forked from Rockachopa/Timmy-time-dashboard
Kimi Agent
ddb872d3b0
- Replace flat file list with layered architecture map (config→agent→prompt→tool→memory→interface) - Add SELF-MODIFICATION section: Timmy knows he can edit his own config and code - Remove false limitation 'cannot modify own source code' - Update tests to match new section headers, add self-modification tests Closes #81 (reasoning depth) Closes #86 (self-modification awareness) [loop-cycle-11]
100 lines
4.3 KiB
Python
100 lines
4.3 KiB
Python
"""Tests for Timmy's self-knowledge capabilities (Issues #78 and #80)."""
|
|
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
import pytest
|
|
|
|
from timmy.prompts import get_system_prompt
|
|
|
|
|
|
class TestSelfKnowledgeInPrompts:
|
|
"""Verify that system prompts contain self-knowledge sections."""
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def mock_settings(self):
|
|
"""Mock config.settings.ollama_model for all tests."""
|
|
# The settings import happens inside get_system_prompt function,
|
|
# so we mock the config module's settings attribute
|
|
mock_settings = MagicMock()
|
|
mock_settings.ollama_model = "test-model"
|
|
|
|
with patch("config.settings", mock_settings):
|
|
yield mock_settings
|
|
|
|
def test_full_prompt_contains_architecture_header(self, mock_settings):
|
|
"""Full prompt should contain 'ARCHITECTURE MAP' section."""
|
|
prompt = get_system_prompt(tools_enabled=True)
|
|
assert "ARCHITECTURE MAP" in prompt
|
|
|
|
def test_full_prompt_contains_tool_safety_reference(self, mock_settings):
|
|
"""Full prompt should mention tool_safety.py specifically."""
|
|
prompt = get_system_prompt(tools_enabled=True)
|
|
assert "tool_safety.py" in prompt
|
|
|
|
def test_full_prompt_contains_known_limitations(self, mock_settings):
|
|
"""Full prompt should contain 'KNOWN LIMITATIONS' section."""
|
|
prompt = get_system_prompt(tools_enabled=True)
|
|
assert "KNOWN LIMITATIONS" in prompt
|
|
|
|
def test_full_prompt_contains_specific_limitation(self, mock_settings):
|
|
"""Full prompt should mention inability to run test suite autonomously."""
|
|
prompt = get_system_prompt(tools_enabled=True)
|
|
assert "Cannot run your own test suite" in prompt
|
|
|
|
def test_lite_prompt_contains_architecture_header(self, mock_settings):
|
|
"""Lite prompt should contain 'ARCHITECTURE' section."""
|
|
prompt = get_system_prompt(tools_enabled=False)
|
|
assert "ARCHITECTURE" in prompt
|
|
|
|
def test_lite_prompt_contains_known_limitations(self, mock_settings):
|
|
"""Lite prompt should also contain 'KNOWN LIMITATIONS' section."""
|
|
prompt = get_system_prompt(tools_enabled=False)
|
|
assert "KNOWN LIMITATIONS" in prompt
|
|
|
|
def test_lite_prompt_is_shorter_than_full_prompt(self, mock_settings):
|
|
"""Lite prompt's self-knowledge section should be shorter than full prompt's."""
|
|
full_prompt = get_system_prompt(tools_enabled=True)
|
|
lite_prompt = get_system_prompt(tools_enabled=False)
|
|
|
|
# Lite prompt should be shorter overall
|
|
assert len(lite_prompt) < len(full_prompt), (
|
|
f"Lite prompt ({len(lite_prompt)} chars) should be shorter than "
|
|
f"full prompt ({len(full_prompt)} chars)"
|
|
)
|
|
|
|
def test_full_prompt_contains_architecture_layers(self, mock_settings):
|
|
"""Full prompt should describe architecture layers."""
|
|
prompt = get_system_prompt(tools_enabled=True)
|
|
|
|
# Should describe key architectural layers
|
|
assert "Config layer" in prompt
|
|
assert "Agent layer" in prompt
|
|
assert "Memory layer" in prompt
|
|
assert "agents.yaml" in prompt
|
|
|
|
def test_full_prompt_contains_self_modification(self, mock_settings):
|
|
"""Full prompt should describe self-modification pathway."""
|
|
prompt = get_system_prompt(tools_enabled=True)
|
|
assert "SELF-MODIFICATION" in prompt
|
|
assert "agents.yaml" in prompt
|
|
assert "explain proposed changes" in prompt
|
|
|
|
def test_lite_prompt_contains_self_modification(self, mock_settings):
|
|
"""Lite prompt should mention self-modification ability."""
|
|
prompt = get_system_prompt(tools_enabled=False)
|
|
assert "SELF-MODIFICATION" in prompt
|
|
|
|
def test_full_prompt_contains_capabilities(self, mock_settings):
|
|
"""Full prompt should list current capabilities."""
|
|
prompt = get_system_prompt(tools_enabled=True)
|
|
assert "YOUR CURRENT CAPABILITIES" in prompt
|
|
|
|
def test_lite_prompt_is_condensed(self, mock_settings):
|
|
"""Lite prompt should have condensed self-knowledge (no detailed descriptions)."""
|
|
prompt = get_system_prompt(tools_enabled=False)
|
|
|
|
# Should have the key sections but in condensed form
|
|
assert "ARCHITECTURE" in prompt
|
|
assert "YOUR CURRENT CAPABILITIES" in prompt
|
|
assert "YOUR KNOWN LIMITATIONS" in prompt
|