feat:Added Token Retrieve Feature Issue:#117

[AbdulTawabJuly]

Feature
I added token counting so you can see how many tokens each LLM call uses. This helps you track API costs and understand what's eating up your budget.

Approach
I added token tracking to the state so it accumulates as the agent runs. Created some helper functions to pull token counts from the API responses.

Implementation

• Backend: Added token tracking to the state and created utility functions to extract token data from API responses
• Agent Nodes: Each of the 4 nodes now captures and logs token usage when enabled
• Frontend: Made a token display card that shows breakdown per node with cost estimates
• CLI: Added token summary output at the end so you can see the totals

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

[gemini-code-assist]

Summary of Changes

Hello @AbdulTawabJuly, 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 introduces a significant enhancement by integrating a robust token usage tracking system throughout the application. The primary goal is to provide users with clear visibility into the token consumption of their Large Language Model (LLM) calls, thereby enabling better cost management and resource optimization. The changes span the backend to collect and store token data, the agent nodes to record usage during their operations, and both the frontend and CLI to present this information in an accessible and informative manner.

Highlights

• Token Usage Tracking: Implemented a comprehensive token counting feature across the application to monitor LLM API costs and usage.
• Backend Integration: Added token tracking to the application state and created utility functions to extract token counts from both LangChain and native Google GenAI client responses.
• Agent Node Updates: All four core agent nodes (query generation, web research, reflection, and answer finalization) are now configured to capture and log their respective token usage.
• Frontend Visualization: Introduced a new frontend component, the Token Usage Display, which presents a detailed breakdown of token consumption per node, including estimated costs.
• CLI Output Enhancement: Added a token usage summary to the command-line interface (CLI) output, providing an overview of total tokens used at the end of each run.
• Configuration Option: A new track_token_usage boolean field has been added to the Configuration class, allowing users to enable or disable token tracking, defaulting to True.

Using Gemini Code Assist

The 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 /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

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 .gemini/ folder in the base of the repository. Detailed instructions can be found here.

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

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces a valuable token usage tracking feature, enhancing cost monitoring capabilities. The changes span across the backend, frontend, and CLI examples, providing a comprehensive implementation. The backend now tracks token usage per agent node, the frontend displays this information in a new collapsible UI component, and the CLI prints a summary.

My review highlights a few areas for improvement, primarily focused on maintainability and UI consistency. I've pointed out some code duplication in the backend that could be refactored, a hardcoded dependency in the frontend that could be made more robust, and some minor UI inconsistencies. Addressing these points will help improve the long-term quality of the codebase. Overall, this is a well-executed feature.