DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-annotation

Inline selection annotations and batch comments for DeepSeek Harness assistant replies.

Developer ToolsBrowser & WebSecurity & PolicySkills & Workflows
4GitHub Stars0ForksUpdated2026-09-20

Install

$ dsh plugin --profile web add ./dsh-annotation.tgz

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 DeepSeek Harness Web plugin that introduces ChatGPT-style inline selection annotations. Users can highlight specific text in completed assistant responses, attach localized review comments, batch them together, and send them seamlessly through the official composer with structured prompt handling and UI reference chips.

Key Capabilities

  • Text selection toolbar for creating inline numbered annotations or highlight-only markers on completed assistant replies
  • Composer integration that batches multiple comments, optional task text, and image attachments into a single user message
  • Structured prompt protocol requiring the LLM to reply item by item with correlated floating annotation chips
  • Intelligent slash command passthrough allowing commands like /model or /goal without dropping pending drafts
  • Local draft persistence in browser storage with restore, JSON export, and clear controls
  • IME-safe inline editor with auto-save and focus handover back to the official composer

Useful For

  • Conducting detailed code reviews or document revisions without manually quoting snippets
  • Batching multiple critique points on a long LLM output into a single focused turn
  • Marking specific confusing sentences in complex explanations for clarification

Who It Fits

  • Developers performing code review with AI assistance
  • Technical writers and researchers reviewing lengthy AI outputs
  • DeepSeek Harness Web users needing structured, multi-point feedback workflows

Documented Limitations

  • Annotations are restricted to text within a single assistant message; cross-message selections are rejected
  • Unsent drafts are persisted in local browser storage only and do not sync across devices
  • Requires model compliance with acknowledgement tags for status tracking; unstructured model outputs revert to plain text labels
  • Unsent image attachments cannot be restored upon page refresh

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.

No automated security signals have been published yet.

Source & Registry Notes

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

Source repository
ruisenbai/dsh-annotation
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
925e169 · 2026-09-21

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
4GitHub stars
Forks
0
Open issues
3
Last commit
2026-09-20
Last release
2026-09-20
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