deepagents-code==0.1.81

### Features

- The agent can now discover marketplace plugins ([#6719](https://github.com/langchain-ai/deepagents/pull/6719)).
- You can open the effort selector during active runs ([#6724](https://github.com/langchain-ai/deepagents/pull/6724)) and the cost breakdown from the footer ([#6723](https://github.com/langchain-ai/deepagents/pull/6723)).
- Added `--no-tracing` and an explicit tracing status indicator ([#6721](https://github.com/langchain-ai/deepagents/pull/6721)).
- Renamed `/summarization-model` to `/offload model` ([#6774](https://github.com/langchain-ai/deepagents/pull/6774)).
- Highlighted the active line in multiline chat input ([#6746](https://github.com/langchain-ai/deepagents/pull/6746)).

### Bug Fixes

- Use `ChatBedrockConverse` for non-Anthropic Bedrock models ([#6718](https://github.com/langchain-ai/deepagents/pull/6718)).
- Prevented concurrent writes to local threads ([#6717](https://github.com/langchain-ai/deepagents/pull/6717)).
- Hook execution now fails closed if its context changes when a run resumes ([#6712](https://github.com/langchain-ai/deepagents/pull/6712)).
- Improved server-side model catalog, selection, and interactive model metadata handling ([#6773](https://github.com/langchain-ai/deepagents/pull/6773), [#6772](https://github.com/langchain-ai/deepagents/pull/6772)).
- Isolated stored provider endpoints in workspace models ([#6771](https://github.com/langchain-ai/deepagents/pull/6771)).
- Reconciled cache expiry during model requests ([#6763](https://github.com/langchain-ai/deepagents/pull/6763)).
- Preserved dispatch timers across interrupt replays ([#6722](https://github.com/langchain-ai/deepagents/pull/6722)).
- Collapsed idle subagents and reopened them for new work ([#6782](https://github.com/langchain-ai/deepagents/pull/6782)).
- Moved debug MCP server details into a modal ([#6720](https://github.com/langchain-ai/deepagents/pull/6720)).
- Clarified that clearing the chat starts a new thread ([#6726](https://github.com/langchain-ai/deepagents/pull/6726)).

---

Thanks to our community contributors: @kimnamu

**Special thanks** to everyone who reported the issues addressed in this release: @kimnamu ([#6536](https://github.com/langchain-ai/deepagents/issues/6536))

Internal maintainers: @mdrxy

Released by: @mdrxy

<details>
<summary>Git log since deepagents-code==0.1.80</summary>

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

- [`02ed19a`](https://github.com/langchain-ai/deepagents/commit/02ed19a42715fe0e9f2059fe8cf4fe6883054f08) release(deepagents-code): 0.1.81 (#6725)
- [`70288ad`](https://github.com/langchain-ai/deepagents/commit/70288ad564d31631ed409566c71f0cb58fc6c437) fix(code): collapse idle subagents and reopen new work (#6782)
- [`2fd6686`](https://github.com/langchain-ai/deepagents/commit/2fd66863c277cacc82dbcb39021e01691fb43e1f) fix(code): highlight the first line of multiline chat input (#6781)
- [`a282003`](https://github.com/langchain-ai/deepagents/commit/a282003b502e5b7a97cee97b792efd1ec87e9972) fix(code): reconcile cache expiry during model requests (#6763)
- [`4b94102`](https://github.com/langchain-ai/deepagents/commit/4b9410272a4e4885ec70fb1ec8549e307a15e585) fix(code): unify model catalogs and selection on the server (#6773)
- [`7ee648f`](https://github.com/langchain-ai/deepagents/commit/7ee648ffc65f91450678d5ffa1604fda605ece7f) chore(code): trim startup tips and clarify prompt history hints (#6780)
- [`1d468d9`](https://github.com/langchain-ai/deepagents/commit/1d468d9f3d7f43de096a342dabd7abafbad61f73) fix(code): use `ChatBedrockConverse` for non-Anthropic Bedrock models (#6718)
- [`3086f7b`](https://github.com/langchain-ai/deepagents/commit/3086f7b918b53b12a6ad675231ebd4752d4a420a) fix(code): fail closed when hook context changes on resume (#6712)
- [`3d16423`](https://github.com/langchain-ai/deepagents/commit/3d16423afbcbb11ea428265c91c203235c2e82b2) fix(code): resolve interactive model metadata on the server (#6772)
- [`7803173`](https://github.com/langchain-ai/deepagents/commit/78031730dbe1ae418f39be96f6d2b1e60fbe4545) fix(code): isolate stored provider endpoints in workspace models (#6771)
- [`df20c07`](https://github.com/langchain-ai/deepagents/commit/df20c0748015af173bc60588d69fef6865c01319) feat(code): add `--no-tracing` and explicit tracing status (#6721)
- [`52cc3e2`](https://github.com/langchain-ai/deepagents/commit/52cc3e2f52b5dac038da9f56ddfeb6898c3e8c85) feat(code): teach the agent to discover marketplace plugins (#6719)
- [`40df83f`](https://github.com/langchain-ai/deepagents/commit/40df83ff74ddeba9c3e8575a2b8f228b3819a7be) fix(code): move debug MCP server details into a modal (#6720)
- [`b643f6f`](https://github.com/langchain-ai/deepagents/commit/b643f6f34be0142fc3e33cd7402f171e62e69cc3) feat(code): rename `/summarization-model` to `/offload model` (#6774)
- [`100cb4c`](https://github.com/langchain-ai/deepagents/commit/100cb4c3edce8bae25057b6f2a736f8f547c211e) test(code): stabilize resume cost and replay timing assertions (#6766)
- [`c431ee5`](https://github.com/langchain-ai/deepagents/commit/c431ee5caed20aa94718f81653948d7f2a665106) chore(deps): bump `deepagents` pin in `deepagents-code` to 0.7.22 (#6764)
- [`dcba425`](https://github.com/langchain-ai/deepagents/commit/dcba42543955cadd63718f64ba0165864e7323ad) release(deepagents): 0.7.22 (#6744)
- [`337f4d0`](https://github.com/langchain-ai/deepagents/commit/337f4d08e26ddd2e8409535c12be451e4bf2c2ef) chore(deps): raise dependency minimums for `all` (#6730)
- [`b0f9b41`](https://github.com/langchain-ai/deepagents/commit/b0f9b41cad6089640ea479a3fbc255a1fb0171b6) fix(code): prevent concurrent local thread writers (#6717)
- [`6ac63cf`](https://github.com/langchain-ai/deepagents/commit/6ac63cf2cead6adb50e4404adc1cbf1b27ccdc41) feat(code): open effort selector during active runs (#6724)
- [`99e1e9a`](https://github.com/langchain-ai/deepagents/commit/99e1e9a4f9e58b7e436df29e7458731e9fd5bd89) feat(code): highlight the active multiline chat input line (#6746)
- [`4c55f5a`](https://github.com/langchain-ai/deepagents/commit/4c55f5a80c376f61144e91cb796ca4303e7bc2a4) feat(code): open cost breakdown from the footer (#6723)
- [`8468bad`](https://github.com/langchain-ai/deepagents/commit/8468bad7054cb778aa8b199ee5a644a5acca0332) fix(code): clarify clear hint starts a new thread (#6726)
- [`899a9f7`](https://github.com/langchain-ai/deepagents/commit/899a9f79161ef9a19bc5a378cbd4215bb946f583) fix(code): preserve dispatch timers across interrupt replays (#6722)

</details>