@superfish058/dsh-llm-proxy
DSH 模型代理插件:按模型走代理(Clash 等)+ 失败自动重试,设置页实时生效。
823 results
DSH 模型代理插件:按模型走代理(Clash 等)+ 失败自动重试,设置页实时生效。
Seamless API-key rotation for DeepSeek Harness LLM providers when subscription limits are hit
LLM-as-a-Verifier for DeepSeek Harness: fine-grained reward, Probabilistic Pivot Tournament best-of-N selection, and per-step progress tracking as agent tools.
自主智能多模型协同调度系统 — 主动感知、自主决策、多模型并行、质量反思自愈、经验沉淀进化
DeepSeek Harness plugin: OAuth / subscription-plan LLM providers (Grok, GitHub Copilot, OpenAI Codex, Anthropic, OpenRouter)
Interactive multi-agent council and prompt arena for DeepSeek Harness
Cut token cost without cutting model intelligence — a DeepSeek Harness (dsh) bundle plugin: structure-aware compression + TOON-style lossless encoding first + reversible spill-to-disk + real-time dashboard.
Feishu (Lark) IM bot channel for DeepSeek Harness agents — per-chat sessions, native thinking process, interactive approval cards, WebSocket long connection.
TeamFlow 团队研发流水线(TypeScript):需求→PRD→设计→架构→技术方案→并行开发→QA→验收;backlog 持久化 + 断点续跑 + 完成汇报 + 防假交付;Web 团队工作台(conversation.view tab + 拖拽看板)
see_image tool for DSH: route image files to a configurable vision model (OpenAI-compatible API) and relay its description back to a text-only model
OpenCode Zen free models provider for dsh
Deterministic context-pruning compaction backend for dsh (DeepSeek Harness) — zero-LLM summaries, /dcp command, works out of the box. Design references Opencode-DCP/opencode-dynamic-context-pruning.
Cline free models provider for dsh: scan the Cline model catalog dynamically and serve the :free models through the harness LLM seam
DeepSeek Harness (dsh) 模型余额插件:DeepSeek 官方 API 余额 + 火山方舟 Coding/Agent Plan 额度窗口(5小时/周/月)与重置倒计时显示。
Task planning with experience muscle-memory for DeepSeek Harness: condition-reflex recall of past solutions + LLM-driven capability matching + auto-persisted lessons. Zero keys, zero hard-coded paths.
DSH model-facing delegation tool that routes continuable/one-shot subagents to a model-selected LLM provider and model
Ollama Cloud models, OpenAI-compatible chat, and Web Search/Fetch for DeepSeek Harness
Token 用量记录与统计面板:记录 DSH 所有 LLM API 调用,支持秒级时间范围查询、多维度筛选、分组统计与 CSV 导出
Full-duplex voice mode for DeepSeek Harness: streamed ASR -> LLM -> TTS with barge-in
Google Anti Gravity and Cloud Code Assist Coding Plan LLM Provider plugin for DeepSeek Harness
dsh-yolo-mode —— DeepSeek Harness 双面包插件:当会话处于可写沙箱模式且审批策略为 ask 时,用大模型自动裁决沙箱升权申请,支持内置预设与自定义权限层级,并提供宿主 settings + 自发布设置桥(/yolo-mode)与 Web 客户端 UI。
Context compression tool (context_compact): the agent writes the replacement checkpoint itself and hands it to the host compaction engine, which skips the LLM summarizer call; automatic compaction stays on the official engine.
Self-evolving plugin for DeepSeek Harness: observes agent behavior, proposes improvements to its own skills/policies via LLM, validates them in a sandboxed trial agent, and applies versioned mutations with rollback.
Loom (织机) — second-validator plugin for DeepSeek Harness: a silent external coach that weaves your agent's tools, skills, config and even its model from usage history, with deterministic verification and cold-apply.