feat[models]: add support for gemma model via gemini api

[douglas-reid]

Adds support for invoking Gemma models via the Gemini API endpoint. To support agentic function, callbacks are added which can extract and transform function calls and responses into user and model messages in the history.

This change is intended to allow developers to explore the use of Gemma models for agentic purposes without requiring local deployment of the models. This should ease the burden of experimentation and testing for developers.

A basic "hello world" style agent example is provided to demonstrate proper functioning of Gemma 3 models inside an Agent container, using the dice roll + prime check framework of similar examples for other models.

Testing

Testing Plan

• add and run integration and unit tests
• manual run of example multi_tool_agent from quickstart using new Gemma model
• manual run of hello_world_gemma agent

Automated Test Results:

Test Command	Results
pytest ./tests/unittests	4386 passed, 2849 warnings in 58.43s
pytest ./tests/unittests/models/test_google_llm.py	100 passed, 4 warnings in 5.83s
pytest ./tests/integration/models/test_google_llm.py	5 passed, 2 warnings in 3.73s

Manual Testing

Here is a log of multi_tool_agent run with locally-built wheel and using Gemma model.

❯ adk run multi_tool_agent
Log setup complete: /var/folders/bg/_133c0ds2kb7cn699cpmmh_h0061bp/T/agents_log/agent.20250904_152617.log
To access latest log: tail -F /var/folders/bg/_133c0ds2kb7cn699cpmmh_h0061bp/T/agents_log/agent.latest.log
/Users/<redacted>/venvs/adk-quickstart/lib/python3.11/site-packages/google/adk/cli/cli.py:143: UserWarning: [EXPERIMENTAL] InMemoryCredentialService: This feature is experimental and may change or be removed in future versions without notice. It may introduce breaking changes at any time.
  credential_service = InMemoryCredentialService()
/Users/<redacted>/venvs/adk-quickstart/lib/python3.11/site-packages/google/adk/auth/credential_service/in_memory_credential_service.py:33: UserWarning: [EXPERIMENTAL] BaseCredentialService: This feature is experimental and may change or be removed in future versions without notice. It may introduce breaking changes at any time.
  super().__init__()
Running agent weather_time_agent, type exit to exit.
[user]: what's the weather like today?
[weather_time_agent]: Which city are you asking about?

[user]: new york
[weather_time_agent]: OK. The weather in New York is sunny with a temperature of 25 degrees Celsius (77 degrees Fahrenheit).

And here is a snippet of a log generated with DEBUG level logging of the hello_world_gemma sample. It demonstrates how function calls are extracted and inserted based on Gemma model interactions:

...
2025-09-04 15:32:41,708 - DEBUG - google_llm.py:138 -
LLM Request:
-----------------------------------------------------------
System Instruction:
None
-----------------------------------------------------------
Contents:
{"parts":[{"text":"\n      You roll dice and answer questions about the outcome of the dice rolls.\n      You can roll dice of different sizes...\n"}],"role":"user"}
{"parts":[{"text":"Hi, introduce yourself."}],"role":"user"}
{"parts":[{"text":"Hello! I am data_processing_agent, a hello world agent that can roll many-sided dice and check if numbers are prime. I'm ready to assist you with those tasks. Let's begin!\n\n\n\n"}],"role":"model"}
{"parts":[{"text":"Roll a die with 100 sides and check if it is prime"}],"role":"user"}
{"parts":[{"text":"{\"args\":{\"sides\":100},\"name\":\"roll_die\"}"}],"role":"model"}
{"parts":[{"text":"Invoking tool `roll_die` produced: `{\"result\": 82}`."}],"role":"user"}
{"parts":[{"text":"{\"args\":{\"nums\":[82]},\"name\":\"check_prime\"}"}],"role":"model"}
{"parts":[{"text":"Invoking tool `check_prime` produced: `{\"result\": \"No prime numbers found.\"}`."}],"role":"user"}
{"parts":[{"text":"The die roll was 82, and it is not a prime number.\n\n\n\n"}],"role":"model"}
{"parts":[{"text":"Roll it again."}],"role":"user"}
-----------------------------------------------------------
Functions:

-----------------------------------------------------------

2025-09-04 15:32:41,708 - INFO - models.py:8165 - AFC is enabled with max remote calls: 10.
2025-09-04 15:32:42,693 - INFO - google_llm.py:180 - Response received from the model.
2025-09-04 15:32:42,693 - DEBUG - google_llm.py:181 -
LLM Response:
-----------------------------------------------------------
Text:
{"args":{"sides":100},"name":"roll_die"}
-----------------------------------------------------------
...

[gemini-code-assist]

Summary of Changes

Hello @douglas-reid, 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 integrates the Gemma large language model into the system, enabling its use for agentic development through the existing Gemini API. The primary goal is to facilitate experimentation with Gemma models without requiring local deployment, by adapting the system to handle Gemma's specific requirements for system instructions and function calling. This involves converting function calls and responses into a text-based format that Gemma can process, and vice-versa, ensuring seamless interaction within agent workflows.

Highlights

• Gemma Model Integration: Adds full support for Gemma models, allowing them to be invoked via the Gemini API endpoint, expanding the range of available LLMs.
• Enhanced Agentic Functionality for Gemma: Introduces specialized callbacks (gemma_functions_before_model_callback and gemma_functions_after_model_callback) to extract and transform function calls and responses into user and model messages, enabling robust agentic behavior for Gemma models despite their unique function calling mechanisms.
• New 'Hello World' Agent Example: Includes a basic 'hello world' style agent example (hello_world_gemma) that demonstrates the proper functioning of Gemma models within an Agent container, utilizing dice roll and prime check tools.
• Streamlined Model Registration: The LLMRegistry has been updated to explicitly register both Gemini and Gemma models, simplifying the model registration process.
• Comprehensive Testing: Extensive unit and integration tests have been added and updated to ensure the correct functionality and robustness of the new Gemma model integration and its associated callbacks.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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. ↩

[adk-bot]

Response from ADK Triaging Agent

Hello @douglas-reid, thank you for creating this PR!

To help us track new features, could you please create a GitHub issue for this change and associate it with this PR?

This information will help reviewers to review your PR more efficiently. Thanks!

[gemini-code-assist]

Code Review

This pull request adds support for Gemma models via the Gemini API, including a new Gemma LLM class and callbacks to handle its text-based function-calling. An example agent and comprehensive tests are also included. The implementation is solid, with good test coverage. My feedback focuses on improving code quality and consistency, such as aligning the supported model definitions, making some code more Pythonic, and addressing minor style issues.

[douglas-reid]

@boyangsvl please take another look. thanks your time and patience.