deepagents-code==0.1.74
VoiceBlender/voiceblenderdeepagents-code==0.1.74Sep 23, 2026by github-actions[bot]
Upgrading?
AI Summary
Adds interactive features for thread management and usage tracking, along with bug fixes for API errors and performance optimizations for data loading.
Key Highlights
- Added inline thread mentions & picker via `@@`.
- Usage summaries now show human invocations.
- Retry bare `openai.APIError` exceptions raised mid-stream.
- Performance improvements include reusing Auto classifier history.
New Features
- Added inline thread mentions & picker via `@@`
Full Release Notes
### Features - Added inline thread mentions & picker via `@@` ([#6197](https://github.com/langchain-ai/deepagents/pull/6197)). - Usage summaries now show human invocations ([#6500](https://github.com/langchain-ai/deepagents/pull/6500)). ### Bug Fixes - Retry bare `openai.APIError` exceptions raised mid-stream ([#6499](https://github.com/langchain-ai/deepagents/pull/6499)). - Keep prompt recall results out of the file picker ([#6494](https://github.com/langchain-ai/deepagents/pull/6494)). - Read `hooks.json` as UTF-8 in the legacy hook loader ([#6501](https://github.com/langchain-ai/deepagents/pull/6501)). ### Performance Improvements - Reuse Auto classifier history ([#6056](https://github.com/langchain-ai/deepagents/pull/6056)). - Rank checkpoint and message row IDs before loading blobs and prompts ([#6488](https://github.com/langchain-ai/deepagents/pull/6488), [#6489](https://github.com/langchain-ai/deepagents/pull/6489)). - Log thread-loading phase timings ([#6490](https://github.com/langchain-ai/deepagents/pull/6490)). --- Thanks to our community contributors: @JessYanCoding Internal maintainers: @mdrxy Released by: @mdrxy <details> <summary>Git log since deepagents-code==0.1.73</summary> This commit history includes changes to this package. Commits are listed newest first. - [`e109d04`](https://github.com/langchain-ai/deepagents/commit/e109d04a9a61cfaf7719211c1e3c35889127eae2) release(deepagents-code): 0.1.74 (#6493) - [`0779f31`](https://github.com/langchain-ai/deepagents/commit/0779f314841ec4216a189b70c615d06194731ecd) feat(code): show human invocations in usage teardown (#6500) - [`854f655`](https://github.com/langchain-ai/deepagents/commit/854f655aad543cb993f6376f97a775eac1b727ec) chore(deps): bump `deepagents` pin in `deepagents-code` to 0.7.18 (#6506) - [`61bada8`](https://github.com/langchain-ai/deepagents/commit/61bada8bcbb62a40bfbe0345831228756f0ba353) fix(code): read `hooks.json` as UTF-8 in the legacy hook loader (#6501) - [`c172018`](https://github.com/langchain-ai/deepagents/commit/c17201847dd65390662a763ddd93ed84bbb8931c) release(deepagents): 0.7.18 (#6491) - [`0f95915`](https://github.com/langchain-ai/deepagents/commit/0f959156b828f9deb08438b71dbc9a65c13b1714) fix(code): retry bare `openai.APIError` raised mid-stream (#6499) - [`9a50bf5`](https://github.com/langchain-ai/deepagents/commit/9a50bf5c966fb599e240a6c52167133daaff5565) chore(deps): raise dependency minimums for `all` (#6498) - [`44926fa`](https://github.com/langchain-ai/deepagents/commit/44926fa8f26dfb24d9a0e3ded335c48b123d193d) perf(code): reuse Auto classifier history (#6056) - [`9d3da12`](https://github.com/langchain-ai/deepagents/commit/9d3da1287ba5656d52ad7f2c75cf9062d46a4959) feat(code): add thread picker (#6197) - [`86b7f85`](https://github.com/langchain-ai/deepagents/commit/86b7f85af7424ff2491206070897818d71e163cb) fix(code): keep prompt recall out of file picker (#6494) - [`ad038f8`](https://github.com/langchain-ai/deepagents/commit/ad038f87e07e13791ff9b1e239326d2c959fd412) perf(code): log thread loading phase timings (#6490) - [`17ea378`](https://github.com/langchain-ai/deepagents/commit/17ea378fcb04f15c916e64eaf24a833b3a63c504) perf(code): rank message row IDs before loading prompts (#6489) - [`933eaea`](https://github.com/langchain-ai/deepagents/commit/933eaeaddea12d1d6fcd0a8cd7716e948ff1df58) perf(code): rank checkpoint row IDs before loading blobs (#6488) - [`333f6ab`](https://github.com/langchain-ai/deepagents/commit/333f6abc6e49a63146b1590f473eb9145d019d7c) docs(code): clarify non-interactive approval semantics (#6483) </details>
Related Repositories
ollama/ollama★ 184,217
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
fatedier/frp★ 110,057
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
infiniflow/ragflow★ 92,619
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
gohugoio/hugo★ 90,198
The world’s fastest framework for building websites.
junegunn/fzf★ 83,715
:cherry_blossom: A command-line fuzzy finder