Enum StructuredJudgeError 

#[non_exhaustive]
pub enum StructuredJudgeError {
    Call(String),
    Parse(String),
}

结构化裁判调用的错误:区分“LLM 调用失败“与“结构化解析失败“, 由调用方映射到自己的错误域(如 EvalError::PredictorError / EvalError::ParseError)。

Variants (Non-exhaustive)

Non-exhaustive enums could have additional variants added in future. Therefore, when matching against variants of non-exhaustive enums, an extra wildcard arm must be added to account for any future variants.

Call(String)

底层 LLM 调用失败(网络 / 限流 / 返回异常)。

Parse(String)

工具调用参数无法按目标类型反序列化,或 tool_calls 为空。

Trait Implementations

impl Debug for StructuredJudgeError

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Display for StructuredJudgeError

fn fmt(&self, __formatter: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Error for StructuredJudgeError

fn source(&self) -> Option<&(dyn Error + 'static)>

Returns the lower-level source of this error, if any.

fn description(&self) -> &str

👎Deprecated since 1.42.0:

use the Display impl or to_string()

fn cause(&self) -> Option<&dyn Error>

👎Deprecated since 1.33.0:

replaced by Error::source, which can support downcasting

fn provide<'a>(&'a self, request: &mut Request<'a>)

🔬This is a nightly-only experimental API. (error_generic_member_access)

Provides type-based access to context intended for error reports.