fix: preserve per-step usage in AssistantMessage #441
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 Python SDK was discarding `id` and `usage` fields from assistant messages during parsing, making it impossible to track per-step token usage. This is inconsistent with the TypeScript SDK which preserves these fields. Changes: - Add `message_id` and `usage` fields to `AssistantMessage` dataclass - Extract these fields in `message_parser.py` when parsing assistant messages Use case: - Monitor per-step token consumption for cost analysis - Detect when API features like `clear_tool_results` trigger by observing input_tokens drops between steps - Parity with TypeScript SDK behavior
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Outdated suggestions cannot be applied.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.
The Python SDK was discarding
idandusagefields from assistant messages during parsing, making it impossible to track per-step token usage. This is inconsistent with the TypeScript SDK which preserves these fields.Changes:
message_idandusagefields toAssistantMessagedataclassmessage_parser.pywhen parsing assistant messagesUse case:
clear_tool_resultstrigger by observing input_tokens drops between steps