Struct ScriptedTasks 

pub struct ScriptedTasks { /* private fields */ }

Answers each task from its own queue of JSON documents.

Implementations

impl ScriptedTasks

pub fn new(provider: impl Into<ProviderKey>, model: impl Into<ModelKey>) -> Self

A provider with native schema support and no answers yet.

pub fn answer(self, task: &str, answer: Value) -> Self

Queues answer for the task or call task.

pub fn failing(self, task: &str, error: ProviderError) -> Self

Queues a provider failure for the task or call task.

pub fn tagged(self, tag: impl Into<String>) -> Self

Adds a tag to the profile, for routing by tag.

pub fn calls(&self) -> Vec<ModelRequest>

Every request received, in order.

pub fn called(&self) -> Vec<String>

The task ids called, in order.

pub fn unanswered(&self) -> Vec<String>

Tasks with answers never asked for.

pub fn router(self: &Arc<Self>) -> Arc<PolicyRouter>

A router over this provider alone.

Trait Implementations

impl Debug for ScriptedTasks

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

Formats the value using the given formatter.

impl ModelProvider for ScriptedTasks

fn provider_key(&self) -> ProviderKey

The configured provider key, e.g. "openai". Labels every metric, attempt record and replay entry this provider produces.

fn model_key(&self) -> ModelKey

The configured model key, e.g. "gpt-4o-2024-08-06".

fn capabilities(&self) -> ProviderCapabilities

What this provider-model pair can actually do (spec §20.3).

fn profile(&self) -> ModelProfile

The full routing profile: keys, capabilities, and the cost, region and tags routing filters on.

fn generate<'life0, 'async_trait>( &'life0 self, request: ModelRequest, ) -> Pin<Box<dyn Future<Output = Result<ModelResponse, ProviderError>> + Send + 'async_trait>>

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

Runs one model call and returns the whole answer.

fn reference(&self) -> ModelRef

The provider-model pair, as routing and health tracking key it.

fn supports( &self, requirements: &CapabilityRequirements, ) -> Result<(), CapabilityMismatch>

Checks the declared capabilities against requirements.

fn stream<'life0, 'async_trait>( &'life0 self, request: ModelRequest, ) -> Pin<Box<dyn Future<Output = Result<ModelStream, ProviderError>> + Send + 'async_trait>>

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

Runs one model call and returns its answer incrementally.