@mastra/evals 1.4.0 → 1.5.0-alpha.0

package/dist/chunk-QRAONHNV.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/scorers/code/checks/index.ts"],"names":[],"mappings":";;;;AAoBO,SAAS,QAAA,CAAS,QAAA,EAAkB,OAAA,GAA2B,EAAC,EAAG;AACxE,EAAA,MAAM,EAAE,UAAA,GAAa,IAAA,EAAK,GAAI,OAAA;AAC9B,EAAA,OAAO,YAAA,CAAa;AAAA,IAClB,EAAA,EAAI,gBAAA;AAAA,IACJ,IAAA,EAAM,gBAAA;AAAA,IACN,WAAA,EAAa,8BAA8B,QAAQ,CAAA,CAAA,CAAA;AAAA,IACnD,IAAA,EAAM;AAAA,GACP,CAAA,CACE,UAAA,CAAW,OAAO,EAAE,KAAI,KAAM;AAC7B,IAAA,IAAI,SAAS,GAAA,CAAI,MAAA,CACd,MAAA,CAAO,CAAA,CAAA,KAAK,EAAE,IAAA,KAAS,WAAW,CAAA,CAClC,GAAA,CAAI,OAAK,iCAAA,CAAkC,CAAC,CAAC,CAAA,CAC7C,KAAK,GAAG,CAAA;AACX,IAAA,IAAI,MAAA,GAAS,QAAA;AACb,IAAA,IAAI,UAAA,EAAY;AACd,MAAA,MAAA,GAAS,OAAO,WAAA,EAAY;AAC5B,MAAA,MAAA,GAAS,OAAO,WAAA,EAAY;AAAA,IAC9B;AACA,IAAA,OAAO,EAAE,MAAA,EAAQ,MAAA,EAAQ,OAAO,MAAA,CAAO,QAAA,CAAS,MAAM,CAAA,EAAE;AAAA,EAC1D,CAAC,CAAA,CACA,aAAA,CAAc,CAAC,EAAE,SAAQ,KAAM;AAC9B,IAAA,OAAO,OAAA,CAAQ,oBAAA,EAAsB,KAAA,GAAQ,CAAA,GAAI,CAAA;AAAA,EACnD,CAAC,CAAA;AACL;AAWO,SAAS,QAAA,CAAS,QAAA,EAAkB,OAAA,GAA2B,EAAC,EAAG;AACxE,EAAA,MAAM,EAAE,UAAA,GAAa,IAAA,EAAK,GAAI,OAAA;AAC9B,EAAA,OAAO,YAAA,CAAa;AAAA,IAClB,EAAA,EAAI,gBAAA;AAAA,IACJ,IAAA,EAAM,gBAAA;AAAA,IACN,WAAA,EAAa,wCAAwC,QAAQ,CAAA,CAAA,CAAA;AAAA,IAC7D,IAAA,EAAM;AAAA,GACP,CAAA,CACE,UAAA,CAAW,OAAO,EAAE,KAAI,KAAM;AAC7B,IAAA,IAAI,SAAS,GAAA,CAAI,MAAA,CACd,MAAA,CAAO,CAAA,CAAA,KAAK,EAAE,IAAA,KAAS,WAAW,CAAA,CAClC,GAAA,CAAI,OAAK,iCAAA,CAAkC,CAAC,CAAC,CAAA,CAC7C,KAAK,GAAG,CAAA;AACX,IAAA,IAAI,MAAA,GAAS,QAAA;AACb,IAAA,IAAI,UAAA,EAAY;AACd,MAAA,MAAA,GAAS,OAAO,WAAA,EAAY;AAC5B,MAAA,MAAA,GAAS,OAAO,WAAA,EAAY;AAAA,IAC9B;AACA,IAAA,OAAO,EAAE,QAAQ,MAAA,EAAQ,QAAA,EAAU,CAAC,MAAA,CAAO,QAAA,CAAS,MAAM,CAAA,EAAE;AAAA,EAC9D,CAAC,CAAA,CACA,aAAA,CAAc,CAAC,EAAE,SAAQ,KAAM;AAC9B,IAAA,OAAO,OAAA,CAAQ,oBAAA,EAAsB,QAAA,GAAW,CAAA,GAAI,CAAA;AAAA,EACtD,CAAC,CAAA;AACL;AAWO,SAAS,MAAA,CAAO,QAAA,EAAkB,OAAA,GAA2B,EAAC,EAAG;AACtE,EAAA,MAAM,EAAE,UAAA,GAAa,IAAA,EAAK,GAAI,OAAA;AAC9B,EAAA,OAAO,YAAA,CAAa;AAAA,IAClB,EAAA,EAAI,cAAA;AAAA,IACJ,IAAA,EAAM,cAAA;AAAA,IACN,WAAA,EAAa,4BAA4B,QAAQ,CAAA,CAAA,CAAA;AAAA,IACjD,IAAA,EAAM;AAAA,GACP,CAAA,CACE,UAAA,CAAW,OAAO,EAAE,KAAI,KAAM;AAC7B,IAAA,IAAI,SAAS,GAAA,CAAI,MAAA,CACd,MAAA,CAAO,CAAA,CAAA,KAAK,EAAE,IAAA,KAAS,WAAW,CAAA,CAClC,GAAA,CAAI,OAAK,iCAAA,CAAkC,CAAC,CAAC,CAAA,CAC7C,KAAK,EAAE,CAAA;AACV,IAAA,IAAI,MAAA,GAAS,QAAA;AACb,IAAA,IAAI,UAAA,EAAY;AACd,MAAA,MAAA,GAAS,OAAO,WAAA,EAAY;AAC5B,MAAA,MAAA,GAAS,OAAO,WAAA,EAAY;AAAA,IAC9B;AACA,IAAA,OAAO,EAAE,MAAA,EAAQ,MAAA,EAAQ,OAAA,EAAS,WAAW,MAAA,EAAO;AAAA,EACtD,CAAC,CAAA,CACA,aAAA,CAAc,CAAC,EAAE,SAAQ,KAAM;AAC9B,IAAA,OAAO,OAAA,CAAQ,oBAAA,EAAsB,OAAA,GAAU,CAAA,GAAI,CAAA;AAAA,EACrD,CAAC,CAAA;AACL;AAgBO,SAAS,OAAA,CAAQ,OAAA,EAAiB,OAAA,GAA0B,EAAC,EAAG;AACrE,EAAA,MAAM,EAAE,KAAA,GAAQ,KAAA,EAAM,GAAI,OAAA;AAC1B,EAAA,OAAO,YAAA,CAAa;AAAA,IAClB,EAAA,EAAI,eAAA;AAAA,IACJ,IAAA,EAAM,eAAA;AAAA,IACN,WAAA,EAAa,oCAAoC,OAAO,CAAA,CAAA;AAAA,IACxD,IAAA,EAAM;AAAA,GACP,CAAA,CACE,UAAA,CAAW,OAAO,EAAE,KAAI,KAAM;AAC7B,IAAA,MAAM,SAAS,GAAA,CAAI,MAAA,CAChB,MAAA,CAAO,CAAA,CAAA,KAAK,EAAE,IAAA,KAAS,WAAW,CAAA,CAClC,GAAA,CAAI,OAAK,iCAAA,CAAkC,CAAC,CAAC,CAAA,CAC7C,KAAK,EAAE,CAAA;AACV,IAAA,MAAM,KAAA,GAAQ,KAAA,GAAQ,IAAI,MAAA,CAAO,CAAA,CAAA,EAAI,QAAQ,MAAM,CAAA,CAAA,CAAA,EAAK,OAAA,CAAQ,KAAK,CAAA,GAAI,OAAA;AACzE,IAAA,MAAM,OAAA,GAAU,KAAA,CAAM,IAAA,CAAK,MAAM,CAAA;AACjC,IAAA,OAAO,EAAE,MAAA,EAAQ,OAAA,EAAS,OAAA,CAAQ,QAAA,IAAY,OAAA,EAAQ;AAAA,EACxD,CAAC,CAAA,CACA,aAAA,CAAc,CAAC,EAAE,SAAQ,KAAM;AAC9B,IAAA,OAAO,OAAA,CAAQ,oBAAA,EAAsB,OAAA,GAAU,CAAA,GAAI,CAAA;AAAA,EACrD,CAAC,CAAA;AACL;AAmBO,SAAS,UAAA,CAAW,QAAA,EAAkB,OAAA,GAA6B,EAAC,EAAG;AAC5E,EAAA,MAAM,EAAE,UAAA,GAAa,IAAA,EAAM,SAAA,EAAU,GAAI,OAAA;AACzC,EAAA,OAAO,YAAA,CAAa;AAAA,IAClB,EAAA,EAAI,kBAAA;AAAA,IACJ,IAAA,EAAM,kBAAA;AAAA,IACN,WAAA,EAAa,gCAAgC,QAAQ,CAAA,CAAA,CAAA;AAAA,IACrD,IAAA,EAAM;AAAA,GACP,CAAA,CACE,UAAA,CAAW,OAAO,EAAE,KAAI,KAAM;AAC7B,IAAA,IAAI,SAAS,GAAA,CAAI,MAAA,CACd,MAAA,CAAO,CAAA,CAAA,KAAK,EAAE,IAAA,KAAS,WAAW,CAAA,CAClC,GAAA,CAAI,OAAK,iCAAA,CAAkC,CAAC,CAAC,CAAA,CAC7C,KAAK,GAAG,CAAA;AACX,IAAA,IAAI,MAAA,GAAS,QAAA;AACb,IAAA,IAAI,UAAA,EAAY;AACd,MAAA,MAAA,GAAS,OAAO,WAAA,EAAY;AAC5B,MAAA,MAAA,GAAS,OAAO,WAAA,EAAY;AAAA,IAC9B;AACA,IAAA,MAAM,KAAA,GAAQ,gBAAA,CAAiB,iBAAA,CAAkB,MAAA,EAAQ,MAAM,CAAA;AAC/D,IAAA,OAAO,EAAE,MAAA,EAAQ,MAAA,EAAQ,KAAA,EAAO,SAAA,EAAU;AAAA,EAC5C,CAAC,CAAA,CACA,aAAA,CAAc,CAAC,EAAE,SAAQ,KAAM;AAC9B,IAAA,MAAM,KAAA,GAAQ,OAAA,CAAQ,oBAAA,EAAsB,KAAA,IAAS,CAAA;AACrD,IAAA,MAAM,CAAA,GAAI,QAAQ,oBAAA,EAAsB,SAAA;AACxC,IAAA,OAAO,CAAA,KAAM,MAAA,GAAa,KAAA,IAAS,CAAA,GAAI,IAAI,CAAA,GAAK,KAAA;AAAA,EAClD,CAAC,CAAA;AACL;AAmBO,SAAS,UAAA,CAAW,QAAA,EAAkB,OAAA,GAA6B,EAAC,EAAG;AAC5E,EAAA,MAAM,EAAE,KAAA,GAAQ,CAAA,EAAE,GAAI,OAAA;AACtB,EAAA,OAAO,YAAA,CAAa;AAAA,IAClB,EAAA,EAAI,mBAAA;AAAA,IACJ,IAAA,EAAM,mBAAA;AAAA,IACN,WAAA,EAAa,gBAAgB,QAAQ,CAAA,YAAA,EAAe,QAAQ,CAAA,GAAI,CAAA,UAAA,EAAa,KAAK,CAAA,MAAA,CAAA,GAAW,EAAE,CAAA,CAAA;AAAA,IAC/F,IAAA,EAAM;AAAA,GACP,CAAA,CACE,UAAA,CAAW,OAAO,EAAE,KAAI,KAAM;AAC7B,IAAA,MAAM,EAAE,KAAA,EAAM,GAAI,gBAAA,CAAiB,IAAI,MAAM,CAAA;AAC7C,IAAA,MAAM,QAAQ,KAAA,CAAM,MAAA,CAAO,CAAA,CAAA,KAAK,CAAA,KAAM,QAAQ,CAAA,CAAE,MAAA;AAChD,IAAA,OAAO,EAAE,UAAU,aAAA,EAAe,KAAA,EAAO,aAAa,KAAA,EAAO,MAAA,EAAQ,SAAS,KAAA,EAAM;AAAA,EACtF,CAAC,CAAA,CACA,aAAA,CAAc,CAAC,EAAE,SAAQ,KAAM;AAC9B,IAAA,OAAO,OAAA,CAAQ,oBAAA,EAAsB,MAAA,GAAS,CAAA,GAAI,CAAA;AAAA,EACpD,CAAC,CAAA;AACL;AAWO,SAAS,WAAW,QAAA,EAAkB;AAC3C,EAAA,OAAO,YAAA,CAAa;AAAA,IAClB,EAAA,EAAI,oBAAA;AAAA,IACJ,IAAA,EAAM,oBAAA;AAAA,IACN,WAAA,EAAa,gBAAgB,QAAQ,CAAA,gBAAA,CAAA;AAAA,IACrC,IAAA,EAAM;AAAA,GACP,CAAA,CACE,UAAA,CAAW,OAAO,EAAE,KAAI,KAAM;AAC7B,IAAA,MAAM,EAAE,KAAA,EAAM,GAAI,gBAAA,CAAiB,IAAI,MAAM,CAAA;AAC7C,IAAA,MAAM,QAAQ,KAAA,CAAM,MAAA,CAAO,CAAA,CAAA,KAAK,CAAA,KAAM,QAAQ,CAAA,CAAE,MAAA;AAChD,IAAA,OAAO,EAAE,QAAA,EAAU,KAAA,EAAO,MAAA,EAAQ,UAAU,CAAA,EAAE;AAAA,EAChD,CAAC,CAAA,CACA,aAAA,CAAc,CAAC,EAAE,SAAQ,KAAM;AAC9B,IAAA,OAAO,OAAA,CAAQ,oBAAA,EAAsB,MAAA,GAAS,CAAA,GAAI,CAAA;AAAA,EACpD,CAAC,CAAA;AACL;AAWO,SAAS,UAAU,aAAA,EAAyB;AACjD,EAAA,OAAO,YAAA,CAAa;AAAA,IAClB,EAAA,EAAI,kBAAA;AAAA,IACJ,IAAA,EAAM,kBAAA;AAAA,IACN,WAAA,EAAa,CAAA,yBAAA,EAA4B,aAAA,CAAc,IAAA,CAAK,UAAK,CAAC,CAAA,CAAA,CAAA;AAAA,IAClE,IAAA,EAAM;AAAA,GACP,CAAA,CACE,UAAA,CAAW,OAAO,EAAE,KAAI,KAAM;AAC7B,IAAA,MAAM,EAAE,KAAA,EAAM,GAAI,gBAAA,CAAiB,IAAI,MAAM,CAAA;AAE7C,IAAA,IAAI,UAAA,GAAa,CAAA;AACjB,IAAA,KAAA,MAAW,QAAQ,KAAA,EAAO;AACxB,MAAA,IAAI,aAAa,aAAA,CAAc,MAAA,IAAU,IAAA,KAAS,aAAA,CAAc,UAAU,CAAA,EAAG;AAC3E,QAAA,UAAA,EAAA;AAAA,MACF;AAAA,IACF;AACA,IAAA,MAAM,MAAA,GAAS,eAAe,aAAA,CAAc,MAAA;AAC5C,IAAA,OAAO,EAAE,WAAA,EAAa,KAAA,EAAO,aAAA,EAAe,MAAA,EAAO;AAAA,EACrD,CAAC,CAAA,CACA,aAAA,CAAc,CAAC,EAAE,SAAQ,KAAM;AAC9B,IAAA,OAAO,OAAA,CAAQ,oBAAA,EAAsB,MAAA,GAAS,CAAA,GAAI,CAAA;AAAA,EACpD,CAAC,CAAA;AACL;AAWO,SAAS,aAAa,GAAA,EAAa;AACxC,EAAA,OAAO,YAAA,CAAa;AAAA,IAClB,EAAA,EAAI,sBAAA;AAAA,IACJ,IAAA,EAAM,sBAAA;AAAA,IACN,WAAA,EAAa,4BAA4B,GAAG,CAAA,qBAAA,CAAA;AAAA,IAC5C,IAAA,EAAM;AAAA,GACP,CAAA,CACE,UAAA,CAAW,OAAO,EAAE,KAAI,KAAM;AAC7B,IAAA,MAAM,EAAE,KAAA,EAAM,GAAI,gBAAA,CAAiB,IAAI,MAAM,CAAA;AAC7C,IAAA,OAAO,EAAE,OAAO,KAAA,CAAM,MAAA,EAAQ,KAAK,MAAA,EAAQ,KAAA,CAAM,UAAU,GAAA,EAAI;AAAA,EACjE,CAAC,CAAA,CACA,aAAA,CAAc,CAAC,EAAE,SAAQ,KAAM;AAC9B,IAAA,OAAO,OAAA,CAAQ,oBAAA,EAAsB,MAAA,GAAS,CAAA,GAAI,CAAA;AAAA,EACpD,CAAC,CAAA;AACL;AAWO,SAAS,WAAA,GAAc;AAC5B,EAAA,OAAO,YAAA,CAAa;AAAA,IAClB,EAAA,EAAI,qBAAA;AAAA,IACJ,IAAA,EAAM,qBAAA;AAAA,IACN,WAAA,EAAa,kCAAA;AAAA,IACb,IAAA,EAAM;AAAA,GACP,CAAA,CACE,UAAA,CAAW,OAAO,EAAE,KAAI,KAAM;AAC7B,IAAA,MAAM,EAAE,KAAA,EAAM,GAAI,gBAAA,CAAiB,IAAI,MAAM,CAAA;AAC7C,IAAA,OAAO,EAAE,KAAA,EAAO,KAAA,CAAM,QAAQ,MAAA,EAAQ,KAAA,CAAM,WAAW,CAAA,EAAE;AAAA,EAC3D,CAAC,CAAA,CACA,aAAA,CAAc,CAAC,EAAE,SAAQ,KAAM;AAC9B,IAAA,OAAO,OAAA,CAAQ,oBAAA,EAAsB,MAAA,GAAS,CAAA,GAAI,CAAA;AAAA,EACpD,CAAC,CAAA;AACL;AAYO,SAAS,YAAA,GAAe;AAC7B,EAAA,OAAO,YAAA,CAAa;AAAA,IAClB,EAAA,EAAI,sBAAA;AAAA,IACJ,IAAA,EAAM,sBAAA;AAAA,IACN,WAAA,EAAa,8CAAA;AAAA,IACb,IAAA,EAAM;AAAA,GACP,CAAA,CACE,UAAA,CAAW,OAAO,EAAE,KAAI,KAAM;AAC7B,IAAA,MAAM,WAAA,GAAc,qBAAA,CAAsB,GAAA,CAAI,MAAM,CAAA;AACpD,IAAA,MAAM,UAAA,GAAa,WAAA,CAAY,MAAA,CAAO,CAAA,GAAA,KAAO,GAAA,CAAI,KAAA,KAAU,MAAA,IAAW,GAAA,CAAI,MAAA,IAAU,GAAA,CAAI,MAAA,CAAO,KAAM,CAAA,CAAE,MAAA;AACvG,IAAA,OAAO,EAAE,UAAA,EAAY,UAAA,EAAY,YAAY,MAAA,EAAQ,MAAA,EAAQ,eAAe,CAAA,EAAE;AAAA,EAChF,CAAC,CAAA,CACA,aAAA,CAAc,CAAC,EAAE,SAAQ,KAAM;AAC9B,IAAA,OAAO,OAAA,CAAQ,oBAAA,EAAsB,MAAA,GAAS,CAAA,GAAI,CAAA;AAAA,EACpD,CAAC,CAAA;AACL;AAIA,SAAS,sBAAsB,MAAA,EAAgD;AAC7E,EAAA,MAAM,cAAqB,EAAC;AAC5B,EAAA,KAAA,MAAW,WAAW,MAAA,EAAQ;AAC5B,IAAA,MAAM,MAAA,GAAS,SAAS,OAAA,EAAS,eAAA;AACjC,IAAA,MAAM,YAAY,MAAA,GACd,MAAA,GACC,OAAA,EAAS,OAAA,EAAiB,OACvB,MAAA,CAAO,CAAC,CAAA,KAAW,CAAA,CAAE,SAAS,iBAAiB,CAAA,CAChD,IAAI,CAAC,CAAA,KAAW,EAAE,cAAc,CAAA;AACvC,IAAA,KAAA,MAAW,GAAA,IAAO,MAAA,IAAU,SAAA,IAAa,EAAC,EAAG;AAC3C,MAAA,IAAI,GAAA,EAAK,WAAA,CAAY,IAAA,CAAK,GAAG,CAAA;AAAA,IAC/B;AAAA,EACF;AACA,EAAA,OAAO,WAAA;AACT;AA4BO,IAAM,MAAA,GAAS;AAAA,EACpB,QAAA;AAAA,EACA,QAAA;AAAA,EACA,MAAA;AAAA,EACA,OAAA;AAAA,EACA,UAAA;AAAA,EACA,UAAA;AAAA,EACA,UAAA;AAAA,EACA,SAAA;AAAA,EACA,YAAA;AAAA,EACA,WAAA;AAAA,EACA;AACF","file":"chunk-QRAONHNV.js","sourcesContent":["import { createScorer } from '@mastra/core/evals';\nimport stringSimilarity from 'string-similarity';\nimport { extractToolCalls, getTextContentFromMastraDBMessage } from '../../utils';\n\n// ─── Output Text Checks ───────────────────────────────────────────────────────\n\nexport interface IncludesOptions {\n  /** Case-insensitive match (default: true) */\n  ignoreCase?: boolean;\n}\n\n/**\n * Scores 1 if the agent's output text contains the expected substring, 0 otherwise.\n *\n * @example\n * ```ts\n * import { checks } from '@mastra/evals';\n * const scorer = checks.includes('sunny');\n * ```\n */\nexport function includes(expected: string, options: IncludesOptions = {}) {\n  const { ignoreCase = true } = options;\n  return createScorer({\n    id: 'check-includes',\n    name: 'Includes Check',\n    description: `Checks if output includes \"${expected}\"`,\n    type: 'agent',\n  })\n    .preprocess(async ({ run }) => {\n      let output = run.output\n        .filter(m => m.role === 'assistant')\n        .map(m => getTextContentFromMastraDBMessage(m))\n        .join(' ');\n      let target = expected;\n      if (ignoreCase) {\n        output = output.toLowerCase();\n        target = target.toLowerCase();\n      }\n      return { output, target, found: output.includes(target) };\n    })\n    .generateScore(({ results }) => {\n      return results.preprocessStepResult?.found ? 1 : 0;\n    });\n}\n\n/**\n * Scores 1 if the agent's output text does NOT contain the substring, 0 otherwise.\n *\n * @example\n * ```ts\n * import { checks } from '@mastra/evals';\n * const scorer = checks.excludes('error');\n * ```\n */\nexport function excludes(unwanted: string, options: IncludesOptions = {}) {\n  const { ignoreCase = true } = options;\n  return createScorer({\n    id: 'check-excludes',\n    name: 'Excludes Check',\n    description: `Checks that output does not include \"${unwanted}\"`,\n    type: 'agent',\n  })\n    .preprocess(async ({ run }) => {\n      let output = run.output\n        .filter(m => m.role === 'assistant')\n        .map(m => getTextContentFromMastraDBMessage(m))\n        .join(' ');\n      let target = unwanted;\n      if (ignoreCase) {\n        output = output.toLowerCase();\n        target = target.toLowerCase();\n      }\n      return { output, target, excluded: !output.includes(target) };\n    })\n    .generateScore(({ results }) => {\n      return results.preprocessStepResult?.excluded ? 1 : 0;\n    });\n}\n\n/**\n * Scores 1 if the output text exactly equals the expected string (after optional normalization).\n *\n * @example\n * ```ts\n * import { checks } from '@mastra/evals';\n * const scorer = checks.equals('Hello, world!');\n * ```\n */\nexport function equals(expected: string, options: IncludesOptions = {}) {\n  const { ignoreCase = true } = options;\n  return createScorer({\n    id: 'check-equals',\n    name: 'Equals Check',\n    description: `Checks if output equals \"${expected}\"`,\n    type: 'agent',\n  })\n    .preprocess(async ({ run }) => {\n      let output = run.output\n        .filter(m => m.role === 'assistant')\n        .map(m => getTextContentFromMastraDBMessage(m))\n        .join('');\n      let target = expected;\n      if (ignoreCase) {\n        output = output.toLowerCase();\n        target = target.toLowerCase();\n      }\n      return { output, target, isEqual: output === target };\n    })\n    .generateScore(({ results }) => {\n      return results.preprocessStepResult?.isEqual ? 1 : 0;\n    });\n}\n\nexport interface MatchesOptions {\n  /** If true, the output must match the pattern exactly (anchored). Default: false (substring match). */\n  exact?: boolean;\n}\n\n/**\n * Scores 1 if the output matches the given regular expression, 0 otherwise.\n *\n * @example\n * ```ts\n * import { checks } from '@mastra/evals';\n * const scorer = checks.matches(/\\d{1,3}°[FC]/);\n * ```\n */\nexport function matches(pattern: RegExp, options: MatchesOptions = {}) {\n  const { exact = false } = options;\n  return createScorer({\n    id: 'check-matches',\n    name: 'Matches Check',\n    description: `Checks if output matches pattern ${pattern}`,\n    type: 'agent',\n  })\n    .preprocess(async ({ run }) => {\n      const output = run.output\n        .filter(m => m.role === 'assistant')\n        .map(m => getTextContentFromMastraDBMessage(m))\n        .join('');\n      const regex = exact ? new RegExp(`^${pattern.source}$`, pattern.flags) : pattern;\n      const matched = regex.test(output);\n      return { output, pattern: pattern.toString(), matched };\n    })\n    .generateScore(({ results }) => {\n      return results.preprocessStepResult?.matched ? 1 : 0;\n    });\n}\n\nexport interface SimilarityOptions {\n  /** Minimum similarity threshold (0-1) to score 1. Default: 0.7 */\n  threshold?: number;\n  /** Case-insensitive comparison (default: true) */\n  ignoreCase?: boolean;\n}\n\n/**\n * Returns the string similarity score (0-1) between the output and an expected string.\n * Useful for fuzzy matching when exact equality is too strict.\n *\n * @example\n * ```ts\n * import { checks } from '@mastra/evals';\n * const scorer = checks.similarity('Sunny, 72°F');\n * ```\n */\nexport function similarity(expected: string, options: SimilarityOptions = {}) {\n  const { ignoreCase = true, threshold } = options;\n  return createScorer({\n    id: 'check-similarity',\n    name: 'Similarity Check',\n    description: `Checks string similarity to \"${expected}\"`,\n    type: 'agent',\n  })\n    .preprocess(async ({ run }) => {\n      let output = run.output\n        .filter(m => m.role === 'assistant')\n        .map(m => getTextContentFromMastraDBMessage(m))\n        .join(' ');\n      let target = expected;\n      if (ignoreCase) {\n        output = output.toLowerCase();\n        target = target.toLowerCase();\n      }\n      const score = stringSimilarity.compareTwoStrings(output, target);\n      return { output, target, score, threshold };\n    })\n    .generateScore(({ results }) => {\n      const score = results.preprocessStepResult?.score ?? 0;\n      const t = results.preprocessStepResult?.threshold;\n      return t !== undefined ? (score >= t ? 1 : 0) : score;\n    });\n}\n\n// ─── Tool Call Checks ─────────────────────────────────────────────────────────\n\nexport interface CalledToolOptions {\n  /** Minimum number of times the tool must be called. Default: 1 */\n  times?: number;\n}\n\n/**\n * Scores 1 if the agent called the specified tool (at least `times` times).\n *\n * @example\n * ```ts\n * import { checks } from '@mastra/evals';\n * const scorer = checks.calledTool('get_weather');\n * const twice = checks.calledTool('search', { times: 2 });\n * ```\n */\nexport function calledTool(toolName: string, options: CalledToolOptions = {}) {\n  const { times = 1 } = options;\n  return createScorer({\n    id: 'check-called-tool',\n    name: 'Called Tool Check',\n    description: `Checks that \"${toolName}\" was called${times > 1 ? ` at least ${times} times` : ''}`,\n    type: 'agent',\n  })\n    .preprocess(async ({ run }) => {\n      const { tools } = extractToolCalls(run.output);\n      const count = tools.filter(t => t === toolName).length;\n      return { toolName, expectedTimes: times, actualCount: count, passed: count >= times };\n    })\n    .generateScore(({ results }) => {\n      return results.preprocessStepResult?.passed ? 1 : 0;\n    });\n}\n\n/**\n * Scores 1 if the agent did NOT call the specified tool.\n *\n * @example\n * ```ts\n * import { checks } from '@mastra/evals';\n * const scorer = checks.didNotCall('delete_user');\n * ```\n */\nexport function didNotCall(toolName: string) {\n  return createScorer({\n    id: 'check-did-not-call',\n    name: 'Did Not Call Check',\n    description: `Checks that \"${toolName}\" was NOT called`,\n    type: 'agent',\n  })\n    .preprocess(async ({ run }) => {\n      const { tools } = extractToolCalls(run.output);\n      const count = tools.filter(t => t === toolName).length;\n      return { toolName, count, passed: count === 0 };\n    })\n    .generateScore(({ results }) => {\n      return results.preprocessStepResult?.passed ? 1 : 0;\n    });\n}\n\n/**\n * Scores 1 if the tools were called in the specified order (relaxed: allows other calls in between).\n *\n * @example\n * ```ts\n * import { checks } from '@mastra/evals';\n * const scorer = checks.toolOrder(['search', 'summarize', 'respond']);\n * ```\n */\nexport function toolOrder(expectedOrder: string[]) {\n  return createScorer({\n    id: 'check-tool-order',\n    name: 'Tool Order Check',\n    description: `Checks tool call order: [${expectedOrder.join(' → ')}]`,\n    type: 'agent',\n  })\n    .preprocess(async ({ run }) => {\n      const { tools } = extractToolCalls(run.output);\n      // Check that expectedOrder appears as a subsequence of tools\n      let orderIndex = 0;\n      for (const tool of tools) {\n        if (orderIndex < expectedOrder.length && tool === expectedOrder[orderIndex]) {\n          orderIndex++;\n        }\n      }\n      const passed = orderIndex === expectedOrder.length;\n      return { actualTools: tools, expectedOrder, passed };\n    })\n    .generateScore(({ results }) => {\n      return results.preprocessStepResult?.passed ? 1 : 0;\n    });\n}\n\n/**\n * Scores 1 if the agent used no more than `max` tool calls.\n *\n * @example\n * ```ts\n * import { checks } from '@mastra/evals';\n * const scorer = checks.maxToolCalls(5);\n * ```\n */\nexport function maxToolCalls(max: number) {\n  return createScorer({\n    id: 'check-max-tool-calls',\n    name: 'Max Tool Calls Check',\n    description: `Checks that no more than ${max} tool calls were made`,\n    type: 'agent',\n  })\n    .preprocess(async ({ run }) => {\n      const { tools } = extractToolCalls(run.output);\n      return { count: tools.length, max, passed: tools.length <= max };\n    })\n    .generateScore(({ results }) => {\n      return results.preprocessStepResult?.passed ? 1 : 0;\n    });\n}\n\n/**\n * Scores 1 if the agent made no tool calls at all.\n *\n * @example\n * ```ts\n * import { checks } from '@mastra/evals';\n * const scorer = checks.usedNoTools();\n * ```\n */\nexport function usedNoTools() {\n  return createScorer({\n    id: 'check-used-no-tools',\n    name: 'Used No Tools Check',\n    description: 'Checks that no tools were called',\n    type: 'agent',\n  })\n    .preprocess(async ({ run }) => {\n      const { tools } = extractToolCalls(run.output);\n      return { count: tools.length, passed: tools.length === 0 };\n    })\n    .generateScore(({ results }) => {\n      return results.preprocessStepResult?.passed ? 1 : 0;\n    });\n}\n\n/**\n * Scores 1 if none of the tool invocations resulted in an error state.\n * Checks for tool invocations with state other than 'result' (i.e., missing results).\n *\n * @example\n * ```ts\n * import { checks } from '@mastra/evals';\n * const scorer = checks.noToolErrors();\n * ```\n */\nexport function noToolErrors() {\n  return createScorer({\n    id: 'check-no-tool-errors',\n    name: 'No Tool Errors Check',\n    description: 'Checks that no tool calls resulted in errors',\n    type: 'agent',\n  })\n    .preprocess(async ({ run }) => {\n      const invocations = extractRawInvocations(run.output);\n      const errorCount = invocations.filter(inv => inv.state === 'call' || (inv.result && inv.result.error)).length;\n      return { errorCount, totalCalls: invocations.length, passed: errorCount === 0 };\n    })\n    .generateScore(({ results }) => {\n      return results.preprocessStepResult?.passed ? 1 : 0;\n    });\n}\n\n// ─── Internal helpers ──────────────────────────────────────────────────────────\n\nfunction extractRawInvocations(output: Parameters<typeof extractToolCalls>[0]) {\n  const invocations: any[] = [];\n  for (const message of output) {\n    const legacy = message?.content?.toolInvocations;\n    const fromParts = legacy\n      ? undefined\n      : (message?.content as any)?.parts\n          ?.filter((p: any) => p.type === 'tool-invocation')\n          .map((p: any) => p.toolInvocation);\n    for (const inv of legacy ?? fromParts ?? []) {\n      if (inv) invocations.push(inv);\n    }\n  }\n  return invocations;\n}\n\n// ─── Convenience namespace ────────────────────────────────────────────────────\n\n/**\n * Quick Checks — composable micro-scorers for common assertions.\n *\n * These are zero-LLM, zero-ceremony scorers that plug into the existing\n * `scorers: [...]` array anywhere scorers are used. Internally they are\n * standard `createScorer()` instances with the same observability, storage,\n * and pipeline integration as any other scorer.\n *\n * @example\n * ```ts\n * import { checks } from '@mastra/evals';\n *\n * await runEvals({\n *   data: [...],\n *   target: myAgent,\n *   scorers: [\n *     checks.includes('sunny'),\n *     checks.calledTool('get_weather'),\n *     checks.toolOrder(['search', 'summarize']),\n *     checks.noToolErrors(),\n *   ],\n * });\n * ```\n */\nexport const checks = {\n  includes,\n  excludes,\n  equals,\n  matches,\n  similarity,\n  calledTool,\n  didNotCall,\n  toolOrder,\n  maxToolCalls,\n  usedNoTools,\n  noToolErrors,\n};\n"]}

package/dist/docs/SKILL.md

@@ -3,7 +3,7 @@ name: mastra-evals
 description: Documentation for @mastra/evals. Use when working with @mastra/evals APIs, configuration, or implementation.
 metadata:
   package: "@mastra/evals"
-  version: "1.4.0"
+  version: "1.5.0-alpha.0"
 ---
 
 ## When to use
@@ -18,12 +18,14 @@ Read the individual reference documents for detailed explanations and code examp
 
 - [Built-in scorers](references/docs-evals-built-in-scorers.md) - Overview of Mastra's ready-to-use scorers for evaluating AI outputs across quality, safety, and performance dimensions.
 - [Scorers overview](references/docs-evals-overview.md) - Overview of scorers in Mastra, detailing their capabilities for evaluating AI outputs and measuring performance.
+- [Quick Checks](references/docs-evals-quick-checks.md) - Zero-LLM micro-scorers for fast, deterministic assertions on agent output text and tool usage.
 
 ### Reference
 
 - [Reference: Answer relevancy scorer](references/reference-evals-answer-relevancy.md) - Documentation for the Answer Relevancy Scorer in Mastra, which evaluates how well LLM outputs address the input query.
 - [Reference: Answer similarity scorer](references/reference-evals-answer-similarity.md) - Documentation for the Answer Similarity Scorer in Mastra, which compares agent outputs against ground truth answers for CI/CD testing.
 - [Reference: Bias scorer](references/reference-evals-bias.md) - Documentation for the Bias Scorer in Mastra, which evaluates LLM outputs for various forms of bias, including gender, political, racial/ethnic, or geographical bias.
+- [Reference: Quick Checks](references/reference-evals-checks.md) - API reference for Quick Checks, zero-LLM composable micro-scorers for common assertions like text matching, tool usage, and tool ordering.
 - [Reference: Completeness scorer](references/reference-evals-completeness.md) - Documentation for the Completeness Scorer in Mastra, which evaluates how thoroughly LLM outputs cover key elements present in the input.
 - [Reference: Content similarity scorer](references/reference-evals-content-similarity.md) - Documentation for the Content Similarity Scorer in Mastra, which measures textual similarity between strings and provides a matching score.
 - [Reference: Context precision scorer](references/reference-evals-context-precision.md) - Documentation for the Context Precision Scorer in Mastra. Evaluates the relevance and precision of retrieved context for generating expected outputs using Mean Average Precision.

package/dist/docs/assets/SOURCE_MAP.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.4.0",
+  "version": "1.5.0-alpha.0",
   "package": "@mastra/evals",
   "exports": {},
   "modules": {}

package/dist/docs/references/docs-evals-built-in-scorers.md

@@ -45,4 +45,20 @@ These scorers evaluate adherence to format, style, and safety requirements:
 - [`tone-consistency`](https://mastra.ai/reference/evals/tone-consistency): Measures consistency in formality, complexity, and style (`0-1`, higher is better)
 - [`toxicity`](https://mastra.ai/reference/evals/toxicity): Detects harmful or inappropriate content (`0-1`, lower is better)
 - [`bias`](https://mastra.ai/reference/evals/bias): Detects potential biases in the output (`0-1`, lower is better)
-- [`keyword-coverage`](https://mastra.ai/reference/evals/keyword-coverage): Assesses technical terminology usage (`0-1`, higher is better)
+- [`keyword-coverage`](https://mastra.ai/reference/evals/keyword-coverage): Assesses technical terminology usage (`0-1`, higher is better)
+
+### Quick Checks
+
+Zero-LLM micro-scorers for fast, deterministic assertions. See the [Quick Checks](https://mastra.ai/docs/evals/quick-checks) guide for usage details.
+
+- [`checks.includes`](https://mastra.ai/reference/evals/checks): Scores 1 if output contains a substring (`0` or `1`)
+- [`checks.excludes`](https://mastra.ai/reference/evals/checks): Scores 1 if output does not contain a substring (`0` or `1`)
+- [`checks.equals`](https://mastra.ai/reference/evals/checks): Scores 1 if output exactly matches a string (`0` or `1`)
+- [`checks.matches`](https://mastra.ai/reference/evals/checks): Scores 1 if output matches a regex (`0` or `1`)
+- [`checks.similarity`](https://mastra.ai/reference/evals/checks): String similarity via Dice coefficient (`0-1`, or binary with threshold)
+- [`checks.calledTool`](https://mastra.ai/reference/evals/checks): Scores 1 if a tool was called at least N times (`0` or `1`)
+- [`checks.didNotCall`](https://mastra.ai/reference/evals/checks): Scores 1 if a tool was not called (`0` or `1`)
+- [`checks.toolOrder`](https://mastra.ai/reference/evals/checks): Scores 1 if tools were called in order (`0` or `1`)
+- [`checks.maxToolCalls`](https://mastra.ai/reference/evals/checks): Scores 1 if tool call count is within limit (`0` or `1`)
+- [`checks.usedNoTools`](https://mastra.ai/reference/evals/checks): Scores 1 if no tools were called (`0` or `1`)
+- [`checks.noToolErrors`](https://mastra.ai/reference/evals/checks): Scores 1 if no tool calls had errors (`0` or `1`)

package/dist/docs/references/docs-evals-overview.md

@@ -135,6 +135,7 @@ Once registered, you can score traces interactively within Studio under the **Ob
 
 ## Next steps
 
+- Use [Quick Checks](https://mastra.ai/docs/evals/quick-checks) for fast, deterministic assertions on text and tool usage
 - Learn how to create your own scorers in the [Creating Custom Scorers](https://mastra.ai/docs/evals/custom-scorers) guide
 - Explore built-in scorers in the [Built-in Scorers](https://mastra.ai/docs/evals/built-in-scorers) section
 - Test scorers with [Studio](https://mastra.ai/docs/studio/overview)

package/dist/docs/references/docs-evals-quick-checks.md

@@ -0,0 +1,136 @@
+# Quick Checks
+
+Quick Checks are composable micro-scorers for common assertions like "output contains X" or "agent called tool Y." They require no LLM, run instantly, and plug into the same `scorers: [...]` array as any other scorer.
+
+## When to use Quick Checks
+
+Use Quick Checks when you need fast, deterministic assertions:
+
+- Verify output text contains or excludes specific strings
+- Confirm an agent called (or avoided) specific tools
+- Validate tool call ordering and count limits
+- Gate CI pipelines with zero-cost binary checks
+- Combine with LLM-based scorers for layered evaluation
+
+For subjective or semantic evaluation, use [LLM-based scorers](https://mastra.ai/docs/evals/built-in-scorers) instead.
+
+## Quickstart
+
+```typescript
+import { checks } from '@mastra/evals/checks'
+import { runEvals } from '@mastra/core/evals'
+import { weatherAgent } from '../agents'
+
+const result = await runEvals({
+  data: [{ input: 'What is the weather in Brooklyn?' }],
+  target: weatherAgent,
+  scorers: [checks.includes('Brooklyn'), checks.calledTool('get_weather'), checks.noToolErrors()],
+})
+
+console.log(result.scores)
+// { 'check-includes': 1, 'check-called-tool': 1, 'check-no-tool-errors': 1 }
+```
+
+## Available checks
+
+Quick Checks fall into two categories:
+
+### Text checks
+
+These scorers evaluate the agent's text output:
+
+| Check                    | What it does                          | Score                            |
+| ------------------------ | ------------------------------------- | -------------------------------- |
+| `checks.includes(str)`   | Output contains substring             | 1 or 0                           |
+| `checks.excludes(str)`   | Output does not contain substring     | 1 or 0                           |
+| `checks.equals(str)`     | Output exactly equals string          | 1 or 0                           |
+| `checks.matches(regex)`  | Output matches regular expression     | 1 or 0                           |
+| `checks.similarity(str)` | Dice coefficient similarity to string | 0-1 (or binary with `threshold`) |
+
+### Tool call checks
+
+These scorers evaluate tool usage from the agent's run:
+
+| Check                     | What it does                     | Score  |
+| ------------------------- | -------------------------------- | ------ |
+| `checks.calledTool(name)` | Tool was called at least N times | 1 or 0 |
+| `checks.didNotCall(name)` | Tool was not called              | 1 or 0 |
+| `checks.toolOrder([...])` | Tools called in expected order   | 1 or 0 |
+| `checks.maxToolCalls(n)`  | No more than N tool calls total  | 1 or 0 |
+| `checks.usedNoTools()`    | No tools called at all           | 1 or 0 |
+| `checks.noToolErrors()`   | No tool invocations had errors   | 1 or 0 |
+
+## Combining checks with LLM scorers
+
+Checks compose with LLM-based scorers in a single `runEvals` call. Use checks for deterministic gates and LLM scorers for qualitative evaluation:
+
+```typescript
+import { checks } from '@mastra/evals/checks'
+import { createFaithfulnessScorer } from '@mastra/evals/scorers/prebuilt'
+import { runEvals } from '@mastra/core/evals'
+import { myAgent } from '../agents'
+
+const result = await runEvals({
+  data: [
+    {
+      input: 'What is the weather in Brooklyn?',
+      context: ['Brooklyn weather data: sunny, 72°F'],
+    },
+  ],
+  target: myAgent,
+  scorers: [
+    // Deterministic checks (instant, free)
+    checks.includes('Brooklyn'),
+    checks.calledTool('get_weather'),
+    checks.excludes('error'),
+    checks.noToolErrors(),
+
+    // LLM-based scorer (semantic, costs tokens)
+    createFaithfulnessScorer({ model: 'openai/gpt-5-mini' }),
+  ],
+})
+```
+
+## Using checks in live scoring
+
+Attach checks to agents for continuous monitoring:
+
+```typescript
+import { Agent } from '@mastra/core/agent'
+import { checks } from '@mastra/evals/checks'
+
+export const weatherAgent = new Agent({
+  name: 'Weather Agent',
+  instructions: 'Answer weather questions using the get_weather tool.',
+  model: 'openai/gpt-5.5',
+  tools: { get_weather: weatherTool },
+  scorers: {
+    noErrors: {
+      scorer: checks.noToolErrors(),
+      sampling: { type: 'ratio', rate: 1 },
+    },
+    mentionCity: {
+      scorer: checks.includes('Brooklyn'),
+      sampling: { type: 'ratio', rate: 0.5 },
+    },
+  },
+})
+```
+
+## How checks work
+
+Each check is a standard `createScorer()` instance with a `preprocess` step and a `generateScore` step. They follow the same [four-step pipeline](https://mastra.ai/docs/evals/custom-scorers) as any other scorer:
+
+1. **preprocess**: Extracts and normalizes relevant data from the agent run (text content, tool calls)
+2. **generateScore**: Converts the preprocessed result into a score (typically binary 1 or 0)
+
+Because checks skip the `analyze` and `generateReason` steps and make no LLM calls, they run in microseconds.
+
+> **Note:** Visit the [Quick Checks reference](https://mastra.ai/reference/evals/checks) for the full API, including all parameters and options for each check.
+
+## Related
+
+- [Quick Checks reference](https://mastra.ai/reference/evals/checks)
+- [Built-in Scorers](https://mastra.ai/docs/evals/built-in-scorers)
+- [Custom Scorers](https://mastra.ai/docs/evals/custom-scorers)
+- [`runEvals()` reference](https://mastra.ai/reference/evals/run-evals)

package/dist/docs/references/reference-evals-checks.md

@@ -0,0 +1,210 @@
+# Quick Checks
+
+Quick Checks are zero-LLM, composable micro-scorers for common assertions. They plug into the existing `scorers: [...]` array anywhere scorers are used — in `runEvals`, live scoring, experiments, and Studio.
+
+Internally they are standard `createScorer()` instances, so they have the same observability, storage, and pipeline integration as any other scorer.
+
+## Usage example
+
+```typescript
+import { checks } from '@mastra/evals/checks'
+import { runEvals } from '@mastra/core/evals'
+import { myAgent } from '../agents'
+
+const result = await runEvals({
+  data: [{ input: 'What is the weather in Brooklyn?' }],
+  target: myAgent,
+  scorers: [
+    checks.includes('sunny'),
+    checks.calledTool('get_weather'),
+    checks.toolOrder(['get_weather', 'summarize']),
+    checks.noToolErrors(),
+  ],
+})
+
+console.log(result.scores)
+```
+
+## Text checks
+
+### `checks.includes(expected, options?)`
+
+Scores 1 if the agent's output text contains the expected substring, 0 otherwise.
+
+```typescript
+checks.includes('sunny')
+checks.includes('Sunny', { ignoreCase: false })
+```
+
+**expected** (`string`): Substring to search for in the output.
+
+**options.ignoreCase** (`boolean`): Case-insensitive matching. (Default: `true`)
+
+Returns: `1` if found, `0` otherwise.
+
+### `checks.excludes(unwanted, options?)`
+
+Scores 1 if the agent's output text does NOT contain the substring, 0 otherwise.
+
+```typescript
+checks.excludes('error')
+checks.excludes('Error', { ignoreCase: false })
+```
+
+**unwanted** (`string`): Substring that must not appear in the output.
+
+**options.ignoreCase** (`boolean`): Case-insensitive matching. (Default: `true`)
+
+Returns: `1` if absent, `0` otherwise.
+
+### `checks.equals(expected, options?)`
+
+Scores 1 if the output text exactly equals the expected string after optional normalization.
+
+```typescript
+checks.equals('Hello, world!')
+checks.equals('Hello', { ignoreCase: false })
+```
+
+**expected** (`string`): Exact string the output must match.
+
+**options.ignoreCase** (`boolean`): Case-insensitive matching. (Default: `true`)
+
+Returns: `1` if equal, `0` otherwise.
+
+### `checks.matches(pattern, options?)`
+
+Scores 1 if the output matches the given regular expression.
+
+```typescript
+checks.matches(/\d+°[FC]/)
+checks.matches(/^hello$/, { exact: true })
+```
+
+**pattern** (`RegExp`): Regular expression to test against the output.
+
+**options.exact** (`boolean`): Anchor the pattern to match the entire output (adds ^ and $). (Default: `false`)
+
+Returns: `1` if matched, `0` otherwise.
+
+### `checks.similarity(expected, options?)`
+
+Returns the string similarity score (0-1) between the output and an expected string using the Dice coefficient. When a `threshold` is set, returns binary 1/0 instead.
+
+```typescript
+checks.similarity('Sunny, 72°F')
+checks.similarity('Sunny, 72°F', { threshold: 0.7 })
+```
+
+**expected** (`string`): Reference string to compare against.
+
+**options.threshold** (`number`): Minimum similarity score (0-1) to return 1. When omitted, returns the raw similarity score.
+
+**options.ignoreCase** (`boolean`): Case-insensitive comparison. (Default: `true`)
+
+Returns: Raw similarity score (0-1), or binary `1`/`0` when `threshold` is set.
+
+## Tool call checks
+
+### `checks.calledTool(toolName, options?)`
+
+Scores 1 if the agent called the specified tool at least the required number of times.
+
+```typescript
+checks.calledTool('get_weather')
+checks.calledTool('search', { times: 2 })
+```
+
+**toolName** (`string`): Name of the tool to look for.
+
+**options.times** (`number`): Minimum number of times the tool must be called. (Default: `1`)
+
+Returns: `1` if called at least `times` times, `0` otherwise.
+
+### `checks.didNotCall(toolName)`
+
+Scores 1 if the agent did NOT call the specified tool.
+
+```typescript
+checks.didNotCall('delete_user')
+```
+
+**toolName** (`string`): Name of the tool that must not appear.
+
+Returns: `1` if the tool was not called, `0` otherwise.
+
+### `checks.toolOrder(expectedOrder)`
+
+Scores 1 if the tools were called in the specified order. Uses relaxed matching — other tool calls between the expected tools are allowed.
+
+```typescript
+checks.toolOrder(['search', 'summarize', 'respond'])
+```
+
+**expectedOrder** (`string[]`): Tool names in the expected calling sequence. Must appear as a subsequence of the actual tool calls.
+
+Returns: `1` if the expected order is satisfied, `0` otherwise.
+
+### `checks.maxToolCalls(max)`
+
+Scores 1 if the agent used no more than `max` tool calls.
+
+```typescript
+checks.maxToolCalls(5)
+```
+
+**max** (`number`): Maximum number of tool calls allowed.
+
+Returns: `1` if within the limit, `0` otherwise.
+
+### `checks.usedNoTools()`
+
+Scores 1 if the agent made no tool calls at all.
+
+```typescript
+checks.usedNoTools()
+```
+
+Returns: `1` if no tools were called, `0` otherwise.
+
+### `checks.noToolErrors()`
+
+Scores 1 if none of the tool invocations resulted in an error state. Detects both error results (`result.error` present) and incomplete tool calls (`state === 'call'`).
+
+```typescript
+checks.noToolErrors()
+```
+
+Returns: `1` if all tool calls succeeded, `0` otherwise.
+
+## Combining checks with other scorers
+
+Checks compose with LLM-based and code-based scorers in the same `scorers` array:
+
+```typescript
+import { checks } from '@mastra/evals/checks'
+import { createAnswerRelevancyScorer } from '@mastra/evals/scorers/prebuilt'
+import { runEvals } from '@mastra/core/evals'
+import { myAgent } from '../agents'
+
+const result = await runEvals({
+  data: [{ input: 'What is the weather in Brooklyn?' }],
+  target: myAgent,
+  scorers: [
+    // Zero-LLM checks
+    checks.includes('Brooklyn'),
+    checks.calledTool('get_weather'),
+    checks.noToolErrors(),
+    // LLM-based scorer
+    createAnswerRelevancyScorer({ model: 'openai/gpt-5-mini' }),
+  ],
+})
+```
+
+## Related
+
+- [Quick Checks overview](https://mastra.ai/docs/evals/quick-checks)
+- [Built-in Scorers](https://mastra.ai/docs/evals/built-in-scorers)
+- [`createScorer()` reference](https://mastra.ai/reference/evals/create-scorer)
+- [`runEvals()` reference](https://mastra.ai/reference/evals/run-evals)
+- [Custom Scorers](https://mastra.ai/docs/evals/custom-scorers)