DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Run Speed — DSH Plugin for DeepSeek Harness
← Plugins
R

dsh-run-speed

Run Speed

Per-session run-speed control for DeepSeek Harness without changing the selected model or reasoning effort

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:yjc925925/dsh-run-speed#5d20aabd0e06c3c9c3b26a4b7b69792855f5e5e1
READMECompatibilityVersions

Compatibility and provenance

Run Speed is published as dsh-run-speed and currently resolves to version 0.1.3. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
github
Registry updated
10/7/2026

Versions

0.1.3stable
10/7/2026

Related plugins

Loading related plugins…

Latest
0.1.3
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
web
License
MIT
Source
github
GitHub
★ 0
Weekly downloads
0
Last push
10/7/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in

Related plugins

More verified plugins in models-usage.

Whale Widgetdsh-whale-widgetDeepSeek balance whale widget in the bottom-right corner of the DSH Web interface: balance/today’s usage/peak-off-peak pricing, customizable bubble click sequence (text/balance/today/peak-off-peak/image/random phrases and parallel weighted selection), per-line styles and fonts, floating quick editinClient Ui Model Capabilities@linxin666/dsh-client-ui-model-capabilitiesPer-model capability declarations (image input and reasoning efforts) for custom pi-ai providers, edited in place on the Models settings cards; writes the official llm-pi-ai settings namespace, no DSH source changes.Cost Meterdsh-cost-meterDeepSeek Harness session cost statistics plugin: current session cost, today’s charges, historical records, and synchronization with official pricing; supports multi-provider, multi-model price calculation (built-in pricing catalog for 170+ model IDs with automatic matching); queries and displays suCodex Subscriptiondsh-codex-subscriptionUse ChatGPT and Codex subscriptions in DeepSeek Harness with OAuth, quota, safe resets, web search, images, and Fast mode

README


description: "A per-session run-speed selector for DSH that adds parallel-execution guidance without changing the selected model or reasoning effort." kind: "package-bundle"

dsh-run-speed

This optional DSH bundle adds a Run speed menu to the composer and a matching /run-speed command. It lets you choose, per session, how aggressively the agent may fan work out to parallel background subagents while the selected provider, model, and reasoning effort stay exactly as they are.

ModeAdded prompt textParallel subagents中文
Standardnonethe model's normal strategy标准
Fastone dynamic prompt sectionup to 3, launched together in one message快速
Turboone dynamic prompt section4 through 6极速

The plugin never switches provider, model, or reasoning effort, and it never patches Harness core packages. Install or remove the bundle through the DSH plugin manager; cordis.patch.yml contributes a single plugin entry (id: run-speed).

Repository: https://github.com/yjc925925/dsh-run-speed

Usage

The composer control and the command are two views of the same state: the button drives the Host command through the remote command service, reads the authoritative mode back from it when it mounts, and adopts the mode it just applied after a switch succeeds. Both the English words and the Chinese equivalents are accepted; bare /run-speed and /run-speed status report the current mode.

/run-speed                 # -> "Run speed: standard."
/run-speed fast            # -> "Run speed set to fast. Model and reasoning effort remain unchanged."
/run-speed 极速            # same as /run-speed turbo

The composer control sits in the conversation.input.right slot (order 30) and is disabled while the session is running or removed, and while a switch is in flight.

Model Experience

Selected run-speed policy

What the model sees

Fast and Turbo contribute one dynamic system-prompt section (user:run-speed, order 425). Its text tells the parent and every child to keep the current provider, model, and reasoning effort, to batch independent parallel-safe tool calls, to keep dependent work serial rather than delegating it, and to partition file ownership so that two agents never write the same file. Standard contributes an empty section — the section itself is always registered, but its text is an empty string, so no tokens are spent.

Token effect

Fast and Turbo add a short fixed prompt and can spend substantially more tokens overall by running parallel subagents. Standard adds no model tokens.

KV Cache effect

Changing modes replaces the active system prompt on the next model request and can start a new reusable request prefix. Flipping modes back and forth therefore costs cache re-use on the following request.

Layout

PathContents
src/index.tsHost half: RUN_SPEED_GUIDANCE, parseRunSpeedMode(input), the user:run-speed prompt section, and the /run-speed command
src/types.tsRunSpeedMode union ('standard' | 'fast' | 'turbo') shared by both halves
src/client/index.tsBrowser half: dictionary registration plus the conversation.input.right slot contribution
src/client/RunSpeedControl.tsxThe composer menu component
src/client/locales.tsSimplified Chinese (key source) and English dictionaries
src/client/RunSpeedControl.module.cssStylesheet for the control
tests/run-speed.client.spec.tsVitest suite for parsing, guidance text, and per-session isolation
lib/index.jsPrebuilt Host ESM entry
lib/client.js + lib/client.js.mapPrebuilt browser bundle and its source map
lib/types/**/*.d.ts + *.d.ts.maptsc declaration output and its declaration maps
locale/{en,zh}.jsonPlugin-manager card copy

The repository ships the prebuilt lib/ artifacts, so the bundle can be installed and run without a build step. The sources are published alongside them for review and for future maintenance.

Development

This package is developed as a member of the deepseek-harness monorepo at packages/client/ui-run-speed/. Committed here are the sources, the Vitest suite, and the build configuration, because the npm tarball's files allowlist excluded all of them.

A standalone build is not wired up yet. The build and type-check configuration reaches into monorepo scaffolding that this repository does not contain: tsdown.config.ts imports ../tsdown.client.ts; tsconfig.host.json extends ../../../tsconfig.base.json with five project references; tsconfig.client.json extends ../../../tsconfig.base.client.json with nine.

The declared dependencies are not the problem. npm install resolves every @deepseek-ai/dsh-* pin from the public registry in a couple of seconds — those releases carry the next dist-tag rather than latest, which is why npm view <pkg> version suggests they are missing. What is missing here are the build tools themselves: the test script needs vitest and the bundle script needs tsdown, and neither is declared in this package.json — they are inherited from the monorepo root. In a bare clone, npm test therefore fails at the tool, not at the sources.

The supported way to rebuild is still from a deepseek-harness checkout:

# from a deepseek-harness checkout
pnpm --filter dsh-run-speed bundle
pnpm --filter dsh-run-speed test

Making this repository self-contained — declaring vitest and tsdown, and replacing the two inherited tsconfig bases with in-repo equivalents — is the natural next step, and is not done here. The committed lib/ artifacts are the build output of 0.2.0-rc.2; deliberate differences from the raw npm tarball — no build-machine paths, a shipped and rewritten client.js.map, and a corrected test script — are recorded in CHANGELOG.md.

Known Limitations and Deferred Work

  • Process-local selection — the Host keeps the selection in a WeakMap<Session, RunSpeedMode> and it resets to Standard when DSH restarts. The control queries the Host for the authoritative mode whenever it mounts, and adopts the mode it just applied after a successful switch; it does not poll the Host afterwards, so it stays in step because both sides share the same command.
  • Policy rather than a throughput guarantee — the plugin requests parallel work, but provider capacity, rate limits, task dependencies, and the model's own decomposition decision still determine wall-clock speed.
  • Status text is a wire contract — the browser half parses the Host's Run speed: <mode>. reply to learn the current mode, so that wording is part of the Host/browser interface and must change in both places at once.

English summary

dsh-run-speed adds a per-session Run speed selector to DeepSeek Harness. It chooses how aggressively the agent may fan work out to parallel background subagents — Standard (no added prompt text), Fast (up to 3), or Turbo (4–6) — while explicitly preserving the selected provider, model, and reasoning effort. The selection is reachable from the composer toolbar and from the /run-speed command, is stored in Host memory per session, and resets to Standard when DSH restarts.

License

MIT. See LICENSE and NOTICE for attribution.