Merge remote-tracking branch 'upstream/main'

Author: discopops

contributing/samples/adk_documentation/adk_release_analyzer/agent.py

@@ -548,3 +548,114 @@ def _git_grep(
       check=False,  # Don't raise error on non-zero exit code (1 means no match)
   )
   return grep_process
+
+
+def get_file_diff_for_release(
+    repo_owner: str,
+    repo_name: str,
+    start_tag: str,
+    end_tag: str,
+    file_path: str,
+) -> Dict[str, Any]:
+  """Gets the diff/patch for a specific file between two release tags.
+
+  This is useful for incremental processing where you want to analyze
+  one file at a time instead of loading all changes at once.
+
+  Args:
+      repo_owner: The name of the repository owner.
+      repo_name: The name of the repository.
+      start_tag: The older tag (base) for the comparison.
+      end_tag: The newer tag (head) for the comparison.
+      file_path: The relative path of the file to get the diff for.
+
+  Returns:
+      A dictionary containing the status and the file diff details.
+  """
+  url = f"{GITHUB_BASE_URL}/repos/{repo_owner}/{repo_name}/compare/{start_tag}...{end_tag}"
+
+  try:
+    comparison_data = get_request(url)
+    changed_files = comparison_data.get("files", [])
+
+    for file_data in changed_files:
+      if file_data.get("filename") == file_path:
+        return {
+            "status": "success",
+            "file": {
+                "relative_path": file_data.get("filename"),
+                "status": file_data.get("status"),
+                "additions": file_data.get("additions"),
+                "deletions": file_data.get("deletions"),
+                "changes": file_data.get("changes"),
+                "patch": file_data.get("patch", "No patch available."),
+            },
+        }
+
+    return error_response(f"File {file_path} not found in the comparison.")
+  except requests.exceptions.HTTPError as e:
+    return error_response(f"HTTP Error: {e}")
+  except requests.exceptions.RequestException as e:
+    return error_response(f"Request Error: {e}")
+
+
+def get_changed_files_summary(
+    repo_owner: str, repo_name: str, start_tag: str, end_tag: str
+) -> Dict[str, Any]:
+  """Gets a summary of changed files between two releases without patches.
+
+  This is a lighter-weight version of get_changed_files_between_releases
+  that only returns file paths and metadata, without the actual diff content.
+  Use this for planning which files to analyze.
+
+  Args:
+      repo_owner: The name of the repository owner.
+      repo_name: The name of the repository.
+      start_tag: The older tag (base) for the comparison.
+      end_tag: The newer tag (head) for the comparison.
+
+  Returns:
+      A dictionary containing the status and a summary of changed files.
+  """
+  url = f"{GITHUB_BASE_URL}/repos/{repo_owner}/{repo_name}/compare/{start_tag}...{end_tag}"
+
+  try:
+    comparison_data = get_request(url)
+    changed_files = comparison_data.get("files", [])
+
+    # Group files by directory for easier processing
+    files_by_dir: Dict[str, List[Dict[str, Any]]] = {}
+    formatted_files = []
+
+    for file_data in changed_files:
+      file_info = {
+          "relative_path": file_data.get("filename"),
+          "status": file_data.get("status"),
+          "additions": file_data.get("additions"),
+          "deletions": file_data.get("deletions"),
+          "changes": file_data.get("changes"),
+      }
+      formatted_files.append(file_info)
+
+      # Group by top-level directory
+      path = file_data.get("filename", "")
+      parts = path.split("/")
+      top_dir = parts[0] if parts else "root"
+      if top_dir not in files_by_dir:
+        files_by_dir[top_dir] = []
+      files_by_dir[top_dir].append(file_info)
+
+    return {
+        "status": "success",
+        "total_files": len(formatted_files),
+        "files": formatted_files,
+        "files_by_directory": files_by_dir,
+        "compare_url": (
+            f"https://github.com/{repo_owner}/{repo_name}"
+            f"/compare/{start_tag}...{end_tag}"
+        ),
+    }
+  except requests.exceptions.HTTPError as e:
+    return error_response(f"HTTP Error: {e}")
+  except requests.exceptions.RequestException as e:
+    return error_response(f"Request Error: {e}")

contributing/samples/adk_documentation/tools.py

@@ -24,11 +24,11 @@ distributed via the `google.adk.tools.bigquery` module. These tools include:
 5. `get_job_info`
   Fetches metadata about a BigQuery job.
 
-5. `execute_sql`
+6. `execute_sql`
 
   Runs or dry-runs a SQL query in BigQuery.
 
-6. `ask_data_insights`
+7. `ask_data_insights`
 
   Natural language-in, natural language-out tool that answers questions
   about structured data in BigQuery. Provides a one-stop solution for generating
@@ -38,18 +38,18 @@ distributed via the `google.adk.tools.bigquery` module. These tools include:
   the official [Conversational Analytics API documentation](https://cloud.google.com/gemini/docs/conversational-analytics-api/overview)
   for instructions.
 
-7. `forecast`
+8. `forecast`
 
   Perform time series forecasting using BigQuery's `AI.FORECAST` function,
   leveraging the TimesFM 2.0 model.
 
-8. `analyze_contribution`
+9. `analyze_contribution`
 
   Perform contribution analysis in BigQuery by creating a temporary
   `CONTRIBUTION_ANALYSIS` model and then querying it with
   `ML.GET_INSIGHTS` to find top contributors for a given metric.
 
-9. `detect_anomalies`
+10. `detect_anomalies`
 
   Perform time series anomaly detection in BigQuery by creating a temporary
   `ARIMA_PLUS` model and then querying it with

contributing/samples/bigquery/README.md

@@ -0,0 +1,55 @@
+# BigQuery MCP Toolset Sample
+
+## Introduction
+
+This sample agent demonstrates using ADK's `McpToolset` to interact with
+BigQuery's official MCP endpoint, allowing an agent to access and execute
+toole by leveraging the Model Context Protocol (MCP). These tools include:
+
+
+1. `list_dataset_ids`
+
+  Fetches BigQuery dataset ids present in a GCP project.
+
+2. `get_dataset_info`
+
+  Fetches metadata about a BigQuery dataset.
+
+3. `list_table_ids`
+
+  Fetches table ids present in a BigQuery dataset.
+
+4. `get_table_info`
+
+  Fetches metadata about a BigQuery table.
+
+5. `execute_sql`
+
+  Runs or dry-runs a SQL query in BigQuery.
+
+## How to use
+
+Set up your project and local authentication by following the guide
+[Use the BigQuery remote MCP server](https://docs.cloud.google.com/bigquery/docs/use-bigquery-mcp).
+This agent uses Application Default Credentials (ADC) to authenticate with the
+BigQuery MCP endpoint.
+
+Set up environment variables in your `.env` file for using
+[Google AI Studio](https://google.github.io/adk-docs/get-started/quickstart/#gemini---google-ai-studio)
+or
+[Google Cloud Vertex AI](https://google.github.io/adk-docs/get-started/quickstart/#gemini---google-cloud-vertex-ai)
+for the LLM service for your agent. For example, for using Google AI Studio you
+would set:
+
+* GOOGLE_GENAI_USE_VERTEXAI=FALSE
+* GOOGLE_API_KEY={your api key}
+
+Then run the agent using `adk run .` or `adk web .` in this directory.
+
+## Sample prompts
+
+* which weather datasets exist in bigquery public data?
+* tell me more about noaa_lightning
+* which tables exist in the ml_datasets dataset?
+* show more details about the penguins table
+* compute penguins population per island.

contributing/samples/bigquery_mcp/README.md

@@ -0,0 +1,15 @@
+# Copyright 2025 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

contributing/samples/bigquery_mcp/__init__.py

@@ -0,0 +1,51 @@
+# Copyright 2025 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.agents.llm_agent import LlmAgent
+from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPConnectionParams
+from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
+import google.auth
+
+BIGQUERY_AGENT_NAME = "adk_sample_bigquery_mcp_agent"
+BIGQUERY_MCP_ENDPOINT = "https://bigquery.googleapis.com/mcp"
+BIGQUERY_SCOPE = "https://www.googleapis.com/auth/bigquery"
+
+# Initialize the tools to use the application default credentials.
+# https://cloud.google.com/docs/authentication/provide-credentials-adc
+credentials, project_id = google.auth.default(scopes=[BIGQUERY_SCOPE])
+credentials.refresh(google.auth.transport.requests.Request())
+oauth_token = credentials.token
+
+bigquery_mcp_toolset = McpToolset(
+    connection_params=StreamableHTTPConnectionParams(
+        url=BIGQUERY_MCP_ENDPOINT,
+        headers={"Authorization": f"Bearer {oauth_token}"},
+    )
+)
+
+# 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 using MCP."
+    ),
+    instruction="""\
+        You are a data science agent with access to several BigQuery tools provided via MCP.
+        Make use of those tools to answer the user's questions.
+    """,
+    tools=[bigquery_mcp_toolset],
+)

contributing/samples/bigquery_mcp/agent.py

@@ -0,0 +1,15 @@
+# Copyright 2025 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