fix(langchain): report token counts when trace content is enabled #2899
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
There was a problem hiding this comment.
Important
Looks good to me! 👍
Reviewed everything up to 7be2996 in 1 minute and 54 seconds. Click for details.
- Reviewed
132lines of code in1files - Skipped
0files when reviewing. - Skipped posting
4draft comments. View those below. - Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.
1. packages/opentelemetry-instrumentation-langchain/opentelemetry/instrumentation/langchain/callback_handler.py:163
- Draft comment:
Removal of the early return (if not should_send_prompts()) ensures token counts are always recorded. Confirm this is intentional and that no sensitive prompt data is recorded when prompts should be suppressed. - Reason this comment was not posted:
Comment looked like it was already resolved.
2. packages/opentelemetry-instrumentation-langchain/opentelemetry/instrumentation/langchain/callback_handler.py:208
- Draft comment:
Consider using isinstance(generation.message.content, str) instead of 'is str' to accurately detect string content. - Reason this comment was not posted:
Comment was on unchanged code.
3. packages/opentelemetry-instrumentation-langchain/opentelemetry/instrumentation/langchain/callback_handler.py:163
- Draft comment:
Removing the early return now always processes token counts even when prompts are disabled. Confirm this is the intended behavior. - Reason this comment was not posted:
Confidence changes required:33%<= threshold50%None
4. packages/opentelemetry-instrumentation-langchain/opentelemetry/instrumentation/langchain/callback_handler.py:209
- Draft comment:
Consider replacing 'if generation.message.content is str:' with isinstance(generation.message.content, str) for correct type checking. - Reason this comment was not posted:
Comment was on unchanged code.
Workflow ID: wflow_TWTaKPpvbgPVJp9n
You can customize by changing your verbosity settings, reacting with 👍 or 👎, replying to comments, or adding code review rules.
nirga
approved these changes
May 7, 2025
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.
Important
_set_chat_response()incallback_handler.pynow always calculates and sets token counts, independent of prompt content tracing._set_chat_response()incallback_handler.pynow calculates token counts regardless ofshould_send_prompts()result.input_tokens,output_tokens,total_tokens,cache_read_tokens) are always set as span attributes if they are greater than zero._set_chat_response()based onshould_send_prompts().This description was created by
for 7be2996. You can customize this summary. It will automatically update as commits are pushed.