mirror of
https://github.com/langchain-ai/deepagents.git
synced 2026-07-21 09:15:22 -04:00
github-actions[bot]
18679a1a88
> [!CAUTION] > Merging this PR will automatically publish to **PyPI** and create a **GitHub release**. For the full release process, see [`.github/RELEASING.md`](https://github.com/langchain-ai/deepagents/blob/main/.github/RELEASING.md). --- _Release notes preview: keep this section in sync with the package `CHANGELOG.md`. The published GitHub release body is extracted from the merged `CHANGELOG.md` by `release.yml`, not from this PR description._ --- ## [0.1.42](https://github.com/langchain-ai/deepagents/compare/deepagents-code==0.1.41...deepagents-code==0.1.42) (2026-07-17) ### Features - Plugins are now generally available. ([#4797](https://github.com/langchain-ai/deepagents/issues/4797)) - Added search to the plugin list and now summarize plugin changes after reloads. ([#4765](https://github.com/langchain-ai/deepagents/issues/4765), [#4767](https://github.com/langchain-ai/deepagents/issues/4767)) - Added Kimi K3 to the OpenRouter model selector. ([#4803](https://github.com/langchain-ai/deepagents/issues/4803)) - Added hidden `connect` and `reconnect` keywords for `/restart`. ([#4807](https://github.com/langchain-ai/deepagents/issues/4807)) - Debug Console thread IDs can now be clicked to copy, with an added LangSmith link. ([#4760](https://github.com/langchain-ai/deepagents/issues/4760)) - Added auto-approve (YOLO) mode to trace metadata. ([#4764](https://github.com/langchain-ai/deepagents/issues/4764)) ### Bug Fixes - Improved plugin marketplace loading and onboarding, including asynchronous marketplace additions and polish for empty marketplace states. ([#4766](https://github.com/langchain-ai/deepagents/issues/4766), [#4759](https://github.com/langchain-ai/deepagents/issues/4759)) - Clarified plugin component discovery and reload status. ([#4774](https://github.com/langchain-ai/deepagents/issues/4774)) - Avoided blocking MCP OAuth token refresh. ([#4770](https://github.com/langchain-ai/deepagents/issues/4770)) - Restored keyboard focus for marketplace details. ([#4763](https://github.com/langchain-ai/deepagents/issues/4763)) - Dismissed the startup tip when submitting an initial prompt with `-m`. ([#4779](https://github.com/langchain-ai/deepagents/issues/4779)) _End release notes preview._ --- > [!NOTE] > A **New Contributors** section is appended to the GitHub release notes automatically at publish time (see [Release Pipeline](https://github.com/langchain-ai/deepagents/blob/main/.github/RELEASING.md#release-pipeline), step 2). --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: langchain-oss-automated-triage[bot] <248757908+langchain-oss-automated-triage[bot]@users.noreply.github.com>
Deep Agents Evals
End-to-end behavioral evaluation suite for the Deep Agents SDK. Each eval runs an agent against a real LLM, captures the full trajectory (tool calls, file mutations, final response), and scores it on correctness and efficiency.
See EVAL_CATALOG.md for the full list of evals and categories, and MODEL_GROUPS.md for the model catalog used by the eval workflow.
The suite also includes Harbor integration for running sandboxed benchmarks like Terminal Bench 2.0.
Results
| Suite | CI | LangSmith |
|---|---|---|
| Evals | evals.yml | deepagents-evals |
| Harbor | harbor.yml | deepagents-harbor |
Contributing
Architecture, writing new evals, category system, Harbor setup, and LangSmith integration are all documented in CONTRIBUTING.md.
Resources
- LangChain Academy — Comprehensive, free courses on LangChain libraries and products, made by the LangChain team.
- Code of Conduct — community guidelines and standards