dsh-subagent-conductor
EN: Settings and default-route layer for official DeepSeek Harness subagents: session/role/global model routing with a composer selector. ZH: 面向 DeepSeek Harness Web 官方子代理的设置与默认路由层:会话/角色/全局模型路由与输入框选择器。
116 results
EN: Settings and default-route layer for official DeepSeek Harness subagents: session/role/global model routing with a composer selector. ZH: 面向 DeepSeek Harness Web 官方子代理的设置与默认路由层:会话/角色/全局模型路由与输入框选择器。
DeepSeek Harness (dsh) plugin that registers Lynkr — a self-hosted, multi-provider LLM tier-routing gateway — as a custom OpenAI-compatible provider in settings.yaml.
Shadow-mode SLM router for DeepSeek Harness: per-turn weak/strong prediction via vertical-small-model CLI, writes ~/.dsh/slm-shadow/session-slm-shadow.jsonl; does NOT change the active model (S1 shadow only).
Long-lived AI companions with WeChat channel routing for DeepSeek Harness
Give text-only DeepSeek-V4-Pro real vision with zero new dependencies and DeepSeek-only routing: images are described by deepseek-v4-flash-vision-exp (your existing DEEPSEEK_API_KEY), then the text is handed to V4-Pro.
DSH LLM provider hub with a native model-configuration panel, gateway routes, model catalogs and live model discovery. Supports three wire protocols, custom User-Agent, model overrides and live routing without hand-editing settings.yaml.
Minimal emergency-maintenance terminal front-end for DeepSeek Harness: session picker + resume, inherited permission presets, live model/effort routing. · DSH 救援 TUI:WebUI 挂掉时的极简终端维护入口(会话续聊 / 权限继承 / 模型路由切换)。
TokenLab provider bundle for DeepSeek Harness with native Responses, Messages and Chat routing plus multimodal and async tools.
Task delegation router for DSH: main model plans/verifies, sub-models search/browse/code/verify.
Durable DeepSeek Harness bundle: the local-model performance tuning carried as a re-installable plugin layer (compaction, tool-result pruning, time context, cloud title routing, text-toolcall guard) — survives dsh updates
将用户意图解析为可编辑、可观测、可学习的多跳工具调用图,消费 CDP 语义与 adapter 桥接工具
Display companion for dsh-vision-router: keep Auto Vision routing, and put a square picture button on each original model row. Does nothing unless dsh-vision-router is installed.
dsh plugin: routes ask-user questions to every interaction surface bound to the asking session (TUI panel, Feishu card, web, ...) — first answer wins
Multi-engine web search for DeepSeek Harness: an aggregated ctx.web search provider (auto-routing + sequential fallback, free engines keep search alive) plus a web_search_pro model tool with per-query engine choice, fan-out, batch and verticals — Brave, B
DSH plugin: declare VIRTUAL model ids bound to a pluggable routing algorithm (priority, round-robin) over real provider/model candidates; using the virtual id transparently dispatches to a real provider chosen by the algorithm, with failover.
Abstract interaction layer between DeepSeek Harness (DSH) and IM platforms (Feishu, WeCom, ...). Channel-agnostic hub with proven interaction patterns (dedupe, instant ack, wait-reply, followup wakeup, scoring-based model routing, approval gate) plus pluggable adapters for Feishu and WeCom.
dsh 外挂式网络路由:按 hostname 给 dsh 请求分流——勾选的域名走本地代理(Clash 等),其余直连。内置嗅探,自动扫描 dsh 访问过的 hostname,设置页勾选即生效(保存即热生效,免重启)。纯外挂:dependencies 空,运行时零 require,全靠宿主 ctx 注入;不碰 settings.yaml provider 配置。
DSH Effort Router(模型分流):按每一轮请求的难度自动选择模型与思考强度——简单问题走便宜快模型,难题才叫强模型。规则判定零 token,灰区交给一次小模型裁定,图片档强度随难度升降(low/high/max)。每轮请求级覆盖,不改你的会话选择与默认模型。
Flash-only reasoning-effort routing for DeepSeek Harness: classifies each step by its shape and sets the DeepSeek flash model's reasoning effort to match. The model never changes; effort max is opt-in.
Self-evolving deterministic rule objects before DeepSeek Harness model calls