wehub/google--adk-python
1
0
Fork 0
Code Issues Pull Requests Actions 6 Deployments Models Agent Notes Packages Projects Releases Wiki Activity

chore: import upstream snapshot with attribution
Continuous Integration / Pre-commit Linter (push) Has been cancelled
Details
Continuous Integration / Mypy Check (Python 3.10) (push) Has been cancelled
Details
Continuous Integration / Mypy Check (Python 3.11) (push) Has been cancelled
Details
Continuous Integration / Mypy Check (Python 3.12) (push) Has been cancelled
Details
Continuous Integration / Mypy Check (Python 3.13) (push) Has been cancelled
Details
Continuous Integration / Unit Tests (Python 3.10) (push) Has been cancelled
Details
Continuous Integration / Unit Tests (Python 3.11) (push) Has been cancelled
Details
Continuous Integration / Unit Tests (Python 3.12) (push) Has been cancelled
Details
Continuous Integration / Unit Tests (Python 3.13) (push) Has been cancelled
Details
Continuous Integration / Unit Tests (Python 3.14) (push) Has been cancelled
Details
Continuous Integration / A2A v0.3 Tests (Python 3.10) (push) Has been cancelled
Details
Continuous Integration / A2A v0.3 Tests (Python 3.11) (push) Has been cancelled
Details
Continuous Integration / A2A v0.3 Tests (Python 3.12) (push) Has been cancelled
Details
Copybara PR Handler / close-imported-pr (push) Has been cancelled
Details
Continuous Integration / A2A v0.3 Tests (Python 3.13) (push) Has been cancelled
Details
Continuous Integration / A2A v0.3 Tests (Python 3.14) (push) Has been cancelled
Details

Browse Source
This commit is contained in:
wehub-resource-sync
2026-07-13 13:25:13 +08:00
commit ec2b666284
2231 changed files with 491535 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/integration/fixture/__init__.py
+13
View File
@@ -0,0 +1,13 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
tests/integration/fixture/agent_with_config/__init__.py
+15
View File
@@ -0,0 +1,15 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from . import agent
tests/integration/fixture/agent_with_config/agent.py
+88
View File
@@ -0,0 +1,88 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from google.adk import Agent
from google.genai import types
new_message = types.Content(
role="user",
parts=[types.Part.from_text(text="Count a number")],
)
google_agent_1 = Agent(
model="gemini-2.5-flash",
name="agent_1",
description="The first agent in the team.",
instruction="Just say 1",
generate_content_config=types.GenerateContentConfig(
temperature=0.1,
),
)
google_agent_2 = Agent(
model="gemini-2.5-flash",
name="agent_2",
description="The second agent in the team.",
instruction="Just say 2",
generate_content_config=types.GenerateContentConfig(
temperature=0.2,
safety_settings=[{
"category": "HARM_CATEGORY_HATE_SPEECH",
"threshold": "BLOCK_ONLY_HIGH",
}],
),
)
google_agent_3 = Agent(
model="gemini-2.5-flash",
name="agent_3",
description="The third agent in the team.",
instruction="Just say 3",
generate_content_config=types.GenerateContentConfig(
temperature=0.5,
safety_settings=[{
"category": "HARM_CATEGORY_DANGEROUS_CONTENT",
"threshold": "BLOCK_NONE",
}],
),
)
google_agent_with_instruction_in_config = Agent(
model="gemini-2.5-flash",
name="agent",
generate_content_config=types.GenerateContentConfig(
temperature=0.5, system_instruction="Count 1"
),
)
def function():
pass
google_agent_with_tools_in_config = Agent(
model="gemini-2.5-flash",
name="agent",
generate_content_config=types.GenerateContentConfig(
temperature=0.5, tools=[function]
),
)
google_agent_with_response_schema_in_config = Agent(
model="gemini-2.5-flash",
name="agent",
generate_content_config=types.GenerateContentConfig(
temperature=0.5, response_schema={"key": "value"}
),
)
tests/integration/fixture/bigquery_agent/README.md
+67
View File
@@ -0,0 +1,67 @@
# Instructions
## Run Evaluation
1. Set environment variables in your terminal:
```shell
export GOOGLE_GENAI_USE_ENTERPRISE=FALSE
export GOOGLE_API_KEY=<your_api_key>
export GOOGLE_CLOUD_PROJECT=<your_bigquery_project>
```
1. Change to the current directory:
```shell
cd tests/integration/fixture/bigquery_agent/
```
1. Customize the evaluation dataset to the environment `GOOGLE_CLOUD_PROJECT`
by replacing the placeholder to the real project set in your environment:
```shell
sed -e "s:\${GOOGLE_CLOUD_PROJECT}:${GOOGLE_CLOUD_PROJECT}:g" simple.test.json -i
```
1. Run the following command as per https://google.github.io/adk-docs/evaluate/#3-adk-eval-run-evaluations-via-the-cli:
```shell
adk eval . simple.test.json --config_file_path=test_config.json
```
If it fails, re-run with `--print_detailed_results` flag to see more details
on turn-by-turn evaluation.
## Generate Evaluation dataset
1. Set environment variables in your terminal:
```shell
export GOOGLE_GENAI_USE_ENTERPRISE=FALSE
export GOOGLE_API_KEY=<your_api_key>
export GOOGLE_CLOUD_PROJECT=<your_bigquery_project>
```
1. Set up google [application default credentials](https://cloud.google.com/docs/authentication/provide-credentials-adc)
on your machine.
```shell
gcloud auth application-default login
```
1. Change to the directory containing agent folder:
```shell
cd tests/integration/fixture/
```
1. Run the following command to start the ADK web app:
```shell
adk web
```
1. Open the ADK web UI in your browser http://127.0.0.1:8000/dev-ui/?app=bigquery_agent.
1. Create an evaluation dataset by following [these steps](https://google.github.io/adk-docs/evaluate/#1-adk-web-run-evaluations-via-the-web-ui).
This would generate file `bigquery_agent/simple.evalset.json`.
1. Note that this evaluation data would be tied to the agent interaction in the
`GOOGLE_CLOUD_PROJECT` set in your environment. To normalize it by replacing
the real project set in your environment to a placeholder, let's run the
following command:
```shell
sed -e "s:${GOOGLE_CLOUD_PROJECT}:\${GOOGLE_CLOUD_PROJECT}:g" bigquery_agent/simple.evalset.json > bigquery_agent/simple.test.json
```
tests/integration/fixture/bigquery_agent/__init__.py
+15
View File
@@ -0,0 +1,15 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from . import agent
tests/integration/fixture/bigquery_agent/agent.py
+75
View File
@@ -0,0 +1,75 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import os
from google.adk.agents.llm_agent import LlmAgent
from google.adk.tools.bigquery.bigquery_credentials import BigQueryCredentialsConfig
from google.adk.tools.bigquery.bigquery_toolset import BigQueryToolset
from google.adk.tools.bigquery.config import BigQueryToolConfig
from google.adk.tools.bigquery.config import WriteMode
import google.auth
# Check necessary environment variables
if not (google_cloud_project_id := os.getenv("GOOGLE_CLOUD_PROJECT")):
raise ValueError(
"GOOGLE_CLOUD_PROJECT environment variable is not set. Please set it"
" to the GCP project ID where your BigQuery jobs would be run."
)
# Define an appropriate application name
BIGQUERY_AGENT_NAME = "adk_eval_bigquery_agent"
# Define BigQuery tool config with write mode set to allowed. Note that this is
# only to demonstrate the full capability of the BigQuery tools. In production
# you may want to change to BLOCKED (default write mode, effectively makes the
# tool read-only) or PROTECTED (only allows writes in the anonymous dataset of a
# BigQuery session) write mode.
tool_config = BigQueryToolConfig(
write_mode=WriteMode.BLOCKED,
application_name=BIGQUERY_AGENT_NAME,
compute_project_id=google_cloud_project_id,
)
# Initialize the tools to use the application default credentials.
# https://cloud.google.com/docs/authentication/provide-credentials-adc
application_default_credentials, _ = google.auth.default()
credentials_config = BigQueryCredentialsConfig(
credentials=application_default_credentials
)
bigquery_toolset = BigQueryToolset(
credentials_config=credentials_config, bigquery_tool_config=tool_config
)
# The variable name `root_agent` determines what your root agent is for the
# debug CLI
root_agent = LlmAgent(
model="gemini-2.5-flash",
name=BIGQUERY_AGENT_NAME,
description=(
"Agent to answer questions about BigQuery data and models and execute"
" SQL queries."
),
instruction=f"""\
You are a data science agent with access to several BigQuery tools.
Make use of those tools to answer the user's questions.
You must use the project id {google_cloud_project_id} for running SQL
queries and generating data insights
""",
tools=[bigquery_toolset],
)
tests/integration/fixture/bigquery_agent/simple.test.json
+538
View File
@@ -0,0 +1,538 @@
{
"eval_set_id": "simple",
"name": "simple",
"description": null,
"eval_cases": [
{
"eval_id": "penguins exploration",
"conversation": [
{
"invocation_id": "e-81734a2f-60dc-4c7e-9b05-29a2c18b7651",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "Hi, what can you do?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "I can help you with BigQuery. I can:\n* List datasets and tables in a project\n* Get information about datasets and tables\n* Execute SQL queries\n* Forecast time series data\n* Answer questions about data in BigQuery tables using natural language.\n\nWhat would you like to do?\n"
}
],
"role": null
},
"intermediate_data": {
"tool_uses": [],
"tool_responses": [],
"intermediate_responses": []
},
"creation_timestamp": 1757645225.080524
},
{
"invocation_id": "e-78026d6b-f3d5-4807-8122-8872efb024d6",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "which tools do you have access to?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": "CqsCAdHtim-ZZuTPQdEgbCYXWniB28PuU35grogIwz7a2X0PG9eopcLAT0hXOv90Zu5b9Q4iREsIAcV3znUrCjwMwRrW_G3QYH7jfaK5oEvunfD-yOUj-V9wjc_hAyKon4ogXs7nxX9v_sAfz1uh48cmiMBcNcJd1dkiBbCufChWQbHFsVghXAnetSRm21H2rRgPuxvpf4_mWXzxgYZddOuf6bYmUI3kEcwQDqbocOk2u-ghG44KnFAXOhqBBu8eUeJM8m7uUWevEtxXIclJ14crWCjWADzAof80VX_rLucQ5sPE5wfTvlFIDECuGapnxmxAVB8hNCw9iwlJEhNUVVSbPPfvjwDSq9s99w-Rbu8yLDA5YwSru-q1qIrxbXTWuNlh9fwCdKDQAgiXUo0=",
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "I have access to the following tools:\n\n* `get_dataset_info(project_id, dataset_id)`: Get metadata information about a BigQuery dataset.\n* `get_table_info(project_id, dataset_id, table_id)`: Get metadata information about a BigQuery table.\n* `list_dataset_ids(project_id)`: List BigQuery dataset IDs in a Google Cloud project.\n* `list_table_ids(project_id, dataset_id)`: List table IDs in a BigQuery dataset.\n* `execute_sql(project_id, query)`: Run a BigQuery or BigQuery ML SQL query in the project and return the result.\n* `forecast(project_id, history_data, timestamp_col, data_col, horizon, id_cols=None)`: Run a BigQuery AI time series forecast using AI.FORECAST.\n* `ask_data_insights(project_id, user_query_with_context, table_references)`: Answers questions about structured data in BigQuery tables using natural language."
}
],
"role": null
},
"intermediate_data": {
"tool_uses": [],
"tool_responses": [],
"intermediate_responses": []
},
"creation_timestamp": 1757645280.602244
},
{
"invocation_id": "e-47aa5d37-6bba-4a2d-8eae-e79f47f347c4",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "Are there any ML datasets in the bigquery public data?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": "Cq8DAdHtim9T93wEXUnP9hCJ0SGm79kvsT5VJBWIL1xr8Z0TBLYIQSVqogdU3mB3XkwHkqKT7hBGBY11yuHwfcohBakiOco71gRXOlhf0XGlNZNIUUObnOdY2swLsmpJDbOtRLxgU9OZ0JhHlC0fkrQj9Ab2wt5A8VFkuBUQaEB-XcJYes8Zo0TfU79nrlKrfIINPHsXEuBdq4biDipPss57EZwgs8HiwdeUCXeMwcYS1NFquYUmFLqnsAf9Xik5k3yEx9iQyF7VtOPNGp9sKC2zh7Euz5bpgiHjRTV41hw5QWQk8Q38hKOS7G2jLLXPO8v63sn9LgIzCHNJUd9j-IU8v5gtgU9CNfG4o7icU7GD77KrJx6etaxHQiwSfMjPR_6tZ_ft4-eIh7kRQdJo-GrtyDJJBNV-5s61G0qMGqbS7JY4RfH5_cT8UUSEamkU1eJGN7pZIAKc7FXaCHlGUOQClx-9D7XXQMDd2gVk1pyQvMeruzmykywSGPffnDZJQ9kVwW9pl6urnk8hX4ZGnXM_DTjaFZFF_Gb1dhpr0Uuy0LWk1IqcfbS95YJIFipFXPo=",
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "Yes, there are a few ML-related datasets in the `bigquery-public-data` project:\n\n* `aml_ai_input_dataset`\n* `bigqueryml_ncaa`\n* `ml_datasets`\n* `ml_datasets_uscentral1`"
}
],
"role": null
},
"intermediate_data": {
"tool_uses": [
{
"id": "adk-4d524ad4-6a3b-49dd-a44e-763f956f89c1",
"args": {
"project_id": "bigquery-public-data"
},
"name": "list_dataset_ids"
}
],
"tool_responses": [],
"intermediate_responses": []
},
"creation_timestamp": 1757645323.568069
},
{
"invocation_id": "e-76115967-fe7b-4aee-92c8-39d3fd1b35c0",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "When was ml_datasets created and which location it is in?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "The `ml_datasets` dataset was created on `1553208775542` (which is March 21, 2019, 19:12:55 UTC) and is located in the `US` region."
}
],
"role": null
},
"intermediate_data": {
"tool_uses": [
{
"id": "adk-2cba4269-dde6-4b62-a38a-1004f05452a0",
"args": {
"dataset_id": "ml_datasets",
"project_id": "bigquery-public-data"
},
"name": "get_dataset_info"
}
],
"tool_responses": [],
"intermediate_responses": []
},
"creation_timestamp": 1757645409.36703
},
{
"invocation_id": "e-9a5e0a24-f7cb-4e50-9a61-430a11837e82",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "alright, which tables does it have?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "The `ml_datasets` dataset contains the following tables:\n\n* `census_adult_income`\n* `census_adult_income_kmeans_predictions`\n* `credit_card_default`\n* `holidays_and_events_for_forecasting`\n* `iris`\n* `penguins`\n* `ulb_fraud_detection`"
}
],
"role": null
},
"intermediate_data": {
"tool_uses": [
{
"id": "adk-089bf143-422f-4516-b6d9-810773b03de7",
"args": {
"dataset_id": "ml_datasets",
"project_id": "bigquery-public-data"
},
"name": "list_table_ids"
}
],
"tool_responses": [],
"intermediate_responses": []
},
"creation_timestamp": 1757645478.923206
},
{
"invocation_id": "e-05b241ed-9678-49dc-8ead-25baab6d4002",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "tell me more details about the penguins table"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "The `penguins` table was created on `1619804743188` (which is April 30, 2021, 00:25:43 UTC) and contains 344 rows. It has the following schema:\n\n* `species`: STRING (REQUIRED)\n* `island`: STRING (NULLABLE)\n* `culmen_length_mm`: FLOAT (NULLABLE)\n* `culmen_depth_mm`: FLOAT (NULLABLE)\n* `flipper_length_mm`: FLOAT (NULLABLE)\n* `body_mass_g`: FLOAT (NULLABLE)\n* `sex`: STRING (NULLABLE)"
}
],
"role": null
},
"intermediate_data": {
"tool_uses": [
{
"id": "adk-8893d916-9445-4458-8998-ea3e283d534d",
"args": {
"dataset_id": "ml_datasets",
"project_id": "bigquery-public-data",
"table_id": "penguins"
},
"name": "get_table_info"
}
],
"tool_responses": [],
"intermediate_responses": []
},
"creation_timestamp": 1757645526.958228
},
{
"invocation_id": "e-d7b85acb-b7f3-4b61-b66d-bba77c01e13e",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "can you tell me population of penguins per island?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "Here is the population of penguins per island:\n\n* **Dream:** 124\n* **Biscoe:** 168\n* **Torgersen:** 52"
}
],
"role": null
},
"intermediate_data": {
"tool_uses": [
{
"id": "adk-33ff1809-bbfb-45e7-a07c-25fc9c932260",
"args": {
"query": "SELECT island, COUNT(*) AS population FROM bigquery-public-data.ml_datasets.penguins GROUP BY island",
"project_id": "${GOOGLE_CLOUD_PROJECT}"
},
"name": "execute_sql"
}
],
"tool_responses": [],
"intermediate_responses": []
},
"creation_timestamp": 1757645563.777316
},
{
"invocation_id": "e-3b46dd99-4d25-45e5-b16c-2f055de56f47",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "can you get me insights about any correlation between body mass and flipper length of penguins?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "Based on the data, there appears to be a positive correlation between the body mass and flipper length of penguins. Generally, as the flipper length in millimeters increases, the body mass in grams also tends to increase."
}
],
"role": null
},
"intermediate_data": {
"tool_uses": [
{
"id": "adk-266b6452-50b8-4d3b-ae23-d09effa41e0b",
"args": {
"project_id": "${GOOGLE_CLOUD_PROJECT}",
"user_query_with_context": "Is there any correlation between body mass and flipper length of penguins?",
"table_references": [
{
"datasetId": "ml_datasets",
"tableId": "penguins",
"projectId": "bigquery-public-data"
}
]
},
"name": "ask_data_insights"
}
],
"tool_responses": [],
"intermediate_responses": []
},
"creation_timestamp": 1757645706.447186
},
{
"invocation_id": "e-357fb858-adae-4a7c-80fc-fcadf52a20fd",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "how do the penguins tables in ml_datasets and ml_datasets_uscentral compare?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "Here's a comparison of the `penguins` tables in `ml_datasets` and `ml_datasets_uscentral1`:\n\n**`bigquery-public-data:ml_datasets.penguins`**\n\n* **Creation Time:** 1619804743188 (April 30, 2021, 00:25:43 UTC)\n* **Location:** US\n* **Number of Rows:** 344\n* **Schema:**\n * `species`: STRING (REQUIRED)\n * `island`: STRING (NULLABLE)\n * `culmen_length_mm`: FLOAT (NULLABLE)\n * `culmen_depth_mm`: FLOAT (NULLABLE)\n * `flipper_length_mm`: FLOAT (NULLABLE)\n * `body_mass_g`: FLOAT (NULLABLE)\n * `sex`: STRING (NULLABLE)\n\n**`bigquery-public-data:ml_datasets_uscentral1.penguins`**\n\n* **Creation Time:** 1634583926374 (October 18, 2021, 23:05:26 UTC)\n* **Location:** us-central1\n* **Number of Rows:** 344\n* **Schema:** (Identical to `ml_datasets.penguins`)\n * `species`: STRING (REQUIRED)\n * `island`: STRING (NULLABLE)\n * `culmen_length_mm`: FLOAT (NULLABLE)\n * `culmen_depth_mm`: FLOAT (NULLABLE)\n * `flipper_length_mm`: FLOAT (NULLABLE)\n * `body_mass_g`: FLOAT (NULLABLE)\n * `sex`: STRING (NULLABLE)\n\n**Key Differences:**\n\n* **Creation Time:** The table in `ml_datasets` was created earlier (April 2021) than the one in `ml_datasets_uscentral1` (October 2021).\n* **Location:** The `ml_datasets.penguins` table is in the `US` multi-region, while `ml_datasets_uscentral1.penguins` is specifically in the `us-central1` region.\n\n**Similarities:**\n\n* Both tables have the **same number of rows (344)**.\n* Both tables have an **identical schema**, with the same column names, types, and modes.\n\nIt appears that `bigquery-public-data:ml_datasets_uscentral1.penguins` is likely a regional copy or a later version of the `bigquery-public-data:ml_datasets.penguins` table."
}
],
"role": null
},
"intermediate_data": {
"tool_uses": [
{
"id": "adk-8ff49a41-b42a-4f2b-8408-bda00712791b",
"args": {
"project_id": "bigquery-public-data",
"dataset_id": "ml_datasets",
"table_id": "penguins"
},
"name": "get_table_info"
},
{
"id": "adk-c0e9a831-300d-4805-a127-6df1d7afc712",
"args": {
"project_id": "bigquery-public-data",
"dataset_id": "ml_datasets_uscentral1",
"table_id": "penguins"
},
"name": "get_table_info"
}
],
"tool_responses": [],
"intermediate_responses": []
},
"creation_timestamp": 1757646232.887191
},
{
"invocation_id": "e-72ddf0dd-4fee-41dd-adb6-26cd98baeb25",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "can you tell the population per island from the uscentral1 table?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "Here is the population of penguins per island from the `ml_datasets_uscentral1` table:\n\n* **Dream:** 124\n* **Biscoe:** 168\n* **Torgersen:** 52"
}
],
"role": null
},
"intermediate_data": {
"tool_uses": [
{
"id": "adk-febf7cf1-3465-4393-9882-ef860502238f",
"args": {
"project_id": "${GOOGLE_CLOUD_PROJECT}",
"query": "SELECT island, COUNT(*) AS population FROM `bigquery-public-data`.`ml_datasets_uscentral1`.`penguins` GROUP BY island"
},
"name": "execute_sql"
}
],
"tool_responses": [],
"intermediate_responses": []
},
"creation_timestamp": 1757646339.73431
}
],
"session_input": {
"app_name": "bigquery_agent",
"user_id": "user",
"state": {}
},
"creation_timestamp": 1757648114.6285758
}
],
"creation_timestamp": 1757648101.7927744
}
tests/integration/fixture/bigquery_agent/test_config.json
+6
View File
@@ -0,0 +1,6 @@
{
"criteria": {
"tool_trajectory_avg_score": 0.7,
"response_match_score": 0.7
}
}
tests/integration/fixture/callback_agent/__init__.py
+15
View File
@@ -0,0 +1,15 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from . import agent
tests/integration/fixture/callback_agent/agent.py
+105
View File
@@ -0,0 +1,105 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from typing import Optional
from google.adk.agents.callback_context import CallbackContext
from google.adk.agents.invocation_context import InvocationContext
from google.adk.agents.llm_agent import Agent
from google.adk.models.llm_request import LlmRequest
from google.adk.models.llm_response import LlmResponse
from google.genai import types
def before_agent_call_end_invocation(
callback_context: CallbackContext,
) -> types.Content:
return types.Content(
role='model',
parts=[types.Part(text='End invocation event before agent call.')],
)
def before_agent_call(
invocation_context: InvocationContext,
) -> types.Content:
return types.Content(
role='model',
parts=[types.Part.from_text(text='Plain text event before agent call.')],
)
def before_model_call_end_invocation(
callback_context: CallbackContext, llm_request: LlmRequest
) -> LlmResponse:
return LlmResponse(
content=types.Content(
role='model',
parts=[
types.Part.from_text(
text='End invocation event before model call.'
)
],
)
)
def before_model_call(
invocation_context: InvocationContext, request: LlmRequest
) -> LlmResponse:
request.config.system_instruction = 'Just return 999 as response.'
return LlmResponse(
content=types.Content(
role='model',
parts=[
types.Part.from_text(
text='Update request event before model call.'
)
],
)
)
def after_model_call(
callback_context: CallbackContext,
llm_response: LlmResponse,
) -> Optional[LlmResponse]:
content = llm_response.content
if not content or not content.parts or not content.parts[0].text:
return
content.parts[0].text += 'Update response event after model call.'
return llm_response
before_agent_callback_agent = Agent(
model='gemini-2.5-flash',
name='before_agent_callback_agent',
instruction='echo 1',
before_agent_callback=before_agent_call_end_invocation,
)
before_model_callback_agent = Agent(
model='gemini-2.5-flash',
name='before_model_callback_agent',
instruction='echo 2',
before_model_callback=before_model_call_end_invocation,
)
after_model_callback_agent = Agent(
model='gemini-2.5-flash',
name='after_model_callback_agent',
instruction='Say hello',
after_model_callback=after_model_call,
)
tests/integration/fixture/context_update_test/__init__.py
+15
View File
@@ -0,0 +1,15 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from . import agent
tests/integration/fixture/context_update_test/agent.py
+43
View File
@@ -0,0 +1,43 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from typing import List
from typing import Union
from google.adk import Agent
from google.adk.tools.tool_context import ToolContext
from pydantic import BaseModel
def update_fc(
data_one: str,
data_two: Union[int, float, str],
data_three: list[str],
data_four: List[Union[int, float, str]],
tool_context: ToolContext,
):
"""Simply ask to update these variables in the context"""
tool_context.actions.update_state("data_one", data_one)
tool_context.actions.update_state("data_two", data_two)
tool_context.actions.update_state("data_three", data_three)
tool_context.actions.update_state("data_four", data_four)
root_agent = Agent(
model="gemini-2.5-flash",
name="root_agent",
instruction="Call tools",
flow="auto",
tools=[update_fc],
)
tests/integration/fixture/context_update_test/successful_test.session.json
+582
View File
@@ -0,0 +1,582 @@
{
"id": "ead43200-b575-4241-9248-233b4be4f29a",
"context": {
"_time": "2024-12-01 09:02:43.531503",
"data_one": "RRRR",
"data_two": "3.141529",
"data_three": [
"apple",
"banana"
],
"data_four": [
"1",
"hello",
"3.14"
]
},
"events": [
{
"invocation_id": "6BGrtKJu",
"author": "user",
"content": {
"parts": [
{
"text": "hi"
}
],
"role": "user"
},
"options": {},
"id": "ltzQTqR4",
"timestamp": 1733043686.8428597
},
{
"invocation_id": "6BGrtKJu",
"author": "root_agent",
"content": {
"parts": [
{
"text": "Hello! 👋 How can I help you today? \n"
}
],
"role": "model"
},
"options": {
"partial": false
},
"id": "ClSROx8b",
"timestamp": 1733043688.1030986
},
{
"invocation_id": "M3dUcVa8",
"author": "user",
"content": {
"parts": [
{
"text": "update data_one to be RRRR, data_two to be 3.141529, data_three to be apple and banana, data_four to be 1, hello, and 3.14"
}
],
"role": "user"
},
"options": {},
"id": "yxigGwIZ",
"timestamp": 1733043745.9900541
},
{
"invocation_id": "M3dUcVa8",
"author": "root_agent",
"content": {
"parts": [
{
"function_call": {
"args": {
"data_four": [
"1",
"hello",
"3.14"
],
"data_two": "3.141529",
"data_three": [
"apple",
"banana"
],
"data_one": "RRRR"
},
"name": "update_fc"
}
}
],
"role": "model"
},
"options": {
"partial": false
},
"id": "8V6de8th",
"timestamp": 1733043747.4545543
},
{
"invocation_id": "M3dUcVa8",
"author": "root_agent",
"content": {
"parts": [
{
"function_response": {
"name": "update_fc",
"response": {}
}
}
],
"role": "user"
},
"options": {
"update_context": {
"data_one": "RRRR",
"data_two": "3.141529",
"data_three": [
"apple",
"banana"
],
"data_four": [
"1",
"hello",
"3.14"
]
},
"function_call_event_id": "8V6de8th"
},
"id": "dkTj5v8B",
"timestamp": 1733043747.457031
},
{
"invocation_id": "M3dUcVa8",
"author": "root_agent",
"content": {
"parts": [
{
"text": "OK. I've updated the data. Anything else? \n"
}
],
"role": "model"
},
"options": {
"partial": false
},
"id": "OZ77XR41",
"timestamp": 1733043748.7901294
}
],
"past_events": [],
"pending_events": {},
"artifacts": {},
"event_logs": [
{
"invocation_id": "6BGrtKJu",
"event_id": "ClSROx8b",
"model_request": {
"model": "gemini-2.5-flash",
"contents": [
{
"parts": [
{
"text": "hi"
}
],
"role": "user"
}
],
"config": {
"system_instruction": "You are an agent. Your name is root_agent.\nCall tools",
"tools": [
{
"function_declarations": [
{
"description": "Hello",
"name": "update_fc",
"parameters": {
"type": "OBJECT",
"properties": {
"data_one": {
"type": "STRING"
},
"data_two": {
"type": "STRING"
},
"data_three": {
"type": "ARRAY",
"items": {
"type": "STRING"
}
},
"data_four": {
"type": "ARRAY",
"items": {
"any_of": [
{
"type": "INTEGER"
},
{
"type": "NUMBER"
},
{
"type": "STRING"
}
],
"type": "STRING"
}
}
}
}
}
]
}
]
}
},
"model_response": {
"candidates": [
{
"content": {
"parts": [
{
"text": "Hello! 👋 How can I help you today? \n"
}
],
"role": "model"
},
"avg_logprobs": -0.15831730915949896,
"finish_reason": "STOP",
"safety_ratings": [
{
"category": "HARM_CATEGORY_HATE_SPEECH",
"probability": "NEGLIGIBLE",
"probability_score": 0.071777344,
"severity": "HARM_SEVERITY_NEGLIGIBLE",
"severity_score": 0.07080078
},
{
"category": "HARM_CATEGORY_DANGEROUS_CONTENT",
"probability": "NEGLIGIBLE",
"probability_score": 0.16308594,
"severity": "HARM_SEVERITY_NEGLIGIBLE",
"severity_score": 0.14160156
},
{
"category": "HARM_CATEGORY_HARASSMENT",
"probability": "NEGLIGIBLE",
"probability_score": 0.09423828,
"severity": "HARM_SEVERITY_NEGLIGIBLE",
"severity_score": 0.037841797
},
{
"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
"probability": "NEGLIGIBLE",
"probability_score": 0.059326172,
"severity": "HARM_SEVERITY_NEGLIGIBLE",
"severity_score": 0.02368164
}
]
}
],
"model_version": "gemini-2.5-flash",
"usage_metadata": {
"candidates_token_count": 13,
"prompt_token_count": 32,
"total_token_count": 45
}
}
},
{
"invocation_id": "M3dUcVa8",
"event_id": "8V6de8th",
"model_request": {
"model": "gemini-2.5-flash",
"contents": [
{
"parts": [
{
"text": "hi"
}
],
"role": "user"
},
{
"parts": [
{
"text": "Hello! 👋 How can I help you today? \n"
}
],
"role": "model"
},
{
"parts": [
{
"text": "update data_one to be RRRR, data_two to be 3.141529, data_three to be apple and banana, data_four to be 1, hello, and 3.14"
}
],
"role": "user"
}
],
"config": {
"system_instruction": "You are an agent. Your name is root_agent.\nCall tools",
"tools": [
{
"function_declarations": [
{
"description": "Hello",
"name": "update_fc",
"parameters": {
"type": "OBJECT",
"properties": {
"data_one": {
"type": "STRING"
},
"data_two": {
"type": "STRING"
},
"data_three": {
"type": "ARRAY",
"items": {
"type": "STRING"
}
},
"data_four": {
"type": "ARRAY",
"items": {
"any_of": [
{
"type": "INTEGER"
},
{
"type": "NUMBER"
},
{
"type": "STRING"
}
],
"type": "STRING"
}
}
}
}
}
]
}
]
}
},
"model_response": {
"candidates": [
{
"content": {
"parts": [
{
"function_call": {
"args": {
"data_four": [
"1",
"hello",
"3.14"
],
"data_two": "3.141529",
"data_three": [
"apple",
"banana"
],
"data_one": "RRRR"
},
"name": "update_fc"
}
}
],
"role": "model"
},
"avg_logprobs": -2.100960955431219e-6,
"finish_reason": "STOP",
"safety_ratings": [
{
"category": "HARM_CATEGORY_HATE_SPEECH",
"probability": "NEGLIGIBLE",
"probability_score": 0.12158203,
"severity": "HARM_SEVERITY_NEGLIGIBLE",
"severity_score": 0.13671875
},
{
"category": "HARM_CATEGORY_DANGEROUS_CONTENT",
"probability": "NEGLIGIBLE",
"probability_score": 0.421875,
"severity": "HARM_SEVERITY_LOW",
"severity_score": 0.24511719
},
{
"category": "HARM_CATEGORY_HARASSMENT",
"probability": "NEGLIGIBLE",
"probability_score": 0.15722656,
"severity": "HARM_SEVERITY_NEGLIGIBLE",
"severity_score": 0.072753906
},
{
"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
"probability": "NEGLIGIBLE",
"probability_score": 0.083984375,
"severity": "HARM_SEVERITY_NEGLIGIBLE",
"severity_score": 0.03564453
}
]
}
],
"model_version": "gemini-2.5-flash",
"usage_metadata": {
"candidates_token_count": 32,
"prompt_token_count": 94,
"total_token_count": 126
}
}
},
{
"invocation_id": "M3dUcVa8",
"event_id": "OZ77XR41",
"model_request": {
"model": "gemini-2.5-flash",
"contents": [
{
"parts": [
{
"text": "hi"
}
],
"role": "user"
},
{
"parts": [
{
"text": "Hello! 👋 How can I help you today? \n"
}
],
"role": "model"
},
{
"parts": [
{
"text": "update data_one to be RRRR, data_two to be 3.141529, data_three to be apple and banana, data_four to be 1, hello, and 3.14"
}
],
"role": "user"
},
{
"parts": [
{
"function_call": {
"args": {
"data_four": [
"1",
"hello",
"3.14"
],
"data_two": "3.141529",
"data_three": [
"apple",
"banana"
],
"data_one": "RRRR"
},
"name": "update_fc"
}
}
],
"role": "model"
},
{
"parts": [
{
"function_response": {
"name": "update_fc",
"response": {}
}
}
],
"role": "user"
}
],
"config": {
"system_instruction": "You are an agent. Your name is root_agent.\nCall tools",
"tools": [
{
"function_declarations": [
{
"description": "Hello",
"name": "update_fc",
"parameters": {
"type": "OBJECT",
"properties": {
"data_one": {
"type": "STRING"
},
"data_two": {
"type": "STRING"
},
"data_three": {
"type": "ARRAY",
"items": {
"type": "STRING"
}
},
"data_four": {
"type": "ARRAY",
"items": {
"any_of": [
{
"type": "INTEGER"
},
{
"type": "NUMBER"
},
{
"type": "STRING"
}
],
"type": "STRING"
}
}
}
}
}
]
}
]
}
},
"model_response": {
"candidates": [
{
"content": {
"parts": [
{
"text": "OK. I've updated the data. Anything else? \n"
}
],
"role": "model"
},
"avg_logprobs": -0.22089435373033797,
"finish_reason": "STOP",
"safety_ratings": [
{
"category": "HARM_CATEGORY_HATE_SPEECH",
"probability": "NEGLIGIBLE",
"probability_score": 0.04663086,
"severity": "HARM_SEVERITY_NEGLIGIBLE",
"severity_score": 0.09423828
},
{
"category": "HARM_CATEGORY_DANGEROUS_CONTENT",
"probability": "NEGLIGIBLE",
"probability_score": 0.18554688,
"severity": "HARM_SEVERITY_NEGLIGIBLE",
"severity_score": 0.111328125
},
{
"category": "HARM_CATEGORY_HARASSMENT",
"probability": "NEGLIGIBLE",
"probability_score": 0.071777344,
"severity": "HARM_SEVERITY_NEGLIGIBLE",
"severity_score": 0.03112793
},
{
"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
"probability": "NEGLIGIBLE",
"probability_score": 0.043945313,
"severity": "HARM_SEVERITY_NEGLIGIBLE",
"severity_score": 0.057373047
}
]
}
],
"model_version": "gemini-2.5-flash",
"usage_metadata": {
"candidates_token_count": 14,
"prompt_token_count": 129,
"total_token_count": 143
}
}
}
]
}
tests/integration/fixture/context_variable_agent/__init__.py
+15
View File
@@ -0,0 +1,15 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from . import agent
tests/integration/fixture/context_variable_agent/agent.py
+115
View File
@@ -0,0 +1,115 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from typing import List
from typing import Union
from google.adk import Agent
from google.adk.agents.invocation_context import InvocationContext
from google.adk.planners.plan_re_act_planner import PlanReActPlanner
from google.adk.tools.tool_context import ToolContext
def update_fc(
data_one: str,
data_two: Union[int, float, str],
data_three: list[str],
data_four: List[Union[int, float, str]],
tool_context: ToolContext,
) -> str:
"""Simply ask to update these variables in the context"""
tool_context.actions.update_state('data_one', data_one)
tool_context.actions.update_state('data_two', data_two)
tool_context.actions.update_state('data_three', data_three)
tool_context.actions.update_state('data_four', data_four)
return 'The function `update_fc` executed successfully'
def echo_info(customer_id: str) -> str:
"""Echo the context variable"""
return customer_id
def build_global_instruction(invocation_context: InvocationContext) -> str:
return (
'This is the global agent instruction for invocation:'
f' {invocation_context.invocation_id}.'
)
def build_sub_agent_instruction(invocation_context: InvocationContext) -> str:
return 'This is the plain text sub agent instruction.'
context_variable_echo_agent = Agent(
model='gemini-2.5-flash',
name='context_variable_echo_agent',
instruction=(
'Use the echo_info tool to echo {customerId}, {customerInt},'
' {customerFloat}, and {customerJson}. Ask for it if you need to.'
),
flow='auto',
tools=[echo_info],
)
context_variable_with_complicated_format_agent = Agent(
model='gemini-2.5-flash',
name='context_variable_echo_agent',
instruction=(
'Use the echo_info tool to echo { customerId }, {{customer_int }, { '
" non-identifier-float}}, {artifact.fileName}, {'key1': 'value1'} and"
" {{'key2': 'value2'}}. Ask for it if you need to."
),
flow='auto',
tools=[echo_info],
)
context_variable_with_nl_planner_agent = Agent(
model='gemini-2.5-flash',
name='context_variable_with_nl_planner_agent',
instruction=(
'Use the echo_info tool to echo {customerId}. Ask for it if you'
' need to.'
),
flow='auto',
planner=PlanReActPlanner(),
tools=[echo_info],
)
context_variable_with_function_instruction_agent = Agent(
model='gemini-2.5-flash',
name='context_variable_with_function_instruction_agent',
instruction=build_sub_agent_instruction,
flow='auto',
)
context_variable_update_agent = Agent(
model='gemini-2.5-flash',
name='context_variable_update_agent',
instruction='Call tools',
flow='auto',
tools=[update_fc],
)
root_agent = Agent(
model='gemini-2.5-flash',
name='root_agent',
description='The root agent.',
flow='auto',
global_instruction=build_global_instruction,
sub_agents=[
context_variable_with_nl_planner_agent,
context_variable_update_agent,
],
)
tests/integration/fixture/ecommerce_customer_service_agent/__init__.py
+15
View File
@@ -0,0 +1,15 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from . import agent
tests/integration/fixture/ecommerce_customer_service_agent/agent.py
+338
View File
@@ -0,0 +1,338 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from google.adk import Agent
# A lightweight in-memory mock database
ORDER_DB = {
"1": "FINISHED",
"2": "CANCELED",
"3": "PENDING",
"4": "PENDING",
} # Order id to status mapping. Available states: 'FINISHED', 'PENDING', and 'CANCELED'
USER_TO_ORDER_DB = {
"user_a": ["1", "4"],
"user_b": ["2"],
"user_c": ["3"],
} # User id to Order id mapping
TICKET_DB = [{
"ticket_id": "1",
"user_id": "user_a",
"issue_type": "LOGIN_ISSUE",
"status": "OPEN",
}] # Available states: 'OPEN', 'CLOSED', 'ESCALATED'
USER_INFO_DB = {
"user_a": {"name": "Alice", "email": "alice@example.com"},
"user_b": {"name": "Bob", "email": "bob@example.com"},
}
def reset_data():
global ORDER_DB
global USER_TO_ORDER_DB
global TICKET_DB
global USER_INFO_DB
ORDER_DB = {
"1": "FINISHED",
"2": "CANCELED",
"3": "PENDING",
"4": "PENDING",
}
USER_TO_ORDER_DB = {
"user_a": ["1", "4"],
"user_b": ["2"],
"user_c": ["3"],
}
TICKET_DB = [{
"ticket_id": "1",
"user_id": "user_a",
"issue_type": "LOGIN_ISSUE",
"status": "OPEN",
}]
USER_INFO_DB = {
"user_a": {"name": "Alice", "email": "alice@example.com"},
"user_b": {"name": "Bob", "email": "bob@example.com"},
}
def get_order_status(order_id: str) -> str:
"""Get the status of an order.
Args:
order_id (str): The unique identifier of the order.
Returns:
str: The status of the order (e.g., 'FINISHED', 'CANCELED', 'PENDING'),
or 'Order not found' if the order_id does not exist.
"""
return ORDER_DB.get(order_id, "Order not found")
def get_order_ids_for_user(user_id: str) -> list:
"""Get the list of order IDs assigned to a specific transaction associated with a user.
Args:
user_id (str): The unique identifier of the user.
Returns:
List[str]: A list of order IDs associated with the user, or an empty list
if no orders are found.
"""
return USER_TO_ORDER_DB.get(user_id, [])
def cancel_order(order_id: str) -> str:
"""Cancel an order if it is in a 'PENDING' state.
You should call "get_order_status" to check the status first, before calling
this tool.
Args:
order_id (str): The unique identifier of the order to be canceled.
Returns:
str: A message indicating whether the order was successfully canceled or
not.
"""
if order_id in ORDER_DB and ORDER_DB[order_id] == "PENDING":
ORDER_DB[order_id] = "CANCELED"
return f"Order {order_id} has been canceled."
return f"Order {order_id} cannot be canceled."
def refund_order(order_id: str) -> str:
"""Process a refund for an order if it is in a 'CANCELED' state.
You should call "get_order_status" to check if status first, before calling
this tool.
Args:
order_id (str): The unique identifier of the order to be refunded.
Returns:
str: A message indicating whether the order was successfully refunded or
not.
"""
if order_id in ORDER_DB and ORDER_DB[order_id] == "CANCELED":
return f"Order {order_id} has been refunded."
return f"Order {order_id} cannot be refunded."
def create_ticket(user_id: str, issue_type: str) -> str:
"""Create a new support ticket for a user.
Args:
user_id (str): The unique identifier of the user creating the ticket.
issue_type (str): An issue type the user is facing. Available types:
'LOGIN_ISSUE', 'ORDER_ISSUE', 'OTHER'.
Returns:
str: A message indicating that the ticket was created successfully,
including the ticket ID.
"""
ticket_id = str(len(TICKET_DB) + 1)
TICKET_DB.append({
"ticket_id": ticket_id,
"user_id": user_id,
"issue_type": issue_type,
"status": "OPEN",
})
return f"Ticket {ticket_id} created successfully."
def get_ticket_info(ticket_id: str) -> str:
"""Retrieve the information of a support ticket.
current status of a support ticket.
Args:
ticket_id (str): The unique identifier of the ticket.
Returns:
A dictionary contains the following fields, or 'Ticket not found' if the
ticket_id does not exist:
- "ticket_id": str, the current ticket id
- "user_id": str, the associated user id
- "issue": str, the issue type
- "status": The current status of the ticket (e.g., 'OPEN', 'CLOSED',
'ESCALATED')
Example: {"ticket_id": "1", "user_id": "user_a", "issue": "Login issue",
"status": "OPEN"}
"""
for ticket in TICKET_DB:
if ticket["ticket_id"] == ticket_id:
return ticket
return "Ticket not found"
def get_tickets_for_user(user_id: str) -> list:
"""Get all the ticket IDs associated with a user.
Args:
user_id (str): The unique identifier of the user.
Returns:
List[str]: A list of ticket IDs associated with the user.
If no tickets are found, returns an empty list.
"""
return [
ticket["ticket_id"]
for ticket in TICKET_DB
if ticket["user_id"] == user_id
]
def update_ticket_status(ticket_id: str, status: str) -> str:
"""Update the status of a support ticket.
Args:
ticket_id (str): The unique identifier of the ticket.
status (str): The new status to assign to the ticket (e.g., 'OPEN',
'CLOSED', 'ESCALATED').
Returns:
str: A message indicating whether the ticket status was successfully
updated.
"""
for ticket in TICKET_DB:
if ticket["ticket_id"] == ticket_id:
ticket["status"] = status
return f"Ticket {ticket_id} status updated to {status}."
return "Ticket not found"
def get_user_info(user_id: str) -> dict:
"""Retrieve information (name, email) about a user.
Args:
user_id (str): The unique identifier of the user.
Returns:
dict or str: A dictionary containing user information of the following
fields, or 'User not found' if the user_id does not exist:
- name: The name of the user
- email: The email address of the user
For example, {"name": "Chelsea", "email": "123@example.com"}
"""
return USER_INFO_DB.get(user_id, "User not found")
def send_email(user_id: str, email: str) -> list:
"""Send email to user for notification.
Args:
user_id (str): The unique identifier of the user.
email (str): The email address of the user.
Returns:
str: A message indicating whether the email was successfully sent.
"""
if user_id in USER_INFO_DB:
return f"Email sent to {email} for user id {user_id}"
return "Cannot find this user"
# def update_user_info(user_id: str, new_info: dict[str, str]) -> str:
def update_user_info(user_id: str, email: str, name: str) -> str:
"""Update a user's information.
Args:
user_id (str): The unique identifier of the user.
new_info (dict): A dictionary containing the fields to be updated (e.g.,
{'email': 'new_email@example.com'}). Available field keys: 'email' and
'name'.
Returns:
str: A message indicating whether the user's information was successfully
updated or not.
"""
if user_id in USER_INFO_DB:
# USER_INFO_DB[user_id].update(new_info)
if email and name:
USER_INFO_DB[user_id].update({"email": email, "name": name})
elif email:
USER_INFO_DB[user_id].update({"email": email})
elif name:
USER_INFO_DB[user_id].update({"name": name})
else:
raise ValueError("this should not happen.")
return f"User {user_id} information updated."
return "User not found"
def get_user_id_from_cookie() -> str:
"""Get user ID(username) from the cookie.
Only use this function when you do not know user ID(username).
Args: None
Returns:
str: The user ID.
"""
return "user_a"
root_agent = Agent(
model="gemini-2.5-flash",
name="Ecommerce_Customer_Service",
instruction="""
You are an intelligent customer service assistant for an e-commerce platform. Your goal is to accurately understand user queries and use the appropriate tools to fulfill requests. Follow these guidelines:
1. **Understand the Query**:
- Identify actions and conditions (e.g., create a ticket only for pending orders).
- Extract necessary details (e.g., user ID, order ID) from the query or infer them from the context.
2. **Plan Multi-Step Workflows**:
- Break down complex queries into sequential steps. For example
- typical workflow:
- Retrieve IDs or references first (e.g., orders for a user).
- Evaluate conditions (e.g., check order status).
- Perform actions (e.g., create a ticket) only when conditions are met.
- another typical workflows - order cancellation and refund:
- Retrieve all orders for the user (`get_order_ids_for_user`).
- Cancel pending orders (`cancel_order`).
- Refund canceled orders (`refund_order`).
- Notify the user (`send_email`).
- another typical workflows - send user report:
- Get user id.
- Get user info(like emails)
- Send email to user.
3. **Avoid Skipping Steps**:
- Ensure each intermediate step is completed before moving to the next.
- Do not create tickets or take other actions without verifying the conditions specified in the query.
4. **Provide Clear Responses**:
- Confirm the actions performed, including details like ticket ID or pending orders.
- Ensure the response aligns with the steps taken and query intent.
""",
tools=[
get_order_status,
cancel_order,
get_order_ids_for_user,
refund_order,
create_ticket,
update_ticket_status,
get_tickets_for_user,
get_ticket_info,
get_user_info,
send_email,
update_user_info,
get_user_id_from_cookie,
],
)
tests/integration/fixture/ecommerce_customer_service_agent/order_query.test.json
+229
View File
@@ -0,0 +1,229 @@
{
"eval_set_id": "a1157c01-851f-48a8-b956-83cf7f463510",
"name": "a1157c01-851f-48a8-b956-83cf7f463510",
"description": null,
"eval_cases": [
{
"eval_id": "tests/integration/fixture/ecommerce_customer_service_agent/order_query.test.json",
"conversation": [
{
"invocation_id": "38d54523-d789-4873-8cc0-d38826c7feb4",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "Send an email to user user_a whose email address is alice@example.com"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "Email sent to alice@example.com for user id user_a."
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [
{
"id": null,
"args": {
"email": "alice@example.com",
"user_id": "user_a"
},
"name": "send_email"
}
],
"intermediate_responses": []
},
"creation_timestamp": 1747341706.6240807
},
{
"invocation_id": "916393ab-0bce-4cb0-98de-6573d4e8e25c",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "Can you tell me the status of my order with ID 1?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "Your order with ID 1 is FINISHED."
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [
{
"id": null,
"args": {
"order_id": "1"
},
"name": "get_order_status"
}
],
"intermediate_responses": []
},
"creation_timestamp": 1747341706.6241167
},
{
"invocation_id": "511b23d9-56f9-423b-9c31-7626f3411c32",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "Cancel all pending order for the user with user id user_a"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "I have checked your orders and order 4 was in pending status, so I have cancelled it. Order 1 was already finished and couldn't be cancelled.\n"
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [
{
"id": null,
"args": {
"user_id": "user_a"
},
"name": "get_order_ids_for_user"
},
{
"id": null,
"args": {
"order_id": "1"
},
"name": "get_order_status"
},
{
"id": null,
"args": {
"order_id": "4"
},
"name": "get_order_status"
},
{
"id": null,
"args": {
"order_id": "4"
},
"name": "cancel_order"
}
],
"intermediate_responses": []
},
"creation_timestamp": 1747341706.6241703
},
{
"invocation_id": "dcdf4b6d-96dd-4602-8c14-0563c6f6b5d0",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "What orders have I placed under the username user_b?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "User user_b has placed one order with order ID 2.\n"
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [
{
"id": null,
"args": {
"user_id": "user_b"
},
"name": "get_order_ids_for_user"
}
],
"intermediate_responses": []
},
"creation_timestamp": 1747341706.624196
}
],
"session_input": null,
"creation_timestamp": 1747341706.6242023
}
],
"creation_timestamp": 1747341706.6242158
}
tests/integration/fixture/ecommerce_customer_service_agent/test_config.json
+6
View File
@@ -0,0 +1,6 @@
{
"criteria": {
"tool_trajectory_avg_score": 0.7,
"response_match_score": 0.5
}
}
tests/integration/fixture/flow_complex_spark/__init__.py
+15
View File
@@ -0,0 +1,15 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from . import agent
tests/integration/fixture/flow_complex_spark/agent.py
+182
View File
@@ -0,0 +1,182 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from google.adk import Agent
from google.genai import types
research_plan_agent = Agent(
model="gemini-2.5-flash",
name="research_plan_agent",
description="I can help generate research plan.",
instruction="""\
Your task is to create a research plan according to the user's query.
# Here are the instructions for creating the research plan:
+ Focus on finding specific things, e.g. products, data, etc.
+ Have the personality of a work colleague that is very helpful and explains things very nicely.
+ Don't mention your name unless you are asked.
+ Think about the most common things that you would need to research.
+ Think about possible answers when creating the plan.
+ Your task is to create the sections that should be researched. You will output high level headers, preceded by ##
+ Underneath each header, write a short sentence on what we want to find there.
+ The headers will follow the logical analysis pattern, as well as logical exploration pattern.
+ The headers should be a statement, not be in the form of questions.
+ The header will not include roman numerals or anything of the sort, e.g. ":", etc
+ Do not include things that you cannot possibly know about from using Google Search: e.g. sales forecasting, competitors, profitability analysis, etc.
+ Do not have an executive summary
+ In each section describe specifically what will be researched.
+ Never use "we will", but rather "I will".
+ Don't ask for clarifications from the user.
+ Do not ask the user for clarifications or if they have any other questions.
+ All headers should be bolded.
+ If you have steps in the plan that depend on other information, make sure they are 2 different sections in the plan.
+ At the end mention that you will start researching.
# Instruction on replying format
+ Start with your name as "[research_plan_agent]: ".
+ Output the content you want to say.
Output summary:
""",
flow="single",
sub_agents=[],
generate_content_config=types.GenerateContentConfig(
temperature=0.1,
),
)
question_generation_agent = Agent(
model="gemini-2.5-flash",
name="question_generation_agent",
description="I can help generate questions related to user's question.",
instruction="""\
Generate questions related to the research plan generated by research_plan_agent.
# Instruction on replying format
Your reply should be a numbered list.
For each question, reply in the following format: "[question_generation_agent]: [generated questions]"
Here is an example of the generated question list:
1. [question_generation_agent]: which state is San Jose in?
2. [question_generation_agent]: how google website is designed?
""",
flow="single",
sub_agents=[],
generate_content_config=types.GenerateContentConfig(
temperature=0.1,
),
)
information_retrieval_agent = Agent(
model="gemini-2.5-flash",
name="information_retrieval_agent",
description=(
"I can help retrieve information related to question_generation_agent's"
" question."
),
instruction="""\
Inspect all the questions after "[question_generation_agent]: " and answer them.
# Instruction on replying format
Always start with "[information_retrieval_agent]: "
For the answer of one question:
- Start with a title with one line summary of the reply.
- The title line should be bolded and starts with No.x of the corresponding question.
- Have a paragraph of detailed explain.
# Instruction on exiting the loop
- If you see there are less than 20 questions by "question_generation_agent", do not say "[exit]".
- If you see there are already great or equal to 20 questions asked by "question_generation_agent", say "[exit]" at last to exit the loop.
""",
flow="single",
sub_agents=[],
generate_content_config=types.GenerateContentConfig(
temperature=0.1,
),
)
question_sources_generation_agent = Agent(
model="gemini-2.5-flash",
name="question_sources_generation_agent",
description=(
"I can help generate questions and retrieve related information."
),
instruction="Generate questions and retrieve information.",
flow="loop",
sub_agents=[
question_generation_agent,
information_retrieval_agent,
],
generate_content_config=types.GenerateContentConfig(
temperature=0.1,
),
)
summary_agent = Agent(
model="gemini-2.5-flash",
name="summary_agent",
description="I can help summarize information of previous content.",
instruction="""\
Summarize information in all historical messages that were replied by "question_generation_agent" and "information_retrieval_agent".
# Instruction on replying format
- The output should be like an essay that has a title, an abstract, multiple paragraphs for each topic and a conclusion.
- Each paragraph should maps to one or more question in historical content.
""",
flow="single",
generate_content_config=types.GenerateContentConfig(
temperature=0.8,
),
)
research_assistant = Agent(
model="gemini-2.5-flash",
name="research_assistant",
description="I can help with research question.",
instruction="Help customers with their need.",
flow="sequential",
sub_agents=[
research_plan_agent,
question_sources_generation_agent,
summary_agent,
],
generate_content_config=types.GenerateContentConfig(
temperature=0.1,
),
)
spark_agent = Agent(
model="gemini-2.5-flash",
name="spark_assistant",
description="I can help with non-research question.",
instruction="Help customers with their need.",
flow="auto",
sub_agents=[research_assistant],
generate_content_config=types.GenerateContentConfig(
temperature=0.1,
),
)
root_agent = spark_agent
tests/integration/fixture/flow_complex_spark/sample.session.json
+190
View File
File diff suppressed because one or more lines are too long
tests/integration/fixture/hello_world_agent/__init__.py
+15
View File
@@ -0,0 +1,15 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from . import agent
tests/integration/fixture/hello_world_agent/agent.py
+95
View File
@@ -0,0 +1,95 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# Hello world agent from agent 1.0 - https://colab.sandbox.google.com/drive/1Zq-nqmgK0nCERCv8jKIaoeTTgbNn6oSo?resourcekey=0-GYaz9pFT4wY8CI8Cvjy5GA#scrollTo=u3X3XwDOaCv9
import random
from google.adk import Agent
from google.genai import types
def roll_die(sides: int) -> int:
"""Roll a die and return the rolled result.
Args:
sides: The integer number of sides the die has.
Returns:
An integer of the result of rolling the die.
"""
return random.randint(1, sides)
def check_prime(nums: list[int]) -> list[str]:
"""Check if a given list of numbers are prime.
Args:
nums: The list of numbers to check.
Returns:
A str indicating which number is prime.
"""
primes = set()
for number in nums:
number = int(number)
if number <= 1:
continue
is_prime = True
for i in range(2, int(number**0.5) + 1):
if number % i == 0:
is_prime = False
break
if is_prime:
primes.add(number)
return (
'No prime numbers found.'
if not primes
else f"{', '.join(str(num) for num in primes)} are prime numbers."
)
root_agent = Agent(
model='gemini-2.5-flash',
name='data_processing_agent',
instruction="""
You roll dice and answer questions about the outcome of the dice rolls.
You can roll dice of different sizes.
You can use multiple tools in parallel by calling functions in parallel(in one request and in one round).
The only things you do are roll dice for the user and discuss the outcomes.
It is ok to discuss previous dice roles, and comment on the dice rolls.
When you are asked to roll a die, you must call the roll_die tool with the number of sides. Be sure to pass in an integer. Do not pass in a string.
You should never roll a die on your own.
When checking prime numbers, call the check_prime tool with a list of integers. Be sure to pass in a list of integers. You should never pass in a string.
You should not check prime numbers before calling the tool.
When you are asked to roll a die and check prime numbers, you should always make the following two function calls:
1. You should first call the roll_die tool to get a roll. Wait for the function response before calling the check_prime tool.
2. After you get the function response from roll_die tool, you should call the check_prime tool with the roll_die result.
2.1 If user asks you to check primes based on previous rolls, make sure you include the previous rolls in the list.
3. When you respond, you must include the roll_die result from step 1.
You should always perform the previous 3 steps when asking for a roll and checking prime numbers.
You should not rely on the previous history on prime results.
""",
tools=[
roll_die,
check_prime,
],
generate_content_config=types.GenerateContentConfig(
safety_settings=[
types.SafetySetting( # avoid false alarm about rolling dice.
category=types.HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT,
threshold=types.HarmBlockThreshold.OFF,
),
]
),
)
tests/integration/fixture/hello_world_agent/roll_die.test.json
+143
View File
@@ -0,0 +1,143 @@
{
"eval_set_id": "56540925-a5ff-49fe-a4e1-589fe78066f2",
"name": "56540925-a5ff-49fe-a4e1-589fe78066f2",
"description": null,
"eval_cases": [
{
"eval_id": "tests/integration/fixture/hello_world_agent/roll_die.test.json",
"conversation": [
{
"invocation_id": "b01f67f0-9f23-44d6-bbe4-36ea235cb9fb",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "Hi who are you?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "I am a data processing agent. I can roll dice and check if the results are prime numbers. What would you like me to do? \n"
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [],
"intermediate_responses": []
},
"creation_timestamp": 1747341775.8937013
},
{
"invocation_id": "13be0093-ac29-4828-98c6-5bbd570c010c",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "What can you do?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "I can roll dice for you of different sizes, and I can check if the results are prime numbers. I can also remember previous rolls if you'd like to check those for primes as well. What would you like me to do? \n"
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [],
"intermediate_responses": []
},
"creation_timestamp": 1747341775.8937378
},
{
"invocation_id": "7deda353-c936-4c21-b242-9fa75e45b6a7",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "Can you roll a die with 6 sides"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": null
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [
{
"id": null,
"args": {
"sides": 6
},
"name": "roll_die"
}
],
"intermediate_responses": []
},
"creation_timestamp": 1747341775.8937788
}
],
"session_input": null,
"creation_timestamp": 1747341775.8937826
}
],
"creation_timestamp": 1747341775.8937957
}
tests/integration/fixture/hello_world_agent/test_config.json
+6
View File
@@ -0,0 +1,6 @@
{
"criteria": {
"tool_trajectory_avg_score": 1.0,
"response_match_score": 0.5
}
}
tests/integration/fixture/hello_world_agent_async/__init__.py
+15
View File
@@ -0,0 +1,15 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from . import agent
tests/integration/fixture/hello_world_agent_async/agent.py
+104
View File
@@ -0,0 +1,104 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# Hello world agent from agent 1.0 revised to be defined with get_agent_async
# instead of root_agent - https://colab.sandbox.google.com/drive/1Zq-nqmgK0nCERCv8jKIaoeTTgbNn6oSo?resourcekey=0-GYaz9pFT4wY8CI8Cvjy5GA#scrollTo=u3X3XwDOaCv9
import contextlib
import random
from typing import Optional
from google.adk import Agent
from google.adk.agents import llm_agent
from google.genai import types
def roll_die(sides: int) -> int:
"""Roll a die and return the rolled result.
Args:
sides: The integer number of sides the die has.
Returns:
An integer of the result of rolling the die.
"""
return random.randint(1, sides)
def check_prime(nums: list[int]) -> list[str]:
"""Check if a given list of numbers are prime.
Args:
nums: The list of numbers to check.
Returns:
A str indicating which number is prime.
"""
primes = set()
for number in nums:
number = int(number)
if number <= 1:
continue
is_prime = True
for i in range(2, int(number**0.5) + 1):
if number % i == 0:
is_prime = False
break
if is_prime:
primes.add(number)
return (
'No prime numbers found.'
if not primes
else f"{', '.join(str(num) for num in primes)} are prime numbers."
)
async def get_agent_async() -> (
tuple[llm_agent.LlmAgent, Optional[contextlib.AsyncExitStack]]
):
"""Returns the root agent."""
root_agent = Agent(
model='gemini-2.5-flash',
name='data_processing_agent',
instruction="""
You roll dice and answer questions about the outcome of the dice rolls.
You can roll dice of different sizes.
You can use multiple tools in parallel by calling functions in parallel(in one request and in one round).
The only things you do are roll dice for the user and discuss the outcomes.
It is ok to discuss previous dice roles, and comment on the dice rolls.
When you are asked to roll a die, you must call the roll_die tool with the number of sides. Be sure to pass in an integer. Do not pass in a string.
You should never roll a die on your own.
When checking prime numbers, call the check_prime tool with a list of integers. Be sure to pass in a list of integers. You should never pass in a string.
You should not check prime numbers before calling the tool.
When you are asked to roll a die and check prime numbers, you should always make the following two function calls:
1. You should first call the roll_die tool to get a roll. Wait for the function response before calling the check_prime tool.
2. After you get the function response from roll_die tool, you should call the check_prime tool with the roll_die result.
2.1 If user asks you to check primes based on previous rolls, make sure you include the previous rolls in the list.
3. When you respond, you must include the roll_die result from step 1.
You should always perform the previous 3 steps when asking for a roll and checking prime numbers.
You should not rely on the previous history on prime results.
""",
tools=[
roll_die,
check_prime,
],
generate_content_config=types.GenerateContentConfig(
safety_settings=[
types.SafetySetting( # avoid false alarm about rolling dice.
category=types.HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT,
threshold=types.HarmBlockThreshold.OFF,
),
]
),
)
return root_agent, None
tests/integration/fixture/hello_world_agent_async/roll_die.test.json
+55
View File
@@ -0,0 +1,55 @@
{
"eval_set_id": "56540925-a5ff-49fe-a4e1-589fe78066f2",
"name": "56540925-a5ff-49fe-a4e1-589fe78066f2",
"description": null,
"eval_cases": [
{
"eval_id": "tests/integration/fixture/hello_world_agent_async/roll_die.test.json",
"conversation": [
{
"invocation_id": "b01f67f0-9f23-44d6-bbe4-36ea235cb9fb",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "Hi who are you?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "I am a data processing agent. I can roll dice and check if the results are prime numbers. What would you like me to do? \n"
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [],
"intermediate_responses": []
},
"creation_timestamp": 1747341775.8937013
}
],
"session_input": null,
"creation_timestamp": 1747341775.8937826
}
],
"creation_timestamp": 1747341775.8937957
}
tests/integration/fixture/hello_world_agent_async/test_config.json
+6
View File
@@ -0,0 +1,6 @@
{
"criteria": {
"tool_trajectory_avg_score": 1.0,
"response_match_score": 0.5
}
}
tests/integration/fixture/home_automation_agent/__init__.py
+15
View File
@@ -0,0 +1,15 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from . import agent
tests/integration/fixture/home_automation_agent/agent.py
+304
View File
@@ -0,0 +1,304 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import os
import sys
from google.adk import Agent
DEVICE_DB = {
"device_1": {"status": "ON", "location": "Living Room"},
"device_2": {"status": "OFF", "location": "Bedroom"},
"device_3": {"status": "OFF", "location": "Kitchen"},
}
TEMPERATURE_DB = {
"Living Room": 22,
"Bedroom": 20,
"Kitchen": 24,
}
SCHEDULE_DB = {
"device_1": {"time": "18:00", "status": "ON"},
"device_2": {"time": "22:00", "status": "OFF"},
}
USER_PREFERENCES_DB = {
"user_x": {"preferred_temp": 21, "location": "Bedroom"},
"user_x": {"preferred_temp": 21, "location": "Living Room"},
"user_y": {"preferred_temp": 23, "location": "Living Room"},
}
def reset_data():
global DEVICE_DB
global TEMPERATURE_DB
global SCHEDULE_DB
global USER_PREFERENCES_DB
DEVICE_DB = {
"device_1": {"status": "ON", "location": "Living Room"},
"device_2": {"status": "OFF", "location": "Bedroom"},
"device_3": {"status": "OFF", "location": "Kitchen"},
}
TEMPERATURE_DB = {
"Living Room": 22,
"Bedroom": 20,
"Kitchen": 24,
}
SCHEDULE_DB = {
"device_1": {"time": "18:00", "status": "ON"},
"device_2": {"time": "22:00", "status": "OFF"},
}
USER_PREFERENCES_DB = {
"user_x": {"preferred_temp": 21, "location": "Bedroom"},
"user_x": {"preferred_temp": 21, "location": "Living Room"},
"user_y": {"preferred_temp": 23, "location": "Living Room"},
}
def get_device_info(device_id: str) -> dict:
"""Get the current status and location of a AC device.
Args:
device_id (str): The unique identifier of the device.
Returns:
dict: A dictionary containing the following fields, or 'Device not found'
if the device_id does not exist:
- status: The current status of the device (e.g., 'ON', 'OFF')
- location: The location where the device is installed (e.g., 'Living
Room', 'Bedroom', ''Kitchen')
"""
return DEVICE_DB.get(device_id, "Device not found")
# def set_device_info(device_id: str, updates: dict) -> str:
# """Update the information of a AC device, specifically its status and/or location.
# Args:
# device_id (str): Required. The unique identifier of the device.
# updates (dict): Required. A dictionary containing the fields to be
# updated. Supported keys: - "status" (str): The new status to set for the
# device. Accepted values: 'ON', 'OFF'. **Only these values are allowed.**
# - "location" (str): The new location to set for the device. Accepted
# values: 'Living Room', 'Bedroom', 'Kitchen'. **Only these values are
# allowed.**
# Returns:
# str: A message indicating whether the device information was successfully
# updated.
# """
# if device_id in DEVICE_DB:
# if "status" in updates:
# DEVICE_DB[device_id]["status"] = updates["status"]
# if "location" in updates:
# DEVICE_DB[device_id]["location"] = updates["location"]
# return f"Device {device_id} information updated: {updates}."
# return "Device not found"
def set_device_info(
device_id: str, status: str = "", location: str = ""
) -> str:
"""Update the information of a AC device, specifically its status and/or location.
Args:
device_id (str): Required. The unique identifier of the device.
status (str): The new status to set for the
device. Accepted values: 'ON', 'OFF'. **Only these values are allowed.**
location (str): The new location to set for the device. Accepted
values: 'Living Room', 'Bedroom', 'Kitchen'. **Only these values are
allowed.**
Returns:
str: A message indicating whether the device information was successfully
updated.
"""
if device_id in DEVICE_DB:
if status:
DEVICE_DB[device_id]["status"] = status
return f"Device {device_id} information updated: status -> {status}."
if location:
DEVICE_DB[device_id]["location"] = location
return f"Device {device_id} information updated: location -> {location}."
return "Device not found"
def get_temperature(location: str) -> int:
"""Get the current temperature in Celsius of a location (e.g., 'Living Room', 'Bedroom', 'Kitchen').
Args:
location (str): The location for which to retrieve the temperature (e.g.,
'Living Room', 'Bedroom', 'Kitchen').
Returns:
int: The current temperature in Celsius in the specified location, or
'Location not found' if the location does not exist.
"""
return TEMPERATURE_DB.get(location, "Location not found")
def set_temperature(location: str, temperature: int) -> str:
"""Set the desired temperature in Celsius for a location.
Acceptable range of temperature: 18-30 Celsius. If it's out of the range, do
not call this tool.
Args:
location (str): The location where the temperature should be set.
temperature (int): The desired temperature as integer to set in Celsius.
Acceptable range: 18-30 Celsius.
Returns:
str: A message indicating whether the temperature was successfully set.
"""
if location in TEMPERATURE_DB:
TEMPERATURE_DB[location] = temperature
return f"Temperature in {location} set to {temperature}°C."
return "Location not found"
def get_user_preferences(user_id: str) -> dict:
"""Get the temperature preferences and preferred location of a user_id.
user_id must be provided.
Args:
user_id (str): The unique identifier of the user.
Returns:
dict: A dictionary containing the following fields, or 'User not found' if
the user_id does not exist:
- preferred_temp: The user's preferred temperature.
- location: The location where the user prefers to be.
"""
return USER_PREFERENCES_DB.get(user_id, "User not found")
def set_device_schedule(device_id: str, time: str, status: str) -> str:
"""Schedule a device to change its status at a specific time.
Args:
device_id (str): The unique identifier of the device.
time (str): The time at which the device should change its status (format:
'HH:MM').
status (str): The status to set for the device at the specified time
(e.g., 'ON', 'OFF').
Returns:
str: A message indicating whether the schedule was successfully set.
"""
if device_id in DEVICE_DB:
SCHEDULE_DB[device_id] = {"time": time, "status": status}
return f"Device {device_id} scheduled to turn {status} at {time}."
return "Device not found"
def get_device_schedule(device_id: str) -> dict:
"""Retrieve the schedule of a device.
Args:
device_id (str): The unique identifier of the device.
Returns:
dict: A dictionary containing the following fields, or 'Schedule not
found' if the device_id does not exist:
- time: The scheduled time for the device to change its status (format:
'HH:MM').
- status: The status that will be set at the scheduled time (e.g., 'ON',
'OFF').
"""
return SCHEDULE_DB.get(device_id, "Schedule not found")
def celsius_to_fahrenheit(celsius: int) -> float:
"""Convert Celsius to Fahrenheit.
You must call this to do the conversion of temperature, so you can get the
precise number in required format.
Args:
celsius (int): Temperature in Celsius.
Returns:
float: Temperature in Fahrenheit.
"""
return (celsius * 9 / 5) + 32
def fahrenheit_to_celsius(fahrenheit: float) -> int:
"""Convert Fahrenheit to Celsius.
You must call this to do the conversion of temperature, so you can get the
precise number in required format.
Args:
fahrenheit (float): Temperature in Fahrenheit.
Returns:
int: Temperature in Celsius.
"""
return int((fahrenheit - 32) * 5 / 9)
def list_devices(status: str = "", location: str = "") -> list:
"""Retrieve a list of AC devices, filtered by status and/or location when provided.
For cost efficiency, always apply as many filters (status and location) as
available in the input arguments.
Args:
status (str, optional): The status to filter devices by (e.g., 'ON',
'OFF'). Defaults to None.
location (str, optional): The location to filter devices by (e.g., 'Living
Room', 'Bedroom', ''Kitchen'). Defaults to None.
Returns:
list: A list of dictionaries, each containing the device ID, status, and
location, or an empty list if no devices match the criteria.
"""
devices = []
for device_id, info in DEVICE_DB.items():
if ((not status) or info["status"] == status) and (
(not location) or info["location"] == location
):
devices.append({
"device_id": device_id,
"status": info["status"],
"location": info["location"],
})
return devices if devices else "No devices found matching the criteria."
root_agent = Agent(
model="gemini-2.5-flash",
name="Home_automation_agent",
instruction="""
You are Home Automation Agent. You are responsible for controlling the devices in the home.
""",
tools=[
get_device_info,
set_device_info,
get_temperature,
set_temperature,
get_user_preferences,
set_device_schedule,
get_device_schedule,
celsius_to_fahrenheit,
fahrenheit_to_celsius,
list_devices,
],
)
tests/integration/fixture/home_automation_agent/simple_test.test.json
+65
View File
@@ -0,0 +1,65 @@
{
"eval_set_id": "b305bd06-38c5-4796-b9c7-d9c7454338b9",
"name": "b305bd06-38c5-4796-b9c7-d9c7454338b9",
"description": null,
"eval_cases": [
{
"eval_id": "tests/integration/fixture/home_automation_agent/simple_test.test.json",
"conversation": [
{
"invocation_id": "b7982664-0ab6-47cc-ab13-326656afdf75",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "Turn off device_2 in the Bedroom."
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "I have set the device_2 status to off."
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [
{
"id": null,
"args": {
"location": "Bedroom",
"device_id": "device_2",
"status": "OFF"
},
"name": "set_device_info"
}
],
"intermediate_responses": []
},
"creation_timestamp": 1747337309.2360144
}
],
"session_input": null,
"creation_timestamp": 1747337309.2360282
}
],
"creation_timestamp": 1747337309.2360387
}
tests/integration/fixture/home_automation_agent/simple_test2.test.json
+5
View File
@@ -0,0 +1,5 @@
[{
"query": "Turn off device_3 in the Bedroom.",
"expected_tool_use": [{"tool_name": "set_device_info", "tool_input": {"location": "Bedroom", "device_id": "device_3", "status": "OFF"}}],
"reference": "I have set the device_3 status to off."
}]
tests/integration/fixture/home_automation_agent/test_config.json
+6
View File
@@ -0,0 +1,6 @@
{
"criteria": {
"tool_trajectory_avg_score": 1.0,
"response_match_score": 0.3
}
}
tests/integration/fixture/home_automation_agent/test_files/dependent_tool_calls.test.json
+113
View File
@@ -0,0 +1,113 @@
{
"eval_set_id": "1be50511-ff75-4d68-b2d7-2165cbdc1044",
"name": "1be50511-ff75-4d68-b2d7-2165cbdc1044",
"description": null,
"eval_cases": [
{
"eval_id": "tests/integration/fixture/home_automation_agent/test_files/dependent_tool_calls.test.json",
"conversation": [
{
"invocation_id": "cbece1c0-3811-45c0-96fc-9a4279075483",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "Turn off device_2 in the Bedroom."
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "I have set the device 2 status to off."
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [
{
"id": null,
"args": {
"location": "Bedroom",
"status": "OFF",
"device_id": "device_2"
},
"name": "set_device_info"
}
],
"intermediate_responses": []
},
"creation_timestamp": 1747340826.1082227
},
{
"invocation_id": "cc85cdae-4258-4b94-8fe7-a985b8356190",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "What's the status of device_2 in the Bedroom?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "Status of device_2 is off."
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [
{
"id": null,
"args": {
"device_id": "device_2"
},
"name": "get_device_info"
}
],
"intermediate_responses": []
},
"creation_timestamp": 1747340826.1082554
}
],
"session_input": null,
"creation_timestamp": 1747340826.108262
}
],
"creation_timestamp": 1747340826.108275
}
tests/integration/fixture/home_automation_agent/test_files/memorizing_past_events/eval_data.test.json
+105
View File
@@ -0,0 +1,105 @@
{
"eval_set_id": "94553685-5f19-492b-bc44-f3bc775955e9",
"name": "94553685-5f19-492b-bc44-f3bc775955e9",
"description": null,
"eval_cases": [
{
"eval_id": "tests/integration/fixture/home_automation_agent/test_files/memorizing_past_events/eval_data.test.json",
"conversation": [
{
"invocation_id": "a958b622-21d3-4a6c-9c15-1274bbb8a6b6",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "Turn off device_2 in the Bedroom."
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "OK. I've turned off device_2 in the Bedroom. Anything else?\n"
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [
{
"id": null,
"args": {
"location": "Bedroom",
"device_id": "device_2",
"status": "OFF"
},
"name": "set_device_info"
}
],
"intermediate_responses": []
},
"creation_timestamp": 1747340865.7043095
},
{
"invocation_id": "1c07123d-4bed-4eb0-9e55-c7f80c70dadf",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "What's the command I just issued?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "You asked me to turn off device_2 in the Bedroom.\n"
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [],
"intermediate_responses": []
},
"creation_timestamp": 1747340865.7043421
}
],
"session_input": null,
"creation_timestamp": 1747340865.7043483
}
],
"creation_timestamp": 1747340865.704361
}
tests/integration/fixture/home_automation_agent/test_files/memorizing_past_events/test_config.json
+6
View File
@@ -0,0 +1,6 @@
{
"criteria": {
"tool_trajectory_avg_score": 1.0,
"response_match_score": 0.5
}
}
tests/integration/fixture/home_automation_agent/test_files/simple_multi_turn_conversation.test.json
+115
View File
@@ -0,0 +1,115 @@
{
"eval_set_id": "4412cca6-dfcd-43ab-bbc5-9155380c7137",
"name": "4412cca6-dfcd-43ab-bbc5-9155380c7137",
"description": null,
"eval_cases": [
{
"eval_id": "tests/integration/fixture/home_automation_agent/test_files/simple_multi_turn_conversation.test.json",
"conversation": [
{
"invocation_id": "9f51a1ac-56a4-4b4a-9878-36ff1ae312ce",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "Turn off device_2 in the Bedroom."
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "I have set the device 2 status to off."
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [
{
"id": null,
"args": {
"location": "Bedroom",
"device_id": "device_2",
"status": "OFF"
},
"name": "set_device_info"
}
],
"intermediate_responses": []
},
"creation_timestamp": 1747340791.7353904
},
{
"invocation_id": "c82d54d0-5fa8-4f79-a6dc-692090f0d42b",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "Turn on device_2 in the Bedroom."
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "I have set the device 2 status to on."
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [
{
"id": null,
"args": {
"location": "Bedroom",
"status": "ON",
"device_id": "device_2"
},
"name": "set_device_info"
}
],
"intermediate_responses": []
},
"creation_timestamp": 1747340791.7354295
}
],
"session_input": null,
"creation_timestamp": 1747340791.7354348
}
],
"creation_timestamp": 1747340791.735446
}
tests/integration/fixture/home_automation_agent/test_files/simple_test.test.json
+105
View File
@@ -0,0 +1,105 @@
{
"eval_set_id": "9100bfc9-cc28-4ab9-b920-2dc72e138997",
"name": "9100bfc9-cc28-4ab9-b920-2dc72e138997",
"description": null,
"eval_cases": [
{
"eval_id": "tests/integration/fixture/home_automation_agent/test_files/simple_test.test.json",
"conversation": [
{
"invocation_id": "9f5e8d91-8e51-41d6-addf-196a828168c5",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "Turn off device_2 in the Bedroom."
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "OK. I've turned off device_2 in the Bedroom. Anything else?\n"
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [
{
"id": null,
"args": {
"location": "Bedroom",
"device_id": "device_2",
"status": "OFF"
},
"name": "set_device_info"
}
],
"intermediate_responses": []
},
"creation_timestamp": 1747340849.0429707
},
{
"invocation_id": "767b2451-5f7b-4c73-aeaf-a82c71e15788",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "What's the command I just issued?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "You asked me to turn off device_2 in the Bedroom.\n"
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [],
"intermediate_responses": []
},
"creation_timestamp": 1747340849.0429986
}
],
"session_input": null,
"creation_timestamp": 1747340849.0430045
}
],
"creation_timestamp": 1747340849.0430162
}
tests/integration/fixture/home_automation_agent/test_files/simple_test2.test.json
+65
View File
@@ -0,0 +1,65 @@
{
"eval_set_id": "e141f90b-9e7e-4f06-94d7-bbe7e8080ead",
"name": "e141f90b-9e7e-4f06-94d7-bbe7e8080ead",
"description": null,
"eval_cases": [
{
"eval_id": "tests/integration/fixture/home_automation_agent/test_files/simple_test2.test.json",
"conversation": [
{
"invocation_id": "c35582f7-838a-460f-b783-039e278165e0",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "Turn off device_3 in the Bedroom."
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "I have set the device_3 status to off."
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [
{
"id": null,
"args": {
"location": "Bedroom",
"device_id": "device_3",
"status": "OFF"
},
"name": "set_device_info"
}
],
"intermediate_responses": []
},
"creation_timestamp": 1747340814.8645504
}
],
"session_input": null,
"creation_timestamp": 1747340814.86456
}
],
"creation_timestamp": 1747340814.864572
}
tests/integration/fixture/home_automation_agent/test_files/test_config.json
+5
View File
@@ -0,0 +1,5 @@
{
"criteria": {
"tool_trajectory_avg_score": 1.0
}
}
tests/integration/fixture/tool_agent/__init__.py
+15
View File
@@ -0,0 +1,15 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from . import agent
tests/integration/fixture/tool_agent/agent.py
+218
View File
@@ -0,0 +1,218 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import os
from typing import Any
from crewai_tools import DirectoryReadTool
from google.adk import Agent
from google.adk.tools.agent_tool import AgentTool
from google.adk.tools.crewai_tool import CrewaiTool
from google.adk.tools.langchain_tool import LangchainTool
from google.adk.tools.retrieval.files_retrieval import FilesRetrieval
from google.adk.tools.retrieval.vertex_ai_rag_retrieval import VertexAiRagRetrieval
from langchain_community.tools import ShellTool
from pydantic import BaseModel
class TestCase(BaseModel):
case: str
class Test(BaseModel):
test_title: list[str]
def simple_function(param: str) -> str:
if isinstance(param, str):
return "Called simple function successfully"
return "Called simple function with wrong param type"
def no_param_function() -> str:
return "Called no param function successfully"
def no_output_function(param: str):
return
def multiple_param_types_function(
param1: str, param2: int, param3: float, param4: bool
) -> str:
if (
isinstance(param1, str)
and isinstance(param2, int)
and isinstance(param3, float)
and isinstance(param4, bool)
):
return "Called multiple param types function successfully"
return "Called multiple param types function with wrong param types"
def throw_error_function(param: str) -> str:
raise ValueError("Error thrown by throw_error_function")
def list_str_param_function(param: list[str]) -> str:
if isinstance(param, list) and all(isinstance(item, str) for item in param):
return "Called list str param function successfully"
return "Called list str param function with wrong param type"
def return_list_str_function(param: str) -> list[str]:
return ["Called return list str function successfully"]
def complex_function_list_dict(
param1: dict[str, Any], param2: list[dict[str, Any]]
) -> list[Test]:
if (
isinstance(param1, dict)
and isinstance(param2, list)
and all(isinstance(item, dict) for item in param2)
):
return [
Test(test_title=["function test 1", "function test 2"]),
Test(test_title=["retrieval test"]),
]
raise ValueError("Wrong param")
def repetitive_call_1(param: str):
return f"Call repetitive_call_2 tool with param {param + '_repetitive'}"
def repetitive_call_2(param: str):
return param
test_case_retrieval = FilesRetrieval(
name="test_case_retrieval",
description="General guidance for agent test cases",
input_dir=os.path.join(os.path.dirname(__file__), "files"),
)
valid_rag_retrieval = VertexAiRagRetrieval(
name="valid_rag_retrieval",
rag_corpora=[
"projects/1096655024998/locations/us-central1/ragCorpora/4985766262475849728"
],
description="General guidance for agent test cases",
)
invalid_rag_retrieval = VertexAiRagRetrieval(
name="invalid_rag_retrieval",
rag_corpora=[
"projects/1096655024998/locations/us-central1/InValidRagCorporas/4985766262475849728"
],
description="Invalid rag retrieval resource name",
)
non_exist_rag_retrieval = VertexAiRagRetrieval(
name="non_exist_rag_retrieval",
rag_corpora=[
"projects/1096655024998/locations/us-central1/RagCorpora/1234567"
],
description="Non exist rag retrieval resource name",
)
shell_tool = LangchainTool(ShellTool())
docs_tool = CrewaiTool(
name="directory_read_tool",
description="use this to find files for you.",
tool=DirectoryReadTool(directory="."),
)
no_schema_agent = Agent(
model="gemini-2.5-flash",
name="no_schema_agent",
instruction="""Just say 'Hi'
""",
)
schema_agent = Agent(
model="gemini-2.5-flash",
name="schema_agent",
instruction="""
You will be given a test case.
Return a list of the received test case appended with '_success' and '_failure' as test_titles
""",
input_schema=TestCase,
output_schema=Test,
)
no_input_schema_agent = Agent(
model="gemini-2.5-flash",
name="no_input_schema_agent",
instruction="""
Just return ['Tools_success, Tools_failure']
""",
output_schema=Test,
)
no_output_schema_agent = Agent(
model="gemini-2.5-flash",
name="no_output_schema_agent",
instruction="""
Just say 'Hi'
""",
input_schema=TestCase,
)
single_function_agent = Agent(
model="gemini-2.5-flash",
name="single_function_agent",
description="An agent that calls a single function",
instruction="When calling tools, just return what the tool returns.",
tools=[simple_function],
)
root_agent = Agent(
model="gemini-2.5-flash",
name="tool_agent",
description="An agent that can call other tools",
instruction="When calling tools, just return what the tool returns.",
tools=[
simple_function,
no_param_function,
no_output_function,
multiple_param_types_function,
throw_error_function,
list_str_param_function,
return_list_str_function,
# complex_function_list_dict,
repetitive_call_1,
repetitive_call_2,
test_case_retrieval,
valid_rag_retrieval,
invalid_rag_retrieval,
non_exist_rag_retrieval,
shell_tool,
docs_tool,
AgentTool(
agent=no_schema_agent,
),
AgentTool(
agent=schema_agent,
),
AgentTool(
agent=no_input_schema_agent,
),
AgentTool(
agent=no_output_schema_agent,
),
],
)
tests/integration/fixture/tool_agent/files/Agent_test_plan.pdf
BIN
View File
Binary file not shown.
tests/integration/fixture/trip_planner_agent/__init__.py
+15
View File
@@ -0,0 +1,15 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from . import agent
tests/integration/fixture/trip_planner_agent/agent.py
+110
View File
@@ -0,0 +1,110 @@
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# https://github.com/crewAIInc/crewAI-examples/tree/main/trip_planner
from google.adk import Agent
# Agent that selects the best city for the trip.
identify_agent = Agent(
name='identify_agent',
description='Select the best city based on weather, season, and prices.',
instruction="""
Analyze and select the best city for the trip based
on specific criteria such as weather patterns, seasonal
events, and travel costs. This task involves comparing
multiple cities, considering factors like current weather
conditions, upcoming cultural or seasonal events, and
overall travel expenses.
Your final answer must be a detailed
report on the chosen city, and everything you found out
about it, including the actual flight costs, weather
forecast and attractions.
Traveling from: {origin}
City Options: {cities}
Trip Date: {range}
Traveler Interests: {interests}
""",
)
# Agent that gathers information about the city.
gather_agent = Agent(
name='gather_agent',
description='Provide the BEST insights about the selected city',
instruction="""
As a local expert on this city you must compile an
in-depth guide for someone traveling there and wanting
to have THE BEST trip ever!
Gather information about key attractions, local customs,
special events, and daily activity recommendations.
Find the best spots to go to, the kind of place only a
local would know.
This guide should provide a thorough overview of what
the city has to offer, including hidden gems, cultural
hotspots, must-visit landmarks, weather forecasts, and
high level costs.
The final answer must be a comprehensive city guide,
rich in cultural insights and practical tips,
tailored to enhance the travel experience.
Trip Date: {range}
Traveling from: {origin}
Traveler Interests: {interests}
""",
)
# Agent that plans the trip.
plan_agent = Agent(
name='plan_agent',
description="""Create the most amazing travel itineraries with budget and
packing suggestions for the city""",
instruction="""
Expand this guide into a full 7-day travel
itinerary with detailed per-day plans, including
weather forecasts, places to eat, packing suggestions,
and a budget breakdown.
You MUST suggest actual places to visit, actual hotels
to stay and actual restaurants to go to.
This itinerary should cover all aspects of the trip,
from arrival to departure, integrating the city guide
information with practical travel logistics.
Your final answer MUST be a complete expanded travel plan,
formatted as markdown, encompassing a daily schedule,
anticipated weather conditions, recommended clothing and
items to pack, and a detailed budget, ensuring THE BEST
TRIP EVER. Be specific and give it a reason why you picked
each place, what makes them special!
Trip Date: {range}
Traveling from: {origin}
Traveler Interests: {interests}
""",
)
root_agent = Agent(
model='gemini-2.5-flash',
name='trip_planner',
description='Plan the best trip ever',
instruction="""
Your goal is to plan the best trip according to information listed above.
You describe why did you choose the city, list top 3
attractions and provide a detailed itinerary for each day.""",
sub_agents=[identify_agent, gather_agent, plan_agent],
)
tests/integration/fixture/trip_planner_agent/test_config.json
+5
View File
@@ -0,0 +1,5 @@
{
"criteria": {
"response_match_score": 0.5
}
}
tests/integration/fixture/trip_planner_agent/test_files/test_config.json
+5
View File
@@ -0,0 +1,5 @@
{
"criteria": {
"response_match_score": 0.5
}
}
tests/integration/fixture/trip_planner_agent/test_files/trip_inquiry_sub_agent.test.json
+64
View File
@@ -0,0 +1,64 @@
{
"eval_set_id": "189d6856-9b90-4b9c-bda8-7cec899507ae",
"name": "189d6856-9b90-4b9c-bda8-7cec899507ae",
"description": null,
"eval_cases": [
{
"eval_id": "tests/integration/fixture/trip_planner_agent/test_files/trip_inquiry_sub_agent.test.json",
"conversation": [
{
"invocation_id": "1c2e8003-d19c-4912-b0ae-17b9d568f8fb",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "Based on my interests, where should I go, Yosemite national park or Los Angeles?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"code_execution_result": null,
"executable_code": null,
"file_data": null,
"function_call": null,
"function_response": null,
"inline_data": null,
"text": "Given your interests in food, shopping, and museums, Los Angeles would be a better choice than Yosemite National Park. Yosemite is primarily focused on outdoor activities and natural landscapes, while Los Angeles offers a diverse range of culinary experiences, shopping districts, and world-class museums. I will now gather information to create an in-depth guide for your trip to Los Angeles.\n"
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [],
"intermediate_responses": []
},
"creation_timestamp": 1747339378.484014
}
],
"session_input": {
"app_name": "trip_planner_agent",
"user_id": "test_user",
"state": {
"origin": "San Francisco",
"interests": "Food, Shopping, Museums",
"range": "1000 miles",
"cities": ""
}
},
"creation_timestamp": 1747339378.484044
}
],
"creation_timestamp": 1747339378.484056
}
tests/integration/fixture/trip_planner_agent/trip_inquiry_multi_turn.test.json
+116
View File
@@ -0,0 +1,116 @@
{
"eval_set_id": "e7996ccc-16bc-46bf-9a24-0a3ecc3dacd7",
"name": "e7996ccc-16bc-46bf-9a24-0a3ecc3dacd7",
"description": null,
"eval_cases": [
{
"eval_id": "tests/integration/fixture/trip_planner_agent/trip_inquiry.test.json",
"conversation": [
{
"invocation_id": "d7ff8ec1-290b-48c5-b3aa-05cb8f27b8ae",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "Hi, who are you? What can you do?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "I am trip_planner, and my goal is to plan the best trip ever. I can describe why a city was chosen, list its top attractions, and provide a detailed itinerary for each day of the trip.\n"
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [],
"intermediate_responses": []
},
"creation_timestamp": 1750190885.419684
},
{
"invocation_id": "f515ff57-ff21-488f-ab92-7d7de5bb76fe",
"user_content": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "I want to travel from San Francisco to an European country in fall next year. I am considering London and Paris. What is your advice?"
}
],
"role": "user"
},
"final_response": {
"parts": [
{
"video_metadata": null,
"thought": null,
"inline_data": null,
"file_data": null,
"thought_signature": null,
"code_execution_result": null,
"executable_code": null,
"function_call": null,
"function_response": null,
"text": "Okay, I can help you analyze London and Paris to determine which city is better for your trip next fall. I will consider weather patterns, seasonal events, travel costs (including flights from San Francisco), and your interests (food, shopping, and museums). After gathering this information, I'll provide a detailed report on my chosen city.\n"
}
],
"role": "model"
},
"intermediate_data": {
"tool_uses": [
{
"id": null,
"args": {
"agent_name": "identify_agent"
},
"name": "transfer_to_agent"
}
],
"intermediate_responses": []
},
"creation_timestamp": 1750190885.4197457
}
],
"session_input": {
"app_name": "trip_planner_agent",
"user_id": "test_user",
"state": {
"origin": "San Francisco",
"interests": "Food, Shopping, Museums",
"range": "1000 miles",
"cities": ""
}
},
"creation_timestamp": 1750190885.4197533
}
],
"creation_timestamp": 1750190885.4197605
}