building-langflow-componentslisted

# Building Langflow Components A Langflow Component is a Python class that becomes a draggable node in the visual flow editor. Every component is a contract between the flow JSON (which references the class by name) and the runtime (which loads and executes it). Get the contract right and the component lasts forever; get it wrong and you break saved flows for every user who ever used it. ## Read first (always) List `learnings/` and read every file relevant to the current component (provider, bundle, AI runtime, etc.). Project-specific naming conventions, banned dependencies, icon rules, or provider-specific patterns live there and override the defaults in this SKILL.md. If a learning conflicts with this file, **the learning wins** — mention it to the user. Also read `AGENTS.md` at the Langflow repo root — it's canonical and may have evolved. ## Tradeoff — when to apply, when to lighten up Apply the full discipline (immutable name, full test suite with `ComponentTestBaseWith[out]Client`, ADR for non-obvious design, BUNDLE_API changelog when relevant) for **every new component that ships**. Lighten formality for: throwaway experiments, components behind `LFX_DEV=...,my_local_only` that will never enter `__init__.py`, internal sandbox tests. Even then, follow the class structure — it's how the framework discovers the component at all. ## The non-negotiable rule > **A component's class name is its identity in every saved flow.** Renaming `OpenAIModelComponent` to `OpenAI