Struct CompletionModel 

pub struct CompletionModel<H = Client> {
    pub model: String,
    pub strict_tools: bool,
    pub tool_result_array_content: bool,
    pub intent: CopilotIntent,
    /* private fields */
}

Fields

model: String

strict_tools: bool

tool_result_array_content: bool

intent: CopilotIntent

Implementations

impl<H> CompletionModel<H>

where Client<H>: HttpClientExt + Clone + Debug + 'static, H: Clone + Default + Debug + WasmCompatSend + WasmCompatSync + 'static,

pub fn new(client: Client<H>, model: impl Into<String>) -> Self

pub fn with_strict_tools(self) -> Self

pub fn with_tool_result_array_content(self) -> Self

pub fn with_intent(self, intent: CopilotIntent) -> Self

Set the Copilot openai-intent header for completion and streaming requests.

pub fn with_panel_intent(self) -> Self

Use the generic chat panel openai-intent header for completion and streaming requests.

pub fn with_edits_intent(self) -> Self

Use the edit-oriented openai-intent header for completion and streaming requests.

pub async fn raw_completion( &self, completion_request: CompletionRequest, ) -> Result<CopilotCompletionResponse, CompletionError>

Execute a completion on whichever route this model is configured for and return Copilot’s own wire response.

This is the escape hatch for fields rig does not normalize; completion::CompletionModel::completion shares the same request, transport, telemetry and error path.

On the chat route the transport request id (x-request-id) is not on the wire type and is dropped here; use Self::raw_completion_with_request_id when the typed route must reproduce everything completion returns.

pub async fn raw_completion_with_request_id( &self, completion_request: CompletionRequest, ) -> Result<(CopilotCompletionResponse, Option<String>), CompletionError>

Self::raw_completion plus the transport request id from the x-request-id response header.

The pair exists because the chat route’s wire type (openai::completion::CompletionResponse) has no slot for a transport id — it is the shared OpenAI-compatible shape — while the normalized completion::CompletionResponse carries one. Without this method, raw_completion(..) followed by NormalizeCompletionResponse::normalize would silently lack the provider_request_id that completion::CompletionModel::completion reports. Reassemble with with_optional_provider_request_id. On the responses route the wire type carries the id itself; the pair’s second element is that same value, so reassembly is a no-op there.

pub async fn raw_stream( &self, completion_request: CompletionRequest, ) -> Result<RawStreamingResult<CopilotStreamingResponse>, CompletionError>

Open a stream on whichever route this model is configured for, keeping the terminal record provider-native.

Trait Implementations

impl<H: Clone> Clone for CompletionModel<H>

fn clone(&self) -> CompletionModel<H>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<H> CompletionModel for CompletionModel<H>

where Client<H>: HttpClientExt + Clone + Debug + 'static, H: Clone + Default + Debug + WasmCompatSend + WasmCompatSync + 'static,

async fn completion( &self, completion_request: CompletionRequest, ) -> Result<CompletionResponse, CompletionError>

Generates a completion response for the given completion request.

async fn stream( &self, completion_request: CompletionRequest, ) -> Result<StreamingCompletionResponse, CompletionError>

Streams a completion response for the given completion request.

fn completion_request( &self, prompt: impl Into<Message>, ) -> CompletionRequestBuilder<Self>

where Self: Sized + Clone,

Generates a completion request builder for the given prompt.

fn capabilities(&self) -> ProviderCapabilities

Provider behavior a runtime should account for when preparing requests.

impl<H> ConstructCompletionModel<Client<CopilotExt, H>> for CompletionModel<H>

where Client<H>: HttpClientExt + Clone + Debug + 'static, H: Clone + Default + Debug + WasmCompatSend + WasmCompatSync + 'static,

fn construct(client: &Client<H>, model: String) -> Self

Build this model from its provider client and a model identifier.