← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-term-glossary

In-place term dictionary and explanation popup for DeepSeek Harness conversations with token usage display.

Terminal & TUIDeveloper ToolsSecurity & Policy
2GitHub Stars0ForksUpdated2026-10-18

Install

$ dsh plugin --profile <profile 名称> add dsh-term-glossary

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-term-glossary is a DeepSeek Harness UI plugin that allows users to select unfamiliar terms inside conversations and request instant sidecar explanations. It shows the core meaning, purpose, and usage in an overlay popup alongside precise token consumption, using contextual session clues without polluting the active conversation history.

Key Capabilities

  • Context-aware inline term selection trigger with on-demand search popup
  • Bypassed sidecar LLM call that avoids consuming active chat rounds or session turns
  • Automatic domain detection using sanitized recent user message history and conversation title
  • Token usage reporting (input, output, cache, and total) and active model identification
  • Multi-route model fallback with pre-token abort and fail-safe sanitization

Useful For

  • Quickly clarifying technical, medical, legal, or financial jargon without leaving the current chat stream
  • Checking term definitions while preserving the current agent prompt context and message history
  • Inspecting prompt and generation token costs for auxiliary model queries

Who It Fits

  • DeepSeek Harness users reading complex domain-specific responses
  • Developers and researchers needing quick definitions without disrupting active chat context
  • Users monitoring model token consumption closely

Documented Limitations

  • Requires DeepSeek Harness with a web UI environment (Desktop client or `dsh web`)
  • Hard-depends on `webServer` and `llm` services to activate
  • Only triggers on non-editable text selections; input boxes and text areas are ignored
  • Follow-up inquiries within the pop-up are disabled in v0.3+; each trigger is single-turn
  • Context harvesting adds roughly 200–700 tokens to prompt inputs per request, with a total output cap of 2400 tokens

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, 0 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
ashz555/dsh-term-glossary
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
226a6d4 · 2026-10-18

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
2GitHub stars
Forks
0
Open issues
0
Last commit
2026-10-18
Last release
2026-10-18
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