View as Markdown

Default model tools

recording_sample_frames

Sample video frames from a recording

Inspects raw Recording pixels directly on the recording's SOURCE-time axis, including capture-session footage that intentionally has no Episode-of-one. It samples up to 4 explicit source-time points or up to 8 deterministic frames inside one <=30s region. This operation never creates or mutates an Episode, Program, or Recording. It serves choosing exact recording_id ranges for one multi-source episode_create, with no throwaway Episode as a visual probe. Results contain source-time and recording identity only—no fabricated Episode revision, Program camera, or occurrence fields. Every call publishes bounded, unguessable frame URLs and a gallery. Without delivery, extracted JPEGs that fit the aggregate model-content budget arrive inline, and otherwise as linked delivery from the same artifacts. BitterClip samples pixels; it does not interpret them.

Surface: Default model and app

Product release eb8538f4a297f331d0399351c1e175bffcd212d2
Public contract commit 20688e11af473a363145ed880d5019c90a7ec1e2
Public contract SHA-256 87a94b85a84dc19245fc03f9b544c70d64bd9f5e08585dcccb38157cace5700d
Captured 2026-10-04T11:55:45.577Z. Review or improve this contract on GitHub.

These blocks show the complete MCP descriptors captured from serving Rails. Security schemes and resource URIs can differ by connected host.

Default model descriptor

{
  "name": "recording_sample_frames",
  "title": "Sample video frames from a recording",
  "description": "Inspects raw Recording pixels directly on the recording's SOURCE-time axis, including capture-session footage that intentionally has no Episode-of-one. It samples up to 4 explicit source-time points or up to 8 deterministic frames inside one <=30s region. This operation never creates or mutates an Episode, Program, or Recording. It serves choosing exact recording_id ranges for one multi-source episode_create, with no throwaway Episode as a visual probe. Results contain source-time and recording identity only—no fabricated Episode revision, Program camera, or occurrence fields. Every call publishes bounded, unguessable frame URLs and a gallery. Without delivery, extracted JPEGs that fit the aggregate model-content budget arrive inline, and otherwise as linked delivery from the same artifacts. BitterClip samples pixels; it does not interpret them.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "recording_id": {
        "type": "string",
        "description": "Exact src_... Recording handle returned by recordings_list or Project evidence."
      },
      "times": {
        "type": "array",
        "description": "Explicit Recording SOURCE-time seconds. Exactly one of times or region is allowed. Maximum 4.",
        "items": {
          "type": "number",
          "minimum": 0
        },
        "minItems": 1,
        "maxItems": 4
      },
      "region": {
        "type": "array",
        "description": "Recording SOURCE-time [start_seconds, end_seconds] region sampled at deterministic interior midpoints. Exactly one of times or region is allowed. Hard cap 30 seconds.",
        "items": {
          "type": "number",
          "minimum": 0
        },
        "minItems": 2,
        "maxItems": 2
      },
      "count": {
        "type": "integer",
        "description": "Frames from one <=30s region. Default 5, maximum 8.",
        "minimum": 1,
        "maximum": 8
      },
      "detail": {
        "type": "string",
        "enum": [
          "standard",
          "high"
        ],
        "description": "standard is the default; high is for fine visual evidence."
      },
      "delivery": {
        "type": "string",
        "enum": [
          "inline",
          "links"
        ],
        "description": "Optional explicit delivery override. When omitted, extracted JPEGs resolve to inline when their aggregate bytes fit the model-content budget and to links otherwise. inline returns adjacent JPEG image blocks plus URLs; links omits only the JPEG blocks while retaining inline captions, camera provenance, and public gallery/frame URLs."
      },
      "purpose": {
        "type": "string",
        "description": "Optional short reason for sampling, echoed in the result."
      }
    },
    "required": [
      "recording_id"
    ],
    "additionalProperties": false,
    "allOf": [
      {
        "oneOf": [
          {
            "required": [
              "times"
            ]
          },
          {
            "required": [
              "region"
            ]
          }
        ]
      }
    ]
  },
  "annotations": {
    "title": "Sample video frames from a recording",
    "readOnlyHint": false,
    "destructiveHint": false,
    "idempotentHint": false,
    "openWorldHint": false
  },
  "securitySchemes": [
    {
      "type": "noauth"
    }
  ],
  "_meta": {
    "securitySchemes": [
      {
        "type": "noauth"
      }
    ],
    "ui": {
      "resourceUri": "ui://bitterclip/frame-sample-gallery.862dbf163e33.html",
      "visibility": [
        "model",
        "app"
      ]
    },
    "openai/widgetAccessible": true,
    "openai/outputTemplate": "ui://bitterclip/frame-sample-gallery.862dbf163e33.html",
    "openai/toolInvocation/invoking": "Sampling recording...",
    "openai/toolInvocation/invoked": "Frames ready"
  }
}

App descriptor

{
  "name": "recording_sample_frames",
  "title": "Sample video frames from a recording",
  "description": "Inspects raw Recording pixels directly on the recording's SOURCE-time axis, including capture-session footage that intentionally has no Episode-of-one. It samples up to 4 explicit source-time points or up to 8 deterministic frames inside one <=30s region. This operation never creates or mutates an Episode, Program, or Recording. It serves choosing exact recording_id ranges for one multi-source episode_create, with no throwaway Episode as a visual probe. Results contain source-time and recording identity only—no fabricated Episode revision, Program camera, or occurrence fields. Every call publishes bounded, unguessable frame URLs and a gallery. Without delivery, extracted JPEGs that fit the aggregate model-content budget arrive inline, and otherwise as linked delivery from the same artifacts. BitterClip samples pixels; it does not interpret them.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "recording_id": {
        "type": "string",
        "description": "Exact src_... Recording handle returned by recordings_list or Project evidence."
      },
      "times": {
        "type": "array",
        "description": "Explicit Recording SOURCE-time seconds. Exactly one of times or region is allowed. Maximum 4.",
        "items": {
          "type": "number",
          "minimum": 0
        },
        "minItems": 1,
        "maxItems": 4
      },
      "region": {
        "type": "array",
        "description": "Recording SOURCE-time [start_seconds, end_seconds] region sampled at deterministic interior midpoints. Exactly one of times or region is allowed. Hard cap 30 seconds.",
        "items": {
          "type": "number",
          "minimum": 0
        },
        "minItems": 2,
        "maxItems": 2
      },
      "count": {
        "type": "integer",
        "description": "Frames from one <=30s region. Default 5, maximum 8.",
        "minimum": 1,
        "maximum": 8
      },
      "detail": {
        "type": "string",
        "enum": [
          "standard",
          "high"
        ],
        "description": "standard is the default; high is for fine visual evidence."
      },
      "delivery": {
        "type": "string",
        "enum": [
          "inline",
          "links"
        ],
        "description": "Optional explicit delivery override. When omitted, extracted JPEGs resolve to inline when their aggregate bytes fit the model-content budget and to links otherwise. inline returns adjacent JPEG image blocks plus URLs; links omits only the JPEG blocks while retaining inline captions, camera provenance, and public gallery/frame URLs."
      },
      "purpose": {
        "type": "string",
        "description": "Optional short reason for sampling, echoed in the result."
      }
    },
    "required": [
      "recording_id"
    ],
    "additionalProperties": false,
    "allOf": [
      {
        "oneOf": [
          {
            "required": [
              "times"
            ]
          },
          {
            "required": [
              "region"
            ]
          }
        ]
      }
    ]
  },
  "annotations": {
    "title": "Sample video frames from a recording",
    "readOnlyHint": false,
    "destructiveHint": false,
    "idempotentHint": false,
    "openWorldHint": false
  },
  "securitySchemes": [
    {
      "type": "noauth"
    }
  ],
  "_meta": {
    "securitySchemes": [
      {
        "type": "noauth"
      }
    ],
    "ui": {
      "resourceUri": "ui://bitterclip/frame-sample-gallery.862dbf163e33.html",
      "visibility": [
        "model",
        "app"
      ]
    },
    "openai/widgetAccessible": true,
    "openai/outputTemplate": "ui://bitterclip/frame-sample-gallery.862dbf163e33.html",
    "openai/toolInvocation/invoking": "Sampling recording...",
    "openai/toolInvocation/invoked": "Frames ready"
  },
  "outputSchema": {
    "type": "object",
    "properties": {
      "subject_type": {
        "type": "string",
        "enum": [
          "recording"
        ]
      },
      "recording_id": {
        "type": "string",
        "description": "Authorized Recording sampled."
      },
      "purpose": {
        "type": [
          "string",
          "null"
        ]
      },
      "duration_seconds": {
        "type": "number",
        "description": "Recording source duration used for this sample."
      },
      "detail": {
        "type": "string",
        "enum": [
          "standard",
          "high"
        ]
      },
      "delivery": {
        "type": "string",
        "enum": [
          "inline",
          "links"
        ]
      },
      "projection": {
        "type": "string",
        "enum": [
          "original"
        ]
      },
      "presentation": {
        "type": "string",
        "enum": [
          "source"
        ]
      },
      "content_bytes": {
        "type": "integer"
      },
      "sampled_pixel_change": {
        "type": "object",
        "description": "Bounded mean-absolute channel difference between consecutive successful sampled stills in chronological Recording SOURCE time, compared on a 64×64 sRGB 3-band raster. Returned artifact dimensions stay native. This is a measurement at sampled instants only: it does not observe anything between samples and is not a motion, duration, payoff, quality, or taste claim. Decode failure is typed unavailable without fabricating a zero.",
        "properties": {
          "status": {
            "type": "string",
            "enum": [
              "measured",
              "insufficient",
              "unavailable"
            ]
          },
          "reason": {
            "type": [
              "string",
              "null"
            ],
            "description": "Typed reason when status is insufficient or unavailable."
          },
          "metric": {
            "type": [
              "string",
              "null"
            ],
            "description": "mean_absolute_channel_difference when a pair could be scored."
          },
          "overall_level": {
            "type": [
              "string",
              "null"
            ],
            "enum": [
              "none",
              "near_zero",
              "low",
              "moderate",
              "high",
              null
            ],
            "description": "Coarse class of the largest measured adjacent pair; null when unmeasured."
          },
          "overall_normalized_difference": {
            "type": [
              "number",
              "null"
            ],
            "description": "Largest adjacent-pair difference in [0, 1] when measured."
          },
          "summary": {
            "type": "string",
            "description": "Literal measurement sentence. Does not claim events between samples."
          },
          "pairs": {
            "type": "array",
            "description": "Chronological adjacent pairs on Recording SOURCE time. Request order is not used.",
            "items": {
              "type": "object",
              "properties": {
                "from_seconds": {
                  "type": "number"
                },
                "to_seconds": {
                  "type": "number"
                },
                "time_axis": {
                  "type": "string",
                  "enum": [
                    "episode",
                    "source"
                  ]
                },
                "from_camera_ref": {
                  "type": "string"
                },
                "to_camera_ref": {
                  "type": "string"
                },
                "status": {
                  "type": "string",
                  "enum": [
                    "measured",
                    "unavailable"
                  ]
                },
                "reason": {
                  "type": [
                    "string",
                    "null"
                  ]
                },
                "normalized_difference": {
                  "type": [
                    "number",
                    "null"
                  ]
                },
                "level": {
                  "type": [
                    "string",
                    "null"
                  ],
                  "enum": [
                    "none",
                    "near_zero",
                    "low",
                    "moderate",
                    "high",
                    null
                  ]
                }
              },
              "required": [
                "from_seconds",
                "to_seconds",
                "status"
              ]
            }
          }
        },
        "required": [
          "status",
          "summary",
          "pairs"
        ]
      },
      "mode": {
        "type": "string",
        "enum": [
          "times",
          "region"
        ]
      },
      "region": {
        "type": [
          "array",
          "null"
        ],
        "items": {
          "type": "number"
        },
        "description": "Resolved source-time region in region mode."
      },
      "sample_id": {
        "type": "string"
      },
      "gallery_url": {
        "type": "string"
      },
      "sample_expires_at": {
        "type": [
          "string",
          "null"
        ]
      },
      "manifest_url": {
        "type": [
          "string",
          "null"
        ]
      },
      "frame_artifact_delivery": {
        "type": "string",
        "enum": [
          "cdn",
          "public_route"
        ]
      },
      "handle_policy": {
        "type": "string",
        "description": "Handle policy: raw Recording handles are tool-call-only, not user-facing."
      },
      "frames": {
        "type": "array",
        "description": "Recording frames with source-time provenance and public image handles.",
        "items": {
          "type": "object",
          "properties": {
            "frame_id": {
              "type": "string"
            },
            "sample_id": {
              "type": "string"
            },
            "caption": {
              "type": "string"
            },
            "source_seconds": {
              "type": "number"
            },
            "source_timecode": {
              "type": "string"
            },
            "recording_id": {
              "type": "string"
            },
            "source_id": {
              "type": "string"
            },
            "source_title": {
              "type": [
                "string",
                "null"
              ]
            },
            "projection": {
              "type": "string",
              "enum": [
                "original"
              ]
            },
            "presentation": {
              "type": "string",
              "enum": [
                "source"
              ]
            },
            "width": {
              "type": "integer"
            },
            "height": {
              "type": "integer"
            },
            "mime_type": {
              "type": "string"
            },
            "image_url": {
              "type": "string"
            },
            "thumbnail_url": {
              "type": "string"
            },
            "download_url": {
              "type": "string"
            },
            "open_url": {
              "type": "string"
            }
          },
          "required": [
            "frame_id",
            "sample_id",
            "caption",
            "source_seconds",
            "source_timecode",
            "recording_id",
            "source_id",
            "projection",
            "presentation",
            "width",
            "height",
            "mime_type",
            "image_url",
            "thumbnail_url",
            "download_url",
            "open_url"
          ]
        }
      },
      "errors": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "source_seconds": {
              "type": [
                "number",
                "null"
              ]
            },
            "error_code": {
              "type": "string"
            },
            "message": {
              "type": "string"
            }
          },
          "required": [
            "error_code",
            "message"
          ]
        }
      },
      "camera_refs": {
        "type": [
          "array",
          "null"
        ],
        "description": "Comparison contact-sheet column order; null for an ordinary single-camera sample.",
        "items": {
          "type": "string"
        }
      },
      "model_image_delivery": {
        "type": "string",
        "enum": [
          "frames",
          "contact_sheet",
          "none"
        ],
        "description": "Shape of model-visible image content for this result."
      },
      "model_image_count": {
        "type": "integer",
        "description": "Number of adjacent MCP image blocks: one for a comparison contact sheet, individual frame count for ordinary inline delivery, or zero for links."
      }
    },
    "required": [
      "subject_type",
      "recording_id",
      "sample_id",
      "gallery_url",
      "mode",
      "projection",
      "presentation",
      "duration_seconds",
      "detail",
      "frames",
      "errors",
      "sampled_pixel_change"
    ],
    "additionalProperties": false
  }
}

Live Workspace descriptor

{
  "name": "recording_sample_frames",
  "title": "Sample video frames from a recording",
  "description": "Inspects raw Recording pixels directly on the recording's SOURCE-time axis, including capture-session footage that intentionally has no Episode-of-one. It samples up to 4 explicit source-time points or up to 8 deterministic frames inside one <=30s region. This operation never creates or mutates an Episode, Program, or Recording. It serves choosing exact recording_id ranges for one multi-source episode_create, with no throwaway Episode as a visual probe. Results contain source-time and recording identity only—no fabricated Episode revision, Program camera, or occurrence fields. Every call publishes bounded, unguessable frame URLs and a gallery. Without delivery, extracted JPEGs that fit the aggregate model-content budget arrive inline, and otherwise as linked delivery from the same artifacts. BitterClip samples pixels; it does not interpret them.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "recording_id": {
        "type": "string",
        "description": "Exact src_... Recording handle returned by recordings_list or Project evidence."
      },
      "times": {
        "type": "array",
        "description": "Explicit Recording SOURCE-time seconds. Exactly one of times or region is allowed. Maximum 4.",
        "items": {
          "type": "number",
          "minimum": 0
        },
        "minItems": 1,
        "maxItems": 4
      },
      "region": {
        "type": "array",
        "description": "Recording SOURCE-time [start_seconds, end_seconds] region sampled at deterministic interior midpoints. Exactly one of times or region is allowed. Hard cap 30 seconds.",
        "items": {
          "type": "number",
          "minimum": 0
        },
        "minItems": 2,
        "maxItems": 2
      },
      "count": {
        "type": "integer",
        "description": "Frames from one <=30s region. Default 5, maximum 8.",
        "minimum": 1,
        "maximum": 8
      },
      "detail": {
        "type": "string",
        "enum": [
          "standard",
          "high"
        ],
        "description": "standard is the default; high is for fine visual evidence."
      },
      "delivery": {
        "type": "string",
        "enum": [
          "inline",
          "links"
        ],
        "description": "Optional explicit delivery override. When omitted, extracted JPEGs resolve to inline when their aggregate bytes fit the model-content budget and to links otherwise. inline returns adjacent JPEG image blocks plus URLs; links omits only the JPEG blocks while retaining inline captions, camera provenance, and public gallery/frame URLs."
      },
      "purpose": {
        "type": "string",
        "description": "Optional short reason for sampling, echoed in the result."
      }
    },
    "required": [
      "recording_id"
    ],
    "additionalProperties": false,
    "allOf": [
      {
        "oneOf": [
          {
            "required": [
              "times"
            ]
          },
          {
            "required": [
              "region"
            ]
          }
        ]
      }
    ]
  },
  "annotations": {
    "title": "Sample video frames from a recording",
    "readOnlyHint": false,
    "destructiveHint": false,
    "idempotentHint": false,
    "openWorldHint": false
  },
  "securitySchemes": [
    {
      "type": "noauth"
    }
  ],
  "_meta": {
    "securitySchemes": [
      {
        "type": "noauth"
      }
    ],
    "openai/toolInvocation/invoking": "Sampling recording...",
    "openai/toolInvocation/invoked": "Frames ready"
  },
  "outputSchema": {
    "type": "object",
    "properties": {
      "subject_type": {
        "type": "string",
        "enum": [
          "recording"
        ]
      },
      "recording_id": {
        "type": "string",
        "description": "Authorized Recording sampled."
      },
      "purpose": {
        "type": [
          "string",
          "null"
        ]
      },
      "duration_seconds": {
        "type": "number",
        "description": "Recording source duration used for this sample."
      },
      "detail": {
        "type": "string",
        "enum": [
          "standard",
          "high"
        ]
      },
      "delivery": {
        "type": "string",
        "enum": [
          "inline",
          "links"
        ]
      },
      "projection": {
        "type": "string",
        "enum": [
          "original"
        ]
      },
      "presentation": {
        "type": "string",
        "enum": [
          "source"
        ]
      },
      "content_bytes": {
        "type": "integer"
      },
      "sampled_pixel_change": {
        "type": "object",
        "description": "Bounded mean-absolute channel difference between consecutive successful sampled stills in chronological Recording SOURCE time, compared on a 64×64 sRGB 3-band raster. Returned artifact dimensions stay native. This is a measurement at sampled instants only: it does not observe anything between samples and is not a motion, duration, payoff, quality, or taste claim. Decode failure is typed unavailable without fabricating a zero.",
        "properties": {
          "status": {
            "type": "string",
            "enum": [
              "measured",
              "insufficient",
              "unavailable"
            ]
          },
          "reason": {
            "type": [
              "string",
              "null"
            ],
            "description": "Typed reason when status is insufficient or unavailable."
          },
          "metric": {
            "type": [
              "string",
              "null"
            ],
            "description": "mean_absolute_channel_difference when a pair could be scored."
          },
          "overall_level": {
            "type": [
              "string",
              "null"
            ],
            "enum": [
              "none",
              "near_zero",
              "low",
              "moderate",
              "high",
              null
            ],
            "description": "Coarse class of the largest measured adjacent pair; null when unmeasured."
          },
          "overall_normalized_difference": {
            "type": [
              "number",
              "null"
            ],
            "description": "Largest adjacent-pair difference in [0, 1] when measured."
          },
          "summary": {
            "type": "string",
            "description": "Literal measurement sentence. Does not claim events between samples."
          },
          "pairs": {
            "type": "array",
            "description": "Chronological adjacent pairs on Recording SOURCE time. Request order is not used.",
            "items": {
              "type": "object",
              "properties": {
                "from_seconds": {
                  "type": "number"
                },
                "to_seconds": {
                  "type": "number"
                },
                "time_axis": {
                  "type": "string",
                  "enum": [
                    "episode",
                    "source"
                  ]
                },
                "from_camera_ref": {
                  "type": "string"
                },
                "to_camera_ref": {
                  "type": "string"
                },
                "status": {
                  "type": "string",
                  "enum": [
                    "measured",
                    "unavailable"
                  ]
                },
                "reason": {
                  "type": [
                    "string",
                    "null"
                  ]
                },
                "normalized_difference": {
                  "type": [
                    "number",
                    "null"
                  ]
                },
                "level": {
                  "type": [
                    "string",
                    "null"
                  ],
                  "enum": [
                    "none",
                    "near_zero",
                    "low",
                    "moderate",
                    "high",
                    null
                  ]
                }
              },
              "required": [
                "from_seconds",
                "to_seconds",
                "status"
              ]
            }
          }
        },
        "required": [
          "status",
          "summary",
          "pairs"
        ]
      },
      "mode": {
        "type": "string",
        "enum": [
          "times",
          "region"
        ]
      },
      "region": {
        "type": [
          "array",
          "null"
        ],
        "items": {
          "type": "number"
        },
        "description": "Resolved source-time region in region mode."
      },
      "sample_id": {
        "type": "string"
      },
      "gallery_url": {
        "type": "string"
      },
      "sample_expires_at": {
        "type": [
          "string",
          "null"
        ]
      },
      "manifest_url": {
        "type": [
          "string",
          "null"
        ]
      },
      "frame_artifact_delivery": {
        "type": "string",
        "enum": [
          "cdn",
          "public_route"
        ]
      },
      "handle_policy": {
        "type": "string",
        "description": "Handle policy: raw Recording handles are tool-call-only, not user-facing."
      },
      "frames": {
        "type": "array",
        "description": "Recording frames with source-time provenance and public image handles.",
        "items": {
          "type": "object",
          "properties": {
            "frame_id": {
              "type": "string"
            },
            "sample_id": {
              "type": "string"
            },
            "caption": {
              "type": "string"
            },
            "source_seconds": {
              "type": "number"
            },
            "source_timecode": {
              "type": "string"
            },
            "recording_id": {
              "type": "string"
            },
            "source_id": {
              "type": "string"
            },
            "source_title": {
              "type": [
                "string",
                "null"
              ]
            },
            "projection": {
              "type": "string",
              "enum": [
                "original"
              ]
            },
            "presentation": {
              "type": "string",
              "enum": [
                "source"
              ]
            },
            "width": {
              "type": "integer"
            },
            "height": {
              "type": "integer"
            },
            "mime_type": {
              "type": "string"
            },
            "image_url": {
              "type": "string"
            },
            "thumbnail_url": {
              "type": "string"
            },
            "download_url": {
              "type": "string"
            },
            "open_url": {
              "type": "string"
            }
          },
          "required": [
            "frame_id",
            "sample_id",
            "caption",
            "source_seconds",
            "source_timecode",
            "recording_id",
            "source_id",
            "projection",
            "presentation",
            "width",
            "height",
            "mime_type",
            "image_url",
            "thumbnail_url",
            "download_url",
            "open_url"
          ]
        }
      },
      "errors": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "source_seconds": {
              "type": [
                "number",
                "null"
              ]
            },
            "error_code": {
              "type": "string"
            },
            "message": {
              "type": "string"
            }
          },
          "required": [
            "error_code",
            "message"
          ]
        }
      },
      "camera_refs": {
        "type": [
          "array",
          "null"
        ],
        "description": "Comparison contact-sheet column order; null for an ordinary single-camera sample.",
        "items": {
          "type": "string"
        }
      },
      "model_image_delivery": {
        "type": "string",
        "enum": [
          "frames",
          "contact_sheet",
          "none"
        ],
        "description": "Shape of model-visible image content for this result."
      },
      "model_image_count": {
        "type": "integer",
        "description": "Number of adjacent MCP image blocks: one for a comparison contact sheet, individual frame count for ordinary inline delivery, or zero for links."
      }
    },
    "required": [
      "subject_type",
      "recording_id",
      "sample_id",
      "gallery_url",
      "mode",
      "projection",
      "presentation",
      "duration_seconds",
      "detail",
      "frames",
      "errors",
      "sampled_pixel_change"
    ],
    "additionalProperties": false
  }
}

Errors

[
  "recording_not_found",
  "stale_recording",
  "invalid_input",
  "invalid_time_range",
  "time_out_of_range",
  "source_media_unavailable",
  "ffmpeg_busy",
  "ffmpeg_missing",
  "ffmpeg_timeout",
  "frame_extraction_failed",
  "frame_artifact_publish_failed",
  "payload_budget_exceeded"
]

Examples

[
  {
    "label": "Inspect one movement on raw footage",
    "input": {
      "recording_id": "src_...",
      "region": [
        1404,
        1412
      ],
      "count": 4,
      "purpose": "choose the clearest squat repetitions"
    }
  }
]