This change keeps dependencies to their major versions, but for the pre 1.0.0 releases pinned to minor releases as they could have breaking changes.
PyYAML: Version 7.0 is in development and could have breaking changes
absolufy-imports: The package is archived and no longer maintained.
anyio: Follows SemVer, so version 5.0 could have breaking changes.
authlib: Follows a SemVer-like pattern, so version 2.0 could have breaking changes.
click: A mature library, version 9.0 is the expected boundary for breaking changes.
fastapi: As a pre-1.0 library, the next minor release could have breaking changes.
google-api-python-client: Although in maintenance, version 3.0 could still have breaking changes.
google-cloud-aiplatform: Follows SemVer, so breaking changes are expected in version 2.0.
google-cloud-secret-manager: A stable Google library, version 3.0 could lead to breaking changes.
google-cloud-speech: A stable Google library, version 3.0 could lead to breaking changes.
google-cloud-storage: A stable Google library.
google-genai: As an official Google SDK, version 2.0 is the expected boundary for breaking changes.
graphviz: As a pre-1.0 library, the next minor release could have breaking changes.
mcp: As an SDK, version 2.0 is the boundary for potential breaking changes.
opentelemetry-api: Follows SemVer; version 2.0 could have breaking changes.
opentelemetry-exporter-gcp-trace: It's tied to the v1 OpenTelemetry API, so version 2.0 would likely be a breaking change.
opentelemetry-sdk: It's coupled to the v1 API, so version 2.0 would likely be a breaking change.
pydantic: This stops upgrades to the incompatible version 3.0 after its major 2.0 rewrite.
python-dateutil: Follows to SemVer, making version 3.0 the boundary for potential breaking changes.
python-dotenv: Locks to stable version 1.0 major release.
requests: As a more mature library, version 3.0 is boundary for breaking changes.
sqlalchemy: This locks the dependency to the stable version 2.0 API after its major rewrite.
starlette: As a pre-1.0 library, the next minor release could have breaking changes.
tenacity: This is a mature library, version 9.0 is boundary for breaking changes.
typing-extensions: Major versions are tied to large typing changes in Python itself.
tzlocal: The library has a history of introducing breaking API changes between major versions.
uvicorn: As a pre-1.0 library, the next minor release could have breaking changes.
watchdog: As a stable library, version 7.0 could have breaking changes.
websockets: Follows SemVer, so version 16.0 is the boundary for breaking changes.
PiperOrigin-RevId: 794677571
Verified with uv on Python 3.12 and 3.13 using the same ignores as CI.
3.12:
uv python install 3.12 && uv venv --python 3.12 .venv && source .venv/bin/activate
uv sync --extra test --extra eval --extra a2a
python -m pytest tests/unittests --ignore=tests/unittests/artifacts/test_artifact_service.py --ignore=tests/unittests/tools/google_api_tool/test_googleapi_to_openapi_converter.py
3.13: repeated the above with 3.13 (separate env)
Result: All unit tests passed
PiperOrigin-RevId: 794669437
Corrects a typo in the `StreamableHTTPConnectionParams` docstring, changing "SSE" to "Streamable HTTP" to accurately reflect the referenced client.
PiperOrigin-RevId: 794424727
For Vertex model backend, we send response back. This doesn't work for streaming tools that the return type is AsyncGenerator. So the fix here is to ignore the return type when it's AsyncGenerator.
We can't distinguish streaming vs non-streaming tool with AsyncGenerator though as LiveRequestQueue is optional in streaming tool.
Adds an `ignore_response` option to `build_function_declaration` to skip including the return type in the function declaration. This is enabled for tools that return `AsyncGenerator`, as the model does not yet support understanding these return types, while streaming tools can still handle them. Also, removes redundant return statements in `_get_mandatory_params`.
PiperOrigin-RevId: 794392846
This is to address the name conflict issue of tools returned by different toolset. Mainly it's to give each toolset a namespace.
We have a flag `add_tool_name_prefix` to decide whether to apply this behavior
We have a `tool_name_prefix` to let client specify a custom prefix, if not set , toolset name will be used as prefix.
PiperOrigin-RevId: 794306796
Merge https://github.com/google/adk-python/pull/1815
fix: path parameter extraction for complex Google API endpoints
- Fix GoogleApiToOpenApiConverter to handle path parameters in complex endpoints like /v1/documents/{documentId}:batchUpdate
- Use Google Discovery Document 'location' field
- Add comprehensive test suite for Google Docs batchUpdate functionality
- Verify parameter location handling for complex endpoint patterns
- Test schema validation for BatchUpdateDocumentRequest/Response
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/1815 from goldylocks87:fix-issue-1814-path-parameter-extraction af5508ec6975b1ccbc34931a0041e422ee259c16
PiperOrigin-RevId: 794301898
Spanner toolset support basic operations to interact with Spanner table metadata and query results.
Consolidate BigQueryTool into generic GoogleTool, so that BigQueryToolset and SpannerToolset can share.
PiperOrigin-RevId: 794259782
The issue was caused by a breaking change in Python 3.13's inspect.cleandoc() function that made it more conservative about whitespace handling:
Root Cause:
- Python 3.12-: inspect.cleandoc() used line.lstrip() - strips all whitespace (spaces, tabs, etc.)
- Python 3.13+: inspect.cleandoc() uses line.lstrip(' ') - strips only space characters
PiperOrigin-RevId: 793921360
Demonstrates intelligent triage system with root planning agent and parallel
execution agents.
Use session state to store the execution plan and coordinate with other specialized agents.
Check out README.md for more details.
PiperOrigin-RevId: 793884758
Google Team Member
Xuan Yang
Wei Sun (Jack)
Kacper Jawoszek
Xiang (Sean) Zhou
George Weale
Hangfei Lin
Goldy
Shangjie Chen