Pytest/Vitest와 LangSmith로 ReAct 에이전트 테스트하기

pip install -U langgraph langchain[openai] langchain-community e2b-code-interpreter

# Make sure you have langsmith>=0.3.1
pip install -U "langsmith[pytest]"

from langchain_community.tools import TavilySearchResults
from e2b_code_interpreter import Sandbox
from langchain_community.tools.polygon.aggregates import PolygonAggregates
from langchain_community.utilities.polygon import PolygonAPIWrapper
from typing_extensions import Annotated, TypedDict, Optional, Literal

# Define search tool
search_tool = TavilySearchResults(
  max_results=5,
  include_raw_content=True,
)

# Define code tool
def code_tool(code: str) -> str:
  """Execute python code and return the result."""
  sbx = Sandbox()
  execution = sbx.run_code(code)

  if execution.error:
      return f"Error: {execution.error}"
  return f"Results: {execution.results}, Logs: {execution.logs}"

# Define input schema for stock ticker tool
class TickerToolInput(TypedDict):
  """Input format for the ticker tool.
    The tool will pull data in aggregate blocks (timespan_multiplier * timespan) from the from_date to the to_date
  """
  ticker: Annotated[str, ..., "The ticker symbol of the stock"]
  timespan: Annotated[Literal["minute", "hour", "day", "week", "month", "quarter", "year"], ..., "The size of the time window."]
  timespan_multiplier: Annotated[int, ..., "The multiplier for the time window"]
  from_date: Annotated[str, ..., "The date to start pulling data from, YYYY-MM-DD format - ONLY include the year month and day"]
  to_date: Annotated[str, ..., "The date to stop pulling data, YYYY-MM-DD format - ONLY include the year month and day"]

api_wrapper = PolygonAPIWrapper()
polygon_aggregate = PolygonAggregates(api_wrapper=api_wrapper)

# Define stock ticker tool
def ticker_tool(query: TickerToolInput) -> str:
  """Pull data for the ticker."""
  return polygon_aggregate.invoke(query)

from typing_extensions import Annotated, TypedDict
from langchain.agents import create_agent


class AgentOutputFormat(TypedDict):
    numeric_answer: Annotated[float | None, ..., "The numeric answer, if the user asked for one"]
    text_answer: Annotated[str | None, ..., "The text answer, if the user asked for one"]
    reasoning: Annotated[str, ..., "The reasoning behind the answer"]

agent = create_agent(
    model="openai:gpt-4o-mini",
    tools=[code_tool, search_tool, polygon_aggregates],
    response_format=AgentOutputFormat,
    system_prompt="You are a financial expert. Respond to the users query accurately",
)

Create a `tests/test_agent.py` file.

from app import agent, polygon_aggregates, search_tool # import from wherever your agent is defined
import pytest
from langsmith import testing as t

@pytest.mark.langsmith
@pytest.mark.parametrize(
  # <-- Can still use all normal pytest markers
  "query",
  ["Hello!", "How are you doing?"],
)
def test_no_tools_on_offtopic_query(query: str) -> None:
  """Test that the agent does not use tools on offtopic queries."""
  # Log the test example
  t.log_inputs({"query": query})
  expected = []
  t.log_reference_outputs({"tool_calls": expected})
  # Call the agent's model node directly instead of running the ReACT loop.
  result = agent.nodes["agent"].invoke(
      {"messages": [{"role": "user", "content": query}]}
  )
  actual = result["messages"][0].tool_calls
  t.log_outputs({"tool_calls": actual})
  # Check that no tool calls were made.
  assert actual == expected

@pytest.mark.langsmith
def test_searches_for_correct_ticker() -> None:
  """Test that the model looks up the correct ticker on simple query."""
  # Log the test example
  query = "What is the price of Apple?"
  t.log_inputs({"query": query})
  expected = "AAPL"
  t.log_reference_outputs({"ticker": expected})
  # Call the agent's model node directly instead of running the full ReACT loop.
  result = agent.nodes["agent"].invoke(
      {"messages": [{"role": "user", "content": query}]}
  )
  tool_calls = result["messages"][0].tool_calls
  if tool_calls[0]["name"] == polygon_aggregates.name:
      actual = tool_calls[0]["args"]["ticker"]
  else:
      actual = None
  t.log_outputs({"ticker": actual})
  # Check that the right ticker was queried
  assert actual == expected

@pytest.mark.langsmith
def test_executes_code_when_needed() -> None:
  query = (
      "In the past year Facebook stock went up by 66.76%, "
      "Apple by 25.24%, Google by 37.11%, Amazon by 47.52%, "
      "Netflix by 78.31%. Whats the avg return in the past "
      "year of the FAANG stocks, expressed as a percentage?"
  )
  t.log_inputs({"query": query})
  expected = 50.988
  t.log_reference_outputs({"response": expected})
  # Test that the agent executes code when needed
  result = agent.invoke({"messages": [{"role": "user", "content": query}]})
  t.log_outputs({"result": result["structured_response"].get("numeric_answer")})
  # Grab all the tool calls made by the LLM
  tool_calls = [
      tc["name"]
      for msg in result["messages"]
      for tc in getattr(msg, "tool_calls", [])
  ]
  # This will log the number of steps taken by the agent, which is useful for
  # determining how efficiently the agent gets to an answer.
  t.log_feedback(key="num_steps", score=len(result["messages"]) - 1)
  # Assert that the code tool was used
  assert "code_tool" in tool_calls
  # Assert that a numeric answer was provided:
  assert result["structured_response"].get("numeric_answer") is not None
  # Assert that the answer is correct
  assert abs(result["structured_response"]["numeric_answer"] - expected) <= 0.01

from typing_extensions import Annotated, TypedDict
from langchain.chat_models import init_chat_model

class Grade(TypedDict):
  """Evaluate the groundedness of an answer in source documents."""
  score: Annotated[
      bool,
      ...,
      "Return True if the answer is fully grounded in the source documents, otherwise False.",
  ]

judge_llm = init_chat_model("gpt-4o").with_structured_output(Grade)

@pytest.mark.langsmith
def test_grounded_in_source_info() -> None:
  """Test that response is grounded in the tool outputs."""
  query = "How did Nvidia stock do in 2024 according to analysts?"
  t.log_inputs({"query": query})
  result = agent.invoke({"messages": [{"role": "user", "content": query}]})
  # Grab all the search calls made by the LLM
  search_results = "\n\n".join(
      msg.content
      for msg in result["messages"]
      if msg.type == "tool" and msg.name == search_tool.name
  )
  t.log_outputs(
      {
          "response": result["structured_response"].get("text_answer"),
          "search_results": search_results,
      }
  )
  # Trace the feedback LLM run separately from the agent run.
  with t.trace_feedback():
      # Instructions for the LLM judge
      instructions = (
          "Grade the following ANSWER. "
          "The ANSWER should be fully grounded in (i.e. supported by) the source DOCUMENTS. "
          "Return True if the ANSWER is fully grounded in the DOCUMENTS. "
          "Return False if the ANSWER is not grounded in the DOCUMENTS."
      )
      answer_and_docs = (
          f"ANSWER: {result['structured_response'].get('text_answer', '')}\n"
          f"DOCUMENTS:\n{search_results}"
      )
      # Run the judge LLM
      grade = judge_llm.invoke(
          [
              {"role": "system", "content": instructions},
              {"role": "user", "content": answer_and_docs},
          ]
      )
      t.log_feedback(key="groundedness", score=grade["score"])
  assert grade['score']

pytest --langsmith-output tests