Feat/session compaction

[raphaelmansuy]

[google-cla[bot]]

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[bot]]

Summary of Changes

Hello @raphaelmansuy, I'm Gemini Code Assist[^1]! 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 new 'Session Compaction' feature designed to optimize token usage in long-running conversations. It achieves this by automatically summarizing older parts of the conversation history using an LLM, replacing the original events with a concise summary in the LLM's context. This significantly reduces the number of tokens sent to the LLM while preserving conversational context, leading to cost savings and improved performance for extended interactions. The feature is configurable through new CompactionConfig options, allowing fine-tuning of when and how compaction occurs, and includes mechanisms to maintain context continuity. Comprehensive examples and documentation are provided to facilitate adoption and understanding.

Highlights

• New Feature: Session Compaction: Introduces a new session compaction feature to automatically summarize older conversation history using an LLM, significantly reducing token usage in long-running conversations.
• Configurable Compaction Logic: The new compaction package provides a Compactor and Config struct, allowing configuration of compaction interval, overlap size, custom LLM model for summarization, and system prompts.
• Integration with Core Components: The CompactionConfig has been integrated into launcher.Config and runner.Config, enabling the feature across console and web launchers.
• Intelligent Event Filtering: A new internal/context/compaction_filter.go file provides logic to filter session events for LLM context, ensuring that only compaction summaries and non-compacted events are sent, preventing redundant token usage.
• Comprehensive Documentation and Examples: New documentation (GETTING_STARTED.md, README.md) and a debug example (debug/main.go) have been added to guide users on how to enable, configure, and observe session compaction.
• Asynchronous Compaction Triggering: Compaction is triggered asynchronously after each successful invocation within the runner, ensuring minimal impact on the main conversation flow.

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 :thumbsup: and :thumbsdown: 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.

[^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.

[rakyll]

How does this change relate to ADK's official compaction capabilities? An experimental implementation is at https://github.com/google/adk-python/blob/f7f6837fdede6a7670ceedfbeac07f926506f7f6/src/google/adk/apps/app.py#L63 and we will port it to ADK Go once it's more mature.

[raphaelmansuy]

How does this change relate to ADK's official compaction capabilities? An experimental implementation is at https://github.com/google/adk-python/blob/f7f6837fdede6a7670ceedfbeac07f926506f7f6/src/google/adk/apps/app.py#L63 and we will port it to ADK Go once it's more mature.

Yes it is based on this experimental implementation

[jinzhongjia]

Oh, great

Since this is a new library, could we import the feature first and then mark it as an experimental, unstable API for use?