{
  "id": "text-offset-map",
  "name": "Unicode Evidence Offset Mapping",
  "description": "Translate caller-supplied UTF-8 byte, UTF-16 code-unit or Unicode code-point offsets into all three coordinate systems and LF-based line/column positions. Only exact scalar boundaries are valid; text is never normalized or rewritten.",
  "category": "document-assurance",
  "priceUsd": "0.003",
  "pricingStatus": "proposed-unverified",
  "pricing": {
    "unit": "one successful operation call",
    "proposedNominalUsd": "0.003",
    "sixDecimalTokenBaseUnits": "3000",
    "subscription": false,
    "includesPayerWalletOrNetworkFees": false,
    "liveQuoteVerified": false,
    "condition": "Actual SDK challenge is authoritative only within the caller's explicit authorization; configured six-decimal token peg is an operator assertion, not a conversion guarantee."
  },
  "intents": [
    "Reconcile byte and character offsets from different extraction tools",
    "Convert annotation spans between UTF-8 UTF-16 and code-point systems"
  ],
  "whenToUse": [
    "Reconcile byte and character offsets from different extraction tools",
    "Convert annotation spans between UTF-8 UTF-16 and code-point systems"
  ],
  "whenNotToUse": [
    "Grapheme cluster, display-width, tokenizer or normalization mapping",
    "Offsets into binary files or malformed Unicode"
  ],
  "capabilities": [
    "Rejects offsets inside multibyte UTF-8 sequences or surrogate pairs",
    "Line and column are 1-based; LF starts a new line and CR counts as a scalar",
    "Duplicate offsets preserve caller order"
  ],
  "related": [
    "evidence-quote-check",
    "text-edits-apply"
  ],
  "limits": {
    "inputBytes": 100000,
    "outputBytes": 400000,
    "jsonNodes": 8000,
    "depth": 20,
    "findings": 200,
    "offsets": 1000,
    "textCodeUnits": 90000,
    "lineConvention": "1-based-LF-lines-codepoint-columns"
  },
  "errorCodes": [
    "INPUT_LIMIT",
    "OUTPUT_LIMIT",
    "COMPLEXITY_LIMIT",
    "UNSAFE_KEY",
    "INVALID_UNICODE",
    "INVALID_NUMBER",
    "OFFSET_OUT_OF_RANGE",
    "INVALID_BOUNDARY"
  ],
  "requirementsProfile": {
    "format": "declared-requirements-v1",
    "facts": {
      "execution.suppliedCode": false,
      "execution.remoteMutation": false,
      "execution.llmInference": false,
      "execution.paidMcp": false,
      "verification.semanticTruth": false,
      "verification.sourceAuthenticity": false,
      "verification.liveVulnerabilities": false,
      "numbers.arbitraryPrecisionJson": false,
      "numbers.model": "ieee754-binary64",
      "privacy.requestBodyPersisted": false,
      "execution.deterministic": true,
      "execution.networkAccess": false,
      "privacy.resultBodyPersisted": false,
      "payment.x402": true,
      "payment.mpp": true,
      "operation.id": "text-offset-map",
      "operation.category": "document-assurance",
      "limit.httpRequestBytes": 131072,
      "limit.requestBytes": 100000,
      "limit.responseBytes": 524288,
      "limit.resultBytes": 400000,
      "limit.jsonDepth": 20,
      "limit.jsonNodes": 8000,
      "textOffsets.profile": "unicode-scalar-offset-map-v1",
      "textOffsets.utf8": true,
      "textOffsets.utf16": true,
      "textOffsets.codepoints": true,
      "textOffsets.graphemes": false,
      "textOffsets.lineConvention": "1-based-LF-lines-codepoint-columns",
      "input.text.maxLength": 90000,
      "input.offsets.maxItems": 1000
    },
    "unknownPolicy": "Undeclared requirements are unknown, never compatible. Matching declared facts does not establish semantic fit or input validity.",
    "preflight": "/preflight"
  },
  "documentation": "/reference/tools/text-offset-map.md",
  "serviceContract": "/reference/services/text-offset-map.json",
  "errors": [
    {
      "status": 400,
      "meaning": "Malformed JSON, missing/invalid idempotency key, or payment identifier mismatch",
      "retry": "Correct the request before payment"
    },
    {
      "status": 402,
      "meaning": "Payment challenge or rejected payment",
      "retry": "Use official protocol SDK; inspect payment outcome before another payment"
    },
    {
      "status": 409,
      "meaning": "Idempotency conflict, duplicate proof, or PAYMENT_UNCERTAIN",
      "retry": "Keep original key, body, and proof; reconcile uncertainty with operator; never blindly repay"
    },
    {
      "status": 413,
      "meaning": "Input or generated output too large",
      "retry": "Reduce input; no payment attempted for validation failure"
    },
    {
      "status": 415,
      "meaning": "Unsupported media type or compression",
      "retry": "Send uncompressed application/json"
    },
    {
      "status": 422,
      "meaning": "Schema or service-specific semantic validation failure",
      "retry": "Correct input using returned error code; no payment attempted"
    },
    {
      "status": 429,
      "meaning": "Request/payment-attempt rate exceeded",
      "retry": "Wait for rate limit window; preserve existing payment identity"
    },
    {
      "status": 503,
      "meaning": "Payment configuration/provider/state unavailable, or live DNS preparation failed before settlement",
      "retry": "Check readiness; DNS preparation failures may retry the identical key/body/credential only; uncertainty requires reconciliation"
    }
  ],
  "numericPrecision": "JavaScript IEEE-754 numbers; use strings for large integer IDs/exact decimals where the schema accepts strings. No lossless numeric parsing.",
  "paymentWorkflow": {
    "discoveryOnly": false,
    "supportedProtocols": [
      "x402",
      "mpp"
    ],
    "x402": {
      "credentialHeader": "PAYMENT-SIGNATURE",
      "challengeHeader": "PAYMENT-REQUIRED",
      "receiptHeader": "PAYMENT-RESPONSE",
      "version": 2,
      "scheme": "exact",
      "paymentIdentifier": "payment-identifier extension MUST equal the HTTP Idempotency-Key",
      "sdk": "@x402/core with @x402/evm"
    },
    "mpp": {
      "supported": true,
      "credentialHeader": "Authorization",
      "challengeHeader": "WWW-Authenticate",
      "receiptHeader": "Payment-Receipt",
      "method": "tempo",
      "intent": "charge",
      "sdk": "mppx",
      "tokenDecimals": 6
    },
    "steps": [
      "Check configured readiness and the exact service schema",
      "Generate a fresh random Idempotency-Key for this operation; never use a discovery probe fixture for purchases",
      "Send valid input without a credential to obtain the official protocol challenge",
      "Use the official SDK and authorized wallet to fulfill the challenge",
      "Retry only with identical key, body, protocol and credential",
      "On PAYMENT_UNCERTAIN stop and request operator reconciliation; never blindly pay again"
    ],
    "versionedRetries": "Request fingerprint includes service release version. Retries across a version upgrade can conflict; coordinate upgrades outside the 24-hour replay window and reconcile pending attempts.",
    "docs": "/llms.txt"
  },
  "method": "POST",
  "paths": {
    "x402": "/v1/x402/text-offset-map",
    "mpp": "/v1/mpp/text-offset-map"
  },
  "inputSchema": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "text": {
        "type": "string",
        "maxLength": 90000
      },
      "from": {
        "type": "string",
        "enum": [
          "utf16",
          "utf8",
          "codepoint"
        ]
      },
      "offsets": {
        "maxItems": 1000,
        "type": "array",
        "items": {
          "type": "integer",
          "minimum": 0,
          "maximum": 360000
        }
      }
    },
    "required": [
      "text",
      "from",
      "offsets"
    ],
    "additionalProperties": false
  },
  "outputSchema": {
    "type": "object",
    "required": [
      "operation",
      "version",
      "result",
      "provenance"
    ],
    "properties": {
      "operation": {
        "const": "text-offset-map",
        "type": "string"
      },
      "version": {
        "const": "0.29.0",
        "type": "string"
      },
      "result": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "profile": {
            "type": "string",
            "const": "unicode-scalar-offset-map-v1"
          },
          "points": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "input": {
                  "type": "integer",
                  "minimum": 0,
                  "maximum": 9007199254740991
                },
                "utf16": {
                  "type": "integer",
                  "minimum": 0,
                  "maximum": 9007199254740991
                },
                "utf8": {
                  "type": "integer",
                  "minimum": 0,
                  "maximum": 9007199254740991
                },
                "codepoint": {
                  "type": "integer",
                  "minimum": 0,
                  "maximum": 9007199254740991
                },
                "line": {
                  "type": "integer",
                  "minimum": 0,
                  "maximum": 9007199254740991
                },
                "column": {
                  "type": "integer",
                  "minimum": 0,
                  "maximum": 9007199254740991
                }
              },
              "required": [
                "input",
                "utf16",
                "utf8",
                "codepoint",
                "line",
                "column"
              ],
              "additionalProperties": false
            }
          },
          "totals": {
            "type": "object",
            "properties": {
              "utf16": {
                "type": "integer",
                "minimum": 0,
                "maximum": 9007199254740991
              },
              "utf8": {
                "type": "integer",
                "minimum": 0,
                "maximum": 9007199254740991
              },
              "codepoint": {
                "type": "integer",
                "minimum": 0,
                "maximum": 9007199254740991
              },
              "lines": {
                "type": "integer",
                "minimum": 0,
                "maximum": 9007199254740991
              }
            },
            "required": [
              "utf16",
              "utf8",
              "codepoint",
              "lines"
            ],
            "additionalProperties": false
          },
          "lineConvention": {
            "type": "string",
            "const": "1-based-LF-lines-codepoint-columns"
          }
        },
        "required": [
          "profile",
          "points",
          "totals",
          "lineConvention"
        ],
        "additionalProperties": false
      },
      "provenance": {
        "type": "object",
        "required": [
          "inputSha256",
          "outputSha256",
          "deterministic",
          "externalRequests"
        ],
        "properties": {
          "inputSha256": {
            "type": "string",
            "pattern": "^[a-f0-9]{64}$"
          },
          "outputSha256": {
            "type": "string",
            "pattern": "^[a-f0-9]{64}$"
          },
          "deterministic": {
            "const": true
          },
          "externalRequests": {
            "const": 0
          }
        }
      }
    },
    "additionalProperties": false
  },
  "exampleInput": {
    "text": "A😀\né",
    "from": "utf8",
    "offsets": [
      0,
      1,
      5,
      6,
      8
    ]
  },
  "exampleResponse": {
    "operation": "text-offset-map",
    "version": "0.29.0",
    "result": {
      "profile": "unicode-scalar-offset-map-v1",
      "points": [
        {
          "input": 0,
          "utf16": 0,
          "utf8": 0,
          "codepoint": 0,
          "line": 1,
          "column": 1
        },
        {
          "input": 1,
          "utf16": 1,
          "utf8": 1,
          "codepoint": 1,
          "line": 1,
          "column": 2
        },
        {
          "input": 5,
          "utf16": 3,
          "utf8": 5,
          "codepoint": 2,
          "line": 1,
          "column": 3
        },
        {
          "input": 6,
          "utf16": 4,
          "utf8": 6,
          "codepoint": 3,
          "line": 2,
          "column": 1
        },
        {
          "input": 8,
          "utf16": 5,
          "utf8": 8,
          "codepoint": 4,
          "line": 2,
          "column": 2
        }
      ],
      "totals": {
        "utf16": 5,
        "utf8": 8,
        "codepoint": 4,
        "lines": 2
      },
      "lineConvention": "1-based-LF-lines-codepoint-columns"
    },
    "provenance": {
      "inputSha256": "b96469ff1344750024c3ccbbc17e975ddfefb337ec5759bfd1515689289beee8",
      "outputSha256": "1fd72d8c7258d8e48f78132366cde6e3eceece17efe526d8cf9b606f512113ee",
      "deterministic": true,
      "externalRequests": 0
    }
  },
  "requiredHeaders": {
    "Content-Type": "application/json",
    "Idempotency-Key": "random 16–128 character operation identifier"
  },
  "fixedExample": "/reference/examples/text-offset-map.json",
  "execution": {
    "deterministic": true,
    "externalRequests": 0,
    "maxExternalRequests": 0,
    "resultSnapshotPersisted": false,
    "fixedExampleIsIllustrativeSnapshot": false,
    "requiresPayment": true,
    "supportsMcpExecution": false
  },
  "releaseSnapshot": {
    "format": "static-release-reference-v1",
    "sourceVersion": "0.29.0",
    "sourceRegistrySha256": "a2b5ec09bf6c38b9d2879d746a4fded374f5928b445377b0270ef6aa8e6cac65",
    "generatedAt": "2026-10-06T15:38:00Z",
    "releaseAcceptance": "not-verified-by-generator",
    "runtimeReadiness": "not-evaluated",
    "livePaymentsVerified": false,
    "indexingVerified": false,
    "apiOrigin": null,
    "notice": "Build-time release reference. Runtime readiness, deployment, payment settlement and external indexing are not evaluated here. Prices are proposed; this file cannot authorize execution or payment."
  }
}