DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-model-palette

Global provider-aware model command palette and model management panel for DeepSeek Harness Web.

UI & ProductivityDeveloper ToolsBrowser & WebSecurity & Policy
1GitHub Stars1ForksUpdated2026-09-19

Install

$ dsh plugin --profile web add github:Jensen-Yao/dsh-model-palette#v0.11.0

Plugin Overview & Capabilities

AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.

source-grounded
dsh-model-palette replaces the native DeepSeek Harness model selector with a global Alt+M command palette. It provides unified fuzzy search across models and providers, favorites, recent history, live provider/model configuration, connection testing, protocol splitting (Responses vs Chat Completions), transient request retries, local loopback relays, and optional OpenRouter media generation tools.

Key Capabilities

  • Global Alt+M document-level command palette with fuzzy search across model and provider IDs/names
  • Provider filter rail with live model counts, favorites, and recents ranking
  • Universal reasoning effort selector and model capability declarations
  • In-UI provider and model configuration with live API key validation and connection testing
  • Protocol classification and splitting between openai-responses and openai-completions routes
  • Transient request retry rules configurable per provider and model
  • Built-in loopback relay for network-constrained gateways (such as B.AI)
  • Bundled and remotely refreshable model capacity presets
  • Optional OpenRouter media generation tools for images and asynchronous video tasks

Useful For

  • Quickly switching models across multi-provider setups in DeepSeek Harness Web
  • Configuring, validating, and testing LLM provider endpoints and keys directly from the Web UI
  • Managing protocol incompatibilities between Responses and Chat Completions routes
  • Automating retry policies on unstable upstream endpoints or rate-limited gateways
  • Generating images and async videos using OpenRouter media models within the DSH workspace

Who It Fits

  • DeepSeek Harness Web users managing multiple LLM providers and models
  • Developers needing granular control over endpoint protocols, retries, and reasoning parameters
  • Users operating in restricted network environments requiring loopback relays

Documented Limitations

  • Requires DeepSeek Harness @deepseek-ai/dsh >= 0.1.2-alpha.3 and Node.js >= 22.19
  • Credential reveal is strictly limited to localhost / 127.0.0.1 connections
  • Live protocol diagnostic probes and key validations send minimal real API requests that may incur charges
  • Media generation features require explicit OpenRouter API configuration and patch activation

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

No automated security signals have been published yet.

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
Jensen-Yao/dsh-model-palette
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
4e7e14c · 2026-09-19

This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.

Repository Activity

GitHub stars
1GitHub stars
Forks
1
Open issues
0
Last commit
2026-09-19
Last release
2026-09-19
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app