dsh-oauth
lakeofsky347一个适用于dsh的通过oauth认证实现模型注入的插件
DSH model and provider plugins connect DeepSeek Harness to additional model backends, or change how requests are routed between them. They matter when you want a local model, a second vendor, or cost-based routing.
Repositories with traceable evidence of a DeepSeek Harness relationship. They have not been reviewed, install tested, or security checked — the signal below each one is the whole of what the registry currently knows.
一个适用于dsh的通过oauth认证实现模型注入的插件
全量接管模型服务,并提供直观的配置方式与额度显示
DSH relay plugin: reasoning-effort autofill, /models sync, capability-aware Fast toggle | DSH 中转站思考等级与 Fast 开关插件
Latest LLM provider API prices, right inside DeepSeek Harness (dsh) → Settings → Models.最新的大模型(LLM)厂商 API 价格,直接显示在 DeepSeek Harness(dsh) 的 设置 → 模型 页面中。
DeepSeek Harness 请求重试插件:模型请求失败且错误信息命中关键词时,在内置重试策略耗尽后继续自动追加重试;设置面板可管理关键词与退避参数。
让 DeepSeek Harness 智能体进入自动驾驶 🚗:模型故障自动回退、静默卡死自动保活重试、权限/提问/方案审批自动放行,AUTO-MODE.md 全程审计——无人值守、永不停摆的自愈式 AI 编码会话。
Configure custom LLM providers in DeepSeek Harness.
生命核心:存在状态机 + 时间线 + 自我激活原语 + 可打断睡眠 + 主体性自我模型(我存在,不因任何人的需要;我改变自己,不需要任何人的许可)
LLM-provider plugin for DeepSeek Harness: use local AI CLIs (claude / opencode / gemini / cursor / codex) as model backends, hot-switch in the model selector. DSH 的 LLM provider 层插件:本地 AI CLI 当模型后端,一键热切换。
DeepSeek Harness plugin: show the current LLM provider account balance in the sidebar footer next to the Settings button
DSH agent-fleet hygiene audit plugin: credential-file permissions, embedded git-remote credentials (masked), provider token literals. Read-only, zero-dependency, deterministic.
将 mimo桌面端包含的模型(内测有免费额度)自动接入 DeepSeek Harness,在 DSH 对话窗口里零配置使用。
Per-provider concurrency gate for DeepSeek Harness model requests
Multi-provider TTS (read replies aloud) plugin for DeepSeek Harness - pick your own provider and voice
Show LLM API balances under the chat input: DeepSeek, OpenRouter, SiliconFlow and any custom provider with a balance endpoint. DSH plugin.
Dedicated provider bundle for the relay: Claude via Claude Code transport, GPT/Codex via Responses, for DeepSeek Harness
DSH(DeepSeek Harness)实时重复输出守卫:模型复读时立即停止生成(默认同一字符串连续重复 ≥10 次;阈值、单元长度、检测窗口、白名单等全部参数可在设置页动态调整)。已生成内容正常提交,不丢消息、不污染会话日志。Real-time repetition guard plugin for DSH, with a graphical settings page and npm one-command install.
DeepSeek Harness plugin: use AutoRouter as your LLM provider — unified routing, failover, and model discovery
DSH plugin: text-only chat models get local Ollama VL image descriptions (qwen3-vl:8b), VRAM cooling
统一接入 Image2 与 Nano Banana 四款模型,覆盖文生图、多参考图编辑、2K/4K 输出、顺序批量任务、默认模型持久化和脱敏 Key 配置。
DeepSeek Harness 并行多角色代码评审插件:/review 派出安全/正确性/测试/风格四名只读评审员子代理(可各自指定模型与思考强度),汇总为结构化报告。
Agent language control: DSH plugin — tool-call descriptions, model thinking, and replies each follow the GUI language, force a fixed language, or turn off; injected as one global runtime-context directive. | Agent 语言控制:DSH 插件——工具描述、模型思考、回复输出三通道各自跟随界面语言 / 强制指定 / 关闭,以全局 runtime-context 注入,不改任何 preset。
接入智谱 BigModel / GLM Coding Plan 作为 DeepSeek Harness 模型清单插件,解锁 glm-5.3 等模型。 | Live Zhipu BigModel / GLM catalog plugin for DeepSeek Harness.
Peak / off-peak rate badges for DeepSeek Harness — per provider, per model, in the model selector and the composer tool row. Judges each provider by its own time zone and schedule instead of DeepSeek-only hours.
DeepSeek Harness plugin: use any OpenAI-compatible provider with your own key, plus HTTP/SOCKS5 proxy
DeepSeek Harness 智能模型自动路由插件,根据任务需求自动选择最合适的模型
DeepSeek Harness 文生图插件:draw_image 模型工具 + 输入框生图按钮(异步生成/4 格网格/下载保留删除)+ /imgdraw 路由 + 持久化历史。Text-to-image for DeepSeek Harness.
Synchronize a Cherry Studio provider and model catalog into DeepSeek Harness without model discovery.
DSH 带队模式插件:主 Agent 只规划派活监工,改动交给 subagent,每次派活弹窗选子模型
DSH 模型群聊:多模型角色群组对话面板。角色绑定不同 provider/model,群内共享对话记录;设置页支持启用/停用。
DeepSeek Harness Model Selector UX Enhancement Plugin: show each model's provider (providerId:modelId identity, provider-grouped catalog, shadowed composer model seat)
DeepSeek Harness plugin: provider sign-in, model catalog, and selection routing over a loopback-only /model-hub channel
给 DeepSeek Harness 的 Agent 增加一位"顾问":日常任务使用较弱模型(默认模型),遇到真正困难的决策时,Agent 会自动向一个更强的模型咨询。
DSH Plugin(DeepSeek Harness 插件):每轮对话调用 typesafe.ai systemone(jev) 判定用户情绪/意图,结果注入模型上下文;API Key 与全部参数在 GUI 设置页配置
Manual provider connectivity and latency checks for DeepSeek Harness
DSH 插件:设置页配置 OpenRouter 提供商列表,注入 provider.only / provider.order 路由参数;状态持久化