Starstruk Logo MarkStarstruk

deepagents-code==0.1.75

FoundationVision/VARdeepagents-code==0.1.75Sep 23, 2026by github-actions[bot]

Upgrading?

What changed from 2.18.0 → deepagents-code==0.1.75?What's new in @pascal-app/cli@1.0.3 after deepagents-code==0.1.75?

AI Summary

This update improves performance by warming MCP caches without blocking the event loop and ensures token and cost breakdowns remain updated while the view is open.

Key Highlights

  • Lazy MCP caches warm without blocking the event loop
  • Token and cost breakdowns refresh while the view is open

New Features

  • Non-blocking cache warming
  • Real-time cost breakdown refresh

Full Release Notes

### Bug Fixes

- Lazy MCP caches now warm without blocking the event loop.
- Token and cost breakdowns now refresh while the view is open.

---

Internal maintainers: @mdrxy

Released by: @mdrxy

<details>
<summary>Git log since deepagents-code==0.1.74</summary>

This commit history includes changes to this package. Commits are listed newest first.

- [`c526854`](https://github.com/langchain-ai/deepagents/commit/c52685431535b143b860a995eaadfbabcf9b409c) release(deepagents-code): 0.1.75 (#6518)
- [`460feb6`](https://github.com/langchain-ai/deepagents/commit/460feb63301e61e7e40e27932ca41a908c442841) chore(deps): raise dependency minimums for `all` (#6511)
- [`95b338e`](https://github.com/langchain-ai/deepagents/commit/95b338e52844680b23ed6aa38ddb54b2acb90848) chore(deps): bump `genai-prices` in `deepagents-code` to 0.1.8 (#6516)
- [`22524ed`](https://github.com/langchain-ai/deepagents/commit/22524edb7702d6fb31ffefd2d7d19549b17d2ed6) fix(code): refresh token and cost breakdown while open (#6520)
- [`e6419a6`](https://github.com/langchain-ai/deepagents/commit/e6419a6fbabf18d8232fb6b0a0283bc933b4bae3) fix(code): warm lazy MCP caches off the event loop (#6517)

</details>

Related Repositories

rasbt/LLMs-from-scratch★ 107,041

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

lyogavin/airllm★ 40,150

AirLLM 2.8T LLM inference with single 4GB GPU

NirDiamant/RAG_Techniques★ 29,958

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

microsoft/OmniParser★ 25,539

A simple screen parsing tool towards pure vision based GUI agent

karpathy/nn-zero-to-hero★ 24,906

Neural Networks: Zero to Hero