Struct VsCodeCopilotProvider 

pub struct VsCodeCopilotProvider { /* private fields */ }

VSCode Copilot LLM provider (proxy-based).

Connects to copilot-api proxy for GitHub Copilot access.

Implementations

impl VsCodeCopilotProvider

pub fn new() -> VsCodeCopilotProviderBuilder

Create a new provider builder with default settings.

pub fn with_proxy(proxy_url: impl Into<String>) -> VsCodeCopilotProviderBuilder

Create a provider builder with custom proxy URL.

pub fn get_client(&self) -> &VsCodeCopilotClient

Get a reference to the HTTP client for advanced operations.

pub async fn list_models(&self) -> Result<ModelsResponse>

List available models from the Copilot API.

OODA-79: Dynamic Model Discovery

Delegates to the underlying client to fetch available models. Returns models that are available for the authenticated user.

Trait Implementations

impl Clone for VsCodeCopilotProvider

fn clone(&self) -> VsCodeCopilotProvider

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Default for VsCodeCopilotProvider

fn default() -> Self

Returns the “default value” for a type.

impl EmbeddingProvider for VsCodeCopilotProvider

fn name(&self) -> &str

Get the name of this provider.

fn model(&self) -> &str

Get the embedding model.

fn dimension(&self) -> usize

Get the dimension of the embeddings.

fn max_tokens(&self) -> usize

Get the maximum number of tokens per input.

fn embed<'life0, 'life1, 'async_trait>( &'life0 self, texts: &'life1 [String], ) -> Pin<Box<dyn Future<Output = LlmResult<Vec<Vec<f32>>>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Generate embeddings for a batch of texts.

fn embed_one<'life0, 'life1, 'async_trait>( &'life0 self, text: &'life1 str, ) -> Pin<Box<dyn Future<Output = Result<Vec<f32>>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Generate embedding for a single text.

impl LLMProvider for VsCodeCopilotProvider

fn supports_tool_streaming(&self) -> bool

OODA-05: Enable streaming with tool calls for real-time token display.

fn chat_with_tools_stream<'life0, 'life1, 'life2, 'life3, 'async_trait>( &'life0 self, messages: &'life1 [ChatMessage], tools: &'life2 [ToolDefinition], tool_choice: Option<ToolChoice>, options: Option<&'life3 CompletionOptions>, ) -> Pin<Box<dyn Future<Output = LlmResult<BoxStream<'static, LlmResult<StreamChunk>>>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait, 'life3: 'async_trait,

Stream LLM response with tool calls (OODA-05).

Returns a stream of StreamChunk events for real-time:

• Content display
• Tool call progress
• Token counting and rate display

This enables the React agent to use StreamingProgress instead of SpinnerGuard, providing ⚡ N tokens (M t/s) display.

fn name(&self) -> &str

Get the name of this provider.

fn model(&self) -> &str

Get the current model.

fn max_context_length(&self) -> usize

Get the maximum context length for the model.

fn complete<'life0, 'life1, 'async_trait>( &'life0 self, prompt: &'life1 str, ) -> Pin<Box<dyn Future<Output = LlmResult<LLMResponse>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Generate a completion for the given prompt.

fn complete_with_options<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, prompt: &'life1 str, options: &'life2 CompletionOptions, ) -> Pin<Box<dyn Future<Output = LlmResult<LLMResponse>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait,

Generate a completion with custom options.

fn chat<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, messages: &'life1 [ChatMessage], options: Option<&'life2 CompletionOptions>, ) -> Pin<Box<dyn Future<Output = LlmResult<LLMResponse>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait,

Generate a chat completion with messages.

fn chat_with_tools<'life0, 'life1, 'life2, 'life3, 'async_trait>( &'life0 self, messages: &'life1 [ChatMessage], tools: &'life2 [ToolDefinition], tool_choice: Option<ToolChoice>, options: Option<&'life3 CompletionOptions>, ) -> Pin<Box<dyn Future<Output = LlmResult<LLMResponse>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait, 'life3: 'async_trait,

Generate a chat completion with tool/function calling support.

fn stream<'life0, 'life1, 'async_trait>( &'life0 self, prompt: &'life1 str, ) -> Pin<Box<dyn Future<Output = LlmResult<BoxStream<'static, LlmResult<String>>>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Generate a streaming completion.

fn supports_streaming(&self) -> bool

Check if the model supports streaming.

fn supports_json_mode(&self) -> bool

Check if the model supports JSON mode.

fn supports_function_calling(&self) -> bool

Check if the model supports function/tool calling.

fn model_name(&self) -> Option<String>

Get the model name as an Option<String>.