DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-lcx-codex

DeepSeek Harness plugin managing the GPT Responses lifecycle with Native V2 compaction, replay, and hosted web search capabilities.

VisionTerminal & TUIDeveloper ToolsBrowser & WebSecurity & PolicySkills & Workflows
0GitHub Stars0ForksUpdated2026-09-10

Install

$ dsh plugin --profile web add [email protected]

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-lcx-codex is a DeepSeek Harness plugin that acts as a wire owner for GPT Responses sessions across ordinary turns, tool executions, Native V2 compaction, replay, session resume, and GPT model switching. It integrates GPT-5.6 prompt caching options, native history compaction checkpoints, and hosted/alpha web search tools without overriding DSH's native agent, session, and tool management.

Key Capabilities

  • Unified GPT Responses request and SSE wire ownership throughout conversation turns
  • Native V2 history compaction and replay with state persistence in checkpoints
  • GPT-5.6 implicit prompt caching with TTL configuration for stable topologies
  • Integration of GPT Hosted Search into DSH's native web search provider
  • Capability-probed Alpha stateful web actions (search, open, click, screenshot)
  • Isolated Pi 0.84.3 runtime dependency without host package overrides

Useful For

  • Optimizing token usage and prompt caching on long-running GPT sessions
  • Performing native V2 compaction and replay during context-heavy workflows
  • Routing web search through GPT Hosted Search and stateful browser actions on Sub2API or NewAPI endpoints
  • Seamlessly migrating or resuming GPT sessions across restarts and compatible route models

Who It Fits

  • DeepSeek Harness users leveraging GPT endpoints via Sub2API, NewAPI, or direct OpenAI routes
  • Developers needing granular control over prompt caching, context compaction, and SSE transport

Documented Limitations

  • Requires disabling LCX before switching to non-GPT models like Claude or Gemini
  • Dynamic tool additions from newly activated skills can reset the prompt cache epoch
  • Content-level prompt cache breakpoints are not supported on current routes
  • Alpha search capabilities fail-closed if capability probes do not pass
  • Credentialed ALPHA-004 runtime is explicitly not covered

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
kk3ya03-star/dsh-lcx-codex
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
b87a0bd · 2026-09-14

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
2
Last commit
2026-09-10
Last release
2026-09-10
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