Update prompt using bad responses from langsmith about tchoung-te HOT 3 CLOSED

from datetime import datetime, timedelta, timezone

from langsmith import Client
from langsmith.beta import convert_runs_to_test

# How we are sampling runs to include in our test
end_time = datetime.now(tz=timezone.utc)
start_time = end_time - timedelta(days=14)
project_name="tchoung-te"
run_filter = f'and(gt(start_time, "{start_time.isoformat()}"), lt(end_time, "{end_time.isoformat()}"))'


# Fetch the runs we want to convert to a test
client = Client()

prod_runs = list(
    client.list_runs(
        project_name=project_name,
        execution_order=1,
        filter=run_filter,
    )
)

# Name of the dataset we want to create
dataset_name = f'{project_name}-backtesting {start_time.strftime("%Y-%m-%d")}-{end_time.strftime("%Y-%m-%d")}'
# This converts the runs to a dataset + test
# It does not actually invoke your model
convert_runs_to_test(
    prod_runs,
    # Name of the resulting dataset
    dataset_name=dataset_name,
    # Whether to include the run outputs as reference/ground truth
    include_outputs=True,
    # Whether to include the full traces in the resulting test project
    # (default is to just include the root run)
    load_child_runs=True,
)