@dsh-polyglot/bundle
dsh-polyglot — the model switch for DSH: one generic OpenAI-compatible ctx.llm adapter, curated free/cheap DeepSeek provider presets, and automatic provider fallback when a free tier rate-limits you
128 results
dsh-polyglot — the model switch for DSH: one generic OpenAI-compatible ctx.llm adapter, curated free/cheap DeepSeek provider presets, and automatic provider fallback when a free tier rate-limits you
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、各类中转等),生成后自动视觉自检反馈,优于 modlens。
DeepSeek Harness multi-model routing plugin: route tasks to custom specialist agents (vision / image generation / translation / speech / subagent) with per-agent providers & models, multimodal account sign-in, OAuth account pools, and realtime usage stats
Delegate light subagent tasks to cheaper models: automatic Flash/Pro routing for DeepSeek Harness subagent calls, with /delegate overrides, budget caps, and a routing-ledger panel.
DeepSeek Harness 小白零门槛零费用套件:4个永久免费模型一键接入(智谱/硅基流动/讯飞星火/OpenRouter)、免费模型智能路由(自动测速优选最快)、DeepSeek 计价时段提醒、在线帮助中心。
DSH plugin — Hermes-style Mixture-of-Agents request aggregator: router → parallel reference advisors → aggregator stream, with dual-provider failover (official + OpenCode Go) and V4P triple-gate cost guard.
DeepSeek Harness plugin that enhances custom provider setup by auto-discovering models and auto-populating contextWindow, maxTokens, vision, and reasoning capabilities from models.dev
Two-tier model router for DeepSeek Harness: an LLM Judge sends each turn to the cheap Fast chain or the Smart chain by expected cost, with multi-model fallback chains, exponential-backoff failover, cache-aware switching and task-level orchestration. A DSH adaptation of pi-shift-router.
Voice input plugin for DeepSeek Harness
Proxy Router: route listed hostnames through an HTTP/SOCKS proxy for ctx.web fetches (host plugin) + settings card (client bundle)
Project-level direction, boundary, and reuse governance for AI coding agents.
Dynamic skill runtime manager for DeepSeek Harness
Unified ModelID routing for DeepSeek Harness: one logical model id over multiple providers, first-token failover with cooldown, health-aware ranking, fallback reasoning efforts, purpose-based simple/complex task split, per-tier reasoning effort, and a settings-page management panel.
One-key ClawRouters plugin for DeepSeek Harness: chat, image generation, video generation, and web search
DSH plugin: TRAE SOLO supplier for dsh-router. Provides the traework supplier (free SOLO chat channel, ported from traework2api) to dsh-router through the router.suppliers cordis service.
AutoRouter (model routing gateway / relay) LLM adapter for the DeepSeek Harness
Multi-provider quota, balance and Token-cost dashboard for DeepSeek Harness Web, with a draggable widget, usage analytics, local pricing and route diagnostics.
DeepSeek Harness plugin: learning agentic router — rule + UCB + LinUCB + k-NN experts under an EXP3 meta-selector, with a durable quality-reward flywheel, REAL model switching via the session request-header precedence chain, and STEP-LEVEL routing (v1.5.0)
Register AllRouter as a DSH provider: one base URL and one key for Kimi K3, Claude, GPT, Grok, GLM, DeepSeek, MiniMax-H3. Switch models without managing separate providers; every call reports real cost.
通用多平台 API 额度/余额实时监视器(DeepSeek Harness Web GUI 插件):侧边栏实时显示 DeepSeek 官方接口 / OpenCode Go 订阅等平台余额与订阅额度(其余平台走自定义接口),DeepSeek 峰谷时段倒计时(官方峰谷定价:工作日高峰 2 倍、空闲半价),跟随 DSH 明暗主题,可调刷新间隔(30s–5min),配置跨重启/浏览器持久化。
Configurable near-field trigger that reminds a DeepSeek Harness agent to load the J-Space Cognition Suite only when rules say it is worth it
DeepSeek Harness 峰谷定价自动模型路由插件:高峰时段自动使用 deepseek-v4-flash,空闲时段自动使用 deepseek-v4-pro;用户显式选择的模型始终优先。
Hybrid model router for DeepSeek Harness: declarative rules, user-configurable cost control (cost-first / quality-first / balanced), optional LLM task classifier, and failure fallback chains.
Route the first prompt to one of DeepSeek Harness's four shipped Agent Presets with DeepSeek V4 Flash.