recordings_visual_identity_read

Default model descriptor

{
  "name": "recordings_visual_identity_read",
  "title": "Read image identifications and application status",
  "description": "Read saved exact-image answers, current native background work, capability limits and guarded recovery actions. Optional contextual image questions include source time, marked box, media evidence and a signed question_context. Inspect the actual evidence before answering; raw examples are not a recognition-training checklist. Poll pending application with include_questions false. A completed update does not establish identity throughout a Recording.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "recording_id": {
        "type": "string"
      },
      "source_seconds": {
        "type": "number",
        "minimum": 0,
        "description": "Deliberately inspect retained marked images nearest this Recording time. Returned times are exact; do not assume the requested time was sampled."
      },
      "include_questions": {
        "type": "boolean",
        "default": true
      },
      "visual_identity_decision_id": {
        "type": "string"
      }
    },
    "required": [
      "recording_id"
    ],
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": true,
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false
  },
  "securitySchemes": [
    {
      "type": "noauth"
    }
  ],
  "_meta": {
    "securitySchemes": [
      {
        "type": "noauth"
      }
    ],
    "ui": {
      "visibility": [
        "model",
        "app"
      ]
    },
    "openai/widgetAccessible": true
  }
}

App descriptor

{
  "name": "recordings_visual_identity_read",
  "title": "Read image identifications and application status",
  "description": "Read saved exact-image answers, current native background work, capability limits and guarded recovery actions. Optional contextual image questions include source time, marked box, media evidence and a signed question_context. Inspect the actual evidence before answering; raw examples are not a recognition-training checklist. Poll pending application with include_questions false. A completed update does not establish identity throughout a Recording.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "recording_id": {
        "type": "string"
      },
      "source_seconds": {
        "type": "number",
        "minimum": 0,
        "description": "Deliberately inspect retained marked images nearest this Recording time. Returned times are exact; do not assume the requested time was sampled."
      },
      "include_questions": {
        "type": "boolean",
        "default": true
      },
      "visual_identity_decision_id": {
        "type": "string"
      }
    },
    "required": [
      "recording_id"
    ],
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": true,
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false
  },
  "securitySchemes": [
    {
      "type": "noauth"
    }
  ],
  "_meta": {
    "securitySchemes": [
      {
        "type": "noauth"
      }
    ],
    "ui": {
      "visibility": [
        "model",
        "app"
      ]
    },
    "openai/widgetAccessible": true
  },
  "outputSchema": {
    "type": "object",
    "properties": {
      "recording_id": {
        "type": "string"
      },
      "visual_identity_questions": {
        "type": "object"
      },
      "decision": {
        "type": "object"
      }
    },
    "required": [],
    "additionalProperties": false
  }
}

Live Workspace descriptor

{
  "name": "recordings_visual_identity_read",
  "title": "Read image identifications and application status",
  "description": "Read saved exact-image answers, current native background work, capability limits and guarded recovery actions. Optional contextual image questions include source time, marked box, media evidence and a signed question_context. Inspect the actual evidence before answering; raw examples are not a recognition-training checklist. Poll pending application with include_questions false. A completed update does not establish identity throughout a Recording.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "recording_id": {
        "type": "string"
      },
      "source_seconds": {
        "type": "number",
        "minimum": 0,
        "description": "Deliberately inspect retained marked images nearest this Recording time. Returned times are exact; do not assume the requested time was sampled."
      },
      "include_questions": {
        "type": "boolean",
        "default": true
      },
      "visual_identity_decision_id": {
        "type": "string"
      }
    },
    "required": [
      "recording_id"
    ],
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": true,
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false
  },
  "securitySchemes": [
    {
      "type": "noauth"
    }
  ],
  "_meta": {
    "securitySchemes": [
      {
        "type": "noauth"
      }
    ]
  },
  "outputSchema": {
    "type": "object",
    "properties": {
      "recording_id": {
        "type": "string"
      },
      "visual_identity_questions": {
        "type": "object"
      },
      "decision": {
        "type": "object"
      }
    },
    "required": [],
    "additionalProperties": false
  }
}

Errors

[
  "recording_not_found",
  "visual_identity_decision_not_found",
  "invalid_input"
]

Examples

[]