linshenkx/prompt-optimizer · error · VariableExtractionParseError

Extraction result must have a "variables" array.

Error message

Extraction result must have a "variables" array.

What it means

The parsed LLM response is an object, but it lacks a 'variables' array (the field is missing, or is not an Array). 'variables' is a required field of the unified extraction response, so normalization fails before any per-variable validation runs.

Source

Thrown at packages/core/src/services/variable-extraction/service.ts:199

      } catch (fallbackError) {
        throw new VariableExtractionParseError(
          `Failed to parse LLM response: ${error instanceof Error ? error.message : String(error)}. Raw content length: ${content.length} characters.`
        );
      }
    }
  }

  /**
   * 标准化提取响应（统一结构）
   */
  private normalizeExtractionResponse(data: any): VariableExtractionResponse {
    if (!data || typeof data !== 'object') {
      throw new VariableExtractionParseError('Extraction result is not a valid object.');
    }

    // 验证 variables 字段
    if (!Array.isArray(data.variables)) {
      throw new VariableExtractionParseError('Extraction result must have a "variables" array.');
    }

    // 验证 summary 字段
    if (typeof data.summary !== 'string') {
      throw new VariableExtractionParseError('Extraction result must have a "summary" string.');
    }

    // 标准化每个变量
    const variables: ExtractedVariable[] = data.variables.map((variable: any, index: number) => {
      // 验证必需字段
      if (!variable || typeof variable !== 'object') {
        throw new VariableExtractionParseError(`variables[${index}] is not a valid object.`);
      }

      if (typeof variable.name !== 'string' || !variable.name.trim()) {
        throw new VariableExtractionParseError(`variables[${index}] is missing a valid "name" field.`);
      }

View on GitHub (pinned to 3e677b1d9f)

Solutions

1. Update the prompt/template to state that the output MUST include "variables": [] (empty array when nothing is extracted).
2. Log the parsed object keys to see what field name the model used instead.
3. Add a pre-normalization shim mapping the actual field (e.g. data.extracted or Object.values(data.variables)) to data.variables.
4. Try a stronger model or few-shot example showing the exact schema.

Example fix

// before
return this.normalizeExtractionResponse(parsed);

// after
if (!Array.isArray(parsed.variables) && Array.isArray(parsed.extracted)) parsed.variables = parsed.extracted;
return this.normalizeExtractionResponse(parsed);

const hasVariablesArray = (d: unknown): d is { variables: unknown[]; [k: string]: unknown } =>
  isExtractionObject(d) && Array.isArray((d as any).variables);

try {
  await extractionService.extract({ modelKey, content });
} catch (e) {
  if (e instanceof VariableExtractionParseError && /"variables" array/.test(e.message)) {
    // remap the actual field name (e.g. extracted) and retry once
  }
  throw e;
}

When it happens

Trigger: Model returns an object whose variables field is omitted, an object instead of an array (e.g. a keyed map of variables), or a string. Reached via extract() when the model's JSON deviates from the required {variables: [], summary: ""} shape.

Common situations: Model returns {"extracted": [...]} or {"result": {"variables": [...]}} (extra nesting); model returns variables as an object keyed by name; prompt template edited so the field name changed; model omits the field when it finds no variables instead of returning an empty array.

Related errors

• Extraction result must have a "summary" string.
• variables[${index}] is not a valid object.
• variables[${index}] is missing a valid "name" field.
• variables[${index}] is missing a valid "value" field.
• Invalid import data format

AI-assisted analysis of linshenkx/prompt-optimizer@3e677b1d9f (2026-08-27). Data as JSON: /api/errors/605f41479ad88ca2. Report an issue: GitHub.