Use buffered token count for tool output tracking#2822
Open
onmete wants to merge 1 commit intoopenshift:mainfrom
Open
Use buffered token count for tool output tracking#2822onmete wants to merge 1 commit intoopenshift:mainfrom
onmete wants to merge 1 commit intoopenshift:mainfrom
Conversation
Tool output tokens were counted with raw len(tokens) while tool definitions and AIMessage tokens used _get_token_count() which applies a 10% TOKEN_BUFFER_WEIGHT. This inconsistency caused tool outputs to be slightly under-counted, making the remaining budget appear larger than it actually was. Fix: use TokenHandler._get_token_count() for tool output tokens so all budget items are accounted for uniformly. Made-with: Cursor
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: The full list of commands accepted by this bot can be found here. DetailsNeeds approval from an approver in each of these files:Approvers can indicate their approval by writing |
|
@onmete: all tests passed! Full PR test history. Your PR dashboard. DetailsInstructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository. I understand the commands that are listed here. |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Tool output tokens were counted with
len(content_tokens)(raw token count) while tool definitions andAIMessagetokens were counted withTokenHandler._get_token_count(), which applies a 10%TOKEN_BUFFER_WEIGHT. This inconsistency caused tool outputs to be slightly under-counted (~10%), making the remaining budget appear slightly larger than it actually was.Fix: apply
_get_token_count()for tool output token tracking so all budget items use the same accounting:This is a small but correctness-oriented change that makes the budget uniform.
Type of change
Related Tickets & Documents
Checklist before requesting a review
Testing
test_tool_output_token_tracking_uses_buffer_weightwhich spies onTokenHandler._get_token_countand asserts it is called at least 3 times during a single tool call round (tool definitions + AIMessage + tool output), confirming the buffered path is taken for tool outputs.make test-unit).make verifypasses (black, ruff, pylint 10/10, mypy clean).Made with Cursor