← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-paste-collapse

Collapses large text pastes in the DeepSeek Harness composer into Codex-style preview pills and expands them before sending to the model.

UI & ProductivityTerminal & TUIBrowser & Web
0GitHub Stars0ForksUpdated2026-10-23

Install

No clear install command was found in the current repository evidence.

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-paste-collapse is a DeepSeek Harness UI plugin that collapses text pastes exceeding 1,000 characters into compact Codex-style placeholders and interactive preview pills within the composer. The host side intercepts the turn in agent/pre-step and expands the placeholder back to full text before the model processes it, maintaining composer readability without modifying token consumption.

Key Capabilities

  • Collapses pastes exceeding 1,000 characters into numbered [Pasted Content N chars] placeholders
  • Renders an interactive pill above the composer displaying first-line preview and character count
  • Provides a side drawer panel showing the complete pasted text with a copy button
  • Restores the full text on the host via agent/pre-step FIFO expansion before model execution
  • Renders collapsed pills inside sent user message bubbles using the conversation.user.text.node slot

Useful For

  • Pasting large code snippets, logs, or JSON payloads into DSH without cluttering the input composer
  • Reviewing large pasted content in an accessible drawer side panel rather than scrolling through wall-of-text input
  • Maintaining readable conversation history when working with multi-thousand-character prompt inputs

Who It Fits

  • DeepSeek Harness developers working frequently with extensive code blocks or error stacks
  • Prompt engineers and power users who paste lengthy documents into the DSH chat interface

Documented Limitations

  • Does not save LLM tokens; full uncompressed text is always passed to the model
  • Pastes are stored purely in memory; host restart causes unexpanded placeholders to be sent as raw text
  • In-memory capacity is bounded (host retains newest 50 texts, client retains newest 100 texts)
  • Falls back to inserting uncollapsed raw text if the host does not respond within 10 seconds

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
matata2017/dsh-paste-collapse
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
ee0c53f · 2026-10-23

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
2026-10-23
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