DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-llm-aimux

DeepSeek Harness LLM adapter that exposes aimux providers as configurable DSH model routes.

Terminal & TUIDeveloper ToolsSkills & Workflows
0GitHub Stars0ForksUpdated2026-08-17

Install

$ dsh plugin --profile web add @arcships/dsh-llm-aimux

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-llm-aimux integrates the aimux LLM access layer with DeepSeek Harness. Users configure provider routes, credentials, model metadata, and optional relay endpoints through DSH settings and the Models page.

Key Capabilities

  • Registers configurable DSH model routes backed by aimux providers.
  • Supports streaming chat, tool calls, reasoning blocks, and separated cache token usage.
  • Resolves credentials through DSH credentials when available or provider environment variables otherwise.
  • Supports per-route provider selection, display names, endpoint overrides, and custom headers.
  • Updates configured routes without restart and merges runtime and catalogue model metadata.
  • Provides a configurable streaming chunk-idle timeout.

Useful For

  • Use DeepSeek, Groq, Moonshot, or other aimux-backed providers from DSH model routes.
  • Configure an LLM relay or gateway with a custom base URL and headers.
  • Manage provider credentials from the DSH Models page or environment variables.
  • Expose provider model metadata and context limits in DSH.

Who It Fits

  • DeepSeek Harness users configuring external LLM providers.
  • Developers operating multi-provider or gateway-based LLM setups.
  • Users who need aimux-backed models in DSH.

Documented Limitations

  • The project describes itself as a young experiment tracking a developer-preview DSH release; breaking changes are expected.
  • Image input is unsupported and fails with UNSUPPORTED because attachment references are not resolved to bytes.
  • Subscription and OAuth channels are not supported.
  • Endpoint interrogation does not support draft, unstored routes.
  • Routes cannot overlap with built-in llm-pi-ai routes; conflicting configurations require distinct route IDs.
  • aimux is configured for one request attempt; retry handling is owned by the DSH agent layer.

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 1 runtime, 7 development, 4 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
arcships/dsh-llm-aimux
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
12eea00 · 2026-09-13

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
0GitHub stars
Forks
0
Open issues
0
Last commit
2026-08-17
Last release
No release detected
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