dsh-tavily-web-search
Tavily-backed web search provider plugin (bundle) for DeepSeek Harness — registers a ctx.web search provider using the Tavily REST API
601 results
Tavily-backed web search provider plugin (bundle) for DeepSeek Harness — registers a ctx.web search provider using the Tavily REST API
Fold provider token usage from the durable session log, price it with a peak/off-peak table, and surface totals in the dsh web GUI plus a standalone overview page and JSON API.
DSH Web plugin: DeepSeek peak/off-peak pricing, other-provider flat rates (e.g. z-ai/glm-5.3-flash), a live per-session cost estimate, and a hover cache-hit trend chart.
Use the opencode local server (OpenCode Zen client channel) as a provider in dsh
Custom provider enhancements: User-Agent override, reasoning-level switching, and image-input declaration for DSH custom providers · 自定义供应方增强:UA 覆盖、推理等级切换、图片输入声明。
DSH rc.8 Web settings row for active providers' model-request retry budget
LiteLLM /v1/search-backed web search provider for the DeepSeek Harness web capability seam (ctx.web). One search is one HTTP request — no model turn.
DSH 供应商管理插件:在设置 → 模型页为每个供应商提供启用/禁用开关,禁用后该供应商的模型从输入框模型选择器和 /model 命令弹层中隐藏,且会话不会再调用该供应商的模型;模型选择器新增关键字搜索;供应商编辑卡片支持点击标题内联重命名。
DSH web UI 插件:把输入框官方「模型选择」控件替换为两个独立按钮(供应商选择 + 模型选择,两级联动),保留推理等级调节;只动这一处控件,不改 DSH 源码。
Keyless web search provider for DeepSeek Harness backed by 360 Search (so.com). 免 API Key 的 DSH 联网搜索提供方。
Volcengine Ark (火山方舟) web-search provider for the DSH web seam: calls the Ark Responses API with the native web_search tool and maps url_citation annotations to search sources.
Bioinformatics skill router plugin for DeepSeek Harness: searchable index over a large skill library, an anysearch web-search provider, remote-exec tooling, and scenario guidance for literature review, bio-data analysis, and remote training
A DSH-native OAuth multiplexer for subscription-backed model providers
Searchable, collapsible model selector for the DeepSeek Harness web UI. Replaces the composer model seat with a search box and per-provider group collapse while reusing the official shared model directory.
接入 Ant Digital MaaS 与 NVIDIA NIM 流式模型路由 / Installable DSH bundle for Ant Digital MaaS and NVIDIA NIM streaming routes
Keep native vision, drop historical images before they hit relay providers. Global DeepSeek Harness bundle for every agent.
DSH plugin: SearXNG-backed search provider for ctx.web (self-hosted, 1GB-VPS friendly)
DSH plugin: consult multiple expert advisor models in a retro chat-group card — auto-deepen consultation pipeline with real streaming, SSE replay, and 26 provider presets.
Tavily AI search provider for DeepSeek Harness: replaces the official DeepSeek web search (basic/advanced depth, per-credit billing) and adds a settings page for key management and connectivity testing.
DeepSeek Harness plugin: AnySearch-backed web search provider (aggregates exa/tavily/firecrawl via one MCP gateway) registered into ctx.web.
OpenCode Go LLM provider bundle for DeepSeek Harness (DSH rc.6).
Dual-pipeline compaction for DeepSeek Harness: official server-side Responses compaction v2 for OpenAI-routed targets, with a deterministic VCC-style local compiler (zero model calls) as the default fallback and for every other provider.
LiteLLM provider for DeepSeek Harness
Universal OpenAI-compatible LLM provider plugin for DeepSeek Harness (万能插头) — point any local or remote OpenAI-compatible endpoint at the harness and chat with it