deepagents-code==0.1.63

HavocFramework/Havocdeepagents-code==0.1.63Aug 26, 2026by github-actions[bot]

AI Summary

Enhanced model capabilities with new integrations and retry logic, alongside improvements to config management and server stability.

Key Highlights

  • Added Baseten `zai-org/GLM-5.3-Flash` model support
  • Implemented retry middleware for transient model errors
  • Added support for loading managed config from remote sources

New Features

  • Baseten model integration
  • Remote managed config loading
  • Retry middleware for model nodes
  • Click-to-copy debug log path
  • Flush traces before server shutdown

Full Release Notes

### Features

- Added Baseten `zai-org/GLM-5.3-Flash` to the model switcher ([#5844](https://github.com/langchain-ai/deepagents/issues/5844)).
- Added support for loading managed config from a remote source ([#5776](https://github.com/langchain-ai/deepagents/issues/5776)).
- Added retry middleware for transient model errors in model nodes ([#4569](https://github.com/langchain-ai/deepagents/issues/4569)).

### Fixes

- Fixed live cost tracking for dynamic subagents ([#5833](https://github.com/langchain-ai/deepagents/issues/5833)).
- Improved `clear` command descriptions ([#5841](https://github.com/langchain-ai/deepagents/issues/5841)).
- Allowed instrumental Auto actions ([#5832](https://github.com/langchain-ai/deepagents/issues/5832)).
- Ensured traces are flushed before server shutdown ([#5837](https://github.com/langchain-ai/deepagents/issues/5837)).
- Made the debug log path click-to-copy ([#5845](https://github.com/langchain-ai/deepagents/issues/5845)).

---

Internal maintainers: @aolsenjazz, @johannes117, @mdrxy

Released by: @mdrxy

<details>
<summary>Git log since deepagents-code==0.1.62</summary>

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

- [`970003e`](https://github.com/langchain-ai/deepagents/commit/970003e60ba39af104bf47b1b64319d17aa4131b) release(deepagents-code): 0.1.63 (#5834)
- [`948fea8`](https://github.com/langchain-ai/deepagents/commit/948fea88e2c1e0660a3c1c7a077121c573f11675) feat(code): model-node retry middleware for transient model errors (#4569)
- [`ffae2eb`](https://github.com/langchain-ai/deepagents/commit/ffae2ebdbd3b4f5c8f7a2e584179063a2a84fcb0) test(code): pin Unicode charset in diff rendering tests (#5846)
- [`1fc7d1e`](https://github.com/langchain-ai/deepagents/commit/1fc7d1e26d21ff27327b1b0c0a926673c4663001) fix(code): make debug log path click-to-copy (#5845)
- [`731d2d5`](https://github.com/langchain-ai/deepagents/commit/731d2d5a56dc0f9e78cec77722af592ad939edd3) feat(code): add Baseten `zai-org/GLM-5.3-Flash` to model switcher (#5844)
- [`804fdcc`](https://github.com/langchain-ai/deepagents/commit/804fdcc436538686ca345965c0511e0664eb7c34) fix(code): flush traces before server shutdown (#5837)
- [`1f59064`](https://github.com/langchain-ai/deepagents/commit/1f5906427d2b7d2912054d185d856fec8e43e49c) style(code): mark wrapped diff continuations (#5836)
- [`a6b069d`](https://github.com/langchain-ai/deepagents/commit/a6b069db380c5483c414f48d9b57899c749c8528) fix(code): clarify clear command descriptions (#5841)
- [`738bf07`](https://github.com/langchain-ai/deepagents/commit/738bf077f8b079164f11742bfcaa2fa93df138d7) feat(code): define and discover Python extensions (#5631)
- [`56f51d8`](https://github.com/langchain-ai/deepagents/commit/56f51d83a7d6621f2c3954ce69740c46e3cc1426) fix(code,evals): allow instrumental Auto actions (#5832)
- [`9f3a1dd`](https://github.com/langchain-ai/deepagents/commit/9f3a1dd38f8b5dbd828d2f366e9b03dad359fadf) feat(code): load managed config from a remote source (#5776)
- [`37d7777`](https://github.com/langchain-ai/deepagents/commit/37d7777195ff5c30ef789052d02d4387725182b8) fix(code): track live dynamic subagent cost (#5833)

</details>