by WJZ-P

Adds an input-modality selector to custom model settings in the DeepSeek Harness Web UI.

by penguin-oo

Automatic Flash/Pro routing for DeepSeek Harness subagent calls: light tasks go cheap, heavy tasks stay strong — with /delegate overrides.

by NOirBRight

Native Ollama Cloud provider and Web configuration plugin for DeepSeek Harness

by jiay98528-dev

Writes live provider model lists into DSH settings. Composer rings show 5h/7d plan windows or metered balance for the current session model. / 把线上模型列表写进设置，输入框圆环显示当前会话的 5 小时/7 天窗口或按量剩余余额。

by Jesse-njx

dsh-polyglot — the model switch for DSH: generic OpenAI-compatible ctx.llm adapter, curated free/cheap DeepSeek presets, automatic provider fallback on rate limits

by 11zld22

模型信息补全：按模型名自动补全上下文、输出上限、思考档位和图片能力

by qjf44

One-click OpenAI-compatible API (CodeBuddy/vLLM/proxies) with thinking mode, avoiding developer-role content_filter rejection.

by Eve-146T

dsh plugin for openai codex subscriptions that can pool multiple accounts.

by dylan121322

Adaptive model routing: per-request complexity classification with automatic provider routing.

by songoao25

ChatGPT Subscription - a DeepSeek Harness plugin: bind your ChatGPT account via official OAuth and chat with ChatGPT models inside DSH, using your Plus/Pro subscription quota

by GooDAnDReaDY

Per-provider API key rotation for DeepSeek Harness: key pools, automatic 429 rate-limit failover, cooldown probing & Settings UI

by wyouwd1

Manage OpenCode Zen free-tier and Go-tier models in DeepSeek Harness: live listings from opencode.ai, drift per route, four agent tools plus an OpenCode Models settings section.

by GooDAnDReaDY

Automated provider model catalog discovery and quota balance monitoring for DeepSeek Harness

LongCat-2.0 LLM adapter: 1M context, binary thinking mode, tool calling, and streaming over the OpenAI-compatible endpoint.

Adds Claude, Gemini, and a local Ollama model to DSH's native model picker, using your existing Claude Code / Antigravity CLI logins instead of a metered API key, with a working reasoning-effort selec

Add missing reasoning-effort declarations to custom pi-ai models through DSH settings, enabling the native effort picker and handling models added later.

Bring OpenCode Zen free models to DSH: 8 live-discovered providers with zero config, no API key; includes persistent quota tracker with rate-limit detection and reset countdown.

Free conversational ChatGPT Web (GPT 5.6 Luna) model provider for DeepSeek Harness with streaming Markdown.

Route OpenRouter requests through a configured provider list and quantization cap, injected as provider.only/order with allow_fallbacks, plus provider.quantizations.

ClineBot and ClinePass integration for DeepSeek Harness: dedicated settings page, live quota dashboard, in-UI key saving, curated and custom model selection, and a /cline command.

Hand a DSH web session to the locally installed Claude Code CLI: a per-session engine selector (DSH | Claude Code), Claude models and reasoning effort in the model seat, Claude permission modes in pla

Rate-limits LLM requests per provider and per model using a reservation-based token bucket, with queue or reject modes, plus gateway identity rules that rewrite user-agent and inject custom headers.

macOS Keychain credential provider that replaces the local-file provider and uses a signed, notarized universal helper.

DSH model provider for the locally authenticated AGY CLI: Gemini/Claude model discovery, independent reasoning effort, DSH-owned tools, bounded context and tool-result handling, and Windows-safe strea