dsh-voice-plugin
Voice input plugin for DeepSeek Harness
199 results
Voice input plugin for DeepSeek Harness
Collapse very long composer drafts into a summary card without changing DSH message submission.
Liquid Glass input card for the dsh web GUI - kube.io Magnifying Glass SVG refraction with the original coupled-spring press animation and click highlight
Correct Hebrew RTL rendering for the DeepSeek Harness web GUI: per-block direction by dominant script, bidi-safe input fields, and RTL-aware Cmd+Left/Right line navigation.
Codex-style computer use for DeepSeek Harness (DSH): read the screen and drive the mouse & keyboard. Pairs with picturereader (image_scan/image_ocr) to close the look-act-verify loop. Windows.
Prompt-cache observability and logical-input diagnostics for DeepSeek Harness
DSH Web GUI @-mention workspace file picker: input @ to filter git-tracked files plus files re-included via .aiinclude, like Codex/Claude Code file references.
智能输入插件 — 语音输入 + 提示词优化
DeepSeek Harness Web GUI 语音输入插件:在输入框发送键左侧添加麦克风按钮,支持浏览器本地识别、OpenAI 兼容语音转写接口和自定义 JSON 接口,配置可导入/导出。
Add a direct no-input continuation control for failed DeepSeek Harness sessions
DSH web plugin: local offline FunASR voice input (paraformer int8 onnx sidecar, Web Speech fallback, LLM polish).
A compact DSH Web composer island that integrates button-style input extensions without user-defined positioning.
Workspace OS status bar for DeepSeek Harness: task counts, latest run event, and checkup date above the conversation input. Zero deps, read-only, configurable data contract (.dshos/).
DSH web plugin: live Markdown + KaTeX math preview docked ABOVE the composer, via the official conversation.input.dock slot. Zero patches to DSH core.
DSH multimodal input plugin: route file attachments (images, video, audio, text) through per-preset model chains and feed the results to the session model as prompt tokens. Adds a Multimodal settings page.
Voice practice mode for the DSH web app: bilingual (中文 / English) conversation output plus read-aloud (TTS) and speech input (STT). Adds a 语音交流 dialog-mode toggle to the composer.
DeepSeek Harness Cordis plugin: drive Vimina Windows GUI automation via stdio (serve/call). Registers 26 vimina_* tools (scan/click/input/key/VMA scripts/screenshot/window/mouse).
DSH plugin: Feishu (飞书) custom-bot notifications when an agent session settles (idle) or asks for input (ask_user_question). Adapted for DSH 0.1.0-rc.7 (@deepseek-ai/cordis line).
Codex OAuth provider with native compaction and image input support for DeepSeek Harness.
DSH web focus mode plugin: ?focus=conversation.composer shows only the input area, ?focus=conversation.session shows only the message flow, both hiding the DSH main sidebar; auto-resumes the most recent non-blank session when none is current.
DeepSeek Harness plugin: OpenCode Go plan usage readout docked under the composer, aligned with the input bar width
GitHub issue and pull request references for the DeepSeek Harness web GUI: click the GitHub icon at the bottom-right of the input box to search the workspace repository and insert issue/PR references. Data comes from the gh CLI.
Enhanced workspace directory browser for the dsh web UI: quick access to /mnt Windows drives, full breadcrumb ancestry from the filesystem root, and an always-visible path input.
Windows computer-use capability for DeepSeek Harness: screenshot → vision model → simulated mouse/keyboard input, with self-evolving knowledge base.