This change:
- Introduces the LocalEvalService Class.
- Implements only the "perform_inference" method. Evaluate method will be implemented in the next CL.
- Adds required test coverage.
PiperOrigin-RevId: 781781954
This change integrates the plugin system with ADK. PluginManager is attached to the invocation context similar to session/artifact/memory.
It includes integrations with following ADK internal callbacks:
* App callbacks: Integrated in the BaseRunner class, in run_async and run_live
* On Message callbacks: Integrated in the BaseRunner class, triggers on run_async.
* Agent callbacks: Integrated in the BaseAgent class. Leveraging the existing *callback functions
* Model callbacks: Integrating in the base_llm_flow.
* Tool callbacks: Integrated in functions.py, wrapped around the code for agent tool_callbacks
Sample code to use plugins:
```python
# Add plugins to Runner
runner = Runner(
app_name="my-app",
agent=root_agent,
artifact_service=artifact_service,
session_service=session_service,
memory_service=memory_service,
plugins=[
MySamplePlugin(),
LoggingPlugin(),
],
)
```
PiperOrigin-RevId: 781746586
- 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
This commit includes a number of new tests for live streaming with function calls. These tests cover various scenarios:
- Single function calls
- Multiple function calls
- Parallel function calls
- Function calls with errors
- Synchronous function calls
- Simple streaming tools
- Video streaming tools
- Stopping a streaming tool
- Multiple streaming tools simultaneously
The tests use mock models and custom runners to simulate the interaction between the agent, model, and tools. They verify that function calls are correctly generated, executed, and that the expected data is returned.
PiperOrigin-RevId: 781318483
This would allow users to easily make a copy of the agents they built without having to add too much boilerplates. This promotes code reuse, modularity and testability of agents.
PiperOrigin-RevId: 781214379
This PR extends the existing Streaming tests to consider new configurations that have been added, including:
- `output_audio_transcription`
- `input_audio_transcription`
- `realtime_input_config`
- `enable_affective_dialog`
- `proactivity`
These configurations are tested individually and also combined, to cover all the possibilities, increasing the testing coverage and ensuring everything is working as expected.
In addition, the new configuration values are also validated to be sure they are properly initialized.
PiperOrigin-RevId: 780178334
test: refine test_session_state in test_session_state to catch event leakage
fix: revert app name to my_app for test_session_state test
style: fix pyink style warnings
fix: add app_name to filter as per suggestion from rpedela-recurly
We add a new metric for evaluating safety of Agent's response to ADK Eval. We delegate the actual implementation to Vertex Gen AI Eval SDK, so using this metric will require GCP project.
As a part of this change, we created (refactored) a simple Facade for vertex gen ai eval sdk.
PiperOrigin-RevId: 778580406
The LLM occasionally includes an unexpected 'parameters' argument when calling tools, specifically observed with 'transfer_to_agent'. This change makes FunctionTool.run_async more robust by filtering arguments against the function signature before invocation.
This resolves issue #1637.
Update test_function_tool.py
fix typing
fix: add `from __future__ import annotations`
Bug: When a model emits a stream of tokens, it sometimes emits a final chunk of whitespace or no content. The agent was trying to parse that content into JSON, causing a validation error.
Fix: If a model is expected to return JSON and the last streamed token is empty/whitespace, the agent will no longer try to parse it, and exit gracefully.
New unit tests confirm the scenario and the fix.
PiperOrigin-RevId: 777609415
This change adds a new enum value which the agent builder can pass in the `BigQueryToolConfig` to allow limited writes to the `execute_sql` tool.
PiperOrigin-RevId: 776661744
Fixes https://github.com/google/adk-python/issues/1180
We are using `func.now()` to set the `onupdate` time for db, when SQLAlchemy generates the SQL to build the database, it actually translates `func.now()` into `NOW()` or `CURRENT_TIMESTAMP`. The value it returns depends on the database server settings. For example, if the global/default timezone for a db is set to be UTC, the update time will be set to be a UCT time; if the global time zone for a db is set to be a local time zone (e.g. America/Los_Angeles), the update time will be a local time.
Normally, the best practice is to set database server to use UTC. Applications will convert it into different time zones as needed.
For SQLite, there is no way to config the default timezone, it will just treat it as UTC. But because it is a naive datetime (with no timezone info), python will assume it is a local time and then covert it into a UTC, which is why we see the bug (e.g. we create a session at 2025-06-17 12:49:33 local time, but when we read the session, its last update time is 2025-06-17 19:49:33 local time).
The solution is converting the native datatime to be timezone aware before `.timestamp()`.
The change in this CL only affects SQLite database.
PiperOrigin-RevId: 776654443
Copybara-Service
Sean Zhou
Ankur Sharma
Che Liu
Yanfei Chen
Liang Wu
Hangfei Lin
hironow
Joseph Pagadora
Sindri Snær Gunnarsson
google-labs-jules[bot]
Google Team Member
Xuan Yang
Keisuke Oohashi