Improve Trimming #333
Merged
Improve Trimming #333
+429
−373
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
- Simplify pair detection: unified (assistant, user/tool) pairs for both tool-based and simple conversations - Fix priority: system > user (task description) > most recent pairs - Remove unused `get_message_tokens` and `is_tool_result_message` helpers - Add comprehensive test coverage organized by scenario type: - Validation tests - Tool-based conversation tests - Simple conversation tests - Anthropic format tests - Remove redundant final token count verification Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Split the parameterized find_char_position_for_tokens helper into two focused functions: find_max_prefix_length and find_min_suffix_start. Added clearer docstring explaining the binary search approach and inline examples showing what each trim mode produces. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Collaborator
|
In |
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Outdated suggestions cannot be applied.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.
Refactors
trim_prompt_messagesandtrimfunctions indebug_gym/llms/utils.pyfor improved readability and correctness.trim_prompt_messageschanges:role in ["user", "tool"](works with both OpenAI and Anthropic formats)trimchanges:find_char_position_for_tokensinto two focused helpers:find_max_prefix_lengthandfind_min_suffix_startTests: