116 results
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)
为 opencode go 设计的 API 池:根据余额热管理切换不同 API key,官方用量/余额查询 + 设置页图形化管理。
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.
Role-based model routing for DSH subagent delegation.
Unified DeepSeek Harness plugin: role-based subagent routing + per-agent evolution — prefercmd/memory as knowledge allow/deny lists, so repeated tasks start from proven commands and save tokens
DSH web extension: live subagent monitor + role-based subagent routing + Claude Code style .dsh/agents/*.md persona injection
Oh My DSH — tiered model routing for DeepSeek Harness: think/build tiers, an automatic vision tier for images, and image generation through an ordinary chat model (e.g. gpt-5.6-luna on opencode-go), all configured from an 'oh my dsh' settings tab. Works in the Web (Desktop) surface and in the terminal (TUI).
DeepSeek Harness plugin: provider sign-in, model catalog, and selection routing over a loopback-only /model-hub channel
OpenRouter Provider List — 在「插件 → 插件配置」填写 OpenRouter 请求使用的提供商列表与量化位数限制，作为 provider.only / provider.order / provider.quantizations 注入；设置通过 settings 服务持久化到 DSH 设置文档。
Auto-switch DeepSeek models for DeepSeek Harness: routes every model request to the vision model when images are present, to the pro model for complex tasks, and to the fast model otherwise; includes a switch_model tool for manual per-session overrides.
DeepSeek Harness (dsh) plugin for context-mode: in-process ctx_* tools (sandboxed code execution, FTS5 knowledge base) plus context-window routing guidance.
Explicit model routing plus composer/Plan picker for DeepSeek Harness
DSH web plugin that ranks OpenRouter upstream providers by quality, speed, cache-heavy price, context, and uptime, then safely switches the active route.
Cluster mode for DeepSeek Harness: canvas node-graph, multi-agent orchestration, and flow-constrained message routing
Ranked subagent delegation for DeepSeek Harness: role-based model routing with failover, per-route reasoning effort, fork delegation, transparent model labels, and a visual route editor in Settings.
Adaptive image routing for DeepSeek Harness: pass images directly to native multimodal models and transcribe them only for text-only models.
Check-digit mathematics toolbox for DeepSeek Harness (dsh): generate, validate and detect check digits for Luhn, Verhoeff, Damm, ISBN-10/13, EAN-8/13, UPC-A, ISIN, CUSIP, IBAN, CAS Registry Number and ABA routing number, plus ISBN-10 <-> ISBN-13 conversion — zero runtime dependencies
Maestro 模型路由：高阶模型（Planner）定方向、低阶模型（Executor）干具体活的委派调度插件——host 工具 + 设置页
dsh plugin: SYSTEM proxy (env) + LLM traffic-splitting proxy via a process-global undici routing dispatcher
Semantic model routing plugin for DeepSeek Harness
Named subagent profiles with configurable model routing and reasoning for DeepSeek Harness
Runtime-switchable outbound proxy for the DeepSeek Harness: hot-reload HTTP(S)/SOCKS5 routing for every global-fetch request via a settings section.
Provider discovery, matching, health checks, and pre-output failover for DeepSeek Harness.
A lightweight, selectable smart-routing mode for DeepSeek Harness.