by Jensen-Yao

Global Alt+M model command palette for DeepSeek Harness Web: fuzzy search over models and providers, favorites and recents, per-model reasoning effort, provider and model configuration, request retrie

by imMamdouhaboammar

Use ChatGPT and Codex subscriptions in DeepSeek Harness with OAuth, quota runway forecast, safe resets, web search, image generation, and Fast mode.

by kenny2077

Web search for DeepSeek Harness through Z.ai or Zhipu, with Coding Plan MCP quota and REST API billing modes, a native bilingual settings card, and support for reusing an existing ZAI_API_KEY.

by yauntyour

DSH Multimodal Input Plugin: Configure separate processing model chains for different file types (images / videos / audio / text). Before files are passed to the conversation model, they are first processed by preset models into Prompt Tokens (text) and then handed over to the conversation model. The plugin adds a dedicated Multimodal page in DSH settings.

by lim12137

Extra model-request recovery for DeepSeek Harness: retries PI_AI_ERROR failures once after a fixed 20s delay; other error codes keep the built-in dsh-llm-retry exponential backoff.

by ccccwwwxx

Time-based model routing: a settings panel defines weekday peak and off-peak windows and the provider/model each one uses, the choices are read from the harness registry (API keys and subscription log

Connect **OpenCode Zen**'s free models to **DeepSeek Harness**: discover official free-tier models in real time, toggle them on and off individually in settings, and push them to the provider with a single click. **No key required**

by Angelyeye

Tracks DeepSeek Harness LLM token usage and cost (CNY, peak/off-peak pricing) with a settings dashboard, agent tools, HTTP API and persistent storage.

by sanser9

Brings the free models of a locally installed OpenCode CLI into DSH: starts or reuses a local opencode serve, discovers the live catalog and refreshes it every five minutes, and bridges the session ev

by moon16u

A pouch of practical micro-plugins for DSH: per-turn wall-clock time injection, safe restart, session ID header badge, Tavily search provider, configurable LLM request-header routes, and an MCP server

by Sttrevens

Per-turn USD cost badge in the Web UI: session total in the header and per-turn cost in each message footer, with a hover breakdown.

by drscrewdriver

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

by huangyuheng

Real-time Token Usage Dashboard · Real-time token usage dashboard for DeepSeek Harness — live totals, filters by model/day/month/project, smooth trend chart.

by dyuan311

ChatGPT subscription OAuth for the openai-codex provider in DeepSeek Harness

by llmpolska

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.

by QGG4588

DSH automatic model failover · provider-pool failover: on rate limit/quota/timeout, auto-retry with the next untried model from the selected providers' full model pools. Runtime tool: model_failover + Web UI panel.

by a2580vb

DeepSeek Harness LLM adapter for OpenCode Go (opencode.ai/zen): /models discovery with cache, three wire protocols (OpenAI Responses, OpenAI-compatible Chat Completions, Anthropic Messages), tool calling, reasoning mapping, streaming, and the required x-opencode-session affinity header.

by EquityQ

Say goodbye to tedious manual configuration! This plugin lets you directly import MCP configurations from Claude Desktop, Cursor, VS Code, YAML, or the web. Before writing, it automatically performs a security review and risk warnings for you. Just click confirm to seamlessly integrate third-party tools into DSH, and you can manage the relevant settings from **Settings → MCP Installation**.

by quan-v

MCP server configuration UI plugin for DeepSeek Harness (made in DeepSeek Harness)

by fufuf-c

Local token usage and cost dashboard for DeepSeek Harness: four-segment token breakdown (miss/cache-hit/cache-write/output), cache savings estimate against the miss/hit price gap, per-session drill-do

by sharewiner

Manages the default DSH model, provider and model visibility, and optional OpenAI Responses web search.

by yangyongzhen

Per-session cost & usage report cards: tokens, cache hits, duration.

by xinghe-1018

Balance badge that follows the active model provider: official readings for DeepSeek, Qwen Token Plan and Aliyun BSS, plus Moonshot and OpenRouter endpoints not yet key-verified.

Analysis and local fix for dsh-antigravity plugin CallId export error in DSH Desktop Beta