forked from Rockachopa/Timmy-time-dashboard
36fc10097f
* 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>
47 lines
2.0 KiB
Python
47 lines
2.0 KiB
Python
"""Tests for the experiments dashboard route."""
|
|
|
|
from unittest.mock import patch
|
|
|
|
|
|
class TestExperimentsRoute:
|
|
"""Tests for /experiments endpoints."""
|
|
|
|
def test_experiments_page_returns_200(self, client):
|
|
response = client.get("/experiments")
|
|
assert response.status_code == 200
|
|
assert "Autoresearch" in response.text
|
|
|
|
@patch("dashboard.routes.experiments.settings")
|
|
def test_experiments_page_shows_disabled_when_off(self, mock_settings, client):
|
|
mock_settings.autoresearch_enabled = False
|
|
mock_settings.autoresearch_metric = "perplexity"
|
|
mock_settings.autoresearch_time_budget = 300
|
|
mock_settings.autoresearch_max_iterations = 10
|
|
mock_settings.repo_root = "/tmp"
|
|
mock_settings.autoresearch_workspace = "test-experiments"
|
|
response = client.get("/experiments")
|
|
assert response.status_code == 200
|
|
assert "disabled" in response.text.lower() or "Disabled" in response.text
|
|
|
|
@patch("dashboard.routes.experiments.settings")
|
|
def test_start_experiment_when_disabled(self, mock_settings, client):
|
|
mock_settings.autoresearch_enabled = False
|
|
response = client.post("/experiments/start")
|
|
assert response.status_code == 403
|
|
|
|
def test_experiment_detail_not_found(self, client):
|
|
response = client.get("/experiments/nonexistent-id")
|
|
assert response.status_code == 404
|
|
|
|
@patch("dashboard.routes.experiments.settings")
|
|
@patch("timmy.autoresearch.subprocess.run")
|
|
def test_start_experiment_when_enabled(self, mock_run, mock_settings, client):
|
|
mock_settings.autoresearch_enabled = True
|
|
mock_settings.repo_root = "/tmp"
|
|
mock_settings.autoresearch_workspace = "test-experiments"
|
|
mock_run.return_value = type("R", (), {"returncode": 0, "stdout": "", "stderr": ""})()
|
|
response = client.post("/experiments/start")
|
|
assert response.status_code == 200
|
|
data = response.json()
|
|
assert data["status"] == "started"
|