Module llm 

LLM abstraction — decouples agents from specific model providers.

The BaseLlm trait provides a unified interface for generating content from any LLM. The GeminiLlm implementation wraps gemini-live’s Client for Gemini models.

Re-exports

pub use gemini::GeminiLlm;

pub use gemini::GeminiLlmParams;

pub use registry::LlmRegistry;

Modules

gemini

Concrete Gemini LLM implementation using gemini-live Client.

registry

LLM registry — pattern-based resolution of LLM providers.

Structs

EnvTokenProvider

Default token provider — reads GOOGLE_ACCESS_TOKEN from environment.

GcloudTokenProvider

Token provider that shells out to gcloud auth print-access-token, caching the result with a configurable TTL.

LlmRequest

Configuration for an LLM generation request.

LlmResponse

The response from an LLM generation request.

ModelCapabilities

Capability declaration for a model — what callers may rely on without probing. See BaseLlm::capabilities.

TokenUsage

Token usage statistics.

Enums

LlmError

Errors from LLM operations.

Traits

BaseLlm

Trait for LLM providers — decouples agents from specific models.

TokenProvider

Provides access tokens for VertexAI authentication.