streaming

A guide for showing AI responses as they arrive instead of waiting for the complete answer. It explains callbacks that run when streaming starts, for each received piece, and when it ends.

In plain words
What is it for?
Use it when adding real-time response handling with ActiveAgent, including access to the current message and each new content fragment.
Why use it?
It helps applications display incremental output and respond at the right points during an AI response.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/activeagents/activeagent/streaming
Clone the repo
git clone --depth 1 https://github.com/activeagents/activeagent
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,160 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00020 $0.01160
Opus 5 $0.00010 $0.00580
Sonnet 5 $0.00004 $0.00232
Haiku 4.5 $0.00002 $0.00116

Measured 2d ago against content hash 1779142f2551, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

streaming scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/agents/streaming.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{{ $frontmatter.title }}

Stream responses from AI providers in real-time using ActiveAgent's streaming callbacks. This guide covers handling streaming responses with callbacks that execute at different points in the streaming lifecycle.

Overview

ActiveAgent provides three streaming callbacks:

  • on_stream_open - Invoked when the stream begins
  • on_stream - Invoked for every chunk received during streaming
  • on_stream_close - Invoked when the stream completes

Callbacks automatically receive a StreamChunk object if they accept a parameter, providing access to the current message state and incremental delta content.

Basic Streaming

Enable streaming by passing stream: true to your agent or prompt:

<<< @/../test/docs/agents/streaming_examples_test.rb#basic_streaming_agent {ruby:line-numbers} [agent.rb]

<<< @/../test/docs/agents/streaming_examples_test.rb#basic_streaming_usage {ruby:line-numbers} [usage.rb]

StreamChunk Object

Each callback receives a StreamChunk with two attributes:

  • message - The current message object from the provider (accumulated state)
  • delta - The incremental content for this specific chunk (may be nil)

The delta contains only the new content received in the current chunk, while message contains the accumulated message state. Not all chunks contain a delta—some may only contain metadata updates.

def log_chunk(chunk)
  # Delta contains only new content for this chunk
  Rails.logger.debug("New content: #{chunk.delta}")

  # Message contains accumulated provider response
  Rails.logger.debug("Full message so far: #{chunk.message.inspect}")
end

Lifecycle Callbacks

Use callbacks to handle different points in the streaming lifecycle:

on_stream_open

Invoked when streaming begins. Use this to initialize state:

<<< @/../test/docs/agents/streaming_examples_test.rb#lifecycle_open {ruby:line-numbers}

on_stream

Invoked for every chunk. Keep processing lightweight:

<<< @/../test/docs/agents/streaming_examples_test.rb#lifecycle_chunk {ruby:line-numbers}

Read the full file on GitHub · 169 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 169 lines · 20 tokens per session scan A 1779142f2551

Subscribe to this mod's changes

streaming is an agent published in the GitHub repository activeagents/activeagent (971 stars, last pushed 6d ago), licensed MIT. It adds 20 tokens to every session and 1,160 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens