dsh-model-reasoning
Smoothly Model Reasoning (Smoothly MR) — 思磨力提供方参数：外部 DeepSeek Harness 网页客户端插件——一个用于管理 llm-pi-ai 提供方路由参数（重试与退避、超时、传输、缓存、预算、容量）以及每个模型推理效率的设置页面
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add dsh-model-reasoning@0.2.4Model Reasoning 以 dsh-model-reasoning 发布，当前版本为 0.2.4。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
English | 简体中文
| Brand | |
|---|---|
| English brand | Smoothly |
| 中文品牌 | 思磨力 |
| English product name | Smoothly Model Reasoning — short: Smoothly MR |
| 中文产品名 | 思磨力提供方参数 |
Smoothly Model Reasoning (Smoothly MR / 思磨力提供方参数) is an external DeepSeek Harness web
client plugin: a Settings page that manages
the provider-route parameters the built-in Models page deliberately does not
expose — retry & backoff policy, timeouts, transport, caching, thinking budgets,
capacities, request image budgets — plus per-model thinking levels (reasoning
efforts) for third-party (pi-ai) providers. It writes the exact
llm-pi-ai.providers.<route>.* fields the adapter reads, so changes take effect
with no other configuration.
Why an external plugin: adding fields to the built-in ui-settings-models
package would be overwritten by the next official release. This package ships as
an installable bundle that never touches repository source, so official
updates cannot clobber it.
A new Settings section, 「思磨力提供方参数 / Smoothly MR」, placed after the
built-in Models page. Pick any provider route — every entry in the llm-pi-ai
providers dict is editable here, catalog routes included — and manage it in
five parameter groups:
models list, edit the
SELECTED model's own declaration: input modalities (text/image, so a
text-only model stays text-only beside its vision siblings), context and
output caps (contextWindow, maxTokens), and thinking levels
(reasoningEfforts: inherit / non-reasoning / a level set over off minimal low medium high xhigh max) with custom wire spelling per level. The picker
fuses search into the dropdown itself — open it and type to narrow long model
lists by name / id (display-only; stored order and write path untouched).
Apply to all models copies only
the CHECKED dimensions from the editor to every model on the route, plus the
route default thinking level (providers.<route>.reasoning) that unset
models inherit.retryPolicy.mode (normal bounded transient retries vs
always unbounded retries), maxRetries, retryableCodes (the five stable
preset codes plus custom entries), and the shared exponential backoff
(initialDelayMs, maxDelayMs, jitterRatio). Unset values fall back to the
adapter defaults (5 retries, 500 ms initial, 10 s ceiling, 10% jitter).timeoutMs, websocketConnectTimeoutMs,
streamIdleTimeoutMs (default 300 000 ms), and transport
(auto/sse/websocket/websocket-cached).cacheRetention
(none/short/long) and thinkingBudgets token budgets per level
(minimal/low/medium/high).defaultContextWindow,
defaultMaxTokens, defaultInput modalities (text/image) — these three
are FALLBACKS read only by models that declare nothing of their own (set the
real values per model in the Per model tab) — plus the per-request image
payload caps (maxRequestImageBytes,
requestImagePixelBudget, requestImageMaxBytes).Every group's panel opens with a scope badge: 「按模型 / Per model」 writes into the selected model's own declaration, and a dimension you leave unset inherits the route fallback or catalog value; the four other groups are 「整条 路由 / Whole route」 — those fields exist ONLY at route level in the llm-pi-ai schema, so one shared value is the whole truth (the badge's hover tooltip says so; no duplicate text sits beside it).
Every field shows the effective adapter default as its placeholder while unset;
clearing a field removes the override instead of writing an echo of the default.
Local validation mirrors the host's own resolution rules, so most mistakes are
caught before the write; anything the host still refuses surfaces verbatim from
settings.mutate. The write path uses revision fencing, so a concurrent change
is refused rather than silently overwritten. An Apply to all models action
copies the current model's reasoning declaration to every model on the route at
once.
Each selected reasoning level has a wire-spelling field (defaults to the
level name). Change it to remap what that level sends — e.g. max → ultra for a
model that calls its top level Ultra, or high → turbo. off can either send
nothing (default) or a custom value of its own.
⚠️ DSH does not support inventing new level names. The pi-ai schema pins
reasoningEffortskeys to the seven canonical levels and resolution only reads those keys, so a bareultra:key is rejected at write time. "Ultra" is expressed by remapping an existing level's wire spelling (max: ultra).
With no third-party provider configured the page shows a friendly placeholder
pointing at Settings → Models → Add a custom provider. Selecting a catalog
route (no explicit models list) explains that its MODELS stay read-only here —
catalog reasoning levels remain selectable in the composer — while the route's
parameter groups above stay fully editable. Loading / unavailable states are
hinted while the settings document loads.
Prerequisites: a DeepSeek Harness install with the dsh CLI, plus pnpm (the dsh plugin command runs pnpm under the hood). This is an installable bundle — it is loaded by dsh, not imported as a library.
Compatibility: since v0.2.2 the page writes through the settings Remote namespace dsh 0.1.2 introduced (ctx.remote.settings); dsh builds older than 0.1.2 (the connection.api RPC face) are not supported.
The package is published to npm as dsh-model-reasoning:
dsh plugin --profile web add dsh-model-reasoning
This installs the prebuilt bundle and appends it to the web profile. Then restart dsh web and open Settings → 思磨力提供方参数 / Smoothly MR.
dsh plugin --profile web add github:karoc/dsh-model-reasoning#<sha>
A git install runs the package's prepare script to build the bundle. pnpm ≥ 10 requires allowlisting that build once — copy the exact package key pnpm prints into the profile's pnpm-workspace.yaml under allowBuilds, then re-run add (see docs/user/develop/basic/publish.md in the DSH repo).
Bump to the newest release with pnpm update (or re-add to pick up a newer git ref):
dsh plugin --profile web update dsh-model-reasoning
# or, if the dependency spec is pinned: dsh plugin --profile web add dsh-model-reasoning
Then restart dsh web so the new client bundle loads.
dsh plugin --profile web remove dsh-model-reasoning
This removes both the dependency and its bundle layer from the web profile. Restart dsh web for the section to disappear.
cordis.patch.yml # bundle layer: mounts the row that the client-modules
# service discovers (dsh.client manifest)
package.json # dsh.bundle (patch) + dsh.client (web) + exports["./client"]
tsdown.config.ts # self-contained build: node half + module-table client bundle
src/index.ts # host apply (no-op)
src/client/index.ts # client apply: settingsScope.bind(llm-pi-ai) + register settings.section
src/client/ProviderParamsSection.tsx # the settings page (route → group tabs → editors)
src/client/params.ts # managed-field registry: domains, defaults, host-mirroring
# validators, draft model, minimal-op diff engine
src/client/styles.ts # design-token styles (--dsw-alias-*) + injection
src/client/locales.ts # en/zh copy
tests/params.test.ts # unit tests for the pure registry logic
npm install
npm run bundle # emits lib/index.js + lib/client.js
npm test # unit tests for params.ts (node:test runs TypeScript directly)
pnpm release:check # release gate: docs/changelog/tag/tree/build/registry must all pass
npm publish # runs the gate (prepack/prepublishOnly), then postpublish verifies the live release
The bundle leaves the platform packages (react, @deepseek-ai/cordis,
@deepseek-ai/dsh-client-*) external — they resolve at runtime from the loader's
module table; everything else is inlined.
models list expose per-MODEL editors here
(the installed catalog is not reachable from the client); every route's
route-level parameter groups are always editable. Catalog-only per-model
customization via modelOverrides is future work.apiKeyEnv), displayName, baseURL, protocol
(api), and the models list structure stay on the built-in Models page;
this plugin does not duplicate them.max: ultra) edit settings.yaml for that model.provider, maxRetries,
maxRetryDelayMs at route level) are never written by this plugin.ui-settings-general SettingsRoot.tsx navIcon(id) maps known ids and
falls back to a gear for every other id — including this section's
provider-params. When DSH exposes a per-section icon, use
IconThinkOutline16 from dsh-client-ui-primitives for this section.See CONTRIBUTING.md (development + release checklist) and CHANGELOG.md for version history.