Qwen Token Plan CN Responses provider for DeepSeek Harness via the OpenAI Responses API, with Qwen server-side tools, DSH local function tools, text/reasoning/tool-call multi-turn history, persisted i

Configures provider and model reasoning-effort mappings for DeepSeek Harness, with a grouped model picker and composer slider.

Early-stage plugin connecting DeepSeek Harness to a separately deployed, self-hosted OwnDsh server for team identity, model access control, quotas, and usage auditing.

Tencent CodeBuddy model provider for DeepSeek Harness with browser OAuth sign-in and Web UI quota display; install from npm with `dsh plugin --profile web add @tnnevol/dsh-codebuddy`.

DIT.ai provider bundle for DeepSeek Harness: installs 29 OpenAI Chat Completions models and 10 Anthropic Messages models from one DIT_API_KEY, with protocol-specific thinking configuration.

Declare whether a configured third-party model accepts image (multimodal) input; writes the modality into the owning provider settings and verifies it through runtime model resolution.

Connect a sub2api gateway to DeepSeek Harness: OpenAI-compatible multi-provider routes (OpenAI / Claude / Grok / Gemini) behind one base URL, with per-key model discovery, usage lookup, and global vis

Ranks OpenRouter providers for the current DSH model by quantization, speed, cache-heavy price, context, and uptime, with one-click switching to help reduce token costs.

Models+ settings page for the DSH web UI: per-model reasoning-effort tables, input modalities and compat flags saved through the official settings pipeline, with models.dev metadata prefill and API ke

Model Health panel in Settings: lists every model configured in settings.yaml and batch-tests availability and latency for each.

Single-model disable gate: hides denied models from DSH catalogs, blocks direct dispatch with an in-protocol error chunk, and exposes a settings UI for the denylist.

by ringoage

The visual, manual subagent-model picker for DeepSeek Harness — predictable per-session routing with global coverage of every in-process subagent path, complementary to auto-routing plugins.

Governs multi-model access, monthly credits, manual/quality/credit/auto routing, failure rerouting, and usage auditing for DSH.

Control panel for local LLM inference servers in the DSH web view: service registry with health checks and stop controls, named parameter profiles for llama.cpp, SGLang and vLLM with pre-save KV/VRAM

Model pricing for the DSH settings page: per-1M-token prices from models.dev with the harness catalog overlaid, capability tags, cross-provider comparison, and a community promotion feed.

Adaptive model discovery, evaluation, tiering, and subagent routing for DeepSeek Harness.

LLM provider adapter that routes model calls through any ACP (Agent Client Protocol) server — Claude Code, Codex, Gemini CLI, Devin and more — with a registry browser, per-server settings UI, lazy aut

Role-based LLM retry & fallback strategies.

Model switching, model capability configuration, fixed compaction models, subagent routing, and input history enhancement.

Adds OpenAI Codex (ChatGPT) as a selectable DSH provider via the local Codex App Server.

One-click/auto sync provider model lists against /v1/models endpoint.

OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", thinking driven by the model config, Qwen-style response split, and vision-mod

Volcengine Ark Coding Plan LLM provider for DeepSeek Harness: provider-scoped PDF and image input, with Responses API streaming support.

Tiered model routing for DeepSeek Harness: think/build model tiers, vision delegation (the vision model only describes images; the working model acts), image generation, and a high-impact guard.