Struct ReplayProvider 

pub struct ReplayProvider { /* private fields */ }

从录制文件回放的零网络 BaseChatModel。

队列用 Arc<Mutex<VecDeque>> 共享,bind_tools 返回携带工具集的新实例 时与原件共享同一队列(FIFO 顺序在分支间一致)。

Implementations

impl ReplayProvider

pub fn from_file(path: impl AsRef<Path>) -> Result<Self, TestkitError>

读 JSONL 录制文件(缺文件/坏行 → Err)。

pub fn from_exchanges(exchanges: Vec<RecordedExchange>) -> Self

内存构造(手写录播 = MockProvider 的等价物)。

pub fn single(response: LLMResult) -> Self

单一固定响应:任意请求都返回同一 response(最简 mock)。

pub fn with_strategy(self, strategy: ReplayStrategy) -> Self

设置回放策略(默认 FIFO;ByToolName 按工具名路由)。

pub fn bind_tools(&self, tools: Vec<ToolDefinition>) -> Self

绑定工具:返回携带该工具集的新实例(共享同一回放队列)。

回放侧绑工具只是让 agent“绑了工具的循环“前提成立——录播里已含 请求侧 tools 与响应侧 tool_calls,回放逻辑无需改。ByToolName 策略下,tools 同时是路由的匹配键。

pub fn len(&self) -> usize

剩余录播条数。

pub fn is_empty(&self) -> bool

是否已无剩余录播。

Trait Implementations

impl BaseChatModel for ReplayProvider

fn chat<'life0, 'async_trait>( &'life0 self, messages: Vec<Message>, _config: Option<RunnableConfig>, ) -> Pin<Box<dyn Future<Output = Result<LLMResult, Self::Error>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Chat with the model.

fn stream_chat<'life0, 'async_trait>( &'life0 self, messages: Vec<Message>, config: Option<RunnableConfig>, ) -> Pin<Box<dyn Future<Output = Result<Pin<Box<dyn Stream<Item = Result<StreamChunk, Self::Error>> + Send>>, Self::Error>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Stream chat with the model.

fn bind_tools( &self, tools: Vec<ToolDefinition>, ) -> Option<Box<dyn BaseChatModel<Error = Self::Error> + Send + Sync>>

Bind tool definitions for function calling.

fn chat_with_system<'life0, 'async_trait>( &'life0 self, system: String, messages: Vec<Message>, ) -> Pin<Box<dyn Future<Output = Result<LLMResult, Self::Error>> + Send + 'async_trait>>

where 'life0: 'async_trait, Self: Sync + 'async_trait,

Chat with system prompt.

impl BaseLanguageModel<Vec<Message>, LLMResult> for ReplayProvider

fn model_name(&self) -> &str

Returns the model name.

fn get_num_tokens(&self, text: &str) -> usize

Calculates token count for text.

fn temperature(&self) -> Option<f32>

Returns the temperature parameter.

fn max_tokens(&self) -> Option<usize>

Returns the max tokens limit.

fn with_temperature(self, _temp: f32) -> Self

Sets the temperature parameter.

fn with_max_tokens(self, _max: usize) -> Self

Sets the max tokens limit.

impl Clone for ReplayProvider

fn clone(&self) -> ReplayProvider

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Runnable<Vec<Message>, LLMResult> for ReplayProvider

type Error = TestkitError

Error type.

fn invoke<'life0, 'async_trait>( &'life0 self, input: Vec<Message>, config: Option<RunnableConfig>, ) -> Pin<Box<dyn Future<Output = Result<LLMResult, Self::Error>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Transforms single input to output.

fn batch<'life0, 'async_trait>( &'life0 self, inputs: Vec<Input>, config: Option<RunnableConfig>, ) -> Pin<Box<dyn Future<Output = Result<Vec<Output>, Self::Error>> + Send + 'async_trait>>

where 'life0: 'async_trait, Self: 'async_trait,

Batch processing - transforms multiple inputs to outputs.

fn batch_as_completed<'life0, 'async_trait>( &'life0 self, inputs: Vec<Input>, config: Option<RunnableConfig>, ) -> Pin<Box<dyn Future<Output = Result<Vec<(usize, Output)>, Self::Error>> + Send + 'async_trait>>

where 'life0: 'async_trait, Self: 'async_trait,

Batch processing that returns results in completion order.

fn stream<'life0, 'async_trait>( &'life0 self, input: Input, config: Option<RunnableConfig>, ) -> Pin<Box<dyn Future<Output = Result<Pin<Box<dyn Stream<Item = Result<Output, Self::Error>> + Send>>, Self::Error>> + Send + 'async_trait>>

where 'life0: 'async_trait, Self: 'async_trait,

Streaming output - for real-time responses (LLM, etc).

fn transform<'life0, 'async_trait>( &'life0 self, input: Pin<Box<dyn Stream<Item = Result<Input, Self::Error>> + Send>>, config: Option<RunnableConfig>, ) -> Pin<Box<dyn Future<Output = Result<Pin<Box<dyn Stream<Item = Result<Output, Self::Error>> + Send + 'life0>>, Self::Error>> + Send + 'async_trait>>

where 'life0: 'async_trait, Self: 'async_trait,

Stream-to-stream transformation - the core of LCEL streaming.