openai-compatible 38

Bring ChatGPT-like image generation to DeepSeek Harness — Gemini, OpenAI, Seedream, DashScope, local ComfyUI & more.

让 DeepSeek Harness 里任何纯文本模型都能读图。识图是按需调用的 tool —— 图片不进主模型上下文，不看就不花钱；附 23 处缺陷的评测集，换模型可自测。

Display-layer translation for the DSH web app: thinking chain, task cards, and optional answer text, in 8 target languages (local Ollama / any OpenAI-compatible or Anthropic endpoint / Google / Bing, fail-open)

Free-tier model aggregation for the DeepSeek Harness (dsh): registers the freeroute provider over a pool of free-quota upstreams (OpenCode Zen / B.AI / OpenRouter / SenseNova built in, plus remote catalogs and custom gateways), transparent failover before

DeepSeek Harness 外置视觉模型插件：inspect_image 把本地图片或 http(s) 图片 URL 发给任意 OpenAI 兼容端点，视觉模型看图的文字回答直接带回对话；附 Web UI 设置栏。

Voice input for DeepSeek Harness: dictation chunked by pauses and voice messages, each with its own provider fallback chain (Deepgram, Groq, HuggingFace, local whisper.cpp, plus any OpenAI-compatible API of your own).

DeepSeek Harness companion for ClineBot / ClinePass: dynamic subscription models sync, quota exhaustion warnings, session metrics, dedicated settings page, live usage limits, and /cline slash-command.

On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model

Image generation tool for DeepSeek Harness over any OpenAI-compatible images endpoint, with an inline Web UI gallery.

DSH web search provider with four selectable protocols: any OpenAI-compatible Responses API gateway exposing the native web_search tool, DeepSeek's Anthropic-compatible Messages API with the native web_search_20250305 server tool, Zhipu's Web Search API (

DeepSeek Harness 全能插件：识别/生图/改图一体化，无需切换模型——用常规 DeepSeek 模型即可自动调用视觉与生图模型（gemini_vision / gemini_generate_image / gemini_optimize_image）。多后端：Gemini 原生 + 任意 OpenAI 兼容服务（GPT-4o、Qwen-VL、GLM-4V、Moonshot、gpt-image、DALL-E、Flux、Stable Diffusion、OpenRouter、硅基流动、各类中转

Local image / voice / music / SFX generation for DeepSeek Harness with pinned identity: the same character stays the same character across calls, degenerate output is refused rather than returned, and the GPU is untouched when idle. Hand the image half to

DeepSeek Harness 插件：一键配置任意 OpenAI 兼容 API 并自动带思考模式，同时规避 developer 角色被第三方端点拒绝（content_filter）的问题。

只填 Key 的服务商预设：50 家渠道为 DSH 一键写入官方 llm-pi-ai 路由与凭据（插件），并可写入腾讯 WorkBuddy、OpenCode（Key 走其 auth.json）与 cc-switch 的配置（CLI）；核心为纯 JS，可被更多应用的外壳复用。

LoongPort DeepSeek Harness (dsh) Cordis bundle and setup CLI

Dual-protocol DIT.ai provider and first-run onboarding for DeepSeek Harness

MNN Chat 自定义 API 服务接入 DSH：把手机端 MNN Chat（MnnLlmChat）的 OpenAI 兼容 HTTP 服务注册成 DSH 的一个 LLM provider，可在大龙虾里直接对话

DSH plugin for static OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages providers

DSH plugin: inject per-model sampling parameters (top_p, top_k, min_p, repeat_penalty/repetition_penalty, presence_penalty, frequency_penalty) into every chat-completions request sent to an OpenAI-compatible gateway (llama.cpp, SGLang, vLLM).

NewAPI (OpenAI-compatible gateway) chat-completions adapter for the DeepSeek Harness LLM seam. Provider route id 'newapi', display name 'NewAPI'. Dual-face: host half registers the LLM adapter and chat-only model discovery; browser half adds a NewAPI sett

DeepSeek Harness 生图插件：侧边栏全局画廊（Cherry Studio 式绘画页）、对话生图/编辑、可自定义 Provider 端点与代理。

Model relay station for DeepSeek Harness (模型中转站): serve any registered DSH LLM provider (e.g. @tnnevol/dsh-codebuddy) over an OpenAI-compatible /v1 API, so other projects can call those models with a standard OpenAI client.

Per-model reasoning effort declarations for GPT, Gemini and OpenAI-compatible providers in DeepSeek Harness

Token Market provider bundle for DeepSeek Harness

LLMTR AI gateway provider for the DeepSeek Harness LLM seam: 170+ chat models and Türkiye-hosted LLMs behind one OpenAI-compatible key

Review-first request-dialect preflight for custom DeepSeek Harness providers.

DSH plugin: image understanding via any OpenAI-compatible vision API, paste-to-describe, and an animated whale-buddy desktop pet with status bubbles and a floating settings panel

Repairs malformed streaming tool-call deltas from OpenAI-compatible gateways in DeepSeek Harness, before they assemble into an undispatchable call

OpenAI-compatible web search provider (Responses API + web_search tool) for DeepSeek Harness — works with Qwen Token Plan, OpenAI and other compatible gateways, with an in-GUI configuration card

Model relay station for DeepSeek Harness (模型中转站): serve any registered DSH LLM provider (e.g. @tnnevol/dsh-codebuddy) over an OpenAI-compatible /v1 API, so other projects can call those models with a standard OpenAI client.

OpenAI-compatible image generation plugin for DeepSeek Harness.

LANtern（局域网模型灯塔）：把本机 DeepSeek Harness 已注册的全部 AI 模型，以 OpenAI / Anthropic 兼容接口照亮给同一局域网。只读复用 DSH 的模型注册表，全部产物写在插件自己的 data/ 目录内。

Model relay station for DeepSeek Harness (模型中转站): serve any registered DSH LLM provider (e.g. @tnnevol/dsh-codebuddy) over an OpenAI-compatible /v1 API, so other projects can call those models with a standard OpenAI client.

Image and video generation for DeepSeek Harness: routes image models to /images/generations and video models to the async /videos API, exposing image_generate and video_generate tools plus a composer text/image/video output-mode switch.

OpenAI-compatible gateway adapter and dialect fixes for DeepSeek Harness

Token Market provider bundle for DeepSeek Harness

Scoped, reversible tool-call ID compatibility plugin for DeepSeek Harness

Harness-neutral Traditional Chinese enforcer + offline converter (skill, DSH bundle, CLI). One script axis either way + Cantonese/Japanese-only filters. Converts both ways; optional wording preference. Also: an LLM output guard, cp950/GBK console scan.