bug: test_verify in my_weather_tool fails due to incorrect input/output schema

Describe the bug

The test_verify test in resources_servers/my_weather_tool/tests/test_app.py fails with 51 Pydantic validation errors due to incorrect schema format for NeMoGymResponseCreateParamsNonStreaming and NeMoGymResponse objects. The input should use role and content keys, and the response output needs the NeMoGymResponseOutputMessage structure.

If it's designed to succeed, there's a bug in the tutorial. If the test is intentionally broken (tutorial teaches debugging), we should add documentation explaining: Why the test fails (incorrect schema format) and the corrected code.

Steps/Code to reproduce bug

Follow this tutorial to create resource server. Copy and paste the example code into app.py and test_app.py.

Expected behavior

Configs
ng_dump_config
policy_base_url: https://api.openai.com/v1
policy_api_key:
policy_model_name: gpt-4.1-2025-04-14
head_server:
host: 127.0.0.1
port: 11000
disallowed_ports:

• 11000
  head_server_deps:
• ray[default]==2.50.1
• openai==2.6.1
  python_version: 3.12.9

Environment details

• OS version: Ubuntu 22.04.5 LTS
• Python version: Python 3.12.9
• uv pip list output
  Package Version Editable project
  location

  ---

  ---

  accessible-pygments 0.0.5
  accumulation-tree 0.6.4
  aiofiles 24.1.0
  aiohappyeyeballs 2.6.1
  aiohttp 3.12.15
  aiohttp-cors 0.8.1
  aiosignal 1.4.0
  alabaster 1.0.0
  alembic 1.16.5
  annotated-types 0.7.0
  antlr4-python3-runtime 4.9.3
  anyio 4.10.0
  astroid 3.3.11
  asttokens 2.4.1
  attrs 25.3.0
  babel 2.17.0
  beautifulsoup4 4.13.5
  blinker 1.9.0
  brotli 1.1.0
  cachetools 5.5.2
  certifi 2025.8.3
  cffi 1.17.1
  cfgv 3.4.0
  charset-normalizer 3.4.3
  click 8.2.1
  cloudpickle 3.1.1
  colorama 0.4.6
  colorful 0.5.7
  contourpy 1.3.3
  coverage 7.10.5
  cryptography 45.0.7
  cycler 0.12.1
  databricks-sdk 0.65.0
  datasets 4.4.1
  devtools 0.12.2
  dill 0.4.0
  distlib 0.4.0
  distro 1.9.0
  docker 7.1.0
  docutils 0.21.2
  execnet 2.1.1
  executing 2.2.1
  fastapi 0.116.1
  ffmpy 0.6.1
  filelock 3.19.1
  flask 3.1.2
  fonttools 4.59.2
  frozenlist 1.7.0
  fsspec 2025.9.0
  gitdb 4.0.12
  gitpython 3.1.45
  google-api-core 2.27.0
  google-auth 2.40.3
  googleapis-common-protos 1.71.0
  gradio 5.44.1
  gradio-client 1.12.1
  graphene 3.4.3
  graphql-core 3.2.6
  graphql-relay 3.2.0
  greenlet 3.2.4
  groovy 0.1.2
  grpcio 1.76.0
  gunicorn 23.0.0
  h11 0.16.0
  hf-xet 1.1.9
  httpcore 1.0.9
  httpx 0.28.1
  huggingface-hub 0.34.4
  hydra-core 1.3.2
  identify 2.6.13
  idna 3.10
  imagesize 1.4.1
  importlib-metadata 8.7.0
  iniconfig 2.1.0
  itsdangerous 2.2.0
  jinja2 3.1.6
  jiter 0.10.0
  joblib 1.5.2
  jsonschema 4.25.1
  jsonschema-specifications 2025.9.1
  kiwisolver 1.4.9
  mako 1.3.10
  markdown-it-py 3.0.0
  markupsafe 3.0.2
  matplotlib 3.10.6
  mdit-py-plugins 0.5.0
  mdurl 0.1.2
  mlflow 3.3.2
  mlflow-skinny 3.3.2
  mlflow-tracing 3.3.2
  msgpack 1.1.2
  multidict 6.6.4
  multiprocess 0.70.18
  mypy 1.17.1
  mypy-extensions 1.1.0
  myst-parser 4.0.1
  nemo-gym 0.2.0rc0 /home/nvidia/Gym
  nodeenv 1.9.1
  numpy 2.3.2
  nvidia-sphinx-theme 0.0.8
  omegaconf 2.3.0
  openai 2.6.1
  opencensus 0.11.4
  opencensus-context 0.1.3
  opentelemetry-api 1.36.0
  opentelemetry-exporter-prometheus 0.57b0
  opentelemetry-proto 1.38.0
  opentelemetry-sdk 1.36.0
  opentelemetry-semantic-conventions 0.57b0
  orjson 3.11.3
  packaging 25.0
  pandas 2.3.2
  pathspec 0.12.1
  pillow 11.3.0
  platformdirs 4.4.0
  pluggy 1.6.0
  pre-commit 4.3.0
  prometheus-client 0.23.1
  propcache 0.3.2
  proto-plus 1.26.1
  protobuf 6.32.0
  psutil 7.1.3
  py-spy 0.4.1
  pyarrow 21.0.0
  pyasn1 0.6.1
  pyasn1-modules 0.4.2
  pycparser 2.22
  pydantic 2.11.7
  pydantic-core 2.33.2
  pydata-sphinx-theme 0.16.1
  pydub 0.25.1
  pygments 2.19.2
  pyparsing 3.2.3
  pytest 8.4.1
  pytest-asyncio 1.1.0
  pytest-cov 6.2.1
  pytest-xdist 3.8.0
  python-dateutil 2.9.0.post0
  python-multipart 0.0.20
  pytz 2025.2
  pyudorandom 1.0.0
  pyyaml 6.0.2
  ray 2.50.1
  referencing 0.37.0
  requests 2.32.5
  requests-mock 1.12.1
  rich 14.1.0
  roman-numerals-py 3.1.0
  rpds-py 0.27.1
  rsa 4.9.1
  ruff 0.12.11
  safehttpx 0.1.6
  scikit-learn 1.7.1
  scipy 1.16.1
  semantic-version 2.10.0
  shellingham 1.5.4
  six 1.17.0
  smart-open 7.4.1
  smmap 5.0.2
  sniffio 1.3.1
  snowballstemmer 3.0.1
  soupsieve 2.8
  sphinx 8.2.3
  sphinx-autobuild 2025.8.25
  sphinx-autodoc2 0.5.0
  sphinx-copybutton 0.5.2
  sphinx-design 0.6.1
  sphinx-reredirects 1.0.0
  sphinxcontrib-applehelp 2.0.0
  sphinxcontrib-devhelp 2.0.0
  sphinxcontrib-htmlhelp 2.1.0
  sphinxcontrib-jsmath 1.0.1
  sphinxcontrib-mermaid 1.0.0
  sphinxcontrib-qthelp 2.0.0
  sphinxcontrib-serializinghtml 2.0.0
  sqlalchemy 2.0.43
  sqlparse 0.5.3
  starlette 0.47.3
  swagger-plugin-for-sphinx 6.0.0
  tdigest 0.5.2.2
  threadpoolctl 3.6.0
  tomlkit 0.13.3
  tqdm 4.67.1
  typer 0.17.3
  typing-extensions 4.15.0
  typing-inspection 0.4.1
  tzdata 2025.2
  urllib3 2.5.0
  uvicorn 0.35.0
  uvloop 0.21.0
  virtualenv 20.34.0
  watchfiles 1.1.0
  websockets 15.0.1
  werkzeug 3.1.3
  wrapt 2.0.0
  xxhash 3.6.0
  yappi 1.6.10
  yarl 1.20.1
  zipp 3.23.0
  Additional context

Add any other context about the problem here.
Example: GPU model

Start with resources_servers/my_weather_tool/tests/test_app.py and the linked creating-resource-server tutorial, then run test_verify to inspect the reported validation errors. Compare the example inputs and outputs with the named NeMoGymResponse schemas; done means the tutorial example and test agree, or the tutorial clearly documents the intentional failure and corrected code.