Plugins

Vision structurée local-first pour agents texte seul : les images partent vers un VLM local compatible OpenAI et reviennent en preuves JSON (résumé, OCR littéral, régions de mise en page, entités/relations, couleurs, incertitude explicite), avec repli anti-hallucination et pont facultatif de collage/envoi ; coût cloud nul, les images ne quittent jamais la machine.

Route les images du chat vers un modèle de vision fixe compatible OpenAI, renvoie des observations factuelles au modèle principal sélectionné et réutilise les observations par session à travers les rejeux, la compaction et les redémarrages.

Découvre automatiquement les listes de modèles, les prix et les capacités auprès des hôtes d'API compatibles OpenAI, les normalise et émet des configurations de modèles prêtes à l'emploi pour dsh.

Génération d'images compatible OpenAI dans la discussion DSH Desktop : générer en ligne, modifier des images de référence ou enchaîner les modifications de résultats précédents directement (image-to-image) sans re-téléverser, avec nettoyage du stockage.

Badge flottant de solde d'API pour DeepSeek Harness : solde en direct pour DeepSeek, Moonshot, OpenAI et des points de terminaison personnalisés ; déplaçable, redimensionnable, aspect verre dépoli, la couleur du texte s'adaptant au contenu en dessous.

Plugin DeepSeek Harness : bascule du mode réflexion par requête (enable_thinking) pour les modèles de la famille Qwen3 sur des endpoints compatibles OpenAI.

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.

ModelTester — model detection & attribution panel for the DeepSeek Harness web chat. Ranks vendor families (DeepSeek / Anthropic / OpenAI / Google / Qwen / GLM / Kimi / MiniMax / MiMo / LongCat / InternLM / Step / Yi / Llama / Mistral / Nemotron / Grok /

Free web search for DeepSeek Harness: 19 engines (Bing/DuckDuckGo/AnySearch/SearXNG/Exa/Tavily/Keenable/Firecrawl/Parallel keyless; Perplexity/SerpBase/DeepSeek/You.com/Baidu/Kimi/Aliyun/Doubao with key) + OpenAI model built-in web search + adjustable pri

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.

DeepSeek Harness (dsh) plugin that connects Sber GigaChat models: a built-in local OAuth proxy (client-credentials -> OpenAI-compatible endpoint, upstream serialization, legacy tool-calling translation) plus automatic provider-route bootstrap, so GigaChat

Brings the Codex (ChatGPT Plus/Pro) subscription already signed in on this machine into DSH. It (1) shows the 5-hour and weekly windows with their reset times and the remaining reset credits in a sidebar panel, with one-click reset that consumes a credit; (2) registers the subscription route in llm-pi-ai (openai-codex) when the quota is read, so the Codex models appear in the model picker; (3) refreshes the OAuth access token before expiry and writes it back atomically, so no key has to be replaced by hand; and (4) adds a codex tool that delegates a task to the local Codex agent. No API key has to be entered.

DeepSeek Harness 插件：AI 聚合网关可视化控制台——集成 Google Antigravity 与 OpenAI Codex 反代、多账号轮换池、5h/周额度看板与故障转移。

Wire-level LLM inspector: captures the raw HTTP request and response bodies of model provider calls and attributes each capture to the session that caused it through the llm/stream waterfall. The request pane renders the body as a collapsible tree with per-node sizes — one measured request was 98.6% a single 973-entry array — and the response pane reassembles the OpenAI-style SSE chunk stream into reasoning, content, tool calls and usage. Shown in a Conversation View tab and a loopback viewer page.

Sign in with a ChatGPT account and view Codex subscription usage directly in DSH Web's model settings, with browser or device-code OAuth.

Extra LLM provider routes for DeepSeek Harness: OpenCode Go with per-session x-opencode-session routing, and OpenAI Codex over ChatGPT-subscription OAuth.

Manual model probe for DeepSeek Harness: a session-view tab where you pick provider, API type, model and route, then send one real raw HTTP request over openai-completions, openai-responses or anthropic-messages — streaming or not — and read latency, TTFT, HTTP status, token usage and a three-layer diagnosis chain (API request / model response / strict check) on one screen, with errors in plain language.

Registers the Xunfei Loomy cloud channel as an OpenAI-compatible supplier in dsh-router, adding model listing and streaming chat completions.

Expose every model already configured in your local DeepSeek Harness to the LAN over OpenAI- and Anthropic-compatible endpoints, with API keys, per-key rate limits, a circuit breaker, model filters and usage reports.

Declare any number of LLM providers, each with its own endpoint, credential and per-model parameters (reasoning-effort vocabulary, image input, retry policy), across the OpenAI Chat, OpenAI Responses, Anthropic Messages and Google Gemini wire formats, configured from a settings page.

Anchored Standard preset with GPT Patch mode: task-aware first-request anchors using the bundled OpenAI Codex apply_patch instead of edit/write. Built for GPT/Codex models.

Official OpenAI account model connector for DeepSeek Harness

Floating translucent DeepSeek whale elf on the DSH page that opens a draggable, minimizable temporary chat window using the session model or a custom OpenAI-compatible endpoint, with real-time streaming.

Reads AI replies aloud as they stream, with voiced waiting phrases while the model thinks. Edge TTS built in, any OpenAI-compatible cloud engine supported.