← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-annotation

Selection-annotation plugin for DSH Web enabling passage-level notes, batch submission, and structured numbered replies.

UI & ProductivityDeveloper ToolsBrowser & WebRemote Execution
129GitHub Stars12ForksUpdated2026-09-15

Install

$ dsh plugin --profile web add @changfenhuang/dsh-annotation

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-annotation is a client-side bundle plugin for DSH Web that allows users to select text in assistant replies or workspace file previews, attach inline annotations, and submit them alongside prompt questions. The plugin automatically hides raw annotation blocks from user message bubbles before rendering and formats model responses with numbered, interactive hover chips corresponding to each annotated passage.

Key Capabilities

  • Select-to-annotate text in assistant responses and workspace sidebar file previews
  • Cross-turn and cross-message accumulation of numbered annotation items
  • Interactive input chip showing active annotation count with hover preview and removal controls
  • Zero-flicker user bubble DOM cleanup hiding raw annotation payloads while retaining interactive chips
  • Structured prompt injection prompting models to respond in indexed Annotation N format
  • Interactive hoverable chips rendered over model reply annotations showing original passages and notes
  • Bilingual support (English and Simplified Chinese) adapting to DSH locale settings

Useful For

  • Targeted code review and feedback on assistant-generated code blocks or workspace files
  • Multi-point critique and detailed inquiry across long assistant responses in a single turn
  • Referencing specific document passages during deep reasoning and research workflows

Who It Fits

  • Developers and researchers conducting detailed text or code review inside DSH Web
  • Users who need structured, point-by-point follow-up conversations with AI models

Documented Limitations

  • Sidebar annotations do not cover PDFs, images, or HTML rendered within iframes
  • Designed primarily for DSH Web interface profiles with specific DSH core compatibility (0.1.2-rc.1+)

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, 1 development, 1 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
omdsh-dev/dsh-annotation
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
ab59484 · 2026-09-29

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
129GitHub stars
Forks
12
Open issues
14
Last commit
2026-09-15
Last release
2026-09-11
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