Encrypt sensitive credential in session state with KMS

.github/.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "2.6.3"
+  ".": "2.6.2"
 }

.github/workflows/continuous-integration.yml

@@ -44,11 +44,6 @@ jobs:
         with:
           persist-credentials: false
 
-      - name: Install the latest version of uv
-        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
-        with:
-          enable-cache: true
-
       - name: Run pre-commit checks
         uses: pre-commit/action@2c7b3805fd2a0fd8c1884dcaebf91fc102a13ecd # v3.0.1
 

.pre-commit-config.yaml

@@ -50,8 +50,8 @@ repos:
         language: system
         files: \.(py|sh)$
       - id: check-new-py-prefix
-        name: Check new Python files have _ prefix and unit guide
-        description: Enforces private-by-default policy and unit guide requirements for new Python files.
+        name: Check new Python files have _ prefix
+        description: Enforces private-by-default policy for new Python files (see .agents/skills/adk-style/references/visibility.md).
         entry: scripts/check_new_py_files.sh
         language: script
         files: ^src/google/adk/.*\.py$

CHANGELOG.md

@@ -1,12 +1,5 @@
 # Changelog
 
-## [2.6.3](https://github.com/google/adk-python/compare/v2.6.2...v2.6.3) (2026-08-07)
-
-
-### Bug Fixes
-
-* gate --sandbox-launcher behind gcloud beta run deploy ([8120292](https://github.com/google/adk-python/commit/8120292dd108704f5ed071b30dab2e8f019078ff))
-
 ## [2.6.2](https://github.com/google/adk-python/compare/v2.6.1...v2.6.2) (2026-08-03)
 
 ### Bug Fixes

README.md

@@ -4,7 +4,7 @@
 [![PyPI version](https://img.shields.io/pypi/v/google-adk.svg)](https://pypi.org/project/google-adk/)
 [![Python versions](https://img.shields.io/pypi/pyversions/google-adk.svg)](https://pypi.org/project/google-adk/)
 [![PyPI downloads](https://static.pepy.tech/badge/google-adk/month)](https://pepy.tech/project/google-adk)
-[![Continuous Integration](https://github.com/google/adk-python/actions/workflows/continuous-integration.yml/badge.svg)](https://github.com/google/adk-python/actions/workflows/continuous-integration.yml)
+[![Unit Tests](https://github.com/google/adk-python/actions/workflows/python-unit-tests.yml/badge.svg)](https://github.com/google/adk-python/actions/workflows/python-unit-tests.yml)
 [![Docs](https://img.shields.io/badge/docs-latest-blue.svg)](https://google.github.io/adk-docs/)
 
 <h2 align="center">
@@ -56,7 +56,7 @@ Choose the constraints file matching your Python version:
 
 ```bash
 # For example, for Python 3.10
-curl -o constraints-3.10.txt https://raw.githubusercontent.com/google/adk-python/main/constraints-3.10.txt
+curl -o constraints-3.10.txt https://github.com/google/adk-python/blob/main/constraints-3.10.txt
 pip install google-adk -c constraints-3.10.txt
 rm constraints-3.10.txt
 ```
@@ -121,13 +121,8 @@ adk web path/to/agents_dir
 ## 📚 Documentation
 
 - **Getting Started**: https://google.github.io/adk-docs/
-- **Guides**: See
-  [`docs/guides/`](https://github.com/google/adk-python/tree/main/docs/guides)
-  for task-oriented walkthroughs of agents, tools, events, plugins, and
-  workflows.
-- **Samples**: See
-  [`contributing/samples/`](https://github.com/google/adk-python/tree/main/contributing/samples)
-  for runnable example agents.
+- **Samples**: See `contributing/workflow_samples/` and
+  `contributing/task_samples/` for workflow and task API examples.
 
 ## 🤝 Contributing
 

contributing/samples/a2a/a2a_auth/README.md

@@ -61,14 +61,14 @@ The A2A OAuth Authentication sample consists of:
 
    ```bash
    # Start the remote a2a server that serves the BigQuery agent on port 8001
-   adk api_server --a2a --port 8001 contributing/samples/a2a/a2a_auth/remote_a2a
+   adk api_server --a2a --port 8001 contributing/samples/a2a_auth/remote_a2a
    ```
 
 1. **Run the Main Agent**:
 
    ```bash
    # In a separate terminal, run the adk web server
-   adk web contributing/samples/a2a
+   adk web contributing/samples/
    ```
 
 ### Example Interactions

contributing/samples/a2a/a2a_auth/agent.py

@@ -16,7 +16,7 @@
 from google.adk.agents.llm_agent import Agent
 from google.adk.agents.remote_a2a_agent import AGENT_CARD_WELL_KNOWN_PATH
 from google.adk.agents.remote_a2a_agent import RemoteA2aAgent
-from google.adk.integrations.langchain import LangchainTool
+from google.adk.tools.langchain_tool import LangchainTool
 from langchain_community.tools.youtube.search import YouTubeSearchTool
 
 # Instantiate the tool

contributing/samples/a2a/a2a_basic/README.md

@@ -54,14 +54,14 @@ The A2A Basic sample consists of:
 
    ```bash
    # Start the remote a2a server that serves the check prime agent on port 8001
-   adk api_server --a2a --port 8001 contributing/samples/a2a/a2a_basic/remote_a2a
+   adk api_server --a2a --port 8001 contributing/samples/a2a_basic/remote_a2a
    ```
 
 1. **Run the Main Agent**:
 
    ```bash
    # In a separate terminal, run the adk web server
-   adk web contributing/samples/a2a
+   adk web contributing/samples/
    ```
 
 ### Example Interactions

contributing/samples/a2a/a2a_human_in_loop/agent.py

@@ -13,8 +13,6 @@
 # limitations under the License.
 
 
-from typing import Any
-
 from google.adk.agents.llm_agent import Agent
 from google.adk.agents.remote_a2a_agent import AGENT_CARD_WELL_KNOWN_PATH
 from google.adk.agents.remote_a2a_agent import RemoteA2aAgent
@@ -23,7 +21,7 @@
 from google.genai import types
 
 
-def reimburse(purpose: str, amount: float) -> dict[str, Any]:
+def reimburse(purpose: str, amount: float) -> str:
   """Reimburse the amount of money to the employee."""
   return {
       'status': 'ok',
@@ -60,7 +58,7 @@ def reimburse(purpose: str, amount: float) -> dict[str, Any]:
 # the next turn to be routed back to the (remote) approval_agent so it can
 # resume the paused tool instead of restarting at the root reimbursement_agent,
 # the app must be resumable. Without this, the confirmation is delivered to the
-# root agent, which has no pending call, and nothing happens.
+# root agent, which has no pending call, and nothing happens (see issue #5871).
 app = App(
     name='a2a_human_in_loop',
     root_agent=root_agent,

contributing/samples/a2a/a2a_human_in_loop/remote_a2a/human_in_loop/agent.py

@@ -20,7 +20,7 @@
 from google.genai import types
 
 
-def reimburse(purpose: str, amount: float) -> dict[str, Any]:
+def reimburse(purpose: str, amount: float) -> str:
   """Reimburse the amount of money to the employee."""
   return {
       'status': 'ok',

contributing/samples/a2a/a2a_root/README.md

@@ -53,14 +53,14 @@ The A2A Root sample consists of:
 
    ```bash
    # Start the remote agent using uvicorn
-   uvicorn contributing.samples.a2a.a2a_root.remote_a2a.hello_world.agent:a2a_app --host localhost --port 8001
+   uvicorn contributing.samples.a2a_root.remote_a2a.hello_world.agent:a2a_app --host localhost --port 8001
    ```
 
 1. **Run the Main Agent**:
 
    ```bash
    # In a separate terminal, run the adk web server
-   adk web contributing/samples/a2a
+   adk web contributing/samples/
    ```
 
 ### Example Interactions
@@ -130,5 +130,5 @@ Bot: 3, 7 are prime numbers.
 
 **Uvicorn Issues:**
 
-- Make sure the module path is correct: `contributing.samples.a2a.a2a_root.remote_a2a.hello_world.agent:a2a_app`
+- Make sure the module path is correct: `contributing.samples.a2a_root.remote_a2a.hello_world.agent:a2a_app`
 - Check that all dependencies are installed

contributing/samples/adk_team/adk_answering_agent/README.md

@@ -12,12 +12,12 @@ ______________________________________________________________________
 
 ## Interactive Mode
 
-This mode allows you to run the agent locally to review its recommendations in real-time before any changes are made to your repository's discussions.
+This mode allows you to run the agent locally to review its recommendations in real-time before any changes are made to your repository's issues.
 
 ### Features
 
 - **Web Interface**: The agent's interactive mode can be rendered in a web browser using the ADK's `adk web` command.
-- **User Approval**: In interactive mode, the agent is instructed to ask for your confirmation before posting a comment to a GitHub discussion.
+- **User Approval**: In interactive mode, the agent is instructed to ask for your confirmation before posting a comment to a GitHub issue.
 - **Question & Answer**: You can ask ADK related questions, and the agent will provide answers based on its knowledge on ADK.
 
 ### Running in Interactive Mode
@@ -47,7 +47,7 @@ The `main.py` script supports batch processing for ADK oncall team to process di
 To run the agent in batch script mode, first set the required environment variables. Then, execute one of the following commands:
 
 ```bash
-export PYTHONPATH=contributing/samples/adk_team
+export PYTHONPATH=contributing/samples
 
 # Answer a specific discussion
 python -m adk_answering_agent.main --discussion_number 27
@@ -57,9 +57,6 @@ python -m adk_answering_agent.main --recent 10
 
 # Answer a discussion using direct JSON data (saves API calls)
 python -m adk_answering_agent.main --discussion '{"number": 27, "title": "How to...", "body": "I need help with...", "author": {"login": "username"}}'
-
-# Answer a discussion using JSON data read from a file
-python -m adk_answering_agent.main --discussion-file discussion.json
 ```
 
 ______________________________________________________________________
@@ -79,7 +76,7 @@ ______________________________________________________________________
 The `upload_docs_to_vertex_ai_search.py` is a script to upload ADK related docs to Vertex AI Search datastore to update the knowledge base. It can be executed with the following command in your terminal:
 
 ```bash
-export PYTHONPATH=contributing/samples/adk_team # If not already exported
+export PYTHONPATH=contributing/samples # If not already exported
 python -m adk_answering_agent.upload_docs_to_vertex_ai_search
 ```
 
@@ -93,7 +90,7 @@ The agent requires the following Python libraries.
 
 ```bash
 pip install --upgrade pip
-pip install google-adk google-cloud-discoveryengine
+pip install google-adk
 ```
 
 The agent also requires gcloud login:
@@ -105,14 +102,14 @@ gcloud auth application-default login
 The upload script requires the following additional Python libraries.
 
 ```bash
-pip install google-cloud-storage markdown
+pip install google-cloud-storage google-cloud-discoveryengine
 ```
 
 ### Environment Variables
 
 The following environment variables are required for the agent to connect to the necessary services.
 
-- `GITHUB_TOKEN=YOUR_GITHUB_TOKEN`: **(Required)** A GitHub Personal Access Token with read and write permissions for Discussions. Needed for both interactive and workflow modes.
+- `GITHUB_TOKEN=YOUR_GITHUB_TOKEN`: **(Required)** A GitHub Personal Access Token with `issues:write` permissions. Needed for both interactive and workflow modes.
 - `GOOGLE_GENAI_USE_ENTERPRISE=TRUE`: **(Required)** Use Google Vertex AI for the authentication.
 - `GOOGLE_CLOUD_PROJECT=YOUR_PROJECT_ID`: **(Required)** The Google Cloud project ID.
 - `GOOGLE_CLOUD_LOCATION=LOCATION`: **(Required)** The Google Cloud region.