dsh-plugin-effort-declare
Declare per-model reasoning efforts, image input, and openai-completions dialect on hand-declared llm-pi-ai routes. Writes the official namespace; does not intercept llm/stream or replace the Models page.
144 results
Declare per-model reasoning efforts, image input, and openai-completions dialect on hand-declared llm-pi-ai routes. Writes the official namespace; does not intercept llm/stream or replace the Models page.
Agent loop rate limiter — prevents TPM/RPM limit violations by intercepting the LLM streaming pipeline and adding adaptive delays between requests
Voice input plugin for DeepSeek Harness web (China-ready): Alibaba Cloud DashScope ASR via a local bridge. Mic button in the composer, streaming recognition, cursor-aware insertion, silence auto-stop.
Expose DeepSeek Harness as an OpenAI-compatible API server: /v1/chat/completions (stream + non-stream) and /v1/models, each API call backed by a real agent session with tools and a workspace.
使用仓库内新版 mcp-bridge.js 连接已有的本地 Chrome MCP 服务;默认对接 /mcp-new 无会话 Streamable HTTP,也兼容旧 /mcp Session 端点
A pure runtime that routes DeepSeek Harness sessions to pluggable loop engines by agent-preset. Ships no engine; downstream plugins register engines via ctx.engineSwitch.
DingTalk IM bot channel for DeepSeek Harness: each chat drives its own agent, replies and thinking come back as messages over the Stream-mode long connection.
DSH WebUI theme manager: import, preview, use, refresh, and manage mainstream DSH skin packages, persisted on the host at ~/.dsh/dsh-custom-theme-import/library.json.
Feishu/Lark IM channel for DeepSeek Harness: chats drive agents, answers render as streaming rich cards, approvals settle by button clicks
MCP 服务器可视化配置插件:在 DSH Web 设置界面管理 MCP 服务器(stdio / streamable-http / SSE),保存即生效,无需手改配置文件。| Visual MCP server management for DeepSeek Harness: configure stdio / HTTP / SSE servers from the settings UI, hot-synced without editing config files.
DSH harness bundle/plugin: tolerate OpenAI-compatible providers whose streaming responses omit finish_reason (e.g. the Snowflake Cortex gateway) so turns complete instead of failing with a TRANSPORT error.
DeepSeek Harness plugin (temporary, pre-upstream-fix): automatically injects a CPython tempfile shim (PYTHONPATH -> sitecustomize) into every confined shell command on the Windows sandbox, so python/pytest tempfile use works with zero extra tools, zero model-context overhead, and zero escalation.
Qoder CN adapter plugin for DeepSeek Harness: COSY-signed, WAF-encoded streaming against gateway.qoder.com.cn
DSH Feishu self-built app integration: receives text messages over the official Feishu WebSocket long connection, routes them to a DSH agent session, streams safe assistant text deltas through a Feishu CardKit card, and falls back to ordinary text when card streaming is unavailable. Acknowledges with an OK reaction (text fallback). Standalone Cordis bundle — no dsh source changes.
dsh plugin: during long agent thinking, posts a hot-news or reminder message directly into the conversation stream.
A calmer reading view for DeepSeek Harness: native process details, live reasoning, and clean final answers.
DeepSeek Harness plugin: Bilibili keyword video search, video metadata, subtitle transcripts, direct play URLs, and multimodal frame viewing (bilibili_search / bilibili_video / bilibili_subtitles / bilibili_playurl / bilibili_frames). Anonymous by default with risk-control bootstrapping; an optional SESSDATA unlocks login-gated subtitles and higher-quality streams.
在每条会话轮次的统计行上方显示 OpenRouter 实际供应商(StreamLake 等)与通道模型。纯客户端插件,无服务端依赖。
Drop-in replacement for the Codex subagent provider that projects the app-server stream into a harness child session, so Codex runs render as ordinary subagents in the Web UI
Transport-layer data masking for deepseek-harness (dsh): sensitive values never leave the process — the model sees placeholders, you see real values restored live in the stream.
Generative UI for DeepSeek Harness — the agent writes TSX, dsh web renders it live, inline in chat and in a canvas panel
A full-screen interactive terminal UI for the DeepSeek Harness agent runtime — live streaming, reasoning blocks, tool cards, sessions, permissions, plan mode, and a full slash-command suite. The web UI, reimagined for the terminal.
Tolerate OpenAI-compatible model streams that end without a terminal finish_reason so DSH turns complete instead of aborting.
Readable thinking display for DeepSeek Harness: live per-paragraph summaries of the reasoning stream, rendered in the chat history where the 'Think' row is, with a user-chosen summary model (thinking disabled on summary requests).