fix(phase2): restore agent streams and persist extension installations

backend/tests/test_acceptance.py

@@ -0,0 +1,33 @@
+import pytest
+from app.acceptance import score
+
+
+def segment(text, speaker='A', start=0, end=1):
+    return dict(text=text, speaker=speaker, start=start, end=end)
+
+
+def test_exact_and_renamed_speakers():
+    result = score([segment('你好 世界')], [segment('你好 世界', 'cluster_4')])
+    assert result['text']['cer']['rate'] == 0
+    assert result['speaker']['der'] == 0
+    assert result['quality_gate'] == 'not_evaluated'
+
+
+def test_edits_missed_and_false_alarms():
+    result = score([segment('a b')], [segment('a c', start=0, end=2)])
+    assert result['text']['wer']['rate'] == 0.5
+    assert result['speaker']['false_alarm_seconds'] == 1
+    result = score([segment('a')], [])
+    assert result['speaker']['der'] == 1
+
+
+def test_overlap_and_confusion():
+    result = score([segment('a'), segment('b', 'B')], [segment('a')])
+    assert result['speaker']['der'] == 0.5
+    result = score([segment('a'), segment('b','B',1,2)], [segment('a','X',0,2)])
+    assert result['speaker']['confusion_seconds'] == 1
+
+
+def test_requires_reference_and_valid_timing():
+    with pytest.raises(ValueError): score([], [])
+    with pytest.raises(ValueError): score([segment('a', end=float('nan'))], [])

backend/tests/test_installed_extensions.py

@@ -0,0 +1,68 @@
+from pathlib import Path
+import pytest
+from app.agent.tools import ToolRegistry
+from app.extensions import SkillRuntime
+from app.extensions.installed import InstalledRuntime
+
+
+def package(root):
+    root.mkdir(parents=True)
+    (root / 'skill.yaml').write_text('skill_id: audit\nname: Audit\nversion: 1.0.0\npermissions: []\ntools: []\n', encoding='utf-8')
+    return root
+
+
+def runtime(data):
+    return InstalledRuntime(SkillRuntime(ToolRegistry()), 'skill', data)
+
+
+def test_restores_enabled_and_disabled_without_deleting_directory_install(tmp_path):
+    root = package(tmp_path / 'user-source')
+    data = tmp_path / 'data'
+    first = runtime(data); first.install(root); first.enable('audit')
+    second = runtime(data); second.restore()
+    assert second.get('audit').enabled
+    second.disable('audit')
+    third = runtime(data); third.restore()
+    assert not third.get('audit').enabled
+    third.uninstall('audit')
+    assert root.exists()
+    fourth = runtime(data); fourth.restore()
+    assert fourth.list() == []
+
+
+def test_owned_zip_removed_and_changed_packages_not_auto_enabled(tmp_path):
+    data = tmp_path / 'data'
+    owned = data / 'extension-packages/skill-test'
+    root = package(owned / 'nested')
+    first = runtime(data); first.install(root, managed_root=owned); first.enable('audit')
+    (root / 'prompt.md').write_text('changed', encoding='utf-8')
+    first.disable('audit')
+    with pytest.raises(Exception, match='Package changed'):
+        first.enable('audit')
+    second = runtime(data); second.restore()
+    assert second.list() == []
+    assert second.restore_errors[0]['id'] == 'audit'
+    first.uninstall('audit')
+    assert not owned.exists()
+
+
+def test_rejects_claiming_user_directory_as_managed(tmp_path):
+    root = package(tmp_path / 'source')
+    with pytest.raises(ValueError, match='managed'):
+        runtime(tmp_path / 'data').install(root, managed_root=root)
+    assert root.exists()
+
+
+def test_builtin_disabled_plugin_does_not_break_startup():
+    from app.container import build_container
+    first = build_container()
+    first.plugins.disable('text-tools')
+    second = build_container()
+    assert not second.plugins.get('text-tools').enabled
+    assert second.skills.get('knowledge-assistant').missing_dependencies
+    second.plugins.enable('text-tools')
+    third = build_container()
+    assert third.plugins.get('text-tools').enabled
+    assert third.skills.get('knowledge-assistant').enabled
+    for container in (first, second, third):
+        container.plugins.shutdown(); container.mcp_servers.shutdown()