Skip to main content
Stream responses in real-time using processStream(). Supports content chunks, thinking/reasoning, tool calls, and memory persistence.

Basic Streaming

Chunk Types

Your stream can receive different chunk types:

Streaming with Thinking

When thinking is enabled, reasoning content arrives as separate chunks before the final response:

Streaming with Tool Calls

Tool calls are reported as internal_process chunks. The agent handles the tool loop automatically:

Streaming with Memory

Memory is automatically loaded before and saved after streaming:

LLM Standalone Streaming

Direct LLM streaming without agents:

Testing in Prompt Studio

You can test streaming behavior directly in the Portal’s Prompt Studio:
  1. Open Prompts and select or create a prompt
  2. Click the config icon and enable Thinking
  3. Send a message — you’ll see the thinking content appear as a collapsible block above the response

Next Steps

Reasoning

Extended thinking for complex tasks

Memory

Conversation persistence