deepagents-code==0.1.73
unslothai/unslothdeepagents-code==0.1.73Sep 22, 2026by github-actions[bot]
Upgrading?
AI Summary
Enhances the debugging and monitoring experience with new cost breakdowns and cache timers, alongside fixes for cost warnings, thread recovery, and installation locks.
Key Highlights
- Added cache bust timer to the footer.
- Added a durable Debug Console cost breakdown.
- Added support for copying the highlighted thread ID with Ctrl+C.
- Improved cost-warning behavior by showing session cost warnings in a modal.
- Improved thread browsing and resume flows.
New Features
- Added cache bust timer to the footer
- Added a durable Debug Console cost breakdown
- Added support for copying the highlighted thread ID with Ctrl+C
Full Release Notes
### Features - Added cache bust timer to the footer. ([#6394](https://github.com/langchain-ai/deepagents/pull/6394)) - Added a durable Debug Console cost breakdown. ([#6246](https://github.com/langchain-ai/deepagents/pull/6246)) - Added support for copying the highlighted thread ID with `Ctrl+C`. ([#6431](https://github.com/langchain-ai/deepagents/pull/6431)) ### Bug Fixes - Improved cost-warning behavior by showing session cost warnings in a modal and suppressing historical cost warnings when resuming. ([#6393](https://github.com/langchain-ai/deepagents/pull/6393), [#6471](https://github.com/langchain-ai/deepagents/pull/6471)) - Made thread browsing and resume flows more resilient with recoverable thread-picker resume failures, loading labels for thread details, and a clearer thread message count header. ([#6476](https://github.com/langchain-ai/deepagents/pull/6476), [#6430](https://github.com/langchain-ai/deepagents/pull/6430), [#6428](https://github.com/langchain-ai/deepagents/pull/6428)) - Removed contradictory and invalid system-prompt instructions. ([#6072](https://github.com/langchain-ai/deepagents/pull/6072)) - Preserved `ask_user` consent receipts across user turns and reconciled interrupted tool requests. ([#6307](https://github.com/langchain-ai/deepagents/pull/6307), [#6321](https://github.com/langchain-ai/deepagents/pull/6321)) - Cleaned up newly created sandboxes when setup fails. ([#6475](https://github.com/langchain-ai/deepagents/pull/6475)) - Fixed editable refreshes so they stay anchored to the correct checkout. ([#6455](https://github.com/langchain-ai/deepagents/pull/6455)) - Kept installation locks outside the uv tool directory. ([#6472](https://github.com/langchain-ai/deepagents/pull/6472)) - Improved workspace and runtime diagnostics, including separating access-policy compatibility from runtime identity. ([#6384](https://github.com/langchain-ai/deepagents/pull/6384), [#6386](https://github.com/langchain-ai/deepagents/pull/6386)) - Deduplicated mixed-ID model usage. ([#6432](https://github.com/langchain-ai/deepagents/pull/6432)) - Clarified the compaction prompt. ([#6429](https://github.com/langchain-ai/deepagents/pull/6429)) - Restricted auto classifier IDs to the review batch enum. ([#6250](https://github.com/langchain-ai/deepagents/pull/6250)) - Used UTF-8 for prompts and skill files. ([#6474](https://github.com/langchain-ai/deepagents/pull/6474)) --- Thanks to our community contributors: @ChampionsZhang **Special thanks** to everyone who reported the issues addressed in this release: @MatthewFeroz ([#6233](https://github.com/langchain-ai/deepagents/issues/6233)), @wangjiawei-vegetable ([#6029](https://github.com/langchain-ai/deepagents/issues/6029)), @ChampionsZhang ([#6071](https://github.com/langchain-ai/deepagents/issues/6071)), @JessYanCoding ([#6229](https://github.com/langchain-ai/deepagents/issues/6229)) Internal maintainers: @mdrxy Released by: @mdrxy <details> <summary>Git log since deepagents-code==0.1.72</summary> This commit history includes changes to this package. Commits are listed newest first. - [`d5a1896`](https://github.com/langchain-ai/deepagents/commit/d5a18968f2669ce08290b2d7e2c46da13b696efa) release(deepagents-code): 0.1.73 (#6457) - [`2b767bf`](https://github.com/langchain-ai/deepagents/commit/2b767bfb8628ec50fc775fef85cbe780d2d22451) chore(deps): raise dependency minimums for `all` (#6480) - [`71b5c71`](https://github.com/langchain-ai/deepagents/commit/71b5c7115d8769ac28807d0a9991535f50765a14) chore(deps): bump `deepagents` pin in `deepagents-code` to 0.7.17 (#6479) - [`e5406d0`](https://github.com/langchain-ai/deepagents/commit/e5406d0c735c7eb72548b7ea616991987bfb21e6) release(deepagents): 0.7.17 (#6458) - [`cf5c560`](https://github.com/langchain-ai/deepagents/commit/cf5c5606648efa8bb27684fac97d9e794039707d) chore(deps): raise dependency minimums for `all` (#6478) - [`6a41c53`](https://github.com/langchain-ai/deepagents/commit/6a41c537fb1d4af7a34ef2340fff0f1c088548f4) fix(code): keep thread picker resume failures recoverable (#6476) - [`ec128d1`](https://github.com/langchain-ai/deepagents/commit/ec128d14bd59561e955115c39b8d2a1cdd4dc720) fix(code): keep installation locks outside the uv tool directory (#6472) - [`95c7630`](https://github.com/langchain-ai/deepagents/commit/95c763059fdec12991232fc63418755ba568af74) fix(code): separate access-policy compatibility from runtime identity (#6386) - [`ca00490`](https://github.com/langchain-ai/deepagents/commit/ca004904d1e48385d805d6e3b7f62f82739cfc11) fix(code): preserve `ask_user` consent receipts across user turns (#6307) - [`f9ffd51`](https://github.com/langchain-ai/deepagents/commit/f9ffd51154296f81f832f5f184407bc0067acbaf) fix(code): diagnose workspace binding and runtime refusals (#6384) - [`1ec8996`](https://github.com/langchain-ai/deepagents/commit/1ec8996c91fa6f68b3ec8145f279b8c1dea5dc20) fix(code): clean up new sandboxes when setup fails (#6475) - [`2776a66`](https://github.com/langchain-ai/deepagents/commit/2776a66a955976e4fffbf4cd8612828012feaebc) fix(code): remove contradictory and invalid system-prompt instructions (#6072) - [`8feaa0f`](https://github.com/langchain-ai/deepagents/commit/8feaa0fcce7ee967b1411c247d6f4eab202aa66d) fix(code): use UTF-8 for prompts and skill files (#6474) - [`f4c226b`](https://github.com/langchain-ai/deepagents/commit/f4c226b21cc07ee6cee6472ed726f86e69b8af36) feat(code): show cache timing in the footer (#6394) - [`13170ea`](https://github.com/langchain-ai/deepagents/commit/13170ea5b07206c94d535141af7e311666f17b7b) fix(code): suppress historical cost warnings on resume (#6471) - [`c981748`](https://github.com/langchain-ai/deepagents/commit/c9817483eeea620b1523dcfaed2802269c79d4fe) feat(code): add durable Debug Console cost breakdown (#6246) - [`5c09b92`](https://github.com/langchain-ai/deepagents/commit/5c09b9291924df7f67fbc73fda2214a0a50005ea) fix(code): show loading labels for thread details (#6430) - [`376e988`](https://github.com/langchain-ai/deepagents/commit/376e988f98fea5e501050efe250d683259e551f5) fix(code): reconcile interrupted tool requests (#6321) - [`6152733`](https://github.com/langchain-ai/deepagents/commit/6152733cbd6b73709a704f3f41b93e2576c5cd52) fix(code): restrict auto classifier IDs to the review batch enum (#6250) - [`c1395da`](https://github.com/langchain-ai/deepagents/commit/c1395dab009690a30d495bfcae33fb92f62d08c4) fix(code): show session cost warnings in a modal (#6393) - [`bdca132`](https://github.com/langchain-ai/deepagents/commit/bdca132ee7fbf84ab611392adb6846a1c545d26c) fix(code): deduplicate mixed-ID model usage (#6432) - [`0a6bd89`](https://github.com/langchain-ai/deepagents/commit/0a6bd899a0760af76bca025ea6af39997b78e611) feat(code): copy highlighted thread ID with `ctrl+c` (#6431) - [`15cf630`](https://github.com/langchain-ai/deepagents/commit/15cf6301e49e00963df876b6697fcc7c42d027d8) fix(code): clarify compaction prompt (#6429) - [`e775680`](https://github.com/langchain-ai/deepagents/commit/e775680e1cb5a52ba816e6c4663a647a7025d566) fix(code): clarify thread message count header (#6428) - [`edc7458`](https://github.com/langchain-ai/deepagents/commit/edc7458e463349ec6b4db5f0828e77c4be1e9857) chore(deps): bump `deepagents` pin in `deepagents-code` to 0.7.16 (#6453) - [`a6d844d`](https://github.com/langchain-ai/deepagents/commit/a6d844d47126bb905f30e76569110cd68294a0b3) fix(code): anchor editable refresh to its checkout (#6455) - [`0114a3f`](https://github.com/langchain-ai/deepagents/commit/0114a3f824cd5e626acb7b64d3c8e24468319d09) release(deepagents): 0.7.16 (#6372) </details>
Related Repositories
public-apis/public-apis★ 491,133
A collective list of free APIs
NousResearch/hermes-agent★ 255,919
The agent that grows with you
yt-dlp/yt-dlp★ 200,010
A feature-rich command-line audio/video downloader
microsoft/markitdown★ 191,485
Python tool for converting files and office documents to Markdown.
Significant-Gravitas/AutoGPT★ 187,701
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.