{
  "run_id": "doobidoo--mcp-memory-service-gpt-6-luna-1792871321447156136",
  "checker": {
    "claims": [
      {
        "claim": "Store a memory and search by tag",
        "command": "<guest-path> server --http --http-port 18234",
        "evidence": "Probe could not complete: HTTP 404 from http://127.0.0.1:18234/docs (attempts: 404* 404* 404* 404* 404* 404* 404* 404* 404* 404* 404* 404*; * = announced url used)",
        "expected": "The stored memory appears in tag search and has the agent:coldpass tag.",
        "input": "content=Coldpass memory operation sample: project deadline is Friday.; tags=coldpass,deadline; X-Agent-ID=coldpass",
        "kind": "claim",
        "outcome": "Probe could not complete: HTTP 404 from http://127.0.0.1:18234/docs (attempts: 404* 404* 404* 404* 404* 404* 404* 404* 404* 404* 404* 404*; * = announced url used)",
        "source": "Store a memory with `POST /api/memories`, search with `POST /api/search`, retrieve by tag",
        "source_checked": true,
        "source_file": "README.md",
        "verdict": "blocked"
      }
    ],
    "cycle_checks": [
      {
        "claim": "Scheduled or looping main behavior",
        "command": "",
        "evidence": "Inspected README and project entry points; the product exposes memory storage/retrieval APIs and scheduled consolidation, but no required recurring cycle is documented for the quick-start operation.",
        "expected": "identify the product trigger",
        "input": "source inspection",
        "kind": "cycle",
        "outcome": "Inspected README and project entry points; the product exposes memory storage/retrieval APIs and scheduled consolidation, but no required recurring cycle is documented for the quick-start operation.",
        "source": "repository entry points",
        "verdict": "yes"
      }
    ],
    "details": {
      "argv": [
        "<guest-path>",
        "server",
        "--http",
        "--http-port",
        "18234"
      ],
      "blocker": "HTTP 404 from http://127.0.0.1:18234/docs (attempts: 404* 404* 404* 404* 404* 404* 404* 404* 404* 404* 404* 404*; * = announced url used)",
      "kind": "http",
      "working": false
    },
    "evidence_strength": "nothing_checked",
    "example_checks": [
      {
        "claim": "README REST server quick start",
        "command": "<guest-path> server --http --http-port 18234",
        "deferred": false,
        "evidence": "ired permissions.\\nFor more details, see https://huggingface.co/docs/huggingface_hub/authentication\\nInvalid username or password.\nONNX model creation failed, falling back to SentenceTransformer\nNo embedding backend available; using hash embeddings (reduced quality). Install ML dependencies for semantic search: pip install mcp-memory-service[ml]. The hash fallback is refused on databases that already contain memories; set MCP_MEMORY_ALLOW_HASH_EMBEDDINGS=1 to override for testing.\nINFO:     Application startup complete.\nINFO:     Uvicorn running on http://127.0.0.1:18234 (Press CTRL+C to quit)",
        "expected": "Stored content is returned",
        "input": "POST a memory and retrieve by tag",
        "kind": "example",
        "outcome": "command was still running when the product check time ended",
        "source": "README.md \u2014 Agent pipelines (REST API)",
        "verdict": "no"
      }
    ],
    "status": "FAIL"
  },
  "diagnosis": null
}