chore!: bump version to 1.0.0, updated changelog.md and removed src/google/adk/tools/built_in_code_execution_tool.py

Mark src/google/adk/tools/_built_in_code_execution_tool.py as private and will be fully removed soon.

PiperOrigin-RevId: 760889060

CHANGELOG.md

@@ -1,5 +1,60 @@
 # Changelog
 
+## 1.0.0
+
+### ⚠ BREAKING CHANGES
+
+* Evaluation dataset schema is finalized with strong-type pydantic models.
+  (previously saved eval file needs re-generation, for both adk eval cli and
+  the eval tab in adk web UI).
+* `BuiltInCodeExecutor` (in code_executors package) replaces
+  `BuiltInCodeExecutionTool` (previously in tools package).
+* All methods in services are now async, including session service, artifact
+  service and memory service.
+  * `list_events` and `close_session` methods are removed from session service.
+* agent.py file structure with MCP tools are now easier and simpler ([now](https://github.com/google/adk-python/blob/3b5232c14f48e1d5b170f3698d91639b079722c8/contributing/samples/mcp_stdio_server_agent/agent.py#L33) vs [before](https://github.com/google/adk-python/blob/a4adb739c0d86b9ae4587547d2653d568f6567f2/contributing/samples/mcp_agent/agent.py#L41)).
+  Old format is not working anymore.
+* `Memory` schema and `MemoryService` is redesigned.
+* Mark various class attributes as private in the classes in the `tools` package.
+* Disabled session state injection if instruction provider is used.
+  (so that you can have `{var_name}` in the instruction, which is required for code snippets)
+* Toolbox integration is revamped: tools/toolbox_tool.py → tools/toolbox_toolset.py.
+* Removes the experimental `remote_agent.py`. We'll redesign it and bring it back.
+
+### Features
+
+* Dev UI:
+  * A brand new trace view for overall agent invocation.
+  * A revamped evaluation tab and comparison view for checking eval results.
+* Introduced `BaseToolset` to allow dynamically add/remove tools for agents.
+  * Revamped MCPToolset with the new BaseToolset interface.
+  * Revamped GoogleApiTool, GoogleApiToolset and ApplicationIntegrationToolset with the new BaseToolset interface.
+  * Resigned agent.py file structure when needing MCPToolset.
+  * Added ToolboxToolset.
+* Redesigned strong-typed agent evaluation schema.
+  * Allows users to create more cohesive eval sets.
+  * Allows evals to be extended for non-text modality.
+  * Allows for a structured interaction with the uber eval system.
+* Redesigned Memory schema and MemoryService interfaces.
+* Added token usage to LlmResponse.
+* Allowed specifying `--adk_version` in `adk deploy cloud_run` cli. Default is the current version.
+
+### Bug Fixes
+
+* Fixed `adk deploy cloud_run` failing bug.
+* Fixed logs not being printed due to `google-auth` library.
+
+### Miscellaneous Chores
+
+* Display full help text when adk cli receives invalid arguments.
+* `adk web` now binds `127.0.0.1` by default, instead of 0.0.0.0.
+* `InMemoryRunner` now takes `BaseAgent` in constructor.
+* Various docstring improvements.
+* Various UI tweaks.
+* Various bug fixes.
+* Update various contributing/samples for contributors to validate the implementation.
+
+
 ## 0.5.0
 
 ### ⚠ BREAKING CHANGES

src/google/adk/code_executors/built_in_code_executor.py

@@ -13,7 +13,6 @@
 # limitations under the License.
 
 from google.genai import types
-from pydantic import Field
 from typing_extensions import override
 
 from ..agents.invocation_context import InvocationContext

src/google/adk/runners.py

@@ -41,7 +41,7 @@ from .sessions.base_session_service import BaseSessionService
 from .sessions.in_memory_session_service import InMemorySessionService
 from .sessions.session import Session
 from .telemetry import tracer
-from .tools.built_in_code_execution_tool import built_in_code_execution
+from .tools._built_in_code_execution_tool import built_in_code_execution
 
 logger = logging.getLogger('google_adk.' + __name__)
 

src/google/adk/tools/__init__.py

@@ -16,7 +16,6 @@
 from ..auth.auth_tool import AuthToolArguments
 from .apihub_tool.apihub_toolset import APIHubToolset
 from .base_tool import BaseTool
-from .built_in_code_execution_tool import built_in_code_execution
 from .example_tool import ExampleTool
 from .exit_loop_tool import exit_loop
 from .function_tool import FunctionTool
@@ -34,7 +33,6 @@ __all__ = [
     'APIHubToolset',
     'AuthToolArguments',
     'BaseTool',
-    'built_in_code_execution',
     'google_search',
     'VertexAiSearchTool',
     'ExampleTool',

src/google/adk/tools/_built_in_code_execution_tool.py

@@ -52,8 +52,8 @@ class BuiltInCodeExecutionTool(BaseTool):
       llm_request: LlmRequest,
   ) -> None:
     logger.warning(
-        'BuiltInCodeExecutionTool is deprecated. Please use the new'
+        'BuiltInCodeExecutionTool is deprecated and will be removed in 1.1.0.'
-        ' BuiltInCodeExecutor instead.'
+        ' Please use the new BuiltInCodeExecutor instead.'
     )
     if llm_request.model and llm_request.model.startswith('gemini-2'):
       llm_request.config = llm_request.config or types.GenerateContentConfig()

src/google/adk/version.py

@@ -13,4 +13,4 @@
 # limitations under the License.
 
 # version: date+base_cl
-__version__ = "0.5.0"
+__version__ = "1.0.0"