diff --git a/CHANGELOG.md b/CHANGELOG.md index 7acdedf6b..f7607fd02 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -15,6 +15,8 @@ the five borough cores load and `CCTV_NYC_MAX_SOURCES` changes the cap. The catalog-wide ceiling is unchanged; extra cameras share it round-robin with the other packs. +- Tool string length validation counts Unicode characters correctly, including characters outside the basic multilingual plane. + - Treat explicitly current, complete empty vessel coverage as a successful update, clearing obsolete contacts while retaining stale or incomplete snapshots. diff --git a/docs/CURRENT-STATE.md b/docs/CURRENT-STATE.md index c77d1d8e3..7e1970768 100644 --- a/docs/CURRENT-STATE.md +++ b/docs/CURRENT-STATE.md @@ -5310,3 +5310,8 @@ datacenters, dams and the Nepal locator retain that shared credit while displaye Military fragments stitch by source identity. Different mapped parcels merge only when their footprints touch or contain one another, never across a seam tolerance gap. + + +### fix(tools): enforce string schema lengths by Unicode code point + +Count code points for minLength and maxLength, preserving ASCII behavior and regular-expression validation. diff --git a/src/tools/schema.js b/src/tools/schema.js index 7c40c3eb5..cdb63cfc1 100644 --- a/src/tools/schema.js +++ b/src/tools/schema.js @@ -106,9 +106,10 @@ export function validateValue(schema, value, path = 'arguments') { fail('must be a string'); break; } - if (schema.minLength != null && value.length < schema.minLength) + const length = [...value].length; + if (schema.minLength != null && length < schema.minLength) fail(`must be at least ${schema.minLength} characters`); - if (schema.maxLength != null && value.length > schema.maxLength) + if (schema.maxLength != null && length > schema.maxLength) fail(`must be at most ${schema.maxLength} characters`); if ( schema.pattern !== undefined && diff --git a/src/tools/tool-schema-codepoints.test.mjs b/src/tools/tool-schema-codepoints.test.mjs new file mode 100644 index 000000000..c379b77e9 --- /dev/null +++ b/src/tools/tool-schema-codepoints.test.mjs @@ -0,0 +1,20 @@ +import test from 'node:test'; +import assert from 'node:assert/strict'; +import { validateValue } from './schema.js'; +test('tool string schemas count Unicode characters rather than UTF-16 units', () => { + const value = '𠮷野家😀'; + assert.deepEqual(validateValue({ type: 'string', maxLength: 4 }, value), []); + assert.equal( + validateValue({ type: 'string', minLength: 5 }, value).length, + 1, + ); + assert.equal( + validateValue({ type: 'string', maxLength: 3 }, value).length, + 1, + ); + assert.deepEqual( + validateValue({ type: 'string', minLength: 4, maxLength: 4 }, 'abcd'), + [], + ); + assert.equal(validateValue({ type: 'string', minLength: 2 }, '𠮷').length, 1); +});