This repository has been archived on 2026-03-24.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

231 lines
8.0 KiB
Python
Raw Normal View History

"""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", "calculator", 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 = {
"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}"
# web_search removed — dead code, ddgs never installed (#87)
assert "web_search" not in catalog
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)
Claude/remove persona system f vgt m (#126) * Remove persona system, identity, and all Timmy references Strip the codebase to pure orchestration logic: - Delete TIMMY_IDENTITY.md and memory/self/identity.md - Gut brain/identity.py to no-op stubs (empty returns) - Remove all system prompts reinforcing Timmy's character, faith, sovereignty, sign-off ("Sir, affirmative"), and agent roster - Replace identity-laden prompts with generic local-AI-assistant prompts - Remove "You work for Timmy" from all sub-agent system prompts - Rename PersonaTools → AgentTools, PERSONA_TOOLKITS → AGENT_TOOLKITS - Replace "timmy" agent ID with "orchestrator" across routes, marketplace, tools catalog, and orchestrator class - Strip Timmy references from config comments, templates, telegram bot, chat API, and dashboard UI - Delete tests/brain/test_identity.py entirely - Fix all test assertions that checked for persona identity content 729 tests pass (2 pre-existing failures in test_calm.py unrelated). https://claude.ai/code/session_01LjQGUE6nk9W9674zaxrYxy * Add Taskosaur (PM + AI task execution) to docker-compose Spins up Taskosaur alongside the dashboard on `docker compose up`: - postgres:16-alpine (port 5432, Taskosaur DB) - redis:7-alpine (Bull queue backend) - taskosaur (ports 3000 API / 3001 UI) - dashboard now depends_on taskosaur healthy - TASKOSAUR_API_URL injected into dashboard environment Dashboard can reach Taskosaur at http://taskosaur:3000/api on the internal network. Frontend UI accessible at http://localhost:3001. https://claude.ai/code/session_01LjQGUE6nk9W9674zaxrYxy --------- Co-authored-by: Claude <noreply@anthropic.com>
2026-03-04 12:00:49 -05:00
def test_catalog_orchestrator_has_all_base_tools(self):
catalog = get_all_available_tools()
base_tools = {
"shell",
"python",
"read_file",
"write_file",
"list_files",
}
for tool_id in base_tools:
ruff (#169) * polish: streamline nav, extract inline styles, improve tablet UX - Restructure desktop nav from 8+ flat links + overflow dropdown into 5 grouped dropdowns (Core, Agents, Intel, System, More) matching the mobile menu structure to reduce decision fatigue - Extract all inline styles from mission_control.html and base.html notification elements into mission-control.css with semantic classes - Replace JS-built innerHTML with secure DOM construction in notification loader and chat history - Add CONNECTING state to connection indicator (amber) instead of showing OFFLINE before WebSocket connects - Add tablet breakpoint (1024px) with larger touch targets for Apple Pencil / stylus use and safe-area padding for iPad toolbar - Add active-link highlighting in desktop dropdown menus - Rename "Mission Control" page title to "System Overview" to disambiguate from the chat home page - Add "Home — Timmy Time" page title to index.html https://claude.ai/code/session_015uPUoKyYa8M2UAcyk5Gt6h * fix(security): move auth-gate credentials to environment variables Hardcoded username, password, and HMAC secret in auth-gate.py replaced with os.environ lookups. Startup now refuses to run if any variable is unset. Added AUTH_GATE_SECRET/USER/PASS to .env.example. https://claude.ai/code/session_015uPUoKyYa8M2UAcyk5Gt6h * refactor(tooling): migrate from black+isort+bandit to ruff Replace three separate linting/formatting tools with a single ruff invocation. Updates tox.ini (lint, format, pre-push, pre-commit envs), .pre-commit-config.yaml, and CI workflow. Fixes all ruff errors including unused imports, missing raise-from, and undefined names. Ruff config maps existing bandit skips to equivalent S-rules. https://claude.ai/code/session_015uPUoKyYa8M2UAcyk5Gt6h --------- Co-authored-by: Claude <noreply@anthropic.com>
2026-03-11 12:23:35 -04:00
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["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"]
Claude/remove persona system f vgt m (#126) * Remove persona system, identity, and all Timmy references Strip the codebase to pure orchestration logic: - Delete TIMMY_IDENTITY.md and memory/self/identity.md - Gut brain/identity.py to no-op stubs (empty returns) - Remove all system prompts reinforcing Timmy's character, faith, sovereignty, sign-off ("Sir, affirmative"), and agent roster - Replace identity-laden prompts with generic local-AI-assistant prompts - Remove "You work for Timmy" from all sub-agent system prompts - Rename PersonaTools → AgentTools, PERSONA_TOOLKITS → AGENT_TOOLKITS - Replace "timmy" agent ID with "orchestrator" across routes, marketplace, tools catalog, and orchestrator class - Strip Timmy references from config comments, templates, telegram bot, chat API, and dashboard UI - Delete tests/brain/test_identity.py entirely - Fix all test assertions that checked for persona identity content 729 tests pass (2 pre-existing failures in test_calm.py unrelated). https://claude.ai/code/session_01LjQGUE6nk9W9674zaxrYxy * Add Taskosaur (PM + AI task execution) to docker-compose Spins up Taskosaur alongside the dashboard on `docker compose up`: - postgres:16-alpine (port 5432, Taskosaur DB) - redis:7-alpine (Bull queue backend) - taskosaur (ports 3000 API / 3001 UI) - dashboard now depends_on taskosaur healthy - TASKOSAUR_API_URL injected into dashboard environment Dashboard can reach Taskosaur at http://taskosaur:3000/api on the internal network. Frontend UI accessible at http://localhost:3001. https://claude.ai/code/session_01LjQGUE6nk9W9674zaxrYxy --------- Co-authored-by: Claude <noreply@anthropic.com>
2026-03-04 12:00:49 -05:00
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"]
class TestFullToolkitConfirmationWarning:
"""Regression tests for issue #79 — confirmation tool WARNING spam."""
def test_create_full_toolkit_no_confirmation_warning(self, caplog):
"""create_full_toolkit should not emit 'Requires confirmation tool(s)' warnings.
Agno's Toolkit.__init__ validates requires_confirmation_tools against the
initial (empty) tool list. We set the attribute *after* construction to
avoid the spurious warning while keeping per-tool confirmation checks.
"""
import logging
from timmy.tools import create_full_toolkit
with caplog.at_level(logging.WARNING):
create_full_toolkit()
warning_msgs = [
r.message for r in caplog.records if "Requires confirmation tool" in r.message
]
assert warning_msgs == [], f"Unexpected confirmation warnings: {warning_msgs}"
def test_dangerous_tools_listed_for_confirmation(self):
"""After the fix, the toolkit still carries the full DANGEROUS_TOOLS list
so Agno can gate execution at runtime."""
from timmy.tool_safety import DANGEROUS_TOOLS
from timmy.tools import create_full_toolkit
toolkit = create_full_toolkit()
if toolkit is None:
pytest.skip("Agno tools not available")
assert set(toolkit.requires_confirmation_tools) == set(DANGEROUS_TOOLS)