dsh-reasoning-effort-slider
Manifest valid★ 1Reasoning effort slider for DeepSeek Harness — a client (web) bundle that injects a per-session slider into the conversation input, shown when the selected model declares reasoning effort levels. Works with any provider that has reasoning efforts (Bailian, DeepSeek official, OpenAI o-series, etc.)
dsh-reasoning-effort-slider
English | 中文
A DeepSeek Harness client (web) bundle that injects a reasoning-effort slider (Codex GPT-6 style) into the conversation input dock, shown when the selected model declares reasoning effort levels.
- Per-session: sliding only changes the current session's effort (calls
modelDirectories.directoryFor(session).select({provider,model,reasoningEffort})); other sessions are unaffected. - Levels ordered along the harness seven-step off/minimal/low/medium/high/xhigh/max; only the levels the selected model supports are shown.
- Models with one or zero levels (e.g. always-thinking kimi-k3) hide the slider.
- Zero build tooling:
lib/client.jsis written directly inwindow.__ModuleLoader__.load({id, factory})form usingreact/jsx-runtimejsx, for easy static audit.
Keeping the effort across model switches
DSH's own model picker only carries reasoningEffort over when you re-pick the same model; switching models falls back to the target model's defaultEffort, which is undefined when the route configures no reasoning. That undefined is not "the default level": under the qwen dialect it is equivalent to enable_thinking: false, so thinking is silently turned off (verified by capturing the real request body with a mock fetch).
This plugin therefore does two things:
-
Remembers per model: the last level you explicitly picked for each model (
provider/model→ level). -
Carries it over and writes it back on a model switch, clamping to the target model's ladder:
- exact match → keep it;
- otherwise the nearest level at or below (previous
max, target tops out atxhigh→ usexhigh); - nothing lower → the target's lowest level.
Since the slider never shows
off, this rule cannot silently demote "thinking" to "not thinking".
If you have never picked a level (fresh state), the plugin writes nothing and shows a grey "默认" instead, honestly reflecting "unset".
Install
dsh plugin --profile web add dsh-reasoning-effort-slider
Relation to the Bailian plugin
General-purpose (any model declaring reasoningEfforts); can also be an optional dependency of dsh-bailian-models.
License
MIT
Versions
| Latest version | Published | Size |
|---|---|---|
| 1.3.0 | — | — |
| 1.3.1 | — | — |
Comments
Loading…
From the same category
by deepseek-ai
DeepSeek Harness: Everything is a Plugin.
★ 235.9k
MIT
TypeScript
Sep 24, 2026
by nexu-io
🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards,
★ 98.1k
Apache-2.0
TypeScript
Sep 25, 2026
by tt-a1i
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
★ 71.6k
↓ 3.5k/wk
MIT
JavaScript
Sep 25, 2026
dsh plugin --profile agent add @tt-a1i/archify-dshby Tencent
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
★ 30k
↓ 838/wk
NOASSERTION
Go
Sep 25, 2026
dsh plugin --profile web add @wxg-prc-cpg/dsh-weknoraby awesome-dsh-plugin
A curated list of plugins for DeepSeek Harness (dsh) · DeepSeek Harness 插件精选列表
★ 16.9k
CC0-1.0
Python
Sep 25, 2026
by zhu1090093659
DeepSeek Harness (DSH) Web Plugin Aggregation Ecosystem · Everything is a plugin, distributed via the Creative Workshop
★ 8k
Apache-2.0
TypeScript
Sep 25, 2026
dsh plugin --profile web add dsh-web