Skip to content

Conversation

@xyliugo
Copy link
Collaborator

@xyliugo xyliugo commented Aug 29, 2025

Change Type

  • ✨ feat
  • πŸ› fix
  • ♻️ refactor
  • πŸ’„ style
  • πŸ‘· build
  • ⚑️ perf
  • πŸ“ docs
  • πŸ”¨ chore

Description of Change

  • Switched to LiteLLM, which is simpler and more flexible than the OpenAI Agents SDK for testing MCP capabilities.
  • Started building a new agent (mcpmark-agent) on top of LiteLLM.
  • Dropped Stream mode since we already handle looped tool-calling.
  • Added reasoning_effort support (comes built-in with LiteLLM).
  • Removed base_url because LiteLLM doesn’t need it.
  • Got rid of the heavy OpenAI Agents SDK dependency.

Additional Information

image

@xyliugo xyliugo marked this pull request as draft August 29, 2025 18:54
@zjwu0522 zjwu0522 force-pushed the feat/mcpmark-agent branch from 0bf5fa5 to 7a2182e Compare August 30, 2025 17:18
@zjwu0522 zjwu0522 changed the base branch from main to dev August 31, 2025 06:04
@zjwu0522 zjwu0522 marked this pull request as ready for review August 31, 2025 06:04
@zjwu0522 zjwu0522 merged commit b547e57 into dev Aug 31, 2025
2 checks passed
@zjwu0522 zjwu0522 deleted the feat/mcpmark-agent branch August 31, 2025 06:04
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants