Merge https://github.com/google/adk-python/pull/3170
Addresses Feature Request: #3116
This PR adds a `speech_config` to the **LLM Agent configuration** for the **live use case**. When an **asynchronous LLM** call is made to the **Gemini Live API**, it prioritizes the most specific agent configuration's speech_config. If that is null, it then uses the run configuration's speech_config. Unit tests have been added to verify this behavior.
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3170 from qyuo:bidi_agent_speech_config af1bd277d4f95c4a7d9aa0b16828ba3de826ce08
PiperOrigin-RevId: 822305427
changed the LiteLLM content conversion so Part.file_data.file_uri (like the gs://…) becomes a file object with file_id, making sure GCS-backed files reach LiteLLM proxies instead of being dropped add unit tests covering both _get_content and _content_to_message_param paths for file URIs
PiperOrigin-RevId: 817658432
Merge https://github.com/google/adk-python/pull/2857
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"}
-----------------------------------------------------------
...
```
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/2857 from douglas-reid:add-gemma-via-api e6d015f6a9ccbcf20ef7a7af8e4bbe1e9a5936b6
PiperOrigin-RevId: 816451001
Static instructions:
Always added to system instructions for context caching
Dynamic instructions:
Added to system instructions when no static instruction exists (for backward compatibility), OR inserted before last batch of continuous user content when static instructions exist
PiperOrigin-RevId: 809170679
1. add a context cache config in app level which will apply to all agents in the app
2. pass on cache config through invocation context to llm_reqeust
3. store cache metadata in llm_response
4. lookup old cache metadata from latest event for reusing old cache
5. create new cache if old cache cannot be reused
PiperOrigin-RevId: 809158578
Use full media types (image/jpeg, video/mp4, application/pdf) instead of suffixes (jpeg/mp4/pdf) when constructing LiteLLM payloads
This fxes compatibility with providers that validate media types (Anthropic)
Updated and added unit tests to assert full MIME types for image/video/pdf
PiperOrigin-RevId: 800685204
Merge https://github.com/google/adk-python/pull/2212
This PR closes issue #2202
ADK was not parsing the required attribute when using LiteLLM, letting the LLM decide what is required vs not, not respecting function definitions.
## Test Plan
There's a fork of adk-python that is being running live for over 2 weeks in our production environment with millions of requests per day.
Below you can find a screenshot of the unit tests passing. I've also added one change to the test cases to cover this scenario
<img width="1904" height="483" alt="image" src="https://github.com/user-attachments/assets/5a6eb069-63ae-45a3-baca-6b01543f56fb" />
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/2212 from thiagosalvatore:main 7de4037d8016389313f3fb22df40c12bac578523
PiperOrigin-RevId: 797393698
