DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-plugin-pixluna

A DeepSeek Harness Cordis plugin that exposes PixLuna image retrieval as model-callable tools.

Terminal & TUIDeveloper Tools

Install

$ dsh plugin --profile web add dsh-plugin-pixluna

Repository Intelligence

AI-assisted, source-grounded explanation based on the public repository snapshot. It does not replace compatibility or security verification.

source-grounded
dsh-plugin-pixluna ports PixLuna image-source capabilities to DeepSeek Harness. It registers tools for image retrieval, Pixiv lookup, and source discovery, with profile-layer installation and configurable image-source, credential, proxy, and R18 settings.

Key Capabilities

  • Registers the model-callable tools `pixluna_get`, `pixluna_get_pixiv`, and `pixluna_sources`.
  • Retrieves images by number, source, tag, and R18-related options.
  • Looks up Pixiv images by PID, with page and all-pages options.
  • Provides configurable default sources, AI-work exclusion, request delay, proxy settings, and request concurrency.
  • Stores general configuration in DSH settings and Pixiv/source credentials in DSH credentials.
  • Returns remote image URLs rather than embedding image binary data in tool output.

Useful For

  • Let a DSH model retrieve images from configured PixLuna-supported sources.
  • Fetch Pixiv content by a known PID.
  • Discover available image sources through a model-callable tool.
  • Configure image retrieval behavior per DSH profile.

Who It Fits

  • DeepSeek Harness users who want model-callable image retrieval tools.
  • PixLuna users migrating image-source functionality into DSH.
  • DSH profile administrators configuring sources and credentials.

Documented Limitations

  • The plugin requires the DSH tools service before activation.
  • Pixiv Discovery, Following, and PID retrieval require Pixiv credentials.
  • Some booru sources may require or optionally accept source-specific credentials.
  • R18 requests require plugin-level `isR18=true` as well as tool parameter or probability selection.
  • Tool output contains remote image URLs; image flipping, obfuscation, and compression are not included.
  • DSH patch configuration replaces the complete `config` item rather than deeply merging it.

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 2 runtime, 12 development, 5 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
Package Manifest Available

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

info
License Declared

GitHub reports the repository license as MPL-2.0.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Traceable source and registry metadata for this entry, kept separate from runtime verification.

Source repository
PixLunaLab/dsh-plugin-pixluna
Registry source
Public GitHub repository
Source snapshot
d8184dca0b85
Artifact type
plugin
AI enrichment
gpt-5.6-terra · 2026-08-14
Prompt version
dsh-plugin-enrichment-v3

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
1
Forks
0
Open issues
0
Last commit
2026-08-14
Last release