DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-vision-bridge

DSH profile bundle that bridges image attachments to configured vision tools for text-only models.

VisionUI & ProductivityTerminal & TUISecurity & PolicySkills & WorkflowsRemote Execution
0GitHub Stars0ForksUpdated2026-08-16

Install

$ dsh plugin --profile web add ./dsh-vision-bridge

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-vision-bridge lets selected text-only model sessions accept image attachments by saving images to the workspace, instructing the agent to call an available vision tool, and stripping image blocks before model serialization.

Key Capabilities

  • Patches model modality resolution for configured bridged models.
  • Materializes attached images under the session workspace.
  • Adds a pre-step instruction directing the agent to use a fuzzy-selected vision tool.
  • Registers a system-prompt rule requiring analysis through the configured vision tool.
  • Strips image blocks, including nested tool-result images, before text-only adapter serialization.
  • Provides persistent settings for enablement, vision tool, custom prompt, model patterns, and excluded presets.
  • Supports documented Linux/WSL and native Windows image-writing paths.

Useful For

  • Allow DeepSeek and similar text-only model sessions to work with image attachments through a vision-tools skill.
  • Configure vision bridging only for matching provider/model patterns.
  • Keep minimal or other excluded agent presets on the original non-bridged behavior.

Who It Fits

  • DeepSeek Harness users running text-only models with image-analysis workflows.
  • DSH profile administrators configuring vision-tool-based attachment handling.

Documented Limitations

  • A vision-tools skill or another plugin providing a vision tool must be loaded; otherwise the bridge provides a self-heal instruction or notice.
  • The default minimal preset is excluded because it lacks the skill tool.
  • Bridged models do not receive image blocks; analysis depends on the configured vision tool.
  • The admission patch is process-wide, so excluded sessions receive the original reason as text rather than the native error banner.
  • Global LLM patches, pre-step listener, and system rule are shared while the plugin is mounted.

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, 11 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
ShiraGawaAnri/dsh-vision-bridge
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin Bundle
Source checked
65717f9 · 2026-08-16

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
2026-08-16
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