dsh-subagent-codex-plus
One-shot Codex subagent provider over the official app-server protocol
603 results
One-shot Codex subagent provider over the official app-server protocol
Web-search provider for the DeepSeek Harness (ctx.web): real internet search via a built-in in-process metasearch or DuckDuckGo only, no external API key, no external instance, zero runtime dependencies, plus an optional fully-local corpus full-text index.
Tavily-backed web_search / web_fetch providers for DeepSeek Harness — replaces the built-in DeepSeek search backend.
Use the models included with the Loomy desktop app in DeepSeek Harness with no configuration.
Tidal DSH branding, verified multi-provider resources, filterable local analytics, and local provider identity overrides.
Choose default and per-name provider, model, and reasoning effort for newly created DeepSeek Harness Agent Teams teammates, with live team status and restart-safe route views.
A generic provider-dispatcher proxy for DeepSeek Harness. Mounts child plugins under a private isolate realm, records every register* call, and fans one operation out to all recorded children with a configurable strategy (parallel merge / race / bail).
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。
First-class DonSeTch web access for DeepSeek Harness: fetch, search and crawl with browser-grade stealth, keyless engines, BYOK providers and an auto-updating native binary.
Advanced web search plugin with native DeepSeek and OpenAI-compatible (custom) search provider support, with a settings card in the Settings sidebar
Out-of-tree dsh bundle: remote-host discovery (JumpServer + file providers), an SSH terminal backend, and model-facing remote tools
Unofficial DeepSeek Harness LLM provider plugin for SenseNova (OpenAI-compatible). Registers the 'sensenova' provider route with multi-account API-key rotation, a Models-page card, and a live model catalog.
Shared LLM Providers settings shell, card order, and picker sort for DeepSeek Harness plugins
Review-first request-dialect preflight for custom DeepSeek Harness providers.
One-shot Pi subagent provider and true-gateway over the Pi RPC protocol
DSH (DeepSeek Harness) 插件:大模型请求报错时按规则休眠后自动重试。支持 HTTP 状态码 / 机器码 / provider 返回字段=值 三种命中形态,每条规则独立配置休眠时长与最大重试次数;会话框内显示重试卡片,GUI 设置页实时编辑规则。
Per-model and per-route image-input (vision) checkboxes on the Models page's custom-provider cards, writing through the llm-pi-ai settings namespace.
Independent DSH usage and plan-quota plugin with official provider windows, CLIProxyAPI aggregation, and a current-model composer strip.
DSH 官方直连的 LLM 配置补强:模型发现(Models 页「获取可用模型」对 deepseek-official 生效)+ provider 卡片上的 DeepSeek 余额与可用性。零运行时依赖,不改动 DSH 安装。
DSH 模型插件:监控各服务商上游 /models,列出新增模型并勾选添加(检查只读、显式应用、不自动删除)。Monitor provider model catalogs and add newly released models to DeepSeek Harness.
DeepSeek Harness plugin that serves every gpt-load model from one provider group, each model on its own wire protocol (OpenAI Chat Completions or Anthropic Messages), synced from /api/models
dsh web Settings section (Custom models): subagent delegation allow-list, plus per-model image-input / reasoning-effort mapping.
Firecrawl search provider and multi-account settings for DeepSeek Harness
Auto-inject user-chosen skills into DeepSeek Harness sessions and harvest skills from other agent tool dirs (~/.claude, ~/.codex, ...) as extra providers.