Plugins

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.

Pixel-art reasoning-effort slider for DSH Web with continuous 0–100 dragging, 16ms throttled writes, snap-to-level commits, and a WebGL ember fire that ignites as the slider moves.

Per-step thinking-effort pilot for DeepSeek Harness: simple tool rounds stay cheap, failures and heavy work lift one declared step, and agents can change their own depth through a set_effort tool without switching models.

Per-turn reasoning-effort routing that keeps the current provider/model: judges each user message (retry or correction, explicit intent, length, code blocks, errors, task scope) and sets reasoningEffort to a level the model actually declares, so Magpie and other OpenAI-compatible models work too. Ships a composer chip with an auto/manual switch and per-session decision history.

Reasoning-effort slider that replaces the composer model seat: one rail over the levels the current model declares (off/low/high/max on DeepSeek), with a 241-frame portrait that evolves frame by frame as you drag and a per-model choice that survives restarts. Uninstall restores the shipped picker.

Replaces the composer's reasoning-effort dropdown with a card that shows one illustration per level (off / low / high / max); the four levels keep their original meanings, and swapping an illustration only means replacing a file in assets/.

Desktop pet companion for DSH with live task HUD, token and cost stats, balance and peak-hour alerts, reasoning-effort control, current and history conversation search, and session management.

Deep-sea tidal-blue theme for the DeepSeek Harness Web client with a single accent color and matte (non-glass) surfaces in light and dark modes. Same-token UI additions: a single-line dock HUD reading real session projections (context usage vs. window, TPS, cache-hit rate, elapsed time), per-turn subagent delegation cards showing token usage and an optional cost estimate from OpenRouter public prices, sidebar pagination with pinned sections and type-to-filter, and model / reasoning-effort / permission controls under the composer. Each addition can be toggled in the plugin settings.

Glowing reasoning-effort slider for the DeepSeek Harness composer

Remembers the reasoning effort you explicitly chose for each provider and model and restores it when you switch back, without replacing DSH's own model picker.

A simplified version of the Plan/Act feature in the RooCode and Cline VS Code extensions, binding one provider, model and reasoning effort to plan mode and another to act mode, with per-workspace overrides.

Composer UI for DeepSeek Harness that does two things. The reasoning-effort row in the model menu becomes a continuous slider drawn on the row itself, with the rungs read live from the model adapter so any ladder length works; each rung paints its own ember plume into a canvas behind the knob. Separately, the permission trigger renders in the theme error colour whenever full access is the active preset, including its row in the permission menu.

Minimal theme for dsh that removes shadows, glass blur, and brand tinting while tightening radii, plus UI extras: sidebar archive tabs with type-to-filter, model and reasoning-effort controls under the composer, per-turn subagent topology cards, colored cache-hit and context meters, and per-turn duration.

Takes over the model button in the DSH composer and opens its own two-level panel (provider list, then model list with search) built around a continuous draggable reasoning-effort slider: the fill runs blue to violet, higher levels add nebula and dust particles, and every level has its own color. Drag moves one level at a time, and picking a model keeps the panel open and repositions the slider to that model's middle level.

Adds a delete-session action that permanently removes session logs, workspace entries and archives.

Pick the model your subagents run on — with a reasoning-effort ceiling and an output-token cap — enforced in code on every child DSH starts, whichever tool starts it.

Shows DeepSeek API balance and per-turn conversation cost directly in the session UI.

Connects Trae CN desktop app models to DeepSeek Harness with no OAuth flow: reuses the desktop sign-in, exposes 17 models (including deepseek-v4.1-flash) with consumption-rate badges and reasoning-effort mapping.

UI polish layer for the DSH web client: frosted-glass menu surfaces, a draggable reasoning-effort slider that replaces the level radio list, and model-menu navigation that reaches the model list in one click and closes on a single Esc.

Reasoning-effort gear presets for third-party models: 16 vendor/model presets with per-mode custom wire values, written into dsh-llm-pi-ai with pre-write validation and per-rule rejection; per-model switching between OpenAI Chat Completions, OpenAI Responses and Anthropic Messages with automatic route regrouping; plus a composer Optimize button and a settings section that rewrite the input text with a model you pick.

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.

Add missing reasoning-effort declarations to custom pi-ai models through DSH settings, enabling the native effort picker and handling models added later.

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.