refactor: Phase 3 — reorganize tests into module-mirroring subdirectories

Move 97 test files from flat tests/ into 13 subdirectories:
  tests/dashboard/   (8 files — routes, mobile, mission control)
  tests/swarm/       (17 files — coordinator, docker, routing, tasks)
  tests/timmy/       (12 files — agent, backends, CLI, tools)
  tests/self_coding/  (14 files — git safety, indexer, self-modify)
  tests/lightning/   (3 files — L402, LND, interface)
  tests/creative/    (8 files — assembler, director, image/music/video)
  tests/integrations/ (10 files — chat bridge, telegram, voice, websocket)
  tests/mcp/         (4 files — bootstrap, discovery, executor)
  tests/spark/       (3 files — engine, tools, events)
  tests/hands/       (3 files — registry, oracle, phase5)
  tests/scripture/   (1 file)
  tests/infrastructure/ (3 files — router cascade, API)
  tests/security/    (3 files — XSS, regression)

Fix Path(__file__) reference in test_mobile_scenarios.py for new depth.
Add __init__.py to all test subdirectories.

Tests: 1503 passed, 9 failed (pre-existing), 53 errors (pre-existing)

https://claude.ai/code/session_019oMFNvD8uSGSSmBMGkBfQN

tests/self_coding/test_watchdog.py

@@ -0,0 +1,54 @@
+from unittest.mock import MagicMock, patch
+
+from self_tdd.watchdog import _run_tests
+
+
+def _mock_result(returncode: int, stdout: str = "", stderr: str = "") -> MagicMock:
+    m = MagicMock()
+    m.returncode = returncode
+    m.stdout = stdout
+    m.stderr = stderr
+    return m
+
+
+def test_run_tests_returns_true_when_suite_passes():
+    with patch("self_tdd.watchdog.subprocess.run", return_value=_mock_result(0, "5 passed")):
+        passed, _ = _run_tests()
+    assert passed is True
+
+
+def test_run_tests_returns_false_when_suite_fails():
+    with patch("self_tdd.watchdog.subprocess.run", return_value=_mock_result(1, "1 failed")):
+        passed, _ = _run_tests()
+    assert passed is False
+
+
+def test_run_tests_output_includes_stdout():
+    with patch("self_tdd.watchdog.subprocess.run", return_value=_mock_result(0, stdout="5 passed")):
+        _, output = _run_tests()
+    assert "5 passed" in output
+
+
+def test_run_tests_output_combines_stdout_and_stderr():
+    with patch(
+        "self_tdd.watchdog.subprocess.run",
+        return_value=_mock_result(1, stdout="FAILED test_foo", stderr="ImportError: no module named bar"),
+    ):
+        _, output = _run_tests()
+    assert "FAILED test_foo" in output
+    assert "ImportError" in output
+
+
+def test_run_tests_invokes_pytest_with_correct_flags():
+    with patch("self_tdd.watchdog.subprocess.run", return_value=_mock_result(0)) as mock_run:
+        _run_tests()
+    cmd = mock_run.call_args[0][0]
+    assert "pytest" in cmd
+    assert "tests/" in cmd
+    assert "--tb=short" in cmd
+
+
+def test_run_tests_uses_60s_timeout():
+    with patch("self_tdd.watchdog.subprocess.run", return_value=_mock_result(0)) as mock_run:
+        _run_tests()
+    assert mock_run.call_args.kwargs["timeout"] == 60