Merge branch 'main' into feature/support-mcp-tool-prefix

Author: calvingiles

.github/workflows/python-unit-tests.yml

@@ -51,6 +51,7 @@ jobs:
         if [[ "${{ matrix.python-version }}" == "3.9" ]]; then
           pytest tests/unittests \
             --ignore=tests/unittests/a2a \
+            --ignore=tests/unittests/tools/mcp_tool \
             --ignore=tests/unittests/artifacts/test_artifact_service.py \
             --ignore=tests/unittests/tools/google_api_tool/test_googleapi_to_openapi_converter.py
         else

CHANGELOG.md

@@ -1,5 +1,49 @@
 # Changelog
 
+## [1.4.2](https://github.com/google/adk-python/compare/v1.4.1...v1.4.2) (2025-06-20)
+
+
+### Bug Fixes
+
+* Add type checking to handle different response type of genai API client ([4d72d31](https://github.com/google/adk-python/commit/4d72d31b13f352245baa72b78502206dcbe25406))
+  * This fixes the broken VertexAiSessionService
+* Allow more credentials types for BigQuery tools ([2f716ad](https://github.com/google/adk-python/commit/2f716ada7fbcf8e03ff5ae16ce26a80ca6fd7bf6))
+
+## [1.4.1](https://github.com/google/adk-python/compare/v1.3.0...v1.4.1) (2025-06-18)
+
+
+### Features
+
+* Add Authenticated Tool (Experimental) ([dcea776](https://github.com/google/adk-python/commit/dcea7767c67c7edfb694304df32dca10b74c9a71))
+* Add enable_affective_dialog and proactivity to run_config and llm_request ([fe1d5aa](https://github.com/google/adk-python/commit/fe1d5aa439cc56b89d248a52556c0a9b4cbd15e4))
+* Add import session API in the fast API ([233fd20](https://github.com/google/adk-python/commit/233fd2024346abd7f89a16c444de0cf26da5c1a1))
+* Add integration tests for litellm with and without turning on add_function_to_prompt ([8e28587](https://github.com/google/adk-python/commit/8e285874da7f5188ea228eb4d7262dbb33b1ae6f))
+* Allow data_store_specs pass into ADK VAIS built-in tool ([675faef](https://github.com/google/adk-python/commit/675faefc670b5cd41991939fe0fc604df331111a))
+* Enable MCP Tool Auth (Experimental) ([157d9be](https://github.com/google/adk-python/commit/157d9be88d92f22320604832e5a334a6eb81e4af))
+* Implement GcsEvalSetResultsManager to handle storage of eval sets on GCS, and refactor eval set results manager ([0a5cf45](https://github.com/google/adk-python/commit/0a5cf45a75aca7b0322136b65ca5504a0c3c7362))
+* Re-factor some eval sets manager logic, and implement GcsEvalSetsManager to handle storage of eval sets on GCS ([1551bd4](https://github.com/google/adk-python/commit/1551bd4f4d7042fffb497d9308b05f92d45d818f))
+* Support real time input config ([d22920b](https://github.com/google/adk-python/commit/d22920bd7f827461afd649601326b0c58aea6716))
+* Support refresh access token automatically for rest_api_tool ([1779801](https://github.com/google/adk-python/commit/177980106b2f7be9a8c0a02f395ff0f85faa0c5a))
+
+### Bug Fixes
+
+* Fix Agent generate config err ([#1305](https://github.com/google/adk-python/issues/1305)) ([badbcbd](https://github.com/google/adk-python/commit/badbcbd7a464e6b323cf3164d2bcd4e27cbc057f))
+* Fix Agent generate config error ([#1450](https://github.com/google/adk-python/issues/1450)) ([694b712](https://github.com/google/adk-python/commit/694b71256c631d44bb4c4488279ea91d82f43e26))
+* Fix liteLLM test failures ([fef8778](https://github.com/google/adk-python/commit/fef87784297b806914de307f48c51d83f977298f))
+* Fix tracing for live ([58e07ca](https://github.com/google/adk-python/commit/58e07cae83048d5213d822be5197a96be9ce2950))
+* Merge custom http options with adk specific http options in model api request ([4ccda99](https://github.com/google/adk-python/commit/4ccda99e8ec7aa715399b4b83c3f101c299a95e8))
+* Remove unnecessary double quote on Claude docstring ([bbceb4f](https://github.com/google/adk-python/commit/bbceb4f2e89f720533b99cf356c532024a120dc4))
+* Set explicit project in the BigQuery client ([6d174eb](https://github.com/google/adk-python/commit/6d174eba305a51fcf2122c0fd481378752d690ef))
+* Support streaming in litellm + adk and add corresponding integration tests ([aafa80b](https://github.com/google/adk-python/commit/aafa80bd85a49fb1c1a255ac797587cffd3fa567))
+* Support project-based gemini model path to use google_search_tool ([b2fc774](https://github.com/google/adk-python/commit/b2fc7740b363a4e33ec99c7377f396f5cee40b5a))
+* Update conversion between Celsius and Fahrenheit ([1ae176a](https://github.com/google/adk-python/commit/1ae176ad2fa2b691714ac979aec21f1cf7d35e45))
+
+### Chores
+
+* Set `agent_engine_id` in the VertexAiSessionService constructor, also use the `agent_engine_id` field instead of overriding `app_name` in FastAPI endpoint ([fc65873](https://github.com/google/adk-python/commit/fc65873d7c31be607f6cd6690f142a031631582a))
+
+
+
 ## [1.3.0](https://github.com/google/adk-python/compare/v1.2.1...v1.3.0) (2025-06-11)
 
 

contributing/samples/bigquery/README.md

@@ -40,13 +40,28 @@ would set:
 ### With Application Default Credentials
 
 This mode is useful for quick development when the agent builder is the only
-user interacting with the agent. The tools are initialized with the default
-credentials present on the machine running the agent.
+user interacting with the agent. The tools are run with these credentials.
 
 1. Create application default credentials on the machine where the agent would
 be running by following https://cloud.google.com/docs/authentication/provide-credentials-adc.
 
-1. Set `RUN_WITH_ADC=True` in `agent.py` and run the agent
+1. Set `CREDENTIALS_TYPE=None` in `agent.py`
+
+1. Run the agent
+
+### With Service Account Keys
+
+This mode is useful for quick development when the agent builder wants to run
+the agent with service account credentials. The tools are run with these
+credentials.
+
+1. Create service account key by following https://cloud.google.com/iam/docs/service-account-creds#user-managed-keys.
+
+1. Set `CREDENTIALS_TYPE=AuthCredentialTypes.SERVICE_ACCOUNT` in `agent.py`
+
+1. Download the key file and replace `"service_account_key.json"` with the path
+
+1. Run the agent
 
 ### With Interactive OAuth
 
@@ -72,7 +87,7 @@ type.
   Note: don't create a separate .env, instead put it to the same .env file that
   stores your Vertex AI or Dev ML credentials
 
-1. Set `RUN_WITH_ADC=False` in `agent.py` and run the agent
+1. Set `CREDENTIALS_TYPE=AuthCredentialTypes.OAUTH2` in `agent.py` and run the agent
 
 ## Sample prompts
 

contributing/samples/bigquery/agent.py

@@ -15,31 +15,42 @@
 import os
 
 from google.adk.agents import llm_agent
+from google.adk.auth import AuthCredentialTypes
 from google.adk.tools.bigquery import BigQueryCredentialsConfig
 from google.adk.tools.bigquery import BigQueryToolset
 from google.adk.tools.bigquery.config import BigQueryToolConfig
 from google.adk.tools.bigquery.config import WriteMode
 import google.auth
 
-RUN_WITH_ADC = False
+# Define an appropriate credential type
+CREDENTIALS_TYPE = AuthCredentialTypes.OAUTH2
 
 
+# Define BigQuery tool config
 tool_config = BigQueryToolConfig(write_mode=WriteMode.ALLOWED)
 
-if RUN_WITH_ADC:
-  # Initialize the tools to use the application default credentials.
-  application_default_credentials, _ = google.auth.default()
-  credentials_config = BigQueryCredentialsConfig(
-      credentials=application_default_credentials
-  )
-else:
+if CREDENTIALS_TYPE == AuthCredentialTypes.OAUTH2:
   # Initiaze the tools to do interactive OAuth
   # The environment variables OAUTH_CLIENT_ID and OAUTH_CLIENT_SECRET
   # must be set
   credentials_config = BigQueryCredentialsConfig(
       client_id=os.getenv("OAUTH_CLIENT_ID"),
       client_secret=os.getenv("OAUTH_CLIENT_SECRET"),
   )
+elif CREDENTIALS_TYPE == AuthCredentialTypes.SERVICE_ACCOUNT:
+  # Initialize the tools to use the credentials in the service account key.
+  # If this flow is enabled, make sure to replace the file path with your own
+  # service account key file
+  # https://cloud.google.com/iam/docs/service-account-creds#user-managed-keys
+  creds, _ = google.auth.load_credentials_from_file("service_account_key.json")
+  credentials_config = BigQueryCredentialsConfig(credentials=creds)
+else:
+  # 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

contributing/samples/mcp_sse_agent/agent.py

@@ -16,8 +16,8 @@
 import os
 
 from google.adk.agents.llm_agent import LlmAgent
+from google.adk.tools.mcp_tool.mcp_session_manager import SseConnectionParams
 from google.adk.tools.mcp_tool.mcp_toolset import MCPToolset
-from google.adk.tools.mcp_tool.mcp_toolset import SseServerParams
 
 _allowed_path = os.path.dirname(os.path.abspath(__file__))
 
@@ -31,7 +31,7 @@
     """,
     tools=[
         MCPToolset(
-            connection_params=SseServerParams(
+            connection_params=SseConnectionParams(
                 url='http://localhost:3000/sse',
                 headers={'Accept': 'text/event-stream'},
             ),