Struct ResolvedEndpoint 

pub struct ResolvedEndpoint {

    pub name: String,
    pub endpoint_type: EndpointType,
    pub url: String,
    pub model: Option<String>,
    pub api_key: Option<String>,
    pub headers: HashMap<String, String>,
    pub command: Option<String>,
    pub args: Vec<String>,
    pub vision: bool,
    pub input_price_per_1m: f64,
    pub output_price_per_1m: f64,
    pub cached_input_price_per_1m: f64,
    pub cache_write_price_per_1m: f64,
    pub cache_pricing: bool,
    pub cache_markers: bool,
    pub per_call_price: f64,
    pub max_attempts: u32,
    pub fallbacks: Vec<String>,
    pub provider: Provider,
    pub deployment: Option<String>,
    pub api_version: Option<String>,
    pub auth: AuthConfig,
    pub header_commands: HashMap<String, String>,
    pub aws: AwsConfig,
}

Resolved endpoint ready for use in calls.

Fields

name: String

Endpoint name.

endpoint_type: EndpointType

Endpoint type.

url: String

Base URL for HTTP-based endpoints.

model: Option<String>

Model name (LLM endpoints only).

api_key: Option<String>

API key / bearer token.

headers: HashMap<String, String>

Custom HTTP headers.

command: Option<String>

Command for MCP subprocess endpoints.

args: Vec<String>

Arguments for MCP subprocess endpoints.

vision: bool

Whether this endpoint accepts image parts (vision).

input_price_per_1m: f64

Input token pricing per 1M tokens.

output_price_per_1m: f64

Output token pricing per 1M tokens.

cached_input_price_per_1m: f64

Cached-input (prompt cache read) pricing per 1M tokens.

cache_write_price_per_1m: f64

Cache-write (cache creation) input pricing per 1M tokens.

cache_pricing: bool

Bill cache reads/writes at their cache rates (default true).

cache_markers: bool

Send provider-side prompt-cache markers (default true).

per_call_price: f64

Flat cost per call.

max_attempts: u32

Retry budget for a single chat completion (default 3; global env override HARNESS_LLM_CALL_ATTEMPTS).

fallbacks: Vec<String>

Ordered names of fallback endpoints tried when this endpoint exhausts its attempts (LLM endpoints only).

provider: Provider

LLM provider protocol.

deployment: Option<String>

Azure OpenAI deployment name (provider azure).

api_version: Option<String>

Azure OpenAI API version (provider azure).

auth: AuthConfig

Authentication configuration.

header_commands: HashMap<String, String>

Headers produced by running a command per call.

aws: AwsConfig

AWS credential settings (provider bedrock).

Implementations

impl ResolvedEndpoint

pub fn default_llm() -> Self

Creates a default LLM endpoint from environment variables.

Trait Implementations

impl Clone for ResolvedEndpoint

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ResolvedEndpoint

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

Formats the value using the given formatter.