fix: dynamic truncation threshold for code execution output #857
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
…#833) Prevent ContextWindowExceededError when single command output exceeds context limit. Previously hardcoded at 1MB which could overflow smaller context windows. Now calculates threshold based on model's context window settings, matching the LARGE_MESSAGE_TO_TOPIC_RATIO pattern used in history.py.
Collaborator
|
This truncation is not intended for the LLM, that is meant to truncate the tool output before saving it to a file, which happens automatically in _90_save_tool_call_file.py. |
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Outdated suggestions cannot be applied.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.
Fixes #833
The truncation threshold was hardcoded at 1MB which causes ContextWindowExceededError on smaller context windows.
Changed to calculate threshold based on model's context settings (12.5% of available history, min 50K chars). This matches the pattern already used in history.py for large messages.