linshenkx/prompt-optimizer · error · VariableExtractionParseError
variables[${index}] is missing a valid "value" field.
Error message
variables[${index}] is missing a valid "value" field. What it means
The variables array entry at ${index} has a 'value' field that is missing or not a string. The unified schema requires every extracted variable to carry a string value (even an empty string), so normalization aborts at this entry.
Source
Thrown at packages/core/src/services/variable-extraction/service.ts:219
// 验证 summary 字段
if (typeof data.summary !== 'string') {
throw new VariableExtractionParseError('Extraction result must have a "summary" string.');
}
// 标准化每个变量
const variables: ExtractedVariable[] = data.variables.map((variable: any, index: number) => {
// 验证必需字段
if (!variable || typeof variable !== 'object') {
throw new VariableExtractionParseError(`variables[${index}] is not a valid object.`);
}
if (typeof variable.name !== 'string' || !variable.name.trim()) {
throw new VariableExtractionParseError(`variables[${index}] is missing a valid "name" field.`);
}
if (typeof variable.value !== 'string') {
throw new VariableExtractionParseError(`variables[${index}] is missing a valid "value" field.`);
}
if (!variable.position || typeof variable.position !== 'object') {
throw new VariableExtractionParseError(`variables[${index}] is missing a valid "position" object.`);
}
if (typeof variable.position.originalText !== 'string') {
throw new VariableExtractionParseError(
`variables[${index}].position is missing a valid "originalText" field.`
);
}
if (typeof variable.position.occurrence !== 'number') {
throw new VariableExtractionParseError(
`variables[${index}].position is missing a valid "occurrence" number.`
);
}
View on GitHub (pinned to 3e677b1d9f)
Solutions
- Add a coercion shim: String(v.value ?? '') when value is a primitive.
- Map alternate keys: v.value ?? v.text ?? v.content.
- Fix the prompt/template to require "value" as a string (use "" when unmatched) with a few-shot example.
- Drop entries without any value-like field if they are hallucinated.
Example fix
// before
return this.normalizeExtractionResponse(parsed);
// after
parsed.variables = parsed.variables.map(v => ({ ...v, value: typeof v.value === 'string' ? v.value : String(v.value ?? v.text ?? '') }));
return this.normalizeExtractionResponse(parsed); Defensive patterns
Strategy: validation
Type guard
const hasStringValue = (v: unknown): boolean => !!v && typeof v === 'object' && typeof (v as any).value === 'string';
Try / catch
try {
await extractionService.extract({ modelKey, content });
} catch (e) {
if (e instanceof VariableExtractionParseError && /"value" field/.test(e.message)) {
// coerce primitives with String() / map text/content keys, then retry
}
throw e;
} Prevention
- Coerce non-string values (String(v.value ?? '')) before passing to the service.
- Map alternate keys (text, content) to value in pre-processing.
- Instruct the model to always emit value as a string, using "" when unmatched.
When it happens
Trigger: The model returns a variable object where value is undefined, null, a number, boolean, or object. Common when the model omits value for unresolvable variables or returns typed values (e.g. numbers, booleans) instead of strings. Reached via extract().
Common situations: Model returns {"name":"count","value":3} (number not string); model omits value when the variable has no textual match; model uses 'text' or 'content' as the key; template example shows optional value.
Related errors
- variables[${index}] is not a valid object.
- variables[${index}] is missing a valid "name" field.
- Extraction result must have a "variables" array.
- Extraction result must have a "summary" string.
- Invalid import data format
AI-assisted analysis of linshenkx/prompt-optimizer@3e677b1d9f (2026-08-27).
Data as JSON: /api/errors/8adb567771f188c9.
Report an issue: GitHub.