org.llm4s.llmconnect.streaming

Snapshot of accumulator state

Anthropic-specific streaming response handler

Base implementation of StreamingResponseHandler with common functionality

OpenAI-specific streaming response handler

Server-Sent Events (SSE) parser for streaming LLM responses.

Handles the SSE format used by both OpenAI and Anthropic streaming endpoints. SSE format consists of fields like:

• data:
• event:
• id:
• retry:
• :

Accumulates streaming chunks into a complete response. Handles content accumulation, tool call accumulation, thinking content, and token tracking.

Factory for creating accumulators

Options for streaming completions with callbacks for different events. Provides a more flexible alternative to the simple onChunk callback.

Companion object with convenience constructors

Handles streaming responses from LLM providers. Manages the lifecycle of streaming, chunk accumulation, and error handling.

Factory for creating provider-specific handlers