feat(Guardrails Node): Require Chat model only for LLM checks #22241
+669
−444
Conversation
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
…s-node-only-show-model-connector-if-the-selected
BundleMonUnchanged files (2)
No change in files bundle size Groups updated (2)
Final result: ✅ View report in BundleMon website ➡️ |
Codecov Report❌ Patch coverage is 📢 Thoughts on this report? Let us know! |
![cubic-dev-ai[bot]](https://avatars.githubusercontent.com/in/1082092?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
1 issue found across 7 files
Prompt for AI agents (all 1 issues)
Understand the root cause of the following 1 issues and fix them.
<file name="packages/@n8n/nodes-langchain/nodes/Guardrails/Guardrails.node.ts">
<violation number="1" location="packages/@n8n/nodes-langchain/nodes/Guardrails/Guardrails.node.ts:15">
`model` availability is determined only from item 0 guardrails, so later items that enable LLM checks fail with `Chat Model is required`. Iterate all items (or evaluate per item) when deciding to load the chat model.</violation>
</file>
Reply to cubic to teach it or ask questions. Re-run a review with @cubic-dev-ai review this PR
| const items = this.getInputData(); | ||
| const operation = this.getNodeParameter('operation', 0) as 'classify' | 'sanitize'; | ||
| const model = operation === 'classify' ? await getChatModel.call(this) : null; | ||
| const model = hasLLMGuardrails(this.getNodeParameter('guardrails', 0) as GuardrailsOptions) |
Contributor
There was a problem hiding this comment.
model availability is determined only from item 0 guardrails, so later items that enable LLM checks fail with Chat Model is required. Iterate all items (or evaluate per item) when deciding to load the chat model.
Prompt for AI agents
Address the following comment on packages/@n8n/nodes-langchain/nodes/Guardrails/Guardrails.node.ts at line 15:
<comment>`model` availability is determined only from item 0 guardrails, so later items that enable LLM checks fail with `Chat Model is required`. Iterate all items (or evaluate per item) when deciding to load the chat model.</comment>
<file context>
@@ -10,7 +12,9 @@ export class Guardrails implements INodeType {
const items = this.getInputData();
const operation = this.getNodeParameter('operation', 0) as 'classify' | 'sanitize';
- const model = operation === 'classify' ? await getChatModel.call(this) : null;
+ const model = hasLLMGuardrails(this.getNodeParameter('guardrails', 0) as GuardrailsOptions)
+ ? await getChatModel.call(this)
+ : null;
</file context>
This comment has been minimized.
This comment has been minimized.
|
E2E Tests: n8n tests passed after 10m 23.8s Run Details
Groups
This message was posted automatically by
currents.dev | Integration Settings
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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
This PR makes Chat model requirement more granular, requiring it only when LLM checks are present
2025-11-24.14-48-01.mp4
Had to add versioning, so that old classification guardrails that use only non-LLM checks don't look like that
Related Linear tickets, Github issues, and Community forum posts
https://linear.app/n8n/issue/NODE-3984/guardrails-node-only-show-model-connector-if-the-selected-action-is
Review / Merge checklist
release/backport(if the PR is an urgent fix that needs to be backported)