Merge branch 'main' into test/tool-confirmation-coverage

Author: rohityan

.github/workflows/pr-triage.yml

@@ -15,26 +15,24 @@
 name: ADK Pull Request Triaging Agent
 
 on:
-  pull_request_target:
-    types: [opened, reopened, edited]
   schedule:
     # Run every 6 hours
     - cron: '0 */6 * * *'
   workflow_dispatch:
     inputs:
       pr_number:
-        description: 'The Pull Request number to triage'
-        required: true
+        description: 'The Pull Request number to triage (leave empty for batch mode)'
+        required: false
+        type: 'string'
+      pr_count:
+        description: 'Number of PRs to process in batch mode (default: 10)'
+        required: false
+        default: '10'
         type: 'string'
 
 jobs:
   agent-triage-pull-request:
-    if: >-
-      github.event_name == 'schedule' ||
-      github.event_name == 'workflow_dispatch' || (
-        github.event.pull_request.head.repo.full_name == github.repository &&
-        !contains(github.event.pull_request.labels.*.name, 'google-contributor')
-      )
+    if: github.repository == 'google/adk-python'
     runs-on: ubuntu-latest
     permissions:
       pull-requests: write
@@ -62,6 +60,7 @@ jobs:
           OWNER: 'google'
           REPO: 'adk-python'
           PULL_REQUEST_NUMBER: ${{ github.event.pull_request.number || github.event.inputs.pr_number || '' }}
+          PR_COUNT_TO_PROCESS: ${{ github.event.inputs.pr_count || '10' }}
           INTERACTIVE: ${{ vars.PR_TRIAGE_INTERACTIVE }}
           PYTHONPATH: contributing/samples/adk_team
         run: python -m adk_pr_triaging_agent.main

AGENTS.md

@@ -1,33 +1,3 @@
-# AI Coding Assistant Context
-
-This document provides context for AI coding assistants (Antigravity, Gemini CLI, etc.) to understand the ADK Python project and assist with development.
-
-## ADK Knowledge, Architecture, and Style
-
-For all matters regarding ADK development, please use the appropriate skill:
-
-- **`adk-architecture`**: Use this skill whenever you need to understand the architecture, event flow, or state management of the ADK system, or when designing or modifying core components and public APIs.
-  - Read `.agents/skills/adk-architecture/SKILL.md` for full instructions.
-- **`adk-style`**: Use this skill whenever writing code, tests, or reviewing PRs for the ADK project to ensure compliance with styling and coding conventions. Also use it for committing, bug fixing, and testing rules.
-  - Read `.agents/skills/adk-style/SKILL.md` for full instructions.
-- **`adk-git`**: Use this skill for any git operation (commit, push, pull, rebase, etc.). It provides guidelines for Conventional Commits and branch naming.
-  - Read `.agents/skills/adk-git/SKILL.md` for full instructions.
-- **`adk-sample-creator`**: Use this skill when creating new samples demonstrating features or agent patterns, or when adding examples to subdirectories under `contributing/`.
-  - Read `.agents/skills/adk-sample-creator/SKILL.md` for full instructions.
-- **`adk-review`**: Use this skill to review local changes for errors, style compliance, unintended outcomes, and to check if associated design docs, guides, samples, or tests need updates.
-  - Read `.agents/skills/adk-review/SKILL.md` for full instructions.
-- **`adk-issue`**: Use this skill when analyzing, triaging, and resolving GitHub issues for the adk-python repository (orchestrating both triage and fix implementation). Do NOT use this skill if the "/adk-issue-analyze" command is explicitly requested.
-  - Read `.agents/skills/adk-issue/SKILL.md` for full instructions.
-- **`adk-issue-analyze`**: Use this skill to fetch, inspect, and analyze a GitHub issue in a strictly read-only manner. Use this skill when the "/adk-issue-analyze" command is explicitly called.
-  - Read `.agents/skills/adk-issue-analyze/SKILL.md` for full instructions.
-- **`adk-issue-fix`**: Use this skill to implement the code changes, unit tests, and documentation updates for an approved GitHub issue fix. Use this skill when the "/adk-issue-fix" command is explicitly called.
-  - Read `.agents/skills/adk-issue-fix/SKILL.md` for full instructions.
-- **`adk-pr-analyze`**: Use this skill to fetch, inspect, and analyze a GitHub pull request in a strictly read-only manner. Use this skill when the "/adk-pr-analyze" command is explicitly called.
-  - Read `.agents/skills/adk-pr-analyze/SKILL.md` for full instructions.
-- **`adk-pr-triage`**: Use this skill to orchestrate triaging and reviewing GitHub pull requests (PRs) (orchestrating both analysis and user review/checkout). Do NOT use this skill if the "/adk-pr-analyze" command is explicitly requested.
-  - Read `.agents/skills/adk-pr-triage/SKILL.md` for full instructions.
-
-
 ## Project Overview
 
 The Agent Development Kit (ADK) is an open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents.
@@ -45,6 +15,10 @@ The Agent Development Kit (ADK) is an open-source, code-first Python toolkit for
 
 For details on how the Runner works and the invocation lifecycle, please refer to the `adk-architecture` skill and the referenced documentation therein.
 
+## ADK Knowledge, Architecture, and Style
+
+Skills related to ADK development are in `.agents/skills/`.
+
 ## Project Architecture
 
 For detailed architecture patterns, component descriptions, and core interfaces, please refer to the **`adk-architecture`** skill at `.agents/skills/adk-architecture/SKILL.md`.

contributing/samples/adk_team/adk_pr_triaging_agent/agent.py

@@ -236,7 +236,7 @@ def list_untriaged_pull_requests(pr_count: int) -> dict[str, Any]:
   query = f"repo:{OWNER}/{REPO} is:open is:pr"
   params = {
       "q": query,
-      "sort": "created",
+      "sort": "updated",
       "order": "desc",
       "per_page": 100,
       "page": 1,

contributing/samples/adk_team/adk_pr_triaging_agent/main.py

@@ -18,6 +18,7 @@
 
 from adk_pr_triaging_agent import agent
 from adk_pr_triaging_agent.settings import OWNER
+from adk_pr_triaging_agent.settings import PR_COUNT_TO_PROCESS
 from adk_pr_triaging_agent.settings import PULL_REQUEST_NUMBER
 from adk_pr_triaging_agent.settings import REPO
 from adk_pr_triaging_agent.utils import call_agent_async
@@ -44,10 +45,14 @@ async def main():
   if pr_number:
     prompt = f"Please triage pull request #{pr_number}!"
   else:
-    print("No pull request number received. Operating in batch mode.")
+    pr_count = parse_number_string(PR_COUNT_TO_PROCESS, default_value=10)
+    print(
+        "No pull request number received. Operating in batch mode (limit:"
+        f" {pr_count})."
+    )
     prompt = (
-        "Please use 'list_untriaged_pull_requests' to find 10 pull requests"
-        " that need triaging, then triage each one according to your"
+        f"Please use 'list_untriaged_pull_requests' to find {pr_count} pull"
+        " requests that need triaging, then triage each one according to your"
         " instructions."
     )
 

contributing/samples/adk_team/adk_pr_triaging_agent/settings.py

@@ -28,5 +28,6 @@
 OWNER = os.getenv("OWNER", "google")
 REPO = os.getenv("REPO", "adk-python")
 PULL_REQUEST_NUMBER = os.getenv("PULL_REQUEST_NUMBER")
+PR_COUNT_TO_PROCESS = os.getenv("PR_COUNT_TO_PROCESS", "10")
 
 IS_INTERACTIVE = os.environ.get("INTERACTIVE", "1").lower() in ["true", "1"]

src/google/adk/cli/cli_tools_click.py

@@ -2000,7 +2000,6 @@ def cli_api_server(
     "cloud_run",
     context_settings={
         "allow_extra_args": True,
-        "allow_interspersed_args": False,
     },
 )
 @click.option(
@@ -2177,34 +2176,7 @@ def cli_deploy_cloud_run(
 
   _warn_if_with_ui(with_ui)
 
-  # Parse arguments to separate gcloud args (after --) from regular args
-  gcloud_args = []
-  if "--" in ctx.args:
-    separator_index = ctx.args.index("--")
-    gcloud_args = ctx.args[separator_index + 1 :]
-    regular_args = ctx.args[:separator_index]
-
-    # If there are regular args before --, that's an error
-    if regular_args:
-      click.secho(
-          "Error: Unexpected arguments after agent path and before '--':"
-          f" {' '.join(regular_args)}. \nOnly arguments after '--' are passed"
-          " to gcloud.",
-          fg="red",
-          err=True,
-      )
-      ctx.exit(2)
-  else:
-    # No -- separator, treat all args as an error to enforce the new behavior
-    if ctx.args:
-      click.secho(
-          f"Error: Unexpected arguments: {' '.join(ctx.args)}. \nUse '--' to"
-          " separate gcloud arguments, e.g.: adk deploy cloud_run [options]"
-          " agent_path -- --min-instances=2",
-          fg="red",
-          err=True,
-      )
-      ctx.exit(2)
+  gcloud_args = ctx.args
 
   try:
     from . import cli_deploy

src/google/adk/cli/utils/local_storage.py

@@ -236,6 +236,21 @@ async def append_event(self, session: Session, event: Event) -> Event:
     service = await self._get_service(session.app_name)
     return await service.append_event(session, event)
 
+  async def close(self) -> None:
+    """Closes all underlying session services."""
+    for service in self._services.values():
+      if hasattr(service, "close"):
+        await service.close()
+    self._services.clear()
+
+  async def __aenter__(self) -> PerAgentDatabaseSessionService:
+    """Enters the async context manager."""
+    return self
+
+  async def __aexit__(self, exc_type, exc_val, exc_tb) -> None:
+    """Exits the async context manager and closes the service."""
+    await self.close()
+
 
 class PerAgentFileArtifactService(BaseArtifactService):
   """Routes artifact storage to per-agent `.adk/artifacts` folders."""

src/google/adk/integrations/parameter_manager/parameter_client.py

@@ -26,9 +26,17 @@
 from google.oauth2 import service_account
 
 from ... import version
+from ...utils import mtls_utils
 
 USER_AGENT = f"google-adk/{version.__version__}"
 
+_DEFAULT_REGIONAL_ENDPOINT_TEMPLATE = (
+    "parametermanager.{location}.rep.googleapis.com"
+)
+_DEFAULT_MTLS_REGIONAL_ENDPOINT_TEMPLATE = (
+    "parametermanager.{location}.rep.mtls.googleapis.com"
+)
+
 
 class ParameterManagerClient:
   """A client for interacting with Google Cloud Parameter Manager.
@@ -113,7 +121,11 @@ def __init__(
     client_options = None
     if location:
       client_options = {
-          "api_endpoint": f"parametermanager.{location}.rep.googleapis.com"
+          "api_endpoint": mtls_utils.get_api_endpoint(
+              location,
+              _DEFAULT_REGIONAL_ENDPOINT_TEMPLATE,
+              _DEFAULT_MTLS_REGIONAL_ENDPOINT_TEMPLATE,
+          )
       }
 
     self._client = parametermanager_v1.ParameterManagerClient(

src/google/adk/models/interactions_utils.py

@@ -1166,6 +1166,53 @@ def _get_latest_user_contents(
   return latest_user_contents
 
 
+async def _create_interactions(
+    api_client: Client,
+    *,
+    create_kwargs: dict[str, Any],
+    stream: bool,
+) -> AsyncGenerator[LlmResponse, None]:
+  """Issue ``interactions.create`` and convert the response(s) to LlmResponses.
+
+  This is the shared transport + conversion loop. The caller assembles
+  ``create_kwargs`` (``model`` or ``agent``, ``input``, ``tools``, etc.); this
+  helper owns issuing the call and mapping the stream to ``LlmResponse``s.
+
+  Args:
+    api_client: The Google GenAI client.
+    create_kwargs: Keyword arguments passed verbatim to
+      ``api_client.aio.interactions.create`` (excluding ``stream``).
+    stream: Whether to stream the response.
+
+  Yields:
+    LlmResponse objects converted from interaction responses.
+  """
+  current_interaction_id: str | None = None
+
+  if stream:
+    responses = await api_client.aio.interactions.create(
+        **create_kwargs, stream=True
+    )
+    aggregated_parts: list[types.Part] = []
+    async for event in responses:
+      logger.debug(build_interactions_event_log(event))
+      interaction_id = _extract_stream_interaction_id(event)
+      if interaction_id:
+        current_interaction_id = interaction_id
+      llm_response = convert_interaction_event_to_llm_response(
+          event, aggregated_parts, current_interaction_id
+      )
+      if llm_response:
+        yield llm_response
+  else:
+    interaction = await api_client.aio.interactions.create(
+        **create_kwargs, stream=False
+    )
+    logger.info('Interaction response received.')
+    logger.debug(build_interactions_response_log(interaction))
+    yield convert_interaction_to_llm_response(interaction)
+
+
 async def generate_content_via_interactions(
     api_client: Client,
     llm_request: LlmRequest,
@@ -1227,49 +1274,18 @@ async def generate_content_via_interactions(
       )
   )
 
-  # Track the current interaction ID from responses
-  current_interaction_id: str | None = None
-
-  if stream:
-    # Streaming mode
-    responses = await api_client.aio.interactions.create(
-        model=llm_request.model,
-        input=input_steps,
-        stream=True,
-        system_instruction=system_instruction,
-        tools=interaction_tools if interaction_tools else None,
-        generation_config=generation_config if generation_config else None,
-        previous_interaction_id=previous_interaction_id,
-    )
-
-    aggregated_parts: list[types.Part] = []
-    async for event in responses:
-      # Log the streaming event
-      logger.debug(build_interactions_event_log(event))
-
-      interaction_id = _extract_stream_interaction_id(event)
-      if interaction_id:
-        current_interaction_id = interaction_id
-      llm_response = convert_interaction_event_to_llm_response(
-          event, aggregated_parts, current_interaction_id
-      )
-      if llm_response:
-        yield llm_response
-
-  else:
-    # Non-streaming mode
-    interaction = await api_client.aio.interactions.create(
-        model=llm_request.model,
-        input=input_steps,
-        stream=False,
-        system_instruction=system_instruction,
-        tools=interaction_tools if interaction_tools else None,
-        generation_config=generation_config if generation_config else None,
-        previous_interaction_id=previous_interaction_id,
-    )
-
-    # Log the response
-    logger.info('Interaction response received from the model.')
-    logger.debug(build_interactions_response_log(interaction))
-
-    yield convert_interaction_to_llm_response(interaction)
+  # Assemble the create() kwargs for the model path and delegate the
+  # transport + conversion loop to the shared helper.
+  create_kwargs: dict[str, Any] = {
+      'model': llm_request.model,
+      'input': input_steps,
+      'system_instruction': system_instruction,
+      'tools': interaction_tools if interaction_tools else None,
+      'generation_config': generation_config if generation_config else None,
+      'previous_interaction_id': previous_interaction_id,
+  }
+
+  async for llm_response in _create_interactions(
+      api_client, create_kwargs=create_kwargs, stream=stream
+  ):
+    yield llm_response

src/google/adk/sessions/database_session_service.py

@@ -79,6 +79,18 @@
 _MARIADB_DIALECT = "mariadb"
 _MYSQL_DIALECT = "mysql"
 _POSTGRESQL_DIALECT = "postgresql"
+# Dialects whose DATETIME/TIMESTAMP columns do not retain timezone info, so
+# timezone-aware datetimes must have their tzinfo stripped before storage. This
+# keeps the value written by create_session consistent with the value read back
+# from storage; otherwise the stale-writer marker comparison in append_event
+# raises a false positive on the first append after create_session. Cloud
+# Spanner is intentionally excluded because its TIMESTAMP is timezone-aware.
+_NAIVE_DATETIME_DIALECTS = (
+    _SQLITE_DIALECT,
+    _POSTGRESQL_DIALECT,
+    _MYSQL_DIALECT,
+    _MARIADB_DIALECT,
+)
 # Tuple key order for in-process per-session lock maps:
 # (app_name, user_id, session_id).
 _SessionLockKey: TypeAlias = tuple[str, str, str]
@@ -348,6 +360,14 @@ def _supports_row_level_locking(self) -> bool:
         _POSTGRESQL_DIALECT,
     )
 
+  def _uses_naive_datetime(self) -> bool:
+    """Returns whether the active dialect stores datetimes without timezone info.
+
+    These dialects persist timezone-naive DATETIME/TIMESTAMP values, so
+    timezone-aware datetimes must have their tzinfo stripped before storage.
+    """
+    return self.db_engine.dialect.name in _NAIVE_DATETIME_DIALECTS
+
   @asynccontextmanager
   async def _with_session_lock(
       self, *, app_name: str, user_id: str, session_id: str
@@ -531,8 +551,7 @@ async def create_session(
       now = datetime.fromtimestamp(platform_time.get_time(), tz=timezone.utc)
       is_sqlite = self.db_engine.dialect.name == _SQLITE_DIALECT
       is_postgresql = self.db_engine.dialect.name == _POSTGRESQL_DIALECT
-      is_mysql = self.db_engine.dialect.name == _MYSQL_DIALECT
-      if is_sqlite or is_postgresql or is_mysql:
+      if self._uses_naive_datetime():
         now = now.replace(tzinfo=None)
 
       storage_session = schema.StorageSession(