doc merge

{
  "type": "object",
  "required": [
    "base",
    "a",
    "b"
  ],
  "additionalProperties": false,
  "properties": {
    "base": {
      "type": "object",
      "additionalProperties": false,
      "description": "The common base both versions came from. Exactly one of text, url or content_base64.",
      "properties": {
        "text": {
          "type": "string",
          "maxLength": 200000,
          "description": "The text directly. Cheapest and clearest — its length is billed as counted here."
        },
        "url": {
          "type": "string",
          "maxLength": 2048,
          "description": "Public http(s) URL of a PDF, DOCX, ODT, HTML or text file. Private and local addresses are refused."
        },
        "content_base64": {
          "type": "string",
          "maxLength": 4000000,
          "description": "The file inline, base64."
        },
        "filename": {
          "type": "string",
          "maxLength": 260,
          "description": "Only consulted when the bytes carry no recognisable signature."
        },
        "format": {
          "type": "string",
          "enum": [
            "auto",
            "pdf",
            "docx",
            "odt",
            "html",
            "markdown",
            "rtf",
            "text"
          ],
          "default": "auto",
          "description": "Override the detected format. \"auto\" reads it from the bytes."
        }
      }
    },
    "a": {
      "type": "object",
      "additionalProperties": false,
      "description": "The first version. Same shape as base.",
      "properties": {
        "text": {
          "type": "string",
          "maxLength": 200000,
          "description": "The text directly. Cheapest and clearest — its length is billed as counted here."
        },
        "url": {
          "type": "string",
          "maxLength": 2048,
          "description": "Public http(s) URL of a PDF, DOCX, ODT, HTML or text file. Private and local addresses are refused."
        },
        "content_base64": {
          "type": "string",
          "maxLength": 4000000,
          "description": "The file inline, base64."
        },
        "filename": {
          "type": "string",
          "maxLength": 260,
          "description": "Only consulted when the bytes carry no recognisable signature."
        },
        "format": {
          "type": "string",
          "enum": [
            "auto",
            "pdf",
            "docx",
            "odt",
            "html",
            "markdown",
            "rtf",
            "text"
          ],
          "default": "auto",
          "description": "Override the detected format. \"auto\" reads it from the bytes."
        }
      }
    },
    "b": {
      "type": "object",
      "additionalProperties": false,
      "description": "The second version. Same shape as base.",
      "properties": {
        "text": {
          "type": "string",
          "maxLength": 200000,
          "description": "The text directly. Cheapest and clearest — its length is billed as counted here."
        },
        "url": {
          "type": "string",
          "maxLength": 2048,
          "description": "Public http(s) URL of a PDF, DOCX, ODT, HTML or text file. Private and local addresses are refused."
        },
        "content_base64": {
          "type": "string",
          "maxLength": 4000000,
          "description": "The file inline, base64."
        },
        "filename": {
          "type": "string",
          "maxLength": 260,
          "description": "Only consulted when the bytes carry no recognisable signature."
        },
        "format": {
          "type": "string",
          "enum": [
            "auto",
            "pdf",
            "docx",
            "odt",
            "html",
            "markdown",
            "rtf",
            "text"
          ],
          "default": "auto",
          "description": "Override the detected format. \"auto\" reads it from the bytes."
        }
      }
    },
    "label_a": {
      "type": "string",
      "maxLength": 60,
      "default": "a",
      "description": "Name for the first version, used in conflict markers and in the conflict list."
    },
    "label_b": {
      "type": "string",
      "maxLength": 60,
      "default": "b",
      "description": "Name for the second version."
    },
    "conflict_style": {
      "type": "string",
      "enum": [
        "markers",
        "keep_base",
        "none"
      ],
      "default": "markers",
      "description": "markers: conflicts appear in merged_text between labelled markers. keep_base: the base wording is kept at the conflict site and the conflict is still reported — this is not a resolution. none: merged_text is withheld while any conflict remains."
    },
    "merge_unit": {
      "type": "string",
      "enum": [
        "paragraph",
        "line"
      ],
      "default": "paragraph",
      "description": "What counts as one piece. paragraph: blank lines separate, which is how a contract is read — but two changes inside one paragraph then collide even when they concern different sentences. line: merges more finely and conflicts less often, though a paragraph written as one long line stays one piece either way."
    },
    "ignore_whitespace": {
      "type": "boolean",
      "default": true,
      "description": "Treat runs of spaces and tabs as one space before comparing. Applied to all three documents alike."
    },
    "include_word_diff": {
      "type": "boolean",
      "default": true,
      "description": "Include a word-level diff of each side against the base for every conflict."
    },
    "max_conflicts_detailed": {
      "type": "integer",
      "minimum": 1,
      "maximum": 200,
      "default": 50,
      "description": "How many conflicts come back with their full text. Beyond this they are still counted and still marked in merged_text, only without the detail block."
    }
  }
}