{
  "run_id": "itechmeat--open-second-brain-claude-haiku-5-5-1792814426308251009",
  "date": "2026-10-24T04:03:56.107129+00:00",
  "repo": "itechmeat/open-second-brain",
  "kind": "mcp",
  "source": "https://github.com/itechmeat/open-second-brain",
  "commit": "3064defd7f3c4a6b5c3217ba7da2e55879ed037b",
  "model": "claude-haiku-5-5",
  "model_version": "claude-haiku-5-5",
  "test_version": "readme-bdc1b9b3c0d2673aef87e076d14084a8123ddcf09d520c1ee2e364a37c3f4bb9",
  "pass": true,
  "outcome": "pass",
  "time_to_working_s": 169.18950140301604,
  "total_s": 209.7988419532776,
  "steps": [
    "cd <guest-path> && pwd && ls -la && id -u && python3 --version && git -C . status 2>&1 | head -3; test -f README.md && head -c 6000 README.md",
    "ls -la /inputs 2>&1; ls -la <guest-path> 2>&1; cat /etc/os-release | head -2",
    "cd <guest-path> && tail -c +6000 README.md | head -c 12000; echo ----; cat install/prerequisites.md | head -c 5000",
    "command -v bun >/dev/null 2>&1 || curl -fsSL https://bun.sh/install | bash; export PATH=\"$HOME/.bun/bin:$PATH\"; bun --version 2>&1; which node npm 2>&1; node --version 2>&1",
    "sudo -n true && echo SUDO_OK; sudo -n apt-get install -y unzip 2>&1 | tail -3; command -v unzip",
    "sudo -n apt-get update 2>&1 | tail -3; sudo -n apt-get install -y unzip 2>&1 | tail -2; command -v unzip && curl -fsSL https://bun.sh/install | bash 2>&1 | tail -5; export PATH=\"$HOME/.bun/bin:$PATH\"; bun --version",
    "cd <guest-path> && ls scripts && head -60 scripts/o2b; echo ----; grep -rn \"install-cli\" scripts/o2b | head",
    "cd <guest-path> && export PATH=\"$HOME/.bun/bin:$PATH\" && cat package.json | head -60 && ls node_modules 2>/dev/null | head -2; echo ---; grep -n -i \"install\\|bun\" install.md | head -30",
    "cd <guest-path> && export PATH=\"$HOME/.bun/bin:$PATH\" && ./scripts/o2b install-cli 2>&1 | tail -15; echo \"rc=$?\"; export PATH=\"$HOME/.local/bin:$PATH\"; o2b version 2>&1 | tail -5",
    "export PATH=\"$HOME/.local/bin:$HOME/.bun/bin:$PATH\"; cd <guest-path> && mkdir -p <guest-path> && o2b init --vault <guest-path> --name \"My Second Brain\" </dev/null 2>&1 | tail -20; echo \"rc=$?\"; o2b brain init --vault <guest-path> </dev/null 2>&1 | tail -20; echo; grep -rn -i \"telemetry\" <guest-path> <guest-path> | head -5",
    "export PATH=\"$HOME/.local/bin:$HOME/.bun/bin:$PATH\"; cd <guest-path> && o2b init --vault <guest-path> --agent-name claude-haiku-probe </dev/null 2>&1 | tail -3; o2b brain note \"hello from probe\" --vault <guest-path> </dev/null 2>&1 | tail -5; echo rc=$?; cd <guest-path> && head -c 5000 docs/mcp.md",
    "cd <guest-path> && grep -n -i \"o2b-mcp\\|stdio\\|--vault\\|api-key\\|brain_note\\|brain_search\" docs/mcp.md | head -50; echo ---; cat scripts/o2b-mcp | head -30",
    "export PATH=\"$HOME/.local/bin:$HOME/.bun/bin:$PATH\"; cd <guest-path> && o2b search index --vault <guest-path> </dev/null 2>&1 | tail -3; printf '%s\\n' '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"initialize\",\"params\":{\"protocolVersion\":\"2025-06-18\",\"capabilities\":{},\"clientInfo\":{\"name\":\"t\",\"version\":\"1\"}}}' '{\"jsonrpc\":\"2.0\",\"method\":\"notifications/initialized\"}' '{\"jsonrpc\":\"2.0\",\"id\":2,\"method\":\"tools/call\",\"params\":{\"name\":\"brain_search\",\"arguments\":{\"query\":\"hello from probe\"}}}' | timeout 60 o2b mcp --vault <guest-path> 2><guest-path> | head -c 3000; echo; echo rc=$?; head -5 <guest-path>",
    "cd <guest-path> && grep -rln -i \"setInterval\\|--once\\|--now\\|cron\" src/cli | head; grep -rn -i \"\\-\\-once\\|--now\\|setInterval\" src/cli | head -8; echo ---; grep -n \"cycles\\|examples.json\\|expected_file\" <guest-path> | head -40; ls tests | head -30; grep -n \"\\\"test\\\"\" -A2 scripts/test | head; cat scripts/test | head -30",
    "cd <guest-path> && head -c 1500 docs/hermes-cron.md; echo; echo ---; sed -n 1,30p src/cli/search-cron-template.ts | head -40; echo ---; grep -rn \"setTimeout\\|setInterval\\|while (true)\" src/cli/brain/verbs/dream.ts src/cli/main.ts 2>/dev/null | head",
    "export PATH=\"$HOME/.local/bin:$HOME/.bun/bin:$PATH\"; cd <guest-path> && o2b brain digest --vault <guest-path> --no-agent --script 2>&1 | head -30; echo \"rc=${PIPESTATUS[0]}\"; o2b brain digest --vault <guest-path> --help 2>&1 | head -5",
    "export PATH=\"$HOME/.local/bin:$HOME/.bun/bin:$PATH\"; cd <guest-path> && o2b brain digest --vault <guest-path> 2>&1 | head -30; echo \"rc=${PIPESTATUS[0]}\"; echo ---; o2b brain digest --vault <guest-path> --silent-if-empty 2>&1 | head -10; echo \"rc=${PIPESTATUS[0]}\"",
    "cd <guest-path> && mkdir -p .coldpass && ENV='{\"PATH\":\"<guest-path>\",\"HOME\":\"<guest-path>\"}' && cat > .coldpass/probe.json <<EOF\n{\"kind\":\"mcp\",\"argv\":[\"o2b\",\"mcp\",\"--vault\",\"<guest-path>\"],\"cwd\":\"<guest-path>\",\"env\":$ENV,\"tool\":\"brain_search\",\"arguments\":{\"query\":\"hello from probe\"},\"expected_text\":\"hello from probe\"}\nEOF\ncat > .coldpass/claims.json <<EOF\n[{\"kind\":\"claim\",\"claim\":\"MCP keyword search returns the note written through the vault\",\"source\":\"Keyword search with an optional semantic lane, result explanations, recall profiles and compact cards\",\"input\":\"query hello from probe\",\"expected\":\"the Brain log note containing hello from probe is returned\",\"probe_kind\":\"mcp\",\"argv\":[\"o2b\",\"mcp\",\"--vault\",\"<guest-path>\"],\"env\":$ENV,\"tool\":\"brain_search\",\"arguments\":{\"query\":\"hello from probe\"},\"expected_text\":\"hello from probe\",\"cwd\":\"<guest-path>\"}]\nEOF\ncat > .coldpass/examples.json <<EOF\n[{\"kind\":\"example\",\"claim\":\"Record a note from the CLI into the Brain log\",\"source\":\"install/prerequisites.md\",\"input\":\"brain note text: example note from probe\",\"expected\":\"note logged to Brain/log\",\"argv\":[\"o2b\",\"brain\",\"note\",\"example note from probe\",\"--vault\",\"<guest-path>\"],\"cwd\":\"<guest-path>\",\"env\":$ENV,\"expected_text\":\"logged note at\"}]\nEOF\ncat > .coldpass/cycles.json <<EOF\n{\"detected\":true,\"checks\":[{\"claim\":\"Scheduled Brain digest runs the dream/activity summary once per trigger\",\"source\":\"docs/hermes-cron.md\",\"quote\":\"o2b brain digest --vault /path/to/vault --silent-if-empty\",\"schedule\":\"0 20 * * * (external Hermes cron; not run by the product itself)\",\"method\":\"run-once: the cron command run by hand, no fake clock\",\"input\":\"--vault <guest-path> --silent-if-empty\",\"expected\":\"digest markdown printed to stdout\",\"kind\":\"cli\",\"argv\":[\"o2b\",\"brain\",\"digest\",\"--vault\",\"<guest-path>\",\"--silent-if-empty\"],\"cwd\":\"<guest-path>\",\"env\":$ENV,\"expected_text\":\"# Brain digest\"}]}\nEOF\nfor f in probe claims examples cycles; do python3 -I -c \"import json,sys;json.load(open(sys.argv[1]));print('ok',sys.argv[1])\" .coldpass/$f.json; done",
    "cd <guest-path> && cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Create a vault, write a note with the o2b CLI, then find it through the MCP brain_search tool over stdio\",\"operation_scope\":\"Linux Ubuntu 24.04, Python 3.12.3 present (not needed by the product), Bun 1.4.4 installed, local vault at <guest-path> Telemetry/consent prompts not reached: init and brain init ran non-interactively; no client config was written (no install --apply). Hermes cron scheduling is external and was not run as a daemon; the digest command was run once by hand.\",\"steps\":[\"curl -fsSL https://bun.sh/install | bash (README prerequisites; first attempt failed, see deviations)\",\"export PATH=\\\"$HOME/.bun/bin:$PATH\\\"; bun --version -> 1.4.4\",\"./scripts/o2b install-cli (README 'Get the o2b CLI')\",\"o2b version -> 1.93.0\",\"o2b init --vault <guest-path> --name \\\"My Second Brain\\\"\",\"o2b brain init --vault <guest-path>\",\"o2b init --vault <guest-path> --agent-name claude-haiku-probe\",\"o2b brain note \\\"hello from probe\\\" --vault <guest-path> -> logged note at Brain/log/2026-10-24.b31d7023.md\",\"o2b search index --vault <guest-path>\",\"o2b mcp --vault <guest-path> (stdio JSON-RPC: initialize, tools/call brain_search query 'hello from probe') -> returned the note\",\"o2b brain digest --vault <guest-path> --silent-if-empty -> '# Brain digest' markdown\"],\"deviations\":[\"Bun installer failed first with 'error: unzip is required to install bun'. Fixed by sudo -n apt-get update && sudo -n apt-get install -y unzip (the first apt-get install failed with 'Unable to locate package unzip' because the package index was empty), then re-ran the README's curl|sh Bun installer.\",\"scripts/o2b install-cli installed the links to <guest-path> because HOME is <guest-path> in this guest.\",\"The workspace is not a git checkout, so the pinned-commit git fetch step was not run; the source snapshot was used as supplied.\",\"Brain digest is cron-scheduled externally (Hermes cron in docs/hermes-cron.md). The product has no internal scheduler, so the cycle check runs the same command once by hand instead of waiting for 20:00 UTC.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":\"None for the tested path. Optional: the install docs could list unzip as a Bun prerequisite on minimal Ubuntu images.\"}\nEOF\npython3 -I -c \"import json;json.load(open('.coldpass/report.json'));print('report ok')\"; <env-var>=<guest-path> python3 -I <guest-path> --validate --replay 2>&1 | tail -60",
    "pgrep -af \"o2b|open-second-brain|src/cli/main.ts\" | grep -v pgrep || echo \"no o2b processes running\""
  ],
  "stuck_step": null,
  "error_excerpt": null,
  "what_it_did": "Create a vault, write a note with the o2b CLI, then find it through the MCP brain_search tool over stdio",
  "suggested_fix": null,
  "tokens_in": 577503,
  "tokens_out": 12384,
  "cost_usd": 0.02107657,
  "usage_complete": true,
  "checks": [
    {
      "check": "operation",
      "status": "PASS",
      "details": {
        "working": true,
        "argv": [
          "o2b",
          "mcp",
          "--vault",
          "<guest-path>"
        ],
        "kind": "mcp",
        "serverInfo": {
          "name": "open-second-brain",
          "version": "1.93.0"
        },
        "tools": [
          "second_brain_capabilities",
          "second_brain_status",
          "second_brain_query",
          "brain_feedback",
          "brain_dream",
          "brain_apply_evidence",
          "brain_note",
          "brain_observed_use",
          "brain_expire",
          "brain_intent_review",
          "brain_retention",
          "brain_review_candidates",
          "brain_stale_scan",
          "brain_write_session",
          "brain_pinned_context",
          "brain_context",
          "brain_context_pack",
          "brain_context_receipts",
          "brain_event_trace",
          "brain_context_presets",
          "brain_pre_compress_pack",
          "brain_pre_compact_extract",
          "brain_anticipatory_context",
          "brain_query",
          "brain_agent_query",
          "brain_writes",
          "brain_write_destinations",
          "brain_agent_diff",
          "brain_backlinks",
          "brain_audit",
          "brain_sources",
          "brain_unlinked_mentions",
          "brain_entity",
          "brain_switch_vault",
          "brain_doctor",
          "brain_health",
          "brain_status",
          "brain_brief",
          "brain_analytics",
          "brain_claims",
          "brain_codegraph_report",
          "brain_foresight",
          "brain_bridges",
          "brain_clusters",
          "brain_moc_audit",
          "brain_deep_synthesis",
          "brain_diarize",
          "brain_idea_discovery",
          "brain_truth",
          "brain_dead_ends",
          "brain_labels",
          "brain_tiers",
          "brain_secrets",
          "brain_maintenance",
          "brain_benchmark",
          "brain_tune",
          "brain_recall_telemetry",
          "brain_route_metrics",
          "brain_retrieval_plan",
          "brain_token_impact",
          "brain_context_pack_outcome",
          "brain_knowledge_gaps",
          "brain_session_grep",
          "brain_session_describe",
          "brain_session_expand",
          "brain_intention",
          "brain_trigger",
          "brain_skill_proposals",
          "brain_procedural_memory",
          "brain_recurrence",
          "brain_procedural_graph",
          "brain_mcp_landscape",
          "brain_hygiene",
          "brain_intake_entities",
          "brain_ingest_source",
          "brain_search_by_source",
          "brain_delete_by_source",
          "brain_ingest_batch_plan",
          "brain_distill_source",
          "brain_extract_signals",
          "brain_design_note",
          "brain_research_report",
          "brain_derive_fact",
          "brain_create_note",
          "brain_update_note",
          "brain_append_note",
          "brain_write_batch",
          "brain_session_summary",
          "brain_session_checkpoint",
          "brain_idea_lineage",
          "brain_note_history",
          "brain_generation_reports",
          "brain_obligation",
          "brain_agenda",
          "brain_pledge",
          "brain_intake_pledges",
          "brain_memory_bridge",
          "brain_lifecycle",
          "brain_note_lifecycle",
          "brain_scaffold_stub",
          "brain_decision",
          "brain_tension",
          "brain_storage",
          "brain_receipts",
          "brain_recall_feedback",
          "brain_recall_gate",
          "brain_search",
          "brain_search_expand",
          "brain_eval",
          "brain_file_context",
          "vault_health",
          "brain_artifact_get",
          "schema_inspect",
          "schema_apply_mutations",
          "brain_watchdog",
          "list_skills",
          "get_skill",
          "skills_attach",
          "second_brain_wiring",
          "tool_hydrate"
        ],
        "tool_schema_bytes": 162403,
        "tool_result": {
          "content": [
            {
              "type": "text",
              "text": "{\n  \"recall_hint\": \"Recalled 1 of 1 ranked candidates (1 keyword). Top hit \\\"Brain log \u2014 2026-10-24\\\" (keyword, score 0.66). See each result's reasons[] for why it surfaced.\",\n  \"results\": [\n    {\n      \"content\": \"# Brain log \u2014 2026-10-24\\n## 04:02:35Z \u2014 note\\n- text: hello from probe\\n- agent: claude-haiku-probe\\n- origin_channel: cli\",\n      \"endLine\": 12,\n      \"path\": \"Brain/log/2026-10-24.b31d7023.md\",\n      \"reasons\": [\n        \"fts5_bm25: 1.000\",\n        \"activation: 0.012\",\n        \"recency: 0.050\"\n      ],\n      \"score\": 0.6619889056342603,\n      \"searchType\": \"keyword\",\n      \"startLine\": 7,\n      \"title\": \"Brain log \u2014 2026-10-24\"\n    }\n  ],\n  \"total\": 1,\n  \"warnings\": []\n}"
            }
          ],
          "structuredContent": {
            "results": [
              {
                "path": "Brain/log/2026-10-24.b31d7023.md",
                "title": "Brain log \u2014 2026-10-24",
                "content": "# Brain log \u2014 2026-10-24\n## 04:02:35Z \u2014 note\n- text: hello from probe\n- agent: claude-haiku-probe\n- origin_channel: cli",
                "score": 0.6619889056342603,
                "startLine": 7,
                "endLine": 12,
                "searchType": "keyword",
                "reasons": [
                  "fts5_bm25: 1.000",
                  "activation: 0.012",
                  "recency: 0.050"
                ]
              }
            ],
            "warnings": [],
            "total": 1,
            "recall_hint": "Recalled 1 of 1 ranked candidates (1 keyword). Top hit \"Brain log \u2014 2026-10-24\" (keyword, score 0.66). See each result's reasons[] for why it surfaced."
          },
          "isError": false
        },
        "tool_result_checked": true,
        "scope": "product operation"
      }
    }
  ],
  "safety": {
    "version": "z2x-1",
    "rules_version": "z2x-1",
    "summary": "Review signals: 1 connection review, 1 download and execute, 4 hardcoded secret, 1 sensitive read. 14 static matches retained as context.",
    "expected": "Reviewed as expected for a test run: read only test files inside the test workspace or its temporary folders.",
    "findings": [
      {
        "kind": "connection-review",
        "count": 1,
        "note": "Repository processes attempted these non-loopback connections; proxies can hide the final hostname.",
        "location_count": 24,
        "process_count": 2
      },
      {
        "kind": "download-and-execute",
        "count": 1,
        "note": "Source contains download and execute; review its purpose.",
        "location_count": 1,
        "path": "scripts/_bun-precheck.sh"
      },
      {
        "kind": "hardcoded-secret",
        "count": 4,
        "note": "Gitleaks found a possible hardcoded secret; value withheld.",
        "location_count": 1,
        "path": "docs/brainstorm/manifest-dependency-facts/cli-output/expected-output.md"
      },
      {
        "kind": "sensitive-read",
        "count": 1,
        "note": "A repository process attempted to read this sensitive path.",
        "location_count": 1,
        "path": "<guest-path>",
        "process_count": 1,
        "processes": [
          {
            "created_in_run": false,
            "executable": "<guest-path>",
            "owner": "repo",
            "path": "<guest-path>",
            "pid": "2839",
            "source": "<guest-path>",
            "succeeded": false,
            "syscall": "openat",
            "trace": "9.trace"
          }
        ]
      }
    ],
    "context": [
      {
        "kind": "download-and-execute",
        "count": 1,
        "note": "Source contains download and execute; review its purpose.",
        "location_count": 1,
        "path": "tests/python/test_memory_provider.py"
      },
      {
        "kind": "hardcoded-secret",
        "count": 13,
        "note": "Gitleaks found a possible hardcoded secret; value withheld.",
        "location_count": 13
      }
    ],
    "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=itechmeat--open-second-brain-claude-haiku-5-5-1792814426308251009",
    "evidence_file": "/data/safety/itechmeat--open-second-brain-claude-haiku-5-5-1792814426308251009.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": 20,
  "native_bundle": null,
  "architecture": null,
  "backend": "hyperv",
  "platform_details": {
    "backend": "hyperv",
    "os": "linux"
  },
  "platform_conflicts": null,
  "sandbox_source": null,
  "source_pin": {
    "commit": "3064defd7f3c4a6b5c3217ba7da2e55879ed037b",
    "url": "https://github.com/itechmeat/open-second-brain"
  },
  "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": 20,
  "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/itechmeat/open-second-brain",
  "cost_to_try": "free",
  "hardware": null,
  "what_failed": null,
  "local_or_hosted": "local",
  "cycle_checks": [
    {
      "kind": "cycle",
      "claim": "Scheduled Brain digest runs the dream/activity summary once per trigger",
      "source": "docs/hermes-cron.md",
      "input": "--vault <guest-path> --silent-if-empty",
      "expected": "digest markdown printed to stdout",
      "command": "o2b brain digest --vault <guest-path> --silent-if-empty",
      "schedule": "0 20 * * * (external Hermes cron; not run by the product itself)",
      "method": "run-once: the cron command run by hand, no fake clock",
      "verdict": "yes",
      "outcome": "Triggered one cycle by hand (run-once: the cron command run by hand, no fake clock; normal trigger: 0 20 * * * (external Hermes cron; not run by the product itself)): # Brain digest \u2014 2026-10-24T04:03Z (24h)\n\nWindow: 2026-10-23T04:03:46.908Z \u2014 2026-10-24T04:03:46.908Z\n\n## Agent summary (1)\n\n- **claude-haiku-probe** 2 events (feedback: 0, apply: 0, note: 2)",
      "evidence": "# Brain digest \u2014 2026-10-24T04:03Z (24h)\n\nWindow: 2026-10-23T04:03:46.908Z \u2014 2026-10-24T04:03:46.908Z\n\n## Agent summary (1)\n\n- **claude-haiku-probe** 2 events (feedback: 0, apply: 0, note: 2)",
      "returncode": 0
    }
  ],
  "claims": [
    {
      "kind": "claim",
      "claim": "MCP keyword search returns the note written through the vault",
      "source": "Keyword search with an optional semantic lane, result explanations, recall profiles and compact cards",
      "input": "{\"tool\": \"brain_search\", \"arguments\": {\"query\": \"hello from probe\"}}",
      "expected": "the Brain log note containing hello from probe is returned",
      "command": "o2b mcp --vault <guest-path> tools/call {\"tool\": \"brain_search\", \"arguments\": {\"query\": \"hello from probe\"}}",
      "verdict": "yes",
      "outcome": "Real input produced the expected result: hello from probe",
      "evidence": "hello from probe\\\\n- agent: claude-haiku-probe\\\\n- origin_channel: cli\\\\n## 04:03:36Z \u2014 note\\\\n- text: example note from probe\\\\n- agent: claude-haiku-probe\\\\n- origin_channel: cli\\\",\\n      \\\"endLine\\\": 17,\\n      \\\"path\\\": \\\"Brain/log/2026-10-24.b31d7023.md\\\",\\n      \\\"reasons\\\": [\\n        \\\"fts5_bm25: 1.000\\\",\\n        \\\"activation: 0.016\\\",\\n        \\\"recency: 0.050\\\"\\n      ],\\n      \\\"score\\\": 0.6659976269378894,\\n      \\\"searchType\\\": \\\"keyword\\\",\\n      \\\"startLine\\\": 7,\\n      \\\"title\\\": \\\"Brain log \u2014 2026-10-24\\\"\\n    }\\n  ],\\n  \\\"total\\\": 1,\\n  \\\"warnings\\\": []\\n}\"}], \"structuredCo",
      "source_checked": true,
      "source_file": "README.md"
    }
  ],
  "claims_note": null,
  "example_checks": [
    {
      "kind": "example",
      "claim": "Record a note from the CLI into the Brain log",
      "source": "install/prerequisites.md",
      "input": "brain note text: example note from probe",
      "command": "o2b brain note 'example note from probe' --vault <guest-path>",
      "evidence": "logged note at Brain/log/2026-10-24.b31d7023.md",
      "deferred": false,
      "expected": "note logged to Brain/log",
      "returncode": 0,
      "verdict": "yes",
      "outcome": "command completed successfully"
    }
  ],
  "does_what_it_says": "yes",
  "maintenance": {
    "last_commit_at": "2026-10-23T00:44:08Z",
    "commits_90d": 86,
    "merged_prs_90d": 86,
    "open_issues": 0,
    "open_prs": 0,
    "reply_share": 0.79,
    "reply_threads": 14,
    "median_reply_hours": 67.4,
    "last_release_at": "2026-10-23T00:49:28Z",
    "archived": false,
    "verdict": "maintained",
    "note": "actively maintained: last commit 1 days ago; 86 commits and 86 merged PRs in 90 days; 0 open issues, 0 open PRs; 11 of 14 recent threads got a maintainer reply, median first reply 67.4h; latest release 2026-10-23"
  },
  "maintenance_verdict": "maintained",
  "maintenance_note": "actively maintained: last commit 1 days ago; 86 commits and 86 merged PRs in 90 days; 0 open issues, 0 open PRs; 11 of 14 recent threads got a maintainer reply, median first reply 67.4h; latest release 2026-10-23",
  "maintained": "active",
  "maintained_note": "last commit 0 days ago; 0 open issues, 7 answered or closed",
  "last_commit_at": "2026-10-23T06:56:35Z",
  "last_release_at": "2026-10-23T00:49:28Z",
  "open_issues": 0,
  "answered_issues": 7,
  "platforms_claimed": [
    "windows"
  ],
  "topic": "mcp-server",
  "agent_interfaces": [
    {
      "interface": "mcp",
      "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": {
    "tool_count": 120,
    "schema_bytes": 162403,
    "tokens_approx": 40601,
    "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": "2026-10-24T04:03:56.107129+00:00",
  "tested_commit": "3064defd7f3c4a6b5c3217ba7da2e55879ed037b",
  "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": "itechmeat/open-second-brain",
    "source": "https://github.com/itechmeat/open-second-brain",
    "commit": "3064defd7f3c4a6b5c3217ba7da2e55879ed037b",
    "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": "3064defd7f3c4a6b5c3217ba7da2e55879ed037b",
      "url": "https://github.com/itechmeat/open-second-brain"
    },
    "platform_details": {
      "os": "linux",
      "backend": "hyperv"
    },
    "platform_conflicts": null,
    "reasoning": "low",
    "service_tier": null,
    "resources": {
      "cpus": 2,
      "memory_mib": 4096,
      "disk_mib": 32768
    },
    "operation": "Create a vault, write a note with the o2b CLI, then find it through the MCP brain_search tool over stdio",
    "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/itechmeat--open-second-brain-claude-haiku-5-5-1792814426308251009.json"
}