Draft: PoC: pytest/langsmith integration tests

A proof of concept of pytest/langsmith integration for agent/tool/prompt integration testing

See #244 (moved)

1. tests/duo_workflow_service/tools/test_issue_integration_simple.py
   • Uses a simple system prompt rather than the real one, to focus the test on the tool prompts. Just checks 2 URLs
   • LangSmith results
2. tests/duo_workflow_service/tools/test_issue_integration_description_variants.py
   • Compares different description variants for the get_issue tool. This gives an example of how we could quickly compare a few different prompt variants to see which performs best. We could rerun the test several times to check for reliability.
   • LangSmith results
   • The failures show that some forms of URL input still can't be handled properly

Note: The tests don't run in CI atm because they need a LangSmith token. But you can run them locally as typical pytest tests, plus a LangSmith environment variable:

export LANGSMITH_TEST_SUITE="LLM Integration tests" # the name of the LangSmith dataset that the tests will be grouped into 
poetry run python -m pytest "tests/duo_workflow_service/tools/test_issue_integration_simple.py"

See also !346 for a different example