Compare commits

..

151 Commits

Author SHA1 Message Date
Wei Sun (Jack) 93a085ad87 chore(version): Bumps version to 1.24.1 patch
Co-authored-by: Wei Sun (Jack) <weisun@google.com>
PiperOrigin-RevId: 866107525
2026-02-05 14:13:02 -08:00
Google Team Member 6645aa07fd feat: Add experimental agent tool simulator
PiperOrigin-RevId: 866100611
2026-02-05 13:57:57 -08:00
Yifan Wang 3686a3a98f chore: update adk web files, updated eval dialog colors, and fixed a2ui component types
Co-authored-by: Yifan Wang <wanyif@google.com>
PiperOrigin-RevId: 866057812
2026-02-05 12:16:54 -08:00
Yifan Wang ae993e884f fix: adding back deprecated eval endpoint for web until we migrate
Co-authored-by: Yifan Wang <wanyif@google.com>
PiperOrigin-RevId: 866049699
2026-02-05 11:58:04 -08:00
George Weale bb89466623 chore: Improve type hints and handle None values in ADK utils
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 866025998
2026-02-05 11:04:46 -08:00
Xuan Yang adbc37fea1 feat: Add progress_callback support to MCPTool and MCPToolset
Fixes: https://github.com/google/adk-python/issues/3811

Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 866025995
2026-02-05 11:04:36 -08:00
George Weale 9b112e2d13 fix: Refactor context filtering to better handle multi-turn invocations
The definition of an "invocation" for context filtering has been updated. An invocation now starts with a user message and can include multiple model turns (like the tool calls and responses) until the next user message. The filtering logic has been rewritten to identify invocation start points based on human user messages

Close #4296

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 866023290
2026-02-05 10:57:56 -08:00
Google Team Member a08bf62b95 feat(otel): add extra attributes to span generated with opentelemetry-instrumentation-google-genai
PiperOrigin-RevId: 865825792
2026-02-05 01:58:30 -08:00
Liang Wu e752bbb756 chore: Remove unused tzlocal dependency and logging
The `tzlocal` library and the logging of the local timezone were not used in the `DatabaseSessionService` logic.

Co-authored-by: Liang Wu <wuliang@google.com>
PiperOrigin-RevId: 865677320
2026-02-04 18:49:55 -08:00
Wei Sun (Jack) fb941f9011 chore(version): Bump version and update changelog for 1.24.0
Co-authored-by: Wei Sun (Jack) <weisun@google.com>
PiperOrigin-RevId: 865651579
2026-02-04 17:26:50 -08:00
Yifan Wang de44bbc17c chore: update adk web
Co-authored-by: Yifan Wang <wanyif@google.com>
PiperOrigin-RevId: 865625039
2026-02-04 16:13:51 -08:00
Kathy Wu 7deffb16fd fix: pass tool context into require_confirmation function in McpTool
Aligns with the FunctionTool implementation of require_confirmation. This fixes https://github.com/google/adk-python/issues/4327.

Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 865566362
2026-02-04 13:55:39 -08:00
nikkie ac1401bd44 fix: Escape Click’s Wrapping in bulled lists of adk web options
Merge https://github.com/google/adk-python/pull/4338

### Link to Issue or Description of Change

**2. Or, if no issue exists, describe the change:**

**Problem:**
Click collapses intended bullet lists in the service URI options.

<img width="709" height="267" alt="image" src="https://github.com/user-attachments/assets/5f74d8a6-f343-41a4-ba6d-570ed0076932" />

**Solution:**
Add `\b` on a line by itself before the formatted block to preserve blank lines.

### Testing Plan

This is format improvement of help message, so I think there is no need to add test case.

**Unit Tests:**

- [ ] I have added or updated unit tests for my change.
- [x] All unit tests pass locally.

```
% pytest tests/unittests/cli  # Python 3.13.8
===================================== 260 passed, 140 warnings in 9.30s ======================================
```

**Manual End-to-End (E2E) Tests:**

`adk web --help`

```
  --session_service_uri TEXT      Optional. The URI of the session service. If set, ADK uses this service.

                                  If unset, ADK chooses a default session service (see
                                  --use_local_storage).
                                  - Use 'agentengine://<agent_engine>' to connect to Agent Engine
                                    sessions. <agent_engine> can either be the full qualified resource
                                    name 'projects/abc/locations/us-central1/reasoningEngines/123' or
                                    the resource id '123'.
                                  - Use 'memory://' to run with the in-memory session service.
                                  - 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 supported database URIs.
```

### Checklist

- [x] I have read the [CONTRIBUTING.md](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) document.
- [x] I have performed a self-review of my own code.
- [x] I have commented my code, particularly in hard-to-understand areas.
- [x] I have added tests that prove my fix is effective or that my feature works.
- [x] New and existing unit tests pass locally with my changes.
- [x] I have manually tested my changes end-to-end.
- [x] Any dependent changes have been merged and published in downstream modules.

COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/4338 from ftnext:escape-wrapping-web-options-bullet-list 9466731aff293d241cc7ae5728bc3c34c5c89dd6
PiperOrigin-RevId: 865533252
2026-02-04 12:40:13 -08:00
Gabriel Bengo 3c63c2ad39 fix(docs): fix grammar and remove duplicate words in documentation and source
Merge https://github.com/google/adk-python/pull/4335

Fixed 'the the' typos and grammatical errors in README, docstrings, and sample agents.

**Please ensure you have read the [contribution guide](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) before creating a pull request.**

### Link to Issue or Description of Change

**1. Link to an existing issue (if applicable):**

- Closes: N/A
- Related: N/A

**2. Or, if no issue exists, describe the change:**

**Problem:**
While exploring the repository, I noticed a few minor writing errors that impact professional readability:
1.  **Grammar:** A subject-verb agreement error in `README.md` and `llms.txt` ("guide the agents works together").
2.  **Duplicate Words:** Several instances of stuttering typos (repeating "the the" or "but the the") in docstrings within `src/` and the `contributing/samples/` directories.

**Solution:**
I have applied the following fixes to improve documentation quality:
*   Corrected phrasing to "guide the agents to work together" in the README.
*   Removed redundant instances of "the" in `eval_metrics.py`, `spanner/settings.py`, and the sample agent docstrings.
*   **No functional code or logic was altered.**

### Testing Plan

**Unit Tests:**

- [x] All unit tests pass locally.

_Summary:_
Since this PR is strictly limited to documentation, comments, and docstrings, no new tests were required. I ran the standard test suite to ensure no syntax errors were accidentally introduced, and everything passed successfully.

**Manual End-to-End (E2E) Tests:**
N/A — This is a static documentation fix.

### Checklist

- [x] I have read the [CONTRIBUTING.md](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) document.
- [x] I have performed a self-review of my own code.
- [ ] I have commented my code, particularly in hard-to-understand areas. (N/A)
- [ ] I have added tests that prove my fix is effective or that my feature works. (N/A - Doc fix only)
- [x] New and existing unit tests pass locally with my changes.
- [ ] I have manually tested my changes end-to-end. (N/A)
- [x] Any dependent changes have been merged and published in downstream modules.

### Additional context

_None._

COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/4335 from 88448844:fix-typos-and-docs 200668dad0c216b81d7008d9d6625ac135c9006e
PiperOrigin-RevId: 865530036
2026-02-04 12:31:54 -08:00
George Weale f90adff8c5 fix: Add query parameters to /run_live for advanced run configurations
The /run_live websocket endpoint now accepts proactive_audio, enable_affective_dialog, and enable_session_resumption as query parameters. These parameters control the corresponding settings within the RunConfig used for the live session

Close #4263

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 865441673
2026-02-04 09:24:01 -08:00
Google Team Member 1de65cf314 No public description
PiperOrigin-RevId: 865138065
2026-02-03 18:26:30 -08:00
Xuan Yang 2220d885cd fix: Check will_continue for streaming function calls
Related: https://github.com/google/adk-python/issues/4311

Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 865074872
2026-02-03 15:33:44 -08:00
Yifan Wang 37e6507ce4 chore: update adk_web, re-work events, and adding A2UI capabilities
Co-authored-by: Yifan Wang <wanyif@google.com>
PiperOrigin-RevId: 865027256
2026-02-03 13:42:44 -08:00
Yeesian Ng 004e15ccb7 feat: Allow passthrough of GOOGLE_CLOUD_LOCATION for AgentEngine deployments
Co-authored-by: Yeesian Ng <ysian@google.com>
PiperOrigin-RevId: 865013321
2026-02-03 13:11:45 -08:00
George Weale 574ec43a17 chore: Improve error handling for LiteLlm import in gemma_llm.py
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 865010258
2026-02-03 13:04:27 -08:00
Liang Wu ce07cd8144 fix(cli): ignore session_db_kwargs for sqlite session services
Close issue #4317

Co-authored-by: Liang Wu <wuliang@google.com>
PiperOrigin-RevId: 864979145
2026-02-03 11:49:13 -08:00
George Weale 706a6dda81 fix: Update OpenTelemetry dependency versions
Relax version constraints for opentelemetry-api and opentelemetry-sdk to allow versions between 1.36.0 and 1.40.0

Close #4229

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 864896212
2026-02-03 08:41:39 -08:00
George Weale da73e718ef fix: Enable pool_pre_ping by default for non-SQLite database engines
This change sets `pool_pre_ping=True` in SQLAlchemy engine kwargs for database backends other than SQLite. This helps ensure that connections from the pool are still valid before being used, preventing issues with stale or disconnected connections. Tests are added to verify the default behavior and that explicit overrides are respected

Close #4211

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 864886767
2026-02-03 08:16:55 -08:00
Google Team Member 125bc85ac5 fix: Resolving MutualTLSChannelError 'OpenSSL' module error on by adding pyopenssl dependency in pyproject.toml
- Add 'pyopenssl' to project dependencies to fix MutualTLSChannelError  encountered during mTLS channel configuration.

PiperOrigin-RevId: 864874340
2026-02-03 07:43:09 -08:00
Google Team Member 6ff10b23be chore: Replace proxy methods with utils implementation
PiperOrigin-RevId: 864802559
2026-02-03 04:01:55 -08:00
Google Team Member f82ceb0ce7 chore: Replace proxy methods with utils implementation
PiperOrigin-RevId: 864773118
2026-02-03 02:27:46 -08:00
George Weale 33012e6dda fix: Make credential key generation stable and prevent cross-user credential leaks
This change updates the credential key generation to use a stable hash (SHA256) instead of Python's built-in hash, which can vary based on PYTHONHASHSEED. It also makes sure that temporary or exchanged OAuth2 fields are excluded from the key calculation. I also added when saving credentials, a copy of the AuthConfig is used to avoid modifying the original shared AuthConfig instance with user-specific exchanged credentials.

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 864599326
2026-02-02 17:51:19 -08:00
George Weale 666cebe369 fix: Add update_timestamp_tz property to StorageSession
This property is a compatibility alias that returns the update timestamp as a POSIX timestamp. It infers whether the database is SQLite using sqlalchemy.inspect to call get_update_timestamp correctly

Close #4334

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 864595914
2026-02-02 17:39:42 -08:00
George Weale dd8cd27b2c chore: Replace print statements with logging in ADK
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 864588921
2026-02-02 17:16:27 -08:00
Max Ind e87a8437fb feat(otel): add extra attributes to span generated with opentelemetry-instrumentation-google-genai
Co-authored-by: Max Ind <maxind@google.com>
PiperOrigin-RevId: 864272319
2026-02-02 03:17:08 -08:00
Google Team Member 7d58e0d2f3 feat: Mark Vertex calls made from non-gemini models
PiperOrigin-RevId: 864253424
2026-02-02 02:23:56 -08:00
Vasilii Novikov 9290b96626 feat: Make OpenAPI tool async
Merge https://github.com/google/adk-python/pull/2872

Closes https://github.com/google/adk-python/issues/787

The OpenAPI tool has been ported to the httpx client to make requests truly asynchronous.

COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/2872 from condorcet:async_openapi_tool bf83f73af93f624126462fb0bd41fef27c53a0b6
PiperOrigin-RevId: 864250822
2026-02-02 02:15:52 -08:00
Xiang (Sean) Zhou 2770012cec chore: Add sample agent that need to go through oauth flow during mcp tool listing
Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 864133951
2026-02-01 20:22:25 -08:00
Xiang (Sean) Zhou 131fbd3948 fix: Fix Pydantic Schema Generation Error for ClientSession
Problem: The test test_openapi_json_schema_accessible was failing because Pydantic couldn't generate a JSON schema for mcp.client.session.ClientSession, which is part of genai_types.ToolListUnion.

Root Cause: The AgentDetails model in src/google/adk/evaluation/app_details.py:37 had tool_declarations: genai_types.ToolListUnion, and ToolListUnion includes mcp.client.session.ClientSession which doesn't have Pydantic core schema support. This model is used in the FastAPI app through EvalCase → Invocation → AppDetails → AgentDetails, causing OpenAPI schema generation to fail.

Solution: Changed the type annotation from genai_types.ToolListUnion to list[Any] in two places:

AgentDetails.tool_declarations
_ToolDeclarations.tool_declarations

This allows Pydantic to generate the OpenAPI schema while maintaining runtime compatibility (the field still accepts the same values).

Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 863765002
2026-01-31 16:26:30 -08:00
Xiang (Sean) Zhou 798f65df86 feat(tools): Implement toolset auth for McpToolset, OpenAPIToolset, and others
Update existing toolsets to utilize the new toolset authentication framework. Key changes:
        - McpToolset: Add _auth_config instance variable, _get_auth_headers()
          method to build auth headers from exchanged credentials, and
          get_auth_config() override. Auth headers are now included when
          creating MCP sessions.
        - OpenAPIToolset: Add _auth_config and get_auth_config() to expose
          auth configuration to the framework.
        - ApplicationIntegrationToolset: Add _auth_config and get_auth_config().
        - APIHubToolset: Add _auth_config and get_auth_config().

When ADK resolves toolset auth before calling get_tools(), it populates exchanged_auth_credential on the auth_config. Toolsets can then use this credential when making authenticated requests.

Also update test fixtures in test_apihub_toolset.py to use real auth objects instead of mocks that fail pydantic validation.

Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 863764941
2026-01-31 16:25:46 -08:00
Xiang (Sean) Zhou ee873cae2e feat(auth): Add framework support for toolset authentication before get_tools
This change adds framework-level support for resolving toolset authentication before calling get_tools(). Key changes:
    - Add _resolve_toolset_auth() method in BaseLlmFlow that iterates
      through toolsets, checks for auth config, and resolves credentials
      via CredentialManager before tool listing
    - Add TOOLSET_AUTH_CREDENTIAL_ID_PREFIX constant for identifying
      toolset auth requests
    - Add skip logic in auth_preprocessor to not resume function calls
      for toolset auth (they do not need it)
    - Add get_auth_response() method to CallbackContext for retrieving
      auth credentials from session state
    - Update CredentialManager to accept CallbackContext instead of
      requiring ToolContext

When a toolset needs authentication but credentials are not available, the flow yields an adk_request_credential event and interrupts the invocation, allowing the user to complete the OAuth flow before retrying.

Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 863543036
2026-01-30 22:36:13 -08:00
Xiang (Sean) Zhou fe82f3cde8 fix!: Make credential manager to accept tool_context instead of callback_context
This seems a breaking change, but actually credential manager is used internally only and also it won't work if some one call it using callback context

Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 863534476
2026-01-30 21:59:43 -08:00
George Weale 798d0053c8 fix: Stream errors as simple JSON objects in ADK web server SSE
The ADK web server's /run_sse endpoint now yields a JSON object like {"error": "..."} when an exception occurs during event generation. The adk_web_server_client is updated to detect this error payload and raise a RuntimeError.

Close #4291

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 863475838
2026-01-30 18:18:31 -08:00
George Weale d0102ecea3 fix: Recognize function responses as non-empty parts in LiteLLM
The `_part_has_payload` helper now returns False for parts containing a function response, preventing the addition of fallback user content when a user turn consists solely of tool outputs.

Close #4249

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 863319497
2026-01-30 11:20:50 -08:00
Liang Wu 63a8eba53f fix: Ensure database sessions are always rolled back on errors
Fixes issue#3328

Co-authored-by: Liang Wu <wuliang@google.com>
PiperOrigin-RevId: 863314939
2026-01-30 11:10:02 -08:00
George Weale 47221cd5c1 fix: Handle HTTP/HTTPS URLs for media files in LiteLLM content conversion
For providers that typically require file IDs (like OpenAI and Azure), if a file URI is an HTTP/HTTPS URL and the MIME type is image, video, or audio, convert it to the corresponding URL-based content type (e.g., "image_url") instead of using the generic "file" type

Close #4112

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 863311703
2026-01-30 11:02:29 -08:00
George Weale 2ac468ea7e fix: Add pre-deployment validation for agent module imports
This change introduces a new function, _validate_agent_import, which attempts to import the user's agent.py file before the deployment process begins. This helps catch common issues such as missing dependencies, incorrect relative imports, or syntax errors in the agent code early, providing more informative error messages to the user.

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 863310033
2026-01-30 10:58:15 -08:00
Google Team Member 00aba2d884 feat: Improve asyncio loop handling and test cleanup
This CL enhances asyncio event loop management and test isolation.

-   **BigQuery Analytics Plugin:** Ensure the asyncio event loop is consistently closed within the BigQuery analytics plugin. This prevents potential resource leaks. Add checks to handle potential deadlocks in Python 3.13+ when creating loops during interpreter shutdown.
-   **Test Thread Pool Cleanup:** Introduce a pytest fixture (`cleanup_thread_pools`) to automatically shut down and clear all tool-related thread pools after each test run in `test_functions_thread_pool.py`. This improves test isolation and prevents order-dependent test failures.
-   **Streaming Test Loop Restoration:** Refactor event loop handling in `test_streaming.py`. A new `_run_with_loop` method is introduced in the custom test runners to create a temporary event loop for each test execution, run the coroutine, and crucially, restore the original event loop afterwards. This prevents tests from interfering with each other's loop state.
-   **Resource Closure:** Ensure services are closed properly in tests by adding `await service.close()` in `test_service_factory.py` and using `async with session_service` in `test_session_service.py`.

PiperOrigin-RevId: 863305565
2026-01-30 10:47:09 -08:00
Xuan Yang 585ebfdac7 feat: Support dynamic config for VertexAiSearchTool
Close: https://github.com/google/adk-python/issues/4067

Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 862965769
2026-01-29 17:09:49 -08:00
Google Team Member c0c98d94b3 test: Ensure BigQueryAgentAnalyticsPlugin is shut down after each test
Improves test reliability by guaranteeing the BigQueryAgentAnalyticsPlugin is shut down after each test execution. This is achieved by wrapping test logic in try/finally blocks, using a yield fixture, or employing a new asynccontextmanager to ensure the plugin.shutdown() method is always called, preventing potential resource leaks between tests.

PiperOrigin-RevId: 862951816
2026-01-29 16:31:04 -08:00
Xuan Yang 288c2c448d chore: Add ADK logger in RestApiTool
Fixes: https://github.com/google/adk-python/issues/3780

Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 862897383
2026-01-29 14:17:52 -08:00
Kathy Wu ecce7e54a6 fix: Change MCP read_resource to return the original contents
Since we will save MCP resource contents to the artifact service, no need to do post-processing based on mime type. Also fixed the implementation; the correct method to call is session.read_resource(uri).

Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 862885513
2026-01-29 13:51:45 -08:00
Xiang (Sean) Zhou 381d44cab4 feat: Add get_auth_config method to toolset to expose auth requirement of the toolset
Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 862597425
2026-01-29 00:23:24 -08:00
Kathy Wu 4341839420 chore: Convert MCPToolset to McpToolset in unittests
MCPToolset has been deprecated, use McpToolset instead.

Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 862457868
2026-01-28 17:04:14 -08:00
Sara Robinson 32f9f92042 chore: Add GitHub Action check to run mypy
Merge https://github.com/google/adk-python/pull/4276

This adds 2 mypy GitHub Actions checks:

* `mypy.yml` runs mypy on every PR. This will list all errors, so it shouldn't block until errors are resolved.
* `mypy-new-errors.yml` compares the PR branch to `main` to ensure no new mypy errors are introduced. This check can be made blocking now and can be removed once all errors are resolved in favor of `mypy.yml`.

### Checklist

- [x] I have read the [CONTRIBUTING.md](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) document.
- [x] I have performed a self-review of my own code.
- [x] I have commented my code, particularly in hard-to-understand areas.
- [x] I have added tests that prove my fix is effective or that my feature works.
- [x] New and existing unit tests pass locally with my changes.
- [x] I have manually tested my changes end-to-end.
- [x] Any dependent changes have been merged and published in downstream modules.

COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/4276 from sararob:mypy-gh-actions 63130773c4862e90e352d4cb79221d78a6b9f5fd
PiperOrigin-RevId: 862226296
2026-01-28 07:27:52 -08:00
Google Team Member a16e3cc67e fix: Fix cases where execution_result_delimiters have None type element due to code_execution_result.output is None
PiperOrigin-RevId: 861933883
2026-01-27 16:29:51 -08:00
Kathy Wu 8f7d9659cf feat: Add methods in MCPToolset for users to access MCP resources (read_resource, list_resources, get_resource_info)
This allows users to access MCP resources on their own within agent logic / using custom tools. I plan on also later adding it to the agent state.

Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 861910520
2026-01-27 15:26:59 -08:00
Google Team Member 3480b3b82d feat: improve error message when failing to get tools from MCP
Include the underlying exception message in the ConnectionError raised when session.list_tools() fails.

PiperOrigin-RevId: 861889733
2026-01-27 14:33:47 -08:00
Liang Wu 65cbf4b35c fix: Make OpenAPI /docs path work again
* The main fix is in eval_metrics.py
* Removed some deprecated paths in the FastAPI server
* Added a unit test to catch future breakages
* Bump fastapi version to be 0.124.1 to capture the fix in https://github.com/fastapi/fastapi/pull/14482
* Removed the upper-bound restriction on fastapi version which was used to temporarily fix the issue

Fixes #3173

Co-authored-by: Liang Wu <wuliang@google.com>
PiperOrigin-RevId: 861867708
2026-01-27 13:41:26 -08:00
Keyur Joshi 4ee125a038 feat: Add interface for agent optimizers
Details:
* The Sampler allows ADK agent optimizers to request evals and receive detailed eval results that can be used to guide agent optimization.
* This interface allows developers to run custom evaluations if needed for their agent. An implementation to interface with the inbuilt LocalEvalService shall be published shortly in a follow-up PR.
* The AgentOptimizer interface describes the general framework for an ADK agent optimizer that uses the Sampler interface to optimize an ADK agent.
* data_types.py contains generic types and base classes to allow intercommunication between the AgentOptimizer, Sampler, and developer code.

Co-authored-by: Keyur Joshi <keyurj@google.com>
PiperOrigin-RevId: 861849691
2026-01-27 12:56:21 -08:00
Xuan Yang 2155a35c51 docs: Update ADK release analyzer to use Gemini 3 Pro with retry and improve file filtering
Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 861784867
2026-01-27 10:31:03 -08:00
nikkie 3bcd8f7f7a fix: EscapieClick’s Wrapping in adk eval help (#4258)
Fix https://github.com/google/adk-python/issues/4257

https://click.palletsprojects.com/en/stable/documentation/#escaping-click-s-wrapping

Co-authored-by: Ankur <ankusharma@google.com>
2026-01-27 09:13:55 -08:00
Google Team Member c34615ecf3 fix: disable save_input_blobs_as_artifacts deprecation warning message for users that don't set it
PiperOrigin-RevId: 861738532
2026-01-27 08:38:46 -08:00
Shangjie Chen 1063fa532c fix: Reload the stale session in database_session_service when the update_time of storage is later than the current in memory session object
This changes the behavior of how we handle stale session, instead of reject the transaction entirely, we aggresively refresh the session.

Removed synchronous inspect(self).session calls within StorageSession.update_timestamp_tz and _dialect_name. This introspection was causing deadlocks/hangs when used with sqlalchemy.ext.asyncio in Python 3.13.

Closes issue: https://github.com/google/adk-python/issues/1733

Co-authored-by: Shangjie Chen <deanchen@google.com>
PiperOrigin-RevId: 861353058
2026-01-26 14:19:14 -08:00
Ankur Sharma 43d6075ea7 feat: allow Vertex AI Client initialization with API Key
Co-authored-by: Ankur Sharma <ankusharma@google.com>
PiperOrigin-RevId: 861335865
2026-01-26 13:36:41 -08:00
Joseph Pagadora 553e376718 feat: Remove overall_eval_status calculation from _CustomMetricEvaluator and add threshold to custom metric function expected signature
Co-authored-by: Joseph Pagadora <jcpagadora@google.com>
PiperOrigin-RevId: 861268984
2026-01-26 11:01:32 -08:00
Jinhyuk Kim 85434e293f feat: Pass event id as a metadata when it is converted into a message
PiperOrigin-RevId: 860929058
2026-01-25 16:05:45 -08:00
Google Team Member 324796b4fe feat: This change restructures the bug report template as per intake process
PiperOrigin-RevId: 860304319
2026-01-23 16:43:56 -08:00
Xuan Yang 853a3b0e14 fix: Do not treat FCs and FRs as invisible when marked as thoughts
Related: https://github.com/google/adk-python/issues/4159

Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 860254198
2026-01-23 14:25:42 -08:00
Xiang (Sean) Zhou 714c3ad047 feat: Support run tools in separate thread for live mode
Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 860242861
2026-01-23 13:55:31 -08:00
George Weale 801233902b fix: fix agent config path handling in generated deployment script
The generated agent deployment script now uses os.path.join and os.path.dirname(__file__) to construct the path to root_agent.yaml. This prevents issues where backslashes in Windows paths could be misinterpreted as Python escape sequences within the f-string, leading to syntax error

Close #4223

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 860236820
2026-01-23 13:39:32 -08:00
Liang Wu 025b42c836 chore: Add unittests.sh script and update CONTRIBUTING.md
This change introduces a new `unittests.sh` script to simplify running unit tests. The script automatically sets up a minimal test environment, runs `pytest`, and then restores the previous development environment. The CONTRIBUTING.md has been updated to include instructions on using this new script.

Co-authored-by: Liang Wu <wuliang@google.com>
PiperOrigin-RevId: 860222798
2026-01-23 13:01:06 -08:00
Xiang (Sean) Zhou 753084fd46 refactor: Extract helper function for llm request building and response processing
Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 860212868
2026-01-23 12:34:04 -08:00
Google Team Member 2380afd287 feat: Refine Feature Request Issue Template
This change updates the feature request issue template to include required and recommended sections. New questions are added to gather more details on the problem, impact, willingness to contribute, and potential API/implementation ideas. Existing questions are rephrased for clarity

PiperOrigin-RevId: 860199885
2026-01-23 12:00:38 -08:00
Kathy Wu 316463be86 docs: Move mcp session feature out of breaking changes
Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 860199237
2026-01-23 11:58:54 -08:00
Xuan Yang 83c24d2e74 docs: Fix ADK release analyzer agent for large releases
Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 860187312
2026-01-23 11:29:42 -08:00
Shangjie Chen e8f7aa3140 fix: Add pypika>=0.50.0 to project.toml since crewai depends on it and the default version does not work with py 3.12+
Co-authored-by: Shangjie Chen <deanchen@google.com>
PiperOrigin-RevId: 860181604
2026-01-23 11:15:19 -08:00
Google Team Member 7edfb2701c docs: update data agent README to match the behavior
PiperOrigin-RevId: 860180180
2026-01-23 11:11:56 -08:00
Max Ind 0d38a3683f fix: remove print debugging artifact
Co-authored-by: Max Ind <maxind@google.com>
PiperOrigin-RevId: 860038888
2026-01-23 03:59:44 -08:00
Kathy Wu 7cf1e447d7 chore: Bumps version to v1.23.0 and updates CHANGELOG.md
Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 859790616
2026-01-22 15:03:52 -08:00
Xuan Yang 3f1b0d0957 chore: minor fix for DebugLoggingPlugin example
Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 859762221
2026-01-22 14:00:17 -08:00
Max Ind 935c279f82 feat(otel): add minimal generate_content {model.name} spans and logs for non-gemini inference and when opentelemetry-inference-google-genai dependency is missing
Co-authored-by: Max Ind <maxind@google.com>
PiperOrigin-RevId: 859667045
2026-01-22 10:18:06 -08:00
Google Team Member 82fa10b71e feat: add new conversational analytics api tool set
PiperOrigin-RevId: 859449435
2026-01-21 23:31:37 -08:00
Xuan Yang bf2b56de6d fix: recursively extract input/output schema for AgentTool
Fixes: https://github.com/google/adk-python/issues/4154

Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 859440231
2026-01-21 23:02:33 -08:00
Liang Wu 3d96b7883b chore: Pin litellm dependency to versions below 1.80.17
This is a stopgap before the actual fix is added for 1.80.17+.

Co-authored-by: Liang Wu <wuliang@google.com>
PiperOrigin-RevId: 859351463
2026-01-21 18:43:26 -08:00
Didier Durand 91ec80c606 docs: fixing multiple typos
Merge https://github.com/google/adk-python/pull/4221

### Link to Issue or Description of Change

N/A

**2. Or, if no issue exists, describe the change:**

Fixing various typos in .py files to improve quality: see commit diffs for details

**Problem:**

See above

**Solution:**
Fixing the typos

### Testing Plan

N/A

**Unit Tests:**

N/A

**Manual End-to-End (E2E) Tests:**

N/A

### Checklist

- [X] I have read the [CONTRIBUTING.md](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) document.
- [X] I have performed a self-review of my own code.
- [N/A] I have commented my code, particularly in hard-to-understand areas.
- [N/A ] I have added tests that prove my fix is effective or that my feature works.
- [N/A] New and existing unit tests pass locally with my changes.
- [N/A] I have manually tested my changes end-to-end.
- [N/A ] Any dependent changes have been merged and published in downstream modules.

### Additional context

N/A

COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/4221 from didier-durand:fix-typos-e 1bcc8e05cdc116451222dd7fd7b0657745f769c1
PiperOrigin-RevId: 859332402
2026-01-21 17:33:51 -08:00
Shangjie Chen 295b345587 chore: Filter out adk_request_input event from content list
Co-authored-by: Shangjie Chen <deanchen@google.com>
PiperOrigin-RevId: 859321034
2026-01-21 16:55:50 -08:00
lwangverizon b57a3d43e4 feat: Allow google search tool to set different model
Merge https://github.com/google/adk-python/pull/4136

**Please ensure you have read the [contribution guide](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) before creating a pull request.**

### Link to Issue or Description of Change

**1. Link to an existing issue (if applicable):**

Allow google search tool to set different model #4135

**2. Or, if no issue exists, describe the change:**

_If applicable, please follow the issue templates to provide as much detail as
possible._

**Problem:**
Currently, the Google Search tool inherits and uses the same LLM model set from the parent agent for processing and summarizing search results. This creates a limitation for users who wish to decouple the agent's reasoning model from the model used for search summarization (e.g., for cost optimization or using a lightweight model for simpler summarization tasks).

**Solution:**
I have updated the Google Search tool to accept an optional LLM model parameter.
Custom Model: Users can now explicitly specify which model should be used for processing search results.
Default Behavior: If no model is specified, the tool defaults to the parent agent's model, ensuring backward compatibility.

```
    # If a custom model is specified, use it instead of the original model
    if self.model is not None:
      llm_request.model = self.model
```

### Testing Plan

Added a new test case test_process_llm_request_with_custom_model in [test_google_search_tool.py] that verifies:

When a custom model parameter is provided to GoogleSearchTool, it overrides the model from the incoming llm_request during process_llm_request
The tool correctly uses the custom model for LLM calls while maintaining other request parameters

**Unit Tests:**

- [X] I have added or updated unit tests for my change.
- [X] All unit tests pass locally.

(base) wanglu2:adk-python/ (feature/allow-google-search-tool-set-different-llm✗) $ uv run pytest ./tests/unittests/tools/test_google_search_tool.py       [22:07:32]
======================================================================== test session starts ========================================================================
platform darwin -- Python 3.13.1, pytest-9.0.2, pluggy-1.6.0
rootdir: /Users/wanglu2/Documents/Git/adk-python
configfile: pyproject.toml
plugins: mock-3.15.1, anyio-4.12.0, xdist-3.8.0, asyncio-1.3.0, langsmith-0.6.0
asyncio: mode=Mode.AUTO, debug=False, asyncio_default_fixture_loop_scope=function, asyncio_default_test_loop_scope=function
collected 21 items

tests/unittests/tools/test_google_search_tool.py .....................                                                                                        [100%]

======================================================================== 21 passed in 7.91s =========================================================================

### Checklist

- [X] I have read the [CONTRIBUTING.md](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) document.
- [X] I have performed a self-review of my own code.
- [X] I have commented my code, particularly in hard-to-understand areas.
- [X] I have added tests that prove my fix is effective or that my feature works.
- [X] New and existing unit tests pass locally with my changes.
- [X] I have manually tested my changes end-to-end.
- [ ] Any dependent changes have been merged and published in downstream modules.

### Additional context

Co-authored-by: Kathy Wu <wukathy@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/4136 from lwangverizon:feature/allow-google-search-tool-set-different-llm 239ea9577bd7befc9a3574aca48dc8243d55192c
PiperOrigin-RevId: 859265757
2026-01-21 14:31:45 -08:00
Google Team Member 9579bea05d feat(plugins): Add flush mechanism to BigQueryAgentAnalyticsPlugin
This change introduces a `flush` method to the `BigQueryAgentAnalyticsPlugin`. This ensures that all pending log events are written to BigQuery before the agent's run completes.

Key changes:

- Added `flush()` method to `BigQueryAgentAnalyticsPlugin` to force write of pending events.

PiperOrigin-RevId: 859263853
2026-01-21 14:27:03 -08:00
Liang Wu 3e3566bd0e chore: Pin litellm dependency to versions below 1.81.0
Update the litellm version constraint in both project dependencies and dev dependencies to exclude versions 1.81.0 and higher because unit test breakages in GitHub actions introduced by it.

This is a stopgap before the actual fix is added. Close #4225

Co-authored-by: Liang Wu <wuliang@google.com>
PiperOrigin-RevId: 859239880
2026-01-21 13:31:01 -08:00
Xiang (Sean) Zhou a04828dd8a feat: Persist user input content to session in live mode
Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 859207592
2026-01-21 12:11:01 -08:00
Didier Durand 5d941460b6 docs: Fix various typos
Merge https://github.com/google/adk-python/pull/4186

COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/4186 from didier-durand:main f8a52b58e133551bec1d98660fd552afd881a8b9
PiperOrigin-RevId: 859203551
2026-01-21 12:01:54 -08:00
Xiang (Sean) Zhou e3d542a5ba feat: Support authentication for MCP tool listing
Currently only tool calling supports MCP auth. This refactors the auth logic into a auth_utils file and uses it for tool listing as well. Fixes https://github.com/google/adk-python/issues/2168.

Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 859201722
2026-01-21 11:57:34 -08:00
Xuan Yang d62f9c896c chore: Always skip executing partial function calls
Related: https://github.com/google/adk-python/issues/4159

Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 859184844
2026-01-21 11:20:16 -08:00
Google Team Member 7b25b8fb1d fix(runner): Yield buffered function_call/function_response events during live streaming
Bug: In live streaming mode, when function_call and function_response events
arrive during active transcription, they are correctly buffered but never
yielded to the caller. This causes callers to miss these events even though
they are saved to the session.

Fix: Add yield buffered_event after appending buffered events to the session
when transcription ends.

Testing:
- Added unit test: test_live_streaming_buffered_function_call_yielded_during_transcription
- Test verifies buffered events are yielded by:
  1. Simulating partial transcription (triggers buffering)
  2. Sending function_call during transcription (gets buffered)
  3. Ending transcription (should yield buffered events)
  4. Asserting both function_call and function_response are in yielded events

Test results:
- With fix: PASSED
- Without fix (yield commented out): FAILED with "Buffered function_call event was not yielded"
- Example event flow after fix:
EVENT: partial=True, input_transcription="Show me the weather"
EVENT: function_call=get_weather, args={'location': 'NYC'} <- Now yielded
EVENT: function_response=get_weather, response={...} <- Now yielded
EVENT: partial=False, input_transcription="Show me the weather for today"
PiperOrigin-RevId: 859158546
2026-01-21 10:21:39 -08:00
Kathy Wu 910f65473f docs: Update to gemini-2.5-flash for api registry and mcp sample agents
Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 859151854
2026-01-21 10:06:46 -08:00
Google Team Member ab89d12834 refactor(plugins)!: use OpenTelemetry for BigQuery plugin tracing
This refactors the BigQueryAgentAnalyticsPlugin to use the standard OpenTelemetry API for trace and span ID generation and propagation, replacing the custom ContextVar implementation.

Key changes:
- Utilizes `opentelemetry.trace` for starting/ending spans.
- Correctly uses `opentelemetry.context` for context attachment and detachment.
- Span information is now derived from the OpenTelemetry context when available.
- Added a fallback mechanism to ensure span_id and parent_span_id are still populated if the OpenTelemetry SDK is not initialized.

To get standard OpenTelemetry trace information in BigQuery logs, users should install `opentelemetry-sdk` and initialize a global `TracerProvider` in their application *before* initializing ADK components.

Example minimal initialization:
```python
# Install: pip install opentelemetry-sdk
from opentelemetry import trace
from opentelemetry.sdk.trace import TracerProvider
trace.set_tracer_provider(TracerProvider())
```

PiperOrigin-RevId: 858965562
2026-01-21 01:05:53 -08:00
Wei Sun (Jack) 645bd0ed10 docs: Switches to gemini 2.5 flash for two samples
Co-authored-by: Wei Sun (Jack) <weisun@google.com>
PiperOrigin-RevId: 858826742
2026-01-20 17:38:53 -08:00
Xiang (Sean) Zhou 1699b090ed chore: Update the comments of request confirmation preprocessor
Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 858816547
2026-01-20 17:04:05 -08:00
George Weale 2367901ec5 chore: Upgrade to headers to 2026
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 858763407
2026-01-20 14:50:09 -08:00
Didier Durand a8f2ddd943 chore: fixing various typos
Merge https://github.com/google/adk-python/pull/4175

### Link to Issue or Description of Change

**1. Link to an existing issue (if applicable):**

N/A: just fixing typos discovered while reading the repo

**2. Or, if no issue exists, describe the change:**

No code change, just typo fixes: see commit diffs for all details

**Problem:**

Trying to improve overall repo quality

**Solution:**

Fixing typos as they get discovered

### Testing Plan

N/A

**Unit Tests:**

N/A

**Manual End-to-End (E2E) Tests:**

N/A

### Checklist

- [X] I have read the [CONTRIBUTING.md](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) document.
- [X] I have performed a self-review of my own code.
- [ ] I have commented my code, particularly in hard-to-understand areas.
- [ ] I have added tests that prove my fix is effective or that my feature works.
- [X] New and existing unit tests pass locally with my changes.
- [ ] I have manually tested my changes end-to-end.
- [ ] Any dependent changes have been merged and published in downstream modules.

COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/4175 from didier-durand:fix-typos-c 16e93ed2d9bc153fa0332ab1ae39633fcc5056e9
PiperOrigin-RevId: 858751240
2026-01-20 14:21:01 -08:00
George Weale 7955177fb2 fix: Update dependency versions in pyproject.toml
Bump authlib to >=1.6.6 and mcp to >=1.23.0.

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 858728187
2026-01-20 13:29:34 -08:00
George Weale 215c2f506e fix: Set LITELLM_MODE to PRODUCTION before importing LiteLLM
LiteLLM defaults to DEV mode, which automatically loads environment variables from a local `.env` file. This change sets LITELLM_MODE to PRODUCTION to prevent LiteLLM from implicitly loading `.env` files when used within ADK.

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 858723362
2026-01-20 13:16:38 -08:00
Lusha Wang 135f763325 feat: Remove @experimental decorator from AgentEngineSandboxCodeExecutor
Co-authored-by: Lusha Wang <lusha@google.com>
PiperOrigin-RevId: 858706929
2026-01-20 12:36:56 -08:00
George Weale 5257869d91 fix: Redact sensitive information from URIs in logs
This change introduces a helper function `_redact_uri_for_log` to sanitize URIs before logging. It removes user credentials from the netloc and redacts the values of query parameters, ensuring that sensitive information like passwords is not exposed in log outputs. The function is applied to all log statements and error messages that include service URIs for session, memory, and artifact services

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 858703465
2026-01-20 12:27:27 -08:00
Xuan Yang 53b67ce634 feat: Add --disable_features CLI option to ADK CLI
This flag can be used to override default feature enable state.

Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 858659818
2026-01-20 10:45:32 -08:00
Wiktoria Walczak 21f63f66ee feat(cli): add otel_to_cloud flag to adk deploy agent_engine command
Co-authored-by: Wiktoria Walczak <wwalczak@google.com>
PiperOrigin-RevId: 858546581
2026-01-20 05:41:39 -08:00
Xuan Yang 69ad605bc4 feat: Use json schema for base_retrieval_tool, load_artifacts_tool, and load_memory_tool declaration when feature enabled
Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 858435881
2026-01-19 23:36:53 -08:00
Liang Wu 4b29d15b3e fix: Handle async driver URLs in migration tool
The migration tool uses synchronous SQLAlchemy engines but users often provide async driver URLs (e.g., postgresql+asyncpg://) since that's what ADK requires at runtime.

This fix:
- Makes `to_sync_url()` public in `_schema_check_utils.py` for reuse
- Updates `migrate_from_sqlalchemy_pickle.py` to convert async URLs
- Updates `migrate_from_sqlalchemy_sqlite.py` to convert async URLs
- Adds comprehensive unit tests for `to_sync_url()` function
- Adds integration test for migration with async driver URLs

Fixes #4176

Co-authored-by: Liang Wu <wuliang@google.com>
PiperOrigin-RevId: 858359061
2026-01-19 19:39:20 -08:00
Xiang (Sean) Zhou 3dd7e3f1b9 chore: Update sample live streaming tools agent to use latest live models
Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 858001541
2026-01-18 21:04:06 -08:00
Google Team Member 81eaeb5eba fix: Remove custom metadata from A2A response events
PiperOrigin-RevId: 857331378
2026-01-16 15:47:38 -08:00
ShaharKatz 7d4326c360 Handle None inferences in eval results for issue #2729 (#3805)
* fixed CR comments

* formatted via isort

---------

Co-authored-by: Ankur <ankusharma@google.com>
2026-01-16 12:35:08 -08:00
Ankur Sharma c222a45ef7 chore: Making the regex to catch cli reference strict by adding word boundary anchor
Right now the regex is over-matching and is returning true for references like these:
from ..utils._client_labels_utils import EVAL_CLIENT_LABEL

Co-authored-by: Ankur Sharma <ankusharma@google.com>
PiperOrigin-RevId: 857255767
2026-01-16 12:10:02 -08:00
Joseph Pagadora ea0934b993 feat: Update adk eval cli to consume custom metrics by adding CustomMetricEvaluator
Co-authored-by: Joseph Pagadora <jcpagadora@google.com>
PiperOrigin-RevId: 857229167
2026-01-16 11:05:52 -08:00
Peter Kaplan 5923da786e feat: Add is_computer_use field to agent information in adk-web server
PiperOrigin-RevId: 857218915
2026-01-16 10:41:47 -08:00
Google Team Member f92d4e397f fix: Make all parts of a thought event be marked as thought
PiperOrigin-RevId: 857218905
2026-01-16 10:40:58 -08:00
Google Team Member 7dc6adf4e5 feat: migrate ToolboxToolset to use toolbox-adk and align validation
### Description of Change

**Problem:**
The `ToolboxToolset` was relying on the legacy `toolbox-core` package. Users wanting to use the Toolbox features were forced to install the heavy `[extensions]` group, lacking a granular installation option. Additionally, `ToolboxToolset` had a validation check enforcing either `toolset_name` or `tool_names` to be present, preventing the default behavior of loading all tools (which `toolbox-adk` supports).

**Solution:**
* Refactored `ToolboxToolset` to delegate to `toolbox-adk`.
* Added a new `toolbox` optional dependency group in `pyproject.toml`.
  * Users can now run `pip install google-adk[toolbox]` to install only the necessary dependencies.
* Updated the `extensions` dependency group to replace `toolbox-core` with `toolbox-adk`.
  * This ensures existing users of `[extensions]` are not broken upon upgrade.
* Removed the restrictive validation check to allow default loading of all tools.
* Updated the `ImportError` message to guide users toward the new granular installation command.

### Testing Plan

**Unit Tests:**
- [x] I have added or updated unit tests for my change.
- [x] All unit tests pass locally.

**Manual End-to-End (E2E) Tests:**
- Verified that the sample agent runs correctly with `toolbox-adk` locally.
- Verified that `ToolboxToolset` can now be instantiated without arguments to load all tools.

### Checklist

- [x] I have read the [CONTRIBUTING.md](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) document.
- [x] I have performed a self-review of my own code.
- [x] I have commented my code, particularly in hard-to-understand areas.
- [x] I have added tests that prove my fix is effective or that my feature works.
- [x] New and existing unit tests pass locally with my changes.
- [x] I have manually tested my changes end-to-end.
- [x] Any dependent changes have been merged and published in downstream modules.

PiperOrigin-RevId: 857171811
2026-01-16 08:27:16 -08:00
Liang Wu d0aef8a4fa docs: Update the migration guide for adding a new database session schema
Co-authored-by: Liang Wu <wuliang@google.com>
PiperOrigin-RevId: 856882485
2026-01-15 17:13:08 -08:00
Akshat8510 e162bb8832 feat: Allow thinking_config in generate_content_config
Merge https://github.com/google/adk-python/pull/4117

**Overview**
 This PR implements the feature request in #4108 to allow `thinking_config` to be set directly within `generate_content_config`, bringing the Python SDK in line with the Go implementation.

 **Changes**
 - **llm_agent.py**: Relaxed the validation logic in `validate_generate_content_config` to remove the `ValueError` for `thinking_config`.
 - **Precedence Warning**: Added an override of `model_post_init` in `LlmAgent` to issue a `UserWarning` if both a `planner` and a manual `thinking_config` are provided.
 - **built_in_planner.py**: Updated `apply_thinking_config` to log an `INFO` message when the planner overwrites an existing configuration on the `LlmRequest`.

 **Testing**
 Verified with a reproduction script covering:
 1. Successful initialization of an agent with direct `thinking_config`.
 2. Validation of `UserWarning` during initialization when conflicting configurations are present.
 3. Confirmation of logger output when the planner performs an overwrite.

 Closes: #4108
 Tagging @invictus2010 for visibility.

Co-authored-by: Liang Wu <wuliang@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/4117 from Akshat8510:feat/allow-thinking-config-4108 5deeb893799379c681d6822dc4a1e42f86d3ed01
PiperOrigin-RevId: 856821447
2026-01-15 14:32:06 -08:00
Kathy Wu 19315fe557 feat: Support authentication for MCP tool listing
Currently only tool calling supports MCP auth. This refactors the auth logic into a auth_utils file and uses it for tool listing as well. Fixes https://github.com/google/adk-python/issues/2168.

Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 856798589
2026-01-15 13:38:19 -08:00
Yeesian Ng 6dbe851fca chore: Add back unit tests for CLI utility to deploy to AgentEngine
Co-authored-by: Yeesian Ng <ysian@google.com>
PiperOrigin-RevId: 856749290
2026-01-15 11:43:07 -08:00
George Weale 6ad18cc2fc fix: Use json.dumps for error messages in SSE events
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 856737497
2026-01-15 11:14:02 -08:00
Yeesian Ng 83d7bb6ef0 fix: Use the correct path for config-based agents when deploying to AgentEngine
Co-authored-by: Yeesian Ng <ysian@google.com>
PiperOrigin-RevId: 856724694
2026-01-15 10:45:58 -08:00
Xiang (Sean) Zhou 19555e7dce fix: Support Generator and Async Generator tool declaration in JSON schema
Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 856713741
2026-01-15 10:19:58 -08:00
Google Team Member ed2c3ebde9 fix: Prevent stopping event processing on events with None content
PiperOrigin-RevId: 856706510
2026-01-15 10:03:40 -08:00
nikkie 50c4b8d33a chore: Disable scheduled GitHub Actions workflows in forks
Merge https://github.com/google/adk-python/pull/4059

### Link to Issue or Description of Change

**1. Link to an existing issue (if applicable):**

- Closes: #3961

**Problem:**
Excessive notifications from periodic workflow runs (every 6 hours for triage, daily for stale-bot and docs upload) in forks where they are not needed.

**Solution:**
Add repository checks to prevent scheduled workflows from running in forked repositories.
The workflows will now only run in the main google/adk-python repository.

### Testing Plan

I think that unit tests and E2E are not needed because this change is for GitHub Actions (not ADK source code).

_Please describe the tests that you ran to verify your changes. This is required
for all PRs that are not small documentation or typo fixes._

**Unit Tests:**

- [ ] I have added or updated unit tests for my change.
- [ ] All unit tests pass locally.

_Please include a summary of passed `pytest` results._

**Manual End-to-End (E2E) Tests:**

_Please provide instructions on how to manually test your changes, including any
necessary setup or configuration. Please provide logs or screenshots to help
reviewers better understand the fix._

### Checklist

- [x] I have read the [CONTRIBUTING.md](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) document.
- [x] I have performed a self-review of my own code.
- [x] I have commented my code, particularly in hard-to-understand areas.
- [ ] I have added tests that prove my fix is effective or that my feature works.
- [ ] New and existing unit tests pass locally with my changes.
- [ ] I have manually tested my changes end-to-end.
- [ ] Any dependent changes have been merged and published in downstream modules.

COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/4059 from ftnext:disable-fork-actions 991cc94674cd5cef2e3c2aacf243ba7dae7b88ad
PiperOrigin-RevId: 856691019
2026-01-15 09:25:19 -08:00
Anantha Narayanan 7db3ce9613 fix: 'NoneType' object is not iterable
Merge https://github.com/google/adk-python/pull/3988

### Link to Issue or Description of Change

**1. Link to an existing issue (if applicable):**

- Closes: https://github.com/google/adk-python/issues/3987
- Related: https://github.com/google/adk-python/issues/3596

**2. Or, if no issue exists, describe the change:**

**Problem:**
Idea about my use case
I'm building the report generation system using google-ask (1.18.0) and building multiple subagents here, I'm passing the one subagent Agent as a tool to another Parent Agent. Note: Sub-agent can do web search.
here, parent agent triggers multiple sub-agent (same agent) multiple times according to use case or complexity of the user input

Describe the bug
here, the bug sometimes sub agents doesn't provide the proper output and resulted in the
```
merged_text = '\n'.join(p.text for p in last_content.parts if p.text)
^^^^^^^^^^^^^^^^^^
TypeError: 'NoneType' object is not iterable
and it's breaking the system of Agents workflow

```

**Solution:**
Creating fallback if there is no **last_content.parts** it will return the empty parts so we won't face the NoneType issue

### Testing Plan
Created a unit test file for this issue
test_google_search_agent_tool_repro.py

**Unit Tests:**

- [X] I have added or updated unit tests for my change.
- [X] All unit tests pass locally.

_Please include a summary of passed `pytest` results._
3677 passed, 2208 warnings in 42.64s

**Manual End-to-End (E2E) Tests:**
N/A

### Checklist

- [X] I have read the [CONTRIBUTING.md](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) document.
- [X] I have performed a self-review of my own code.
- [X] I have commented my code, particularly in hard-to-understand areas.
- [X] I have added tests that prove my fix is effective or that my feature works.
- [X] New and existing unit tests pass locally with my changes.
- [X] I have manually tested my changes end-to-end.
- [ ] Any dependent changes have been merged and published in downstream modules.

### Additional context
N/A

Co-authored-by: Liang Wu <wuliang@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3988 from ananthanarayanan-28:none-type-issue e6ba948345adfc5ac73a5e39d11c68236f117179
PiperOrigin-RevId: 856515019
2026-01-14 23:32:53 -08:00
Xuan Yang 2ed686527a feat: Use json schema for IntegrationConnectorTool declaration when feature enabled
Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 856508415
2026-01-14 23:09:44 -08:00
Xiang (Sean) Zhou ec6abf4010 fix: Use canonical tools to find streaming tools and use tool.name to register them
Original codes use tool.__name__ to register streaming tools, this is problemetic, it only works with python function passed as tools directly, if they are wrapped in FunctionTool, then FunctionTool doesn't have "__name__" property. canonical_tools wrap python function in FunctionTool uniformly thus we can use tool.name uniformly

Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 856472936
2026-01-14 21:00:20 -08:00
Xiang (Sean) Zhou 7c282973ea fix: Support Generator and AsyncGenerator tool declaration
use yield type as return type

Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 856459995
2026-01-14 19:56:34 -08:00
Kathy Wu d4da1bb733 fix: Initialize self._auth_config inside BaseAuthenticatedTool
So that we can access self._auth_config in McpTool for getting auth headers

Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 856451693
2026-01-14 19:19:08 -08:00
Kathy Wu cce430da79 feat: start and close ClientSession in a single task in McpSessionManager
Merge https://github.com/google/adk-python/pull/4025

**Please ensure you have read the [contribution guide](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) before creating a pull request.**

### Link to Issue or Description of Change

**1. Link to an existing issue (if applicable):**

- Closes:
  - #3950
  - #3731
  - #3708

**2. Or, if no issue exists, describe the change:**

**Problem:**
- `ClientSession` of https://github.com/modelcontextprotocol/python-sdk uses AnyIO for async task management.
- AnyIO TaskGroup requires its start and close must happen in a same task.
- Since `McpSessionManager` does not create task per client, the client might be closed by different task, cause the error: `Attempted to exit cancel scope in a different task than it was entered in`.

**Solution:**

I Suggest 2 changes:

Handling the `ClientSession` in a single task
- To start and close `ClientSession` by the same task, we need to wrap the whole lifecycle of `ClientSession` to a single task.
- `SessionContext` wraps the initialization and disposal of `ClientSession` to a single task, ensures that the `ClientSession` will be handled only in a dedicated task.

Add timeout for `ClientSession`
- Since now we are using task per `ClientSession`, task should never be leaked.
- But `McpSessionManager` does not deliver timeout directly to `ClientSession` when the type is not STDIO.
  - There is only timeout for `httpx` client when MCP type is SSE or StreamableHTTP.
  - But the timeout applys only to `httpx` client, so if there is an issue in MCP client itself(e.g. https://github.com/modelcontextprotocol/python-sdk/issues/262), a tool call waits the result **FOREVER**!
- To overcome this issue, I propagated the `sse_read_timeout` to `ClientSession`.
  - `timeout` is too short for timeout for tool call, since its default value is only 5s.
  - `sse_read_timeout` is originally made for read timeout of SSE(default value of 5m or 300s), but actually most of SSE implementations from server (e.g. FastAPI, etc.) sends ping periodically(about 15s I assume), so in a normal circumstances this timeout is quite useless.
  - If the server does not send ping, the timeout is equal to tool call timeout. Therefore, it would be appropriate to use `sse_read_timeout` as tool call timeout.
  - Most of tool calls should finish within 5 minutes, and sse timeout is adjustable if not.
- If this change is not acceptable, we could make a dedicate parameter for tool call timeout(e.g. `tool_call_timeout`).

### Testing Plan
- Although this does not change the interface itself, it changes its own session management logics, some existing tests are no longer valid.
  - I made changes to those tests, especially those of which validate session states(e.g. checking whether `initialize()` called).
  - Since now session is encapsulated with `SessionContext`, we cannot validate the initialized state of the session in `TestMcpSessionManager`, should validate it at `TestSessionContext`.
- Added a simple test for reproducing the issue(`test_create_and_close_session_in_different_tasks`).
- Also made a test for the new component: `SessionContext`.

**Unit Tests:**

- [x] I have added or updated unit tests for my change.
- [x] All unit tests pass locally.

```plaintext
=================================================================================== 3689 passed, 1 skipped, 2205 warnings in 63.39s (0:01:03) ===================================================================================
```

**Manual End-to-End (E2E) Tests:**

_Please provide instructions on how to manually test your changes, including any
necessary setup or configuration. Please provide logs or screenshots to help
reviewers better understand the fix._

### Checklist

- [x] I have read the [CONTRIBUTING.md](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) document.
- [x] I have performed a self-review of my own code.
- [x] I have commented my code, particularly in hard-to-understand areas.
- [x] I have added tests that prove my fix is effective or that my feature works.
- [x] New and existing unit tests pass locally with my changes.
- [x] I have manually tested my changes end-to-end.
- [ ] ~~Any dependent changes have been merged and published in downstream modules.~~ `no deps has been changed`

### Additional context
This PR is related to https://github.com/modelcontextprotocol/python-sdk/pull/1817 since it also fixes endless tool call awaiting.

Co-authored-by: Kathy Wu <wukathy@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/4025 from challenger71498:feat/task-based-mcp-session-manager f7f7cd0c9c96840361c30499d08c33a189f57d86
PiperOrigin-RevId: 856438147
2026-01-14 18:10:03 -08:00
Google Team Member 1133ce219c feat: convert A2UI messages between A2A DataPart metadata and ADK events
1. Convert A2A responses containing a DataPart to ADK events. By default, this is done by serializing the DataPart to JSON and embedding it within the inline_data field of a GenAI Part, wrapped with custom tags (<a2a_datapart_json> and </a2a_datapart_json>).
2. Convert ADK events back to A2A requests. Specifically, messages stored in inline_data with the text/plain mime type and content wrapped within the custom tags (<a2a_datapart_json> and </a2a_datapart_json>) are deserialized from JSON back into an A2A DataPart

PiperOrigin-RevId: 856426615
2026-01-14 17:07:54 -08:00
Xiang (Sean) Zhou 712b5a393d fix: Only filter out audio content when sending history
audio is transcribed thus no need to be sent, but other blob(e.g. image) should still be sent.

Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 856422986
2026-01-14 16:51:19 -08:00
George Weale 89bed43f5e fix: Add finish reason mapping and remove custom file URI handling in LiteLLM
Introduces a function to map LiteLLM finish reason strings to the internal types.FinishReason enum and populates the finish_reason field in LlmResponse. Removes custom logic for handling file URIs, including special casing for different providers, and updates tests accordingly

Close #4125

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 856421317
2026-01-14 16:44:44 -08:00
Kathy Wu 8264211f98 chore: Consolidate test_mcp_toolset.py into one file
There was an extra test_mcp_toolset in the tools/ directory with only one test; I moved it into the main file.

Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 856419611
2026-01-14 16:37:12 -08:00
Xuan Yang 8e7cc16f12 docs: Refactor ADK release analyzer with workflow agents
Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 856412858
2026-01-14 16:19:02 -08:00
George Weale fdc98d5c92 fix: Convert unsupported inline artifact MIME types to text in LoadArtifactsTool
The LoadArtifactsTool now checks if an artifact's inline data MIME type is supported by Gemini. If not, it attempts to convert the artifact content into a text Part

Close #4028

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 856404510
2026-01-14 16:01:06 -08:00
Xiang (Sean) Zhou 7b035aa9fc chore: Always log api backend when connecting to live model
Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 856404282
2026-01-14 16:00:15 -08:00
Google Team Member 672b57f1b7 chore: add a sample BigQuery agent using BigQuery MCP tools
PiperOrigin-RevId: 856400285
2026-01-14 15:49:23 -08:00
Kotaro Saito 38d52b2476 fix(cli): pass log_level to uvicorn in web and api_server commands (#4144)
Explicitly pass the log_level parameter to uvicorn.Config in both
adk web and adk api_server commands. This ensures that Uvicorn's
internal logging respects the configured log level.

Closes #4139
2026-01-14 09:48:32 -08:00
Xuan Yang 79fcddb39f feat: Add --enable_features CLI option to ADK CLI
This flag can be used to override default feature enable state.

Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 856067979
2026-01-13 23:58:26 -08:00
Xuan Yang 8973618b0b chore: Add a DebugLoggingPlugin to record human readable debugging logs
Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 856067925
2026-01-13 23:57:36 -08:00
lwangverizon 8e69a58df4 feat: Add support to automatically create a session if one does not exist
feature/auto-create-new-session

Merge https://github.com/google/adk-python/pull/4072

**Please ensure you have read the [contribution guide](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) before creating a pull request.**

### Link to Issue or Description of Change

**2. Or, if no issue exists, describe the change:**

**Problem:**

When building frontend applications with ADK, there's a limitation where frontends cannot always guarantee that `create_session` is called before initiating a conversation. This creates friction in the user experience because:

- Users may refresh the page or navigate directly to a conversation URL with a specific session_id
- Frontend state management may lose track of whether a session was already created
- Mobile apps or single-page applications have complex lifecycle management where ensuring `create_session` is called first adds unnecessary complexity
- This forces developers to implement additional logic to check session existence before every conversation

Currently, if `get_session` is called with a non-existent session_id, it returns `None`, requiring the frontend to explicitly handle this case and call `create_session` separately.

**Solution:**

Modified the `get_session` method in `DatabaseSessionService` to automatically create a session if it doesn't exist in the database. This "get or create" pattern is common in many frameworks and provides a more developer-friendly API.

The implementation:
1. Attempts to fetch the session from the database
2. If the session doesn't exist (returns `None`), automatically calls `create_session` with the provided parameters
3. Retrieves and returns the newly created session
4. Maintains backward compatibility - existing code continues to work without changes

This allows frontends to simply call `get_session` with a session_id and be confident that the session will be available, regardless of whether it was previously created.

**Benefits:**
- Simplifies frontend integration by removing the need to track session creation state
- Reduces API calls (no need to check existence before calling get_session)
- Follows the principle of least surprise - getting a session with an ID should work reliably
- No breaking changes to existing code that checks for `None` return values

### Testing Plan

**Unit Tests:**

- [x] I have added or updated unit tests for my change.
- [x] All unit tests pass locally.

**pytest results:**

COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/4072 from lwangverizon:feature/auto-create-new-session 5475c6ae91d12332598d521302736eb1db79a8be
PiperOrigin-RevId: 856019482
2026-01-13 21:23:49 -08:00
Xiang (Sean) Zhou 1bedffe457 chore: Remove dead codes for flushing model audio when generation completes
LlmResponse so far doesn't expose generation_complete signal, removing the dead codes.

Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 855835802
2026-01-13 12:28:24 -08:00
Google Team Member 277084e313 refactor(tools): Update ToolboxToolset to wrap toolbox-adk
### Description of Change

**Problem:**
The `ToolboxToolset` was implemented directly within `adk-python`, leading to code duplication and potential drift from the core `toolbox-adk` implementation.

**Solution:**
Refactored `ToolboxToolset` to act as a rigorous wrapper around the `toolbox-adk` package, which delegates all functionality to `toolbox_adk.ToolboxToolset`.

### Testing Plan

**Unit Tests:**

- [x] I have added or updated unit tests for my change.
- [x] All unit tests pass locally.

Summary:
-   Verified initialization flows through to `toolbox-adk`.
-   Verified `auth_token_getters` are correctly propagated.
-   Verified type hints are static-analysis friendly.

**Manual End-to-End (E2E) Tests:**

Manually verified standard toolbox loading and execution with the new wrapper:
```python
from google.adk.tools import ToolboxToolset
from toolbox_adk import CredentialStrategy

# Loading with toolset_name
ts = ToolboxToolset(
    server_url='http://localhost:8080',
    toolset_name='calculator',
    credentials=CredentialStrategy.toolbox_identity()
)
tools = await ts.get_tools()
print(f'Loaded {len(tools)} tools')
```

### Checklist

- [x] I have read the [CONTRIBUTING.md](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) document.
- [x] I have performed a self-review of my own code.
- [x] I have commented my code, particularly in hard-to-understand areas.
- [x] I have added tests that prove my fix is effective or that my feature works.
- [x] New and existing unit tests pass locally with my changes.
- [x] I have manually tested my changes end-to-end.
- [x] Any dependent changes have been merged and published in downstream modules.

PiperOrigin-RevId: 855798474
2026-01-13 10:59:51 -08:00
Xiang (Sean) Zhou ab62b1bffd fix: Use the agent name as the author of the audio event
Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 855789317
2026-01-13 10:38:53 -08:00
Xiang (Sean) Zhou f668a5de44 chore: Update comments about why we can return upon flushing audio caches
Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 855788674
2026-01-13 10:37:28 -08:00
Xuan Yang a5f0d333d7 feat: Use json schema for RestApiTool declaration when feature enabled
Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 855767527
2026-01-13 09:50:59 -08:00
Google Team Member fd2c0f556b chore: Upgrade the sample BQ agent model version to gemini-2.5-flash
This change should give a more intelligent out-of-the-box experience to the sample BigQuery agent users.

PiperOrigin-RevId: 855552871
2026-01-12 23:30:16 -08:00
Joseph Pagadora 6d2f33a59c feat: Update EvalConfig and EvalMetric data models to support custom metrics
Co-authored-by: Joseph Pagadora <jcpagadora@google.com>
PiperOrigin-RevId: 855517478
2026-01-12 21:37:21 -08:00
George Weale 905604faac refactor: Import migration_runner lazily within the migrate command
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 855496468
2026-01-12 20:21:57 -08:00
Xiang (Sean) Zhou a4732a8e50 chore: Updatedate the doc string of LiveRequest
activity_start, activity_end , and blob is sent via send_realtime_input, according to the docstring : https://github.com/googleapis/python-genai/blob/d98c757c7d9a88026ac0f9eb2b1b578e2e7f3bfe/google/genai/live.py#L251, they should be send separately, so makes sense they are mutally exclusive.

And we already make them exclusive in our current logic:
https://github.com/google/adk-python/blob/6c0bf85042c38c7bafe1c183f1bba8bee1ba3570/src/google/adk/flows/llm_flows/base_llm_flow.py#L264-L272, make it clear in docstring

Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 855492864
2026-01-12 20:06:08 -08:00
Liang Wu 75231a30f1 fix: Handle NOT_FOUND error when fetching Vertex AI sessions
Co-authored-by: Liang Wu <wuliang@google.com>
PiperOrigin-RevId: 855464349
2026-01-12 18:17:41 -08:00
Alexis Marasigan b725045e5a fix: fix httpx client closure during event pagination
Merge https://github.com/google/adk-python/pull/3756

move event iteration inside api_client context in get_session

Move event iteration inside the api_client context manager in VertexAiSessionService.get_session() to prevent client closure during multi-page event fetching.

**Please ensure you have read the [contribution guide](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) before creating a pull request.**

### Link to Issue or Description of Change

**1. Link to an existing issue (if applicable):**

- Closes: #3757

**2. Or, if no issue exists, describe the change:**

**Problem:**

When a session contains more than 100 events (requiring pagination), `VertexAiSessionService.get_session()` fails with:

```
RuntimeError: Cannot send a request, as the client has been closed.
```

The root cause is that the `events_iterator` is consumed **outside** the `async with self._get_api_client() as api_client:` context block. When the iterator needs to fetch page 2, 3, etc., the API client has already been closed because the `async with` block has exited.

```python
# Current buggy flow:
async with self._get_api_client() as api_client:
    get_session_response, events_iterator = await asyncio.gather(...)
# ← Client closed here

async for event in events_iterator:  # ← Fails on page 2+ (client closed)
    session.events.append(...)
```

**Solution:**

Move the session creation, user validation, and event iteration **inside** the `async with` block so the API client remains open during the entire pagination process:

```python
async with self._get_api_client() as api_client:
    get_session_response, events_iterator = await asyncio.gather(...)
    # Validation and session creation...
    async for event in events_iterator:  # ← Now works for all pages
        session.events.append(...)
# Client closed after all events are fetched
```

### Testing Plan

**Unit Tests:**

- [x] I have added or updated unit tests for my change.
- [x] All unit tests pass locally.

```bash
pytest tests/unittests/sessions/test_vertex_ai_session_service.py -v
```

**Added regression test:** `test_get_session_pagination_keeps_client_open`
- Creates a `MockAsyncClientWithPagination` that tracks whether it's inside the `async with` context
- Raises `RuntimeError` if iteration happens outside the context (matching real httpx behavior)
- Simulates 3 pages of events (100 + 100 + 50 = 250 events)
- Verifies all 250 events are successfully retrieved

**Manual End-to-End (E2E) Tests:**

1. Deploy an ADK agent to Vertex AI Agent Engine
2. Create a session and send 100+ messages to accumulate >100 events
3. Verify `get_session()` successfully retrieves all events without error

**Before fix:**
```
RuntimeError: Cannot send a request, as the client has been closed.
```

**After fix:**
- Session with 201 events (3 pages) loads successfully
- All events are retrieved and appended to the session

### Checklist

- [x] I have read the [CONTRIBUTING.md](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) document.
- [x] I have performed a self-review of my own code.
- [x] I have commented my code, particularly in hard-to-understand areas.
- [x] I have added tests that prove my fix is effective or that my feature works.
- [x] New and existing unit tests pass locally with my changes.
- [x] I have manually tested my changes end-to-end.
- [x] Any dependent changes have been merged and published in downstream modules.

### Additional context

This bug affects any production deployment where users have extended conversations. Sessions accumulating >100 events (which triggers pagination) become completely unusable as the agent cannot load the session to process new messages.

The fix is minimal and maintains backward compatibility - it only changes the scope of the `async with` block without altering any logic or return values.

**Affected versions:** Tested on google-adk 1.19.0, but the bug exists in earlier versions as well.

COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3756 from AlexisMarasigan:fix/vertex-ai-session-service-paginatio 01fbafa6524312f24f7c9feaffb07bff0ad49b77
PiperOrigin-RevId: 855451813
2026-01-12 17:27:29 -08:00
Google Team Member a4116a6cbf feat: Enhance TraceManager async safety, enrich BigQuery plugin logging, and fix serialization
*   **Async Safety:** Improved TraceManager context variable handling to ensure correct context isolation in concurrent asynchronous operations. This was achieved by using immutable tuples for the span stack and making copies of context dictionaries before modification.
*   **Enhanced Logging:** The BigQueryAgentAnalyticsPlugin now captures richer metadata, including:
    *   Root agent name (via a new context variable).
    *   LLM model name and version.
    *   Usage metadata from LLM requests and responses.
*   **Serialization Fix:** Updated BigQueryAgentAnalyticsPlugin to prevent JSON serialization errors when logging custom objects (e.g., Dataclasses). These are now automatically converted to dictionaries or string representations to ensure successful insertion into BigQuery.

PiperOrigin-RevId: 855415320
2026-01-12 15:46:12 -08:00
1186 changed files with 25137 additions and 7582 deletions
+51 -16
View File
@@ -7,34 +7,69 @@ assignees: ''
---
** Please make sure you read the contribution guide and file the issues in the right place. **
[Contribution guide.](https://google.github.io/adk-docs/contributing-guide/)
## 🔴 Required Information
*Please ensure all items in this section are completed to allow for efficient
triaging. Requests without complete information may be rejected / deprioritized.
If an item is not applicable to you - please mark it as N/A*
**Describe the bug**
**Describe the Bug:**
A clear and concise description of what the bug is.
**To Reproduce**
Please share a minimal code and data to reproduce your problem.
Steps to reproduce the behavior:
**Steps to Reproduce:**
Please provide a numbered list of steps to reproduce the behavior:
1. Install '...'
2. Run '....'
3. Open '....'
4. Provide error or stacktrace
**Expected behavior**
**Expected Behavior:**
A clear and concise description of what you expected to happen.
**Screenshots**
If applicable, add screenshots to help explain your problem.
**Observed Behavior:**
What actually happened? Include error messages or crash stack traces here.
**Desktop (please complete the following information):**
- OS: [e.g. macOS, Linux, Windows]
- Python version(python -V):
- ADK version(pip show google-adk):
**Environment Details:**
- ADK Library Version (pip show google-adk):
- Desktop OS:** [e.g., macOS, Linux, Windows]
- Python Version (python -V):
**Model Information:**
**Model Information:**
- Are you using LiteLLM: Yes/No
- Which model is being used(e.g. gemini-2.5-pro)
- Which model is being used: (e.g., gemini-2.5-pro)
**Additional context**
---
## 🟡 Optional Information
*Providing this information greatly speeds up the resolution process.*
**Regression:**
Did this work in a previous version of ADK? If so, which one?
**Logs:**
Please attach relevant logs. Wrap them in code blocks (```) or attach a
text file.
```text
// Paste logs here
```
**Screenshots / Video:**
If applicable, add screenshots or screen recordings to help explain
your problem.
**Additional Context:**
Add any other context about the problem here.
**Minimal Reproduction Code:**
Please provide a code snippet or a link to a Gist/repo that isolates the issue.
```python
// Code snippet here
```
**How often has this issue occurred?:**
- Always (100%)
- Often (50%+)
- Intermittently (<50%)
- Once / Rare
+33 -8
View File
@@ -10,14 +10,39 @@ assignees: ''
** Please make sure you read the contribution guide and file the issues in the right place. **
[Contribution guide.](https://google.github.io/adk-docs/contributing-guide/)
**Is your feature request related to a problem? Please describe.**
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
## 🔴 Required Information
*Please ensure all items in this section are completed to allow for efficient
triaging. Requests without complete information may be rejected / deprioritized.
If an item is not applicable to you - please mark it as N/A*
**Describe the solution you'd like**
A clear and concise description of what you want to happen.
### Is your feature request related to a specific problem?
Please describe the problem you are trying to solve. (Ex: "I'm always frustrated
when I have to manually handle X...")
**Describe alternatives you've considered**
A clear and concise description of any alternative solutions or features you've considered.
### Describe the Solution You'd Like
A clear and concise description of the feature or API change you want.
Be specific about input/outputs if this involves an API change.
**Additional context**
Add any other context or screenshots about the feature request here.
### Impact on your work
How does this feature impact your work and what are you trying to achieve?
If this is critical for you, tell us if there is a timeline by when you need
this feature.
### Willingness to contribute
Are you interested in implementing this feature yourself or submitting a PR?
(Yes/No)
---
## 🟡 Recommended Information
### Describe Alternatives You've Considered
A clear and concise description of any alternative solutions or workarounds
you've considered and why they didn't work for you.
### Proposed API / Implementation
If you have ideas on how this should look in code, please share a
pseudo-code example.
### Additional Context
Add any other context or screenshots about the feature request here.
@@ -1,102 +0,0 @@
name: Breaking Change Detector
on:
pull_request:
branches:
- main
paths:
- 'src/**'
jobs:
check-api:
runs-on: ubuntu-latest
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
fetch-depth: 0 # Required for accessing the main branch history
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: '3.10'
- name: Install the latest version of uv
uses: astral-sh/setup-uv@v5
- name: Install dependencies
# Syncing installs the package and its dependencies (populating google.* namespace)
# Installing 'griffe' ensures the tool is available in the environment
run: |
uv sync --extra test
uv pip install griffe
- name: Run Breaking Change Detection
# Uses 'uv run python' to execute in the environment with all dependencies installed
run: |
uv run python - <<EOF
import sys
import griffe
from griffe import find_breaking_changes, load, load_git
def check_return_types(old_obj, new_obj):
"""Custom check to strictly compare return type annotations."""
errors = []
# Check Runner.run specifically, or extend to check all methods
try:
old_run = old_obj.members["Runner"].members["run"]
new_run = new_obj.members["Runner"].members["run"]
# Convert to string and strip to compare the annotation text
old_ret = str(old_run.returns).strip()
new_ret = str(new_run.returns).strip()
if old_ret != new_ret:
errors.append(
f"Breaking Change in {new_run.path}: Return type changed from '{old_ret}' to '{new_ret}'"
)
except KeyError:
pass # Member missing (will be caught by standard checks)
except AttributeError:
pass # Member might not be a function
return errors
try:
print("Loading new API (from local source)...")
# allow_inspection=False forces static analysis, preventing sys.modules caching issues
new_api = load("google.adk", search_paths=["src"], allow_inspection=False)
print("Loading baseline API (from main branch)...")
old_api = load_git("google.adk", ref="main", search_paths=["src"], allow_inspection=False)
print("Running detection...")
# 1. Standard Griffe Checks (Removals, Parameter changes)
breakages = list(find_breaking_changes(old_api, new_api))
# 2. Custom Return Type Checks (Workaround for Griffe limitation)
custom_errors = check_return_types(old_api, new_api)
found_issues = False
if breakages:
found_issues = True
print(f"::error::Found {len(breakages)} standard breaking changes!")
for breakage in breakages:
print(breakage.explain())
if custom_errors:
found_issues = True
print(f"::error::Found {len(custom_errors)} return type mismatches!")
for error in custom_errors:
print(f"- {error}")
if found_issues:
sys.exit(1)
print("Success: No breaking changes detected.")
except Exception as e:
print(f"::error::Breaking change detection failed: {e}")
sys.exit(1)
EOF
+2 -2
View File
@@ -1,4 +1,4 @@
# Copyright 2025 Google LLC
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -96,7 +96,7 @@ jobs:
echo ""
set +e
FILES_WITH_FORBIDDEN_IMPORT=$(grep -lE '^from.*cli.*import.*$' $CHANGED_FILES)
FILES_WITH_FORBIDDEN_IMPORT=$(grep -lE '^from.*\bcli\b.*import.*$' $CHANGED_FILES)
GREP_EXIT_CODE=$?
set -e
+1 -1
View File
@@ -1,4 +1,4 @@
# Copyright 2025 Google LLC
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+74
View File
@@ -0,0 +1,74 @@
name: Mypy New Error Check
on:
push:
branches: [ main ]
pull_request:
branches: [ main ]
jobs:
mypy-diff:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: ['3.10', '3.11', '3.12', '3.13',]
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install uv
uses: astral-sh/setup-uv@v5
- name: Generate Baseline (Main)
run: |
# Switch to main branch to generate baseline
git checkout origin/main
git checkout ${{ github.sha }} -- pyproject.toml
# Install dependencies for main
uv venv .venv
source .venv/bin/activate
uv sync --all-extras
# Run mypy, filter for errors only, remove line numbers (file:123: -> file::), and sort
# We ignore exit code (|| true) because we expect errors on main
uv run mypy . | grep "error:" | sed 's/:\([0-9]\+\):/::/g' | sort > main_errors.txt || true
echo "Found $(wc -l < main_errors.txt) errors on main."
- name: Check PR Branch
run: |
# Switch back to the PR commit
git checkout ${{ github.sha }}
# Re-sync dependencies in case the PR changed them
source .venv/bin/activate
uv sync --all-extras
# Run mypy on PR code, apply same processing
uv run mypy . | grep "error:" | sed 's/:\([0-9]\+\):/::/g' | sort > pr_errors.txt || true
echo "Found $(wc -l < pr_errors.txt) errors on PR branch."
- name: Compare and Fail on New Errors
run: |
# 'comm -13' suppresses unique lines in file1 (main) and common lines,
# leaving only lines unique to file2 (PR) -> The new errors.
comm -13 main_errors.txt pr_errors.txt > new_errors.txt
if [ -s new_errors.txt ]; then
echo "::error::The following NEW mypy errors were introduced:"
cat new_errors.txt
exit 1
else
echo "Great job! No new mypy errors introduced."
fi
+32
View File
@@ -0,0 +1,32 @@
name: Mypy Type Check
on:
push:
branches: [ main ]
pull_request:
branches: [ main ]
jobs:
mypy:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: ['3.10', '3.11', '3.12', '3.13',]
steps:
- uses: actions/checkout@v4
- name: Install uv
uses: astral-sh/setup-uv@v1
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install dependencies
run: uv sync --all-extras
- name: Run mypy
run: uv run mypy . --strict
+1 -1
View File
@@ -1,4 +1,4 @@
# Copyright 2025 Google LLC
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+1 -1
View File
@@ -1,4 +1,4 @@
# Copyright 2025 Google LLC
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+2 -1
View File
@@ -1,4 +1,4 @@
# Copyright 2025 Google LLC
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -23,6 +23,7 @@ on:
jobs:
audit-stale-issues:
if: github.repository == 'google/adk-python'
runs-on: ubuntu-latest
timeout-minutes: 60
+5 -3
View File
@@ -15,9 +15,11 @@ jobs:
# - New issues (need component labeling)
# - Issues labeled with "planned" (need owner assignment)
if: >-
github.event_name == 'schedule' ||
github.event.action == 'opened' ||
github.event.label.name == 'planned'
github.repository == 'google/adk-python' && (
github.event_name == 'schedule' ||
github.event.action == 'opened' ||
github.event.label.name == 'planned'
)
permissions:
issues: write
contents: read
@@ -9,6 +9,7 @@ on:
jobs:
upload-adk-docs-to-vertex-ai-search:
if: github.repository == 'google/adk-python'
runs-on: ubuntu-latest
steps:
+2 -2
View File
@@ -24,7 +24,7 @@ agentic architectures that range from simple tasks to complex workflows.
interacts with various services like session management, artifact storage,
and memory, and integrates with application-wide plugins. The runner
provides different execution modes: `run_async` for asynchronous execution
in production, `run_live` for bi-directional streaming interaction, and
in production, `run_live` for bidirectional streaming interaction, and
`run` for synchronous execution suitable for local testing and debugging. At
the end of each invocation, it can perform event compaction to manage
session history size.
@@ -316,7 +316,7 @@ navigation and refactoring.
immediately after the license header, before any other imports.
```python
# Copyright 2025 Google LLC
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+177 -2
View File
@@ -1,5 +1,180 @@
# Changelog
## [1.24.1](https://github.com/google/adk-python/compare/v1.24.0...v1.24.1) (2026-02-06)
### Bug Fixes
* Add back deprecated eval endpoint for web until we migrate([ae993e8](https://github.com/google/adk-python/commit/ae993e884f44db276a4116ebb7a11a2fb586dbfe))
* Update eval dialog colors, and fix a2ui component types ([3686a3a](https://github.com/google/adk-python/commit/3686a3a98f46738549cd7a999f3773b7a6fd1182))
## [1.24.0](https://github.com/google/adk-python/compare/v1.23.0...v1.24.0) (2026-02-04)
### ⚠ BREAKING CHANGES
* Breaking: Make credential manager accept `tool_context` instead of `callback_context` ([fe82f3c](https://github.com/google/adk-python/commit/fe82f3cde854e49be13d90b4c02d786d82f8a202))
### Highlights
* **[Web]**
* **Consolidated Event View**: Replaced the Event tab with a more intuitive "click-to-expand" interaction on message rows, enabling faster debugging within the chat context
* **Enhanced Accessibility**: Added full support for arrow-key navigation for a more seamless, keyboard-centric experience
* **Rich Developer Tooling**: Introduced detailed tooltips for function calls, providing instant visibility into arguments, responses, and state changes
* **A2UI Integration**: Integrated the **A2UI v0.8** standard catalog to automatically render spec-compliant ADK parts as native UI components directly in the chat
### Features
* **[Core]**
* Allow passthrough of `GOOGLE_CLOUD_LOCATION` for Agent Engine deployments ([004e15c](https://github.com/google/adk-python/commit/004e15ccb7c7f683623f8e7d2e77a9d12558c545))
* Add interface for agent optimizers ([4ee125a](https://github.com/google/adk-python/commit/4ee125a03856fdb9ed28245bf7f5917c2d9038db))
* Pass event ID as metadata when converted into a message ([85434e2](https://github.com/google/adk-python/commit/85434e293f7bd1e3711f190f84d5a36804e4462b))
* Restructure the bug report template as per the intake process ([324796b](https://github.com/google/adk-python/commit/324796b4fe05bec3379bfef67071a29552ef355a))
* **[Models]**
* Mark Vertex calls made from non-Gemini models ([7d58e0d](https://github.com/google/adk-python/commit/7d58e0d2f375bc80bdfac9cffea2926fd2344b8a))
* **[Evals]**
* Allow Vertex AI Client initialization with API Key ([43d6075](https://github.com/google/adk-python/commit/43d6075ea7aa49ddb358732f2219ca9598dd286f))
* Remove overall evaluation status calculation from `_CustomMetricEvaluator` and add threshold to custom metric function expected signature ([553e376](https://github.com/google/adk-python/commit/553e376718ceb3d7fb1403231bb720836d71f42c))
* **[Tools]**
* Make OpenAPI tool asynchronous ([9290b96](https://github.com/google/adk-python/commit/9290b966267dc02569786f95aab2a3cb78c7004f))
* Implement toolset authentication for `McpToolset`, `OpenAPIToolset`, and other toolsets ([798f65d](https://github.com/google/adk-python/commit/798f65df86b1bbe33d864e30c5b1f9e155e89810))
* Add framework support for toolset authentication before `get_tools` calls ([ee873ca](https://github.com/google/adk-python/commit/ee873cae2e2df960910d264a4340ce6c0489eb7a))
* Support dynamic configuration for `VertexAiSearchTool` ([585ebfd](https://github.com/google/adk-python/commit/585ebfdac7f1b8007b4e4a7e4258ec5de72c78b1))
* Add `get_auth_config` method to toolset to expose authentication requirements ([381d44c](https://github.com/google/adk-python/commit/381d44cab437cac027af181ae627e7b260b7561e))
* Add methods in `McpToolset` for users to access MCP resources ([8f7d965](https://github.com/google/adk-python/commit/8f7d9659cfc19034af29952fbca765d012169b38))
* Improve error message when failing to get tools from MCP ([3480b3b](https://github.com/google/adk-python/commit/3480b3b82d89de69f77637d7ad034827434df45a))
* **[Services]**
* Improve `asyncio` loop handling and test cleanup ([00aba2d](https://github.com/google/adk-python/commit/00aba2d884d24fb5244d1de84f8dba9cbc3c07e8))
* **[Live]**
* Support running tools in separate threads for live mode ([714c3ad](https://github.com/google/adk-python/commit/714c3ad0477e775fba6696a919a366a293197268))
* **[Observability]**
* Add extra attributes to spans generated with `opentelemetry-instrumentation-google-genai` ([e87a843](https://github.com/google/adk-python/commit/e87a8437fb430e0d4c42c73948e3ba1872040a15))
### Bug Fixes
* Ignore `session_db_kwargs` for SQLite session services ([ce07cd8](https://github.com/google/adk-python/commit/ce07cd8144c8498434f68e61ebeb519bf329f778))
* Resolve `MutualTLSChannelError` by adding `pyopenssl` dependency ([125bc85](https://github.com/google/adk-python/commit/125bc85ac5e1400bc38f7c681f76fa82626c9911))
* Add `update_timestamp_tz` property to `StorageSession` ([666cebe](https://github.com/google/adk-python/commit/666cebe3693d2981fd5fea6e9e4c65e56dcd3f2b))
* Do not treat Function Calls and Function Responses as invisible when marked as thoughts ([853a3b0](https://github.com/google/adk-python/commit/853a3b0e143ce27516f0de51e0e0df2af6ecf465))
* Add pre-deployment validation for agent module imports (credit to @ppgranger, [2ac468e](https://github.com/google/adk-python/commit/2ac468ea7e30ef30c1324ffc86f67dbf32ab7ede))
* Fix cases where `execution_result_delimiters` have `None` type element ([a16e3cc](https://github.com/google/adk-python/commit/a16e3cc67e1cb391228ba78662547672404ae550))
* Disable `save_input_blobs_as_artifacts` deprecation warning message for users not setting it ([c34615e](https://github.com/google/adk-python/commit/c34615ecf3c7bbe0f4275f72543774f258c565b4))
* Fix agent config path handling in generated deployment script ([8012339](https://github.com/google/adk-python/commit/801233902bbd6c0cca63b6fc8c1b0b2531f3f11e))
* Add `pypika>=0.50.0` to `project.toml` to support `crewai` on Python 3.12+ ([e8f7aa3](https://github.com/google/adk-python/commit/e8f7aa3140d2585ac38ebfe31c5b650383499a20))
* Update OpenTelemetry dependency versions to relax version constraints for `opentelemetry-api` and `opentelemetry-sdk` ([706a6dd](https://github.com/google/adk-python/commit/706a6dda8144da147bd9fa42ef85bbfa58fec5d3))
* Enable `pool_pre_ping` by default for non-SQLite database engines ([da73e71](https://github.com/google/adk-python/commit/da73e718efa9557ed33e2fb579de68fcbcf4c7f0))
* Ensure database sessions are always rolled back on errors ([63a8eba](https://github.com/google/adk-python/commit/63a8eba53f2cb07625eb7cd111ff767e8e0030fa))
* Reload stale session in `DatabaseSessionService` when storage update time is later than the in-memory session object ([1063fa5](https://github.com/google/adk-python/commit/1063fa532cad59d8e9f7421ce2f523724d49d541))
* Make credential key generation stable and prevent cross-user credential leaks ([33012e6](https://github.com/google/adk-python/commit/33012e6dda9ef20c7a1dae66a84717de5d782097))
* Change MCP `read_resource` to return original contents ([ecce7e5](https://github.com/google/adk-python/commit/ecce7e54a688a915a1b9d742c39e4684186729be))
* Recognize function responses as non-empty parts in LiteLLM ([d0102ec](https://github.com/google/adk-python/commit/d0102ecea331e062190dbb7578a4ef7f4044306e))
* Handle HTTP/HTTPS URLs for media files in LiteLLM content conversion ([47221cd](https://github.com/google/adk-python/commit/47221cd5c1e778cd4b92ed8d382c639435f5728c))
* Fix Pydantic schema generation error for `ClientSession` ([131fbd3](https://github.com/google/adk-python/commit/131fbd39482980572487a30fea13236d2badd543))
* Fix Clicks Wrapping in `adk eval` help message ([3bcd8f7](https://github.com/google/adk-python/commit/3bcd8f7f7a0683f838005bc209f7d39dc93f850b))
* Stream errors as simple JSON objects in ADK web server SSE endpoint ([798d005](https://github.com/google/adk-python/commit/798d0053c832e7ed52e2e104f8a14f789ba8b17f))
* Remove print debugging artifact ([0d38a36](https://github.com/google/adk-python/commit/0d38a3683f13bc12dc5d181164b6cd5d72fc260c))
### Improvements
* Check `will_continue` for streaming function calls ([2220d88](https://github.com/google/adk-python/commit/2220d885cda875144b52338b5becf6e5546f3f51))
* Update ADK web, rework events, and add A2UI capabilities ([37e6507](https://github.com/google/adk-python/commit/37e6507ce4d8750100d914eb1a62014350ef1795))
* Improve error handling for LiteLLM import in `gemma_llm.py` ([574ec43](https://github.com/google/adk-python/commit/574ec43a175e3bf3a05e73114e8db7196fae7040))
* Replace proxy methods with utils implementation ([6ff10b2](https://github.com/google/adk-python/commit/6ff10b23be01c1f7dd79d13ac8c679c079140f76), [f82ceb0](https://github.com/google/adk-python/commit/f82ceb0ce75d3efed7c046835ddac76c28210013))
* Replace print statements with logging in ADK evaluation components ([dd8cd27](https://github.com/google/adk-python/commit/dd8cd27b2ce505ecca50cdfbb1469db01c82b0af))
* Add sample agent that requires OAuth flow during MCP tool listing, and convert `MCPToolset` to `McpToolset` in unit tests ([2770012](https://github.com/google/adk-python/commit/2770012cecdfc71628a818a75b21faabe828b4e5), [4341839](https://github.com/google/adk-python/commit/43418394202c2d01b0d37f6424bd601148077e27))
* Ensure `BigQueryAgentAnalyticsPlugin` is shut down after each test ([c0c98d9](https://github.com/google/adk-python/commit/c0c98d94b3161d6bf9fff731e0abfc985b53e653))
* Add ADK logger in `RestApiTool` ([288c2c4](https://github.com/google/adk-python/commit/288c2c448d77c574dafadf7851a49e6ff59fa7f4))
* Add GitHub Action check to run `mypy` ([32f9f92](https://github.com/google/adk-python/commit/32f9f92042ab530220ac9d159045c91d311affa7))
* Add `unittests.sh` script and update `CONTRIBUTING.md` ([025b42c](https://github.com/google/adk-python/commit/025b42c8361ad2078593e3e7fc5301df88a532c7))
* Extract helper function for LLM request building and response processing ([753084f](https://github.com/google/adk-python/commit/753084fd46c9637488f33b0a05b4d270f6e03a39))
## [1.23.0](https://github.com/google/adk-python/compare/v1.22.1...v1.23.0) (2026-01-22)
### ⚠ BREAKING CHANGES
* Breaking: Use OpenTelemetry for BigQuery plugin tracing, replacing custom `ContextVar` implementation ([ab89d12](https://github.com/google/adk-python/commit/ab89d1283430041afb303834749869e9ee331721))
### Features
* **[Core]**
* Add support to automatically create a session if one does not exist ([8e69a58](https://github.com/google/adk-python/commit/8e69a58df4eadeccbb100b7264bb518a46b61fd7))
* Remove `@experimental` decorator from `AgentEngineSandboxCodeExecutor` ([135f763](https://github.com/google/adk-python/commit/135f7633253f6a415302142abc3579b664601d5b))
* Add `--disable_features` CLI option to override default feature enable state ([53b67ce](https://github.com/google/adk-python/commit/53b67ce6340f3f3f8c3d732f9f7811e445c76359))
* Add `otel_to_cloud` flag to `adk deploy agent_engine` command ([21f63f6](https://github.com/google/adk-python/commit/21f63f66ee424501d9a70806277463ef718ae843))
* Add `is_computer_use` field to agent information in `adk-web` server ([5923da7](https://github.com/google/adk-python/commit/5923da786eb1aaef6f0bcbc6adc906cbc8bf9b36))
* Allow `thinking_config` in `generate_content_config` ([e162bb8](https://github.com/google/adk-python/commit/e162bb8832a806e2380048e39165bf837455f88c))
* Convert A2UI messages between A2A `DataPart` metadata and ADK events ([1133ce2](https://github.com/google/adk-python/commit/1133ce219c5a7a9a85222b03e348ba6b13830c8f))
* Add `--enable_features` CLI option to override default feature enable state ([79fcddb](https://github.com/google/adk-python/commit/79fcddb39f71a4c1342e63b4d67832b3eccb2652))
* **[Tools]**
* Add flush mechanism to `BigQueryAgentAnalyticsPlugin` to ensure pending log events are written to BigQuery ([9579bea](https://github.com/google/adk-python/commit/9579bea05d946b3d8b4bfec35e510725dd371224))
* Allow Google Search tool to set a different model ([b57a3d4](https://github.com/google/adk-python/commit/b57a3d43e4656f5a3c5db53addff02b67d1fde26))
* Support authentication for MCP tool listing ([e3d542a](https://github.com/google/adk-python/commit/e3d542a5ba3d357407f8cd29cfdd722f583c8564) [19315fe](https://github.com/google/adk-python/commit/19315fe557039fa8bf446525a4830b1c9f40cba9))
* Use JSON schema for `base_retrieval_tool`, `load_artifacts_tool`, and `load_memory_tool` declarations when the feature is enabled ([69ad605](https://github.com/google/adk-python/commit/69ad605bc4bbe9a4f018127fd3625169ee70488e))
* Use JSON schema for `IntegrationConnectorTool` declaration when the feature is enabled ([2ed6865](https://github.com/google/adk-python/commit/2ed686527ac75ff64128ce7d9b1a3befc2b37c64))
* Start and close `ClientSession` in a single task in `McpSessionManager` ([cce430d](https://github.com/google/adk-python/commit/cce430da799766686e65f6cae02ba64e916d5c8a))
* Use JSON schema for `RestApiTool` declaration when the feature is enabled ([a5f0d33](https://github.com/google/adk-python/commit/a5f0d333d7f26f2966ed511d5d9def7a1933f0c2))
* **[Evals]**
* Update `adk eval` CLI to consume custom metrics by adding `CustomMetricEvaluator` ([ea0934b](https://github.com/google/adk-python/commit/ea0934b9934c1fefd129a1026d6af369f126870e))
* Update `EvalConfig` and `EvalMetric` data models to support custom metrics ([6d2f33a](https://github.com/google/adk-python/commit/6d2f33a59cfba358dd758378290125fc2701c411))
* **[Observability]**
* Add minimal `generate_content {model.name}` spans and logs for non-Gemini inference and when `opentelemetry-inference-google-genai` dependency is missing ([935c279](https://github.com/google/adk-python/commit/935c279f8281bde99224f03d936b8abe51cbabfc))
* **[Integrations]**
* Enhance `TraceManager` asynchronous safety, enrich BigQuery plugin logging, and fix serialization ([a4116a6](https://github.com/google/adk-python/commit/a4116a6cbfadc161982af5dabd55a711d79348b7))
* **[Live]**
* Persist user input content to session in live mode ([a04828d](https://github.com/google/adk-python/commit/a04828dd8a848482acbd48acc7da432d0d2cb0aa))
### Bug Fixes
* Recursively extract input/output schema for AgentTool ([bf2b56d](https://github.com/google/adk-python/commit/bf2b56de6d0052e40b6d871b2d22c56e9225e145))
* Yield buffered `function_call` and `function_response` events during live streaming ([7b25b8f](https://github.com/google/adk-python/commit/7b25b8fb1daf54d7694bf405d545d46d2c012d2b))
* Update `authlib` and `mcp` dependency versions ([7955177](https://github.com/google/adk-python/commit/7955177fb28b8e5dc19aae8be94015a7b5d9882a))
* Set `LITELLM_MODE` to `PRODUCTION` before importing LiteLLM to prevent implicit `.env` file loading ([215c2f5](https://github.com/google/adk-python/commit/215c2f506e21a3d8c39551b80f6356943ecae320))
* Redact sensitive information from URIs in logs ([5257869](https://github.com/google/adk-python/commit/5257869d91a77ebd1381538a85e7fdc3a600da90))
* Handle asynchronous driver URLs in the migration tool ([4b29d15](https://github.com/google/adk-python/commit/4b29d15b3e5df65f3503daffa6bc7af85159507b))
* Remove custom metadata from A2A response events ([81eaeb5](https://github.com/google/adk-python/commit/81eaeb5eba6d40cde0cf6147d96921ed1bf7bb31))
* Handle `None` inferences in eval results ([7d4326c](https://github.com/google/adk-python/commit/7d4326c3606a7ff2ba3c0fdef08d4f6af52ee71e))
* Mark all parts of a thought event as thought ([f92d4e3](https://github.com/google/adk-python/commit/f92d4e397f37445fe9032a95ce26646a3a69300b))
* Use `json.dumps` for error messages in SSE events ([6ad18cc](https://github.com/google/adk-python/commit/6ad18cc2fc3a3315a0fc240cb51b3283b53116b4))
* Use the correct path for config-based agents when deploying to AgentEngine ([83d7bb6](https://github.com/google/adk-python/commit/83d7bb6ef0d952ad04c5d9a61aaf202672c7e17d))
* Support Generator and Async Generator tool declarations in JSON schema ([19555e7](https://github.com/google/adk-python/commit/19555e7dce6d60c3b960ca0bc2f928c138ac3cc0) [7c28297](https://github.com/google/adk-python/commit/7c282973ea193841fee79f90b8a91c5e02627ccc))
* Prevent stopping event processing on events with `None` content ([ed2c3eb](https://github.com/google/adk-python/commit/ed2c3ebde9cafbb5e2bf375f44db1e77cee9fb24))
* Fix `'NoneType'` object is not iterable error ([7db3ce9](https://github.com/google/adk-python/commit/7db3ce9613b1c2c97e6ca3cd8115736516dc1556))
* Use canonical tools to find streaming tools and register them by `tool.name` ([ec6abf4](https://github.com/google/adk-python/commit/ec6abf401019c39e8e1a8d1b2c7d5cf5e8c7ac56))
* Initialize `self._auth_config` inside `BaseAuthenticatedTool` to access authentication headers in `McpTool` ([d4da1bb](https://github.com/google/adk-python/commit/d4da1bb7330cdb87c1dcbe0b9023148357a6bd07))
* Only filter out audio content when sending history ([712b5a3](https://github.com/google/adk-python/commit/712b5a393d44e7b5ce35fc459da98361bae4bb16))
* Add finish reason mapping and remove custom file URI handling in LiteLLM ([89bed43](https://github.com/google/adk-python/commit/89bed43f5e0c5ad12dd31c716d372145b7e33e78))
* Convert unsupported inline artifact MIME types to text in `LoadArtifactsTool` ([fdc98d5](https://github.com/google/adk-python/commit/fdc98d5c927bfef021e87cf72103892e4c2ac12a))
* Pass `log_level` to `uvicorn` in `web` and `api_server` commands ([38d52b2](https://github.com/google/adk-python/commit/38d52b247600fb45a2beeb041c4698e90c00d705))
* Use the agent name as the author of the audio event ([ab62b1b](https://github.com/google/adk-python/commit/ab62b1bffd7ad2df5809d430ad1823872b8bd67a))
* Handle `NOT_FOUND` error when fetching Vertex AI sessions ([75231a3](https://github.com/google/adk-python/commit/75231a30f1857d930804769caf88bcc20839dd08))
* Fix `httpx` client closure during event pagination ([b725045](https://github.com/google/adk-python/commit/b725045e5a1192bc9fd5190cbd2758ab6ff02590))
### Improvements
* Add new conversational analytics API toolset ([82fa10b](https://github.com/google/adk-python/commit/82fa10b71e037b565cb407c82e9e908432dab0ff))
* Filter out `adk_request_input` event from content list ([295b345](https://github.com/google/adk-python/commit/295b34558774d1f64022009980e3edd8eb79527b))
* Always skip executing partial function calls ([d62f9c8](https://github.com/google/adk-python/commit/d62f9c896c301aba3a781e868735e16f946a8862))
* Update comments of request confirmation preprocessor ([1699b09](https://github.com/google/adk-python/commit/1699b090edc9e5b13c34f461c8e664187157c5c0))
* Fix various typos ([a8f2ddd](https://github.com/google/adk-python/commit/a8f2ddd943301bbf53f49b3a23300ece45803cc0))
* Update sample live streaming tools agent to use latest live models ([3dd7e3f](https://github.com/google/adk-python/commit/3dd7e3f1b9be05c28adb061864d84c4202a2d922))
* Make the regex to catch CLI reference strict by adding word boundary anchor ([c222a45](https://github.com/google/adk-python/commit/c222a45ef74f7b55c48dc151ba98cd8c30a15c57))
* Migrate `ToolboxToolset` to use `toolbox-adk` and align validation ([7dc6adf](https://github.com/google/adk-python/commit/7dc6adf4e563330a09e4cf28d2b1994c24b007d1) [277084e](https://github.com/google/adk-python/commit/277084e31368302e6338b69d456affd35d5fedfe))
* Always log API backend when connecting to live model ([7b035aa](https://github.com/google/adk-python/commit/7b035aa9fc43a43489aeffea8f877cd7eaa09f35))
* Add a sample BigQuery agent using BigQuery MCP tools ([672b57f](https://github.com/google/adk-python/commit/672b57f1b76580023d1f348de76227291a9c1012))
* Add a `DebugLoggingPlugin` to record human-readable debugging logs ([8973618](https://github.com/google/adk-python/commit/8973618b0b0e90c513873e22af272c147efb4904))
* Upgrade the sample BigQuery agent model version to `gemini-2.5-flash` ([fd2c0f5](https://github.com/google/adk-python/commit/fd2c0f556b786417a9f6add744827b07e7a06b7d))
* Import `migration_runner` lazily within the migrate command ([905604f](https://github.com/google/adk-python/commit/905604faac82aca8ae0935eebea288f82985e9c5))
## [1.22.1](https://github.com/google/adk-python/compare/v1.22.0...v1.22.1) (2026-01-09)
@@ -531,7 +706,7 @@
* Set `max_output_tokens` for the agent builder ([2e2d61b](https://github.com/google/adk-python/commit/2e2d61b6fecb90cd474d6f51255678ff74b67a9b))
* Set default response modality to AUDIO in run_session ([68402bd](https://github.com/google/adk-python/commit/68402bda49083f2d56f8e8488fe13aa58b3bc18c))
* Update remote_a2a_agent to better handle streaming events and avoid duplicate responses ([8e5f361](https://github.com/google/adk-python/commit/8e5f36126498f751171bb2639c7f5a9e7dca2558))
* Update the load_artifacts tool so that the model can reliably call it for follow up questions about the same artifact ([238472d](https://github.com/google/adk-python/commit/238472d083b5aa67551bde733fc47826ff062679))
* Update the load_artifacts tool so that the model can reliably call it for follow-up questions about the same artifact ([238472d](https://github.com/google/adk-python/commit/238472d083b5aa67551bde733fc47826ff062679))
* Fix VertexAiSessionService base_url override to preserve initialized http_options ([8110e41](https://github.com/google/adk-python/commit/8110e41b36cceddb8b92ba17cffaacf701706b36), [c51ea0b](https://github.com/google/adk-python/commit/c51ea0b52e63de8e43d3dccb24f9d20987784aa5))
* Handle `App` instances returned by `agent_loader.load_agent` ([847df16](https://github.com/google/adk-python/commit/847df1638cbf1686aa43e8e094121d4e23e40245))
@@ -698,7 +873,7 @@
* AgentTool returns last content, instead of the content in the last event [bcf0dda](https://github.com/google/adk-python/commit/bcf0dda8bcc221974098f3077007c9e84c63021a)
* Fix adk deploy docker file permission [ad81aa5](https://github.com/google/adk-python/commit/ad81aa54de1f38df580915b7f47834ea8e5f1004)
* Updating BaseAgent.clone() and LlmAgent.clone() to properly clone fields that are lists [29bb75f](https://github.com/google/adk-python/commit/29bb75f975fe0c9c9d9a7e534a9c20158e1cbe1e)
* Make tool description for bigquery `execute_sql` for various write modes self contained [167182b](https://github.com/google/adk-python/commit/167182be0163117f814c70f453d5b2e19bf474df)
* Make tool description for bigquery `execute_sql` for various write modes self-contained [167182b](https://github.com/google/adk-python/commit/167182be0163117f814c70f453d5b2e19bf474df)
* Set invocation_id and branch for event generated when both output_schema and tools are used [3f3aa7b](https://github.com/google/adk-python/commit/3f3aa7b32d63cae5750d71bc586c088427c979ea)
* Rework parallel_agent.py to always aclose async generators [826f554](https://github.com/google/adk-python/commit/826f5547890dc02e707be33a3d6a58b527dac223)
* Add table metadata info into Spanner tool `get_table_schema` and fix the key usage info [81a53b5](https://github.com/google/adk-python/commit/81a53b53d6336011187a50ae8f1544de9b2764a8)
+12
View File
@@ -188,6 +188,18 @@ part before or alongside your code PR.
pytest ./tests/unittests
```
**Alternatively**, use the included `unittests.sh` script which handles
environment setup and restoration automatically:
```shell
./scripts/unittests.sh
```
This script will:
- Set up the test environment with minimal dependencies (`test`, `eval`, `a2a`)
- Run the unit tests
- Restore the full development environment (`--all-extras`)
6. **Auto-format the code:**
**NOTE**: We use `isort` and `pyink` for styles. Use the included
+1 -1
View File
@@ -115,7 +115,7 @@ root_agent = Agent(
### Define a multi-agent system:
Define a multi-agent system with coordinator agent, greeter agent, and task execution agent. Then ADK engine and the model will guide the agents works together to accomplish the task.
Define a multi-agent system with coordinator agent, greeter agent, and task execution agent. Then ADK engine and the model will guide the agents to work together to accomplish the task.
```python
from google.adk.agents import LlmAgent, BaseAgent
+1 -1
View File
@@ -1,5 +1,5 @@
#!/bin/bash
# Copyright 2025 Google LLC
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+1 -1
View File
@@ -1,4 +1,4 @@
# Copyright 2025 Google LLC
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+1 -1
View File
@@ -1,4 +1,4 @@
# Copyright 2025 Google LLC
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,4 +1,4 @@
# Copyright 2025 Google LLC
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.

Some files were not shown because too many files have changed in this diff Show More