howl/tests/test_llm_client.py

from __future__ import annotations

import json
from pathlib import Path
from unittest.mock import MagicMock, patch

import pytest

from howl.llm.schemas import CLASSIFY_EMAIL_TOOL, EmailClassification
from howl.llm.prompts import build_prompt, SYSTEM_PROMPT

FIXTURES_DIR = Path(__file__).parent / "fixtures"


def test_email_classification_validates_valid_data(llm_responses):
    cls = EmailClassification.model_validate(llm_responses["customer_inquiry"])
    assert cls.classification == "customer_inquiry"
    assert cls.action == "move_customer"
    assert 0.0 <= cls.confidence <= 1.0
    assert cls.reasoning


def test_email_classification_rejects_invalid_confidence():
    with pytest.raises(Exception):
        EmailClassification.model_validate({
            "classification": "unknown",
            "confidence": 1.5,  # Out of range
            "action": "inbox_keep",
            "reasoning": "test",
            "priority": "normal",
            "requires_human_review": False,
        })


def test_email_classification_requires_human_review_for_phishing(llm_responses):
    cls = EmailClassification.model_validate(llm_responses["phishing"])
    assert cls.requires_human_review is True


def test_email_classification_low_confidence(llm_responses):
    cls = EmailClassification.model_validate(llm_responses["low_confidence"])
    assert cls.confidence < 0.60
    assert cls.requires_human_review is True


def test_build_prompt_includes_sender_info(customer_message, customer_match):
    prompt = build_prompt(customer_message, "Hello, checking on my order.", customer_match)
    assert customer_message.sender_address in prompt
    assert "customer" in prompt
    assert "Acme Corp" in prompt
    assert "Key account" in prompt


def test_build_prompt_truncates_body(customer_message, unknown_match):
    long_body = "x" * 10000
    prompt = build_prompt(customer_message, long_body, unknown_match, max_body_chars=100)
    assert "truncated" in prompt
    # Body in prompt should be 100 chars, not 10000
    assert "x" * 101 not in prompt


def test_build_prompt_unknown_sender(spam_message, unknown_match):
    prompt = build_prompt(spam_message, "Claim your prize!", unknown_match)
    assert "unknown" in prompt
    # No entity name should appear
    assert "Known as:" not in prompt


def test_classify_email_tool_schema_is_valid():
    """Tool definition should have all required fields for Anthropic tool use."""
    assert CLASSIFY_EMAIL_TOOL["name"] == "classify_email"
    schema = CLASSIFY_EMAIL_TOOL["input_schema"]
    assert schema["type"] == "object"
    required = schema["required"]
    assert "classification" in required
    assert "confidence" in required
    assert "action" in required
    assert "reasoning" in required
    assert "requires_human_review" in required


def test_llm_client_calls_anthropic_and_parses_response(
    settings, customer_message, customer_match
):
    """Test that LLMClient correctly calls the Anthropic SDK and parses tool use output."""
    from howl.llm.client import LLMClient

    mock_tool_use = MagicMock()
    mock_tool_use.type = "tool_use"
    mock_tool_use.input = {
        "classification": "customer_inquiry",
        "confidence": 0.92,
        "action": "move_customer",
        "reasoning": "Known customer inquiry.",
        "priority": "normal",
        "requires_human_review": False,
        "tags": [],
    }

    mock_response = MagicMock()
    mock_response.content = [mock_tool_use]
    mock_response.model = "claude-sonnet-4-6"
    mock_response.stop_reason = "tool_use"
    mock_response.usage.input_tokens = 300
    mock_response.usage.output_tokens = 75

    with patch("howl.llm.client.Anthropic") as MockAnthropic:
        MockAnthropic.return_value.messages.create.return_value = mock_response
        client = LLMClient(settings)
        classification, raw = client.classify(
            customer_message, "Hello, checking my order status.", customer_match
        )

    assert classification.classification == "customer_inquiry"
    assert classification.action == "move_customer"
    assert raw["usage"]["input_tokens"] == 300


def test_llm_client_raises_if_no_tool_use(settings, customer_message, customer_match):
    """LLMClient should raise ValueError if Claude doesn't call the tool."""
    from howl.llm.client import LLMClient

    mock_text_block = MagicMock()
    mock_text_block.type = "text"

    mock_response = MagicMock()
    mock_response.content = [mock_text_block]

    with patch("howl.llm.client.Anthropic") as MockAnthropic:
        MockAnthropic.return_value.messages.create.return_value = mock_response
        client = LLMClient(settings)
        with pytest.raises(ValueError, match="classify_email"):
            client.classify(customer_message, "body", customer_match)