Plugins

Auto Mode for DSH: a flash-model router that auto-picks the best agent preset (standard/code/minimal/cordis) for each new session and executes immediately, no confirmation.

Per-project LLM token usage and RMB cost in the DSH Web sidebar, split by input (cache miss), cache hit, and output with model price auto-pricing.

Alternative WorkflowEngine provider for DSH 0.1.0-rc.7 that runs model-written orchestration in fresh QuickJS/WASM runtimes with a JSON-only host bridge and bounded memory, execution time, and child-agent fan-out.

Smart provider routing: composer-button one-click enable/disable, any channel error (including 4xx) auto-falls-back to the next channel, chain names shown in the model selector without exposing internal channels/models, multi-chain management with settings UI.

vision_analyze tool: analyze a local image or URL with an OpenAI-compatible vision model.

Codex-style token usage dashboard: five stat cards, GitHub-style activity heatmap (daily/weekly views), insights & model ranking; persisted snapshot with incremental sync, survives session deletion.

System parameter adjustment UI: grouped settings page for timeouts, parallelism, LLM retry policy, model params, web search, permissions and presets; safe profile-config editing with line-level YAML matching and post-write validation.

Splits the composer model selector into a searchable, favorite-marking dropdown and a reasoning-effort slider, with Ctrl+P / Ctrl+T quick-switch shortcuts.

Model-agnostic visual-inspection pipeline for text-only agents: page-by-page HTML screenshots plus a ready-made vision-subagent briefing contract (gewu_prep), then source-code truth verification of every finding (gewu_locate); validated on mimo-v2.5 & qwen3.7-plus.

DeepSeek Harness 侧边栏用量仪表盘插件：跨会话 token / 模型 / 活动统计、按会话明细与可选时间尺度的用量趋势图。 Usage dashboard plugin for DeepSeek Harness web: cross-session token, model, and activity stats with a per-session table and a windowed trend chart.

Claude Science-style AIDD research workbench for DeepSeek Harness — ReAct research loop, versioned artifacts with provenance, and 17 skills for virtual screening, molecular generation, ADMET prediction, DTI modeling and model reproduction.

强度表是 DSH Web 开源插件：设置页按模型统计 token 用量（环形图、热力图、趋势），数据仅来自本地日志。一条命令安装，重启即用。 dsh-strength-meter: a DSH plugin. Settings shows per-model token usage (donut, heatmap, trend), local logs. One command, restart.

MCP client hub (stdio / Streamable HTTP / SSE) with a web console for DeepSeek Harness — manage MCP servers, agent skills, slash commands, project & global memory, and prompt sections.

Auto-reject unanswered permission requests with a model-visible timeout notice

Vision for text-only dsh models: paste an image and a configured multimodal model transcribes it to text automatically — transparent twin routing, an agent-callable read-image tool, no built-in keys or relay.

WeChat Mini Program automated testing for DeepSeek Harness (dsh): selector-addressed actions, build-freshness gates, geometry-first assertions that work on text-only models, and screenshot image blocks on vision routes. 微信小程序自动化测试 dsh 插件：选择器寻址、构建新鲜度门、面向纯文

Surgical rewriting of the model-visible conversation history of a DSH session (surface replacement); edit reply and reasoning chain separately. 上下文手术刀：强制改写会话的模型可见历史，回复与思考链分开编辑。

Dynamic multimodal-to-text projection and cross-model vision bridge for DeepSeek Harness (dsh), allowing seamless hot-switching between vision models (Gemini/Claude) and text-only models (DeepSeek).

Anthropic Model Context Protocol (MCP) client bridge plugin for DeepSeek Harness (dsh).

Configurable model-request retry limit for DeepSeek Harness (Settings → General).

Delegate work to external coding agents (Claude Code / Codex CLI / Grok CLI) from DeepSeek Harness: a model-facing harness_call tool, @claude/@codex/@grok mentions, live progress cards with a thinking/tool timeline, and a details side panel.

DeepSeek Harness (DSH) plugin — inject context when user input or model output hits configured keywords, with toggleable/configurable rules and model-editable memory.

A DeepL-style translation surface for dsh: replaces the shell's root frame with a two-pane translator driven by a tool-less agent preset, keeping the shipped settings panel (models, providers, plugins) intact

FAL image generation for DeepSeek Harness: a generate_image tool backed by the FAL queue API (default model fal-ai/flux-2/klein/9b). Images render directly in the conversation, are saved to the workspace, and all settings are editable from the Web GUI.