boost-modules

name	boost-modules
description	Create custom modules for [Harbor Boost](https://github.com/av/harbor/tree/main/boost), an optimizing LLM proxy. Use when building Python modules that intercept/transform LLM chat completions—reasoning chains, prompt injection, structured outputs, artifacts, or custom workflows. Triggers on requests to create Boost modules, extend LLM behavior via proxy, or implement chat completion middleware.

Harbor Boost Custom Modules

Boost modules are Python files that intercept chat completions and can transform, augment, or replace LLM responses.

Module Structure

ID_PREFIX = 'mymodule'  # Models prefixed with this trigger the module

async def apply(chat, llm):
    # chat: conversation history (linked list of ChatNodes)
    # llm: interface to downstream LLM and output streaming
    await llm.stream_final_completion()

Quick Reference

Output Methods

# Stream text to client
await llm.emit_message("Hello")

# Status indicator (formatted per HARBOR_BOOST_STATUS_STYLE)
await llm.emit_status("Processing...")

# Internal completion (not streamed to client)
result = await llm.chat_completion(prompt="Summarize: {text}", text=content, resolve=True)

# Streamed completion (visible to client)
 llm.stream_chat_completion(prompt=, topic=)


 llm.stream_final_completion()
 llm.stream_final_completion(prompt=, msg=chat.tail.content)


 pydantic  BaseModel, Field
 ():
    answer:  = Field(description=)
result =  llm.chat_completion(prompt=, schema=Response, resolve=)


 llm.emit_artifact()