feat: track token usage when stream chat

[xingwanying]

[vercel[bot]]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
petercat	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Sep 11, 2024 6:29am

[petercat-assistant[bot]]

Walkthrough

This PR introduces functionality to track token usage during stream chats. It includes changes to the Assistant component, server-side event handling, and the OpenAI client.

Changes

File	Summary
assistant/src/Assistant/index.md	Updated the token value in the Assistant component.
server/agent/base.py	Added handling for 'on_chat_model_end' event to track token usage.
server/agent/llm/clients/openai.py	Modified the OpenAI client to enable usage streaming and refactored the client initialization.

[codecov[bot]]

Codecov Report

Attention: Patch coverage is 35.71429% with 9 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
server/agent/base.py	0.00%	5 Missing :warning:
server/agent/llm/clients/openai.py	55.55%	4 Missing :warning:

Files with missing lines	Coverage Δ
server/agent/llm/clients/openai.py	78.94% <55.55%> (+3.94%)	:arrow_up:
server/agent/base.py	24.27% <0.00%> (-1.24%)	:arrow_down:

[RaoHai]

LG