test(bias): add efficacy simulation tests and enhance strategy labels
This commit is contained in:
@@ -39,13 +39,23 @@ class ToolBiasEngine:
|
|||||||
lines = ["### Tooling Strategy"]
|
lines = ["### Tooling Strategy"]
|
||||||
|
|
||||||
preferred = []
|
preferred = []
|
||||||
|
low_priority = []
|
||||||
for cat_tools in preset.categories.values():
|
for cat_tools in preset.categories.values():
|
||||||
for t in cat_tools:
|
for t in cat_tools:
|
||||||
if isinstance(t, Tool) and t.weight >= 4:
|
if not isinstance(t, Tool): continue
|
||||||
preferred.append(t.name)
|
if t.weight >= 5:
|
||||||
|
preferred.append(f"{t.name} [HIGH PRIORITY]")
|
||||||
|
elif t.weight == 4:
|
||||||
|
preferred.append(f"{t.name} [PREFERRED]")
|
||||||
|
elif t.weight == 2:
|
||||||
|
low_priority.append(f"{t.name} [NOT RECOMMENDED]")
|
||||||
|
elif t.weight <= 1:
|
||||||
|
low_priority.append(f"{t.name} [LOW PRIORITY]")
|
||||||
|
|
||||||
if preferred:
|
if preferred:
|
||||||
lines.append(f"Preferred tools: {', '.join(preferred)}.")
|
lines.append(f"Preferred tools: {', '.join(preferred)}.")
|
||||||
|
if low_priority:
|
||||||
|
lines.append(f"Low-priority tools: {', '.join(low_priority)}.")
|
||||||
|
|
||||||
if global_bias.category_multipliers:
|
if global_bias.category_multipliers:
|
||||||
lines.append("Category focus multipliers:")
|
lines.append("Category focus multipliers:")
|
||||||
|
|||||||
51
tests/test_bias_efficacy.py
Normal file
51
tests/test_bias_efficacy.py
Normal file
@@ -0,0 +1,51 @@
|
|||||||
|
import pytest
|
||||||
|
from src import ai_client
|
||||||
|
from src.models import ToolPreset, Tool, BiasProfile
|
||||||
|
from unittest.mock import MagicMock, patch
|
||||||
|
|
||||||
|
def test_bias_efficacy_prompt_generation():
|
||||||
|
# Verify that the generated prompt contains the expected nudges and strategy
|
||||||
|
preset = ToolPreset(name="BiasTest", categories={
|
||||||
|
"General": [
|
||||||
|
Tool(name="list_directory", weight=5),
|
||||||
|
Tool(name="search_files", weight=1)
|
||||||
|
]
|
||||||
|
})
|
||||||
|
bias = BiasProfile(name="Balanced", category_multipliers={"General": 1.0})
|
||||||
|
|
||||||
|
with patch("src.ai_client._active_tool_preset", preset):
|
||||||
|
with patch("src.ai_client._active_bias_profile", bias):
|
||||||
|
prompt = ai_client._get_combined_system_prompt()
|
||||||
|
|
||||||
|
# Check strategy section
|
||||||
|
assert "Tooling Strategy" in prompt
|
||||||
|
assert "list_directory" in prompt
|
||||||
|
assert "PREFERRED" in prompt or "HIGH PRIORITY" in prompt
|
||||||
|
|
||||||
|
# Check tool definitions nudging
|
||||||
|
with patch("src.ai_client._agent_tools", {"list_directory": True, "search_files": True}):
|
||||||
|
# Anthropic tools as an example
|
||||||
|
with patch("src.ai_client._CACHED_ANTHROPIC_TOOLS", None):
|
||||||
|
tools = ai_client._get_anthropic_tools()
|
||||||
|
|
||||||
|
ls_tool = next(t for t in tools if t["name"] == "list_directory")
|
||||||
|
search_tool = next(t for t in tools if t["name"] == "search_files")
|
||||||
|
|
||||||
|
assert "[HIGH PRIORITY]" in ls_tool["description"]
|
||||||
|
assert "[LOW PRIORITY]" in ls_tool["description"] or "[LOW PRIORITY]" in search_tool["description"]
|
||||||
|
|
||||||
|
def test_bias_parameter_nudging():
|
||||||
|
preset = ToolPreset(name="ParamTest", categories={
|
||||||
|
"General": [
|
||||||
|
Tool(name="read_file", parameter_bias={"path": "CRITICAL"})
|
||||||
|
]
|
||||||
|
})
|
||||||
|
|
||||||
|
with patch("src.ai_client._active_tool_preset", preset):
|
||||||
|
with patch("src.ai_client._agent_tools", {"read_file": True}):
|
||||||
|
with patch("src.ai_client._CACHED_ANTHROPIC_TOOLS", None):
|
||||||
|
tools = ai_client._get_anthropic_tools()
|
||||||
|
read_tool = next(t for t in tools if t["name"] == "read_file")
|
||||||
|
|
||||||
|
path_param_desc = read_tool["input_schema"]["properties"]["path"]["description"]
|
||||||
|
assert "[CRITICAL]" in path_param_desc
|
||||||
Reference in New Issue
Block a user