fix: remove isInternalAgent flag due to hook ordering race condition #228
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
The isInternalAgent flag was causing a race condition where concurrent internal agents (title/summary generators) would set the flag to true, and normal session message transforms would see the stale value and skip injecting the prunable-tools list. This happened because messages.transform runs before system.transform, so the flag set by system.transform was always stale by the time messages.transform checked it. Fix: Remove the flag entirely and only skip system prompt injection for internal agents (detected in system.transform where it works reliably).
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Outdated suggestions cannot be applied.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.
isInternalAgentflag from session stateThe
messages.transformhook runs beforesystem.transform, but we were settingisInternalAgentinsystem.transform. When concurrent internal agents ran, the flag would be stale by the time the next normal session'smessages.transformchecked it, causing it to skipinsertPruneToolContext().Need a better solution to stop injections for internal agents