Struct CopilotHeadlessRunner 

pub struct CopilotHeadlessRunner { /* private fields */ }

GitHub Copilot Headless (ACP) LLM provider.

Communicates with copilot --acp via the Agent Client Protocol (JSON-RPC over stdio). Spawns a new copilot subprocess per request using NDJSON framing. Uses types from agent-client-protocol-schema for protocol message deserialization.

Copilot manages its own tool execution internally (GitHub tools, code search), but cannot execute external MCP tools. Tool calls are observed and reported via HeadlessToolResponse from converse(). For custom tools, callers should use text-based tool calling (CLI tool loop).

Implementations

impl CopilotHeadlessRunner

pub async fn from_env() -> Self

Create a new provider from environment configuration.

Attempts to discover available models via gh copilot models. Falls back to a static list if discovery fails.

pub async fn with_config(config: CopilotHeadlessConfig) -> Self

Create a new provider with explicit configuration.

pub async fn converse( &self, request: &ChatRequest, ) -> Result<HeadlessToolResponse, RunnerError>

Run a conversation turn and return detailed results including tool call metadata.

Unlike complete(), this returns an HeadlessToolResponse with observed tool calls that copilot executed internally during the turn.

Trait Implementations

impl LlmProvider for CopilotHeadlessRunner

fn name(&self) -> &'static str

Unique provider identifier (e.g., claude_code, copilot)

fn display_name(&self) -> &str

Human-readable display name for the provider

fn capabilities(&self) -> LlmCapabilities

Provider capabilities (streaming, function calling, etc.)

fn default_model(&self) -> &str

Default model to use if not specified in request

fn available_models(&self) -> &[String]

Available models for this provider

fn complete<'life0, 'life1, 'async_trait>( &'life0 self, request: &'life1 ChatRequest, ) -> Pin<Box<dyn Future<Output = Result<ChatResponse, RunnerError>> + Send + 'async_trait>>

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

Perform a chat completion (non-streaming)

fn complete_stream<'life0, 'life1, 'async_trait>( &'life0 self, request: &'life1 ChatRequest, ) -> Pin<Box<dyn Future<Output = Result<ChatStream, RunnerError>> + Send + 'async_trait>>

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

Perform a streaming chat completion

fn health_check<'life0, 'async_trait>( &'life0 self, ) -> Pin<Box<dyn Future<Output = Result<bool, RunnerError>> + Send + 'async_trait>>

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

Check if the provider is healthy and ready to serve requests