DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-llama-responses

DeepSeek Harness LLM adapter and delegation skill bundle to route subagents to a local llama.cpp server via OpenAI Responses protocol.

Developer ToolsSkills & Workflows
1GitHub Stars0ForksUpdated2026-08-24

Install

$ dsh plugin --profile web add git+https://github.com/SnowRikka/dsh-llama-responses.git

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-llama-responses is an installable DeepSeek Harness bundle providing an LLM adapter for local llama.cpp server instances via the OpenAI Responses (/v1/responses) protocol. It enables running subagents on locally hosted models (such as Qwen 3.8 27B) while retaining the primary DeepSeek cloud API for the main agent, cutting API token expenses while maintaining subagent context isolation.

Key Capabilities

  • Registers the llama-responses LLM adapter in DeepSeek Harness via Cordis
  • Translates GenerateOptions and SSE streams to and from OpenAI Responses format
  • Routes subagent tasks (spawn/fork) to local llama-server endpoints
  • Maintains strict parent-child subagent context isolation without conversation inheritance
  • Provides bundled subagent delegation guidelines and skill configurations

Useful For

  • Offloading repetitive or background subagent tasks to local hardware to reduce API costs
  • Testing multi-agent delegations against local llama.cpp deployments
  • Isolating subagent execution contexts from primary parent conversations

Who It Fits

  • DeepSeek Harness developers running local llama.cpp or vLLM compatible instances
  • Users running multi-agent workflows looking to minimize API costs

Documented Limitations

  • Requires a running local llama-server listening on HTTP (e.g. 127.0.0.1:8080)
  • Subagent and skill tools must be explicitly unmasked/enabled in web profiles via cordis patches
  • Requires initial model selection warm-up before subagent routing takes effect

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, 3 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
SnowRikka/dsh-llama-responses
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin Bundle
Source checked
9645dea · 2026-09-15

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
1GitHub stars
Forks
0
Open issues
0
Last commit
2026-08-24
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