jpmschweitzerandClaude Opus 4.6
334d313d17
- Remove references to unimplemented get_benchmark_store from steward and tool tracking tests - Fix steward test fixture calling async initialize_application synchronously by using sync register_household_members instead - Rewrite tool tracking tests to assert actual logging behavior - Change unit test fixture model from Tatlock to lorem-tester so unit tests don't require external services - Add session-scoped _initialize_app fixture to run Claude health check, ensuring integration tests use Claude instead of falling back to Ollama - Increase integration test timeouts from 30s to 120s to match OLLAMA_TIMEOUT - Add Steward reasoning as ReasoningOutputItem in create_response_with_steward so <think> tags appear in chat completion responses - Add test_tatlock_ollama_fallback to verify Ollama fallback path works Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
88 lines
3.3 KiB
Python
88 lines
3.3 KiB
Python
"""
|
|
Tests for tool call tracking.
|
|
|
|
Tests capability extraction and recommendation matching.
|
|
"""
|
|
import pytest
|
|
|
|
from src.core.tool_tracking import ToolCallTracker
|
|
|
|
|
|
class TestToolCallTracker:
|
|
"""Test ToolCallTracker functionality."""
|
|
|
|
def test_extract_capability_delegation_tool(self):
|
|
"""Test extracting capability from delegation tool name."""
|
|
tracker = ToolCallTracker(recommended_capabilities=["librarian"])
|
|
|
|
assert tracker._extract_capability("delegate_to_librarian") == "librarian"
|
|
assert tracker._extract_capability("delegate_to_biographer") == "biographer"
|
|
assert tracker._extract_capability("delegate_to_housekeeper") == "housekeeper"
|
|
|
|
def test_extract_capability_non_delegation_tool(self):
|
|
"""Test that non-delegation tools return unchanged."""
|
|
tracker = ToolCallTracker(recommended_capabilities=[])
|
|
|
|
assert tracker._extract_capability("calculate") == "calculate"
|
|
assert tracker._extract_capability("search_web") == "search_web"
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_track_call_recognizes_delegation_as_recommended(self):
|
|
"""Test that delegate_to_X is recognized when X is recommended."""
|
|
tracker = ToolCallTracker(
|
|
recommended_capabilities=["librarian", "biographer"]
|
|
)
|
|
|
|
await tracker.track_call("delegate_to_librarian", 1.0)
|
|
|
|
# Should record the call
|
|
assert "delegate_to_librarian" in tracker.actual_calls
|
|
assert tracker.actual_calls["delegate_to_librarian"] == [1.0]
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_track_call_detects_not_recommended(self):
|
|
"""Test that unrecommended tools are flagged."""
|
|
tracker = ToolCallTracker(
|
|
recommended_capabilities=["librarian"]
|
|
)
|
|
|
|
await tracker.track_call("delegate_to_housekeeper", 1.0)
|
|
|
|
# Should record the call even though not recommended
|
|
assert "delegate_to_housekeeper" in tracker.actual_calls
|
|
summary = tracker.get_summary()
|
|
assert summary["accuracy"]["not_recommended_but_used"] == 1
|
|
|
|
def test_get_summary_with_delegation_tools(self):
|
|
"""Test summary correctly maps delegation tools to capabilities."""
|
|
tracker = ToolCallTracker(
|
|
recommended_capabilities=["librarian", "biographer"]
|
|
)
|
|
tracker.actual_calls = {
|
|
"delegate_to_librarian": [1.0, 2.0],
|
|
"delegate_to_housekeeper": [0.5], # Not recommended
|
|
}
|
|
|
|
summary = tracker.get_summary()
|
|
|
|
assert summary["accuracy"]["recommended_and_used"] == 1 # librarian
|
|
assert summary["accuracy"]["recommended_but_unused"] == 1 # biographer
|
|
assert summary["accuracy"]["not_recommended_but_used"] == 1 # housekeeper
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_finalize_with_delegation_tools(self):
|
|
"""Test finalize correctly identifies unused recommendations."""
|
|
tracker = ToolCallTracker(
|
|
recommended_capabilities=["librarian", "biographer"]
|
|
)
|
|
tracker.actual_calls = {
|
|
"delegate_to_librarian": [1.0],
|
|
}
|
|
|
|
await tracker.finalize()
|
|
|
|
# Summary should show biographer as recommended but unused
|
|
summary = tracker.get_summary()
|
|
assert summary["accuracy"]["recommended_and_used"] == 1 # librarian
|
|
assert summary["accuracy"]["recommended_but_unused"] == 1 # biographer
|