Structs§
- Completion
Config - Configuration for LLM completion.
- Model
Context Window - Provider-advertised context capacity; independent of completion configuration.
- Stream
Metrics - Provider-neutral final generation metrics.
- Stream
Progress - Provider-neutral progress for a streamed provider frame.
Enums§
- Reasoning
Effort - Reasoning effort level for models that support extended thinking
- Response
Format - Format specification for LLM responses
- Stream
Chunk - Streaming response chunk
Traits§
- LlmGateway
- Abstract interface for LLM providers