# DeepSeek Harness dsh-v0.1.1-rc.1 — v0.1.1-rc.1

- Product: DeepSeek Harness (https://whatsnew.fyi/product/deepseek-harness)
- Vendor: DeepSeek
- Date: 2026-08-21
- Version: dsh-v0.1.1-rc.1
- Original notes: https://github.com/deepseek-ai/deepseek-harness/releases/tag/dsh-v0.1.1-rc.1
- Permalink: https://whatsnew.fyi/product/deepseek-harness/releases/dsh-v0.1.1-rc.1
- Labels: Pre-release

What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.

Reuse: the summaries, labels and curation here are © What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'.

---

- **added** — DeepSeek adapter adds the multimodal visual understanding model DeepSeek-V4-Flash-Vision-Exp
- **fixed** — Fix potential layout issues when editing text before an @ reference in the composer
- **fixed** — Prevent confined processes from escaping Bubblewrap restrictions through /proc/<pid>/root
- **changed** — Improve responsive Markdown tables in conversations, precision for 99.x% cache-hit ratios, and subagent conversation header navigation
- **changed** — Support multiline ask_user_question answers with wrapping and Shift+Enter newlines

[中文](#cn-v0.1.1-rc.1) | [English](#en-v0.1.1-rc.1)

<h3 id="cn-v0.1.1-rc.1">新增功能</h3>

* DeepSeek 适配器新增多模态视觉理解模型 `DeepSeek-V4-Flash-Vision-Exp`

###### 问题修复

* 修复在输入框的 `@` 引用前增删改文本时，潜在的布局问题
* 修复 Bubblewrap 沙箱内的受限进程可经 `/proc/<pid>/root` 绕过限制的问题

###### 体验优化

* 优化会话 Markdown 表格自适应表现、缓存命中率在 99.x% 时的精度显示、子代理会话标题切换交互
* `ask_user_question` 回答内容支持多行输入、自动换行、`Shift+Enter` 换行

---

<h3 id="en-v0.1.1-rc.1">New Features</h3>

* The DeepSeek adapter adds the multimodal visual understanding model `DeepSeek-V4-Flash-Vision-Exp` by @LegGasai

###### Bug Fixes

* Fix potential layout issues when editing text before an `@` reference in the composer by @LegGasai
* Prevent confined processes from escaping Bubblewrap restrictions through `/proc/<pid>/root` by @Kingwl

###### Improvements

* Improve responsive Markdown tables in conversations, precision for 99.x% cache-hit ratios, and subagent conversation header navigation by @07akioni, @pku-xht, and @yixiangihsiang
* Support multiline `ask_user_question` answers with wrapping and `Shift+Enter` newlines by @LegGasai

---

Full Changelog: https://github.com/deepseek-ai/deepseek-harness/compare/dsh-v0.1.0-rc.8...dsh-v0.1.1-rc.1