ADK v0.4.0 release.

PiperOrigin-RevId: 754103716

.github/workflows/pyink.yml

@@ -0,0 +1,59 @@
+name: Check Pyink Formatting
+
+on:
+  pull_request:
+    paths:
+      - 'src/**/*.py'
+      - 'tests/**/*.py'
+      - 'pyproject.toml'
+
+jobs:
+  pyink-check:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.x'
+
+      - name: Install pyink
+        run: |
+          pip install pyink
+
+      - name: Detect changed Python files
+        id: detect_changes
+        run: |
+          git fetch origin ${{ github.base_ref }}
+          CHANGED_FILES=$(git diff --diff-filter=ACMR --name-only origin/${{ github.base_ref }}...HEAD | grep -E '\.py$' || true)
+          echo "CHANGED_FILES=${CHANGED_FILES}" >> $GITHUB_ENV
+
+      - name: Run pyink on changed files
+        if: env.CHANGED_FILES != ''
+        run: |
+          echo "Changed Python files:"
+          echo "$CHANGED_FILES"
+
+          # Run pyink --check
+          set +e
+          pyink --check --config pyproject.toml $CHANGED_FILES
+          RESULT=$?
+          set -e
+
+          if [ $RESULT -ne 0 ]; then
+            echo ""
+            echo "❌ Pyink formatting check failed!"
+            echo "👉 To fix formatting, run locally:"
+            echo ""
+            echo "    pyink --config pyproject.toml $CHANGED_FILES"
+            echo ""
+            exit $RESULT
+          fi
+
+      - name: No changed Python files detected
+        if: env.CHANGED_FILES == ''
+        run: |
+          echo "No Python files changed. Skipping pyink check."

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

@@ -35,5 +35,7 @@ jobs:
       run: |
         source .venv/bin/activate
         pytest tests/unittests \
-          --ignore=tests/unittests/tools/google_api_tool/test_googleapi_to_openapi_converter.py \
-          --ignore=tests/unittests/artifacts/test_artifact_service.py
+          --ignore=tests/unittests/artifacts/test_artifact_service.py \
+          --ignore=tests/unittests/tools/application_integration_tool/clients/test_connections_client.py \
+          --ignore=tests/unittests/tools/google_api_tool/test_googleapi_to_openapi_converter.py        
+          

CHANGELOG.md

@@ -1,5 +1,60 @@
 # Changelog
 
+## 0.4.0
+
+### ⚠ BREAKING CHANGES
+* Set the max size of strings in database columns. MySQL mandates that all VARCHAR-type fields must specify their lengths.
+* Extract content encode/decode logic to a shared util, resolve issues with JSON serialization, and update key length for DB table to avoid key too long issue in mysql.
+* Enhance `FunctionTool` to verify if the model is providing all the mandatory arguments.
+
+### Features
+* Update ADK setup guide to improve onboarding experience.
+* feat: add ordering to recent events in database session service.
+* feat(llm_flows): support async before/after tool callbacks.
+* feat: Added --replay and --resume options to adk run cli. Check adk run --help for more details.
+* Created a new Integration Connector Tool (underlying of the ApplicationIntegrationToolSet) so that we do not force LLM to provide default value.
+
+### Bug Fixes
+
+* Don't send content with empty text to LLM.
+* Fix google search reading undefined for `renderedContent`.
+
+### Miscellaneous Chores
+* Docstring improvements, typo fixings, github action to enfore code styles on formatting and imports, etc.
+
+## 0.3.0
+
+### ⚠ BREAKING CHANGES
+
+* Auth: expose `access_token` and `refresh_token` at top level of auth
+  credentails, instead of a `dict`
+  ([commit](https://github.com/google/adk-python/commit/956fb912e8851b139668b1ccb8db10fd252a6990)).
+
+### Features
+
+* Added support for running agents with MCPToolset easily on `adk web`.
+* Added `custom_metadata` field to `LlmResponse`, which can be used to tag
+  LlmResponse via `after_model_callback`.
+* Added `--session_db_url` to `adk deploy cloud_run` option.
+* Many Dev UI improvements:
+  * Better google search result rendering.
+  * Show websocket close reason in Dev UI.
+  * Better error message showing for audio/video.
+
+### Bug Fixes
+
+* Fixed MCP tool json schema parsing issue.
+* Fixed issues in DatabaseSessionService that leads to crash.
+* Fixed functions.py.
+* Fixed `skip_summarization` behavior in `AgentTool`.
+
+### Miscellaneous Chores
+
+* README.md impprovements.
+* Various code improvements.
+* Various typo fixes.
+* Bump min version of google-genai to 1.11.0.
+
 ## 0.2.0
 
 ### ⚠ BREAKING CHANGES
@@ -45,12 +100,12 @@
 * Initial release of the Agent Development Kit (ADK).
 * Multi-agent, agent-as-workflow, and custom agent support
 * Tool authentication support
-* Rich tool support, e.g. bult-in tools, google-cloud tools, third-party tools, and MCP tools
+* Rich tool support, e.g. built-in tools, google-cloud tools, third-party tools, and MCP tools
 * Rich callback support
 * Built-in code execution capability
 * Asynchronous runtime and execution
 * Session, and memory support
 * Built-in evaluation support
-* Development UI that makes local devlopment easy
+* Development UI that makes local development easy
 * Deploy to Google Cloud Run, Agent Engine
 * (Experimental) Live(Bidi) auido/video agent support and Compositional Function Calling(CFC) support

CONTRIBUTING.md

@@ -25,9 +25,22 @@ This project follows
 
 ## Contribution process
 
+### Requirement for PRs
+
+- All PRs, other than small documentation or typo fixes, should have a Issue assoicated. If not, please create one. 
+- Small, focused PRs. Keep changes minimal—one concern per PR.
+- For bug fixes or features, please provide logs or screenshot after the fix is applied to help reviewers better understand the fix.
+- Please add corresponding testing for your code change if it's not covered by existing tests.
+
+### Large or Complex Changes
+For substantial features or architectural revisions:
+
+- Open an Issue First: Outline your proposal, including design considerations and impact.
+- Gather Feedback: Discuss with maintainers and the community to ensure alignment and avoid duplicate work
+
 ### Code reviews
 
 All submissions, including submissions by project members, require review. We
 use GitHub pull requests for this purpose. Consult
 [GitHub Help](https://help.github.com/articles/about-pull-requests/) for more
-information on using pull requests.
+information on using pull requests.

README.md

@@ -18,11 +18,7 @@
     </h3>
 </html>
 
-Agent Development Kit (ADK) is designed for developers seeking fine-grained
-control and flexibility when building advanced AI agents that are tightly
-integrated with services in Google Cloud. It allows you to define agent
-behavior, orchestration, and tool use directly in code, enabling robust
-debugging, versioning, and deployment anywhere – from your laptop to the cloud.
+Agent Development Kit (ADK) is a flexible and modular framework for developing and deploying AI agents. While optimized for Gemini and the Google ecosystem, ADK is model-agnostic, deployment-agnostic, and is built for compatibility with other frameworks. ADK was designed to make agent development feel more like software development, to make it easier for developers to create, deploy, and orchestrate agentic architectures that range from simple tasks to complex workflows.
 
 
 ---
@@ -45,12 +41,27 @@ debugging, versioning, and deployment anywhere – from your laptop to the cloud
 
 ## 🚀 Installation
 
-You can install the ADK using `pip`:
+### Stable Release (Recommended)
+
+You can install the latest stable version of ADK using `pip`:
 
 ```bash
 pip install google-adk
 ```
 
+The release cadence is weekly.
+
+This version is recommended for most users as it represents the most recent official release.
+
+### Development Version
+Bug fixes and new features are merged into the main branch on GitHub first. If you need access to changes that haven't been included in an official PyPI release yet, you can install directly from the main branch:
+
+```bash
+pip install git+https://github.com/google/adk-python.git@main
+```
+
+Note: The development version is built directly from the latest code commits. While it includes the newest fixes and features, it may also contain experimental changes or bugs not present in the stable release. Use it primarily for testing upcoming changes or accessing critical fixes before they are officially released.
+
 ## 📚 Documentation
 
 Explore the full documentation for detailed guides on building, evaluating, and
@@ -112,10 +123,18 @@ adk eval \
     samples_for_testing/hello_world/hello_world_eval_set_001.evalset.json
 ```
 
+## 🤖 A2A and ADK integration
+
+For remote agent-to-agent communication, ADK integrates with the
+[A2A protocol](https://github.com/google/A2A/).
+See this [example](https://github.com/google/A2A/tree/main/samples/python/agents/google_adk)
+for how they can work together.
 
 ## 🤝 Contributing
 
-We welcome contributions from the community! Whether it's bug reports, feature requests, documentation improvements, or code contributions, please see our [**Contributing Guidelines**](./CONTRIBUTING.md) to get started.
+We welcome contributions from the community! Whether it's bug reports, feature requests, documentation improvements, or code contributions, please see our 
+- [General contribution guideline and flow](https://google.github.io/adk-docs/contributing-guide/#questions).
+- Then if you want to contribute code, please read [Code Contributing Guidelines](./CONTRIBUTING.md) to get started.
 
 ## 📄 License
 

pylintrc

@@ -45,7 +45,7 @@ confidence=
 # can either give multiple identifiers separated by comma (,) or put this
 # option multiple times (only on the command line, not in the configuration
 # file where it should appear only once).You can also use "--disable=all" to
-# disable everything first and then reenable specific checks. For example, if
+# disable everything first and then re-enable specific checks. For example, if
 # you want to run only the similarities checker, you can use "--disable=all
 # --enable=similarities". If you want to run only the classes checker, but have
 # no Warning level messages displayed, use"--disable=all --enable=classes

pyproject.toml

@@ -33,7 +33,7 @@ dependencies = [
   "google-cloud-secret-manager>=2.22.0",     # Fetching secrets in RestAPI Tool
   "google-cloud-speech>=2.30.0",             # For Audo Transcription
   "google-cloud-storage>=2.18.0, <3.0.0",    # For GCS Artifact service
-  "google-genai>=1.9.0",                     # Google GenAI SDK
+  "google-genai>=1.11.0",                    # Google GenAI SDK
   "graphviz>=0.20.2",                        # Graphviz for graph rendering
   "mcp>=1.5.0;python_version>='3.10'",       # For MCP Toolset
   "opentelemetry-api>=1.31.0",               # OpenTelemetry
@@ -119,6 +119,15 @@ line-length = 80
 unstable = true
 pyink-indentation = 2
 pyink-use-majority-quotes = true
+pyink-annotation-pragmas = [
+  "noqa",
+  "pylint:",
+  "type: ignore",
+  "pytype:",
+  "mypy:",
+  "pyright:",
+  "pyre-",
+]
 
 
 [build-system]
@@ -135,15 +144,10 @@ exclude = ['src/**/*.sh']
 name = "google.adk"
 
 [tool.isort]
-# Organize imports following Google style-guide
-force_single_line = true
-force_sort_within_sections = true
-honor_case_in_force_sorted_sections = true
-order_by_type = false
-sort_relative_in_force_sorted_sections = true
-multi_line_output = 3
-line_length = 200
+profile = "google"
+
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]
 asyncio_default_fixture_loop_scope = "function"
+asyncio_mode = "auto"

src/google/adk/agents/base_agent.py

@@ -44,7 +44,7 @@ Args:
   callback_context: MUST be named 'callback_context' (enforced).
 
 Returns:
-  The content to return to the user. When set, the agent run will skipped and
+  The content to return to the user. When set, the agent run will be skipped and
   the provided content will be returned to user.
 """
 
@@ -55,8 +55,8 @@ Args:
   callback_context: MUST be named 'callback_context' (enforced).
 
 Returns:
-  The content to return to the user. When set, the agent run will skipped and
-  the provided content will be appended to event history as agent response.
+  The content to return to the user. When set, the provided content will be
+  appended to event history as agent response.
 """
 
 
@@ -101,8 +101,8 @@ class BaseAgent(BaseModel):
     callback_context: MUST be named 'callback_context' (enforced).
 
   Returns:
-    The content to return to the user. When set, the agent run will skipped and
-    the provided content will be returned to user.
+    The content to return to the user. When set, the agent run will be skipped
+    and the provided content will be returned to user.
   """
   after_agent_callback: Optional[AfterAgentCallback] = None
   """Callback signature that is invoked after the agent run.
@@ -111,8 +111,8 @@ class BaseAgent(BaseModel):
     callback_context: MUST be named 'callback_context' (enforced).
 
   Returns:
-    The content to return to the user. When set, the agent run will skipped and
-    the provided content will be appended to event history as agent response.
+    The content to return to the user. When set, the provided content will be
+    appended to event history as agent response.
   """
 
   @final

src/google/adk/agents/callback_context.py

@@ -23,7 +23,6 @@ from .readonly_context import ReadonlyContext
 if TYPE_CHECKING:
   from google.genai import types
 
-  from ..events.event import Event
   from ..events.event_actions import EventActions
   from ..sessions.state import State
   from .invocation_context import InvocationContext

src/google/adk/agents/llm_agent.py

@@ -15,12 +15,7 @@
 from __future__ import annotations
 
 import logging
-from typing import Any
-from typing import AsyncGenerator
-from typing import Callable
-from typing import Literal
-from typing import Optional
-from typing import Union
+from typing import Any, AsyncGenerator, Awaitable, Callable, Literal, Optional, Union
 
 from google.genai import types
 from pydantic import BaseModel
@@ -62,11 +57,11 @@ AfterModelCallback: TypeAlias = Callable[
 ]
 BeforeToolCallback: TypeAlias = Callable[
     [BaseTool, dict[str, Any], ToolContext],
-    Optional[dict],
+    Union[Awaitable[Optional[dict]], Optional[dict]],
 ]
 AfterToolCallback: TypeAlias = Callable[
     [BaseTool, dict[str, Any], ToolContext, dict],
-    Optional[dict],
+    Union[Awaitable[Optional[dict]], Optional[dict]],
 ]
 
 InstructionProvider: TypeAlias = Callable[[ReadonlyContext], str]

src/google/adk/auth/auth_credential.py

@@ -66,7 +66,8 @@ class OAuth2Auth(BaseModelWithConfig):
   redirect_uri: Optional[str] = None
   auth_response_uri: Optional[str] = None
   auth_code: Optional[str] = None
-  token: Optional[Dict[str, Any]] = None
+  access_token: Optional[str] = None
+  refresh_token: Optional[str] = None
 
 
 class ServiceAccountCredential(BaseModelWithConfig):

src/google/adk/auth/auth_handler.py

@@ -82,7 +82,8 @@ class AuthHandler:
         or not auth_credential.oauth2
         or not auth_credential.oauth2.client_id
         or not auth_credential.oauth2.client_secret
-        or auth_credential.oauth2.token
+        or auth_credential.oauth2.access_token
+        or auth_credential.oauth2.refresh_token
     ):
       return self.auth_config.exchanged_auth_credential
 
@@ -93,7 +94,7 @@ class AuthHandler:
         redirect_uri=auth_credential.oauth2.redirect_uri,
         state=auth_credential.oauth2.state,
     )
-    token = client.fetch_token(
+    tokens = client.fetch_token(
         token_endpoint,
         authorization_response=auth_credential.oauth2.auth_response_uri,
         code=auth_credential.oauth2.auth_code,
@@ -102,7 +103,10 @@ class AuthHandler:
 
     updated_credential = AuthCredential(
         auth_type=AuthCredentialTypes.OAUTH2,
-        oauth2=OAuth2Auth(token=dict(token)),
+        oauth2=OAuth2Auth(
+            access_token=tokens.get("access_token"),
+            refresh_token=tokens.get("refresh_token"),
+        ),
     )
     return updated_credential
 

src/google/adk/cli/cli.py

@@ -39,12 +39,12 @@ class InputFile(BaseModel):
 
 async def run_input_file(
     app_name: str,
+    user_id: str,
     root_agent: LlmAgent,
     artifact_service: BaseArtifactService,
-    session: Session,
     session_service: BaseSessionService,
     input_path: str,
-) -> None:
+) -> Session:
   runner = Runner(
       app_name=app_name,
       agent=root_agent,
@@ -55,9 +55,11 @@ async def run_input_file(
     input_file = InputFile.model_validate_json(f.read())
   input_file.state['_time'] = datetime.now()
 
-  session.state = input_file.state
+  session = session_service.create_session(
+      app_name=app_name, user_id=user_id, state=input_file.state
+  )
   for query in input_file.queries:
-    click.echo(f'user: {query}')
+    click.echo(f'[user]: {query}')
     content = types.Content(role='user', parts=[types.Part(text=query)])
     async for event in runner.run_async(
         user_id=session.user_id, session_id=session.id, new_message=content
@@ -65,23 +67,23 @@ async def run_input_file(
       if event.content and event.content.parts:
         if text := ''.join(part.text or '' for part in event.content.parts):
           click.echo(f'[{event.author}]: {text}')
+  return session
 
 
 async def run_interactively(
-    app_name: str,
     root_agent: LlmAgent,
     artifact_service: BaseArtifactService,
     session: Session,
     session_service: BaseSessionService,
 ) -> None:
   runner = Runner(
-      app_name=app_name,
+      app_name=session.app_name,
       agent=root_agent,
       artifact_service=artifact_service,
       session_service=session_service,
   )
   while True:
-    query = input('user: ')
+    query = input('[user]: ')
     if not query or not query.strip():
       continue
     if query == 'exit':
@@ -100,7 +102,8 @@ async def run_cli(
     *,
     agent_parent_dir: str,
     agent_folder_name: str,
-    json_file_path: Optional[str] = None,
+    input_file: Optional[str] = None,
+    saved_session_file: Optional[str] = None,
     save_session: bool,
 ) -> None:
   """Runs an interactive CLI for a certain agent.
@@ -109,8 +112,11 @@ async def run_cli(
     agent_parent_dir: str, the absolute path of the parent folder of the agent
       folder.
     agent_folder_name: str, the name of the agent folder.
-    json_file_path: Optional[str], the absolute path to the json file, either
-      *.input.json or *.session.json.
+    input_file: Optional[str], the absolute path to the json file that contains
+      the initial session state and user queries, exclusive with
+      saved_session_file.
+    saved_session_file: Optional[str], the absolute path to the json file that
+      contains a previously saved session, exclusive with input_file.
     save_session: bool, whether to save the session on exit.
   """
   if agent_parent_dir not in sys.path:
@@ -118,46 +124,50 @@ async def run_cli(
 
   artifact_service = InMemoryArtifactService()
   session_service = InMemorySessionService()
-  session = session_service.create_session(
-      app_name=agent_folder_name, user_id='test_user'
-  )
 
   agent_module_path = os.path.join(agent_parent_dir, agent_folder_name)
   agent_module = importlib.import_module(agent_folder_name)
+  user_id = 'test_user'
+  session = session_service.create_session(
+      app_name=agent_folder_name, user_id=user_id
+  )
   root_agent = agent_module.agent.root_agent
   envs.load_dotenv_for_agent(agent_folder_name, agent_parent_dir)
-  if json_file_path:
-    if json_file_path.endswith('.input.json'):
-      await run_input_file(
-          app_name=agent_folder_name,
-          root_agent=root_agent,
-          artifact_service=artifact_service,
-          session=session,
-          session_service=session_service,
-          input_path=json_file_path,
-      )
-    elif json_file_path.endswith('.session.json'):
-      with open(json_file_path, 'r') as f:
-        session = Session.model_validate_json(f.read())
-      for content in session.get_contents():
-        if content.role == 'user':
-          print('user: ', content.parts[0].text)
+  if input_file:
+    session = await run_input_file(
+        app_name=agent_folder_name,
+        user_id=user_id,
+        root_agent=root_agent,
+        artifact_service=artifact_service,
+        session_service=session_service,
+        input_path=input_file,
+    )
+  elif saved_session_file:
+
+    loaded_session = None
+    with open(saved_session_file, 'r') as f:
+      loaded_session = Session.model_validate_json(f.read())
+
+    if loaded_session:
+      for event in loaded_session.events:
+        session_service.append_event(session, event)
+        content = event.content
+        if not content or not content.parts or not content.parts[0].text:
+          continue
+        if event.author == 'user':
+          click.echo(f'[user]: {content.parts[0].text}')
         else:
-          print(content.parts[0].text)
-      await run_interactively(
-          agent_folder_name,
-          root_agent,
-          artifact_service,
-          session,
-          session_service,
-      )
-    else:
-      print(f'Unsupported file type: {json_file_path}')
-      exit(1)
+          click.echo(f'[{event.author}]: {content.parts[0].text}')
+
+    await run_interactively(
+        root_agent,
+        artifact_service,
+        session,
+        session_service,
+    )
   else:
-    print(f'Running agent {root_agent.name}, type exit to exit.')
+    click.echo(f'Running agent {root_agent.name}, type exit to exit.')
     await run_interactively(
-        agent_folder_name,
         root_agent,
         artifact_service,
         session,
@@ -165,11 +175,8 @@ async def run_cli(
     )
 
   if save_session:
-    if json_file_path:
-      session_path = json_file_path.replace('.input.json', '.session.json')
-    else:
-      session_id = input('Session ID to save: ')
-      session_path = f'{agent_module_path}/{session_id}.session.json'
+    session_id = input('Session ID to save: ')
+    session_path = f'{agent_module_path}/{session_id}.session.json'
 
     # Fetch the session again to get all the details.
     session = session_service.get_session(

src/google/adk/cli/cli_deploy.py

@@ -54,7 +54,7 @@ COPY "agents/{app_name}/" "/app/agents/{app_name}/"
 
 EXPOSE {port}
 
-CMD adk {command} --port={port} {trace_to_cloud_option} "/app/agents"
+CMD adk {command} --port={port} {session_db_option} {trace_to_cloud_option} "/app/agents"
 """
 
 
@@ -85,6 +85,7 @@ def to_cloud_run(
     trace_to_cloud: bool,
     with_ui: bool,
     verbosity: str,
+    session_db_url: str,
 ):
   """Deploys an agent to Google Cloud Run.
 
@@ -112,6 +113,7 @@ def to_cloud_run(
     trace_to_cloud: Whether to enable Cloud Trace.
     with_ui: Whether to deploy with UI.
     verbosity: The verbosity level of the CLI.
+    session_db_url: The database URL to connect the session.
   """
   app_name = app_name or os.path.basename(agent_folder)
 
@@ -144,6 +146,9 @@ def to_cloud_run(
         port=port,
         command='web' if with_ui else 'api_server',
         install_agent_deps=install_agent_deps,
+        session_db_option=f'--session_db_url={session_db_url}'
+        if session_db_url
+        else '',
         trace_to_cloud_option='--trace_to_cloud' if trace_to_cloud else '',
     )
     dockerfile_path = os.path.join(temp_folder, 'Dockerfile')

src/google/adk/cli/cli_eval.py

@@ -256,7 +256,7 @@ def run_evals(
         )
 
         if final_eval_status == EvalStatus.PASSED:
-          result = "✅ Passsed"
+          result = "✅ Passed"
         else:
           result = "❌ Failed"
 

src/google/adk/cli/cli_tools_click.py

@@ -96,6 +96,23 @@ def cli_create_cmd(
   )
 
 
+def validate_exclusive(ctx, param, value):
+  # Store the validated parameters in the context
+  if not hasattr(ctx, "exclusive_opts"):
+    ctx.exclusive_opts = {}
+
+  # If this option has a value and we've already seen another exclusive option
+  if value is not None and any(ctx.exclusive_opts.values()):
+    exclusive_opt = next(key for key, val in ctx.exclusive_opts.items() if val)
+    raise click.UsageError(
+        f"Options '{param.name}' and '{exclusive_opt}' cannot be set together."
+    )
+
+  # Record this option's value
+  ctx.exclusive_opts[param.name] = value is not None
+  return value
+
+
 @main.command("run")
 @click.option(
     "--save_session",
@@ -105,13 +122,43 @@ def cli_create_cmd(
     default=False,
     help="Optional. Whether to save the session to a json file on exit.",
 )
+@click.option(
+    "--replay",
+    type=click.Path(
+        exists=True, dir_okay=False, file_okay=True, resolve_path=True
+    ),
+    help=(
+        "The json file that contains the initial state of the session and user"
+        " queries. A new session will be created using this state. And user"
+        " queries are run againt the newly created session. Users cannot"
+        " continue to interact with the agent."
+    ),
+    callback=validate_exclusive,
+)
+@click.option(
+    "--resume",
+    type=click.Path(
+        exists=True, dir_okay=False, file_okay=True, resolve_path=True
+    ),
+    help=(
+        "The json file that contains a previously saved session (by"
+        "--save_session option). The previous session will be re-displayed. And"
+        " user can continue to interact with the agent."
+    ),
+    callback=validate_exclusive,
+)
 @click.argument(
     "agent",
     type=click.Path(
         exists=True, dir_okay=True, file_okay=False, resolve_path=True
     ),
 )
-def cli_run(agent: str, save_session: bool):
+def cli_run(
+    agent: str,
+    save_session: bool,
+    replay: Optional[str],
+    resume: Optional[str],
+):
   """Runs an interactive CLI for a certain agent.
 
   AGENT: The path to the agent source code folder.
@@ -129,6 +176,8 @@ def cli_run(agent: str, save_session: bool):
       run_cli(
           agent_parent_dir=agent_parent_folder,
           agent_folder_name=agent_folder_name,
+          input_file=replay,
+          saved_session_file=resume,
           save_session=save_session,
       )
   )
@@ -245,12 +294,13 @@ def cli_eval(
 @click.option(
     "--session_db_url",
     help=(
-        "Optional. The database URL to store the session.\n\n  - Use"
-        " 'agentengine://<agent_engine_resource_id>' to connect to Vertex"
-        " managed session service.\n\n  - Use 'sqlite://<path_to_sqlite_file>'"
-        " to connect to a SQLite DB.\n\n  - See"
-        " https://docs.sqlalchemy.org/en/20/core/engines.html#backend-specific-urls"
-        " for more details on supported DB URLs."
+        """Optional. The database URL to store the session.
+
+  - Use 'agentengine://<agent_engine_resource_id>' to connect to Agent Engine sessions.
+
+  - Use 'sqlite://<path_to_sqlite_file>' to connect to a SQLite DB.
+
+  - See https://docs.sqlalchemy.org/en/20/core/engines.html#backend-specific-urls for more details on supported DB URLs."""
     ),
 )
 @click.option(
@@ -366,12 +416,13 @@ def cli_web(
 @click.option(
     "--session_db_url",
     help=(
-        "Optional. The database URL to store the session.\n\n  - Use"
-        " 'agentengine://<agent_engine_resource_id>' to connect to Vertex"
-        " managed session service.\n\n  - Use 'sqlite://<path_to_sqlite_file>'"
-        " to connect to a SQLite DB.\n\n  - See"
-        " https://docs.sqlalchemy.org/en/20/core/engines.html#backend-specific-urls"
-        " for more details on supported DB URLs."
+        """Optional. The database URL to store the session.
+
+  - Use 'agentengine://<agent_engine_resource_id>' to connect to Agent Engine sessions.
+
+  - Use 'sqlite://<path_to_sqlite_file>' to connect to a SQLite DB.
+
+  - See https://docs.sqlalchemy.org/en/20/core/engines.html#backend-specific-urls for more details on supported DB URLs."""
     ),
 )
 @click.option(
@@ -541,6 +592,18 @@ def cli_api_server(
     default="WARNING",
     help="Optional. Override the default verbosity level.",
 )
+@click.option(
+    "--session_db_url",
+    help=(
+        """Optional. The database URL to store the session.
+
+  - Use 'agentengine://<agent_engine_resource_id>' to connect to Agent Engine sessions.
+
+  - Use 'sqlite://<path_to_sqlite_file>' to connect to a SQLite DB.
+
+  - See https://docs.sqlalchemy.org/en/20/core/engines.html#backend-specific-urls for more details on supported DB URLs."""
+    ),
+)
 @click.argument(
     "agent",
     type=click.Path(
@@ -558,6 +621,7 @@ def cli_deploy_cloud_run(
     trace_to_cloud: bool,
     with_ui: bool,
     verbosity: str,
+    session_db_url: str,
 ):
   """Deploys an agent to Cloud Run.
 
@@ -579,6 +643,7 @@ def cli_deploy_cloud_run(
         trace_to_cloud=trace_to_cloud,
         with_ui=with_ui,
         verbosity=verbosity,
+        session_db_url=session_db_url,
     )
   except Exception as e:
     click.secho(f"Deploy failed: {e}", fg="red", err=True)

src/google/adk/cli/fast_api.py

@@ -756,6 +756,12 @@ def get_fast_api_app(
     except Exception as e:
       logger.exception("Error during live websocket communication: %s", e)
       traceback.print_exc()
+      WEBSOCKET_INTERNAL_ERROR_CODE = 1011
+      WEBSOCKET_MAX_BYTES_FOR_REASON = 123
+      await websocket.close(
+          code=WEBSOCKET_INTERNAL_ERROR_CODE,
+          reason=str(e)[:WEBSOCKET_MAX_BYTES_FOR_REASON],
+      )
     finally:
       for task in pending:
         task.cancel()