agent-file-workbench.luo3407056424.chatgpt.site

{
  "type": "object",
  "properties": {
    "fileId": {
      "type": "string",
      "description": "Optional file ID from workspace_file(list); omitted uses the selected file."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "description": "Maximum semantic rows, pages, or slides; defaults to 20."
    },
    "mode": {
      "type": "string",
      "enum": [
        "semantic",
        "sample",
        "profile",
        "query"
      ],
      "description": "DataFrame modes apply only to table files."
    },
    "data": {
      "type": "object",
      "description": "Declarative DataFrame pipeline. Omit fields you do not need.",
      "properties": {
        "sheet": {
          "type": "string",
          "description": "Optional XLSX worksheet name for the selected dataset."
        },
        "joins": {
          "type": "array",
          "description": "Join other imported datasets by file ID. Use base.column and alias.column in select/filter/groupBy when needed.",
          "items": {
            "type": "object",
            "properties": {
              "fileId": {
                "type": "string",
                "description": "Dataset ID returned by workspace_file(list)."
              },
              "alias": {
                "type": "string",
                "description": "Optional source alias; defaults to joined_1, joined_2, and so on."
              },
              "sheet": {
                "type": "string",
                "description": "Optional XLSX worksheet name for this source."
              },
              "type": {
                "type": "string",
                "enum": [
                  "inner",
                  "left",
                  "right",
                  "full"
                ]
              },
              "leftColumn": {
                "type": "string",
                "description": "Column in the selected base dataset."
              },
              "rightColumn": {
                "type": "string",
                "description": "Column in the joined dataset."
              }
            },
            "required": [
              "fileId",
              "leftColumn",
              "rightColumn"
            ],
            "additionalProperties": false
          }
        },
        "unions": {
          "type": "array",
          "description": "Append rows from compatible imported datasets by column name.",
          "items": {
            "type": "object",
            "properties": {
              "fileId": {
                "type": "string",
                "description": "Dataset ID returned by workspace_file(list)."
              },
              "sheet": {
                "type": "string",
                "description": "Optional XLSX worksheet name for this source."
              }
            },
            "required": [
              "fileId"
            ],
            "additionalProperties": false
          }
        },
        "select": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Columns to project; qualified aliases are supported for joins."
        },
        "filters": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "column": {
                "type": "string"
              },
              "operator": {
                "type": "string",
                "enum": [
                  "eq",
                  "neq",
                  "gt",
                  "gte",
                  "lt",
                  "lte",
                  "contains",
                  "starts_with",
                  "ends_with",
                  "in",
                  "is_null",
                  "not_null"
                ]
              },
              "value": {
                "description": "Scalar value, or an array for the in operator."
              }
            },
            "required": [
              "column",
              "operator"
            ],
            "additionalProperties": false
          }
        },
        "groupBy": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Grouping columns."
        },
        "aggregations": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "operation": {
                "type": "string",
                "enum": [
                  "count",
                  "sum",
                  "mean",
                  "min",
                  "max",
                  "median",
                  "nunique"
                ]
              },
              "column": {
                "type": "string",
                "description": "Omit only for count(*)."
              },
              "as": {
                "type": "string",
                "description": "Optional output column name."
              }
            },
            "required": [
              "operation"
            ],
            "additionalProperties": false
          }
        },
        "sort": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "column": {
                "type": "string"
              },
              "direction": {
                "type": "string",
                "enum": [
                  "asc",
                  "desc"
                ]
              }
            },
            "required": [
              "column"
            ],
            "additionalProperties": false
          }
        },
        "offset": {
          "type": "integer",
          "minimum": 0
        },
        "limit": {
          "type": "integer",
          "minimum": 0
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}