Ai Langchain Nodes

Operator drops an AI Agent node, an OpenAI Chat Model node, and three HTTP Request Tool nodes onto the canvas but only connects the Chat Model. The agent responds without ever calling the tools.

Each tool node must be connected to the AI Agent's `ai_tool` input (the dotted-line port labelled 'Tool'). Verify the agent's exposed tools list reflects all three. Tool nodes provide their `name` + `description` to the LLM — confirm both are set so the model can route.

AI Agent should return `{intent, entities[]}`. Downstream Set node reads `$json.output.intent` but sometimes intent is undefined.

Wire a Structured Output Parser (or Auto-fixing Output Parser) to the agent's `ai_outputParser` input with a JSON schema for `{intent, entities[]}`. Parser validates and (with auto-fixing) re-prompts the model on schema violation. Downstream code should still handle the parsed object's absence defe…

Operator builds a chat UI off the Chat Trigger but the user sees the full LLM response only after 8s — no streaming.

Verify whether the Chat Trigger + AI Agent path supports response streaming on the configured n8n version [REQUIRES-VERIFICATION] — if not, operator-side UX should show a typing indicator until completion, or front the chat with a streaming-capable shim. Do not promise token-by-token UX without con…