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.

Sensenova Provider — DSH Plugin for DeepSeek Harness
← Plugins
S

@alaxrpg/dsh-sensenova-provider

Sensenova Provider

Unofficial DeepSeek Harness LLM provider plugin for SenseNova (OpenAI-compatible). Registers the 'sensenova' provider route with multi-account API-key rotation, a Models-page card, and a live model catalog.

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

npx -y @deepseek-ai/dsh plugin --profile web add github:alaxrpg/dsh-sensenova-provider#d42171fecbffbf43415f6984d24af5dd40455a95
READMECompatibilityVersions

Compatibility and provenance

Sensenova Provider is published as @alaxrpg/dsh-sensenova-provider and currently resolves to version 0.1.0-alpha.7. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
github
Registry updated
9/8/2026

Versions

0.1.0-alpha.7prerelease
9/8/2026
Show 5 more versionsCollapse versions
0.1.0-alpha.6prerelease
9/4/2026
0.1.0-alpha.5prerelease
9/4/2026
0.1.0-alpha.4prerelease
9/4/2026
0.1.0-alpha.3prerelease
9/3/2026
0.1.0-alpha.2prerelease
9/3/2026

Related plugins

Loading related plugins…

Latest
0.1.0-alpha.7
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
9/20/2026
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 editinUsage Stats@ychris12138/dsh-usage-statsToken usage heatmap, provider balances, and subscription quotas for the dsh web GUICodex Connectdsh-codex-connectChatGPT OAuth and Codex models for DeepSeek Harness.Ui Usage Billing@kenz1117/dsh-ui-usage-billingUsage billing dashboard for DeepSeek Harness: sidebar cost metrics plus a full dashboard modal, priced from a current multi-provider catalog with real usage aggregated from session logs.

README

@alaxrpg/dsh-sensenova-provider

Unofficial DeepSeek Harness (DSH) LLM provider plugin for SenseNova (OpenAI-compatible API). Registers the sensenova provider route with a Models-page card, a live model catalog, and multi-account API-key rotation on a single shared base URL.

Reference implementation: @mars-sea/dsh-commandcode-provider (MIT). This plugin keeps only the multi-account connection feature; it drops login flows, usage dashboards, plan windows, and command-line tools.

Features

  • Registers provider route sensenova (display name SenseNova).
  • Live model catalog via GET {apiBase}/v1/models.
  • OpenAI-compatible streaming: POST {apiBase}/v1/chat/completions (SSE).
  • Multiple API keys (accounts) on one shared base URL, with automatic rotation:
    • 429 Too Many Requests → cooldown the key (honors Retry-After; 60 s fallback when absent).
    • 401 Unauthorized → disable the key until the stored credential changes.
    • All keys exhausted → surfaces RATE_LIMIT / INVALID_CREDENTIAL with the earliest reset time.
  • Web settings page (Models-page card + dedicated settings section).

Requirements

  • DSH host >=0.1.2-alpha.3 (alpha line).
  • Node.js >=22.

Compatibility note: the runtime import surface is a stable subset of @deepseek-ai/dsh-llm present since 0.1.1-rc.2 (LlmAdapter, LlmError, ReasoningEffortId, assertUsableApiKey, attributionHeaders, errorChain, resolveRetryPolicy); the drifting ToolCallId symbol is defined locally (src/brand.ts, identity-backed). Runtime loading on 0.1.1-rc.2 hosts works; the declared peer floor >=0.1.2-alpha.3 is the type-level support start (the ToolCallId type first appears there).

Install

dsh plugin --profile <name> add dsh-sensenova-provider

Or install from a local path:

dsh plugin --profile <name> add ./dsh-sensenova-provider

Then configure SenseNova in the Models page: the default credential environment variable is SENSENOVA_API_KEY, and the default base URL is https://token.sensenova.cn/v1.

Configuration

The plugin installs a llm-sensenova settings section with these fields:

FieldTypeDefaultMeaning
apiBasestringhttps://token.sensenova.cn/v1Shared base URL for all accounts.
apiKeyEnvcredential-refSENSENOVA_API_KEYDefault account credential reference.
accounts[]array[]Extra accounts: { id, label, apiKeyEnv }.
activeAccountstring""Preferred account id; empty means auto / first usable.

API keys are stored through the DSH credentials service; they are never logged and never sent to the model.

Development

pnpm install
pnpm run typecheck
pnpm run build    # tsdown → lib/
pnpm test         # node --import tsx --test tests/**/*.test.ts

License

MIT