DeepSeek Harness PluginManifest Valid

dsh-model-priority

Custom model and provider ordering plugin for DeepSeek Harness with drag-and-drop settings and automatic backup.

UI & ProductivityTerminal & TUIDeveloper ToolsRemote Execution

1GitHub Stars0ForksUpdated2026-10-16

Source

Install

$ dsh plugin --profile web add "<本仓目录，或 git 地址>"

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-priority is a DeepSeek Harness plugin that lets users customize the display order of LLM providers and models. It injects a drag-and-drop sorting section directly into the Models Settings panel (via the settings.models.provider-card slot) and wraps ctx.llm provider/model listing methods with stable sorting. When saving, it safely updates configuration files with automated backups.

Key Capabilities

Adds drag-and-drop model reordering inside the DSH Model Settings view
Wraps ctx.llm instance methods (listProviders, listConfigurableProviders, listModels) with stable ordering
Persists custom sorting into ~/.dsh/model-order.json and updates settings source files
Provides automatic timestamped backup and deduplication before writing to configuration files
Includes local HTTP endpoints with host and origin verification to query and manage sorting state

Useful For

Prioritizing frequently used models to appear first in the DSH model selection list
Organizing and grouping custom configured provider models via drag-and-drop in the UI
Ensuring consistent model order between the settings screen and session model pickers

Who It Fits

DeepSeek Harness web UI users configuring multiple model providers
Developers seeking customized model ordering and automated configuration backups

Documented Limitations

Requires restarting DeepSeek Harness web profile after installation for server hooks and client bundles to take effect
Drag-and-drop configuration writeback is limited to user-configured providers (e.g. llm-pi-ai family); built-in DeepSeek model lists are read-only
Does not handle intelligent request routing, failover, or token usage metrics

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.

Dependency Counts

package.json declares 0 runtime, 0 development, 0 peer, and 0 optional dependencies.

info

Dsh Bundle Declared

package.json declares DSH bundle metadata.

info

License Declared

GitHub reports the repository license as MIT.

info

Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info

Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

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

Source repository: mengge237-labs/dsh-model-priority
Registry source: GitHub · dsh-plugin topic
Registry classification: Plugin
Source checked: 11e22c2 · 2026-10-18

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.