dsh-assistant-optimization
Fold mis-rendered thinking content into collapsible blocks, render mermaid inline, show file-edit diff counts, rewrite composer drafts with the current model, and resume interrupted turns from the send button.
1340 results
Fold mis-rendered thinking content into collapsible blocks, render mermaid inline, show file-edit diff counts, rewrite composer drafts with the current model, and resume interrupted turns from the send button.
Play a short chime when any conversation turn finishes. Built-in tones plus one custom upload, configured in Settings → Plugins.
DSH plugin: renders images inline in DeepSeek Harness Web chat and gives text-only models vision — cloud multimodal API first, local Qwen3-VL fallback.
DSH web plugin: a yellow one-line cache-miss notice under the first assistant reply of each turn, when that turn's first request rebuilt the prompt cache.
Adaptive model routing for DeepSeek Harness: per-request complexity classification with automatic provider routing.
为 DeepSeek Harness 添加个性化设置
DSH recap plugin: distills every model request (turn:step) of a session into one sentence, appended incrementally with a cache-friendly prompt (history sentences first, new delta last). Side-effect-free for the agent loop.
User preference memory for DeepSeek Harness: persisted user profile with memory_get/memory_update tools and system-prompt injection
Chinese exam countdown for DeepSeek Harness. Query 64 built-in exams (gaokao, kaoyan, civil service, CET-4/6, CPA, bar exam...) and get days-until dates computed by pure date math with rolling yearly recurrence.
A semantic, theme-compatible motion runtime for DeepSeek Harness.
Enhanced subagent delegation tools for DeepSeek Harness: per-call model/provider/persona/toolFilter overrides, @preset: references, and provider/model composite ids — zero patches, bundle.
DeepSeek Harness plugin: hide the raw chain of thought and show a summarized chain of thought produced by a small model (any Chat Completions-compatible API).
Eyes for text-only DeepSeek on DeepSeek Harness: image understanding via Antigravity IDE quota (default, flash/pro), OpenAI-compatible VLM endpoints, Gemini API, or local Ollama — model-invokable vision tool, wrapper adapters for deepseek/opencode-go, evidence memory, and a polished client panel.
DSH Web manager for global AGENTS.md with Markdown preview, reusable templates, version history, import rollback, and revision-conflict protection.
Reasoning-wait thinking indicator for the DeepSeek Harness web composer
Telegram remote-control surface for dsh sessions: whitelisted chats list, read, prompt, and stop dsh sessions through the host ApiProxy
DSH compatibility plugin that treats redundant non-escalating sandbox permission fields as a no-op
DSH 草稿润色:发送按钮左侧 ✨ 一键调用 LLM 润色输入框草稿,可选携带会话上下文帮助模型理解意图;走 DSH llm 渠道,会话进行中也能用
Windows Computer Use for DeepSeek Harness: window-bound screenshots, robust OCR, verified clicks, pure-OCR mode, pluggable vision models.
LLM-backed prompt optimization bundle for DeepSeek Harness
DeepSeek Harness adapter that exposes each configured vision model as a selectable DeepSeek composite in Web UI.
Visual Cordis plugin-tree composer for the DeepSeek Harness Web UI.
DSH bundle: grok-geo GEO brand audit agent skill — AI-search visibility, recommendations, citations, competitor presence and content-gap diagnosis across 17+ AI engines (ChatGPT/Perplexity/Claude/Gemini/豆包/DeepSeek/Kimi/文心一言...), shipped as a bundled skill provider. Zero-dependency.
DASH — Deepseek Agentic Service Harness. oh-my-pi style TUI on the DSH agent kernel, run in the terminal via `dsh --profile dash`. TypeScript sources in src/, compiled to dist/.