Enhance tool usage tracking with metadata aggregation #4443
Conversation
Summary of ChangesHello @jayy-77, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request significantly enhances the platform's ability to track and report token usage, particularly for complex agent architectures involving multiple tools and sub-agents. By introducing a dedicated Highlights
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. Changelog
Activity
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
adk-bot
added
the
tracing
|
Response from ADK Triaging Agent Hello @jayy-77, thank you for your contribution! To help us review your pull request, could you please fill out the PR description template? Specifically, we would appreciate it if you could provide a description of the change and a detailed testing plan, as outlined in our contribution guidelines. This information is crucial for our reviewers to understand and verify your changes. Thank you! |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request enhances tool usage tracking by adding tool_usage_metadata to events, enabling granular cost tracking for tools and sub-agents. The changes are well-integrated across event definitions, LLM flows, data models, and plugins to propagate, aggregate, and log this new metadata. The implementation introduces new capabilities to ToolContext for managing usage data and a merge_usage_metadata helper for aggregation. I have one suggestion to refactor a piece of code to avoid redundant iteration, which will improve maintainability.
| total_prompt_tokens = 0 | ||
| total_completion_tokens = 0 | ||
| total_tokens = 0 | ||
|
|
||
| for tool_name, usage_metadata in function_response_event.tool_usage_metadata.items(): | ||
| if usage_metadata: | ||
| total_prompt_tokens += getattr(usage_metadata, 'prompt_token_count', 0) or 0 | ||
| total_completion_tokens += getattr(usage_metadata, 'candidates_token_count', 0) or 0 | ||
| total_tokens += getattr(usage_metadata, 'total_token_count', 0) or 0 | ||
|
|
||
| if total_tokens > 0: | ||
| span.set_attribute(GEN_AI_USAGE_INPUT_TOKENS, total_prompt_tokens) | ||
| span.set_attribute(GEN_AI_USAGE_OUTPUT_TOKENS, total_completion_tokens) | ||
| span.set_attribute('gcp.vertex.agent.tool_usage_total_tokens', total_tokens) | ||
|
|
||
| # Add detailed breakdown as custom attribute | ||
| span.set_attribute( | ||
| 'gcp.vertex.agent.tool_usage_breakdown', | ||
| _safe_json_serialize({ | ||
| name: { | ||
| 'prompt_tokens': getattr(usage, 'prompt_token_count', 0) or 0, | ||
| 'completion_tokens': getattr(usage, 'candidates_token_count', 0) or 0, | ||
| 'total_tokens': getattr(usage, 'total_token_count', 0) or 0, | ||
| } | ||
| for name, usage in function_response_event.tool_usage_metadata.items() | ||
| }) | ||
| ) |
There was a problem hiding this comment.
The current implementation iterates over function_response_event.tool_usage_metadata twice: once to calculate total token counts, and a second time in a dictionary comprehension to create the tool_usage_breakdown. This can be optimized by performing both operations in a single loop. This will improve readability and avoid redundant iteration.
total_prompt_tokens = 0
total_completion_tokens = 0
total_tokens = 0
tool_usage_breakdown = {}
for tool_name, usage_metadata in function_response_event.tool_usage_metadata.items():
if usage_metadata:
prompt_tokens = getattr(usage_metadata, 'prompt_token_count', 0) or 0
completion_tokens = getattr(usage_metadata, 'candidates_token_count', 0) or 0
tokens = getattr(usage_metadata, 'total_token_count', 0) or 0
total_prompt_tokens += prompt_tokens
total_completion_tokens += completion_tokens
total_tokens += tokens
tool_usage_breakdown[tool_name] = {
'prompt_tokens': prompt_tokens,
'completion_tokens': completion_tokens,
'total_tokens': tokens,
}
if total_tokens > 0:
span.set_attribute(GEN_AI_USAGE_INPUT_TOKENS, total_prompt_tokens)
span.set_attribute(GEN_AI_USAGE_OUTPUT_TOKENS, total_completion_tokens)
span.set_attribute('gcp.vertex.agent.tool_usage_total_tokens', total_tokens)
# Add detailed breakdown as custom attribute
span.set_attribute(
'gcp.vertex.agent.tool_usage_breakdown',
_safe_json_serialize(tool_usage_breakdown),
)2 participants
Please ensure you have read the contribution guide before creating a pull request.
Link to Issue or Description of Change
1. Link to an existing issue (if applicable):
2. Or, if no issue exists, describe the change:
If applicable, please follow the issue templates to provide as much detail as
possible.
Problem:
A clear and concise description of what the problem is.
Solution:
A clear and concise description of what you want to happen and why you choose
this solution.
Testing Plan
Please describe the tests that you ran to verify your changes. This is required
for all PRs that are not small documentation or typo fixes.
Unit Tests:
Please include a summary of passed
pytestresults.Manual End-to-End (E2E) Tests:
Please provide instructions on how to manually test your changes, including any
necessary setup or configuration. Please provide logs or screenshots to help
reviewers better understand the fix.
Checklist
Additional context
Add any other context or screenshots about the feature request here.