LiteLLM's StreamHandlers output to stderr by default. In cloud environments like GCP, stderr output is treated as ERROR severity regardless of actual log level, causing INFO-level logs to be incorrectly classified as errors.
This change redirects LiteLLM loggers to stdout in two places:
- In `lite_llm.py`: Immediately after litellm import
- In `logs.py`: When `setup_adk_logger()` is called (with guard to check if litellm is imported)
Close#3824
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 843393874
LiteLLM's `ollama_chat` provider does not accept array-based content in messages. This change flattens multipart content by joining text parts or JSON-serializing non-text parts before sending the request to the LiteLLM completion API. This ensures compatibility with Ollama's chat endpoint.
Close#3727
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 843382361
The `_to_litellm_response_format` function now adapts the output format based on the provided model. Gemini models continue to use the "response_schema" key, while OpenAI-compatible models (including Azure OpenAI and Anthropic) now use the "json_schema" key as per LiteLLM's documentation for JSON mode. The schema name is also included in the "json_schema" format.
Close#3713Close#3890
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 843326850
Explicitly resolve the GCP project from arguments or environment variables before calling `spanner.Client`. This avoids redundant calls to `google.auth.default()` that newer versions of the Spanner library might make.
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 843320305
Performance: Switched to BigQuery Storage Write API with async batching, reducing agent latency.
Multimodal: Native support for GCS offloading (ObjectRef) for images, video, and large text.
Reliability: Added connection pooling, retries, and a "rescue flush" for safe shutdown on Cloud Run.
Observability: Fixed distributed tracing hierarchy with ContextVars support.
PiperOrigin-RevId: 843062561
This change introduces an add_session_to_memory method to both CallbackContext and ToolContext, allowing agents and tools to explicitly trigger the saving of the current session to the memory service. This enables more fine-grained control over when session data is persisted for memory generation. A ValueError is raised if the memory service is not configured.
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 843021899
Merge https://github.com/google/adk-python/pull/3875
# Problem
The example in `contributing/samples/human_in_loop/README.md` shows:
```python
await runner.run_async(...)
```
However, `run_async` returns an **async generator**, so awaiting it raises:
```
TypeError: object async_generator can't be used in 'await' expression
```
Additionally, the example payload uses `"ticket-id"` while ADK tools and other examples use `"ticketId"`, creating a mismatch that breaks copy/paste usage.
# Solution
- Updated the snippet to consume the async generator correctly:
```python
async for event in runner.run_async(...):
...
```
- Aligned the payload key from `"ticket-id"` → `"ticketId"` for consistency with ADK schema and other examples.
These changes make the example runnable and consistent with the API’s actual behavior.
# Testing Plan
This PR is a **small documentation correction**, so no unit tests are required per contribution guidelines.
- Verified the corrected snippet manually to ensure it no longer raises `TypeError`.
# Checklist
- [x] I have read the 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 – docs only)*
- [ ] I have added tests that prove my fix is effective or that my feature works. *(N/A – docs only)*
- [ ] New and existing unit tests pass locally with my changes. *(N/A – docs only)*
- [x] I have manually tested my changes end-to-end.
- [ ] Any dependent changes have been merged and published in downstream modules. *(N/A)*
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3875 from krishna-dhulipalla:docs/fix-adk-run_async-example 83fc5b430690b63b8b7bf1025ef03b0761264751
PiperOrigin-RevId: 842952362
When users instantiate LlmAgent directly (not subclassed), the origin inference incorrectly detected ADK's internal google/adk/agents/ path as a mismatch.
Use metadata from AgentLoader when available
Skip inference for google.adk.* module
Close#3143
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 842774292
Context: many issues related to local mult-agent system is tagged with a2a
Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 842397159
Add using the execute sql query return result as list of dictionaries.
In each dictionary the key is the column name and the value is the value of
the that column in a given row.
PiperOrigin-RevId: 840909555
This change introduces a `verify` parameter to `RestApiTool` and `OpenAPIToolset`. This parameter allows users to configure how SSL certificates are verified when making API calls using the `requests` library. Options include providing a path to a CA bundle, disabling verification, or using a custom `ssl.SSLContext`. New methods `configure_verify` and `configure_verify_all` are added to update this setting after initialization. This is useful for environments with TLS-intercepting proxies.
Fixes: https://github.com/google/adk-python/issues/3720
Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 840809727
The RemoteA2aAgent now extracts a "task_id" from the custom metadata of the last agent event in the session, alongside the existing "context_id". This task_id is then included in the A2AMessage sent to the remote A2A service.
Close#3765
PiperOrigin-RevId: 840375992
Update fastapi constraint from <0.119.0 to <0.124.0
Update starlette minimum version from >=0.46.2 to >=0.49.1
Closes#3822
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 840372879
When converting `types.Content` with a `function_response` to LiteLLM's `ChatCompletionToolMessage`, if the response is already a string, use it directly. Otherwise, serialize the response to JSON. This prevents double-serialization of string payloads
Close#3676
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 840013822
This change refactors how session, memory, and artifact services are created in the fast_api server, using the shared service_factory.
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 839997110
This change introduces `Gemma3Ollama`, a new LLM model class for running Gemma 3 models locally via Ollama, leveraging LiteLLM. The function calling logic previously in the `Gemma` class has been refactored into a `GemmaFunctionCallingMixin` and is now used by both `Gemma` and `Gemma3Ollama`. A new sample application, `hello_world_gemma3_ollama`, is added to demonstrate using `Gemma3Ollama` with an agent. Unit tests for `Gemma3Ollama` are also included.
Merge: https://github.com/google/adk-python/pull/3120
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 839996879
This change expands the supported file MIME types and introduces provider-specific handling for file uploads. For providers like OpenAI and Azure, inline file data is now uploaded via `litellm.acreate_file` to obtain a `file_id`, which is then used in the message content. Other providers continue to use base64 encoded file data. Affected functions have been updated to be asynchronous
Merge:https://github.com/google/adk-python/pull/2863
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 839996848
The RemoteA2aAgent now extracts a "task_id" from the custom metadata of the last agent event in the session, alongside the existing "context_id". This task_id is then included in the A2AMessage sent to the remote A2A service.
Close#3765
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 839996774
The warning message shows that ADK Web is for development purposes only and should not be used in production, as it has access to all data. This warning is displayed when the `--with-ui` flag is used with `adk deploy` and `adk deploy to-gke`
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 839795361
Merge https://github.com/google/adk-python/pull/3583
**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: #3582
**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 BigQuery tool in ADK does not provide a way for developers to add custom labels to BigQuery jobs created by their agents. This makes it difficult to:
Track and monitor BigQuery costs associated with specific agents or use cases
Organize and filter BigQuery jobs in the Google Cloud Console
Implement billing attribution and resource organization strategies
Differentiate between jobs from different environments (dev, staging, production)
While the tool automatically adds an internal adk-bigquery-tool label with the caller_id, there's no mechanism for users to add their own custom labels for tracking and monitoring purposes.
**Solution:**
Add a labels configuration field to BigQueryToolConfig that allows users to specify custom key-value pairs to be applied to all BigQuery jobs executed by the agent. The solution should:
Configuration Option: Add an optional labels parameter to BigQueryToolConfig accepting a dictionary of string key-value pairs
Validation: Ensure labels follow BigQuery's requirements (non-empty string keys, string values)
Job Application: Automatically apply configured labels to all BigQuery jobs alongside the existing internal labels Documentation: Provide clear documentation on how to use labels for tracking and monitoring
### Testing Plan
_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:**
- [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._
```
pytest tests/unittests/tools/bigquery/test_bigquery_tool_config.py -v --tb=line -W ignore::UserWarning
========================================= test session starts ==========================================
platform darwin -- Python 3.11.14, pytest-9.0.1, pluggy-1.6.0 -- *****redacted******
cachedir: .pytest_cache
rootdir: *****redacted******
configfile: pyproject.toml
plugins: mock-3.15.1, anyio-4.11.0, xdist-3.8.0, langsmith-0.4.43, asyncio-1.3.0
asyncio: mode=Mode.AUTO, debug=False, asyncio_default_fixture_loop_scope=function, asyncio_default_test_loop_scope=function
collected 14 items
tests/unittests/tools/bigquery/test_bigquery_tool_config.py::test_bigquery_tool_config_experimental_warning PASSED [ 7%]
tests/unittests/tools/bigquery/test_bigquery_tool_config.py::test_bigquery_tool_config_invalid_property PASSED [ 14%]
tests/unittests/tools/bigquery/test_bigquery_tool_config.py::test_bigquery_tool_config_invalid_application_name PASSED [ 21%]
tests/unittests/tools/bigquery/test_bigquery_tool_config.py::test_bigquery_tool_config_max_query_result_rows_default PASSED [ 28%]
tests/unittests/tools/bigquery/test_bigquery_tool_config.py::test_bigquery_tool_config_max_query_result_rows_custom PASSED [ 35%]
tests/unittests/tools/bigquery/test_bigquery_tool_config.py::test_bigquery_tool_config_valid_maximum_bytes_billed PASSED [ 42%]
tests/unittests/tools/bigquery/test_bigquery_tool_config.py::test_bigquery_tool_config_invalid_maximum_bytes_billed PASSED [ 50%]
tests/unittests/tools/bigquery/test_bigquery_tool_config.py::test_bigquery_tool_config_valid_labels PASSED [ 57%]
tests/unittests/tools/bigquery/test_bigquery_tool_config.py::test_bigquery_tool_config_empty_labels PASSED [ 64%]
tests/unittests/tools/bigquery/test_bigquery_tool_config.py::test_bigquery_tool_config_none_labels PASSED [ 71%]
tests/unittests/tools/bigquery/test_bigquery_tool_config.py::test_bigquery_tool_config_invalid_labels_type PASSED [ 78%]
tests/unittests/tools/bigquery/test_bigquery_tool_config.py::test_bigquery_tool_config_invalid_label_key_type PASSED [ 85%]
tests/unittests/tools/bigquery/test_bigquery_tool_config.py::test_bigquery_tool_config_invalid_label_value_type PASSED [ 92%]
tests/unittests/tools/bigquery/test_bigquery_tool_config.py::test_bigquery_tool_config_empty_label_key PASSED [100%]
==================================================================================================== 14 passed in 2.02s ====================================================================================================
```
**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.
- [x] Any dependent changes have been merged and published in downstream modules.
### Additional context
_Add any other context or screenshots about the feature request here._
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3583 from Faraaz1994:feature/bq_label 0fd7fe6a3b1ee20a36f73562e425d007b8d7dc9d
PiperOrigin-RevId: 839523588
The vector_store_similarity_search tool performs similarity search against data in a Spanner vector store table, using the provided Spanner tool settings for configuration.
PiperOrigin-RevId: 839352057
The Gemini API may not always send an explicit transcription finished signal. This change ensures that any buffered input or output transcription text is yielded as a finished transcription when a turn is completed, generation is complete, or the session is interrupted.
Also, refined the check for `event.partial` in runners.py to be more explicit.
Co-authored-by: Hangfei Lin <hangfei@google.com>
PiperOrigin-RevId: 839008606
LlmAgentConfig.model now accepts either a plain model string or a CodeConfig. This lets YAML configs pass a LiteLLM instance with managed API settings (e.g., api_base and fallbacks) so agents can hit KimiK2’s managed endpoint instead of only the default modelID.
Close#3579
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 838978654
This change adds new `POST` endpoint `/apps/{app_name}/users/{user_id}/sessions/{session_id}/artifacts` to the ADK web server. This endpoint lets clients to save new artifacts associated with a specific session. The endpoint uses `SaveArtifactRequest` and returns `SaveArtifactResponse`, including the version and canonical URI of the saved artifact.
Close#1975
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 838977880
Default CLI session storage to SQLite instead of in-memory
Previously, adk run and adk web used in-memory session storage by default, causing sessions to be lost on restart. Now sessions persist to .adk/session.db automatically. To use in-memory storage, pass --session-service-uri memory://
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 838975328
Merge https://github.com/google/adk-python/pull/3700
### Description
This PR refactors the `adk_stale_agent` to address `429 RESOURCE_EXHAUSTED` errors encountered during workflow execution. The previous implementation was inefficient in fetching issue history (using pagination over the REST API) and lacked server-side filtering, causing excessive API calls and huge token consumption that breached Gemini API quotas.
The new implementation switches to a **GraphQL-first approach**, implements server-side filtering via the Search API, adds robust concurrency controls, and significantly improves code maintainability through modular refactoring.
### Root Cause of Failure
The previous workflow failed with the following error due to passing too much context to the LLM and processing too many irrelevant issues:
```text
google.genai.errors.ClientError: 429 RESOURCE_EXHAUSTED.
Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_paid_tier_input_token_count
```
### Key Changes
#### 1. Optimization: REST → GraphQL (`agent.py`)
* **Old:** Fetched issue comments and timeline events using multiple paginated REST API calls (`/timeline`).
* **New:** Implemented `get_issue_state` using a single **GraphQL** query. This fetches comments, `userContentEdits`, and specific timeline events (Labels, Renames) in one network request.
* **Refactoring:** The complex analysis logic has been decomposed into focused helper functions (_fetch_graphql_data, _build_history_timeline, _replay_history_to_find_state) for better readability and testing.
* **Configurable:** Added GRAPHQL_COMMENT_LIMIT and GRAPHQL_TIMELINE_LIMIT settings to tune context depth
* **Impact:** Drastically reduces the data payload size and eliminates multiple API round-trips, significantly lowering the token count sent to the LLM.
#### 2. Optimization: Server-Side Filtering (`utils.py`)
* **Old:** Fetched *all* open issues via REST and filtered them in Python memory.
* **New:** Uses the GitHub Search API (`get_old_open_issue_numbers`) with `created:<DATE` syntax.
* **Impact:** Only fetches issue numbers that actually meet the age threshold, preventing the agent from wasting cycles and tokens on brand-new issues.
#### 3. Concurrency & Rate Limiting (`main.py` & `settings.py`)
* **Old:** Sequential execution loop.
* **New:** Implemented `asyncio.gather` with a configurable `CONCURRENCY_LIMIT` (set to 3).
* **New:** Added `urllib3` retry strategies (exponential backoff) in `utils.py` to handle GitHub API rate limits (HTTP 429) gracefully.
#### 4. Logic Improvements ("Ghost Edits")
* **New Feature:** The agent now detects "Ghost Edits" (where an author updates the issue description without posting a new comment).
* **Action:** If a silent edit is detected on a stale candidate, the agent now alerts maintainers instead of marking it stale, preventing false positives.
### File Comparison Summary
| File | Change |
| :--- | :--- |
| `main.py` | Switched from `InMemoryRunner` loop to `asyncio` chunked processing. Added execution timing and API usage logging. |
| `agent.py` | Replaced REST logic with GraphQL query. Added logic to handle silent body edits. Decomposed giant get_issue_state into helper functions with docstrings. Added _format_days helper. |
| `utils.py` | Added `HTTPAdapter` with Retries. Added `get_old_open_issue_numbers` using Search API. |
| `settings.py` | Removed `ISSUES_PER_RUN`; added configuration for CONCURRENCY_LIMIT, SLEEP_BETWEEN_CHUNKS, and GraphQL limits. |
| `PROMPT_INSTRUCTIONS.txt` | Simplified decision tree; removed date calculation responsibility from LLM. |
### Verification
The new logic minimizes token usage by offloading date calculations to Python and strictly limiting the context passed to the LLM to semantic intent analysis (e.g., "Is this a question?").
* **Metric Check:** The workflow now tracks API calls per issue to ensure we stay within limits.
* **Safety:** Silent edits by users now correctly reset the "Stale" timer.
* **Maintainability:** All complex logic is now isolated in typed helper functions with comprehensive docstrings.
Co-authored-by: Xuan Yang <xygoogle@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3700 from ryanaiagent:feat/improve-stale-agent 888064eff125ae74f7c3a9ad6c74f98de80243a2
PiperOrigin-RevId: 838885530
This change introduces an `AnthropicLlm` base class for direct Anthropic API calls using `AsyncAnthropic`. The existing `Claude` class now inherits from `AnthropicLlm` and is specialized to use `AsyncAnthropicVertex` for models hosted on Vertex AI. The `messages.create` call is now properly awaited
Merge: https://github.com/google/adk-python/pull/2904
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 838851026
This change updates the docstring for `agent_engine_id` to clarify that only the resource ID is expected. It also adds a warning log if the provided `agent_engine_id` contains a '/' character, suggesting it might be a full resource path, and provides guidance on how to extract the ID. Unit tests are added to verify the warning behavior.
Merge: https://github.com/google/adk-python/pull/2941
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 838845022
Also provide a command line tool `adk migrate session` for DB migration
Addresses https://github.com/google/adk-python/discussions/3605
Addresses https://github.com/google/adk-python/issues/3681
To verify:
```
# Start one postgres DB
docker run --name my-postgres -d -e POSTGRES_DB=agent -e POSTGRES_USER=agent -e POSTGRES_PASSWORD=agent -e PGDATA=/var/lib/postgresql/data/pgdata -v pgvolume:/var/lib/postgresql/data -p 5532:5432 postgres
# Connect to an old version of ADK and produce some query data
adk web --session_service_uri=postgresql://agent:agent@localhost:5532/agent
# Check out to the latest branch and restart ADK web
# You should see error log ask you to migrate the DB
# Start a new DB
docker run --name migration-test-db \
-d \ --rm \ -e POSTGRES_DB=agent \ -e POSTGRES_USER=agent \ -e POSTGRES_PASSWORD=agent -e PGDATA=/var/lib/postgresql/data/pgdata -v migration_test_vol:/var/lib/postgresql/data -p 5533:5432 postgres
# DB Migration
adk migrate session \
--source_db_url="postgresql://agent:agent@localhost:5532/agent" \
--dest_db_url="postgresql://agent:agent@localhost:5533/agent"
# Run ADK web with the new DB
adk web --session_service_uri=postgresql+asyncpg://agent:agent@localhost:5533/agent
# You should see the data from old DB is migrated
```
Co-authored-by: Shangjie Chen <deanchen@google.com>
PiperOrigin-RevId: 837341139
This calls the cloudapiregistry.googleapis.com API to get MCP tools from the project's registry, and adds them to ADK.
Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 837166909
Adds the shared adk_services_options decorator to adk run and other commands so developers can pass session/artifact URIs from the CLI
Has new warning for the unsupported memory service on adk run, and removes the legacy --session_db_url/--artifact_storage_uri flags with tests
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 836743358
This change routes adk run and the FastAPI server through the new session/artifact service factory, keeps the default experience backed by per-agent .adk storage
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 836733234
Previously, image parts were always filtered out when converting content to Anthropic message parameters. This change updates the logic to only filter out image parts and log a warning when the content role is not "user". This enables sending image data as part of user prompts to Claude models
Merges: https://github.com/google/adk-python/pull/3286
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 836725196
Merge https://github.com/google/adk-python/pull/3284
**Problem:**
When debugging agents that utilize the `VertexAiSearchTool`, it's currently difficult to inspect the specific configuration parameters (datastore ID, engine ID, filter, max_results, etc.) being passed to the underlying Vertex AI Search API via the `LlmRequest`. This lack of visibility can hinder troubleshooting efforts related to tool configuration.
**Solution:**
This PR enhances the `VertexAiSearchTool` by adding a **debug-level log statement** within the `process_llm_request` method. This log precisely records the parameters being used for the Vertex AI Search configuration just before it's appended to the `LlmRequest`.
This provides developers with crucial visibility into the tool's runtime behavior when debug logging is enabled, significantly improving the **debuggability** of agents using this tool. Corresponding unit tests were updated to rigorously verify this new logging output using `caplog`. Additionally, minor fixes were made to the tests to resolve Pydantic validation errors.
Co-authored-by: Xuan Yang <xygoogle@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3284 from omkute10:feat/add-logging-vertex-search-tool 199c12bf00a57abe202401591088c0423b39b928
PiperOrigin-RevId: 836419886
Merge https://github.com/google/adk-python/pull/2588
## Description
Fixes an issue in `base_llm_flow.py` where, in Bidi-streaming (live) mode, the multi-agent structure causes duplicated responses after tool calling.
## Problem
In Bidi-streaming (live) mode, when utilizing a multi-agent structure, the leaf-level sub-agent and its parent agent both process the same function call response, leading to duplicate replies. This duplication occurs because the parent agent's live connection remains open while initiating a new connection with the child agent.
## Root Cause
The issue originated from the placement of agent transfer logic in the `_postprocess_live` method at lines 547-557. When a `transfer_to_agent` function call was made:
1. The function response was processed in `_postprocess_live`
2. A recursive call to `agent_to_run.run_live` was initiated
3. This prevented the closure of the parent agent's connection at line 175 of the `run_live` method, as that code path was never reached
4. Both the parent and child agents remained active, causing both to process subsequent function responses
## Solution
This PR addresses the issue by ensuring the parent agent's live connection is closed before initiating a new one with the child agent. Changes made:
**Connection Management**: Moved the agent transfer logic from `_postprocess_live` method to the `run_live` method, specifically:
- Removed agent transfer handling from lines 547-557 in `_postprocess_live`
- Added agent transfer handling after connection closure at lines 176-184 in `run_live`
**Code Refactoring**: The agent transfer now occurs in the proper sequence:
1. Parent agent processes the `transfer_to_agent` function response
2. Parent agent's live connection is properly closed (line 175)
3. New connection with child agent is initiated (line 182)
4. Child agent handles subsequent function calls without duplication
**Improved Flow Control**: This ensures that each agent processes function call responses without duplication, maintaining proper connection lifecycle management in multi-agent structures.
## Testing
To verify this fix works correctly:
1. **Multi-Agent Structure Test**: Set up a multi-agent structure with a parent agent that transfers to a child agent via `transfer_to_agent` function call
2. **Bidi-Streaming Mode**: Enable Bidi-streaming (live) mode in the configuration
3. **Function Call Verification**: Trigger a function call that results in agent transfer
4. **Response Monitoring**: Verify that only one response is generated (not duplicated)
5. **Connection Management**: Confirm that parent agent's connection is properly closed before child agent starts
**Expected Behavior**:
- Single function response per call
- Clean agent handoffs without connection leaks
- Proper connection lifecycle management
## Backward Compatibility
This change is **fully backward compatible**:
- No changes to public APIs or method signatures
- Existing single-agent flows remain unaffected
- Non-live (regular async) flows continue to work as before
- Only affects the internal flow control in live multi-agent scenarios
Co-authored-by: Hangfei Lin <hangfei@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/2588 from AlexeyChernenkoPlato:fix/double-function-response-processing-issue 3339260a4e007251137d199bdcef0ddef4487b03
PiperOrigin-RevId: 835619170
This change replaces the use of `ChatCompletionDeveloperMessage` with `ChatCompletionSystemMessage` and sets the role to "system" for providing system instructions to LiteLLM models
Close#3657
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 835388738
Merge https://github.com/google/adk-python/pull/3576
**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: #3557
- Related: #_issue_number_
**2. Or, if no issue exists, describe the change:**
_If applicable, please follow the issue templates to provide as much detail as
possible._
**Problem:**
When creating a BaseAgent with multiple sub-agents, there was no validation to ensure that all sub-agents have unique names. This could lead to confusion when trying to find or reference specific sub-agents by name, as duplicate names would make it ambiguous which agent is being referenced.
**Solution:**
Added a @field_validator for the sub_agents field in BaseAgent that validates all sub-agents have unique names. The validator:
Checks for duplicate names in the sub-agents list
Raises a ValueError with a clear error message listing all duplicate names found
Returns the validated list if all names are unique
Handles edge cases like empty lists gracefully
### Testing Plan
_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:**
- [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._
Added 4 new test cases in tests/unittests/agents/test_base_agent.py:
test_validate_sub_agents_unique_names_single_duplicate: Verifies that a single duplicate name raises ValueError
test_validate_sub_agents_unique_names_multiple_duplicates: Verifies that multiple duplicate names are all reported in the error message
test_validate_sub_agents_unique_names_no_duplicates: Verifies that unique names pass validation successfully
test_validate_sub_agents_unique_names_empty_list: Verifies that empty sub-agents list passes validation
All tests pass locally. You can run with:
pytest tests/unittests/agents/test_base_agent.py::test_validate_sub_agents_unique_names_single_duplicate tests/unittests/agents/test_base_agent.py::test_validate_sub_agents_unique_names_multiple_duplicates tests/unittests/agents/test_base_agent.py::test_validate_sub_agents_unique_names_no_duplicates tests/unittests/agents/test_base_agent.py::test_validate_sub_agents_unique_names_empty_list -v
**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._
Test Case 1: Duplicate names should raise error
from google.adk.agents import Agent
agent1 = Agent(name="sub_agent", model="gemini-2.5-flash")
agent2 = Agent(name="sub_agent", model="gemini-2.5-flash") # Same name
# This should raise ValueError
try:
parent = Agent(
name="parent",
model="gemini-2.5-flash",
sub_agents=[agent1, agent2]
)
except ValueError as e:
print(f"Expected error: {e}")
# Output: Found duplicate sub-agent names: `sub_agent`. All sub-agents must have unique names.
Test Case 2: Unique names should work
from google.adk.agents import Agent
agent1 = Agent(name="agent1", model="gemini-2.5-flash")
agent2 = Agent(name="agent2", model="gemini-2.5-flash")
# This should work without error
parent = Agent(
name="parent",
model="gemini-2.5-flash",
sub_agents=[agent1, agent2]
)
print("Success: Unique names validated correctly")
### 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 change adds validation at the BaseAgent level, so it automatically applies to all agent types that inherit from BaseAgent (e.g., LlmAgent, LoopAgent, etc.). The validation uses Pydantic's field validator system, which runs during object initialization, ensuring the constraint is enforced early and consistently.
The error message clearly identifies which names are duplicated, making it easy for developers to fix the issue:
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3576 from sarojrout:feat/validate-unique-sub-agent-names 07adf1f9a5fc935389eb9dfa3cbc1311f551ebe3
PiperOrigin-RevId: 835358118
Merge https://github.com/google/adk-python/pull/3538
Main change from:
E(inv=2, role=user), E(inv=2, role=model), E(inv=2, role=user),
To:
E(inv=2, role=user), E(inv=2, role=model)
I think the last E(inv=2, role=user) was wrong. Also reformatted.
Co-authored-by: Hangfei Lin <hangfei@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3538 from adrianad:patch-1 627b933bdc3e00e45f704edf95448281e32d127c
PiperOrigin-RevId: 835346467
The `database_session_service` now updates the `update_time` of a session to the event's timestamp when an event is appended
Close#2721
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 834994070
LlmResponse/Event now keep both provider reasoning output and the raw vendor payload so callbacks and loggers can inspect hidden “thoughts” or trace bugs without rewriting adapters.
LiteLLM’s adapter and streaming loop emit reasoning chunks alongside text and aggregate them into final events -> all responses now carry a JSON-safe copy of the source payload for debug. UnsafeLocalCodeExecutor uses the documented exec(code, globals, globals) form, letting helper functions defined inside snippets call each other.
Close#1749
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 834956847
Merge https://github.com/google/adk-python/pull/3430
**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: #3429
**2. Or, if no issue exists, describe the change:**
_If applicable, please follow the issue templates to provide as much detail as
possible._
**Problem:**
The existing `/list-apps` endpoint only returns the name of the folder that each agent is in
**Solution:**
This adds a new endpoint `/list-apps-detailed` which will load each agent using the existing `AgentLoader.load_agent` method, and then return the folder name, display name (with underscores replaced with spaces for a more readable version), description, and the agent type.
This does introduce overhead if you had multiple agents since they all need to be loaded, but by maintaining the existing `/list-apps` endpoint, users can choose which one to hit if they don't want to load all agents. Since the existing `load_agents` method will cache results, there's only a penalty on the first hit.
### Testing Plan
Created a unit test for this, similar to the `/list-apps`. Also tested this with my own ADK instance to verify it loaded correctly.
```
curl --location "localhost:8000/list-apps-detailed"
```
```json
{
"apps": [
{
"name": "agent_1",
"displayName": "Agent 1",
"description": "A test description for a test agent",
"agentType": "package"
},
{
"name": "agent_2",
"displayName": "Agent 2",
"description": "A test description for a test agent ",
"agentType": "package"
},
{
"name": "agent_3",
"displayName": "Agent 3",
"description": "A test description for a test agent",
"agentType": "package"
}
]
}
```
**Unit Tests:**
- [X] I have added or updated unit tests for my change.
- [X] All unit tests pass locally.
3054 passed, 2383 warnings in 46.96s
### 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/3430 from dylan-apex:more-detailed-list-apps e6864fd61a673da5fd2fb28d2d7d72cb90f5af0a
PiperOrigin-RevId: 834907771
Merge https://github.com/google/adk-python/pull/3572
**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):**
N/A
**2. Or, if no issue exists, describe the change:**
**Problem:**
Docs fix
### Checklist
- [ ] I have read the [CONTRIBUTING.md](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) document.
- [ ] 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.
- [ ] 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.
Co-authored-by: Hangfei Lin <hangfei@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3572 from issacg:patch-1 b7c7ed46ff0fb018f4da1537535eff27c323daf5
PiperOrigin-RevId: 834864431
The `Parameter` class now provides default Python names based on the parameter location when the original name is empty. This prevents parameters from having an empty string as their Python name, especially for request bodies defined without a top-level name.
Close#2213
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 834850255
Make sure that the adk run --save_session writes session JSON using the Pydantic camelCase aliases (by_alias=True), matching ADK Web and keeping session files consistent
Close#3558
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 834847209
Merge https://github.com/google/adk-python/pull/3603
**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: #_issue_number_
- Related: #_issue_number_
**2. Or, if no issue exists, describe the change:**
_If applicable, please follow the issue templates to provide as much detail as
possible._
**Problem:**
_A clear and concise description of what the problem is._
**Solution:**
_A clear and concise description of what you want to happen and why you choose
this solution._
### Testing Plan
_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
- [ ] I have read the [CONTRIBUTING.md](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) document.
- [ ] 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.
- [ ] 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.
### Additional context
_Add any other context or screenshots about the feature request here._
Co-authored-by: Hangfei Lin <hangfei@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3603 from holtskinner:patch-1 833405898b747438e3f8a1b8c34095e25135fca3
PiperOrigin-RevId: 834805195
Retrying only on closed_resource error is not enough to be reliable for production environments due to the other network errors that may occur -- remote protocol error, read timeout, etc. We will update this to retry on all errors. Since it is only a one-time retry, it should not affect latency significantly. Fixes https://github.com/google/adk-python/issues/2561.
Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 834514264
It also enables the ADK triaging agent to run periodically on planned but not triaged issues.
Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 834489103
This change will help the tools user identify per agent job usage in BQ console and INFORMATION_SCHEMA views. This change fulfills the feature request #3582. Here is a demo after change: screen/C6YB4ge2FM2ZREi.
PiperOrigin-RevId: 834480140
When this agent was built before the agent name was changed in the build script and accepted like that from the VB so changed to set into that form
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 834479335
This change introduces `input_transcription` and `output_transcription` fields to session events, enabling the storage and retrieval of transcription data in both the database and Vertex AI session services.
Closes#3172
Co-authored-by: Hangfei Lin <hangfei@google.com>
PiperOrigin-RevId: 834366848
Fixes https://github.com/google/adk-python/issues/3174
The event compaction process, configured via `EventsCompactionConfig`, was
previously scheduled as a background task using `asyncio.create_task`.
Because Python's `asyncio.create_task` only holds a weak reference to
the created task and no strong reference was maintained by ADK, the
compaction task could be garbage-collected before it finished executing.
This resulted in event compaction failing silently or only partially
running, preventing session history from being summarized.
### Approaches Considered
Two approaches were considered to fix this:
1. **`asyncio.create_task` + Reference:** Create the task with `create_task` and store a strong reference to it (e.g., in a `set` on the [Runner](http://_vscodecontentref_/0) instance), removing it only when complete via `task.add_done_callback()`.
* **Pros:** The [run_async](http://_vscodecontentref_/1) async generator finishes immediately after yielding the last agent event.
* **Cons:** Adds complexity to the Runner state; background task failures are silent to the [run_async](http://_vscodecontentref_/2) caller; requires enhancement to `runner.close()` to correctly manage pending tasks on shutdown.
2. **`await`:** Directly `await` the compaction coroutine at the end of [run_async](http://_vscodecontentref_/3) after all agent events have been yielded.
* **Pros:** Simple to implement; ensures compaction runs to completion; failures during compaction propagate immediately to the [run_async](http://_vscodecontentref_/4) caller, making them visible and easier to debug.
* **Cons:** The `async for` loop iterating over [run_async](http://_vscodecontentref_/5) will not terminate until compaction finishes.
### Decision
This change implements the `await` approach. Although it means the `async for` loop takes longer to terminate when compaction occurs, it was chosen for its **simplicity and robustness**. Ensuring that compaction either succeeds or fails visibly is preferable to silent background failures.
All agent response events are yielded *before* compaction starts, so there is **no user-perceived delay in receiving the agent's answer** for the current turn.
### Integration Note for Users
Because compaction is now awaited, code consuming events via `async for event in runner.run_async(...)` will only finish iterating *after* compaction is complete (if compaction is triggered for that invocation).
If your application only needs the agent's response to proceed (e.g., displaying a message in a UI and allowing the user to reply), you can process events as they arrive and initiate the next turn without waiting for the `async for` loop to fully terminate. A new call to [run_async](http://_vscodecontentref_/6) for the next user query can be made immediately and will execute concurrently.
**Example:**
```python
async def handle_agent_turn(runner, message):
print("Agent is thinking...")
async for event in runner.run_async(user_id='...', session_id='...', new_message=message):
# Stream events to UI, log, etc.
if event.author == 'model' and event.content and event.content.parts[0].text:
print(f"Agent response: {event.content.parts[0].text}")
# The agent has provided a text response.
# The application can now enable user input for the next turn,
# even though this async for loop might not finish immediately
# if compaction is running.
print("Invocation complete (including compaction if any).")
# In your application:
# A new call to handle_agent_turn(runner, next_message) can be made
# as soon as the user provides the next input, without waiting for
# the previous call's generator to be exhausted.
Co-authored-by: Hangfei Lin <hangfei@google.com>
PiperOrigin-RevId: 833885375
this creates service_factory to handle .adk folder changes (including per-agent .adk defaults and in-memory/custom URI handling)
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 833875524
This change loads the agent or app from the specified directory before creating the session. This allows using the correct application name (from the `App` object if applicable) when initializing the session, rather than always defaulting to the folder name. The variable `root_agent` is also renamed to `agent_or_app` to better reflect that it can be either an Agent or an App
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 833839070
Currently logic to check for a disconnected session only checks for certain headers but doesn't detect all cases, leading to situations where it tries to connect to a session that is down. This adds logic so that we ping the server to check if it is disconnected. Fixes https://github.com/google/adk-python/issues/3321.
Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 833487825
Updates type annotations to use built-in types like `list` and `dict`, and uses `| None` for optional types, along with adding `from __future__ import annotations`
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 832522395
Currently logic to check for a disconnected session only checks for certain headers but doesn't detect all cases, leading to situations where it tries to connect to a session that is down. This adds logic so that we ping the server to check if it is disconnected. Fixes https://github.com/google/adk-python/issues/3321.
Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 832460068
This update enhances the BigQuery agent analytics plugin:
* **Schema Field Descriptions:** The recommended BigQuery table schema now includes descriptions for each field, improving data understandability.
* **Optimized Table Structure:** The plugin now creates the table with daily partitioning on `timestamp` and clustering on `event_type`, `agent`, and `user_id` by default.
* **Truncation Flag:** A new boolean field `is_truncated` is added to the schema to show if the `content` was truncated.
PiperOrigin-RevId: 832436799
In order to make evals more resilient to temporary model failures, we add retry options to llm_requests that are made during evals.
Note that this is a fall back option, if the developer has already specified their own retry options, then those will be honored.
Co-authored-by: Ankur Sharma <ankusharma@google.com>
PiperOrigin-RevId: 832383755
Two tools - detect_anomalies and analyze_contribution are modifying the settings passed to them, which is not right as the settings are held and passed by the top level, which means several tools share the same settings.
PiperOrigin-RevId: 832081738
This is ~27% of the current cold start latency after previous changes are submitted. This change refactors `google.adk.tools/__init__.py` to use `__getattr__` for lazy loading of all tools and related classes. Previously, all modules were imported directly upon `google.adk.tools` import, leading to potentially long initial import times. With lazy loading, modules are only imported when they are first accessed, improving the initial startup performance.
Co-authored-by: Liang Wu <wuliang@google.com>
PiperOrigin-RevId: 831537187
This change:
* Deprecates the `save_live_audio` configuration option in `RunConfig`, introducing `save_live_blob` as its replacement. A warning is issued if `save_live_audio` is used.
* Updates `base_llm_flow.py` to use the new `save_live_blob` flag.
* Ensures that audio events generated by `audio_cache_manager.py` are properly appended to the session service.
* Adds a utility script `pcm_audio_player.py` for playing raw PCM audio files.
Input sample event: 14a5859f-6b6c-46ed-9f28-e5008793b1c6|live_bidi_streaming_multi_agent|user|1e867c7f-dbe1-4268-a7bc-7a9fa5fbd16c|e-7a28a060-29bf-4483-bc5c-17248698a897|1762916981.5932|{"content":{"parts":[{"file_data":{"file_uri":"artifact://live_bidi_streaming_multi_agent/user/1e867c7f-dbe1-4268-a7bc-7a9fa5fbd16c/_adk_live/adk_live_audio_storage_input_audio_1762916981593.pcm#0","mime_type":"audio/pcm"}}],"role":"user"},"invocation_id":"e-7a28a060-29bf-4483-bc5c-17248698a897","author":"user","actions":{"state_delta":{},"artifact_delta":{},"requested_auth_configs":{},"requested_tool_confirmations":{}},"id":"14a5859f-6b6c-46ed-9f28-e5008793b1c6","timestamp":1762916981.5932002}
output sample event:
506c9df4-e143-4ebc-90a5-2f5b2eb26754|live_bidi_streaming_multi_agent|user|1e867c7f-dbe1-4268-a7bc-7a9fa5fbd16c|e-7a28a060-29bf-4483-bc5c-17248698a897|1762916986.10579|{"content":{"parts":[{"file_data":{"file_uri":"artifact://live_bidi_streaming_multi_agent/user/1e867c7f-dbe1-4268-a7bc-7a9fa5fbd16c/_adk_live/adk_live_audio_storage_output_audio_1762916986105.pcm;rate=24000#0","mime_type":"audio/pcm;rate=24000"}}],"role":"model"},"invocation_id":"e-7a28a060-29bf-4483-bc5c-17248698a897","author":"model","actions":{"state_delta":{},"artifact_delta":{},"requested_auth_configs":{},"requested_tool_confirmations":{}},"id":"506c9df4-e143-4ebc-90a5-2f5b2eb26754","timestamp":1762916986.105794}
Co-authored-by: Hangfei Lin <hangfei@google.com>
PiperOrigin-RevId: 831512074
pin crew ai to 3.13 at highest version as it uses chromadb and that uses onnxruntime which does not work yet with 3.14
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 831508884
The change adds an extension point for controlling which request metadata gets attached to A2A requests made by a RemoteAgent.
Instead of taking metadata from custom_metadata of session events users can construct payloads using a2a_request_meta_provider.
request_meta feature was added in v0.3.11 of the a2a-sdk library: https://github.com/a2aproject/a2a-python/releases/tag/v0.3.11
PiperOrigin-RevId: 831506364
This CL adds debug logs to show the history being sent to the live connection and the live connect config used.
Co-authored-by: Hangfei Lin <hangfei@google.com>
PiperOrigin-RevId: 831473597
This changes how content parts are converted for LiteLLM, treating all "text/" mime types as plain text and only "application/pdf" as a file
Close#1940
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 831418696
This is targeting the Client import mostly, but also prevents future latency increase if the other modules in genai adds more 3p dependencies. This change will make ADK only import `live`, `Client` and `_transformers` just-in-time, therefore cutting down cold start latency.
PiperOrigin-RevId: 831244349
This update improves the `BigQueryAgentAnalyticsPlugin` in several ways:
* Corrects the PyArrow schema generation to accurately reflect BigQuery field nullability based on the `mode` attribute.
* Introduces a configurable `shutdown_timeout` in `BigQueryLoggerConfig` to manage how long the plugin waits for pending logs to flush during shutdown.
* Adds more robust error handling within the `shutdown` method and background write tasks, particularly for event loop closure issues.
* Improves internal logging to provide better diagnostics.
* Ensures consistent use of safe content formatting.
PiperOrigin-RevId: 831225837
This change introduces a mechanism for users to register their own custom backend services for sessions, memory, and artifacts without modifying the ADK framework. This enhances the extensibility of ADK.
Two methods of registration are supported, both by placing a file in the parent directory of the agents.
**YAML Configuration (services.yaml or .yml)**
This is the recommended approach for simple services that can be instantiated with a constructor like MyService(uri="...", **kwargs).
Example services.yaml:
```
services:
- scheme: mysession
type: session
class: my_package.my_module.MyCustomSessionService
```
**Python Registration (services.py)**
For services requiring more complex initialization logic, users can define factory functions in a services.py file.
Example services.py
```
from google.adk.cli.service_registry import get_service_registry
from my_package.my_module import MyCustomSessionService
def my_session_factory(uri: str, **kwargs):
# custom initialization logic
return MyCustomSessionService(...)
get_service_registry().register_session_service("mysession", my_session_factory)
```
ADK will load services from services.yaml/.yml first, and then from services.py. If the same service scheme is defined in both, the registration in services.py will take precedence.
To use a registered service, specify its URI via the corresponding command-line flag, e.g., `--session_service_uri=mysession://....`
Co-authored-by: Shangjie Chen <deanchen@google.com>
PiperOrigin-RevId: 831211371
Creates AdkFolderManager for creating/resetting the .adk layout, helper builders that return SQLite- and filesystembacked services for each agent
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 831206377
Retrying only on closed_resource error is not enough to be reliable for production environments due to the other network errors that may occur -- remote protocol error, read timeout, etc. We will update this to retry on all errors. Since it is only a one-time retry, it should not affect latency significantly. Fixes https://github.com/google/adk-python/issues/2561.
PiperOrigin-RevId: 831153803
The `google.cloud.storage` module is now imported within the `__init__` method of `GCSArtifactService`, rather than at the top level. This avoids importing the potentially heavy `storage` module unless an instance of `GCSArtifactService` is actually created.
Co-authored-by: Liang Wu <wuliang@google.com>
PiperOrigin-RevId: 831124463
This is targeting the Client import mostly, but also prevents future latency increase if the other modules in genai adds more 3p dependencies. This change will make ADK only import `live`, `Client` and `_transformers` just-in-time, therefore cutting down cold start latency.
Co-authored-by: Liang Wu <wuliang@google.com>
PiperOrigin-RevId: 831124329
Retrying only on closed_resource error is not enough to be reliable for production environments due to the other network errors that may occur -- remote protocol error, read timeout, etc. We will update this to retry on all errors. Since it is only a one-time retry, it should not affect latency significantly. Fixes https://github.com/google/adk-python/issues/2561.
Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 831123085
This change updates `RemoteA2AAgent` to extract and forward custom metadata from session events to the `a2a-sdk`'s `send_message` method. The metadata is looked for under the key `A2A_METADATA_PREFIX + "metadata"` within the `custom_metadata` of the relevant session events. The `a2a-sdk` dependency is also updated to a version that supports this feature.
This feature was added in v0.3.11 of the a2a-sdk library: https://github.com/a2aproject/a2a-python/releases/tag/v0.3.11
PiperOrigin-RevId: 831120978
This change introduces a shutdown lifecycle hook for plugins. The `PluginManager` now has an `async def shutdown()` method that will call `await plugin.shutdown()` on any registered plugins that implement the method. This is called from `Runner.close()`, allowing plugins to perform cleanup tasks like flushing logs or closing connections when the runner instance is being closed. This improves the reliability of plugins that perform background operations.
PiperOrigin-RevId: 831037737
The agent's instructions are updated to guide it to guess a positive integer, starting from 50 and decreasing, using the `guess_number_tool` until the target is found. The maximum number of retries for the `CustomRetryPlugin` is increased from 6 to 10.
Co-authored-by: Hangfei Lin <hangfei@google.com>
PiperOrigin-RevId: 830984481
Merge https://github.com/google/adk-python/pull/2167, during which:
- Let the already added `max_query_result_rows` field cover for `max_downloaded_rows` field added in the PR
- Revert `max_rows` parameter added to execute_sql function, the tool config control should serve most practical use cases
- Keep the relevant tests for tool config
🤖 Generated with [Claude Code](https://claude.ai/code)
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/2167 from lupuletic:feature/configurable-max-downloaded-rows 23c56905c297d7aec2be4f1eb86ea23c8178bf21
PiperOrigin-RevId: 830701093
Enhanced `save_artifact` in `callback_context.py` to accept `custom_metadata` and added `get_artifact_version` to retrieve artifact details.
Introduced a new sample, `context_offloading_with_artifact`, demonstrating how to use ADK artifacts to offload large data from the LLM context. The sample includes:
- `QueryLargeDataTool`: Generates mock sales reports, saves them as artifacts with custom metadata, and injects the artifact content into the LLM request immediately after creation.
- `CustomLoadArtifactsTool`: Provides summaries of available artifacts to the LLM based on metadata and loads artifact content on demand when `load_artifacts` is called.
Co-authored-by: Hangfei Lin <hangfei@google.com>
PiperOrigin-RevId: 830592786
Merge https://github.com/google/adk-python/pull/2889
# Implement Full async DatabaseSessionService
**Target Issue:** #1005
## Overview
This PR introduces an asynchronous implementation of the `DatabaseSessionService` with minimal breaking changes. The primary goal is to enable effective use of ADK in fully async environments and API endpoints while avoiding event loop blocking during database I/O operations.
## Changes
- Converted `DatabaseSessionService` to use async/await patterns throughout
## Testing Plan
The implementation has been tested following the project's contribution guidelines:
### Unit Tests
- All existing unit tests pass successfully
- Minor update to test requirements added to support `aiosqlite`
### Manual End-to-End Testing
- E2E tests performed using:
- **LLM Provider:** LiteLLM
- **Database:** PostgreSQL with `asyncpg` driver
```python
from google.adk.sessions.database_session_service import DatabaseSessionService
connection_string: str = (
"postgresql+asyncpg://PG_USER:PG_PSWD@PG_HOST:5432/PG_DB"
)
session_service: DatabaseSessionService = DatabaseSessionService(
db_url=connection_string
)
session = await session_service.create_session(
app_name="test_app", session_id="test_session", user_id="test_user"
)
assert session is not None
sessions = await session_service.list_sessions(app_name="test_app", user_id="test_user")
assert len(sessions.sessions) > 0
session = await session_service.get_session(
app_name="test_app", session_id="test_session", user_id="test_user"
)
assert session is not None
await session_service.delete_session(
app_name="test_app", session_id="test_session", user_id="test_user"
)
assert (
await session_service.get_session(
app_name="test_app", session_id="test_session", user_id="test_user"
)
is None
)
```
The implementation have been also tested using the following configurations for llm provider and Runner:
```python
def get_azure_openai_model(deployment_id: str | None = None) -> LiteLlm:
...
if not deployment_id:
deployment_id = os.getenv("AZURE_OPENAI_DEPLOYMENT_ID")
logger.info(f"Using Azure OpenAI deployment ID: {deployment_id}")
return LiteLlm(
model=f"azure/{os.getenv('AZURE_OPENAI_DEPLOYMENT_ID')}",
stream=True,
)
...
@staticmethod
def _get_runner(agent: Agent) -> Runner:
storage=DatabaseSessionService(db_url=get_pg_connection_string())
return Runner(
agent=agent,
app_name=APP_NAME,
session_service=storage,
)
...
async for event in self.runner.run_async(
user_id=user_id,
session_id=session_id,
new_message=content,
run_config=(
RunConfig(
streaming_mode=StreamingMode.SSE, response_modalities=["TEXT"]
)
if stream
else RunConfig()
),
):
last_event = event
if stream:
yield event
...
```
## Breaking Changes
- Database connection string format may need updates for async drivers
Co-authored-by: Shangjie Chen <deanchen@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/2889 from GitMarco27:feature/async_database_session_service e1b1b14934c1fb7975a6832cdd1549e94acab985
PiperOrigin-RevId: 830525148
The tool description now clarifies that `load_artifacts` should be called when a user uploads files, to make those artifacts accessible within the session.
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 830469802
The upper bound for the `fastapi` dependency is adjusted from `<1.119.0` to `<0.119.0`.
Close#3422
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 830465681
Update `_function_declaration_to_tool_param` to use `getattr` when accessing the `required` field within `function_declaration.parameters`. This prevents `AttributeError` when a `FunctionDeclaration`'s parameters schema does not include a `required` attribute
Close#2891
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 830225582
Merge https://github.com/google/adk-python/pull/3352
Replace send() method with send_realtime_input() to fix DeprecationWarning
### Link to Issue or Description of Change
**1. Link to an existing issue (if applicable):**
- Closes: #2393
### Testing Plan
Have run unit test for test_live_request_queue.py
**Unit Tests:**
- [ ] I have added or updated unit tests for my change.
- [x] All unit tests pass locally.
Summary :
tests/unittests/agents/test_live_request_queue.py::test_send_realtime PASSED [100%]
**Manual End-to-End (E2E) Tests:**
### 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.
- [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.
Tested both API variants.
Co-authored-by: Hangfei Lin <hangfei@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3352 from SanjaySiddharth:fix-dep-session.send b23b641a63ff20d1f2dbd9abd519f8facf0aab77
PiperOrigin-RevId: 830182844
Merge https://github.com/google/adk-python/pull/2875
related: https://github.com/google/adk-python/issues/2876
## Reason for this change:
Currently, there is no direct way to access the user_id from within agent contexts, plugins, or callbacks. This limitation prevents several important use cases:
1. **User-specific logging and tracing**: When debugging or monitoring agent behavior, it's crucial to associate actions with specific users for better observability.
2. **User-scoped operations**: Plugins and callbacks often need to perform user-specific operations, such as accessing user-specific resources or applying user-level configurations.
3. **Session management**: The user_id is a key component of session identification, but it's not accessible through the ReadonlyContext interface, requiring workarounds to access it.
## Changes made:
- Added a `user_id` property to the `ReadonlyContext` class in `src/google/adk/agents/readonly_context.py`
- The property exposes the user_id from the underlying invocation context as a readonly field
## Impact:
This change will:
- Enable plugins and callbacks to access the current user's ID directly through the context
- Improve logging and tracing capabilities by allowing user-specific tracking
- Simplify code that needs to perform user-scoped operations without requiring access to internal implementation details
- Maintain backward compatibility as this is an additive change
### Before:
- No direct way to access user_id from ReadonlyContext
### After:
```python
@property
def user_id(self) -> str:
"""The id of the user. READONLY field."""
return self._invocation_context.user_id
```
This is a non-breaking change that adds a new readonly property to the existing ReadonlyContext interface.
Co-authored-by: Hangfei Lin <hangfei@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/2875 from ammmr:ammmr-add-user_id-property-to-readonly-context 771734ebf39cb0748a5dc826436236268fbb58f8
PiperOrigin-RevId: 830170908
The new Sqlite version has fixed schema and use a single column to store Event data, this should avoid DB migration for future add to the Event object.
- This change introduces `SqliteSessionService`, an asynchronous session service using `aiosqlite` that stores event data as JSON within SQLite.
- A migration script, `migrate_from_sqlalchemy_sqlite.py`, is included to transition data from the older SQLAlchemy-based SQLite schema to this new format.
- The CLI service registry is updated to use SqliteSessionService for sqlite:// URIs.
- Throw error when user trying to access a legacy DB and advice the user to do the migration.
Co-authored-by: Shangjie Chen <deanchen@google.com>
PiperOrigin-RevId: 829971174
NOTE:
- This is the expected behavior, so that SSE streaming and non-streaming behaviors are idential to each other in the persisted session.
- The underlying google_llm.py hasn't been fully comply with this behavior, which will be addressed in future changes.
Co-authored-by: Wei Sun (Jack) <weisun@google.com>
PiperOrigin-RevId: 829878175
This change updates the `BigQueryAgentAnalyticsPlugin` (formerly in `bigquery_logging_plugin.py`) to perform BigQuery writes asynchronously in background tasks, preventing blocking of the main agent execution flow. Initialization of BigQuery clients and table creation is also made asynchronous. The content logged in various callbacks has been streamlined and simplified. The plugin file has been renamed to `bigquery_agent_analytics_plugin.py` to match the class name.
PiperOrigin-RevId: 829603260
Merge https://github.com/google/adk-python/pull/2600
**Reason for this change:**
Currently, the detailed llm_request object is logged at the info level when connecting to the live API. This causes two main issues:
1. Excessive log output with large instructions: When instructions are large, the unstructured log output becomes problematic. Since the logs are not structured, any
newline characters in the instruction content cause each line to be output as a separate log entry, resulting in massive log output that floods the logging system.
2. Unnecessary verbosity in production: The detailed request information is primarily useful for debugging purposes and should not appear in standard info-level logs,
especially when connections are established frequently.
**Changes made:**
- Changed logger.info to logger.debug in src/google/adk/models/google_llm.py at line 294 for the live connection logging statement.
**Impact:**
This change will:
- Reduce log noise in production environments where info-level logging is enabled
- Keep the detailed connection information available when debug-level logging is needed for troubleshooting
- Improve log readability by showing only essential information at the info level
**Before:**
logger.info('Connecting to live with llm_request:%s', llm_request)
**After:**
logger.debug('Connecting to live with llm_request:%s', llm_request)
This is a non-breaking change that only affects logging verbosity.
Co-authored-by: Hangfei Lin <hangfei@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/2600 from ammmr:ammmr-info-to-debug-connect-log 36eab157f5d5ca00b44ee6ad8a4e1aeec871600c
PiperOrigin-RevId: 829596092
We need to set project and location parameters when we instantiate the Google GenAI library Client for VertexAi. This used to work before through environment variables but it doesn't seem to work anymore. So we are updating the `ApigeeLlm` wrapper to read from `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` environment variables and pass to the Client constructor.
PiperOrigin-RevId: 829569362
This trimmed schema includes only the fields relevant to agent shells, tool wiring, and common generation parameters, improving efficiency and focus.
The default model for the assistant has also been updated to "gemini-2.5-pro"
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 829513627
Merge https://github.com/google/adk-python/pull/3127
# What this PR does
This PR fixes a bug in the `execute_sql function` within `bigquery/query_tool.py`. The bug caused an error when executing queries that do not return a result set, such as a `CREATE TEMP FUNCTION` statement.
# The problem
Within `execute_sql,` when a user executed a query that doesn't produce a result set, like the following:
```sql
CREATE TEMP FUNCTION f() AS (0); SELECT f();
```
The corresponding BigQuery job object would have its `destination` property set to `None`. This caused an error because the code was written with the expectation of a valid destination table.
# The solution
The fix modifies `execute_sql` to check if the `query_job.destination` is None. If it is, the function correctly identifies the query as a statement that doesn't require a destination and allows it to complete successfully.
This ensures that `execute_sql` can robustly handle these types of queries.
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3127 from na0fu3y:patch-1 69218a8d25699dfa2e18bb305087f01192e91e91
PiperOrigin-RevId: 829270885
This change adds a debug log statement to output the function response IDs and the event list when a matching function call event is not found, which helps in debugging.
Co-authored-by: Hangfei Lin <hangfei@google.com>
PiperOrigin-RevId: 829059186
Capture the function call ID from events and use it to populate the `function_response.id` in subsequent user messages, enabling recording and replaying of test cases involving long-running tools.
Co-authored-by: Liang Wu <wuliang@google.com>
PiperOrigin-RevId: 829042356
Add `_to_litellm_response_format` to convert ADK's `response_schema` types (Pydantic models, JSON schema dicts) into the format needed by LiteLLM for JSON object/schema constraints
Close#1967
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 829037987
In `gemini_llm_connection.py`, accumulate partial transcription texts and emit `LlmResponse` with `partial=True` for each chunk. When the transcription is marked as `finished`, emit a final `LlmResponse` with the full accumulated text and `partial=False`.
In `runners.py`, modify `_should_append_to_history` to only add transcription events to the history when they are fully finished, preventing partial transcriptions from being added.
Co-authored-by: Hangfei Lin <hangfei@google.com>
PiperOrigin-RevId: 829029715
This is about 35% decrease. This change refactors several ADK modules to import `vertexai` and its submodules only when they are first used, rather than at the top of the file. This improves module load times by avoiding unnecessary imports of large dependencies. Imports are also placed within `if TYPE_CHECKING:` blocks where appropriate.
Co-authored-by: Liang Wu <wuliang@google.com>
PiperOrigin-RevId: 829017293
This accounts for about 8% of latency in cold start, because DatabaseSessionService imports from sqlalchemy. After the change, DatabaseSessionService is only imported if it's really needed by the program. The other objects in this file are not affected because they contribute to a small fraction of the latency.
Co-authored-by: Liang Wu <wuliang@google.com>
PiperOrigin-RevId: 829009868
Merge https://github.com/google/adk-python/pull/3324
**Problem:**
ADK seems to not pass output/input transcription `finished` flag from the Gemini.
**Solution:**
Relaxation of checking conditions of valid llm_response for input/output transcription.
### Testing Plan
Unit test `test_receive_transcript_finished` checks if input/output transcription message with no text but `finished` flag is received.
**Unit Tests:**
- [x] I have added or updated unit tests for my change.
- [x] All unit tests pass locally.
<img width="785" height="373" alt="image" src="https://github.com/user-attachments/assets/6d870e9f-1372-4808-91a9-38578c1b3729" />
**Manual End-to-End (E2E) Tests:**
Configure Gemini Agent to produce input & output transcriptions. Observe incoming transcript messages - to see if the finished flag appears at the end agents & users statement.
### 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
The mentioned `finished` flag can be obtained in native Gemini APIs like via Websocket but not via ADK.
Co-authored-by: Hangfei Lin <hangfei@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3324 from ChrisQlasty:fix/transcript_finish e7b8e5e5f5fac1d2dfd495f2dbadb19ed4328b0c
PiperOrigin-RevId: 828987996
SaveFilesAsArtifactsPlugin now resolves the canonical URI for each saved artifact. When the URI is model-accessible (`gs://`, `https://`, `http://`), we add a `Part(file_data=...)` so the LLM can fetch the filedirectly while still emitting the placeholder. If no model-accessible URI exists, we retain the original inline blob alongside the placeholder to preserve access to the uploaded bytes.
Close#2016
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 828786519
The `_run_compaction_default` method is no longer called and can be safely removed.
Co-authored-by: Hangfei Lin <hangfei@google.com>
PiperOrigin-RevId: 828760157
Merge https://github.com/google/adk-python/pull/3403
This PR corrects misspellings identified by the [check-spelling action](https://github.com/marketplace/actions/check-spelling)
Note: while I use tooling to identify errors, the tooling doesn't _actually_ provide the corrections, I'm picking them on my own. I'm a human, and I may make mistakes.
### Testing Plan
The misspellings have been reported at https://github.com/jsoref/adk-python/actions/runs/19056081305/attempts/1#summary-54426435973
The action reports that the changes in this PR would make it happy: https://github.com/jsoref/adk-python/actions/runs/19056081446/attempts/1#summary-54426436321
**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.
- [ ] 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.
### Additional context
- https://github.com/google/adk-python/pull/3382#issuecomment-3488654110
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3403 from jsoref:spelling-markdown 432b7ded3bddfe4a1d8127c50fd7a001f19bda83
PiperOrigin-RevId: 828754459
Merge https://github.com/google/adk-python/pull/2582
Relate to #3306
## Description
Fixes issues #6 and #1785 where ADK commands crash on Windows due to symlink creation requiring admin privileges.
## Problem
On Windows, running ADK commands (like `adk run`) fails with `OSError: [WinError 1314] A required privilege is not held by the client: ...` because the logging system attempts to create a symlink for the latest log file. Windows requires administrator privileges for symlink creation by default (unless Developer Mode is enabled), causing crashes for non-admin users.
## Root Cause
The issue was in [`logs.py`](https://github.com/google/adk-python/blob/main/src/google/adk/cli/utils/logs.py#L72) where `os.symlink()` was called unconditionally without error handling, causing the entire CLI to crash when symlink creation failed.
## Solution
This PR implements graceful symlink handling. Changes made:
- Extracted symlink creation into separate function with error handling
- Added graceful fallback when symlink creation fails
- Replaced crashes with warnings to keep CLI functional
- Improved user messaging about log file locations
This solution follows a similar pattern to the one used in [ROS2](https://github.com/ros2) in its [logging module](https://github.com/ros2/launch/blob/rolling/launch/launch/logging/__init__.py#L93).
## Testing
### Before (broken)
```bash
> adk run my_agent
Log setup complete: C:\Users\username\AppData\Local\Temp\agents_log\agent.20250817_215119.log
Traceback (most recent call last):
File "google\adk\cli\utils\logs.py", line 72, in log_to_tmp_folder
os.symlink(log_filepath, latest_log_link)
OSError: [WinError 1314] A required privilege is not held by the client
```
### After (fixed)
```bash
> adk run my_agent
Log setup complete: C:\Users\username\AppData\Local\Temp\agents_log\agent.20250817_215319.log
UserWarning: Cannot create symlink for latest log file: [WinError 1314] A required privilege is not held by the client
To access latest log: tail -F C:\Users\username\AppData\Local\Temp\agents_log\agent.20250817_215319.log
Running agent my_agent, type exit to exit.
```
Co-authored-by: Wei Sun (Jack) <weisun@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/2582 from lorenzofavaro:fix/windows-symlink-permissions 1e99a6287994f1bfd9ac11550d3dc06205998df5
PiperOrigin-RevId: 828690483
Merge https://github.com/google/adk-python/pull/3382
This PR corrects misspellings identified by the [check-spelling action](https://github.com/marketplace/actions/check-spelling)
Note: while I use tooling to identify errors, the tooling doesn't _actually_ provide the corrections, I'm picking them on my own. I'm a human, and I may make mistakes.
### Testing Plan
The misspellings have been reported at https://github.com/jsoref/adk-python/actions/runs/19056081305/attempts/1#summary-54426435973
The action reports that the changes in this PR would make it happy: https://github.com/jsoref/adk-python/actions/runs/19056081446/attempts/1#summary-54426436321
**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.
- [ ] 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.
### Additional context
- follow-up to #2447
Co-authored-by: Hangfei Lin <hangfei@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3382 from jsoref:spelling 3df5932e97391c437e1638d7163e5e3d5c52d5c3
PiperOrigin-RevId: 828686941
Merge https://github.com/google/adk-python/pull/3394
This PR corrects misspellings identified by the [check-spelling action](https://github.com/marketplace/actions/check-spelling)
Note: while I use tooling to identify errors, the tooling doesn't _actually_ provide the corrections, I'm picking them on my own. I'm a human, and I may make mistakes.
### Testing Plan
The misspellings have been reported at https://github.com/jsoref/adk-python/actions/runs/19056081305/attempts/1#summary-54426435973
The action reports that the changes in this PR would make it happy: https://github.com/jsoref/adk-python/actions/runs/19056081446/attempts/1#summary-54426436321
**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.
- [ ] 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.
### Additional context
- https://github.com/google/adk-python/pull/3382#issuecomment-3488654110
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3394 from jsoref:spelling-contributing c3d5e342c4350f7cae9f8f0c6638b176f2e30e80
PiperOrigin-RevId: 828659867
This commit refactors the `BigQueryAgentAnalyticsPlugin` to leverage the modern BigQuery Storage Write API, replacing the previous implementation that used the legacy `insert_rows_json` method (based on `tabledata.insertAll`).
**Key Changes:**
* **Switched to Storage Write API:** Event logs are now ingested using the `BigQueryWriteClient` from the `google-cloud-bigquery-storage` library.
* **Utilizes Default Stream:** We are using the `_default` stream for sending data, which is an efficient method for streaming in data without needing to manage stream lifecycles. This is ideal for continuous event logging.
* **Apache Arrow Format:** Log entries are converted to the Apache Arrow format using `pyarrow` before being sent. The BigQuery table schema is dynamically converted to an Arrow schema. This binary format is more efficient than JSON.
* **Updated Initialization:** The plugin now initializes both the standard `bigquery.Client` (for table management) and the `BigQueryWriteClient`.
* **Test Updates:** Unit tests in `test_bigquery_logging_plugin.py` have been comprehensively updated to mock the new `BigQueryWriteClient`, `bq_schema_utils`, and `pyarrow` components. Tests now verify calls to `append_rows` and the data structure passed to create the Arrow RecordBatch.
**Benefits of this change:**
* **Improved Performance:** The Storage Write API is designed for high-throughput streaming and offers better performance compared to the legacy API.
* **Reduced Cost:** Ingesting data via the Storage Write API is generally more cost-effective.
* **Enhanced Reliability:** The Storage Write API provides more robust streaming capabilities.
* **Modernization:** Aligns the plugin with the recommended best practices for BigQuery data ingestion.
This change enhances the efficiency and scalability of the BigQuery logging plugin.
PiperOrigin-RevId: 828655496
Merge https://github.com/google/adk-python/pull/3411
## Summary
Fixes AgentTool cleanup to prevent MCP session errors by calling `runner.close()` after sub-agent execution.
## Problem
When using AgentTool with MCP tools, the runner cleanup happened during garbage collection in a different async task context, causing:
```
RuntimeError: Attempted to exit cancel scope in a different task than it was entered in
```
## Solution
- Call `await runner.close()` immediately after sub-agent execution in AgentTool
- This ensures MCP sessions and other resources are cleaned up in the correct async task context
- Updated test mock to include the close() method
## Demo Agents
Added two comprehensive demo agents showing how to use AgentTool with MCP tools:
### mcp_in_agent_tool_remote (SSE mode)
- Uses HTTP/SSE connection to remote MCP server
- Zero-installation setup with `uvx`
- Demonstrates server-side MCP deployment pattern
### mcp_in_agent_tool_stdio (stdio mode)
- Uses subprocess connection with automatic server launch
- Fully automatic setup with `uvx` subdirectory syntax
- Demonstrates embedded MCP deployment pattern
Both demos:
- Use Gemini 2.5 Flash
- Include example prompts for JSON Schema exploration
- Have comprehensive READMEs with architecture diagrams
- Follow ADK agent structure conventions
## Testing
- ✅ All existing unit tests pass
- ✅ Manual testing with both SSE and stdio modes
- ✅ Verified cleanup happens in correct async context
- ✅ No more cancel scope errors with MCP tools
## Related
- Fixes#1112
- Related to #929
Co-authored-by: Wei Sun (Jack) <weisun@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3411 from google:fix/agent-tool-mcp-cleanup 9ae753b5a4
PiperOrigin-RevId: 828651896
Currently ADK web hangs and logs "AGSI callable returned without completing response" when the server is unreachable. To fix, set timeouts for connecting to server.
Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 828648928
- add FileArtifactService that persists artifacts to the local filesystem
- adjust BaseArtifactService and exports so callers can wire in the filebacked implementation
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 828629298
Replace the full JSON schema dump with a compact text summary of key AgentConfig components like LlmAgent, ToolConfig, and GenerateContentConfig
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 828627911
Merge https://github.com/google/adk-python/pull/3407
This PR corrects misspellings identified by the [check-spelling action](https://github.com/marketplace/actions/check-spelling)
Note: while I use tooling to identify errors, the tooling doesn't _actually_ provide the corrections, I'm picking them on my own. I'm a human, and I may make mistakes.
### Testing Plan
The misspellings have been reported at https://github.com/jsoref/adk-python/actions/runs/19056081305/attempts/1#summary-54426435973
The action reports that the changes in this PR would make it happy: https://github.com/jsoref/adk-python/actions/runs/19056081446/attempts/1#summary-54426436321
**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.
- [ ] 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.
### Additional context
- https://github.com/google/adk-python/pull/3382#issuecomment-3488654110
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3407 from jsoref:spelling-issue-template ce8febc6ab5368640c0ec2ae5d6a2c8ac5bf8ed6
PiperOrigin-RevId: 828610865
The blob content is often large and binary, which makes the logs unreadable and can cause excessive logging.
Co-authored-by: Hangfei Lin <hangfei@google.com>
PiperOrigin-RevId: 828523413
The sample agent now uses updated model names for Gemini Live, including a new Vertex model as the default and a new AI Studio model option.
Co-authored-by: Hangfei Lin <hangfei@google.com>
PiperOrigin-RevId: 828515811
2025-11-05 09:57:59 -08:00
417 changed files with 38905 additions and 9227 deletions
* The newly released Gemini [Interactions API](https://ai.google.dev/gemini-api/docs/interactions) is supported in ADK Now. To use it:
```Python
Agent(
model=Gemini(
model="gemini-3-pro-preview",
use_interactions_api=True,
),
name="...",
description="...",
instruction="...",
)
```
see [samples](https://github.com/google/adk-python/tree/main/contributing/samples/interactions_api) for details
* **[Services]**
* Add `add_session_to_memory` to `CallbackContext` and `ToolContext` to explicitly save the current session to memory ([7b356dd](https://github.com/google/adk-python/commit/7b356ddc1b1694d2c8a9eee538f3a41cf5518e42))
* **[Plugins]**
* Add location for table in agent events in plugin BigQueryAgentAnalytics ([507424a](https://github.com/google/adk-python/commit/507424acb9aabc697fc64ef2e9a57875f25f0a21))
* Upgrade BigQueryAgentAnalyticsPlugin to v2.0 with improved performance, multimodal support, and reliability ([7b2fe14](https://github.com/google/adk-python/commit/7b2fe14dab96440ee25b66dae9e66eadba629a56))
* **[A2A]**
* Adds ADK EventActions to A2A response ([32e87f6](https://github.com/google/adk-python/commit/32e87f6381ff8905a06a9a43a0207d758a74299d))
* **[Tools]**
* Add `header_provider` to `OpenAPIToolset` and `RestApiTool` ([e1a7593](https://github.com/google/adk-python/commit/e1a7593ae8455d51cdde46f5165410217400d3c9))
* Add SSL certificate verification configuration to OpenAPI tools using the `verify` parameter ([9d2388a](https://github.com/google/adk-python/commit/9d2388a46f7a481ea1ec522f33641a06c64394ed))
* Use json schema for function tool declaration when feature enabled ([cb3244b](https://github.com/google/adk-python/commit/cb3244bb58904ab508f77069b436f85b442d3299))
* **[Models]**
* Add Gemma3Ollama model integration and a sample ([e9182e5](https://github.com/google/adk-python/commit/e9182e5eb4a37fb5219fc607cd8f06d7e6982e83))
### Bug Fixes
* Install dependencies for py 3.10 ([9cccab4](https://github.com/google/adk-python/commit/9cccab453706138826f313c47118812133e099c4))
* Refactor LiteLLM response schema formatting for different models ([894d8c6](https://github.com/google/adk-python/commit/894d8c6c2652492324c428e8dae68a8646b17485))
* Resolve project and credentials before creating Spanner client ([99f893a](https://github.com/google/adk-python/commit/99f893ae282a04c67cce5f80e87d3bfadd3943e6))
* Avoid false positive "App name mismatch" warnings in Runner ([6388ba3](https://github.com/google/adk-python/commit/6388ba3b2054e60d218eae6ec8abc621ed0a1139))
* Update the code to work with either 1 event or more than 1 events ([4f54660](https://github.com/google/adk-python/commit/4f54660d6de54ddde0fec6e09fdd68890ce657ca))
* OpenAPI schema generation by skipping JSON schema for judge_model_config ([56775af](https://github.com/google/adk-python/commit/56775afc48ee54e9cbea441a6e0fa6c8a12891b9))
* Add tool_name_prefix support to OpenAPIToolset ([82e6623](https://github.com/google/adk-python/commit/82e6623fa97fb9cbc6893b44e228f4da098498da))
* Pass context to client interceptors ([143ad44](https://github.com/google/adk-python/commit/143ad44f8c5d1c56fc92dd691589aaa0b788e485))
* Yield event with error code when agent run raised A2AClientHTTPError ([b7ce5e1](https://github.com/google/adk-python/commit/b7ce5e17b6653074c5b41d08b2027b5e9970a671))
* Handle string function responses in LiteLLM conversion ([2b64715](https://github.com/google/adk-python/commit/2b6471550591ee7fc5f70f79e66a6e4080df442b))
* ApigeeLLM support for Built-in tools like GoogleSearch, BuiltInCodeExecutor when calling Gemini models through Apigee ([a9b853f](https://github.com/google/adk-python/commit/a9b853fe364d08703b37914a89cf02293b5c553b))
* Extract and propagate task_id in RemoteA2aAgent ([82bd4f3](https://github.com/google/adk-python/commit/82bd4f380bd8b4822191ea16e6140fe2613023ad))
* Update FastAPI and Starlette to fix CVE-2025-62727 (ReDoS vulnerability) ([c557b0a](https://github.com/google/adk-python/commit/c557b0a1f2aac9f0ef7f1e0f65e3884007407e30))
* Add client id to token exchange ([f273517](https://github.com/google/adk-python/commit/f2735177f195b8d7745dba6360688ddfebfed31a))
### Improvements
* Normalize multipart content for LiteLLM's ollama_chat provider ([055dfc7](https://github.com/google/adk-python/commit/055dfc79747aa365db8441908d4994f795e94a68))
* Update adk web, fixes image not rendering, state not updating, update drop down box width and trace icons ([df86847](https://github.com/google/adk-python/commit/df8684734bbfd5a8afe3b4362574fe93dcb43048))
* Add sample agent for interaction api integration ([68d7048](https://github.com/google/adk-python/commit/68d70488b9340251a9d37e8ae3a9166870f26aa1))
* Update genAI SDK version ([f0bdcab](https://github.com/google/adk-python/commit/f0bdcaba449f21bd8c27cde7dbedc03bf5ec5349))
* Introduce `build_function_declaration_with_json_schema` to use pydantic to generate json schema for FunctionTool ([51a638b](https://github.com/google/adk-python/commit/51a638b6b85943d4aaec4ee37c95a55386ebac90))
* Update component definition for triaging agent ([ee743bd](https://github.com/google/adk-python/commit/ee743bd19a8134129111fc4769ec24e40a611982))
* Migrate Google tools to use the new feature decorator ([bab5729](https://github.com/google/adk-python/commit/bab57296d553cb211106ece9ee2c226c64a60c57))
* Migrate computer to use the new feature decorator ([1ae944b](https://github.com/google/adk-python/commit/1ae944b39d9cf263e15b36c76480975fe4291d22))
* Add Spanner execute sql query result mode using list of dictionaries ([f22bac0](https://github.com/google/adk-python/commit/f22bac0b202cd8f273bf2dee9fff57be1b40730d))
* Improve error message for missing `invocation_id` and `new_message` in `run_async` ([de841a4](https://github.com/google/adk-python/commit/de841a4a0982d98ade4478f10481c817a923faa2))
* Add enum constraint to `agent_name` for `transfer_to_agent` ([4a42d0d](https://github.com/google/adk-python/commit/4a42d0d9d81b7aab98371427f70a7707dbfb8bc4))
* Add validation for unique sub-agent names ([#3557](https://github.com/google/adk-python/issues/3557)) ([2247a45](https://github.com/google/adk-python/commit/2247a45922afdf0a733239b619f45601d9b325ec))
* Support streaming function call arguments in progressive SSE streaming feature ([786aaed](https://github.com/google/adk-python/commit/786aaed335e1ce64b7e92dff2f4af8316b2ef593))
* **[Models]**
* Enable multi-provider support for Claude and LiteLLM ([d29261a](https://github.com/google/adk-python/commit/d29261a3dc9c5a603feef27ea657c4a03bb8a089))
* **[Tools]**
* Create APIRegistryToolset to add tools from Cloud API registry to agent ([ec4ccd7](https://github.com/google/adk-python/commit/ec4ccd718feeadeb6b2b59fcc0e9ff29a4fd0bac))
* Add an option to disallow propagating runner plugins to AgentTool runner ([777dba3](https://github.com/google/adk-python/commit/777dba3033a9a14667fb009ba017f648177be41d))
* **[Web]**
* Added an endpoint to list apps with details ([b57fe5f](https://github.com/google/adk-python/commit/b57fe5f4598925ec7592917bb32c7f0d6eca287a))
### Bug Fixes
* Allow image parts in user messages for Anthropic Claude ([5453b5b](https://github.com/google/adk-python/commit/5453b5bfdedc91d9d668c9eac39e3bb009a7bbbf))
* Mark the Content as non-empty if its first part contains text or inline_data or file_data or func call/response ([631b583](https://github.com/google/adk-python/commit/631b58336d36bfd93e190582be34069613d38559))
* Fixes double response processing issue in `base_llm_flow.py` where, in Bidi-streaming (live) mode, the multi-agent structure causes duplicated responses after tool calling. ([cf21ca3](https://github.com/google/adk-python/commit/cf21ca358478919207049695ba6b31dc6e0b2673))
* Fix out of bounds error in _run_async_impl ([8fc6128](https://github.com/google/adk-python/commit/8fc6128b62ba576480d196d4a2597564fd0a7006))
* Fix paths for public docs ([cd54f48](https://github.com/google/adk-python/commit/cd54f48fed0c87b54fb19743c9c75e790c5d9135))
* Ensure request bodies without explicit names are named 'body' ([084c2de](https://github.com/google/adk-python/commit/084c2de0dac84697906e2b4beebf008bbd9ae8e1)), closes [#2213](https://github.com/google/adk-python/issues/2213)
* Optimize Stale Agent with GraphQL and Search API to resolve 429 Quota errors ([cb19d07](https://github.com/google/adk-python/commit/cb19d0714c90cd578551753680f39d8d6076c79b))
* Update AgentTool to use Agent's description when input_schema is provided in FunctionDeclaration ([52674e7](https://github.com/google/adk-python/commit/52674e7fac6b7689f0e3871d41c4523e13471a7e))
* Update LiteLLM system instruction role from "developer" to "system" ([2e1f730](https://github.com/google/adk-python/commit/2e1f730c3bc0eb454b76d7f36b7b9f1da7304cfe)), closes [#3657](https://github.com/google/adk-python/issues/3657)
* Update session last update time when appending events ([a3e4ad3](https://github.com/google/adk-python/commit/a3e4ad3cd130714affcaa880f696aeb498cd93af)), closes [#2721](https://github.com/google/adk-python/issues/2721)
* Update the retry_on_closed_resource decorator to retry on all errors ([a3aa077](https://github.com/google/adk-python/commit/a3aa07722a7de3e08807e86fd10f28938f0b267d))
* Windows Path Handling and Normalize Cross-Platform Path Resolution in AgentLoader ([a1c09b7](https://github.com/google/adk-python/commit/a1c09b724bb37513eaabaff9643eeaa68014f14d))
### Documentation
* Add Code Wiki badge to README ([caf23ac](https://github.com/google/adk-python/commit/caf23ac49fe08bc7f625c61eed4635c26852c3ba))
* Add `id` and `custom_metadata` fields to `MemoryEntry` ([4dd28a3](https://github.com/google/adk-python/commit/4dd28a3970d0f76c571caf80b3e1bea1b79e9dde))
* Add a2a_request_meta_provider to RemoteAgent init ([d12468e](https://github.com/google/adk-python/commit/d12468ee5a2b906b6699ccdb94c6a5a4c2822465))
* Add feature decorator for the feature registry system ([871da73](https://github.com/google/adk-python/commit/871da731f1c09c6a62d51b137d9d2e7c9fb3897a))
* Breaking: Raise minimum Python version to 3_10 ([8402832](https://github.com/google/adk-python/commit/840283228ee77fb3dbd737cfe7eb8736d9be5ec8))
* Refactor and rename BigQuery agent analytics plugin ([6b14f88](https://github.com/google/adk-python/commit/6b14f887262722ccb85dcd6cef9c0e9b103cfa6e))
* Pass custom_metadata through forwarding artifact service ([c642f13](https://github.com/google/adk-python/commit/c642f13f216fb64bc93ac46c1c57702c8a2add8c))
* Update save_files_as_artifacts_plugin to never keep inline data ([857de04](https://github.com/google/adk-python/commit/857de04debdeba421075c2283c9bd8518d586624))
* **[Evals]**
* Add support for InOrder and AnyOrder match in ToolTrajectoryAvgScore Metric ([e2d3b2d](https://github.com/google/adk-python/commit/e2d3b2d862f7fc93807d16089307d4df25367a24))
* **[Integrations]**
* Enhance BQ Plugin Schema, Error Handling, and Logging ([5ac5129](https://github.com/google/adk-python/commit/5ac5129fb01913516d6f5348a825ca83d024d33a))
* Schema Enhancements with Descriptions, Partitioning, and Truncation Indicator ([7c993b0](https://github.com/google/adk-python/commit/7c993b01d1b9d582b4e2348f73c0591d47bf2f3a))
* **[Services]**
* Add file-backed artifact service ([99ca6aa](https://github.com/google/adk-python/commit/99ca6aa6e6b4027f37d091d9c93da6486def20d7))
* Add service factory for configurable session and artifact backends ([a12ae81](https://github.com/google/adk-python/commit/a12ae812d367d2d00ab246f85a73ed679dd3828a))
* Add SqliteSessionService and a migration script to migrate existing DB using DatabaseSessionService to SqliteSessionService ([e218254](https://github.com/google/adk-python/commit/e2182544952c0174d1a8307fbba319456dca748b))
* Add transcription fields to session events ([3ad30a5](https://github.com/google/adk-python/commit/3ad30a58f95b8729f369d00db799546069d7b23a))
* Full async implementation of DatabaseSessionService ([7495941](https://github.com/google/adk-python/commit/74959414d8ded733d584875a49fb4638a12d3ce5))
* **[Models]**
* Add experimental feature to use `parameters_json_schema` and `response_json_schema` for McpTool ([1dd97f5](https://github.com/google/adk-python/commit/1dd97f5b45226c25e4c51455c78ebf3ff56ab46a))
* Add support for parsing inline JSON tool calls in LiteLLM responses ([22eb7e5](https://github.com/google/adk-python/commit/22eb7e5b06c9e048da5bb34fe7ae9135d00acb4e))
* Expose artifact URLs to the model when available ([e3caf79](https://github.com/google/adk-python/commit/e3caf791395ce3cc0b10410a852be6e7b0d8d3b1))
* **[Tools]**
* Add BigQuery related label handling ([ffbab4c](https://github.com/google/adk-python/commit/ffbab4cf4ed6ceb313241c345751214d3c0e11ce))
* Allow setting max_billed_bytes in BigQuery tools config ([ffbb0b3](https://github.com/google/adk-python/commit/ffbb0b37e128de50ebf57d76cba8b743a8b970d5))
* Propagate `application_name` set for the BigQuery Tools as BigQuery job labels ([f13a11e](https://github.com/google/adk-python/commit/f13a11e1dc27c5aa46345154fbe0eecfe1690cbb))
* Set per-tool user agent in BQ calls and tool label in BQ jobs ([c0be1df](https://github.com/google/adk-python/commit/c0be1df0521cfd4b84585f404d4385b80d08ba59))
* **[Observability]**
* Migrate BigQuery logging to Storage Write API ([a2ce34a](https://github.com/google/adk-python/commit/a2ce34a0b9a8403f830ff637d0e2094e82dee8e7))
### Bug Fixes
* Add `jsonschema` dependency for Agent Builder config validation ([0fa7e46](https://github.com/google/adk-python/commit/0fa7e4619d589dc834f7508a18bc2a3b93ec7fd9))
* Add None check for `event` in `remote_a2a_agent.py` ([744f94f](https://github.com/google/adk-python/commit/744f94f0c8736087724205bbbad501640b365270))
* Add vertexai initialization for code being deployed to AgentEngine ([b8e4aed](https://github.com/google/adk-python/commit/b8e4aedfbf0eb55b34599ee24e163b41072a699c))
* Change LiteLLM content and tool parameter handling ([a19be12](https://github.com/google/adk-python/commit/a19be12c1f04bb62a8387da686499857c24b45c0))
* Change name for builder agent ([131d39c](https://github.com/google/adk-python/commit/131d39c3db1ae25e3911fa7f72afbe05e24a1c37))
* Ensure event compaction completes by awaiting task ([b5f5df9](https://github.com/google/adk-python/commit/b5f5df9fa8f616b855c186fcef45bade00653c77))
* Fix deploy to cloud run on Windows ([29fea7e](https://github.com/google/adk-python/commit/29fea7ec1fb27989f07c90494b2d6acbe76c03d8))
* Fix error handling when MCP server is unreachable ([ee8106b](https://github.com/google/adk-python/commit/ee8106be77f253e3687e72ae0e236687d254965c))
* Fix error when query job destination is None ([0ccc43c](https://github.com/google/adk-python/commit/0ccc43cf49dc0882dc896455d6603a602d8a28e7))
* Fix Improve logic for checking if a MCP session is disconnected ([a754c96](https://github.com/google/adk-python/commit/a754c96d3c4fd00f9c2cd924fc428b68cc5115fb))
* Fix McpToolset crashing with anyio.BrokenResourceError ([8e0648d](https://github.com/google/adk-python/commit/8e0648df23d0694afd3e245ec4a3c41aa935120a))
* Fix Safely handle `FunctionDeclaration` without a `required` attribute ([93aad61](https://github.com/google/adk-python/commit/93aad611983dc1daf415d3a73105db45bbdd1988))
* Fix status code in error message in RestApiTool ([9b75456](https://github.com/google/adk-python/commit/9b754564b3cc5a06ad0c6ae2cd2d83082f9f5943))
* Fix Use `async for` to loop through event iterator to get all events in vertex_ai_session_service ([9211f4c](https://github.com/google/adk-python/commit/9211f4ce8cc6d918df314d6a2ff13da2e0ef35fa))
* Fix: Fixes DeprecationWarning when using send method ([2882995](https://github.com/google/adk-python/commit/28829952890c39dbdb4463b2b67ff241d0e9ef6d))
* Improve logic for checking if a MCP session is disconnected ([a48a1a9](https://github.com/google/adk-python/commit/a48a1a9e889d4126e6f30b56c93718dfbacef624))
* Improve handling of partial and complete transcriptions in live calls ([1819ecb](https://github.com/google/adk-python/commit/1819ecb4b8c009d02581c2d060fae49cd7fdf653))
* Keep vertex session event after the session update time ([0ec0195](https://github.com/google/adk-python/commit/0ec01956e86df6ae8e6553c70e410f1f8238ba88))
* Let part converters also return multiple parts so they can support more usecases ([824ab07](https://github.com/google/adk-python/commit/824ab072124e037cc373c493f43de38f8b61b534))
* Load agent/app before creating session ([236f562](https://github.com/google/adk-python/commit/236f562cd275f84837be46f7dfb0065f85425169))
* Remove app name from FileArtifactService directory structure ([12db84f](https://github.com/google/adk-python/commit/12db84f5cd6d8b6e06142f6f6411f6b78ff3f177))
* Remove hardcoded `google-cloud-aiplatform` version in agent engine requirements ([e15e19d](https://github.com/google/adk-python/commit/e15e19da05ee1b763228467e83f6f73e0eced4b5))
* Stop updating write mode in the global settings during tool execution ([5adbf95](https://github.com/google/adk-python/commit/5adbf95a0ab0657dd7df5c4a6bac109d424d436e))
* Update description for `load_artifacts` tool ([c485889](https://github.com/google/adk-python/commit/c4858896ff085bedcfbc42b2010af8bd78febdd0))
### Improvements
* Add BigQuery related label handling ([ffbab4c](https://github.com/google/adk-python/commit/ffbab4cf4ed6ceb313241c345751214d3c0e11ce))
* Add demo for rewind ([8eb1bdb](https://github.com/google/adk-python/commit/8eb1bdbc58dc709006988f5b6eec5fda25bd0c89))
* Add debug logging for live connection ([5d5708b](https://github.com/google/adk-python/commit/5d5708b2ab26cb714556311c490b4d6f0a1f9666))
* Add debug logging for missing function call events ([f3d6fcf](https://github.com/google/adk-python/commit/f3d6fcf44411d07169c14ae12189543f44f96c27))
* Add default retry options as fall back to llm_request that are made during evals ([696852a](https://github.com/google/adk-python/commit/696852a28095a024cbe76413ee7617356e19a9e3))
* Add plugin for returning GenAI Parts from tools into the model request ([116b26c](https://github.com/google/adk-python/commit/116b26c33e166bf1a22964e2b67013907fbfcb80))
* Add support for abstract types in AFC ([2efc184](https://github.com/google/adk-python/commit/2efc184a46173529bdfc622db0d6f3866e7ee778))
* Add support for structured output schemas in LiteLLM models ([7ea4aed](https://github.com/google/adk-python/commit/7ea4aed35ba70ec5a38dc1b3b0a9808183c2bab1))
* Add tests for `max_query_result_rows` in BigQuery tool config ([fd33610](https://github.com/google/adk-python/commit/fd33610e967ad814bc02422f5d14dae046bee833))
* Add type hints in `cleanup_unused_files.py` ([2dea573](https://github.com/google/adk-python/commit/2dea5733b759a7a07d74f36a4d6da7b081afc732))
* Add util to build our llms.txt and llms-full.txt files
* Defer import of `google.cloud.storage` in `GCSArtifactService` ([999af55](https://github.com/google/adk-python/commit/999af5588005e7b29451bdbf9252265187ca992d))
* Defer import of `live`, `Client` and `_transformers` in `google.genai` ([22c6dbe](https://github.com/google/adk-python/commit/22c6dbe83cd1a8900d0ac6fd23d2092f095189fa))
* Enhance the messaging with possible fixes for RESOURCE_EXHAUSTED errors from Gemini ([b2c45f8](https://github.com/google/adk-python/commit/b2c45f8d910eb7bca4805c567279e65aff72b58a))
* Improve gepa tau-bench colab for external use ([e02f177](https://github.com/google/adk-python/commit/e02f177790d9772dd253c9102b80df1a9418aa7f))
* Lazy import DatabaseSessionService in the adk/sessions/ module ([5f05749](https://github.com/google/adk-python/commit/5f057498a274d3b3db0be0866f04d5225334f54a))
* Move adk_agent_builder_assistant to built_in_agents ([b2b7f2d](https://github.com/google/adk-python/commit/b2b7f2d6aa5b919a00a92abaf2543993746e939e))
* Plumb memory service from LocalEvalService to EvaluationGenerator ([dc3f60c](https://github.com/google/adk-python/commit/dc3f60cc939335da49399a69c0b4abc0e7f25ea4))
* Removes the unrealistic todo comment of visibility management ([e511eb1](https://github.com/google/adk-python/commit/e511eb1f70f2a3fccc9464ddaf54d0165db22feb))
* Returns agent state regardless if ctx.is_resumable ([d6b928b](https://github.com/google/adk-python/commit/d6b928bdf7cdbf8f1925d4c5227c7d580093348e))
* Stop logging the full content of LLM blobs ([0826755](https://github.com/google/adk-python/commit/082675546f501a70f4bc8969b9431a2e4808bd13))
* Update ADK web to match main branch ([14e3802](https://github.com/google/adk-python/commit/14e3802643a2d8ce436d030734fafd163080a1ad))
* Update agent instructions and retry limit in `plugin_reflect_tool_retry` sample ([01bac62](https://github.com/google/adk-python/commit/01bac62f0c14cce5d454a389b64a9f44a03a3673))
* Update conformance test CLI to handle long-running tool calls ([dd706bd](https://github.com/google/adk-python/commit/dd706bdc4563a2a815459482237190a63994cb6f))
* Update Gemini Live model names in live bidi streaming sample ([aa77834](https://github.com/google/adk-python/commit/aa77834e2ecd4b77dfb4e689ef37549b3ebd6134))
* Fix issue with MCP tools throwing an error ([1a4261a](https://github.com/google/adk-python/commit/1a4261ad4b66cdeb39d39110a086bd6112b17516))
* Remove redundant `format` field from LiteLLM content objects ([489c39d](https://github.com/google/adk-python/commit/489c39db01465e38ecbc2c7f32781c349b8cddc9))
* Update the contribution analysis tool to use original write mode ([54db3d4](https://github.com/google/adk-python/commit/54db3d4434e0706b83a589fa2499d11d439a6e4e))
* Update dependency version constraints to be based on PyPI versions([0b1784e](https://github.com/google/adk-python/commit/0b1784e0e493a0e2df1edfe37e5ed5f4247e7d9d))
### Improvements
@@ -97,13 +310,14 @@
* Add sample agent for VertexAiCodeExecutor ([edfe553](https://github.com/google/adk-python/commit/edfe5539421d196ca4da14d3a37fac7b598f8c8d))
* Adds a new sample agent that demonstrates how to integrate PostgreSQL databases using the Model Context Protocol (MCP) ([45a2168](https://github.com/google/adk-python/commit/45a2168e0e6773e595ecfb825d7e4ab0a38c3a38))
* Add example for using ADK with Fast MCP sampling ([d3796f9](https://github.com/google/adk-python/commit/d3796f9b33251d28d05e6701f11e80f02a2a49e1))
* Refactor gepa sample code and clean-up user demo colab([63353b2](https://github.com/google/adk-python/commit/63353b2b74e23e97385892415c5a3f2a59c3504f))
* Add a service registry to provide a generic way to register custom service implementations to be used in FastAPI server. See short instruction [here](https://github.com/google/adk-python/discussions/3175#discussioncomment-14745120). ([391628f](https://github.com/google/adk-python/commit/391628fcdc7b950c6835f64ae3ccab197163c990))
* Add a service registry to provide a generic way to register custom service implementations to be used in FastAPI server. See [short instruction](https://github.com/google/adk-python/discussions/3175#discussioncomment-14745120). ([391628f](https://github.com/google/adk-python/commit/391628fcdc7b950c6835f64ae3ccab197163c990))
* Add the ability to rewind a session to before a previous invocation ([9dce06f](https://github.com/google/adk-python/commit/9dce06f9b00259ec42241df4f6638955e783a9d1))
* Support resuming a parallel agent with multiple branches paused on tool confirmation requests ([9939e0b](https://github.com/google/adk-python/commit/9939e0b087094038b90d86c2fd35c26dd63f1157))
* Support content union as static instruction ([cc24d61](https://github.com/google/adk-python/commit/cc24d616f80c0eba2b09239b621cf3d176f144ea))
@@ -170,9 +384,8 @@
* Set default for `bypass_multi_tools_limit` to False for GoogleSearchTool and VertexAiSearchTool ([6da7274](https://github.com/google/adk-python/commit/6da727485898137948d72906d86d78b6db6331ac))
* Add more clear instruction to the doc updater agent about one PR for each recommended change ([b21d0a5](https://github.com/google/adk-python/commit/b21d0a50d610407be2f10b73a91274840ffdfe18))
* Add a guideline to avoid content deletion ([16b030b](https://github.com/google/adk-python/commit/16b030b2b25a9b0b489e47b4b148fc4d39aeffcb))
* Add an sample agent for the `ReflectAndRetryToolPlugin` ([9b8a4aa](https://github.com/google/adk-python/commit/9b8a4aad6fe65ef37885e5c3368d2799a2666534))
* Add a sample agent for the `ReflectAndRetryToolPlugin` ([9b8a4aa](https://github.com/google/adk-python/commit/9b8a4aad6fe65ef37885e5c3368d2799a2666534))
* Improve error message when adk web is run in wrong directory ([4a842c5](https://github.com/google/adk-python/commit/4a842c5a1334c3ee01406f796651299589fe12ab))
* Add an sample agent for the `ReflectAndRetryToolPlugin` ([9b8a4aa](https://github.com/google/adk-python/commit/9b8a4aad6fe65ef37885e5c3368d2799a2666534))
* Add span for context caching handling and new cache creation ([a2d9f13](https://github.com/google/adk-python/commit/a2d9f13fa1d31e00ba9493fba321ca151cdd9366))
* Disable the scheduled execution for issue triage workflow ([bae2102](https://github.com/google/adk-python/commit/bae21027d9bd7f811bed638ecce692262cb33fe5))
* Correct the callback signatures ([fa84bcb](https://github.com/google/adk-python/commit/fa84bcb5756773eadff486b99c9bd416b4faa9c6))
@@ -202,7 +415,7 @@
* Add `dry_run` functionality to BigQuery `execute_sql` tool ([960eda3](https://github.com/google/adk-python/commit/960eda3d1f2f46dc93a365eb3de03dc3483fe9bb))
* Support Oauth2 client credentials grant type ([5c6cdcd](https://github.com/google/adk-python/commit/5c6cdcd197a6780fc86d9183fa208f78c8a975d9))
* Support OAuth2 client credentials grant type ([5c6cdcd](https://github.com/google/adk-python/commit/5c6cdcd197a6780fc86d9183fa208f78c8a975d9))
* Add `ReflectRetryToolPlugin` to reflect from errors and retry with different arguments when tool errors ([e55b894](https://github.com/google/adk-python/commit/e55b8946d6a2e01aaf018d6a79d11d13c5286152))
* Support using `VertexAiSearchTool` built-in tool with other tools in the same agent ([4485379](https://github.com/google/adk-python/commit/4485379a049a5c84583a43c85d444ea1f1ba6f12))
* Support using google search built-in tool with other tools in the same agent ([d3148da](https://github.com/google/adk-python/commit/d3148dacc97f0a9a39b6d7a9640f7b7b0d6f9a6c))
@@ -283,7 +496,7 @@
* Add endpoint to generate memory from session ([2595824](https://github.com/google/adk-python/commit/25958242db890b4d2aac8612f7f7cfbb561727fa))
* **[Tools]**
* Add Google Maps Grounding Tool to ADK ([6b49391](https://github.com/google/adk-python/commit/6b493915469ecb42068e24818ab547b0856e4709))
* **MCP:** Initialize tool_name_prefix in MCPToolse ([86dea5b](https://github.com/google/adk-python/commit/86dea5b53ac305367283b7e353b60d0f4515be3b))
* **MCP:** Initialize tool_name_prefix in MCPToolset ([86dea5b](https://github.com/google/adk-python/commit/86dea5b53ac305367283b7e353b60d0f4515be3b))
* **[Evals]**
* Data model for storing App Details and data model for steps ([01923a9](https://github.com/google/adk-python/commit/01923a9227895906ca8ae32712d65b178e2cd7d5))
* Adds Rubric based final response evaluator ([5a485b0](https://github.com/google/adk-python/commit/5a485b01cd64cb49735e13ebd5e7fa3da02cd85f))
@@ -350,7 +563,7 @@
* Fix discussion answering github action workflow to escape the quote in the discussion content JSON [43c9681](https://github.com/google/adk-python/commit/43c96811da891a5b0c9cf1be525665e65f346a13)
* Send full MIME types for image/video/pdf in get_content [e45c3be](https://github.com/google/adk-python/commit/e45c3be23895b5ec68908ad9ee19bd622dcbd003)
* Fix flaky unit tests: tests/unittests/flows/llm_flows/test_functions_simple.py [b92b288](https://github.com/google/adk-python/commit/b92b288c978a9b3d1a76c8bcb96cc8f439ce610b)
* Make UT of a2a consistent about how tests should be skipped when python verison < 3.10 [98b0426](https://github.com/google/adk-python/commit/98b0426cd2dc5e28014ead22b22dbf50d42d0a9a)
* Make UT of a2a consistent about how tests should be skipped when python version < 3.10 [98b0426](https://github.com/google/adk-python/commit/98b0426cd2dc5e28014ead22b22dbf50d42d0a9a)
### Improvements
@@ -441,7 +654,7 @@ with Bigtable for building AI Agent applications(experimental feature) ([a953807
* Using base event's invocation id when merge multiple function response event ([279e4fe](https://github.com/google/adk-python/commit/279e4fedd0b1c0d1499c0f9a4454357af7da490e))
* Avoid crash when there is no candidates_token_count, which is Optional ([22f34e9](https://github.com/google/adk-python/commit/22f34e9d2c552fbcfa15a672ef6ff0c36fa32619))
* Fix the packaging version comparison logic in adk cli ([a2b7909](https://github.com/google/adk-python/commit/a2b7909fc36e7786a721f28e2bf75a1e86ad230d))
* Fixes SequentialAgent.config_type type hint ([8a9a271](https://github.com/google/adk-python/commit/8a9a271141678996c9b84b8c55d4b539d011391c))
* Fixes the host in the ansi bracket of adk web ([cd357bf](https://github.com/google/adk-python/commit/cd357bf5aeb01f1a6ae2a72349a73700ca9f1ed2))
* Add spanner tool name prefix ([a27927d](https://github.com/google/adk-python/commit/a27927dc8197c391c80acb8b2c23d610fba2f887))
@@ -453,7 +666,7 @@ with Bigtable for building AI Agent applications(experimental feature) ([a953807
* Update `openai` dependency version, based on correct OPENAI release ([bb8ebd1](https://github.com/google/adk-python/commit/bb8ebd15f90768b518cd0e21a59b269e30d6d944))
* Add the missing license header for core_callback_config init file ([f8fd6a4](https://github.com/google/adk-python/commit/f8fd6a4f09ab520b8ecdbd8f9fe48228dbff7ebe))
* Creates yaml_utils.py in utils to allow adk dump yaml in the same style ([1fd58cb](https://github.com/google/adk-python/commit/1fd58cb3633992cd88fa7e09ca6eda0f9b34236f))
* Return explict None type for DELETE endpoints ([f03f167](https://github.com/google/adk-python/commit/f03f1677790c0a9e59b6ba6f46010d0b7b64be50))
* Return explicit None type for DELETE endpoints ([f03f167](https://github.com/google/adk-python/commit/f03f1677790c0a9e59b6ba6f46010d0b7b64be50))
* Add _config suffix to all yaml-based agent examples ([43f302c](https://github.com/google/adk-python/commit/43f302ce1ab53077ee8f1486d5294540678921e6))
* Rename run related method and request to align with the conventions ([ecaa7b4](https://github.com/google/adk-python/commit/ecaa7b4c9847b478c7cdc37185b1525f733bb403))
* Update models in samples/ folder to be gemini 2.0+ ([6c217ba](https://github.com/google/adk-python/commit/6c217bad828edf62b41ec06b168f8a6cb7ece2ed))
@@ -478,7 +691,7 @@ with Bigtable for building AI Agent applications(experimental feature) ([a953807
### Bug Fixes
* A2A RPC URL got overriden by host and port param of adk api server ([52284b1](https://github.com/google/adk-python/commit/52284b1bae561e0d6c93c9d3240a09f210551b97))
* A2A RPC URL got overridden by host and port param of adk api server ([52284b1](https://github.com/google/adk-python/commit/52284b1bae561e0d6c93c9d3240a09f210551b97))
* Aclose all async generators to fix OTel tracing context ([a30c63c](https://github.com/google/adk-python/commit/a30c63c5933a770b960b08a6e2f8bf13eece8a22))
* Use PreciseTimestamp for create and update time in database session service to improve precision ([585141e](https://github.com/google/adk-python/commit/585141e0b7dda20abb024c7164073862c8eea7ae))
* Ignore AsyncGenerator return types in function declarations ([e2518dc](https://github.com/google/adk-python/commit/e2518dc371fe77d7b30328d8d6f5f864176edeac))
@@ -506,7 +719,7 @@ with Bigtable for building AI Agent applications(experimental feature) ([a953807
* Group FastAPI endpoints with tags ([c323de5](https://github.com/google/adk-python/commit/c323de5c692223e55372c3797e62d4752835774d))
* Allow implementations to skip defining a close method on Toolset ([944e39e](https://github.com/google/adk-python/commit/944e39ec2a7c9ad7f20c08fd66bf544de94a23d7))
* Add sample agent to test support of output_schema and tools at the same time for gemini model ([f2005a2](https://github.com/google/adk-python/commit/f2005a20267e1ee8581cb79c37aa55dc8e18c0ea))
* Add Github workflow config for uploading ADK docs to knowledge store ([5900273](https://github.com/google/adk-python/commit/59002734559d49a46940db9822b9c5f490220a8c))
* Add GitHub workflow config for uploading ADK docs to knowledge store ([5900273](https://github.com/google/adk-python/commit/59002734559d49a46940db9822b9c5f490220a8c))
* Update ADK Answering agent to reference doc site instead of adk-docs repo ([b5a8bad](https://github.com/google/adk-python/commit/b5a8bad170e271b475385dac440c7983ed207df8))
[](https://github.com/google/adk-python/actions/workflows/python-unit-tests.yml)
@@ -32,7 +33,7 @@ deployment-agnostic, and compatible with other frameworks.
## 🔥 What's new
- **Custom Service Registration**: Add a service registry to provide a generic way to register custom service implementations to be used in FastAPI server. See short instruction [here](https://github.com/google/adk-python/discussions/3175#discussioncomment-14745120). ([391628f](https://github.com/google/adk-python/commit/391628fcdc7b950c6835f64ae3ccab197163c990))
- **Custom Service Registration**: Add a service registry to provide a generic way to register custom service implementations to be used in FastAPI server. See [short instruction](https://github.com/google/adk-python/discussions/3175#discussioncomment-14745120). ([391628f](https://github.com/google/adk-python/commit/391628fcdc7b950c6835f64ae3ccab197163c990))
- **Rewind**: Add the ability to rewind a session to before a previous invocation ([9dce06f](https://github.com/google/adk-python/commit/9dce06f9b00259ec42241df4f6638955e783a9d1)).
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Xiang (Sean) Zhou
Liang Wu
George Weale
Yifan Wang
Google Team Member
Xuan Yang
Krishna vamsi Dhulipalla
hoonji
Kacper Jawoszek
davidkl97
Doug Reid
Lin-Nikaido
Łukasz Lipiński
Ankur Sharma
Bo Yang
Shangjie Chen
Rohit Yanamadala
Kathy Wu
Faraaz Ahmed
Hangfei Lin
Keyur Joshi
Eitan Yarmush
Ishan Raj Singh
happyryan
Virtuoso633
Bastien Jacot-Guillarmod
Om Kute
qieqieplus
Kristen Pereira
AlexeyChernenkoPlato
saroj rout
Adrian Altermatt
Giorgio Boa
Max Ind
Austin Wise
Dylan
Issac
Holt Skinner
Divyansh Shukla
Mimi Sun
Michael Jones
Wei Sun (Jack)
anrzeszutek
milkisbad
Yeesian Ng
Sara Robinson
Catalin Lupuleti
GitMarco27
Amy Wu
Jeff Bryner
Sanjay Siddharth MJ
GenkiNoguchi
Lê Nam Khánh
Henrique Cadioli
Naofumi Yamada
Josh Soref
Krzysztof Czuszynski
Kapil Sachdeva
ananyablonko
Lorenzo
Wei Sun (Jack)