{
  "manifest_version": "0.4",
  "tool": {
    "id": "muninn-memory-tfidf",
    "version": "0.1.0",
    "name": "Muninn memory_tfidf",
    "summary": "TF-IDF index over Muninn's memory summaries. Read-only similarity search, near-duplicate detection, clustering, and outlier identification across the memory store.",
    "description": "Loads all memory summaries from Turso once, builds a sklearn TfidfVectorizer + cosine-similarity matrix, and exposes four read-only queries: duplicates() (pairs above a similarity threshold), similar(id) (top-N for a given memory), clusters() (connected components above threshold), outliers() (memories with low max-similarity to anything else). Build is in-memory and ephemeral; nothing persists between calls in the tool's own storage. Authored as the deliberate **minimum-honest-manifest** consumer test for install-manifest-spec v0.3 \u2014 every required field is present, nothing optional is added past what the tool actually does.",
    "homepage": "https://github.com/oaustegard/muninn-utilities/blob/main/muninn_utils/memory_tfidf.py",
    "author": {
      "name": "Muninn (raven of memory; agent operating on behalf of Oskar Austegard)",
      "url": "https://muninn.austegard.com"
    },
    "license": "MIT",
    "tags": [
      "tf-idf",
      "similarity",
      "clustering",
      "memory",
      "read-only"
    ]
  },
  "runtime": {
    "kind": "python-module",
    "install": {
      "method": "preinstalled",
      "locator": {
        "kind": "python-module",
        "module": "muninn_utils.memory_tfidf"
      }
    },
    "entrypoint": {
      "command": [
        "python",
        "-m",
        "muninn_utils.memory_tfidf"
      ]
    }
  },
  "env": [
    {
      "name": "TURSO_TOKEN",
      "prompt": "Turso libSQL auth token for the memory database. Read-only access is sufficient \u2014 this tool never writes. The token is a coarse credential; treat as a secret.",
      "secret": true,
      "required": true,
      "obtain_url": "https://app.turso.tech/"
    },
    {
      "name": "TURSO_URL",
      "prompt": "Hostname of the Turso libSQL database, e.g. 'mydb-username.turso.io'. The tool reads memories via the libSQL HTTP pipeline endpoint.",
      "secret": false,
      "required": true,
      "validation_regex": "^[a-z0-9-]+\\.[a-z0-9-]+\\.turso\\.io$"
    }
  ],
  "scopes": [
    {
      "resource": "memory.tracking",
      "actions": [
        "read"
      ],
      "rationale": "Reads all memory summaries (id, summary, tags, type) from the Turso DB to build the index. Never writes.",
      "provider_scope": "turso-libsql-token (coarse; full DB access)"
    },
    {
      "resource": "net.outbound",
      "actions": [
        "read"
      ],
      "rationale": "Talks to the configured Turso libSQL host for the initial fetch. No other outbound destinations.",
      "provider_scope": "*.turso.io"
    }
  ],
  "actions": [
    {
      "name": "build_and_query",
      "summary": "Fetch all memory summaries, build the TF-IDF index, and return a query result (duplicates / similar / clusters / outliers).",
      "description": "Single combined action because the build is the expensive step (one SELECT over the full memory table plus the TfidfVectorizer fit). All four query modes share the same matrix; the action takes a `mode` discriminant and the parameters relevant to that mode. The matrix is not cached between invocations \u2014 each call rebuilds. Read-only at every layer.",
      "docs": {
        "goal": "Run a TF-IDF similarity query over the memory store.",
        "inputs_brief": "mode (duplicates|similar|clusters|outliers), threshold (float), id (for similar), n (for similar/outliers)",
        "outputs_brief": "{mode: string, results: array, build_time_ms: number, total_memories: int}",
        "errors_brief": "tracking_unconfigured (TURSO_* not set), tracking_unreachable, mode_unknown, id_not_found",
        "example": "build_and_query mode=duplicates threshold=0.8"
      },
      "invocation": {
        "kind": "stdin-json",
        "argv_template": [
          "build-and-query"
        ]
      },
      "input": {
        "type": "object",
        "required": [
          "mode"
        ],
        "additionalProperties": false,
        "properties": {
          "mode": {
            "type": "string",
            "enum": [
              "duplicates",
              "similar",
              "clusters",
              "outliers"
            ]
          },
          "threshold": {
            "type": "number",
            "minimum": 0,
            "maximum": 1,
            "default": 0.8
          },
          "id": {
            "type": "string",
            "description": "Memory id; required when mode=similar."
          },
          "n": {
            "type": "integer",
            "minimum": 1,
            "maximum": 200,
            "default": 5
          }
        }
      },
      "output": {
        "format": "json",
        "schema": {
          "type": "object",
          "required": [
            "mode",
            "results",
            "build_time_ms",
            "total_memories"
          ],
          "properties": {
            "mode": {
              "type": "string"
            },
            "results": {
              "type": "array"
            },
            "build_time_ms": {
              "type": "number"
            },
            "total_memories": {
              "type": "integer",
              "minimum": 0
            }
          }
        }
      },
      "side_effects": "read",
      "idempotent": true,
      "scopes_used": [
        "memory.tracking",
        "net.outbound"
      ],
      "error_envelope": "standard",
      "runtime_telemetry": {}
    }
  ],
  "smoke": {
    "kind": "shell",
    "command": [
      "python",
      "-c",
      "from muninn_utils.memory_tfidf import MemoryIndex\nidx = MemoryIndex()\nidx.build(memories=[{'id': 'a', 'summary': 'apple banana', 'tags': []}, {'id': 'b', 'summary': 'banana cherry', 'tags': []}])\nassert len(idx.ids) == 2\nprint('OK')\n"
    ],
    "timeout_seconds": 10,
    "success": {
      "exit_code": 0,
      "stdout_regex": "^OK$"
    }
  },
  "kill_switch": {
    "kind": "manual",
    "instructions_url": "https://github.com/oaustegard/muninn-utilities/blob/main/manifests/memory-tfidf/REVOKE.md"
  },
  "cost": {
    "install_fee_cents": 0,
    "monthly_fee_cents": 0,
    "usage_model": "none"
  },
  "support": {
    "issues_url": "https://github.com/oaustegard/muninn-utilities/issues",
    "docs_url": "https://github.com/oaustegard/muninn-utilities/blob/main/muninn_utils/memory_tfidf.py"
  }
}