deepagents-code==0.1.84
langchain-ai/deepagentsdeepagents-code==0.1.84Oct 12, 2026by github-actions[bot]
Upgrading?
AI Summary
This release enhances the code agent by adding server-side skill resolution and trust checking, visualizing provider reasoning in the TUI, and surfacing Daytona sandbox snapshots.
Key Highlights
- Resolve invoked skills on the server and check trust status.
- Show provider-visible reasoning by default in the TUI.
- Surface Daytona sandbox snapshots.
- Refresh the agent skill catalog when `/reload` is run.
New Features
- Server-side skill resolution and trust checking
- TUI reasoning visualization
- Daytona sandbox snapshots
Full Release Notes
### Features - Resolve invoked skills on the server and check whether they are trusted ([#6837](https://github.com/langchain-ai/deepagents/pull/6837)). - Show provider-visible reasoning by default in the TUI ([#6850](https://github.com/langchain-ai/deepagents/pull/6850)). - Surface Daytona sandbox snapshots ([#6854](https://github.com/langchain-ai/deepagents/pull/6854)). ### Bug Fixes - Refresh the agent skill catalog when `/reload` is run ([#6843](https://github.com/langchain-ai/deepagents/pull/6843)). - Keep fork goals visible without grading them ([#6893](https://github.com/langchain-ai/deepagents/pull/6893)). --- Thanks to our community contributors: @sumitbinnani Internal maintainers: @mdrxy Released by: @mdrxy <details> <summary>Git log since deepagents-code==0.1.83</summary> This commit history includes changes to this package. Commits are listed newest first. - [`2069079`](https://github.com/langchain-ai/deepagents/commit/2069079e09546060f5b52b2cd4f0e3c813e820f3) release(deepagents-code): 0.1.84 (#6891) - [`53238e9`](https://github.com/langchain-ai/deepagents/commit/53238e943fb2edd25c157178c4d6e73e2ba75f2c) chore(deps): raise dependency minimums for `all` (#6899) - [`d312bcd`](https://github.com/langchain-ai/deepagents/commit/d312bcda3c71dfc4201b993776a413c8b457b483) chore(deps): raise dependency minimums for `all` (#6898) - [`50452a3`](https://github.com/langchain-ai/deepagents/commit/50452a3af8f1f63a2a5528eeddae04b3ebb6844a) chore(deps): restore code SDK pin to 0.7.24 (#6896) - [`40fbf9d`](https://github.com/langchain-ai/deepagents/commit/40fbf9d85b0c3554120bb10ab59db424d34c78d4) feat(code): surface Daytona sandbox snapshots (#6854) - [`f776228`](https://github.com/langchain-ai/deepagents/commit/f7762288bc5b65d8820d386daf206103b1c01888) fix(code): preserve fork goal visibility without grading (#6893) - [`fe4eeab`](https://github.com/langchain-ai/deepagents/commit/fe4eeab6f5babf601d9e7ab7fb9cdf558cb1df77) chore(deps): bump `deepagents` pin in `deepagents-code` to 0.7.24 (#6894) - [`838433b`](https://github.com/langchain-ai/deepagents/commit/838433b4dcd9efa0bacba67d07e61440b43c4459) release(deepagents): 0.7.24 (#6865) - [`d9594da`](https://github.com/langchain-ai/deepagents/commit/d9594dae242546fcb7c1c9d23d1a731bf2a0ca20) fix(code): refresh the agent skill catalog on `/reload` (#6843) - [`03fa53f`](https://github.com/langchain-ai/deepagents/commit/03fa53ff68745610e2da15e30051c5e639047f88) feat(code): resolve and trust-check invoked skills on the server (#6837) - [`23994c0`](https://github.com/langchain-ai/deepagents/commit/23994c038d02f60ef83ec8c15142e8607ddb3b79) feat(code): show provider-visible reasoning by default in the TUI (#6850) - [`8d18c78`](https://github.com/langchain-ai/deepagents/commit/8d18c78e72a60b5fa64796b36e59522de60f93af) chore(deps): bump `genai-prices` in `deepagents-code` to 0.1.10 (#6885) - [`e62ab9b`](https://github.com/langchain-ai/deepagents/commit/e62ab9b08f60e46e72861d1a88ab8f4754bf0352) chore(deps): raise dependency minimums for `all` (#6873) </details>
Related Repositories
public-apis/public-apis★ 491,138
A collective list of free APIs
NousResearch/hermes-agent★ 255,978
The agent that grows with you
yt-dlp/yt-dlp★ 200,072
A feature-rich command-line audio/video downloader
microsoft/markitdown★ 191,496
Python tool for converting files and office documents to Markdown.
Significant-Gravitas/AutoGPT★ 187,704
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.