feat: rewrite Requesty n8n community node using AI Node SDK - #1
Closed
devin-ai-integration[bot] wants to merge 4 commits into
Closed
feat: rewrite Requesty n8n community node using AI Node SDK#1devin-ai-integration[bot] wants to merge 4 commits into
devin-ai-integration[bot] wants to merge 4 commits into
Conversation
Complete rewrite of the Requesty n8n community node using the official @n8n/ai-node-sdk and n8n-node CLI tooling. Changes: - Replace old node with new LmChatRequesty using supplyModel() pattern - Update credentials to use RequestyApi with Bearer token auth - Add dynamic model loading from /models endpoint (531+ models) - Support all OpenAI-compatible parameters (temperature, maxTokens, etc.) - Add CI workflow for lint/build checks - Add publish workflow for npm releases with provenance - Update to MIT license and proper package metadata Tested end-to-end with n8n v2.22.6: - OpenAI (gpt-4o-mini) and Anthropic (claude-sonnet-4) via Requesty - Tool calling with Calculator (233 tokens, 2 model calls) - Streaming SSE responses - Dynamic model dropdown loading - Parameter options (temperature, max_tokens, top_p, etc.) Co-Authored-By: thibault <thibault.jaigu@gmail.com>
Author
🤖 Devin AI EngineerI'll be helping with this pull request! Here's what you should know: ✅ I will automatically:
⚙️ Control Options:
|
- Rename ai-node-sdk -> @n8n/ai-node-sdk in peerDependencies - Use npm install --ignore-scripts instead of npm ci (no lockfile needed) - Remove cache: npm since no lockfile is committed Co-Authored-By: thibault <thibault.jaigu@gmail.com>
n8n's @n8n/community-nodes/valid-peer-dependencies lint rule requires exactly 'ai-node-sdk' as the peer dep name. This package isn't on npm (provided by n8n at runtime), so CI uses --legacy-peer-deps to skip resolution. Co-Authored-By: thibault <thibault.jaigu@gmail.com>
Co-Authored-By: thibault <thibault.jaigu@gmail.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Complete rewrite of the Requesty n8n community node using
@n8n/ai-node-sdk+n8n-nodeCLI. Replaces the old deprecated implementation with a modernLmChatRequestynode that usessupplyModel()for OpenAI-compatible chat model integration.Key changes:
supplyModel({ type: 'openai', baseUrl: 'https://router.requesty.ai/v1', ... })handles all LangChain/ChatOpenAI plumbing/v1/models/v1/modelsE2E tested with n8n v2.22.6:
openai/gpt-5.5anthropic/claude-opus-4-8openai/o4-minigoogle/gemini-2.5-prodeepseek/deepseek-v4-proxai/grok-4.3Tool calling, streaming, multi-provider routing, and all parameter options verified working through n8n's AI Agent node.
Link to Devin session: https://app.devin.ai/sessions/e433cbc061904ec6be7681e209aa4882
Requested by: @Thibault00