706 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.
DSH web plugin: adds a one-click Compact button and a New Session button to the conversation context meter panel. Compact submits /compact to summarize older history; New Session starts a fresh session in the same workspace (agent preset and permission settings follow the deployment default).
A multi-platform IM gateway for DeepSeek Harness (dsh) — Feishu (Lark), WeCom (WeChat Work), and Telegram, with a visual settings card in the web GUI. Turn your dsh agent into a chat assistant reachable from the messaging apps you already use.
Named subagent library for DeepSeek Harness: a settings-driven roster of role subagents (model + persona + tool filter), exposed to every session through the list_subagents and delegate tools, a /subagent command, and a Settings page.
Enhanced goal surface for the DeepSeek Harness web UI: full lifecycle dock above the composer (create / multiline edit / pause / resume / complete / clear with live round progress), a composer tool-row entry with phase dot, a collapsible chip, and a General-settings switch to hide the entry.
DSH web plugin: a native Settings panel for visualizing and managing MCP servers, skills and rules, with a modular feature registry so future visualizations slot in without touching the shell.
Coding-plan quota and balance readout for the DSH composer toolbar: MiniMax, DeepSeek, Kimi, OpenRouter and Zhipu windows follow the selected model; API keys are reused from DSH model settings.
Manage OpenCode Zen free-tier and Go-tier models in settings.yaml: live model listings from opencode.ai, configured-versus-live drift per route, add/remove through four agent tools plus an OpenCode Models settings section.
DeepSeek Harness 插件：将对话框提交快捷键改为 Ctrl/Cmd+Enter，普通 Enter 换行，可在设置中随时开关。 / A DSH plugin that makes Enter insert a newline and Ctrl/Cmd+Enter submit, toggleable in settings.
Ollama native protocol (/api/chat) provider for DeepSeek Harness: llm-ollama settings namespace, serving LlmAdapter, /api/tags model discovery, and a whole-page Ollama settings section.
Git history viewer for the DSH dock: browse the commit graph, branches, tags and remotes; stage, commit, push and manage repository settings.
OpenCode Go subscription key rotator for DeepSeek Harness (dsh): per-request active-key routing, 429/quota cooldown rotation, cost accounting, dashboard quota scraping, and a web GUI settings section. Self-contained data dir under the plugin install folder — no machine-specific paths.
Provider-level web search+fetch pool for DeepSeek Harness: bypass the official LLM search channel (0 model tokens), failover/rotate across Exa/Tavily/Jina/Firecrawl/Serper/SerpApi/SearXNG/DDG/Brave with quota-aware circuit breaking, multi-key rotation, and a GUI settings page.
Weak-network adaptor for the DeepSeek Harness: transparent long-backoff model-stream retries (10-min cap), local response replay cache, heartbeat auto-reconnect, degraded-mode token economy, and a bilingual (zh/en) settings page. / 弱网适配插件：模型流长退避重试、本地响应缓存、心跳自动重连（默认 10 分钟封顶）、降级省 token、双语设置页。
CodeBuddy (copilot.tencent.com) provider bundle for DeepSeek Harness (dsh): 18 models (DeepSeek, GLM, Kimi, MiniMax, Hunyuan, auto) with adjustable reasoning efforts, CodeBuddy web search / web fetch backends for the stock dsh tools, and a settings card in the Web UI.
Audit the DeepSeek Harness plugin list by origin (official vs self-installed): a /plugin-audit command plus a Source tab in Web Settings
Tavily web search for DSH: settings toggle back to official DeepSeek, keyless by default
DeepSeek Harness plugin: (1) installs an image-input (input modalities) checkbox into the Models settings catalog so a custom model can declare input:[text,image] and DSH passes images straight to it — the core feature; (2) optionally registers an OpenAI-compatible vision relay provider + vision_analyze/vision_status/vision_test/vision_configure tools. Host-only bundle (no settings card).
LAN and reverse-proxy access for the DeepSeek Harness Web UI: returns the settings service on pages that are not localhost, fills in the Web APIs the browser withholds on plain HTTP, and can open a listener of its own so nothing else is needed. Compatible with DeepSeek Harness 0.1.2-alpha.5.
DeepSeek Harness plugin: manage the sidebar-foot action buttons — reorder them by drag-and-drop and control each one from a dedicated settings page with three states (show in sidebar / fold into the "More" menu / fully hide).
Custom HTTP/HTTPS proxy for DeepSeek Harness: routes every host-side fetch (LLM requests, model discovery, market, web search) through your proxy (Clash/mihomo/v2ray) without TUN mode, with a settings card for live host/port edits. 为 DeepSeek Harness 注入自定义 HTTP 代理，无需 TUN 模式，设置页可直接修改地址与端口。
QQ 2007-inspired retro messenger skin for the DeepSeek Harness Web GUI, with Codex-generated original artwork, compact desktop chrome, an account card, optional original send chime, and reversible settings.
DSH bundle plugin: a petdex.dev companion-pet market in the Settings UI with a native macOS desktop pet. Browse, search, install, enable, rename, and delete pets; previews are proxied same-origin to dodge CORS.
Token usage statistics and a 53-week heatmap for DeepSeek Harness Web settings