{
  "run_id": "cosmin-novac--memry-gpt-6-luna-1793175527368646453",
  "date": "2026-10-28T08:20:35.363189+00:00",
  "repo": "cosmin-novac/memry",
  "kind": "repo",
  "source": "https://github.com/cosmin-novac/memry",
  "commit": "9fb6e61975b9ff7f6fee85ec9d4112d1c0c2d8a7",
  "model": "gpt-6-luna",
  "model_version": "gpt-6-luna",
  "test_version": "readme-604d73685be33b2939b2632791fb1de37972f659febb28a139c60d6e81057c18",
  "pass": true,
  "outcome": "pass",
  "time_to_working_s": 68.00112527499732,
  "total_s": 107.99446702003479,
  "steps": [
    "pwd; rg --files -g 'README*' -g 'pyproject.toml' -g 'package.json' -g 'Makefile' -g 'AGENTS.md' -g '*.toml' -g '*.yml' -g '*.yaml' -g 'requirements*.txt' -g '*.json' | head -80",
    "ls -la; find . -maxdepth 3 -type f | sort | head -100; python3 --version",
    "cat README.md; cat pyproject.toml",
    "python3 -m venv /tmp/memry-venv && /tmp/memry-venv/bin/python -m pip install -e '.[dev]'",
    "sed -n '1,220p' src/memry/cli.py; sed -n '1,100p' evals/datasets/synthetic_v1.jsonl; mkdir -p .coldpass",
    "sed -n '1,200p' src/memry/config.py; grep -n 'eval\\|dataset' README.md",
    "MEMRY_DB_PATH=/tmp/memry-run.db /tmp/memry-venv/bin/memry eval --dataset evals/datasets/synthetic_v1.jsonl -k 5",
    "cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"/tmp/memry-venv/bin/memry\",\"eval\",\"--dataset\",\"evals/datasets/synthetic_v1.jsonl\",\"-k\",\"5\"],\"cwd\":\"<guest-path>\",\"env\":{\"MEMRY_DB_PATH\":\"/tmp/memry-probe.db\"},\"expected_text\":\"recall@5:     1.000\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"The built-in evaluation harness scores retrieval deterministically and offline.\",\"source\":\"The harness ingests each case through the full write path, then scores retrieval\",\"input\":\"evals/datasets/synthetic_v1.jsonl -k 5\",\"expected\":\"recall@5:     1.000\",\"probe_kind\":\"cli\",\"argv\":[\"/tmp/memry-venv/bin/memry\",\"eval\",\"--dataset\",\"evals/datasets/synthetic_v1.jsonl\",\"-k\",\"5\"],\"expected_text\":\"recall@5:     1.000\",\"cwd\":\"<guest-path>\",\"env\":{\"MEMRY_DB_PATH\":\"/tmp/memry-claim.db\"}}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Run the synthetic retrieval evaluation\",\"source\":\"README.md / Evaluation\",\"input\":\"synthetic_v1.jsonl, k=5\",\"expected\":\"retrieval metrics\",\"argv\":[\"/tmp/memry-venv/bin/memry\",\"eval\",\"--dataset\",\"evals/datasets/synthetic_v1.jsonl\",\"-k\",\"5\"],\"cwd\":\"<guest-path>\",\"env\":{\"MEMRY_DB_PATH\":\"/tmp/memry-example.db\"},\"expected_text\":\"MRR:\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"checks\":[],\"reason\":\"Inspected README quickstart and CLI entrypoints; they document explicit add/search/eval operations and no cron, scheduled loop, webhook, --once, or --now cycle.\"}\nEOF",
    "<env-var>=<guest-path> python3 -I <guest-path> --validate --replay",
    "cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Run the synthetic retrieval evaluation\",\"operation_scope\":\"Local offline evaluation using the built-in dataset, SQLite, and hash embeddings; Python 3.12.3 in a venv\",\"steps\":[\"Read README.md and pyproject.toml; confirmed Python >=3.11.\",\"Created /tmp/memry-venv and installed the documented development package with pip install -e '.[dev]'.\",\"Ran memry eval --dataset evals/datasets/synthetic_v1.jsonl -k 5; observed 8 cases, 17 questions, recall@5 1.000, and MRR 0.814.\",\"Replayed probe, README claim, and documented evaluation example with the coldpass checker; validation passed.\"],\"deviations\":[],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\nEOF\ncat .coldpass/report.json; ls -la .coldpass"
  ],
  "stuck_step": null,
  "error_excerpt": null,
  "what_it_did": "Run the synthetic retrieval evaluation",
  "suggested_fix": null,
  "tokens_in": 252773,
  "tokens_out": 1459,
  "cost_usd": null,
  "usage_complete": true,
  "checks": [
    {
      "check": "operation",
      "status": "PASS",
      "details": {
        "working": true,
        "argv": [
          "/tmp/memry-venv/bin/memry",
          "eval",
          "--dataset",
          "evals/datasets/synthetic_v1.jsonl",
          "-k",
          "5"
        ],
        "kind": "cli",
        "returncode": 0,
        "stdout": "dataset:      evals/datasets/synthetic_v1.jsonl\ncases:        8  questions: 17\nmemories:     19\nrecall@5:     1.000\nMRR:          0.814\nsearch p50:   0.7 ms   p95: 0.9 ms\nllm:          none   embedder: hash:v1-256",
        "stderr": "",
        "needs_credentials": false,
        "needs_browser": false,
        "scope": "product operation"
      }
    }
  ],
  "safety": {
    "version": "z2x-1",
    "rules_version": "z2x-1",
    "summary": "Review signals: 3 download and execute, 34 known vulnerability.",
    "expected": "Reviewed as expected for a test run: attempted writes that failed, so nothing was written.",
    "findings": [
      {
        "kind": "download-and-execute",
        "count": 3,
        "note": "Source contains download and execute; review its purpose.",
        "location_count": 1,
        "path": "deploy/install.sh"
      },
      {
        "kind": "known-vulnerability",
        "count": 34,
        "note": "OSV reports a known vulnerability in this dependency version.",
        "location_count": 3
      }
    ],
    "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=cosmin-novac--memry-gpt-6-luna-1793175527368646453",
    "evidence_file": "/data/safety/cosmin-novac--memry-gpt-6-luna-1793175527368646453.json.gz"
  },
  "agent_execution": "native_agent",
  "agent_runtime": "codex",
  "agent_runtime_version": "codex-cli 0.164.0",
  "tool_transport": "mcp-assigned-vm",
  "platform": "linux",
  "reasoning": "low",
  "service_tier": "standard",
  "resources": {
    "cpus": 2,
    "memory_mib": 4096,
    "disk_mib": 32768
  },
  "native_tool_calls": 10,
  "native_bundle": null,
  "architecture": null,
  "backend": "hyperv",
  "platform_details": {
    "backend": "hyperv",
    "os": "linux"
  },
  "platform_conflicts": null,
  "sandbox_source": null,
  "source_pin": {
    "commit": "9fb6e61975b9ff7f6fee85ec9d4112d1c0c2d8a7",
    "url": "https://github.com/cosmin-novac/memry"
  },
  "purpose": "initial",
  "profile": {
    "model": "gpt-6-luna",
    "reasoning": "low"
  },
  "fault": {
    "owner": null,
    "status": "resolved",
    "reason": null
  },
  "fix_id": null,
  "verifies_run_id": null,
  "hosting": null,
  "operation_scope": "product operation",
  "tool_calls": 10,
  "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": "none",
  "needs": [],
  "needs_which": null,
  "agent_interface": [
    "cli"
  ],
  "license": "Apache-2.0",
  "repo_url": "https://github.com/cosmin-novac/memry",
  "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": "Inspected README quickstart and CLI entrypoints; they document explicit add/search/eval operations and no cron, scheduled loop, webhook, --once, or --now cycle.",
      "evidence": "Inspected README quickstart and CLI entrypoints; they document explicit add/search/eval operations and no cron, scheduled loop, webhook, --once, or --now cycle.",
      "command": ""
    }
  ],
  "claims": [
    {
      "kind": "claim",
      "claim": "The built-in evaluation harness scores retrieval deterministically and offline.",
      "source": "The harness ingests each case through the full write path, then scores retrieval",
      "input": "evals/datasets/synthetic_v1.jsonl -k 5",
      "expected": "recall@5:     1.000",
      "command": "/tmp/memry-venv/bin/memry eval --dataset evals/datasets/synthetic_v1.jsonl -k 5",
      "verdict": "yes",
      "outcome": "Real input produced the expected result: recall@5:     1.000",
      "evidence": "recall@5:     1.000\nMRR:          0.814\nsearch p50:   0.7 ms   p95: 1.0 ms\nllm:          none   embedder: hash:v1-256\n",
      "returncode": 0,
      "source_checked": true,
      "source_file": "README.md"
    }
  ],
  "claims_note": null,
  "example_checks": [
    {
      "kind": "example",
      "claim": "Run the synthetic retrieval evaluation",
      "source": "README.md / Evaluation",
      "input": "synthetic_v1.jsonl, k=5",
      "command": "/tmp/memry-venv/bin/memry eval --dataset evals/datasets/synthetic_v1.jsonl -k 5",
      "evidence": "dataset:      evals/datasets/synthetic_v1.jsonl\ncases:        8  questions: 17\nmemories:     19\nrecall@5:     1.000\nMRR:          0.814\nsearch p50:   0.7 ms   p95: 0.8 ms\nllm:          none   embedder: hash:v1-256",
      "deferred": false,
      "expected": "retrieval metrics",
      "returncode": 0,
      "verdict": "yes",
      "outcome": "command completed successfully"
    }
  ],
  "does_what_it_says": "yes",
  "maintenance": {
    "archived": false,
    "commits_90d": 231,
    "last_commit_at": "2026-10-28T06:27:15Z",
    "last_release_at": "2026-10-28T06:29:48Z",
    "median_reply_hours": null,
    "merged_prs_90d": 19,
    "note": "actively maintained: last commit 0 days ago; 231 commits and 19 merged PRs in 90 days; 0 open issues, 0 open PRs; latest release 2026-10-28",
    "open_issues": 0,
    "open_prs": 0,
    "reply_share": null,
    "reply_threads": 0,
    "verdict": "maintained"
  },
  "maintenance_verdict": "maintained",
  "maintenance_note": "actively maintained: last commit 0 days ago; 231 commits and 19 merged PRs in 90 days; 0 open issues, 0 open PRs; latest release 2026-10-28",
  "maintained": "active",
  "maintained_note": "last commit 0 days ago",
  "last_commit_at": "2026-10-28T06:29:47Z",
  "last_release_at": "2026-10-28T06:29:48Z",
  "open_issues": null,
  "answered_issues": null,
  "platforms_claimed": [
    "linux"
  ],
  "topic": "mcp-server",
  "agent_interfaces": [
    {
      "interface": "mcp",
      "evidence": "README metadata",
      "observed": false,
      "operation_checked": false
    },
    {
      "interface": "cli",
      "evidence": "independent checker",
      "observed": true,
      "operation_checked": true
    },
    {
      "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": null,
  "tested_at": "2026-10-28T08:20:35.363189+00:00",
  "tested_commit": "9fb6e61975b9ff7f6fee85ec9d4112d1c0c2d8a7",
  "tested_with": {
    "agent": "codex",
    "agent_version": "codex-cli 0.164.0",
    "model": "gpt-6-luna",
    "model_route": "gpt-6-luna",
    "reasoning": "low",
    "os": "linux",
    "backend": "hyperv",
    "transport": "mcp-assigned-vm"
  },
  "setup_identity": {
    "repo": "cosmin-novac/memry",
    "source": "https://github.com/cosmin-novac/memry",
    "commit": "9fb6e61975b9ff7f6fee85ec9d4112d1c0c2d8a7",
    "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 0.164.0",
    "tool_transport": "mcp-assigned-vm",
    "runtime": null,
    "runtime_version": null,
    "runtime_revision": null,
    "sandbox_source": null,
    "guest_setup": null,
    "source_pin": {
      "commit": "9fb6e61975b9ff7f6fee85ec9d4112d1c0c2d8a7",
      "url": "https://github.com/cosmin-novac/memry"
    },
    "platform_details": {
      "os": "linux",
      "backend": "hyperv"
    },
    "platform_conflicts": null,
    "reasoning": "low",
    "service_tier": "standard",
    "resources": {
      "cpus": 2,
      "memory_mib": 4096,
      "disk_mib": 32768
    },
    "operation": "Run the synthetic retrieval evaluation",
    "operation_scope": "product operation",
    "hosting": null,
    "kind": "repo",
    "test_version": "readme-604d73685be33b2939b2632791fb1de37972f659febb28a139c60d6e81057c18",
    "evidence_version": null
  },
  "other_model": null,
  "other_run_id": null,
  "models_agree": null,
  "furthest_model": null,
  "transcript_url": "/transcripts/cosmin-novac--memry-gpt-6-luna-1793175527368646453.txt",
  "report_url": "/reports/cosmin-novac--memry-gpt-6-luna-1793175527368646453.json"
}