Add synchronous Vertex AI Agent Engine query operator

[AlejandroMorgante]

Add RunReasoningEngineQueryOperator for direct synchronous Agent Engine invocations through the public ReasoningEngineExecutionService GAPIC. This complements RunQueryJobOperator when a Google Cloud Storage-backed asynchronous job is not needed.

The hook configures the regional endpoint and forwards retry, timeout, metadata, input, and class method options. The operator returns the complete JSON-serializable GAPIC response, without first fetching the runtime or creating a query job.

The new path is covered by hook and operator unit tests, provider documentation, and the existing Agent Engine system-test example.

related: #68479

Validation

• Targeted unit tests: 44 passed.
• Full Google provider suite: 4973 passed, 59 skipped.
• Provider mypy checks passed.
• Pre-commit and manual prek checks passed.
• Google provider documentation build and spellcheck passed.
• End-to-end GCP system test: 1 passed (details and reproduction steps below).
• AI-assisted Magpie self-review (pr-management-code-review, dry-run) at dfdd1a9: no blocking, major, minor, or nit findings. The public GAPIC surface was cross-checked against the minimum supported google-cloud-aiplatform==1.155.0. No GitHub review was posted.

The complete system test was also run end-to-end against a real GCP environment. It can be reproduced from the Airflow checkout with GCP credentials forwarded to Breeze, SYSTEM_TESTS_GCP_PROJECT configured in files/airflow-breeze-config/environment_variables.env, and a unique environment ID:

SYSTEM_TESTS_ENV_ID=<unique-id> \
BREEZE_INIT_COMMAND='export GOOGLE_CLOUD_PROJECT="${SYSTEM_TESTS_GCP_PROJECT}"' \
breeze testing system-tests \
  --forward-credentials \
  --test-timeout 2400 \
  providers/google/tests/system/google/cloud/vertex_ai/example_vertex_ai_agent_engine.py \
  -q

Latest result: 1 passed in 747.16s. The run exercised create, get, synchronous query, synchronous and deferrable query jobs, update, and delete flows, and completed resource teardown successfully.

The one-time GCP project setup required by the test remains documented in the system test module docstring.

---

Was generative AI tooling used to co-author this PR?

• Yes — Codex (GPT-5)

Generated-by: Codex (GPT-5) following the guidelines

[SameerMesiah97]

Just a few minor comments. Very clean overall.

[AlejandroMorgante]

@MaksYermak I applied the suggested renames-thanks for the feedback! My original intention was to follow the pattern we had been developing, with a synchronous Agent Engine query operator alongside the existing query-job operator, and keep their naming consistent. However, I agree that, from an Airflow user's perspective, matching the underlying client resource and method names makes the API easier to discover and understand.

[MaksYermak]

@AlejandroMorgante could you provide the screenshots of passing system tests for this new operator?

[AlejandroMorgante]

@MaksYermak

@AlejandroMorgante could you provide the screenshots of passing system tests for this new operator?

Hello! Here are the E2E test screenshots showing the synchronous Reasoning Engine query operator, the successful task run, and the response stored in XCom.

[MaksYermak]

@AlejandroMorgante LGTM