플러그인

Maintains reusable named subagent profiles for DeepSeek Harness and runs them with per-profile model, reasoning effort, and agent-preset settings.

Install and call external Agent CLIs (Codex, Claude Code) from DSH without touching the system install. Each CLI gets its own Provider, model, reasoning effort and permission preset, callable directly or as a native subagent.

Memory consolidation tuning for dsh-mneme (autoDream enabled, schema-max output budget, deepseek-chat route) plus the llm-deepseek reasoning-effort fix, an MCP bridge to the auditable seed-society agent runtime, and six yogacara seed skills.

Command Code LLM provider plugin adapted for DSH-Desktop 0.7.1: registers a commandcode route, with a live model catalog, reasoning-effort support, and real-time plan usage display.

Explicit model routing for Main, Subagents, web_search, and image generation, plus a catalog-driven Composer and Plan Review picker with Model, Effort, Context, Fast, and Thinking variants.

Replaces the model button with a Claude Desktop-style model and reasoning-effort switcher, with per-model effort memory, theme-aware styling, smooth slider feel, rounded track, hover highlight, and pixel-dot animation.

Global Alt+M model command palette for DeepSeek Harness Web: fuzzy search over models and providers, favorites and recents, per-model reasoning effort, provider and model configuration, request retries, capacity presets, and optional OpenRouter image/video generation tools.

Planner/executor delegation with named roles: a strong planner steers, disposable executor sub-agents (per-role routes and prompts) implement. Default role plus per-delegation override, a global reasoning-effort knob in the composer chip, and a settings page for role management.

Adds Claude, Gemini, and a local Ollama model to DSH's native model picker, using your existing Claude Code / Antigravity CLI logins instead of a metered API key, with a working reasoning-effort selector for Claude.

Provider-folded model selector for the DSH Web composer with catalog-driven reasoning effort choices.

Adds a model-aware reasoning effort slider with native and animated modes, light and dark palettes, and per-model colors.

Reasoning-effort tier manager for custom API models plus cross-session preference memory: inline low/medium/high/max toggles inside Settings → Models, with atomic settings writes.

Mobile-viewport fixes for the dsh web GUI: overlay drawer sidebar with swipe gestures, icon-only composer with a mode · model · effort status line, centered popovers, and horizontal-overflow/scrollbar centering fixes.

Ranked subagent delegation: role-based model routing with failover, per-route reasoning effort, model-transparent labels, fork delegation, and a visual route editor.

DeepSeek Harness 插件：把「推理等级」(reasoning effort) 档位名翻译成中文，并为接入的自定义第三方模型注入推理等级显示（官方 DSH 默认不注入），所选档位写入出站请求体。

DSH Web GUI 模型能力配置：在「设置 → 模型」的模型目录编辑器内，为每个已配置的模型直接设置是否支持图像与思考等级（reasoning efforts），写入 llm-pi-ai 设置命名空间。

Choose reasoning effort for additional models in DeepSeek Harness, with Off and five standard levels.

Auto-fills reasoning-effort levels, context windows, output limits and image modality for models from unofficial (custom) providers, with data from models.dev.

Official-style composer model trigger with a floating reasoning-effort slider popup.

Model switching and reasoning-effort control for DeepSeek Harness: set_model and list_models agent tools let the agent autonomously change its provider, model or thinking depth (reasoning effort) mid-task with a mandatory reason, a provider whitelist and a context-window token-pressure guard, the active model is injected into the runtime context, and Plan Mode auto-transition switches to a configured planning model on entering plan mode and restores the previous execution model on exit.

Replaces the chat input model picker with a provider-grouped, collapsible list: groups models by provider, folds vision-bridge mirror providers back into their upstream, and carries the reasoning-effort options each model declares in settings. Tested on DSH Desktop only; the DSH web build is untested.

Model capability editor: edit each model reasoning-effort levels and image-input (multimodal) declarations inline in the official model page, written back to settings.yaml as a whole group, with a floating entry as fallback when the anchor breaks.

Declare any number of LLM providers, each with its own endpoint, credential and per-model parameters (reasoning-effort vocabulary, image input, retry policy), across the OpenAI Chat, OpenAI Responses, Anthropic Messages and Google Gemini wire formats, configured from a settings page.