Struct LlmEnv 

pub struct LlmEnv {
    pub provider: Option<String>,
    pub anthropic_key: Option<String>,
    pub base_url: Option<String>,
    pub api_key: Option<String>,
    pub model: Option<String>,
}

Raw environment inputs for client resolution, read once at the crate’s only environment-touching site so that resolution itself stays pure.

Deliberately does NOT derive Debug: two fields carry API keys, and a derived impl would print them through any {:?} or tracing sink.

Fields

provider: Option<String>

CODELORE_LLM_PROVIDER — anthropic or openai-compat; unset lets the presence of an Anthropic key (else the local default) decide.

anthropic_key: Option<String>

ANTHROPIC_API_KEY — the Anthropic dialect’s credential.

base_url: Option<String>

CODELORE_LLM_BASE_URL — the OpenAI-compatible endpoint base.

api_key: Option<String>

CODELORE_LLM_API_KEY — optional bearer token for the OpenAI-compatible endpoint.

model: Option<String>

CODELORE_LLM_MODEL — required for the OpenAI-compatible dialect; overrides the default Anthropic model when the Anthropic dialect is used.

Implementations

impl LlmEnv

pub fn from_process_env() -> Self

Read the LLM configuration from the process environment. Empty or whitespace-only values are treated as unset. This is the crate’s only environment-reading site.

Trait Implementations

impl Clone for LlmEnv

fn clone(&self) -> LlmEnv

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Default for LlmEnv

fn default() -> LlmEnv

Returns the “default value” for a type.