dsh-mobile-hanui
Standalone mobile UI shell for the DeepSeek Harness web GUI (phone layout, drawers, FAB, mobile composer fixes)
1323 results
Standalone mobile UI shell for the DeepSeek Harness web GUI (phone layout, drawers, FAB, mobile composer fixes)
A calm, unified prompt queue for DeepSeek Harness with smart expansion, persistent confirmations, editing, steering, accessible reordering, and official queue removal.
Visual media plugin for DeepSeek Harness: copy native image descriptions and securely normalize, inspect, and play scene-aware videos.
DSH-native HarmonyOS dev assistant: hdc device debugging, an input-row development panel, official-first versioned API docs, DevEco compile assistance, and standalone Command Line Tools support.
DeepSeek brain + automatic image transcription for DeepSeek Harness: a deepseek-vision provider route that transcribes attached images to text before delegating to the text-only DeepSeek adapter. Official deepseek-v4-flash-vision-exp by default (a pure-text V4-Pro brain can see images), any OpenAI-compatible VLM or local Ollama as alternatives, never hangs.
Terminal-style input history for the DeepSeek Harness web composer: edge-first arrows with exact draft/caret restore, browser-local persisted history, Ctrl+R reverse search, workspace-scoped recall, and fully configurable keys — plus sliding-context awareness (compaction summaries join recall/search, a compaction notice with one-click /compact fill) layered on the ordinary composer draft only.
DSH web plugin: VSCode Remote-SSH-like remote development (SSH to supercomputers/servers, remote workspace, file explorer, integrated terminal), integrated with dsh-better-sidebar and DSH settings.
VCC-style instant, near-lossless deterministic compaction engine for the DeepSeek Harness — a drop-in replacement for @deepseek-ai/dsh-compaction-basic
DSH 插件:在设置页可视化编辑系统提示词(deployment persona),支持实时预览与保存。
Langfuse observability for DeepSeek Harness: OpenTelemetry traces, compaction, feedback Scores, and fork lineage
DeepSeek Harness plugin: configurable vision model with vision_read_image tool, composer-bar vision-model selector, and automatic image-to-text conversion for text-only main models.
Structural code intelligence for DeepSeek Harness (dsh) — gives the agent codegraph and codegraph_index tools to find where a symbol is declared, what calls it, and what a change reaches, from a tree-sitter index it builds itself. Compatible with the codegraph CLI's on-disk format.
DeepSeek Harness plugin: model-facing orr_* tools plus the open-record-replay skill for the Open Record/Replay macOS workflow recorder.
A SillyTavern compatibility plugin that keeps DSH authoritative over sessions and execution, with frontend and backend APIs for composing Tavern capabilities with native DSH features.
One DeepSeek Harness Codex capability bundle for ChatGPT login, LLM access, Web Search, and durable Image Creation
DeepSeek Harness bash executor plugin that routes eligible commands through rtk (Rust Token Killer) to compress tool output and save tokens. Optional overlay: install, then enable via --patch.
Miraculous Standard — unified anchored agent preset for DeepSeek V4 Pro/Flash (official API & opencode-go). Minimal-exact two-tool first-request bootstrap, model-aware Pro/Flash paths, unified context gate, epoch-aware catalog management, rc7-ready shell handling.
A live context-window donut for DeepSeek Harness: token usage, compaction savings, and cost at a glance
Agent 运行中也能实时插入修改要求:composer 上方弹出「修改要求」输入条,与底部输入框左对齐,输入框随内容自动换行扩展,发送后注入正在运行的 agent 的下一个决策步骤,无需停止对话。运行时状态文案采用 100 条 Deep 短语池轮换,按钮为 ➤ 旋转 90° 的向上箭头。
Session replay, fork-tree, audit & compare visualization for DeepSeek Harness — time machine for your agent sessions
DeepSeek Harness 插件:在发送栏旁一键分析并优化提示词(复用当前会话模型)
Generate complete AI songs, instrumentals, and BGM with YinChao, including lyrics-to-song, reference-audio creation, and song extension.
Drop or paste images, PDFs, office docs, zips, videos and audio into the DSH composer as workspace file paths instead of model attachments — lets a text-only model agent read them via vision tools.
Per-model capability declaration for DeepSeek Harness: reasoning-effort levels (with wire spellings) and request modalities (text/image) for OpenAI-compatible providers — one settings section, no YAML hand-editing.