n8n community node: DeepSeek R1/Reasoner Chat Model with proper reasoning_content handling for tool calls. Fixes the 'Missing reasoning_content field' error when using AI Agent with tools. Connect this as the Chat Model sub-node to your AI Agent.

DeepSeek Chat Model for n8n AI Agent — fixes strict tool-schema rejection and reasoning_content passback

n8n community node for DeepSeek chat models (Pro / Flash) with reasoning_content (Chain-of-Thought) support, usable as a LangChain sub-node inside the AI Agent and Basic LLM Chain.

Pi extension that fixes the DeepSeek-behind-Bifrost reasoning drop on tool-calling turns. Bifrost relays DeepSeek reasoning in non-standard fields (reasoning / reasoning_details instead of reasoning_content); in tool-calling contexts DeepSeek requires rea

omp/pi extension: remap non-standard reasoning wire fields (e.g. delta.thinking) from OpenAI-compatible gateways to reasoning_content, in-process, no proxy.

Pi Coding Agent extension that fixes the DeepSeek reasoning-chaining contract on tool-calling turns: replays the real reasoning text on continuations, forces non-empty reasoning_content in tool scope, and strips the thinking:disabled kill-switch.

ReiStandard Active Messaging server SDK with pluggable database adapters. Three-axis push schema (messageKind / messageType / messageSubtype) from @rei-standard/amsg-shared. Auto-emits ReasoningPush when the LLM response carries reasoning_content.

OpenCode plugin for Dymium/GhostLLM — injects auth tokens and taps reasoning_content streams

n8n community node: DeepSeek Reasoner Chat Model (ZH) — DeepSeek 思考模式 Chat Model(繁中修正版)。完整保留 reasoning_content 以支援 AI Agent 多輪工具呼叫(修復 400 錯誤),並保留中文輸出。Fork of n8n-nodes-deepseek-reasoner (adcom, MIT)。

n8n community node for DeepSeek chat models (Pro / Flash) with reasoning_content (Chain-of-Thought) support, usable as a LangChain sub-node inside the AI Agent and Basic LLM Chain.

vLLM provider — full vLLM OpenAI-compatible surface: sampling extensions, mm_processor_kwargs, chat_template_kwargs, video, and reasoning_content

Vision/multimodal MCP server for OpenAI-compatible gateways. Reasoning-model aware: thinking off by default, reasoning_content fallback. 8 tools: analyze_image, extract_text_from_screenshot, ui_diff_check, understand_technical_diagram, analyze_data_visual

Fork of @musistudio/claude-code-router with multi-turn DeepSeek thinking-mode fix (reasoning_content replay) for openrouter and deepseek transformer chains.

n8n community node for DeepSeek V4 models (deepseek-v4-flash, deepseek-v4-pro) with thinking mode control

Compatibility and diagnostics for DeepSeek V4 tool-calling agents.

Universal LLM provider compatibility layer — normalizes provider-specific payload differences (thinking formats, output budgets, tool pairing, media transport) into a single dispatch pipeline.

Model-facing describe_image tool for the dsh web GUI: gives a text-only model image understanding by asking a vision-language model at an OpenAI-compatible endpoint to describe one image (local path, http(s) URL, or attachment reference). Hot-pluggable —

A TypeScript CodeAgent harness reconstructed from Arena message and tool traces.

n8n community node for LiteLLM (OpenAI-compatible proxy) with dynamic model list and automatic DeepSeek reasoning support

Community n8n node for DeepSeek V4 models (deepseek-v4-flash, deepseek-v4-pro) with thinking mode control and English UI