feat(core): simplify truncation logic to only keep the newest message #18912
Description
Note
The pull request "feat(core): simplify truncation logic to only keep the newest message" was created by @nicohrubec but did not reference an issue. Therefore this issue was created for better visibility in external tools like Linear.
Changes
- This simplifies AI message truncation to always keep only the last message and truncate it if needed. Previously we dropped oldest messages one by one until we fit within the limit.
- Also added support for truncating plain string arrays (used by embeddings input and previously we just dropped these altogether).
Test Updates
- Updated all node integration and unit tests to work with the new logic.
- Extended the node integration suite to always test the two main scenarios (keep the large message and then either truncate if the last message is large or leave it as is if it is small)
Closes #issue_link_here
Issue is tbd