Merge https://github.com/google/adk-python/pull/3756
move event iteration inside api_client context in get_session
Move event iteration inside the api_client context manager in VertexAiSessionService.get_session() to prevent client closure during multi-page event fetching.
**Please ensure you have read the [contribution guide](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) before creating a pull request.**
### Link to Issue or Description of Change
**1. Link to an existing issue (if applicable):**
- Closes: #3757
**2. Or, if no issue exists, describe the change:**
**Problem:**
When a session contains more than 100 events (requiring pagination), `VertexAiSessionService.get_session()` fails with:
```
RuntimeError: Cannot send a request, as the client has been closed.
```
The root cause is that the `events_iterator` is consumed **outside** the `async with self._get_api_client() as api_client:` context block. When the iterator needs to fetch page 2, 3, etc., the API client has already been closed because the `async with` block has exited.
```python
# Current buggy flow:
async with self._get_api_client() as api_client:
get_session_response, events_iterator = await asyncio.gather(...)
# ← Client closed here
async for event in events_iterator: # ← Fails on page 2+ (client closed)
session.events.append(...)
```
**Solution:**
Move the session creation, user validation, and event iteration **inside** the `async with` block so the API client remains open during the entire pagination process:
```python
async with self._get_api_client() as api_client:
get_session_response, events_iterator = await asyncio.gather(...)
# Validation and session creation...
async for event in events_iterator: # ← Now works for all pages
session.events.append(...)
# Client closed after all events are fetched
```
### Testing Plan
**Unit Tests:**
- [x] I have added or updated unit tests for my change.
- [x] All unit tests pass locally.
```bash
pytest tests/unittests/sessions/test_vertex_ai_session_service.py -v
```
**Added regression test:** `test_get_session_pagination_keeps_client_open`
- Creates a `MockAsyncClientWithPagination` that tracks whether it's inside the `async with` context
- Raises `RuntimeError` if iteration happens outside the context (matching real httpx behavior)
- Simulates 3 pages of events (100 + 100 + 50 = 250 events)
- Verifies all 250 events are successfully retrieved
**Manual End-to-End (E2E) Tests:**
1. Deploy an ADK agent to Vertex AI Agent Engine
2. Create a session and send 100+ messages to accumulate >100 events
3. Verify `get_session()` successfully retrieves all events without error
**Before fix:**
```
RuntimeError: Cannot send a request, as the client has been closed.
```
**After fix:**
- Session with 201 events (3 pages) loads successfully
- All events are retrieved and appended to the session
### Checklist
- [x] I have read the [CONTRIBUTING.md](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) document.
- [x] I have performed a self-review of my own code.
- [x] I have commented my code, particularly in hard-to-understand areas.
- [x] I have added tests that prove my fix is effective or that my feature works.
- [x] New and existing unit tests pass locally with my changes.
- [x] I have manually tested my changes end-to-end.
- [x] Any dependent changes have been merged and published in downstream modules.
### Additional context
This bug affects any production deployment where users have extended conversations. Sessions accumulating >100 events (which triggers pagination) become completely unusable as the agent cannot load the session to process new messages.
The fix is minimal and maintains backward compatibility - it only changes the scope of the `async with` block without altering any logic or return values.
**Affected versions:** Tested on google-adk 1.19.0, but the bug exists in earlier versions as well.
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3756 from AlexisMarasigan:fix/vertex-ai-session-service-paginatio 01fbafa6524312f24f7c9feaffb07bff0ad49b77
PiperOrigin-RevId: 855451813
* **Async Safety:** Improved TraceManager context variable handling to ensure correct context isolation in concurrent asynchronous operations. This was achieved by using immutable tuples for the span stack and making copies of context dictionaries before modification.
* **Enhanced Logging:** The BigQueryAgentAnalyticsPlugin now captures richer metadata, including:
* Root agent name (via a new context variable).
* LLM model name and version.
* Usage metadata from LLM requests and responses.
* **Serialization Fix:** Updated BigQueryAgentAnalyticsPlugin to prevent JSON serialization errors when logging custom objects (e.g., Dataclasses). These are now automatically converted to dictionaries or string representations to ensure successful insertion into BigQuery.
PiperOrigin-RevId: 855415320
gcloud auth team requested that we audit ADK's codebase for places where ADC (google.auth.default) is used, and make sure that the quota project id header is being populated.
Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 855322964
When content capture is disabled, trace attributes for tool arguments, tool responses, LLM requests, LLM responses, and agent data are now set to the string '{}' instead of an empty dictionary
Close#4094
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 855304806
Merge https://github.com/google/adk-python/pull/3999
The AgentSkill in an A2A AgentCard expects examples to be a list of queries as strings. Therefore, agent examples, e.g., as provided by an ExampleTool, must be converted.
This change performs that extraction of just the inputs and converting them to a string to add to the AgentSkill.
### Testing Plan
**Unit Tests:**
- [x] I have added or updated unit tests for my change.
- [x] All unit tests pass locally.
**Manual End-to-End (E2E) Tests:**
Create an agent with ExampleTool and use agent card builder to create agent card for that agent. Fails without this change, succeeds with change included.
### 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.
Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3999 from timn:timn/fix-a2a-examples-from-tool 34c727c3311d2ec945efa3eec652d9e28b6ae2a9
PiperOrigin-RevId: 855288587
This change updates how `file_data.file_uri` parts are converted to LiteLLM content. For providers like OpenAI and Azure, only URIs resembling OpenAI file IDs ("file-...") are passed as file objects. Other URIs are converted to a text placeholder
Close#4038
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 855277306
The fix will use quotes to escape "key", which is column name in the metadata table. Should work for different database types.
Merge https://github.com/google/adk-python/pull/4106
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/4106 from DineshThumma9:fix/mysql-reserved-keyword-issue e39d0d02f3695d6890bc3267417b5dad58f7e8ee
PiperOrigin-RevId: 854411915
Introduces `full_history_when_stateless` to RemoteA2aAgent. When True, stateless agents will receive all session events on each request, instead of only events since their last reply. This allows stateless agents to have access to the complete conversation history.
PiperOrigin-RevId: 854400798
Merge https://github.com/google/adk-python/pull/3745
This change enables Agent Engine deployments to use App objects with event compaction and context caching configs while using the Agent Engine resource name for session operations, rather than App.name.
- Allow app_name parameter to override app.name when both are provided
- Still error when app and agent are both provided (prevents confusion)
- Updated tests to reflect new behavior and added test for override case
- Updateed documentation to clarify the new usage pattern
This fixes the issue where App.name (a simple identifier) conflicts with Agent Engine's requirement for resource names in session creation.
Related to issue #3715
**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: #3715
- Related: #3715
**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 deploying an agent to Agent Engine with event compaction and/or context caching enabled, users must wrap their agent in an `App` object to configure these features. However, when the `App` is passed to `AdkApp` and deployed, session creation fails because:
1. `App.name` is validated as a simple Python identifier (e.g., `"my_agent_name"`) via `validate_app_name()`
2. Agent Engine expects the app name to be either a full Reasoning Engine resource name (e.g., `"projects/123/locations/us-central1/reasoningEngines/456"`) or the reasoning engine ID
3. When an `App` object is passed to `AdkApp`, the deployment stores `App.name` (the simple identifier), but session creation later rejects it as invalid
This prevents users from deploying to Agent Engine with event compaction or context caching enabled.
**Solution:**
Allow the `app_name` parameter in `Runner.__init__()` to override `app.name` when both are provided. This enables Agent Engine (and other deployment scenarios) to:
- Pass the full `App` object to preserve event compaction and context caching configurations
- Override `app.name` with the Agent Engine resource name for session operations
- Successfully create sessions using the resource name while maintaining App-level features
The change is backward compatible: existing code that only provides `app` continues to use `app.name` as before. The override only applies when `app_name` is explicitly provided along with `app`.
### 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.
1. **Updated existing test** (`test_runner_init_raises_error_with_app_and_agent`):
- Changed from testing `app` + `app_name` + `agent` error to testing only `app` + `agent` error
- Verifies that `app` and `agent` cannot both be provided (prevents confusion)
2. **Added new test** (`test_runner_init_allows_app_name_override_with_app`):
- Verifies that `app_name` can override `app.name` when both are provided
- Confirms that `runner.app_name == "override_name"` while `runner.app` still references the original App object
- Ensures all App configs (agent, plugins, context_cache_config, etc.) are preserved
```
pytest tests/unittests/test_runners.py::TestRunnerWithPlugins::test_runner_init_raises_error_with_app_and_agent -v
pytest tests/unittests/test_runners.py::TestRunnerWithPlugins::test_runner_init_allows_app_name_override_with_app -v
```
tests/unittests/test_runners.py::TestRunnerWithPlugins::test_runner_init_allows_app_name_override_with_app PASSED [100%]
tests/unittests/test_runners.py::TestRunnerWithPlugins::test_runner_init_raises_error_with_app_and_agent PASSED [100%]
**Manual End-to-End (E2E) Tests:**
1. Create an agent with event compaction and context caching:
```python
from google.adk import Agent
from google.adk.apps import App
from google.adk.apps import EventsCompactionConfig
from google.adk.agents import ContextCacheConfig
root_agent = Agent(
name="my_agent",
model="gemini-2.5-flash",
instruction="You are a helpful assistant.",
)
app = App(
name="my_agent",
root_agent=root_agent,
events_compaction_config=EventsCompactionConfig(
compaction_interval=2,
overlap_size=1,
),
context_cache_config=ContextCacheConfig(),
)
```
2. Create a Runner with app and override app_name:
```python
from google.adk import Runner
from google.adk.sessions import InMemorySessionService
from google.adk.artifacts import InMemoryArtifactService
runner = Runner(
app=app,
app_name="projects/123/locations/us-central1/reasoningEngines/456", # Resource name
session_service=InMemorySessionService(),
artifact_service=InMemoryArtifactService(),
)
# Verify app_name override worked
assert runner.app_name == "projects/123/locations/us-central1/reasoningEngines/456"
assert runner.app == app # Original app object preserved
assert runner.context_cache_config is not None # Config preserved
assert runner.app.events_compaction_config is not None # Config preserved
```
3. Verify session creation uses the overridden name:
```python
session = await runner.session_service.create_session(
app_name=runner.app_name, # Uses resource name, not app.name
user_id="test_user",
)
```
**Expected Results:**
- Runner creation succeeds with both `app` and `app_name` provided
- `runner.app_name` equals the provided `app_name` (not `app.name`)
- All App configurations (event compaction, context caching) are preserved
- Session creation uses the overridden `app_name`
### 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
**Backward Compatibility:**
This change is fully backward compatible. All existing code patterns continue to work:
- `Runner(app=my_app)` → Still uses `app.name`
- `Runner(app_name="x", agent=my_agent)` → Still works
- `Runner(app=my_app, app_name=None)` → Still works (uses `app.name`)
**Impact on Agent Engine:**
This change enables Agent Engine deployments to support event compaction and context caching. Once this PR is merged, Agent Engine SDK should:
1. Accept `App` objects from `AdkApp(app=my_app, ...)`
2. Create `Runner` with both `app` and `app_name` (resource name):
```python
runner = Runner(
app=my_app, # Preserves event_compaction_config and context_cache_config
app_name=resource_name, # Overrides app.name for session operations
session_service=session_service,
...
)
```
3. Event compaction and context caching will work automatically once the App is passed correctly.
**Related Documentation:**
- Event compaction is documented in `src/google/adk/apps/compaction.py`
- Context caching is documented in `src/google/adk/agents/context_cache_config.py`
- The Runner's App support is documented in `src/google/adk/runners.py`
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3745 from sarojrout:feat/agent-engine-app-name-override 22d91d59df1460d25d06a71e155ad3dc20a69ca8
PiperOrigin-RevId: 854325898
When converting a `types.Content` to LiteLLM messages, if the content contains both `function_response` parts and other types of parts (e.g., text, image), the function now generates a list of LiteLLM messages
Close#4091
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 854240746
The SqliteSessionService now accepts database paths in the form of SQLite URLs (e.g., "sqlite:///./sessions.db", "sqlite+aiosqlite:////absolute.db")
Close#4077
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 853922433
API registry uses a nextPageToken for pagination, so we should loop through all the pages by sending the received nextPageToken to subsequent requests until no token is returned. The first page contains 1P MCP servers, and later pages contain 3P customer servers.
Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 853880449
Fix discovery engine search tool, bigquery agent analytics plugin, and application integration tool to correctly handle the ADC quota project override -- the x-goog-user-project should be set based on the ADC quota project, per gcloud auth team's requirements.
Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 853841124
- Treat Part(thought=True) as reasoning_content when building assistant messages.
- Add unit tests for thought-only and thought+text cases.
Close#4069
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 853790274
Default session and artifact services to in-memory when running in Cloud Run/Kubernetes (or when agents_dir isn’t writable) to prevent startup failures from attempting to create .adk under read-only/unwritable container paths (e.g. /app/agents/.adk). Local development defaults are unchanged.
- ADK_FORCE_LOCAL_STORAGE=1 to always use .adk defaults
- ADK_DISABLE_LOCAL_STORAGE=1 to always avoid local storage
If local artifact initialization raises PermissionError, fall back to in-memory and log a warning
Close#3907
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 853315459
