← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-continue-on-limit

Automatically sends a continue prompt in DeepSeek Harness when local models hit output token caps.

UI & Productivity
2GitHub Stars0ForksUpdated2026-10-17

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-continue-on-limit is an invisible DeepSeek Harness Web GUI plugin designed for local models with conservative output-token limits. When a response is truncated at the end of a session due to max-tokens, the host session projection detects the event and automatically prompts the model to continue without requiring manual user intervention.

Key Capabilities

  • Monitors session events via a host-side session projection (continueMaxTokens) for max-tokens turn endings
  • Automatically dispatches configured continue text (default '继续') via prompt queue
  • Safeguards against infinite loops with a maximum consecutive continuation limit (default 3)
  • Prevents duplicate submissions using minimum interval throttling (default 1500ms)
  • Executes invisibly without occupying UI space or interrupting ongoing user actions

Useful For

  • Running local or smaller LLMs in DeepSeek Harness that frequently truncate long code or text outputs
  • Automating uninterrupted multi-part text generation without manually clicking continue
  • Hands-free long-form writing or large codebase generation workflows

Who It Fits

  • DeepSeek Harness users running local quantized models with strict max-token cutoffs
  • Developers generating lengthy code snippets or scripts needing seamless flow
  • Power users looking to eliminate repetitive manual continuation prompts

Documented Limitations

  • Only active for the currently open/staged session
  • Only triggers when the truncation is at the very tail of the conversation
  • Client configuration is fetched once at page load, requiring restart/refresh when changed
  • Does not distinguish if a user manually sends identical continuation text, potentially depleting consecutive counts early

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 Not Declared

GitHub did not report an SPDX license for this repository snapshot.

low
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
qwert702/dsh-continue-on-limit
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
ebd748e · 2026-10-17

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
2026-10-17
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