Files
tatlock/tests/agents/steward/test_steward_schemas.py
T
jpmschweitzerandClaude 78066fab1b style: apply ruff's automatic fixes and formatter
Mechanical only, and separated from the judgment calls that follow so the
reviewable changes are not buried in a 98-file whitespace diff.

227 automatic fixes: 60 blank lines carrying whitespace, 60 unsorted import
blocks, 34 Optional[X] to X | None, 28 unused imports, 16 deprecated typing
imports, 12 datetime.timezone.utc to datetime.UTC, and assorted smaller
modernisations. Then `ruff format` over src and tests: 98 files reformatted,
35 already conforming.

No file among the unused-import findings defines __all__ or is an __init__.py,
so nothing here removes a re-export.

`make test`: 658 passed, unchanged from HEAD.

Two things observed while verifying, neither addressed here:

`pytest tests/` cannot collect — tests/e2e/test_orchestration_e2e.py uses an
`e2e` marker that is not registered, and the config is strict about markers.
This fails identically at HEAD, so it predates this change; `make test` passes
because it ignores tests/e2e, tests/integration and tests/contracts.

test_tatlock_tool_call_logging_calculator is flaky. It failed once in a full run
with these changes and passed on the next, passes in isolation with them, and
fails in isolation at HEAD. It is order- or timing-dependent, not a regression
from this commit — established by running the full suite both ways rather than
by reasoning about which change could have caused it.

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-11 17:25:18 +02:00

166 lines
6.2 KiB
Python

"""
Tests for Steward schemas.
Tests the structured output models for conversation context and recommendations.
"""
from src.agents.steward.schemas import ConversationContext, StewardRecommendation
class TestConversationContext:
"""Test ConversationContext model."""
def test_context_creation_with_defaults(self):
"""Test creating context with default values."""
context = ConversationContext(has_previous_context=False)
assert context.has_previous_context is False
assert context.relevant_turns == []
assert context.context_summary == ""
def test_context_creation_with_values(self):
"""Test creating context with explicit values."""
context = ConversationContext(
has_previous_context=True,
relevant_turns=[0, 2, 4],
context_summary="User discussed weather in turns 0 and 2",
)
assert context.has_previous_context is True
assert context.relevant_turns == [0, 2, 4]
assert "weather" in context.context_summary
class TestStewardRecommendation:
"""Test StewardRecommendation model."""
def test_recommendation_simple(self):
"""Test simple recommendation with no capabilities needed."""
rec = StewardRecommendation(
recommended_capabilities=[],
reasoning="Simple greeting requires no tools",
estimated_complexity="simple",
conversation_context=ConversationContext(has_previous_context=False),
)
assert rec.recommended_capabilities == []
assert rec.estimated_complexity == "simple"
assert rec.missing_capabilities is None
def test_recommendation_with_capabilities(self):
"""Test recommendation with specific capabilities."""
rec = StewardRecommendation(
recommended_capabilities=["tatlock_core"],
reasoning="Mathematical calculation requires calculator",
estimated_complexity="simple",
conversation_context=ConversationContext(has_previous_context=False),
)
assert "tatlock_core" in rec.recommended_capabilities
assert rec.estimated_complexity == "simple"
def test_recommendation_with_missing_capabilities(self):
"""Test recommendation noting missing capabilities."""
rec = StewardRecommendation(
recommended_capabilities=[],
reasoning="Image generation is not available",
estimated_complexity="simple",
conversation_context=ConversationContext(has_previous_context=False),
missing_capabilities="Image generation capability would be needed",
)
assert rec.missing_capabilities is not None
assert "Image generation" in rec.missing_capabilities
def test_recommendation_complexity_levels(self):
"""Test all complexity levels."""
for complexity in ["simple", "moderate", "complex"]:
rec = StewardRecommendation(
recommended_capabilities=[],
reasoning=f"Testing {complexity} complexity",
estimated_complexity=complexity,
conversation_context=ConversationContext(has_previous_context=False),
)
assert rec.estimated_complexity == complexity
def test_recommendation_with_context(self):
"""Test recommendation with conversation context."""
context = ConversationContext(
has_previous_context=True,
relevant_turns=[1, 3],
context_summary="User asked about calculation in turn 1, now wants explanation",
)
rec = StewardRecommendation(
recommended_capabilities=["tatlock_core"],
reasoning="User wants explanation of previous calculation",
estimated_complexity="moderate",
conversation_context=context,
)
assert rec.conversation_context.has_previous_context is True
assert len(rec.conversation_context.relevant_turns) == 2
def test_format_for_butler_simple(self):
"""Test formatting recommendation for Butler - simple case."""
rec = StewardRecommendation(
recommended_capabilities=["tatlock_core"],
reasoning="Math calculation needed",
estimated_complexity="simple",
conversation_context=ConversationContext(has_previous_context=False),
)
formatted = rec.format_for_butler()
assert "📋 Steward's Analysis" in formatted
assert "SIMPLE" in formatted
assert "tatlock_core" in formatted
def test_format_for_butler_with_context(self):
"""Test formatting with conversation context."""
context = ConversationContext(
has_previous_context=True,
relevant_turns=[0],
context_summary="Previous calculation mentioned",
)
rec = StewardRecommendation(
recommended_capabilities=["tatlock_core"],
reasoning="Follow-up calculation",
estimated_complexity="moderate",
conversation_context=context,
)
formatted = rec.format_for_butler()
assert "Context:" in formatted
assert "Previous calculation" in formatted
def test_format_for_butler_with_missing_capabilities(self):
"""Test formatting with missing capabilities warning."""
rec = StewardRecommendation(
recommended_capabilities=[],
reasoning="No suitable tools available",
estimated_complexity="simple",
conversation_context=ConversationContext(has_previous_context=False),
missing_capabilities="Image generation would be needed",
)
formatted = rec.format_for_butler()
assert "⚠️ Missing:" in formatted
assert "Image generation" in formatted
def test_format_for_butler_no_capabilities(self):
"""Test formatting when no tools needed (conversational)."""
rec = StewardRecommendation(
recommended_capabilities=[],
reasoning="Simple greeting",
estimated_complexity="simple",
conversation_context=ConversationContext(has_previous_context=False),
)
formatted = rec.format_for_butler()
assert "None (conversational response)" in formatted