fix(ai-builder): Strip cache_control markers from persisted tool messages and responder input#2081
Closed
everettbu wants to merge 3 commits into
Closed
fix(ai-builder): Strip cache_control markers from persisted tool messages and responder input#2081everettbu wants to merge 3 commits into
everettbu wants to merge 3 commits into
Conversation
everettbu
added
n8n team
Author
|
Upstream PR was closed or merged. Code is synced via branch mirror. |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Mirror of n8n-io/n8n#26132
Original author: mike12345567
Summary
Fixes an issue where the workflow builder would error with "A maximum of 4 blocks with cache_control may be provided" during multi-step conversations (e.g. building a workflow then following up with "Also send to Slack").
applySubgraphCacheMarkers()mutates subgraph messages in-place, adding cache_control markers toToolMessages. When these messages were persisted to parent state viaextractToolMessagesForPersistence(), the markers came along. The responder then received these stale markers in state.messages alongside its own system prompt marker, exceeding Anthropic's 4-marker limit.Strip cache markers in
extractToolMessagesForPersistence()before returning to parent state.Strip cache markers in
invokeResponderAgent()before passing messages to the LLM.Review / Merge checklist
release/backport(if the PR is an urgent fix that needs to be backported)