fix: Incorrect token count mapping in telemetry #2109
Closed
+5
−3
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
|
Hi @hangfei @Jacksunwei , could you guys be able to have a look, many thanks! 🙏 |
boyangsvl
approved these changes
Jul 22, 2025
boyangsvl
added
the
ready to pull
hangfei
removed
the
ready to pull
|
@tl-nguyen could you fix the two failed checks? |
tl-nguyen
force-pushed
the
fix-telemetry-token-count-mapping
branch
from
9ae6dc6 to
895e3c8
Compare
@hangfei, I fixed them many thanks! |
tl-nguyen
force-pushed
the
fix-telemetry-token-count-mapping
branch
from
895e3c8 to
7774e4e
Compare
tl-nguyen
changed the title
tl-nguyen
changed the title
tl-nguyen
force-pushed
the
fix-telemetry-token-count-mapping
branch
from
7774e4e to
4590843
Compare
|
Hi @hangfei, can we have a look on this one again? 🙏 , many thanks! |
ankursharmas
added
ready to pull
ankursharmas
added
ready to pull
ankursharmas
approved these changes
Jul 24, 2025
ankursharmas
added
the
ready to pull
copybara-service bot
pushed a commit
that referenced
this pull request
Jul 24, 2025
Merge #2109 Fixes #2105 ## Problem When integrating Google ADK with Langfuse using the @observe decorator, the usage details displayed in Langfuse web UI were incorrect. The root cause was in the telemetry implementation where total_token_count was being mapped to gen_ai.usage.output_tokens instead of candidates_token_count. - Expected mapping: - candidates_token_count → completion_tokens (output tokens) - prompt_token_count → prompt_tokens (input tokens) - Previous incorrect mapping: - total_token_count → completion_tokens (wrong!) - prompt_token_count → prompt_tokens (correct) ## Solution Updated trace_call_llm function in telemetry.py to use candidates_token_count for output token tracking instead of total_token_count, ensuring proper token count reporting to observability tools like Langfuse. ## Testing plan - Updated test expectations in test_telemetry.py - Verified telemetry tests pass - Manual verification with Langfuse integration ## Screenshots **Before** <img width="1187" height="329" alt="Screenshot from 2025-07-22 20-20-33" src="https://github.com/user-attachments/assets/ad5fc957-64a2-4524-bd31-0cebb15a5270" /> **After** <img width="1187" height="329" alt="Screenshot from 2025-07-22 20-21-40" src="https://github.com/user-attachments/assets/3920df2a-be75-47e0-9bd0-f961bb72c838" /> _Notes_: From the screenshot, there's another problem: thoughts_token_count field is not mapped, but this should be another issue imo COPYBARA_INTEGRATE_REVIEW=#2109 from tl-nguyen:fix-telemetry-token-count-mapping 3d043f5 PiperOrigin-RevId: 786827802
|
This change has been accepted as a part of c8f8b4a |
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.
Fixes #2105
Problem
When integrating Google ADK with Langfuse using the @observe
decorator, the usage details displayed in Langfuse web UI were
incorrect.
The root cause was in the telemetry implementation where
total_token_count was being mapped to gen_ai.usage.output_tokens
instead of candidates_token_count.
Expected mapping:
Previous incorrect mapping:
Solution
Updated trace_call_llm function in telemetry.py to use
candidates_token_count for output token tracking instead of
total_token_count, ensuring proper token count reporting to
observability tools like Langfuse.
Testing plan
Screenshots
Before
After
Notes: From the screenshot, there's another problem: thoughts_token_count field is not mapped, but this should be another issue imo