(sys.argv[2]) if len(sys.argv) > 2 else {}\n params = StdioServerParameters(command=\"\", args=[], cwd=\"\")\n async with stdio_client(params) as (r, w):\n async with ClientSession(r, w) as s:\n await s.initialize()\n if tool == \"--list\":\n print([t.name for t in (await s.list_tools()).tools]); return\n res = await s.call_tool(tool, args)\n for c in res.content:\n print(getattr(c, \"text\", c))\nasyncio.run(main())\nEOF\ncd && timeout 300 -I --list 2>&1 | tail -5; timeout 300 -I list_strategies '{}' 2>&1 | tail -20", "cd && timeout 300 -I search '{\"query\":\"quantum error correction\",\"engine\":\"wikipedia\"}' 2>&1 | grep -v -E 'INFO|loader' | head -40; echo ---; timeout 200 -I list_search_engines '{}' 2>&1 | grep -v -E 'INFO|loader' | head -20", "cd && grep -rn -i -E 'cron|--once|--now|schedul' README.md | head; echo ---; grep -rln -E 'APScheduler|BackgroundScheduler|add_job' src | head; echo ---; grep -n 'list_strategies' README.md; grep -n 'pip install \"local-deep-research\\[mcp\\]\"' README.md", "cd && wc -l src/local_deep_research/scheduler/background.py && grep -n -E 'def |add_job|interval|cron|IntervalTrigger|CronTrigger' src/local_deep_research/scheduler/background.py | head -60", "cd && cat > probe.json <<'EOF'\n{\"kind\":\"mcp\",\"argv\":[\"\"],\"cwd\":\"\",\"tool\":\"list_strategies\",\"arguments\":{},\"expected_text\":\"langgraph-agent\"}\nEOF\ncat > claims.json <<'EOF'\n[\n {\"kind\":\"claim\",\"claim\":\"list_strategies returns the research strategies including langgraph-agent\",\"source\":\"| `list_strategies` | List research strategies | instant | None |\",\"input\":\"list_strategies with no arguments\",\"expected\":\"strategy list includes langgraph-agent\",\"probe_kind\":\"mcp\",\"argv\":[\"\"],\"tool\":\"list_strategies\",\"arguments\":{},\"expected_text\":\"langgraph-agent\",\"cwd\":\"\"},\n {\"kind\":\"claim\",\"claim\":\"list_search_engines lists available search engines including arxiv\",\"source\":\"| `list_search_engines` | List available search engines | instant | None |\",\"input\":\"list_search_engines with no arguments\",\"expected\":\"engine list includes arxiv\",\"probe_kind\":\"mcp\",\"argv\":[\"\"],\"tool\":\"list_search_engines\",\"arguments\":{},\"expected_text\":\"\\\"name\\\": \\\"arxiv\\\"\",\"cwd\":\"\"}\n]\nEOF\ncat > examples.json <<'EOF'\n[\n {\"kind\":\"example\",\"claim\":\"Benchmark CLI runs a SimpleQA benchmark\",\"source\":\"README.md Benchmarking section\",\"reason\":\"Needs a configured LLM provider and search network access; not available in this guest. Installed package and confirmed entry points only (ldr-mcp and ldr-web). Ran the MCP discovery tools instead.\"},\n {\"kind\":\"example\",\"claim\":\"Python API quick_query / LDRClient research\",\"source\":\"README.md Python API section\",\"reason\":\"Needs an LLM provider and a logged-in LDR user; not configured in this guest.\"}\n]\nEOF\ncat > cycles.json <<'EOF'\n{\"detected\":true,\"checks\":[{\"claim\":\"Subscriptions refresh on a daily/weekly/custom schedule\",\"source\":\"src/local_deep_research/scheduler/background.py\",\"quote\":\"self.scheduler.add_job(\",\"reason\":\"Scheduling is an APScheduler background job per logged-in user with an encrypted per-user database; triggering one cycle by hand needs a running web app with a user session, which was not set up in this guest. No cycle was run.\"}]}\nEOF\nfor f in probe.json claims.json examples.json cycles.json; do -I -c \"import json,sys;json.load(open(sys.argv[1]));print('ok',sys.argv[1])\" $f; done; cd && = timeout 1500 python3 -I --validate --replay 2>&1 | tail -60", "pgrep -fa 'ldr-mcp|ldr-web|local_deep_research' || echo \"no leftover servers\"; cd && cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Install local-deep-research from the pinned source and call its MCP stdio server (ldr-mcp) tools list_strategies and list_search_engines, reading back real results\",\"operation_scope\":\"Linux Ubuntu 24.04, Python 3.12.3, venv at Covers install and the MCP discovery tools only. Not covered: LLM-backed research (quick_research etc.), live search engine results (Wikipedia was rate-limited, returned 0 results), the web UI, and the subscription scheduler, which need an LLM provider and a logged-in user.\",\"steps\":[\"git init; git remote add origin https://github.com/LearningCircuit/local-deep-research; git fetch --depth 1 origin 7c274b6f72355aeef9ef1a51396363414307534f; git reset --mixed FETCH_HEAD\",\"sudo apt-get install -y python3.12-venv (needed for python3 -m venv)\",\"python3 -m venv \",\" install \\\".[mcp]\\\" (run in the checkout; README documents: pip install \\\"local-deep-research[mcp]\\\")\",\" (stdio MCP server); tools/call list_strategies and list_search_engines via an MCP stdio client\"],\"deviations\":[\"README installs from PyPI; this run installed the pinned source checkout with pip install \\\".[mcp]\\\" so the tested code matches the pinned commit.\",\"python3 -m venv failed at first (ensurepip missing); fixed by installing python3.12-venv with sudo apt-get.\",\"The checker path in the task was /inputs/coldpass-preflight.py, which does not exist in this guest; ran instead.\",\"Examples (benchmark CLI, Python API) and the cycle check were not run: they need an LLM provider and a logged-in user. Recorded as blocked with reasons.\",\"Used absolute venv path instead of bare ldr-mcp because the venv was not activated.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":\"None for the tested path. To test research end-to-end, configure an LLM provider (for example Ollama) and a search engine, then rerun the research tools.\"}\nEOF\n -I -c \"import json;json.load(open('.coldpass/report.json'));print('report ok')\"; = timeout 1500 python3 -I --validate --replay 2>&1 | python3 -c \"import sys,json; d=json.loads(sys.stdin.read().strip().splitlines()[-1]); print('valid=',d['valid'],'problems=',d['problems'],'replay=',d['replay']['status'])\"" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Install local-deep-research from the pinned source and call its MCP stdio server (ldr-mcp) tools list_strategies and list_search_engines, reading back real results", "suggested_fix": null, "tokens_in": 476875, "tokens_out": 11344, "cost_usd": 0.021291120000000004, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "" ], "kind": "mcp", "serverInfo": { "name": "local-deep-research", "version": "1.30.0" }, "tools": [ "quick_research", "detailed_research", "generate_report", "analyze_documents", "search", "list_search_engines", "list_strategies", "get_configuration" ], "tool_schema_bytes": 11348, "tool_result": { "content": [ { "type": "text", "text": "{\n \"status\": \"success\",\n \"strategies\": [\n {\n \"name\": \"source-based\",\n \"label\": \"Source-Based (Best for small <16,000 context window)\",\n \"description\": \"Comprehensive research with inline citations. Focuses on finding and extracting information from authoritative sources.\"\n },\n {\n \"name\": \"focused-iteration\",\n \"label\": \"Focused Iteration - Quick (Minimal text output)\",\n \"description\": \"Fast & precise Q&A with iterative search. Good for complex queries requiring specific answers.\"\n },\n {\n \"name\": \"focused-iteration-standard\",\n \"label\": \"Focused Iteration - Comprehensive (Needs >16,000 context window)\",\n \"description\": \"Detailed long-form output with citations. Uses standard citation handler for comprehensive answers.\"\n },\n {\n \"name\": \"topic-organization\",\n \"label\": \"Topic Organization (Clusters by topic)\",\n \"description\": \"Clusters sources into topics with lead texts. Organizes research by themes for structured output.\"\n },\n {\n \"name\": \"langgraph-agent\",\n \"label\": \"LangGraph Agent (Autonomous agentic research)\",\n \"description\": \"Agentic research where the LLM autonomously decides what to search, which engines to use, and when to synthesize. Supports all search engines as tools.\"\n }\n ]\n}" } ], "structuredContent": { "result": { "status": "success", "strategies": [ { "name": "source-based", "label": "Source-Based (Best for small <16,000 context window)", "description": "Comprehensive research with inline citations. Focuses on finding and extracting information from authoritative sources." }, { "name": "focused-iteration", "label": "Focused Iteration - Quick (Minimal text output)", "description": "Fast & precise Q&A with iterative search. Good for complex queries requiring specific answers." }, { "name": "focused-iteration-standard", "label": "Focused Iteration - Comprehensive (Needs >16,000 context window)", "description": "Detailed long-form output with citations. Uses standard citation handler for comprehensive answers." }, { "name": "topic-organization", "label": "Topic Organization (Clusters by topic)", "description": "Clusters sources into topics with lead texts. Organizes research by themes for structured output." }, { "name": "langgraph-agent", "label": "LangGraph Agent (Autonomous agentic research)", "description": "Agentic research where the LLM autonomously decides what to search, which engines to use, and when to synthesize. Supports all search engines as tools." } ] } }, "isError": false }, "tool_result_checked": true, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 1 connection review, 3 hardcoded secret, 53 known vulnerability. 175 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": 4, "process_count": 1, "processes": [ { "address": "208.80.154.224:443", "executable": "", "owner": "repo", "pid": "3426", "source": "ldr-mcp" } ] }, { "kind": "hardcoded-secret", "count": 3, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 3 }, { "kind": "known-vulnerability", "count": 53, "note": "OSV reports a known vulnerability in this dependency version.", "location_count": 6 } ], "context": [ { "kind": "hardcoded-secret", "count": 172, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 55 } ], "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=LearningCircuit--local-deep-research-claude-haiku-5-5-1792761300474358264", "evidence_file": "/data/safety/LearningCircuit--local-deep-research-claude-haiku-5-5-1792761300474358264.json.gz" }, "agent_execution": "native_agent", "agent_runtime": "claude-code", "agent_runtime_version": "2.1.300 (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": 16, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "7c274b6f72355aeef9ef1a51396363414307534f", "url": "https://github.com/LearningCircuit/local-deep-research" }, "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": 16, "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/LearningCircuit/local-deep-research", "cost_to_try": "free", "hardware": "GPU", "what_failed": null, "local_or_hosted": "both", "cycle_checks": [ { "kind": "cycle", "claim": "Subscriptions refresh on a daily/weekly/custom schedule", "source": "src/local_deep_research/scheduler/background.py", "input": "", "expected": "", "command": "", "schedule": "", "method": "", "verdict": "blocked", "outcome": "Scheduling is an APScheduler background job per logged-in user with an encrypted per-user database; triggering one cycle by hand needs a running web app with a user session, which was not set up in this guest. No cycle was run.", "evidence": "Scheduling is an APScheduler background job per logged-in user with an encrypted per-user database; triggering one cycle by hand needs a running web app with a user session, which was not set up in this guest. No cycle was run." } ], "claims": [ { "kind": "claim", "claim": "list_strategies returns the research strategies including langgraph-agent", "source": "| `list_strategies` | List research strategies | instant | None |", "input": "{\"tool\": \"list_strategies\", \"arguments\": {}}", "expected": "strategy list includes langgraph-agent", "command": " tools/call {\"tool\": \"list_strategies\", \"arguments\": {}}", "verdict": "yes", "outcome": "Real input produced the expected result: langgraph-agent", "evidence": "langgraph-agent\\\",\\n \\\"label\\\": \\\"LangGraph Agent (Autonomous agentic research)\\\",\\n \\\"description\\\": \\\"Agentic research where the LLM autonomously decides what to search, which engines to use, and when to synthesize. Supports all search engines as tools.\\\"\\n }\\n ]\\n}\"}], \"structuredContent\": {\"result\": {\"status\": \"success\", \"strategies\": [{\"name\": \"source-based\", \"label\": \"Source-Based (Best for small <16,000 context window)\", \"description\": \"Comprehensive research with inline citations. Focuses on finding and extracting information from authoritative sources.\"}, {\"name\": \"focus", "source_checked": true, "source_file": "README.md" }, { "kind": "claim", "claim": "list_search_engines lists available search engines including arxiv", "source": "| `list_search_engines` | List available search engines | instant | None |", "input": "{\"tool\": \"list_search_engines\", \"arguments\": {}}", "expected": "engine list includes arxiv", "command": " tools/call {\"tool\": \"list_search_engines\", \"arguments\": {}}", "verdict": "yes", "outcome": "Real input produced the expected result: \"name\": \"arxiv\"", "evidence": "\"name\": \"arxiv\", \"description\": \"Search papers uploaded to ArXiv.\", \"strengths\": [\"scientific papers\", \"academic research\", \"physics\", \"computer science\", \"mathematics\", \"statistics\", \"machine learning\", \"preprints\"], \"weaknesses\": [\"non-academic topics\", \"consumer products\", \"news\", \"general information\"], \"requires_api_key\": false, \"is_local\": false}, {\"name\": \"brave\", \"description\": \"Search the web using the Brave search engine.\", \"strengths\": [\"privacy-focused web search\", \"product information\", \"reviews\", \"recent content\", \"news\", \"broad coverage\"], \"weaknesses\": [\"requires API key with u", "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Benchmark CLI runs a SimpleQA benchmark", "source": "README.md Benchmarking section", "input": "", "command": "", "evidence": "Needs a configured LLM provider and search network access; not available in this guest. Installed package and confirmed entry points only (ldr-mcp and ldr-web). Ran the MCP discovery tools instead.", "deferred": false, "expected": "documented command completes successfully", "verdict": "blocked", "outcome": "Needs a configured LLM provider and search network access; not available in this guest. Installed package and confirmed entry points only (ldr-mcp and ldr-web). Ran the MCP discovery tools instead." }, { "kind": "example", "claim": "Python API quick_query / LDRClient research", "source": "README.md Python API section", "input": "", "command": "", "evidence": "Needs an LLM provider and a logged-in LDR user; not configured in this guest.", "deferred": false, "expected": "documented command completes successfully", "verdict": "blocked", "outcome": "Needs an LLM provider and a logged-in LDR user; not configured in this guest." } ], "does_what_it_says": "yes", "maintenance": { "last_commit_at": "2026-10-23T11:50:31Z", "commits_90d": 1075, "merged_prs_90d": 1127, "open_issues": 968, "open_prs": 232, "reply_share": null, "reply_threads": 0, "median_reply_hours": null, "last_release_at": "2026-08-28T21:43:07Z", "archived": false, "verdict": "maintained", "note": "actively maintained: last commit 0 days ago; 1075 commits and 1127 merged PRs in 90 days; 968 open issues, 232 open PRs; latest release 2026-08-28" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 0 days ago; 1075 commits and 1127 merged PRs in 90 days; 968 open issues, 232 open PRs; latest release 2026-08-28", "maintained": "active", "maintained_note": "last commit 0 days ago; 17 open issues, 1 answered or closed", "last_commit_at": "2026-10-23T12:40:34Z", "last_release_at": "2026-08-28T21:43:07Z", "open_issues": 17, "answered_issues": 1, "platforms_claimed": [ "linux", "mac", "windows" ], "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 }, { "interface": "api", "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": 8, "schema_bytes": 11348, "tokens_approx": 2837, "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": "2026-10-23T13:33:41.129117+00:00", "tested_commit": "7c274b6f72355aeef9ef1a51396363414307534f", "tested_with": { "agent": "claude-code", "agent_version": "2.1.300 (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": "LearningCircuit/local-deep-research", "source": "https://github.com/LearningCircuit/local-deep-research", "commit": "7c274b6f72355aeef9ef1a51396363414307534f", "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": "2.1.300 (Claude Code)", "tool_transport": "mcp-assigned-vm", "runtime": null, "runtime_version": null, "runtime_revision": null, "sandbox_source": null, "guest_setup": null, "source_pin": { "commit": "7c274b6f72355aeef9ef1a51396363414307534f", "url": "https://github.com/LearningCircuit/local-deep-research" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": null, "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Install local-deep-research from the pinned source and call its MCP stdio server (ldr-mcp) tools list_strategies and list_search_engines, reading back real results", "operation_scope": "product operation", "hosting": null, "kind": "mcp", "test_version": "readme-bdc1b9b3c0d2673aef87e076d14084a8123ddcf09d520c1ee2e364a37c3f4bb9", "evidence_version": null }, "other_model": null, "other_run_id": null, "models_agree": null, "furthest_model": null, "transcript_url": null, "report_url": "/reports/LearningCircuit--local-deep-research-claude-haiku-5-5-1792761300474358264.json" }