by nobu121

Attaches a stable per-conversation x-opencode-session header to OpenCode / OpenCode Go provider requests, fixing 400 MissingSessionID errors and keeping session affinity and prompt-cache routing intac

by WNJXYK

Use your OpenAI subscription with DeepSeek Harness to access GPT models, image generation, and web search.

by Coco-king

DeepSeek Harness plugin: When the model request URL contains opencode.ai, attach the `x-opencode-session` request header, whose value reuses the session id from the request itself (fixed within the same conversation, unchanged across restarts/network interruptions, and different for different conversations).

by orrinzeng

Log directly into your Cursor account within DeepSeek Harness and use your Cursor subscription — no API Key required, and no dependency on Cursor IDE or Cursor CLI. In DeepSeek Harness, directly log into your Cursor account and

by TiantianFlow

Private DSH One Gateway — loopback, identity-first ingress for DeepSeek Harness

by loyalchiiina

WorkBuddy Switching Hub for DSH: LLM provider + multi-account ledger (credits/check-in/expiry/cooldown/one-click switch). All-in-one, self-contained, privacy-masked.

by anye-99

DeepSeek Harness plugin: Huawei Cloud CodeArts browser login and credential management, and registers CodeBuddy / WorkBuddy / LobsterAI / Qoder / TRAE / Cline / Loomy / Raccoon / MiniMax / TeleAgent / ZCode / Step Code / Antigravity as LLM providers, including multi-account pool, silent renewal, quota, and daily check-in.

by sanshanya

Per-model capability declaration for DeepSeek Harness: reasoning-effort levels (wire spellings) + request modalities (vision) for OpenAI-compatible providers. Settings section, zero runtime harness de

by dat-lequoc

Kiro provider for DeepSeek Harness with Builder ID login, live model discovery, and reasoning effort controls

by ymh0000123

DeepSeek Harness plugin: make a custom llm-pi-ai provider masquerade as Claude Code / Codex clients (spoofed client identity request headers). A DeepSeek Harness plugin: masquerade a custom llm-pi-ai provider as Claude Code / Codex clients (spoofed client ide

by lujianjun19

GitHub Copilot LLM adapter: OAuth device-flow sign-in, live model discovery from the Copilot API, vision support for image-capable models (gpt-4.1, gpt-4o), and two wire protocols (Chat Completions an

by functy23

Optimized WorkBuddy2API Gateway + DSH Native Panel: UA, header family, and device fingerprint aligned with the official WorkBuddy Desktop 5.9.2, with the kernel independently updatable.

by licyer

# DSH Web Model Quota and Usage Monitoring Plugin

by zeng6125-rgb

DSH Plugin: LLM Auto-Retry Settings Card — configurable retry count, backoff, and jitter, plus 25 checkable error codes (you can also enter your own). When a response is truncated by the output token limit, it automatically continues generating, and the prompt is fully editable. Changes take effect in real time.

by ckanner

Use your ChatGPT subscription as a model provider in DeepSeek Harness (dsh). Sign in with ChatGPT over OAuth — no API key — and the account's own models appear in the model picker.

by taikaikaikai-pixel

CodeBuddy & Trae provider bundle for DeepSeek Harness (dsh): subscription-quota LLM access via loopback tap bridges — 18+ models, OAuth/API-key, usage metering. Unofficial, BYOC.

by TonyWu2333

DeepSeek Harness (dsh) plugin for Inception Mercury: renders the diffusion denoising stream live inside the answer bubble

by linkbag

Role-based AI swarms for DeepSeek Harness: an architect plans, parallel builders execute, reviewers gate quality, and an integrator ships. Per-role model pinning with fallback chains, review loops, ev

by better-er

DSH Web Plugin: Built on DeepSeek's official BPE tokenization table, it renders a token status bar in real time below the composer, displaying streaming TPS, output tokens, and first-token latency, while comparing the estimated versus actual deviation from the previous step. A self-contained pure plugin that does not modify any DSH source code.

by Lzh3070

Composer cost chip: prices the current session DeepSeek API spend message-by-message with the official pricing table (incl. the 2026-08-17 peak/off-peak policy); hover for the breakdown, today (DSH) t

by Lbunc

Add local large model capabilities for DSH: One-click start/stop for local llama.cpp large models (dual-slot × dual-modal × dual-preset) on the Settings → Plugins page — in-card configuration, install with a single command, automatic registration, ready to use right after installation.

by lincong1987

dsh plugin: Flexible model switching for sub-agents and plan execution. Choose more suitable models for sub-agent and plan execution.

by functy23

The Functy branch of corrinehu/dsh-workbuddy-connect: Dashboard, multi-account rotation, and quota display — connecting the WorkBuddy model to DeepSeek Harness.

by Jonah-Wu23

DeepSeek Harness plugin: connect logged-in Antigravity CLI (agy) as chat and subagent model provider