This repository has been archived on 2026-03-24. You can view files and clone it. You cannot open issues or pull requests or push a commit.
Files
Timmy-time-dashboard/tests/timmy/test_timmy_tools.py
Alexander Whitestone 36fc10097f Claude/angry cerf (#173)
* feat: set qwen3.5:latest as default model

- Make qwen3.5:latest the primary default model for faster inference
- Move llama3.1:8b-instruct to fallback chain
- Update text fallback chain to prioritize qwen3.5:latest

Retains full backward compatibility via cascade fallback.

* test: remove ~55 brittle, duplicate, and useless tests

Audit of all 100 test files identified tests that provided no real
regression protection. Removed:

- 4 files deleted entirely: test_setup_script (always skipped),
  test_csrf_bypass (tautological assertions), test_input_validation
  (accepts 200-500 status codes), test_security_regression (fragile
  source-pattern checks redundant with rendering tests)
- Duplicate test classes (TestToolTracking, TestCalculatorExtended)
- Mock-only tests that just verify mock wiring, not behavior
- Structurally broken tests (TestCreateToolFunctions patches after import)
- Empty/pass-body tests and meaningless assertions (len > 20)
- Flaky subprocess tests (aider tool calling real binary)

All 1328 remaining tests pass. Net: -699 lines, zero coverage loss.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: prevent test pollution from autoresearch_enabled mutation

test_autoresearch_perplexity.py was setting settings.autoresearch_enabled = True
but never restoring it in the finally block — polluting subsequent tests.
When pytest-randomly ordered it before test_experiments_page_shows_disabled_when_off,
the victim test saw enabled=True and failed to find "Disabled" in the page.

Fix both sides:
- Restore autoresearch_enabled in the finally block (root cause)
- Mock settings explicitly in the victim test (defense in depth)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Trip T <trip@local>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-11 16:55:27 -04:00

197 lines
6.6 KiB
Python

"""Functional tests for timmy.tools — tool tracking, persona toolkits, catalog.
Covers tool usage statistics, persona-to-toolkit mapping, catalog generation,
and graceful degradation when Agno is unavailable.
"""
import pytest
from timmy.tools import (
_TOOL_USAGE,
PERSONA_TOOLKITS,
_track_tool_usage,
get_all_available_tools,
get_tool_stats,
get_tools_for_persona,
)
@pytest.fixture(autouse=True)
def clear_usage():
"""Clear tool usage tracking between tests."""
_TOOL_USAGE.clear()
yield
_TOOL_USAGE.clear()
# ── Tool usage tracking ──────────────────────────────────────────────────────
class TestToolTracking:
def test_track_creates_agent_entry(self):
_track_tool_usage("agent-1", "web_search", success=True)
assert "agent-1" in _TOOL_USAGE
assert len(_TOOL_USAGE["agent-1"]) == 1
def test_track_records_metadata(self):
_track_tool_usage("agent-1", "shell", success=False)
entry = _TOOL_USAGE["agent-1"][0]
assert entry["tool"] == "shell"
assert entry["success"] is False
assert "timestamp" in entry
def test_track_multiple_calls(self):
_track_tool_usage("a1", "search")
_track_tool_usage("a1", "read")
_track_tool_usage("a1", "search")
assert len(_TOOL_USAGE["a1"]) == 3
def test_track_multiple_agents(self):
_track_tool_usage("a1", "search")
_track_tool_usage("a2", "shell")
assert len(_TOOL_USAGE) == 2
class TestGetToolStats:
def test_stats_for_specific_agent(self):
_track_tool_usage("a1", "search")
_track_tool_usage("a1", "read")
_track_tool_usage("a1", "search")
stats = get_tool_stats("a1")
assert stats["agent_id"] == "a1"
assert stats["total_calls"] == 3
assert set(stats["tools_used"]) == {"search", "read"}
assert len(stats["recent_calls"]) == 3
def test_stats_for_unknown_agent(self):
stats = get_tool_stats("nonexistent")
assert stats["total_calls"] == 0
assert stats["tools_used"] == []
assert stats["recent_calls"] == []
def test_stats_recent_capped_at_10(self):
for i in range(15):
_track_tool_usage("a1", f"tool_{i}")
stats = get_tool_stats("a1")
assert len(stats["recent_calls"]) == 10
def test_stats_all_agents(self):
_track_tool_usage("a1", "search")
_track_tool_usage("a2", "shell")
_track_tool_usage("a2", "read")
stats = get_tool_stats()
assert "a1" in stats
assert "a2" in stats
assert stats["a1"]["total_calls"] == 1
assert stats["a2"]["total_calls"] == 2
def test_stats_empty(self):
stats = get_tool_stats()
assert stats == {}
# ── Persona toolkit mapping ──────────────────────────────────────────────────
class TestPersonaToolkits:
def test_all_expected_personas_present(self):
expected = {
"echo",
"mace",
"helm",
"seer",
"forge",
"quill",
"lab",
"pixel",
"lyra",
"reel",
}
assert set(PERSONA_TOOLKITS.keys()) == expected
def test_get_tools_for_known_persona_returns_toolkit(self):
"""Known personas should return a Toolkit with registered tools."""
result = get_tools_for_persona("echo")
assert result is not None
def test_get_tools_for_unknown_persona(self):
result = get_tools_for_persona("nonexistent")
assert result is None
def test_creative_personas_return_toolkit(self):
"""Creative personas (pixel, lyra, reel) return toolkits."""
for persona_id in ("pixel", "lyra", "reel"):
result = get_tools_for_persona(persona_id)
assert result is not None
# ── Tool catalog ─────────────────────────────────────────────────────────────
class TestToolCatalog:
def test_catalog_contains_base_tools(self):
catalog = get_all_available_tools()
base_tools = {
"web_search",
"shell",
"python",
"read_file",
"write_file",
"list_files",
}
for tool_id in base_tools:
assert tool_id in catalog, f"Missing base tool: {tool_id}"
def test_catalog_tool_structure(self):
catalog = get_all_available_tools()
for tool_id, info in catalog.items():
assert "name" in info, f"{tool_id} missing 'name'"
assert "description" in info, f"{tool_id} missing 'description'"
assert "available_in" in info, f"{tool_id} missing 'available_in'"
assert isinstance(info["available_in"], list)
def test_catalog_orchestrator_has_all_base_tools(self):
catalog = get_all_available_tools()
base_tools = {
"web_search",
"shell",
"python",
"read_file",
"write_file",
"list_files",
}
for tool_id in base_tools:
assert "orchestrator" in catalog[tool_id]["available_in"], (
f"Orchestrator missing tool: {tool_id}"
)
def test_catalog_echo_research_tools(self):
catalog = get_all_available_tools()
assert "echo" in catalog["web_search"]["available_in"]
assert "echo" in catalog["read_file"]["available_in"]
# Echo should NOT have shell
assert "echo" not in catalog["shell"]["available_in"]
def test_catalog_forge_code_tools(self):
catalog = get_all_available_tools()
assert "forge" in catalog["shell"]["available_in"]
assert "forge" in catalog["python"]["available_in"]
assert "forge" in catalog["write_file"]["available_in"]
def test_catalog_forge_has_aider(self):
"""Verify Aider AI tool is available in Forge's toolkit."""
catalog = get_all_available_tools()
assert "aider" in catalog
assert "forge" in catalog["aider"]["available_in"]
assert "orchestrator" in catalog["aider"]["available_in"]
class TestAiderTool:
"""Test the Aider AI coding assistant tool."""
def test_aider_in_tool_catalog(self):
"""Verify Aider appears in the tool catalog."""
catalog = get_all_available_tools()
assert "aider" in catalog
assert "forge" in catalog["aider"]["available_in"]