578 results
DSH plugin: start/stop a local llama.cpp llama-server from the settings → plugins page — two model slots (A/B) with per-slot model-file selection, eight editable launch-parameter groups (text/vision × fast/long × 2 slots), and one shared DSH provider carrying both slots' models with four thinking-effort levels.
智谱 MCP 三件套 for DSH:联网搜索(search)、网页读取(reader)、开源仓库(zread)原生 provider 与工具,附设置页卡片。Zhipu MCP suite (web search / reader / zread) as native DSH providers and tools, with a settings card.
DeepSeek Harness plugin: live account balance/usage panel for every configured LLM provider (draggable floating-ball widget, configurable refresh interval and balance thresholds)
Compact provider balances and local token-usage analytics for dsh web
Inspect, measure, search, and compare the exact provider-neutral context assembled by DeepSeek Harness.
Two-level model circuit breaker with failover for DeepSeek Harness: trip a model or a whole provider after repeated request failures and route the next request to a configured fallback
DSH web plugin: 为自定义模型（OpenAI-compatible pi-ai provider）增加思考强度（reasoning effort）配置 —— 设置页新增「思考强度」分区，按模型配置思考级别与线格式、按 provider 配置默认思考强度，直接写入 llm-pi-ai 设置，composer 模型选择器随即生效。
Register models, assist with portraits, and select the Agent model from a secret-free catalog for DeepSeek Harness.
梁文峰时间拦截官方 DeepSeek API 请求：北京时间工作日高峰时段 09:00-12:00、14:00-18:00 自动拦截发往官方 provider `deepseek-official` 的模型请求，可切换到第三方中转或预留的本机转 API 端口，未配置则阻止并提示；非高峰不拦、正常走官方，专治高峰掉速与刷屏。标准可安装 dsh 插件，host 单半身，设置经 cordis 配置文件注入。
为 DeepSeek Harness (dsh) 开发插件并走官方机制安装（独立 npm bundle + dsh plugin add）。当用户要求开发/创建 dsh 或 deepseek-harness 插件、给 dsh 添加工具/搜索 provider/LLM 适配器/设置卡片/UI 皮肤/事件钩子，或排查 dsh 插件安装失败时使用。含可复制模板、官方安装三形态、验证清单与常见坑。
Composable three-tier memory control plane for DeepSeek Harness: persistent runtime context, searchable project documents, pluggable long-term memory, guarded strategies, WebUI, and headless tools.
Web access for DeepSeek Harness — multi-provider search/fetch on ctx.web, plus GitHub/PDF/YouTube extraction.
DSH web search provider facade: routes ctx.web.search to third-party engines (SearXNG/Tavily/Serper/Brave/Bing/Google CSE). Replaces the built-in DeepSeek-only search with configurable third-party APIs.
Token usage dashboard, provider balances, and subscription quotas for the dsh web GUI
Ventus 搜索：Bing/360/Bilibili 多引擎搜索 + 类 Readability 正文抓取，双 provider 注册进 ctx.web，带设置卡与总开关。
Adaptive Reversible Context (ARC) for DeepSeek Harness — provider-aware, cache-conscious context governance with reversible recovery.
DeepSeek Harness plugin: provider account balance inside each Models settings row, queried through a loopback-pinned RPC channel with the stored API key kept on the host
OpenCode-style web search (Exa / Parallel MCP) provider for the DeepSeek Harness ctx.web seam. Gives any model, including opencode-go's deepseek-v4-flash, a working web_search tool without a DeepSeek official API key.
Volcengine Ark Agent Plan & Coding Plan providers for DeepSeek Harness (DSH), with verified thinking-effort compatibility
Firecrawl-backed search provider for the DeepSeek Harness web capability seam (ctx.web)
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.
Token usage statistics for the DeepSeek Harness Web UI: captures per-request LLM usage from the llm/stream waterfall, persists it, and renders animated charts grouped by API (provider), model, and date.
Aggregated web-search provider for DeepSeek Harness: one prioritized queue over AnySearch / TinyFish / Tavily / Brave / Exa / Firecrawl / Jina / SerpApi / Serper, multiple API keys per entry, ordered fallback per request.
Local multi-plan bridge for DeepSeek Harness: use your existing ChatGPT Codex, Claude, ZCode (GLM) and Qwen subscriptions through one loopback proxy, with a settings-page status card and one-click provisioning. No dsh core changes.