Struct ProviderConfig 

#[non_exhaustive]
pub struct ProviderConfig {
    pub provider_type: Option<String>,
    pub wire_api: Option<String>,
    pub base_url: String,
    pub api_key: Option<String>,
    pub bearer_token: Option<String>,
    pub azure: Option<AzureProviderOptions>,
    pub headers: Option<HashMap<String, String>>,
    pub model_id: Option<String>,
    pub wire_model: Option<String>,
    pub max_prompt_tokens: Option<i64>,
    pub max_output_tokens: Option<i64>,
}

Configures a custom inference provider (BYOK — Bring Your Own Key).

Routes session requests through an alternative model provider (OpenAI-compatible, Azure, Anthropic, or local) instead of GitHub Copilot’s default routing.

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

provider_type: Option<String>

Provider type: "openai", "azure", or "anthropic". Defaults to "openai" on the CLI.

wire_api: Option<String>

API format (openai/azure only): "completions" or "responses". Defaults to "completions".

base_url: String

API endpoint URL.

api_key: Option<String>

API key. Optional for local providers like Ollama.

bearer_token: Option<String>

Bearer token for authentication. Sets the Authorization header directly. Use for services requiring bearer-token auth instead of API key. Takes precedence over api_key when both are set.

azure: Option<AzureProviderOptions>

Azure-specific options.

headers: Option<HashMap<String, String>>

Custom HTTP headers included in outbound provider requests.

model_id: Option<String>

Well-known model ID used to look up agent config and default token limits. Also used as the wire model when wire_model is unset. Falls back to SessionConfig::model.

wire_model: Option<String>

Model name sent to the provider API for inference. Use this when the provider’s model name (e.g. an Azure deployment name or a custom fine-tune name) differs from model_id. Falls back to model_id, then to SessionConfig::model.

max_prompt_tokens: Option<i64>

Overrides the resolved model’s default max prompt tokens. The runtime triggers conversation compaction before sending a request when the prompt (system message, history, tool definitions, user message) would exceed this limit.

max_output_tokens: Option<i64>

Overrides the resolved model’s default max output tokens. When hit, the model stops generating and returns a truncated response.

Implementations

impl ProviderConfig

pub fn new(base_url: impl Into<String>) -> Self

Construct a ProviderConfig with the required base_url set; all other fields default to unset.

pub fn with_provider_type(self, provider_type: impl Into<String>) -> Self

Set the provider type ("openai", "azure", or "anthropic").

pub fn with_wire_api(self, wire_api: impl Into<String>) -> Self

Set the API format ("completions" or "responses"; openai/azure only).

pub fn with_api_key(self, api_key: impl Into<String>) -> Self

Set the API key. Optional for local providers like Ollama.

pub fn with_bearer_token(self, bearer_token: impl Into<String>) -> Self

Set the bearer token used to populate the Authorization header. Takes precedence over api_key when both are set.

pub fn with_azure(self, azure: AzureProviderOptions) -> Self

Set Azure-specific options.

pub fn with_headers(self, headers: HashMap<String, String>) -> Self

Set the custom HTTP headers attached to outbound provider requests.

pub fn with_model_id(self, model_id: impl Into<String>) -> Self

Set the well-known model ID used to look up agent config and default token limits. Falls back to the session’s configured model when unset.

pub fn with_wire_model(self, wire_model: impl Into<String>) -> Self

Set the model name sent to the provider API for inference. Use this when the provider’s model name (e.g. an Azure deployment name or a custom fine-tune name) differs from model_id.

pub fn with_max_prompt_tokens(self, max: i64) -> Self

Override the resolved model’s default max prompt tokens. The runtime triggers conversation compaction when the prompt would exceed this limit.

pub fn with_max_output_tokens(self, max: i64) -> Self

Override the resolved model’s default max output tokens. When hit, the model stops generating and returns a truncated response.

Trait Implementations

impl Clone for ProviderConfig

fn clone(&self) -> ProviderConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ProviderConfig

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

Formats the value using the given formatter.

impl Default for ProviderConfig

fn default() -> ProviderConfig

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ProviderConfig

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ProviderConfig

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.