Модели и провайдеры

Use a local TraeX coding agent as a DeepSeek Harness model provider over ACP.

DSH-native video understanding with configurable multimodal providers

Generic LLM gateway model provider plugin for DeepSeek Harness: mounts newapi / LiteLLM / Higress / any OpenAI-compatible gateway as provider routes, auto-discovers the model list, enriches every model with models.dev parameters, and dispatches each model

Automatically fills in reasoning-effort levels for models from unofficial (custom) providers, with data sourced from models.dev.

A GUI subagent-model selector beside the main model seat: pick a model and reasoning effort per session, applied to every in-process subagent.

xAI Grok subscription chat: SuperGrok or X Premium+ OAuth, a displayed model subset, Responses through the Grok CLI proxy, and always-on server-side web_search and x_search.

Unofficial Cursor subscription chat: Host-owned CLI session login, a displayed model catalog, and subscription usage rails. Cursor staff treat this class of private-client usage as against ToS.

ChatGPT Codex subscription chat: official OAuth, a Sol/Terra/Luna catalog with Fast rows, live usage limits, and optional search and view_image tools.

Weak-network adaptor: transparent long-backoff model-stream retries (10-min cap), local response replay cache, heartbeat auto-reconnect, and degraded-mode token economy, with a bilingual (zh/en) settings page.

Automatic provider failover on rate limits or quota exhaustion: switch between providers with configurable per-provider models, a cooldown, and a permanent last-entry fallback.

Connect a sub2api gateway to DeepSeek Harness: OpenAI-compatible multi-provider routes (OpenAI / Claude / Grok / Gemini) behind one base URL, with per-key model discovery, usage lookup, and global vision/image tools.

Один плагин DeepSeek Harness для всех провайдеров pi-ai, включая OAuth по подписке

Провайдер загрузки HTTP(S), устойчивый к SSRF, для DeepSeek Harness

Бюджеты шагов, вызовов инструментов и токенов провайдера на ход для DeepSeek Harness с безопасным отказом (fail-closed)

Провайдер OAuth OpenAI Codex и адаптер моделей для dsh-oauth и DeepSeek Harness

Доступ к вебу для DeepSeek Harness — поиск/загрузка через нескольких провайдеров в ctx.web, плюс извлечение данных из GitHub/PDF/YouTube.

WebSearchProvider на основе Bocha и устанавливаемый набор профиля для DeepSeek Harness

Обнаружение провайдеров, сопоставление, проверка работоспособности и отказоустойчивость перед выводом для DeepSeek Harness.

Провайдер поиска на основе Brave Search API для интерфейса веб-возможностей DeepSeek Harness (ctx.web). Один поиск — один HTTP-запрос, без хода модели.