Merge https://github.com/google/adk-python/pull/1130
This enables the use of the `model-optimizer-*` family of models in vertex, as per the [documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/vertex-ai-model-optimizer#using-vertex-ai-model-optimizer).
To use this, ensure your location is set to `global` and pass a model optimizer model to an agent:
```python
root_agent = Agent(
model="model-optimizer-exp-04-09",
name="fast_and_slow_agent",
instruction="Answer any question the user gives you - easy or hard.",
generate_content_config=types.GenerateContentConfig(
temperature=0.01,
model_selection_config=ModelSelectionConfig(
feature_selection_preference=FeatureSelectionPreference.BALANCED
# Options: PRIORITIZE_QUALITY, BALANCED, PRIORITIZE_COST
)
),
)
```
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/1130 from calvingiles:feat-model-optimizer 1a76bfa22420edb07d83415dcea6dd0114084e8e
PiperOrigin-RevId: 784921913
- Allow run_async to break on partial events instead of raising ValueError
- Generate aggregated streaming content regardless of finish_reason
- Add error_code and error_message to final streaming responses if model response is interrupted.
PiperOrigin-RevId: 781377328
Merge https://github.com/google/adk-python/pull/1451
## Description
Fixes https://github.com/google/adk-python/issues/1306 by using `async for` with `await self.llm_client.acompletion()` instead of synchronous `for` loop.
## Changes
- Updated test mocks to properly handle async streaming by creating an async generator
- Ensured proper parameter handling to avoid duplicate stream parameter
## Testing Plan
- All unit tests now pass with the async streaming implementation
- Verified with `pytest tests/unittests/models/test_litellm.py` that all streaming tests pass
- Manually tested with a sample agent using LiteLLM to confirm streaming works properly
# Test Evidence:
https://youtu.be/hSp3otI79DM
Let me know if you need anything else from me for this PR
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/1451 from avidelatm:fix/litellm-async-streaming d35b9dc90b2fd6fad44c3869de0fda2514e50055
PiperOrigin-RevId: 774835130
#non-breaking
The correct conversion from 25 degrees Celsius is 77 degrees Fahrenheit. The previous value of 41 was wrong.
PiperOrigin-RevId: 772528757
Merge https://github.com/google/adk-python/pull/981
issue: https://github.com/google/adk-python/issues/982
This pull request introduces a new configuration option, `realtime_input_config`, to the `RunConfig` class.
**Reason for this change:**
Currently, there is no direct way to configure real-time audio input behaviors, such as Voice Activity Detection (VAD), for live agents through the `RunConfig`. The Gemini API documentation (specifically [Configure automatic VAD](https://ai.google.dev/gemini-api/docs/live#configure-automatic-vad)) outlines parameters for VAD that users may want to customize.
This change enables users to pass these real-time input configurations, providing more granular control over the audio input for live agents.
**Changes made:**
- Added a new optional field `realtime_input_config: Optional[types.RealtimeInputConfig]` to the `RunConfig` class.
- The docstring for `realtime_input_config` has been added to explain its purpose.
**Example Usage (Conceptual):**
While the specific structure of `types.RealtimeInputConfig` would define the exact parameters, a user might configure it like this:
```python
# (Assuming types.RealtimeInputConfig and types.VadConfig are defined elsewhere)
# import your_project.types as types
run_config = RunConfig(
# ... other configurations ...
realtime_input_config=types.RealtimeInputConfig(
automatic_activity_detection =types.AutomaticActivityDetection(
# VAD specific parameters like sensitivity, endpoint_duration_millis etc.
# based on https://ai.google.dev/gemini-api/docs/live#configure-automatic-vad
)
# Potentially other real-time input settings could be added here in the future
)
)
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/981 from ammmr:patch-add-realtime-input-config b2e17fbf5742d264029ad49bf632422b5c5b1e0a
PiperOrigin-RevId: 770797640
Merge https://github.com/google/adk-python/pull/1211
### Description
When using the Google.GenAI backend (GEMINI_API), file uploads fail if the `file_data` or `inline_data` parts of the request contain a `display_name`. The Gemini API (non-Vertex) does not support this attribute, causing a `ValueError`.
This commit updates the `_preprocess_request` method in the `Gemini` class to sanitize the request. It now iterates through all content parts and sets `display_name` to `None` if the determined backend is `GEMINI_API`. This ensures compatibility, similar to the existing handling of the `labels` attribute.
Fixes#1182
### Testing Plan
**1. Unit Tests**
- Added a new parameterized test `test_preprocess_request_handles_backend_specific_fields` to `tests/unittests/models/test_google_llm.py`.
- This test verifies:
- When the backend is `GEMINI_API`, `display_name` in `file_data` and `inline_data` is correctly set to `None`.
- When the backend is `VERTEX_AI`, `display_name` remains unchanged.
- All unit tests passed successfully.
```shell
pytest ./tests/unittests/models/test_google_llm.py ░▒▓ ✔ adk-python base system 21:14:02
============================================================================================ test session starts ============================================================================================
platform darwin -- Python 3.12.10, pytest-8.3.5, pluggy-1.6.0
rootdir: /Users/leo/PycharmProjects/adk-python
configfile: pyproject.toml
plugins: anyio-4.9.0, langsmith-0.3.42, asyncio-0.26.0, mock-3.14.0, xdist-3.6.1
asyncio: mode=Mode.AUTO, asyncio_default_fixture_loop_scope=function, asyncio_default_test_loop_scope=function
collected 20 items
tests/unittests/models/test_google_llm.py .................... [100%]
============================================================================================ 20 passed in 3.19s =============================================================================================
```
**2. Manual End-to-End (E2E) Test**
I manually verified the fix using `adk web`. The test was configured to use a **Google AI Studio API key**, which is the scenario where the bug occurs.
- **Before the fix:**
When uploading a file, the request failed with the error: `{"error": "display_name parameter is not supported in Gemini API."}`. This confirms the bug.
<img width="968" alt="Screenshot 2025-06-06 at 21 22 35" src="https://github.com/user-attachments/assets/f1ab2db2-d5ec-40fc-a182-9932562b21e1" />
- **After the fix:**
With the patch applied, the same file upload was processed successfully. The agent correctly analyzed the file and responded without errors.
<img width="973" alt="Screenshot 2025-06-06 at 21 23 24" src="https://github.com/user-attachments/assets/e03228f6-0b7d-4bf9-955a-ac24efb4fb72" />
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/1211 from ystory:fix/display-name d3efebe74aca635a7a255063e64f07cc44016f05
PiperOrigin-RevId: 769278445
Even though litellm type definitions and openai API specifies content as list of dictionaries (with type and relevant attributes potentially to allow multimodal inputs/outputs in addition to text), ollama has been demonstrating marshal errors. As a workaround this change simplifies the content as string when there is no more than one content part.
Fixes#642, #928, #376
PiperOrigin-RevId: 766890141
This is in response to the litellm v1.71.2 + ollama v0.9.0 sending function call chunks with 0 indices across multiple calls and lacking call ids.
Solutions introduced:
1. increment fallback index when accumulated arg becomes json parsable.
2. tolerate finish reason == stop when tool calls are present
3. fallback to index when tool call id is None
Fixes https://github.com/google/adk-python/issues/294
PiperOrigin-RevId: 766258344
--
cef3ca1ed3493eebaeab3e03bdf5e56b35c0b8ef by Lucas Nobre <lucaas.sn@gmail.com>:
feat: Add index tracking to handle parallel tool call using litellm
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/759 from lucasnobre212:fix/issue_484 65e22934bf839f9ea03963b9ec6c23fdce03f59f
PiperOrigin-RevId: 764902433
Copybara import of the project:
--
79962881ca1c17eb6d7bd9dcf31a44df93c9badd by Almas Akchabayev <almas.akchabayev@gmail.com>:
fix: separate thinking from text parts in streaming mode
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/777 from almeynman:separate-thinking-and-text-parts-in-stream-mode b63dcc7fd0fc3973888dcbb9d4cc7e7e0a66e7f7
PiperOrigin-RevId: 764561932
