feat(llm-obs): added report evaluator integration from pydantic (#17032)

## Description
Add integration for pydantic ai report evaluators that return scalars (i.e. return a `ScalarResult` object) to be submitted as summary evaluators in experiments sdks
<!-- Provide an overview of the change and motivation for the change -->

## Testing
Pydantic summary report evaluators are working in experiments. I used this [test script](https://github.com/DataDog/llm-obs/pull/245/changes#diff-ab2adacd550f0dd442d7bcdbf2a73ed6bb5064ad6f5ad5ddbe7a19ec45875df8) which generated [this experiment](https://dd.datad0g.com/llm/experiments/0a70a7d8-215b-44a5-9b12-cbd045d99d6b?project=jenn-test-pydantic-evaluators).

Added unit tests as well confirming that both sync and async pydantic summary evaluators are working and that unsupported types (i.e. non ScalarReport types) fail as expected.
<!-- Describe your testing strategy or note what tests are included -->

## Risks

<!-- Note any risks associated with this change, or "None" if no risks -->
None

## Additional Notes

<!-- Any other information that would be helpful for reviewers -->


Co-authored-by: jennifer.mickel <jennifer.mickel@datadoghq.com>

Author: jennm

.riot/requirements/151ddb8.txt

@@ -2,59 +2,48 @@
 # This file is autogenerated by pip-compile with Python 3.11
 # by the following command:
 #
-#    pip-compile --allow-unsafe --no-annotate .riot/requirements/aed405b.in
+#    pip-compile --allow-unsafe --no-annotate .riot/requirements/17d690f.in
 #
 aiohappyeyeballs==2.6.1
-aiohttp==3.13.3
+aiohttp==3.13.5
 aiosignal==1.4.0
 annotated-doc==0.0.4
 annotated-types==0.7.0
 anyio==4.13.0
-appdirs==1.4.4
 attrs==26.1.0
 backoff==2.2.1
-boto3==1.42.77
-botocore==1.42.77
+boto3==1.42.80
+botocore==1.42.80
 certifi==2026.2.25
 cffi==2.0.0
 charset-normalizer==3.4.6
 click==8.3.1
-colorama==0.4.6
 coverage[toml]==7.13.5
 cryptography==46.0.6
-dataclasses-json==0.6.7
-datasets==4.8.4
-deepeval==3.9.3
-dill==0.4.1
+deepeval==3.9.5
 distro==1.9.0
 docstring-parser==0.17.0
 execnet==2.1.2
-filelock==3.25.2
 frozenlist==1.8.0
-fsspec[http]==2026.2.0
 genai-prices==0.0.56
-google-api-core[grpc]==2.30.0
+google-api-core[grpc]==2.30.1
 google-auth[requests]==2.49.1
-google-cloud-aiplatform==1.143.0
-google-cloud-bigquery==3.40.1
-google-cloud-core==2.5.0
+google-cloud-aiplatform==1.144.0
+google-cloud-bigquery==3.41.0
+google-cloud-core==2.5.1
 google-cloud-resource-manager==1.17.0
 google-cloud-storage==3.10.1
 google-crc32c==1.8.0
-google-genai==1.68.0
-google-resumable-media==2.8.0
+google-genai==1.70.0
+google-resumable-media==2.8.2
 googleapis-common-protos[grpc]==1.73.1
-griffe==2.0.2
-griffecli==2.0.2
 griffelib==2.0.2
-grpc-google-iam-v1==0.14.3
-grpcio==1.78.0
-grpcio-status==1.78.0
+grpc-google-iam-v1==0.14.4
+grpcio==1.80.0
+grpcio-status==1.80.0
 h11==0.16.0
-hf-xet==1.4.2
 httpcore==1.0.9
 httpx==0.28.1
-huggingface-hub==1.8.0
 hypothesis==6.45.0
 idna==3.11
 importlib-metadata==8.7.1
@@ -64,50 +53,47 @@ jiter==0.13.0
 jmespath==1.1.0
 jsonpatch==1.33
 jsonpointer==3.1.1
-langchain==0.2.17
-langchain-community==0.2.19
-langchain-core==0.2.43
-langchain-openai==0.1.25
-langchain-text-splitters==0.2.4
-langsmith==0.1.147
-logfire-api==4.30.0
+langchain==1.2.14
+langchain-core==1.2.23
+langgraph==1.1.4
+langgraph-checkpoint==4.0.1
+langgraph-prebuilt==1.0.8
+langgraph-sdk==0.3.12
+langsmith==0.7.23
+logfire-api==4.31.0
 markdown-it-py==4.0.0
 markupsafe==3.0.3
-marshmallow==3.26.2
 mdurl==0.1.2
 mock==5.2.0
 multidict==6.7.1
-multiprocess==0.70.19
-mypy-extensions==1.1.0
 nest-asyncio==1.6.0
-numpy==1.26.4
-openai==1.109.1
+numpy==2.4.4
+openai==2.30.0
 opentelemetry-api==1.40.0
 opentelemetry-sdk==1.40.0
 opentelemetry-semantic-conventions==0.61b0
 opentracing==2.4.0
-orjson==3.11.7
-packaging==24.2
-pandas==3.0.1
+orjson==3.11.8
+ormsgpack==1.12.2
+packaging==26.0
+pandas==3.0.2
 pluggy==1.6.0
 portalocker==3.2.0
 posthog==5.4.0
 propcache==0.4.1
 proto-plus==1.27.2
 protobuf==6.33.6
-pyarrow==23.0.1
 pyasn1==0.6.3
 pyasn1-modules==0.4.2
 pycparser==3.0
 pydantic==2.12.5
-pydantic-ai-slim==1.30.1
+pydantic-ai-slim==1.75.0
 pydantic-core==2.41.5
-pydantic-evals==1.30.1
-pydantic-graph==1.30.1
+pydantic-evals==1.75.0
+pydantic-graph==1.75.0
 pydantic-settings==2.13.1
 pyfiglet==1.0.4
-pygments==2.19.2
-pysbd==0.3.4
+pygments==2.20.0
 pytest==9.0.2
 pytest-asyncio==0.21.1
 pytest-cov==7.1.0
@@ -118,34 +104,31 @@ pytest-xdist==3.8.0
 python-dateutil==2.9.0.post0
 python-dotenv==1.2.2
 pyyaml==6.0.3
-ragas==0.1.21
-regex==2026.2.28
-requests==2.33.0
+requests==2.33.1
 requests-toolbelt==1.0.0
 rich==14.3.3
 s3transfer==0.16.0
-sentry-sdk==2.56.0
+sentry-sdk==2.57.0
 shellingham==1.5.4
 six==1.17.0
 sniffio==1.3.1
 sortedcontainers==2.4.0
-sqlalchemy==2.0.48
 tabulate==0.9.0
-tenacity==8.5.0
-tiktoken==0.12.0
+tenacity==9.1.4
 tqdm==4.67.3
 typer==0.24.1
 typing-extensions==4.15.0
-typing-inspect==0.9.0
 typing-inspection==0.4.2
 urllib3==2.6.3
+uuid-utils==0.14.1
 vcrpy==8.1.1
 websockets==16.0
 wheel==0.46.3
 wrapt==2.1.2
 xxhash==3.6.0
 yarl==1.23.0
 zipp==3.23.0
+zstandard==0.25.0
 
 # The following packages are considered to be unsafe in a requirements file:
 setuptools==82.0.1