Add Straico Chat Model Node

[nlp-deutschland-de]

Summary

This PR introduces the LmChatStraico node to integrate Straico's chat-completion models into n8n workflows for AI chains and agents.

New Files

• New Files: nodes/llms/LmChatStraico/LmChatStraico.node.ts
• nodes/llms/LmChatStraico/StraicoChatModel.ts
• credentials/StraicoApi.credentials.ts
• nodes/llms/LmChatStraico/straico.svg

Updated Files

nodes/agents/Agent/V1/AgentV1.node.ts:

• Added lmChatStraico to supported language model connections for AI Agent V1 compatibility.

nodes/agents/Agent/V2/AgentV2.node.ts:

• Added lmChatStraico to supported language model connections for AI Agent V2 compatibility.

package.json:

• Registered StraicoApi.credentials.ts and LmChatStraico.node.ts in the credentials and nodes arrays.

Testing

Functional Tests:

• Tested LmChatStraico node with input “Hi” to confirm successful API calls and valid completions.
• Verified maxTokens defaults to 1024, resolving HTTP 422 error.
• Tested invalid inputs (e.g., maxTokens: 0, undefined) to ensure proper defaults and validation.
• Validated model selection via GET /models and parameter passing to StraicoChatModel.

Error Handling:

• Simulated API failures (HTTP 401, 429, 422, 500) to verify ChatResult error messages.
• Tested retry logic with invalid baseURL to confirm exponential backoff.

Additional Notes

• Documentation also added to n8n-docs and added a pull request
• Straico API Documentation
• Straico Website
• n8n Community Nodes Guide

[CLAassistant]

All committers have signed the CLA.

[cubic-dev-ai]

cubic found 4 issues across 6 files. Review them in cubic.dev

_{React with 👍 or 👎 to teach cubic. Tag @cubic-dev-ai to give specific feedback.}

[Joffcom]

Hey @nlp-deutschland-de,

Thanks for the PR, We have created "GHC-2274" as the internal reference to get this reviewed.

One of us will be in touch if there are any changes needed, in most cases this is normally within a couple of weeks but it depends on the current workload of the team.

[Joffcom]

Hey @nlp-deutschland-de,

As covered in our contribution guide we no longer accept new nodes being added from a PR unless requested or cleared by the team first. The best way to do this would be through community nodes which can be published to npm although at the moment support for AI nodes may not be fully functional so it would be a case of waiting a bit longer for this.