Files
Timmy-time-dashboard/tests/test_agentic_loop.py
Alexander Whitestone 9d78eb31d1 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

241 lines
7.7 KiB
Python

"""Unit tests for the agentic loop module.
Tests cover planning, execution, max_steps enforcement, failure
adaptation, progress callbacks, and response cleaning.
"""
from unittest.mock import AsyncMock, MagicMock, patch
import pytest
from timmy.agentic_loop import _parse_steps, run_agentic_loop
# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------
def _mock_run(content: str):
"""Create a mock return value for agent.run()."""
m = MagicMock()
m.content = content
return m
# ---------------------------------------------------------------------------
# _parse_steps
# ---------------------------------------------------------------------------
class TestParseSteps:
def test_numbered_with_dot(self):
text = "1. Search for data\n2. Write to file\n3. Verify"
assert _parse_steps(text) == ["Search for data", "Write to file", "Verify"]
def test_numbered_with_paren(self):
text = "1) Read config\n2) Update value\n3) Restart"
assert _parse_steps(text) == ["Read config", "Update value", "Restart"]
def test_fallback_plain_lines(self):
text = "Search the web\nWrite results\nDone"
assert _parse_steps(text) == ["Search the web", "Write results", "Done"]
def test_empty_returns_empty(self):
assert _parse_steps("") == []
# ---------------------------------------------------------------------------
# run_agentic_loop
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_planning_phase_produces_steps():
"""Planning prompt returns numbered step list."""
mock_agent = MagicMock()
mock_agent.run = MagicMock(
side_effect=[
_mock_run("1. Search AI news\n2. Write to file\n3. Verify"),
_mock_run("Found 5 articles about AI."),
_mock_run("Wrote summary to /tmp/ai_news.md"),
_mock_run("File verified, 15 lines."),
_mock_run("Searched, wrote, verified."),
]
)
with (
patch("timmy.agentic_loop._get_loop_agent", return_value=mock_agent),
patch("timmy.agentic_loop._broadcast_progress", new_callable=AsyncMock),
):
result = await run_agentic_loop("Search AI news and write summary")
assert result.status == "completed"
assert len(result.steps) == 3
@pytest.mark.asyncio
async def test_loop_executes_all_steps():
"""Loop calls agent.run() for plan + each step + summary."""
mock_agent = MagicMock()
mock_agent.run = MagicMock(
side_effect=[
_mock_run("1. Do A\n2. Do B"),
_mock_run("A done"),
_mock_run("B done"),
_mock_run("All done"),
]
)
with (
patch("timmy.agentic_loop._get_loop_agent", return_value=mock_agent),
patch("timmy.agentic_loop._broadcast_progress", new_callable=AsyncMock),
):
result = await run_agentic_loop("Do A and B")
# plan + 2 steps + summary = 4 calls
assert mock_agent.run.call_count == 4
assert len(result.steps) == 2
@pytest.mark.asyncio
async def test_loop_respects_max_steps():
"""Loop stops at max_steps and returns status='partial'."""
mock_agent = MagicMock()
mock_agent.run = MagicMock(
side_effect=[
_mock_run("1. A\n2. B\n3. C\n4. D\n5. E"),
_mock_run("A done"),
_mock_run("B done"),
_mock_run("Completed 2 of 5 steps."),
]
)
with (
patch("timmy.agentic_loop._get_loop_agent", return_value=mock_agent),
patch("timmy.agentic_loop._broadcast_progress", new_callable=AsyncMock),
):
result = await run_agentic_loop("Do 5 things", max_steps=2)
assert len(result.steps) == 2
assert result.status == "partial"
@pytest.mark.asyncio
async def test_failure_triggers_adaptation():
"""Failed step feeds error back to model, step marked as adapted."""
mock_agent = MagicMock()
mock_agent.run = MagicMock(
side_effect=[
_mock_run("1. Read config\n2. Update setting\n3. Verify"),
_mock_run("Config: timeout=30"),
Exception("Permission denied"),
_mock_run("Adapted: wrote to ~/config.yaml instead"),
_mock_run("Verified: timeout=60"),
_mock_run("Updated config via alternative path."),
]
)
with (
patch("timmy.agentic_loop._get_loop_agent", return_value=mock_agent),
patch("timmy.agentic_loop._broadcast_progress", new_callable=AsyncMock),
):
result = await run_agentic_loop("Update config timeout to 60")
assert result.status == "completed"
assert any(s.status == "adapted" for s in result.steps)
@pytest.mark.asyncio
async def test_progress_callback_fires():
"""on_progress called for each step completion."""
events = []
async def on_progress(desc, step, total):
events.append((step, total))
mock_agent = MagicMock()
mock_agent.run = MagicMock(
side_effect=[
_mock_run("1. Do A\n2. Do B"),
_mock_run("A done"),
_mock_run("B done"),
_mock_run("All done"),
]
)
with (
patch("timmy.agentic_loop._get_loop_agent", return_value=mock_agent),
patch("timmy.agentic_loop._broadcast_progress", new_callable=AsyncMock),
):
await run_agentic_loop("Do A and B", on_progress=on_progress)
assert len(events) == 2
assert events[0] == (1, 2)
assert events[1] == (2, 2)
@pytest.mark.asyncio
async def test_result_contains_step_metadata():
"""AgenticResult.steps has status and duration per step."""
mock_agent = MagicMock()
mock_agent.run = MagicMock(
side_effect=[
_mock_run("1. Search\n2. Write"),
_mock_run("Found results"),
_mock_run("Written to file"),
_mock_run("Done"),
]
)
with (
patch("timmy.agentic_loop._get_loop_agent", return_value=mock_agent),
patch("timmy.agentic_loop._broadcast_progress", new_callable=AsyncMock),
):
result = await run_agentic_loop("Search and write")
for step in result.steps:
assert step.status in ("completed", "failed", "adapted")
assert step.duration_ms >= 0
assert step.description
assert step.result
@pytest.mark.asyncio
async def test_config_default_used():
"""When max_steps=0, uses settings.max_agent_steps."""
mock_agent = MagicMock()
# Return more steps than default config allows (10)
steps_text = "\n".join(f"{i}. Step {i}" for i in range(1, 15))
side_effects = [_mock_run(steps_text)]
# 10 step results + summary
for i in range(1, 11):
side_effects.append(_mock_run(f"Step {i} done"))
side_effects.append(_mock_run("Summary"))
mock_agent.run = MagicMock(side_effect=side_effects)
with (
patch("timmy.agentic_loop._get_loop_agent", return_value=mock_agent),
patch("timmy.agentic_loop._broadcast_progress", new_callable=AsyncMock),
):
result = await run_agentic_loop("Do 14 things", max_steps=0)
# Should be capped at 10 (config default)
assert len(result.steps) == 10
@pytest.mark.asyncio
async def test_planning_failure_returns_failed():
"""If the planning phase fails, result.status is 'failed'."""
mock_agent = MagicMock()
mock_agent.run = MagicMock(side_effect=Exception("Model offline"))
with (
patch("timmy.agentic_loop._get_loop_agent", return_value=mock_agent),
patch("timmy.agentic_loop._broadcast_progress", new_callable=AsyncMock),
):
result = await run_agentic_loop("Do something")
assert result.status == "failed"
assert "Planning failed" in result.summary