chore: sync main -> v2#4915
Open
Jacksunwei wants to merge 300 commits intov2from
Open
Conversation
Renames the imported module from `agentic_sandbox` to `k8s_agent_sandbox` in `gke_code_executor.py` and updates the required version in `pyproject.toml` to `>=0.1.1.post3`. Closes #4883 Co-authored-by: Liang Wu <wuliang@google.com> PiperOrigin-RevId: 885840142
- Introduced a new `AuthScheme` named `GcpIamConnectorAuth` in `google.adk.integrations.iam_connector` package. - The feature is currently disabled through the newly added `GCP_IAM_CONNECTOR_AUTH`experimentation flag. - The newly added `GcpAuthProvider` class in `adk/integrations/iam_connector/gcp_auth_provider.py` is for internal ADK use and developer should not depend on it. PiperOrigin-RevId: 886070137
PiperOrigin-RevId: 886119834
The ADK experimental warnings can already be disabled with an environment variable, enable the same behavior for A2A to avoid log spam. Co-authored-by: Tim Niemueller <timdn@google.com> PiperOrigin-RevId: 886233489
This change introduces a separate async session factory for Spanner connections configured with `read_only=True` Close #4771 Co-authored-by: George Weale <gweale@google.com> PiperOrigin-RevId: 886267104
Modified compaction logic to exclude events containing function calls for which no corresponding function response has been recorded in the session. Added helper functions to identify pending function call IDs and check if an event contains such IDs. Applied this exclusion to both sliding window and token threshold-based compaction strategies Close #4740 Co-authored-by: George Weale <gweale@google.com> PiperOrigin-RevId: 886268526
Kebab-case is the standard for skill names/directories given by the Skill spec. However, to enable support for importing within skill scripts (python does not allow imports with kebab-case, only snake case), allow snake case for the skill name. Co-authored-by: Kathy Wu <wukathy@google.com> PiperOrigin-RevId: 886351132
DiscoveryEngineSearchTool hardcoded search_result_mode to CHUNKS, which fails with a 400 error for structured datastores (e.g. Jira Cloud connectors) that require DOCUMENTS mode. This broke VertexAiSearchTool with bypass_multi_tools_limit=True for structured data. Add auto-detection: default mode is now None, which tries CHUNKS first and automatically falls back to DOCUMENTS when the API returns the structured-datastore error. Users can also explicitly set the mode via the new SearchResultMode enum to skip auto-detection. Fixes #3406 Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com> PiperOrigin-RevId: 886354417
PiperOrigin-RevId: 886400492
Co-authored-by: Xuan Yang <xygoogle@google.com> PiperOrigin-RevId: 886446298
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
PiperOrigin-RevId: 886852929
Support Starlette lifespan protocol in to_a2a() so users can run
async startup/shutdown logic (e.g. initializing DB connections,
loading prompt registries) without resorting to module-level globals.
The lifespan parameter accepts a standard Starlette async context
manager. Internally, a composed lifespan runs the A2A route setup
first, then delegates to the user's lifespan if provided. This also
replaces the deprecated add_event_handler("startup", ...) pattern
with the modern Starlette(lifespan=...) constructor.
Closes #4701
Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 886892363
This change enables the conversion of ADK EventActions, serialized within A2A object metadata, back into ADK Event objects. It includes logic to parse JSON-encoded metadata values and to merge EventActions from multiple sources within an A2A Task Close #3968 Co-authored-by: George Weale <gweale@google.com> PiperOrigin-RevId: 886927688
PiperOrigin-RevId: 888114589
The log message when instantiating DatabaseSessionService is updated from "Falling back to..." to "Using..." for clarity. Close #4890 Co-authored-by: George Weale <gweale@google.com> PiperOrigin-RevId: 888160397
Close #4947 Co-authored-by: George Weale <gweale@google.com> PiperOrigin-RevId: 888296476
PiperOrigin-RevId: 888314229
…82.6 Versions 1.82.7 and 1.82.8 of LiteLLM were affected by a supply chain attack and are now explicitly excluded from the dependency constraints for both project and dev dependencies. Co-authored-by: George Weale <gweale@google.com> PiperOrigin-RevId: 888818704
Co-authored-by: Sasha Sobran <asobran@google.com> PiperOrigin-RevId: 888850792
Introduces a new index `idx_events_app_user_session_ts` on the `events` table in both V0 and V1 database schemas. This index covers `app_name`, `user_id`, `session_id`, and `timestamp` (descending) to improve query performance. Modifies `DatabaseSessionService` to automatically create any missing indexes defined in the SQLAlchemy metadata when preparing the database tables. Close #4827 Co-authored-by: George Weale <gweale@google.com> PiperOrigin-RevId: 888877174
Update the `model_config` for `Event` to set `extra='ignore'`. This allows the `Event` model to be initialized with fields not explicitly defined in the model, preventing errors when deserializing data that may contain additional, unneeded fields. This allows the session service to accept 2.0 events. Co-authored-by: Shangjie Chen <deanchen@google.com> PiperOrigin-RevId: 889327445
…sionService Introduces a new helper function, `_get_or_create_state`, which uses a nested transaction (SAVEPOINT) to safely attempt creating a state row. If a concurrent transaction has already inserted the row, the inner insert will fail with an IntegrityError, which is caught, and the already-existing row is then fetched Close #4954 Co-authored-by: George Weale <gweale@google.com> PiperOrigin-RevId: 889441684
…d LiteLLM upperbound Co-authored-by: Sasha Sobran <asobran@google.com> PiperOrigin-RevId: 889449878
…or clearer agent feedback and correct typing PiperOrigin-RevId: 889521009
- Migrate `tools/bigquery` to `integrations/bigquery` to match standard ADK layout. - Update unit tests to fully assert integration migration. Co-authored-by: Haiyuan Cao <haiyuan@google.com> PiperOrigin-RevId: 889634966
- Migrate `tools/bigquery` to `integrations/bigquery` to match standard ADK layout. - Update unit tests to fully assert integration migration. PiperOrigin-RevId: 889796517
The rewind logic is updated to ensure that state keys set during session creation are not nullified when rewinding. Previously, any key not present in the state at the rewind point was removed. Now, only keys that have appeared in any event's state delta are considered for nullification during a rewind, preventing the removal of initial session state Close #4933 PiperOrigin-RevId: 905322038
Co-authored-by: Shangjie Chen <deanchen@google.com> PiperOrigin-RevId: 905354260
Merge #5295 ## Summary Fixes #5294. This PR tightens `VertexAiRagMemoryService` memory scoping by replacing the ambiguous dot-delimited RAG `display_name` format with an encoded v1 format for new uploads. Search results are now parsed into exact `app_name`, `user_id`, and `session_id` components before being accepted. The change also keeps compatibility for old unambiguous legacy display names in the exact `app.user.session` form, while ignoring ambiguous legacy names that contain extra dot-delimited components. ## Why The previous client-side filter used: ```python context.source_display_name.startswith(f"{app_name}.{user_id}.") ``` That can collide for IDs such as `alice` and `alice.smith`, allowing memory stored under `demo.alice.smith.*` to pass a lookup for `demo` / `alice`. ## Tests ```text PYTHONPATH=src python -m pytest tests/unittests/memory -q 42 passed, 2 warnings python -m isort --check-only src/google/adk/memory/vertex_ai_rag_memory_service.py tests/unittests/memory/test_vertex_ai_rag_memory_service.py passed python -m pyink --check --config pyproject.toml src/google/adk/memory/vertex_ai_rag_memory_service.py tests/unittests/memory/test_vertex_ai_rag_memory_service.py passed git diff --check -- src/google/adk/memory/vertex_ai_rag_memory_service.py tests/unittests/memory/test_vertex_ai_rag_memory_service.py passed ``` ## Checklist - [x] I have read the CONTRIBUTING.md document. - [x] I have performed a self-review of my own code. - [x] I have added tests that prove my fix is effective. - [x] New and existing unit tests pass locally with my changes. COPYBARA_INTEGRATE_REVIEW=#5295 from petrmarinec:fix/vertex-rag-memory-scope 64a8f5a PiperOrigin-RevId: 905365796
Merge #5343 ## Summary Fixes #5341 — `convert_genai_part_to_a2a_part()` drops `Part(text='')` because the truthiness check `if part.text:` treats empty strings as falsy. ## Root Cause `Part(text='')` is valid and is produced in at least two places in the ADK: 1. **`code_executors/code_execution_utils.py`** — when code execution completes with `None` output 2. **`models/interactions_utils.py`** — when the Interactions API returns `None` text content Gemini 2.5 Flash (thinking mode) also emits empty text parts. When the converter drops all parts the A2A message ends up with zero parts and the client sees "broken thinking" with no content. ## Fix Change line 182 from `if part.text:` to `if part.text is not None:` so that empty strings are correctly wrapped as `TextPart` while `None` is still skipped. ## Test Added `test_convert_empty_text_part` — verifies that `Part(text='')` produces a valid `TextPart(text='')` instead of returning `None`. COPYBARA_INTEGRATE_REVIEW=#5343 from voidborne-d:fix/part-converter-empty-text dbb2f20 PiperOrigin-RevId: 905370961
… detection to schema resolution PiperOrigin-RevId: 905576545
PiperOrigin-RevId: 906139925
Use sphinx-click to automatically generate documentation for the CLI commands in the google.adk.cli module. Closes #4500 Co-authored-by: Sasha Sobran <asobran@google.com> PiperOrigin-RevId: 906328549
Co-authored-by: George Weale <gweale@google.com> PiperOrigin-RevId: 906466855
Co-authored-by: Xuan Yang <xygoogle@google.com> PiperOrigin-RevId: 906753501
PiperOrigin-RevId: 906864805
Merge #5489 Closes #5488 ## Summary Bumps the `litellm` constraint from `<=1.82.6` to `>=1.83.7,<=1.83.14` in both the base project dependencies and the `[test]` extras. The current cap was added in [`77f1c41`](77f1c41) to exclude the March 2026 supply-chain compromise of litellm 1.82.7 and 1.82.8. Since then, **five CVEs have been disclosed against litellm `<=1.82.6`** (2 critical, 3 high), with patches in 1.83.0 and 1.83.7. The new lower bound (1.83.7) is strictly above the originally compromised versions, so the original concern is still respected. The upper bound is pinned to the current latest release on PyPI (1.83.14) per reviewer request, mirroring the project's prior exact-version cap pattern. New litellm releases will require an explicit ADK PR to admit, the same way `<=1.82.6` did. Full CVE list and rationale in the linked issue (#5488). ## Diff Two identical edits, one in project deps (line 126) and one in `[test]` extras (line 145): ```diff - "litellm>=1.75.5,<=1.82.6", # ... supply chain attack ... + "litellm>=1.83.7,<=1.83.14", # For LiteLlm class. Lower bound: 5 CVE patches (2026-04). Upper bound pinned to current latest; bump deliberately. See #5488. ``` ## Testing plan 1. Re-installed `google-adk` (editable) against the updated constraint; pip resolved litellm to 1.83.13 (latest stable compatible with the rest of the lockfile, inside the new `[1.83.7, 1.83.14]` window). 2. Ran `tests/unittests/models/test_litellm.py` and `tests/unittests/models/test_litellm_import.py`; **all 259 tests pass**. Output below. 3. Verified `pyproject.toml` is parseable as TOML. ### Upstream litellm test output ``` collected 259 items tests/unittests/models/test_litellm.py ................................. [ 12%] ........................................................................ [ 40%] ........................................................................ [ 68%] ........................................................................ [ 96%] ....... [ 98%] tests/unittests/models/test_litellm_import.py ... [100%] ============================= 259 passed in 6.57s ============================== ``` ## Heads up: litellm hard-pins python-dotenv While verifying, we discovered that **litellm 1.83.7 (and every subsequent version through 1.83.14) hard-pins `python-dotenv==1.0.1`** as an unconditional core dependency. By contrast, litellm 1.82.6 declared `python-dotenv>=0.2.0` (loose). This does **not** affect adk-python itself -- ADK declares `python-dotenv>=1,<2`, which admits `1.0.1` cleanly. But any downstream project that has tightened `python-dotenv` (e.g. `>=1.2.x`) will hit a resolver conflict after this bump and may need to either relax its python-dotenv constraint or apply a package-manager override. This is a litellm anti-pattern, not an ADK problem; included here so reviewers know to expect downstream issues of that shape. ## Out of scope `langgraph` has a similar dep cap (`<0.4.8`) and one medium-severity CVE ([GHSA-g48c-2wqr-h844](GHSA-g48c-2wqr-h844)), but bumping past 0.4.x requires porting ADK's use of the removed `graph.graph` API (per [#1687](#1687)). That is real engineering work, not a dep cap bump, and is left as a separate effort. COPYBARA_INTEGRATE_REVIEW=#5489 from cwest:topic/bump-litellm-cap 559f0c2 PiperOrigin-RevId: 906979886
Co-authored-by: Kathy Wu <wukathy@google.com> PiperOrigin-RevId: 907023117
PiperOrigin-RevId: 907140836
Co-authored-by: Wiktoria Walczak <wwalczak@google.com> PiperOrigin-RevId: 907418898
`gemini-1.*` and `gemini-2.0*` models are respectively deprecated and scheduled for shutdown on June 1, 2026. `gemini-2.5*` models are their successors. No regressions in unit tests: ``` ========================================================================================== 5583 passed, 2237 warnings in 84.91s (0:01:24) =========================================================================================== ``` PiperOrigin-RevId: 907663315
… and `output_schema` together PiperOrigin-RevId: 907857917
…ation tests PiperOrigin-RevId: 907996031
Previously it was just in adk create, now add it to adk deploy in case users create an agent on their own and need to deploy with api key. Moved the shared logic into a utils/onboarding.py file Co-authored-by: Kathy Wu <wukathy@google.com> PiperOrigin-RevId: 908191494
Close #5103 Co-authored-by: Kathy Wu <wukathy@google.com> PiperOrigin-RevId: 908196458
Co-authored-by: Sasha Sobran <asobran@google.com> PiperOrigin-RevId: 908322085
… 3.1 tool calls Fixes #5407 END_PUBLIC Merge #5408 ## Summary - Tool call parts received via `LiveServerToolCall` in `GeminiLlmConnection.receive()` are now yielded immediately instead of being deferred until `turn_complete` - This unblocks function/tool calling for Gemini 3.1 Flash Live models which do not emit `turn_complete` until they receive the tool response ## Problem Gemini 3.1 Flash Live models send tool calls via `LiveServerToolCall` and wait for the tool response before sending `turn_complete`. The current code accumulates `tool_call_parts` and only yields them on `turn_complete` or loop exit, creating a deadlock where tools are never executed. ## Fix Yield `tool_call_parts` immediately after receiving `message.tool_call`. This is backward-compatible — earlier models that send `turn_complete` after tool calls will still work because the existing yield paths become no-ops when `tool_call_parts` is already empty. ## Test plan - [x] Tested with `gemini-3.1-flash-live-preview` in live mode — tool calls now execute on the first message and the model responds with audio after receiving tool results - [x] Verified no regression with the existing `turn_complete`-based flow Co-authored-by: Sasha Sobran <asobran@google.com> COPYBARA_INTEGRATE_REVIEW=#5408 from sandeshveerani4:fix/live-tool-call-yield ca0e760 PiperOrigin-RevId: 908326192
…onal` for conversation_scenario support Close #5214 Co-authored-by: George Weale <gweale@google.com> PiperOrigin-RevId: 908347275
Co-authored-by: George Weale <gweale@google.com> PiperOrigin-RevId: 908397117
Co-authored-by: Kathy Wu <wukathy@google.com> PiperOrigin-RevId: 908414335
Co-authored-by: Yifan Wang <wanyif@google.com> PiperOrigin-RevId: 908496612
Co-authored-by: Yifan Wang <wanyif@google.com> PiperOrigin-RevId: 908883116
…mResponse Co-authored-by: George Weale <gweale@google.com> PiperOrigin-RevId: 908900779
This fixes an issue where AgentEngineSandboxCodeExecutor catches the wrong exception class when attempting to recover from externally-deleted sandboxes. Fixes #5480 Co-authored-by: Amaad Martin <amaadmartin@google.com> PiperOrigin-RevId: 908965545
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
20 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Automated sync of v1 changes from main into v2. The oncall is responsible for reviewing and merging this PR. Resolve conflicts in favor of the v2 implementation.