mastra-ai/mastra · error · Error

Either context or contextExtractor is required for Context P

Error message

Either context or contextExtractor is required for Context Precision scoring

What it means

createContextPrecisionScorer needs retrieved context to judge: it must come either from a static options.context array or be computed per-run via options.contextExtractor. If neither is supplied the scorer cannot obtain context at scoring time, so the factory throws immediately. This is construction-time configuration validation in packages/evals/src/scorers/llm/context-precision/index.ts:62.

Source

Thrown at packages/evals/src/scorers/llm/context-precision/index.ts:62

  output: ScorerRunOutputForLLMJudge;
  options: ContextPrecisionMetricOptions;
}) => {
  if (options.contextExtractor && isScorerRunInputForAgent(input) && isScorerRunOutputForAgent(output)) {
    return options.contextExtractor(input, output);
  }

  return options.context ?? [];
};

export function createContextPrecisionScorer({
  model,
  options,
}: {
  model: MastraModelConfig;
  options: ContextPrecisionMetricOptions;
}) {
  if (!options.context && !options.contextExtractor) {
    throw new Error('Either context or contextExtractor is required for Context Precision scoring');
  }
  if (options.context && options.context.length === 0) {
    throw new Error('Context array cannot be empty if provided');
  }

  return createScorer<ScorerRunInputForLLMJudge, ScorerRunOutputForLLMJudge>({
    id: 'context-precision-scorer',
    name: 'Context Precision Scorer',
    description:
      'A scorer that evaluates the relevance and precision of retrieved context nodes for generating expected outputs',
    judge: {
      model,
      instructions: CONTEXT_PRECISION_AGENT_INSTRUCTIONS,
    },
    type: 'agent',
  })
    .analyze({
      description: 'Evaluate the relevance of each context piece for generating the expected output',

View on GitHub (pinned to 75dd419e61)

Solutions

1. Pass context: ['retrieved chunk 1', ...] for a fixed context set
2. Pass contextExtractor: ({ run }) => string[] to pull context from each run (e.g. from retrievedDocuments)
3. Verify both keys are spelled exactly context and contextExtractor on the options object
4. If you actually need recall-style checking, confirm you are using the right metric, but note it has the same requirement

Example fix

// before
const scorer = createContextPrecisionScorer({ model: 'openai/gpt-4o', options: {} });

// after
const scorer = createContextPrecisionScorer({
  model: 'openai/gpt-4o',
  options: { contextExtractor: ({ run }) => run.input?.retrievedDocuments?.map(d => d.content) ?? [] },
});

function validateContextOptions(o: ContextPrecisionMetricOptions): void {
  if (!o.context && !o.contextExtractor) {
    throw new Error('Context Precision needs options.context or options.contextExtractor');
  }
}
validateContextOptions(options);

function hasContextSource(o: ContextPrecisionMetricOptions): o is ContextPrecisionMetricOptions & ({ context: string[] } | { contextExtractor: (...a: unknown[]) => string[] }) {
  return Boolean(o.context) || Boolean(o.contextExtractor);
}

try {
  const scorer = createContextPrecisionScorer({ model, options });
} catch (err) {
  if ((err as Error).message.includes('context or contextExtractor is required')) {
    throw new ConfigError('Wire context or contextExtractor into Context Precision options');
  }
  throw err;
}

When it happens

Trigger: Calling createContextPrecisionScorer({ model, options: {} }); passing options without context and without contextExtractor (e.g. only scale or other metric options); building options from config where both keys were dropped.

Common situations: Copying a context-precision example and deleting the context option; expecting the scorer to auto-derive context from the run's retrievedDocuments (it does not unless contextExtractor reads them); switching scorers and not updating the options object.

Related errors

• MASTR_SCORER_FAILED_TO_CREATE_MISSING_ID
• Either expectedTool or expectedToolOrder must be provided
• Context array cannot be empty if provided
• No context available for evaluation
• Either context or contextExtractor is required for Context R

AI-assisted analysis of mastra-ai/mastra@75dd419e61 (2026-08-30). Data as JSON: /api/errors/5b3600569f270ecb. Report an issue: GitHub.