dsh-thinking-effort-autoswitcher
Manifest validReplaces the composer model picker with a model + thinking-effort picker and an Auto level; Auto scores each turn by how far the conversation has drifted from the main objective and by repeated failur
Thinking effort autoswitcher
English | 简体中文

A DSH plugin that turns the composer model selector into a compact
model + thinking-effort picker, adds an Auto level, and shows the effort each
turn actually used.
Version 0.1.0. Scope and limitations are listed below.
What it does
- Model + effort picker — replaces the
conversation.input.modelslot. The menu lists models grouped by provider, then the current model's real effort levels (off/low/high/max, whatever the provider exposes) and anAutoentry. - Arrow cycling —
←decreases,→increases. The ladder is[real levels…, Auto]:→from the highest level lands onAuto,←fromAutoreturns to the highest level. There is no wrap-around. - Mouse-aware — the arrow shortcut is ignored while the pointer is inside the composer card, so caret movement is never hijacked. Anywhere else on the page it works.
- Slide animation — the effort word in the button slides horizontally (old word out, new word in) inside a fixed-width slot, so the button never jumps; the word uses a flowing cool-tone gradient with a light glow.
- Per-turn real effort — while
Autois on, each completed turn shows the effort that turn actually sent (read fromrequest/headerevents, not from the current picker state). Turns without a recorded header showdefault. - Escape hatch — if the replacement picker misbehaves, keep the plugin but
set
localStorage['thinking-effort:no-replace'] = '1'and reload: a compact effort chip inconversation.input.lefttakes over.
Install
Link the plugin into the profile's dependencies and list it in
dsh.profile.bundles; the bundle's own cordis.patch.yml inserts the loader
row, so the profile patch needs no extra entry.
// ~/.dsh/profiles/<profile>/package.json
{
"dependencies": { "dsh-thinking-effort-autoswitcher": "link:C:/path/to/thinking-effort-plugin" },
"dsh": { "profile": { "bundles": ["...", "dsh-thinking-effort-autoswitcher"] } }
}
Then fully restart DSH (the Host half only loads at startup).
Auto scoring (Host half)
The Host exposes two same-origin JSON routes:
| Route | Purpose |
|---|---|
POST /thinking-effort/evaluate | score the current turn and return a target level; apply: true applies it |
POST /thinking-effort/turns | return the effort each turn actually sent (from request/header) |
How the score is built
-
failure (0–5, deterministic) — only the latest turn. A tool call failing ≥2 times with the same name and arguments is one repeat group worth 2; a
turn/endwithreason.kind === 'error'adds 2; capped at 5. -
importance (0–10, judged) — one small model call comparing the latest user message against an anchor. The anchor is the active goal objective when a goal is running, otherwise the first user message. Closer to the anchor and larger blast radius score higher; peripheral exploration scores lower. The judge uses the model's lowest level (preferring
off); if the reply cannot be parsed the score falls back to 5 andimportanceRawis returned for debugging. -
mapping:
total = wI * importance + wA * failure maximum = wI * 10 + wA * 5 interval = maximum / levelCount index = floor(total / interval) // clamped to 0 … levelCount-1Weights live in the plugin's patch row and only their ratio matters:
- insert: - id: thinking-effort name: 'dsh-thinking-effort-autoswitcher' config: weights: { importance: 1, failure: 1 }
When the Client calls it
- switching to
Autoevaluates immediately (cold start lands on the middle level first); - each completed turn evaluates once from the turn-tail tag, debounced 600 ms, at most once per turn;
- a 404/405 marks the route unavailable and stops further calls; the menu shows “auto scoring not connected” instead of silently retrying.
Per-turn history
/thinking-effort/turns groups request/header events between turn/start
and turn/end:
{"ok":true,"turns":[{"turn":1,"effort":"low","seq":18,"endSeq":100}]}
The Client caches the answer per session, matches each turn-tail entry by its
closing seq (then by the last endSeq <= seq, then by turn number), and
shows that recorded effort; only when the route is unavailable does it fall
back to the live selection.
Activation notes
The Host half loads only when:
- the plugin is linked into the profile's
node_modules; - a loader row exists for it (the bundle patch already inserts one);
index.jsexportsexport const inject = ['webServer'].
Point 3 bit this plugin once: without a declared dependency, apply can run
before the HTTP carrier exists, ctx.get('webServer') is undefined, the code
silently returns, and the plugin still reports fiberPhase: active while every
request falls through to the SPA fallback (405 with allow: GET, HEAD).
Self-check:
curl.exe -s -X POST "http://127.0.0.1:<port>/thinking-effort/evaluate" `
-H "content-type: application/json" -H "sec-fetch-site: same-origin" `
-d '{"sessionId":"probe"}'
A structured JSON answer (for example {"ok":false,"error":"session-not-live"})
means the route is live; 405 means it is not.
Known limitations
- The per-turn tag prefers the recorded
request/headereffort; it falls back to the current selection only when the route is unavailable. Turns with no recorded header (for example a cancelled turn) showdefault. conversation.input.model.labelcontributions from other plugins are not forwarded.- The menu has no search box and no roving keyboard focus.
selectModelmay be refused while an agent is running; the response carriesapplied: falsewithapplyError, and the UI keeps the manual choice.
License
MIT — see LICENSE.
Comments
Loading…
Similar plugins
Codex-style reasoning-effort slider for the DeepSeek Harness composer
★ 0
MIT
JavaScript
dsh plugin --profile web add dsh-thinking-sliderby imkingjh999
DSH plugin: auto reasoning_effort (low/high/max) per turn via MiniMax complexity scorer + token ledger + per-reply metadata label
★ 0
MIT
TypeScript
Aug 26, 2026
dsh plugin --profile web add dsh-adaptive-effortby zhangzhenwen1
Auto-adjust model reasoning effort per task (off/low/high/max): task classification, [effort=...] markers, in-turn error escalation, DeepSeek peak-pricing-period capping with countdown notices, and ma
★ 0
↓ 61/wk
MIT
JavaScript
Aug 30, 2026
dsh plugin --profile web add dsh-task-effortby Rczlin
Gives pi-ai routed models a reasoning-effort ladder without manual settings: falls back declared to models.dev to a 7-tier default, and replaces the composer model chip with a Codex-style vertical pic
★ 0
JavaScript
Oct 8, 2026
dsh plugin --profile web add @dsh-better-reasoning/pluginby Mu-scorpio
Configures provider and model reasoning-effort mappings for DeepSeek Harness, with a grouped model picker and composer slider.
★ 9
↓ 633/wk
MIT
TypeScript
Sep 15, 2026
dsh plugin --profile web add dsh-reasoning-effortby Gorkaseto
A plugin for DeepSeek Harness (DSH) that enables effort choice in custom providers and replaces the standard "Effort" menu item with an intuitive, sticky effort slider directly inside the composer model menu.
★ 0
Apache-2.0
JavaScript
Oct 21, 2026
dsh plugin --profile web add dsh-effort-picker