Module llm

Expand description

Provider-neutral conversation types shared by routing, clients, and translation.

Structs§

AggLlmResponse: Normalized, fully-buffered response — the aggregate of a completed generation. This is the terminal form of a streamed LlmResponse.
InputCacheUsage: Optional cache-token detail kept out of the common, cache-free usage allocation.
InstructionBlock: Instruction content separated from normal conversation messages.
LlmRequest: Normalized request representation shared by Switchyard components.
Message: One normalized conversation message.
OutputParams: Output budget and structured-output options.
PreservationMetadata: Exact source payloads retained for lossless same-format round trips.
ProviderExtensions: Provider-specific fields that do not have first-class conversation fields.
ReasoningParams: Provider reasoning controls preserved by translation.
ResponseOutput: One assistant output item in a normalized response.
SamplingParams: Provider sampling parameters with common cross-provider names.
ToolCall: Normalized assistant tool call.
ToolDefinition: Normalized tool definition.
ToolResult: Normalized tool result message content.
Usage: Normalized token usage counts.

ContentBlock: Normalized content block variants carried by messages and tool results.
FileSource: File payload forms supported by the conversation model.
ImageSource: Image payload forms supported by the conversation model.
MediaSource: Audio and video payload forms supported by the conversation model.
Role: Actor role normalized across provider APIs.
StopReason: Normalized reason a model stopped producing output.
ToolChoice: Normalized tool choice policy.