broken query method in LanggraphAgent class

[DmytroPaliichuk]

Environment details

• OS type and version: macOS 15.6.1 (24G90)
• Python version: Python 3.11.13
• pip freeze:
  annotated-types==0.7.0
  anyio==4.12.0
  blinker==1.9.0
  blockbuster==1.5.26
  bottleneck==1.6.0
  cachetools==6.2.4
  certifi==2025.11.12
  cffi==2.0.0
  charset-normalizer==3.4.4
  click==8.3.1
  cloudpickle==3.1.2
  cryptography==46.0.3
  distro==1.9.0
  docstring-parser==0.17.0
  filetype==1.2.0
  flask==3.1.2
  forbiddenfruit==0.1.4
  google-api-core==2.28.1
  google-auth==2.45.0
  google-cloud-aiplatform==1.132.0
  google-cloud-appengine-logging==1.7.0
  google-cloud-audit-log==0.4.0
  google-cloud-bigquery==3.39.0
  google-cloud-core==2.5.0
  google-cloud-logging==3.13.0
  google-cloud-resource-manager==1.15.0
  google-cloud-storage==3.7.0
  google-cloud-trace==1.17.0
  google-crc32c==1.8.0
  google-genai==1.56.0
  google-resumable-media==2.8.0
  googleapis-common-protos==1.72.0
  grpc-google-iam-v1==0.14.3
  grpcio==1.76.0
  grpcio-status==1.76.0
  grpcio-tools==1.75.1
  h11==0.16.0
  httpcore==1.0.9
  httpx==0.28.1
  httpx-sse==0.4.3
  idna==3.11
  importlib-metadata==8.7.1
  itsdangerous==2.2.0
  jinja2==3.1.6
  jsonpatch==1.33
  jsonpointer==3.0.0
  jsonschema-rs==0.29.1
  langchain-core==1.2.5
  langchain-google-genai==4.1.2
  langchain-google-vertexai==3.2.0
  langgraph==1.0.5
  langgraph-api==0.6.14
  langgraph-checkpoint==3.0.1
  langgraph-cli==0.4.11
  langgraph-prebuilt==1.0.5
  langgraph-runtime-inmem==0.20.1
  langgraph-sdk==0.3.1
  langsmith==0.5.1
  markupsafe==3.0.3
  numexpr==2.14.1
  numpy==2.4.0
  opentelemetry-api==1.38.0
  opentelemetry-exporter-gcp-logging==1.11.0a0
  opentelemetry-exporter-gcp-trace==1.11.0
  opentelemetry-exporter-otlp-proto-common==1.38.0
  opentelemetry-exporter-otlp-proto-http==1.38.0
  opentelemetry-proto==1.38.0
  opentelemetry-resourcedetector-gcp==1.11.0a0
  opentelemetry-sdk==1.38.0
  opentelemetry-semantic-conventions==0.59b0
  orjson==3.11.5
  ormsgpack==1.12.1
  packaging==25.0
  proto-plus==1.27.0
  protobuf==6.33.2
  pyarrow==22.0.0
  pyasn1==0.6.1
  pyasn1-modules==0.4.2
  pycparser==2.23
  pydantic==2.12.5
  pydantic-core==2.41.5
  pyjwt==2.10.1
  python-dateutil==2.9.0.post0
  python-dotenv==1.2.1
  pyyaml==6.0.3
  requests==2.32.5
  requests-toolbelt==1.0.0
  rsa==4.9.1
  setuptools==80.9.0
  shapely==2.1.2
  six==1.17.0
  sniffio==1.3.1
  sse-starlette==2.1.3
  starlette==0.50.0
  structlog==25.5.0
  tenacity==9.1.2
  truststore==0.10.4
  typing-extensions==4.15.0
  typing-inspection==0.4.2
  urllib3==2.6.2
  uuid-utils==0.12.0
  uvicorn==0.40.0
  validators==0.35.0
  watchfiles==1.1.1
  websockets==15.0.1
  werkzeug==3.1.4
  xxhash==3.6.0
  zipp==3.23.0
  zstandard==0.25.0

Steps to reproduce

1. Create LangGraph agent and deploy it
2. Get remote agent and try to query it

Code example

Deploy

from vertexai import agent_engines

agent = LanggraphAgent(
    model="gemini-2.0-flash-exp",
    model_kwargs={"temperature": 0.2},
    runnable_builder=runnable_builder,
)

remote_agent = agent_engines.create(
    agent_engine=agent,
    requirements=requirements,
    extra_packages=["./main.py"],
    display_name="Agent", 
    description="Agent"
)

Query remote agent

remote_agent = agent_engines.get(
    resource_name=f"projects/{PROJECT_ID}/locations/{LOCATION}/reasoningEngines/{REASONING_ENGINE_ID}"
)

response = remote_agent.query(
    input=query_str
    )

Stack trace

google.api_core.exceptions.FailedPrecondition: 400 Reasoning Engine Execution failed.
Please refer to our documentation (https://cloud.google.com/vertex-ai/generative-ai/docs/agent-engine/troubleshooting/use) for checking logs and other troubleshooting tips.
Error Details: {"detail":"Agent Engine Error: An error occurred during invocation. Exception: No module named 'langchain.load'

Thanks!