tatlock/tests/agents/steward/test_steward_service.py

"""
Tests for Steward service layer.

Tests request analysis, logging, and benchmarking integration.
"""

from unittest.mock import AsyncMock, MagicMock, patch

import pytest

from src.agents.steward.schemas import ConversationContext, StewardRecommendation
from src.agents.steward.service import (
    _build_enriched_query,
    _extract_capabilities,
    analyze_request,
    format_steward_note,
)
from src.core.startup import register_household_members


@pytest.fixture(scope="module", autouse=True)
def setup_household_registry():
    """Initialize household registry before running tests."""
    register_household_members()


class TestAnalyzeRequest:
    """Test the analyze_request service function."""

    @pytest.mark.asyncio
    async def test_analyze_simple_greeting(self):
        """Test analyzing a simple greeting."""
        # Mock the Steward agent's analyze method (plain text approach)
        mock_agent = MagicMock()
        mock_agent.analyze = AsyncMock(
            return_value="Simple greeting requires no tools. This is a simple request."
        )

        with patch("src.agents.steward.service.get_steward_agent", return_value=mock_agent):
            result = await analyze_request(
                "Hello!",
                conversation_history=[],
            )

            assert result.recommended_capabilities == []
            assert result.estimated_complexity == "simple"
            assert mock_agent.analyze.called

    @pytest.mark.asyncio
    async def test_analyze_math_request(self):
        """Test analyzing a mathematical request."""
        mock_agent = MagicMock()
        mock_agent.analyze = AsyncMock(
            return_value="Mathematical calculation requires tatlock_core for solving this simple problem."
        )

        with patch("src.agents.steward.service.get_steward_agent", return_value=mock_agent):
            result = await analyze_request(
                "What's sqrt(144)?",
                conversation_history=[],
            )

            assert "tatlock_core" in result.recommended_capabilities
            assert result.estimated_complexity == "simple"

    @pytest.mark.asyncio
    async def test_analyze_with_conversation_history(self):
        """Test analyzing with previous conversation context."""
        mock_agent = MagicMock()
        mock_agent.analyze = AsyncMock(
            return_value="Follow-up to previous calculation in turn 0. Requires tatlock_core. Complexity: moderate."
        )

        conversation_history = [
            {"role": "user", "content": "What's 2 + 2?"},
            {"role": "assistant", "content": "4"},
        ]

        with patch("src.agents.steward.service.get_steward_agent", return_value=mock_agent):
            result = await analyze_request(
                "And what's that times 5?",
                conversation_history=conversation_history,
            )

            assert result.conversation_context.has_previous_context is True
            assert 0 in result.conversation_context.relevant_turns

            # Verify conversation history was passed
            call_kwargs = mock_agent.analyze.call_args.kwargs
            assert "conversation_history" in call_kwargs
            assert len(call_kwargs["conversation_history"]) == 2

    @pytest.mark.asyncio
    async def test_analyze_with_missing_capabilities(self):
        """Test analyzing request that needs unavailable capabilities."""
        mock_agent = MagicMock()
        mock_agent.analyze = AsyncMock(
            return_value="Image generation not available. Would be needed for this request. Complexity: simple."
        )

        with patch("src.agents.steward.service.get_steward_agent", return_value=mock_agent):
            result = await analyze_request(
                "Generate an image of a sunset",
                conversation_history=[],
            )

            assert result.missing_capabilities is not None
            assert "not available" in result.missing_capabilities

    @pytest.mark.asyncio
    async def test_analyze_with_conversation_id(self):
        """Test that analysis includes conversation ID in context."""
        mock_agent = MagicMock()
        mock_agent.analyze = AsyncMock(
            return_value="This simple request requires tatlock_core to solve."
        )

        with patch("src.agents.steward.service.get_steward_agent", return_value=mock_agent):
            result = await analyze_request(
                "Test request",
                conversation_history=[],
                conversation_id="test_conv_123",
            )

            # Verify analysis completed successfully
            assert result.recommended_capabilities == ["tatlock_core"]
            assert result.estimated_complexity == "simple"

    @pytest.mark.asyncio
    async def test_analyze_handles_errors(self):
        """Test error handling in analyze_request."""
        mock_agent = MagicMock()
        mock_agent.analyze = AsyncMock(side_effect=Exception("Test error"))

        with patch("src.agents.steward.service.get_steward_agent", return_value=mock_agent):
            with pytest.raises(Exception, match="Test error"):
                await analyze_request("Test", conversation_history=[])


class TestFormatStewardNote:
    """Test the format_steward_note function."""

    @pytest.mark.asyncio
    async def test_format_simple_note(self):
        """Test formatting a simple recommendation."""
        rec = StewardRecommendation(
            recommended_capabilities=["tatlock_core"],
            reasoning="Math needed",
            estimated_complexity="simple",
            conversation_context=ConversationContext(has_previous_context=False),
        )

        note = await format_steward_note(rec)

        assert "📋 Steward's Analysis" in note
        assert "SIMPLE" in note
        assert "tatlock_core" in note

    @pytest.mark.asyncio
    async def test_format_note_with_context(self):
        """Test formatting note with conversation context."""
        context = ConversationContext(
            has_previous_context=True,
            relevant_turns=[0, 1],
            context_summary="Previous discussion about calculations",
        )

        rec = StewardRecommendation(
            recommended_capabilities=["tatlock_core"],
            reasoning="Follow-up calculation",
            estimated_complexity="moderate",
            conversation_context=context,
        )

        note = await format_steward_note(rec)

        assert "Context:" in note
        assert "Previous discussion" in note

    @pytest.mark.asyncio
    async def test_format_note_with_missing_capabilities(self):
        """Test formatting note with missing capabilities warning."""
        rec = StewardRecommendation(
            recommended_capabilities=[],
            reasoning="Not available",
            estimated_complexity="simple",
            conversation_context=ConversationContext(has_previous_context=False),
            missing_capabilities="Advanced research tools needed",
        )

        note = await format_steward_note(rec)

        assert "⚠️  Missing:" in note
        assert "Advanced research" in note


@pytest.mark.unit
class TestBuildEnrichedQuery:
    """Tests for _build_enriched_query function."""

    def test_no_enrichment_without_context(self):
        """Test no enrichment when memory context is empty."""
        query = "What's the weather?"
        result = _build_enriched_query(query, {})

        assert result == query

    def test_enrichment_adds_location(self):
        """Test location is appended for weather queries."""
        query = "What's the weather?"
        memory_context = {"profile": {"location": "Amsterdam", "timezone": "Europe/Amsterdam"}}

        result = _build_enriched_query(query, memory_context)

        assert "location=Amsterdam" in result
        assert query in result
        assert "[User Context:" in result

    def test_no_location_when_specified(self):
        """Test location is not appended when already specified."""
        query = "What's the weather in London?"
        memory_context = {"profile": {"location": "Amsterdam"}}

        result = _build_enriched_query(query, memory_context)

        # Should not add Amsterdam since location is specified
        assert result == query

    def test_enrichment_adds_timezone(self):
        """Test timezone is appended for time queries."""
        query = "What time is it?"
        memory_context = {"profile": {"timezone": "Europe/Amsterdam"}}

        result = _build_enriched_query(query, memory_context)

        assert "timezone=Europe/Amsterdam" in result

    def test_no_timezone_when_specified(self):
        """Test timezone is not appended when already specified."""
        query = "What time is it in UTC?"
        memory_context = {"profile": {"timezone": "Europe/Amsterdam"}}

        result = _build_enriched_query(query, memory_context)

        assert result == query

    def test_enrichment_adds_temperature_unit(self):
        """Test temperature unit is appended for weather queries."""
        query = "What's the weather?"
        memory_context = {
            "profile": {"location": "Amsterdam"},
            "preferences": {"temperature_unit": "celsius"},
        }

        result = _build_enriched_query(query, memory_context)

        assert "temperature_unit=celsius" in result

    def test_multiple_context_fields(self):
        """Test multiple context fields are appended."""
        query = "What time and weather today?"
        memory_context = {
            "profile": {"location": "Amsterdam", "timezone": "Europe/Amsterdam"},
            "preferences": {"temperature_unit": "celsius"},
        }

        result = _build_enriched_query(query, memory_context)

        assert "location=Amsterdam" in result
        assert "timezone=Europe/Amsterdam" in result
        assert "temperature_unit=celsius" in result

    def test_no_enrichment_for_unrelated_query(self):
        """Test no enrichment for queries that don't need context."""
        query = "Tell me a joke"
        memory_context = {"profile": {"location": "Amsterdam", "timezone": "Europe/Amsterdam"}}

        result = _build_enriched_query(query, memory_context)

        assert result == query


class TestExtractCapabilities:
    """Capability extraction reads the declared DELEGATE line, not free prose.

    The prompt tells the Steward to state its choice on a DELEGATE line and to
    explain itself on REASON/COMPLEXITY/CONTEXT lines. An earlier version
    substring-matched capability domains across the entire response, so ordinary
    English in the explanation routed requests: "description" contains the
    housekeeper domain "script", "acknowledge" contains "know". These tests pin
    that the explanation can no longer influence routing.
    """

    # (prose, why it used to misroute)
    SUBSTRING_TRAPS = [
        ("The user wants a description of the algorithm.", "script -> housekeeper"),
        ("I should discover what the answer is.", "cover -> housekeeper"),
        ("That sounds fantastic, let me compute it.", "fan -> housekeeper"),
        (
            "I acknowledge the request to add two numbers.",
            "knowledge/know -> librarian, biographer",
        ),
        ("The user asks about the economy myth.", "my -> biographer"),
        ("Convert 98.6 Fahrenheit to Celsius.", "temperature is a housekeeper domain"),
    ]

    @pytest.mark.parametrize("prose,reason", SUBSTRING_TRAPS)
    def test_reason_prose_cannot_add_capabilities(self, prose, reason):
        """Explanatory prose must not summon agents the Steward did not request."""
        text = f"DELEGATE: tatlock_core to calculate\nREASON: {prose}\nCOMPLEXITY: simple"

        assert _extract_capabilities(text) == ["tatlock_core"], f"regression: {reason}"

    def test_delegate_line_task_text_does_not_leak(self):
        """A domain word inside the task description must not add a capability.

        "home" is a housekeeper domain, but this is plainly a memory recall.
        """
        text = "DELEGATE: biographer to recall the user's home address\nREASON: personal data"

        assert _extract_capabilities(text) == ["biographer"]

    def test_multiple_delegate_lines(self):
        """Each DELEGATE line contributes its capability, in order, deduplicated."""
        text = (
            "DELEGATE: biographer to recall the user's location\n"
            "DELEGATE: librarian to search_web for the forecast\n"
            "DELEGATE: biographer to recall preferences\n"
        )

        assert _extract_capabilities(text) == ["biographer", "librarian"]

    def test_capability_named_later_on_the_line(self):
        """A loosely worded DELEGATE line still resolves by name."""
        text = "DELEGATE: ask the librarian to search the web"

        assert _extract_capabilities(text) == ["librarian"]

    def test_domain_fallback_within_delegate_line(self):
        """With no capability named, domains on the DELEGATE line still resolve."""
        text = "DELEGATE: turn on the lights in the kitchen"

        assert _extract_capabilities(text) == ["housekeeper"]

    def test_conversational_response_selects_nothing(self):
        """No DELEGATE line means no capability, which is the prompt's chat path."""
        text = "This is a simple greeting. No capabilities are needed. COMPLEXITY: simple"

        assert _extract_capabilities(text) == []

    def test_malformed_response_still_routes_by_name(self):
        """If the format is ignored, a named capability is still honoured."""
        text = "I think the librarian should handle this research request."

        assert _extract_capabilities(text) == ["librarian"]

    def test_malformed_response_does_not_route_on_domains(self):
        """...but bare prose must not route on domain words alone."""
        text = "The user wants a description of home automation, and I acknowledge it."

        assert _extract_capabilities(text) == []

    def test_case_insensitive_delegate_marker(self):
        text = "delegate: Librarian to search_web"

        assert _extract_capabilities(text) == ["librarian"]

    def test_empty_input(self):
        assert _extract_capabilities("") == []