Merge remote-tracking branch 'origin/main' into feat/export-service

# Conflicts:
#	backend/app/routes.py

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_community_packages.py

@@ -0,0 +1,67 @@
+import asyncio
+import importlib.util
+from pathlib import Path
+
+import pytest
+
+from app.config import BACKEND_DIR
+from app.container import build_container
+from app.contracts import ModelCapability, PluginCommandContext, ToolCall
+from app.agent.tools import ToolExecutionContext
+from app.extensions.archive import install_zip
+
+ROOT = BACKEND_DIR / 'extensions/community'
+
+
+def load(path):
+    spec = importlib.util.spec_from_file_location(path.stem, path)
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    return module
+
+
+def test_analysis_ignores_metadata_and_code_and_keeps_line_numbers():
+    server = load(ROOT / 'plugins/markdown-workbench/server.py')
+    sample = (ROOT / 'plugins/markdown-workbench/example.md').read_text(encoding='utf-8')
+    report = server.inspect_markdown(sample)
+    assert report['summary']['headings'] == 3
+    assert report['summary']['tasks'] == 2
+    assert report['summary']['open_tasks'] == 1
+    assert [(item['line'], item['code']) for item in report['issues']] == [(7, 'heading_jump'), (11, 'duplicate_heading')]
+    assert report['tasks'][0]['line'] == 8
+    assert server.inspect_markdown('Title\n===\n\nSubtitle\n---')['summary']['headings'] == 2
+    assert server.inspect_markdown('```\n# code')['issues'][0]['code'] == 'unclosed_fence'
+    with pytest.raises(ValueError):
+        server.inspect_markdown('x' * 100001)
+    many = server.inspect_markdown('\n'.join('- [ ] task' for _ in range(205)))
+    assert many['truncated'] and many['summary']['tasks'] == 205 and len(many['tasks']) == 200
+
+
+def test_zip_install_real_mcp_tool_command_and_skill(tmp_path):
+    builder = load(ROOT / 'build_packages.py')
+    output = tmp_path / 'dist'
+    catalog = builder.build(output)
+    assert builder.build(output) == catalog
+    runtime = build_container()
+    sample = (ROOT / 'plugins/markdown-workbench/example.md').read_text(encoding='utf-8')
+    async def run():
+        plugin = install_zip((output / 'markdown-workbench-1.0.0.zip').read_bytes(), 'plugin', tmp_path / 'installed', runtime.plugins.install)
+        assert not plugin.enabled
+        skill = install_zip((output / 'note-reviewer-1.0.0.zip').read_bytes(), 'skill', tmp_path / 'installed', runtime.skills.install)
+        assert 'markdown-workbench.inspect_markdown' in skill.missing_dependencies
+        assert runtime.plugins.enable('markdown-workbench').status == 'ready'
+        result = await runtime.tools.execute(ToolCall(tool_call_id='community-test', name='markdown-workbench.inspect_markdown', arguments={'text': sample}), ToolExecutionContext(run_id='community-test'))
+        assert result.success, result.error_message
+        assert result.output['summary']['issues'] == 2
+        command = await runtime.plugins.execute_command('markdown-workbench.inspect-selection', {}, PluginCommandContext(selection=sample))
+        assert '1 项未完成任务' in command.effect.payload.message
+        assert runtime.skills.enable('note-reviewer').status == 'ready'
+        config = runtime.skills.build_agent_configuration('note-reviewer', [ModelCapability.chat, ModelCapability.tool_calling])
+        assert 'notes.read' in config.allowed_tools
+        assert '不得改变用户指定的检查范围' in config.system_prompt
+        runtime.plugins.disable('markdown-workbench')
+        assert runtime.skills.get('note-reviewer').status == 'dependency_missing'
+    try:
+        asyncio.run(run())
+    finally:
+        runtime.plugins.shutdown()

backend/tests/test_context_budget.py

@@ -0,0 +1,144 @@
+import asyncio
+from functools import wraps
+from unittest.mock import AsyncMock
+
+import pytest
+from pydantic import ValidationError
+
+from app.contracts import Message, ModelContextPolicy, ModelRequest, ProviderConfig
+from app.providers.base import ProviderError, ProviderTurn
+from app.providers.context_budget import prepare_context
+from app.providers.factory import ProviderFactory
+
+
+def async_test(fn):
+    @wraps(fn)
+    def run(*args, **kwargs):
+        return asyncio.run(fn(*args, **kwargs))
+    return run
+
+
+def config(mode="detect", **kwargs):
+    return ProviderConfig(provider_id="p", provider_type="openai_compatible", name="test",
+        context_policies=[ModelContextPolicy(model="test", context_window=8192, output_reserve=512,
+                                            threshold=0.1, mode=mode, **kwargs)])
+
+
+def request():
+    return ModelRequest(provider_id="p", model="test", system="Keep this system instruction",
+        messages=[Message(role="user", content="旧文本" * 500), Message(role="assistant", content="历史答复"),
+                  Message(role="user", content="继续"), Message(role="assistant", content="近期答复"),
+                  Message(role="user", content="最新问题")])
+
+
+@async_test
+async def test_threshold_detect_blocks_before_network():
+    complete = AsyncMock()
+    with pytest.raises(ProviderError, match="已达到") as error:
+        await prepare_context(request(), config(), complete)
+    assert error.value.code == "CONTEXT_COMPRESSION_REQUIRED"
+    complete.assert_not_called()
+
+
+@async_test
+async def test_compress_preserves_archive_system_and_recent_turns():
+    original = request()
+    copy = original.model_dump()
+    complete = AsyncMock(return_value=ProviderTurn(text="已讨论旧文本。"))
+    prepared = await prepare_context(original, config("compress", prompt="自定义摘要指令"), complete)
+    assert original.model_dump() == copy
+    assert prepared.system == original.system
+    assert prepared.messages[-3:] == original.messages[-3:]
+    assert prepared.max_tokens == 512
+    assert complete.call_args.args[0].system == "自定义摘要指令"
+    assert not complete.call_args.args[0].tools
+
+
+@async_test
+async def test_unknown_model_unmodified():
+    original = request().model_copy(update={"model": "other"})
+    complete = AsyncMock()
+    assert await prepare_context(original, config(), complete) is original
+    complete.assert_not_called()
+
+
+@async_test
+async def test_single_oversize_turn_is_not_discarded():
+    original = request().model_copy(update={"messages": request().messages[:1]})
+    complete = AsyncMock()
+    with pytest.raises(ProviderError, match="没有可压缩"):
+        await prepare_context(original, config("compress"), complete)
+    complete.assert_not_called()
+
+
+@async_test
+async def test_tool_history_is_not_split():
+    original = request()
+    original.messages.insert(2, Message(role="tool", content="result", tool_call_id="call"))
+    complete = AsyncMock()
+    with pytest.raises(ProviderError, match="工具调用历史"):
+        await prepare_context(original, config("compress"), complete)
+    complete.assert_not_called()
+
+
+@async_test
+async def test_ineffective_summary_fails_without_mutation():
+    original = request()
+    copy = original.model_dump()
+    with pytest.raises(ProviderError, match="未缩短"):
+        await prepare_context(original, config("compress"), AsyncMock(return_value=ProviderTurn(text="长" * 6000)))
+    assert original.model_dump() == copy
+
+
+@async_test
+async def test_override_output_budget_is_counted():
+    settings = config()
+    from app.request_overrides import RequestOverride
+    settings.request_overrides = [RequestOverride(body={"max_completion_tokens": 9000})]
+    with pytest.raises(ProviderError, match="占满"):
+        await prepare_context(request(), settings, AsyncMock())
+
+
+@async_test
+async def test_factory_stream_exposes_actionable_error_without_network():
+    adapter = ProviderFactory(None).build(config())
+    events = [event async for event in adapter.stream(request())]
+    assert [e.event.value for e in events] == ["Error", "Done"]
+    assert events[0].data["code"] == "CONTEXT_COMPRESSION_REQUIRED"
+
+
+def test_invalid_and_duplicate_config_rejected():
+    with pytest.raises(ValidationError):
+        ModelContextPolicy(model="test", context_window=1024, output_reserve=1024)
+    settings = config().model_dump()
+    settings["context_policies"] *= 2
+    with pytest.raises(ValidationError, match="同一模型"):
+        ProviderConfig.model_validate(settings)
+
+
+@async_test
+async def test_factory_compression_status_and_usage_request_are_separate(monkeypatch):
+    from datetime import datetime, timezone
+    from app.contracts import ModelEvent, ModelEventType
+    from app.services.usage_service import usage_context
+    seen = []
+
+    class Adapter:
+        async def complete(self, req):
+            seen.append((req, usage_context.get()))
+            return ProviderTurn(text="历史摘要。")
+
+        async def stream(self, req):
+            seen.append((req, usage_context.get()))
+            yield ModelEvent(event=ModelEventType.text_delta, timestamp=datetime.now(timezone.utc), data={"text": "回答"})
+            yield ModelEvent(event=ModelEventType.done, timestamp=datetime.now(timezone.utc), data={"status": "completed"})
+
+    factory = ProviderFactory(None)
+    monkeypatch.setattr(factory, "_build", lambda _: Adapter())
+    adapter = factory.build(config("compress"))
+    original = request()
+    events = [event async for event in adapter.stream(original)]
+    assert [e.event.value for e in events] == ["ContextStatus", "TextDelta", "Done"]
+    assert [e.sequence for e in events] == [0, 1, 2]
+    assert seen[0][1]["request_id"] != seen[1][1]["request_id"]
+    assert seen[1][0].messages[-3:] == original.messages[-3:]

backend/tests/test_extension_archive.py

@@ -0,0 +1,87 @@
+import asyncio
+import io
+import stat
+import zipfile
+
+import pytest
+from starlette.requests import Request
+
+from app.errors import ApiError
+from app.extensions import ExtensionError
+from app.extensions.archive import install_zip
+from app.extensions import archive as module
+
+
+def zipped(files):
+    output = io.BytesIO()
+    with zipfile.ZipFile(output, 'w', zipfile.ZIP_DEFLATED) as archive:
+        for name, value in files:
+            if isinstance(name, str) and '\\' in name:
+                entry = zipfile.ZipInfo()
+                entry.filename = name  # Keep malicious separators on Windows too.
+                name = entry
+            archive.writestr(name, value)
+    return output.getvalue()
+
+
+@pytest.mark.parametrize('kind', ['skill', 'plugin'])
+@pytest.mark.parametrize('prefix', ['', 'package/'])
+def test_install_keeps_package_resources(tmp_path, kind, prefix):
+    data = zipped([(prefix + kind + '.yaml', 'name: test'), (prefix + 'assets/说明.txt', 'hello')])
+    root = install_zip(data, kind, tmp_path, lambda root: root)
+    assert (root / 'assets/说明.txt').read_text() == 'hello'
+
+
+@pytest.mark.parametrize('path', ['../outside', '/outside', 'C:/outside', 'a\\b', 'NUL.txt', 'a/../b', 'a./x'])
+def test_unsafe_paths_rejected_and_cleaned(tmp_path, path):
+    with pytest.raises(ApiError):
+        install_zip(zipped([('skill.yaml', 'name: x'), (path, 'x')]), 'skill', tmp_path, lambda _: pytest.fail('must not install'))
+    assert list(tmp_path.iterdir()) == []
+
+
+def test_links_duplicates_and_size_limits(tmp_path, monkeypatch):
+    link = zipfile.ZipInfo('link')
+    link.create_system = 3
+    link.external_attr = (stat.S_IFLNK | 0o777) << 16
+    cases = [zipped([(link, '../outside')]), zipped([('skill.yaml', 'x'), ('SKILL.yaml', 'x')]), b'not a zip']
+    for data in cases:
+        with pytest.raises(ApiError):
+            install_zip(data, 'skill', tmp_path, lambda _: pytest.fail('must not install'))
+        assert list(tmp_path.iterdir()) == []
+    monkeypatch.setattr(module, 'MAX_EXPANDED_BYTES', 3)
+    with pytest.raises(ApiError, match='50 MiB'):
+        install_zip(zipped([('skill.yaml', 'xxxxx')]), 'skill', tmp_path, lambda _: None)
+    assert list(tmp_path.iterdir()) == []
+
+
+def test_manifest_validation_failure_preserved_and_cleaned(tmp_path):
+    def reject(_):
+        raise ExtensionError('BAD_MANIFEST', 'invalid manifest')
+    with pytest.raises(ExtensionError, match='invalid manifest'):
+        install_zip(zipped([('plugin.yaml', 'x')]), 'plugin', tmp_path, reject)
+    assert list(tmp_path.iterdir()) == []
+    with pytest.raises(ApiError, match='plugin.yaml'):
+        install_zip(zipped([('skill.yaml', 'x')]), 'plugin', tmp_path, reject)
+    assert list(tmp_path.iterdir()) == []
+
+
+@pytest.mark.parametrize('kind', ['skill', 'plugin'])
+def test_upload_route_uses_real_manifest_validation(tmp_path, monkeypatch, kind):
+    from app import routes
+    from app.container import build_container
+    runtime = build_container()
+    monkeypatch.setattr(routes, 'container', runtime)
+    data = zipped([(kind + '.yaml', f'id: zip-example\nname: ZIP example\nversion: 1.0.0\ndescription: test\n')])
+    sent = False
+    async def receive():
+        nonlocal sent
+        assert not sent
+        sent = True
+        return {'type': 'http.request', 'body': data, 'more_body': False}
+    request = Request({'type': 'http', 'method': 'POST', 'headers': []}, receive)
+    try:
+        result = asyncio.run(getattr(routes, f'install_{kind}_zip')(request))
+        assert getattr(result.manifest, kind + '_id') == 'zip-example'
+        assert not result.enabled
+    finally:
+        runtime.plugins.shutdown()

backend/tests/test_global_persona.py

@@ -0,0 +1,48 @@
+import asyncio
+import pytest
+from app.contracts import ModelRequest, Message, ProviderConfig
+from app.errors import ApiError
+from app.services.persona_settings import PersonaSettings, DialoguePair, save_persona, load_persona, apply_global_persona
+
+
+def request():
+    return ModelRequest(provider_id="p", model="test", system="任务要求", messages=[Message(role="user", content="hello")])
+
+
+def test_global_persona_persists_and_keeps_task_prompt():
+    save_persona(PersonaSettings(name="老师", system_prompt="耐心解释", dialogue_pairs=[DialoguePair(user="问题", assistant="回答"), DialoguePair()]))
+    assert load_persona().version == 1
+    original = request()
+    assembled = apply_global_persona(original)
+    assert assembled.system == "任务要求\n\n全局人设 / Global persona\n耐心解释\n\n预设对话示例 / Example dialogue\nUser: 问题\nAssistant: 回答"
+    assert original.system == "任务要求"
+    with pytest.raises(ApiError):
+        save_persona(PersonaSettings())
+
+
+def test_empty_persona_omits_all_global_sections():
+    save_persona(PersonaSettings(system_prompt="  ", dialogue_pairs=[DialoguePair(user=" ")]))
+    assert apply_global_persona(request()).system == "任务要求"
+
+
+def test_existing_provider_reads_latest_global_persona_for_complete_and_stream(monkeypatch):
+    from app.providers.factory import ProviderFactory
+    from app.providers.base import ProviderTurn
+    seen = []
+    class Adapter:
+        async def complete(self, req):
+            seen.append(req.system)
+            return ProviderTurn(text="ok")
+        async def stream(self, req):
+            seen.append(req.system)
+            if False: yield
+    factory = ProviderFactory(None)
+    monkeypatch.setattr(factory, "_build", lambda _: Adapter())
+    adapter = factory.build(ProviderConfig(provider_id="p",name="test",provider_type="openai_compatible"))
+    save_persona(PersonaSettings(system_prompt="全局人设"))
+    async def run():
+        await adapter.complete(request())
+        async for _ in adapter.stream(request()): pass
+    asyncio.run(run())
+    assert len(seen) == 2
+    assert all(text.count("全局人设 / Global persona") == 1 for text in seen)

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()

backend/tests/test_large_local_media.py

@@ -0,0 +1,69 @@
+import asyncio
+import sys
+from contextlib import nullcontext
+from types import SimpleNamespace
+
+import pytest
+
+from app.errors import ApiError
+from app.providers.routing import ModelRoutingService, MAX_LOCAL_MEDIA_BYTES, MAX_MEDIA_BYTES, RoutedTranscript
+from app.services import transcription_service as jobs
+from app.config import get_settings
+
+
+def test_large_media_requires_local_only_and_respects_size_limit():
+    path = get_settings().attachments_path / 'large.mp3'
+    path.parent.mkdir(parents=True, exist_ok=True)
+    with path.open('wb') as file:
+        file.truncate(MAX_MEDIA_BYTES + 1)
+    with pytest.raises(ApiError):
+        ModelRoutingService._media_file(path)
+    with ModelRoutingService._media_file(path, local_only=True):
+        pass
+    with pytest.raises(ApiError):
+        asyncio.run(jobs.create_transcription('large.mp3', local_only=False))
+    with path.open('wb') as file:
+        file.truncate(MAX_LOCAL_MEDIA_BYTES + 1)
+    with pytest.raises(ApiError):
+        ModelRoutingService._media_file(path, local_only=True)
+
+
+def test_decode_recovers_one_corrupt_packet_without_shifting_following_audio(monkeypatch):
+    from app.local_models.worker import decode
+    class Samples(list):
+        def reshape(self, *_): return self
+        def astype(self, *_): return self
+        def to_ndarray(self): return self
+    class InvalidDataError(Exception): pass
+    def broken(): raise InvalidDataError()
+    packets = [SimpleNamespace(decode=lambda: [Samples([1] * 3200)]),
+               SimpleNamespace(decode=broken, duration=100, time_base=.001),
+               SimpleNamespace(decode=lambda: [Samples([2] * 3200)])]
+    container = SimpleNamespace(streams=SimpleNamespace(audio=[1]), demux=lambda **_: iter(packets))
+    fake_av = SimpleNamespace(open=lambda *_a, **_kw: nullcontext(container),
+        error=SimpleNamespace(InvalidDataError=InvalidDataError),
+        AudioResampler=lambda **_: SimpleNamespace(resample=lambda frame: [] if frame is None else [frame]))
+    fake_numpy = SimpleNamespace(float32=float, zeros=lambda count, **_: Samples([0] * count),
+        concatenate=lambda frames: Samples(value for frame in frames for value in frame),
+        isfinite=lambda _: SimpleNamespace(all=lambda: True))
+    monkeypatch.setitem(sys.modules, 'av', fake_av)
+    monkeypatch.setitem(sys.modules, 'numpy', fake_numpy)
+    warnings = []
+    output = decode('test.mp3', warnings=warnings)
+    assert output == [1] * 3200 + [0] * 1600 + [2] * 3200
+    assert warnings == ['MEDIA_CORRUPT_PACKETS_SKIPPED:1']
+    with pytest.raises(ValueError, match='one hour'):
+        decode('test.mp3', limit_seconds=.25)
+
+
+def test_decode_warning_reaches_persisted_job(monkeypatch):
+    from app.container import container
+    path = get_settings().attachments_path / 'audio.mp3'
+    path.parent.mkdir(parents=True, exist_ok=True)
+    path.write_bytes(b'audio')
+    async def transcribe(*_args, **_kwargs):
+        return RoutedTranscript(text='decoded', source='local', warnings=['MEDIA_CORRUPT_PACKETS_SKIPPED:1'])
+    monkeypatch.setattr(container.model_routing, 'transcribe', transcribe)
+    job = asyncio.run(jobs.create_transcription('audio.mp3', local_only=True))
+    assert job.status == 'completed'
+    assert jobs.require_job(job.job_id).warnings == ['MEDIA_CORRUPT_PACKETS_SKIPPED:1']

backend/tests/test_usage_overrides.py

@@ -92,3 +92,41 @@ def test_real_adapter_body_and_usage_persistence():
     result = summary()
     assert result["request_count"] == 1 and result["totals"]["input_tokens"] == 10
     assert result["complete_requests"] == 1
+
+
+def test_usage_calendar_series_splits_sources_and_preserves_missing_counters():
+    start = datetime(2026, 9, 1, tzinfo=timezone.utc)
+    for source, hour, count in [('local', 15, 0), ('api', 16, 12), ('api', 17, None)]:
+        attempt = UsageAttempt('p', 'm', 'openai_compatible', source=source)
+        attempt.started_at = (start + timedelta(hours=hour)).isoformat()
+        if count is not None:
+            attempt.observe({'usage': {'input_tokens': count}})
+        attempt.persist()
+    result = aggregate(start, start + timedelta(days=2), timezone_offset=480)
+    assert result['series'][0]['local']['totals']['input_tokens'] == 0
+    second = result['series'][1]
+    assert second['date'] == '2026-09-02'
+    assert second['api']['requests'] == 2
+    assert second['api']['totals']['input_tokens'] == 12
+    assert second['api']['coverage']['input_tokens'] == 1
+    assert second['api']['totals']['output_tokens'] is None
+    assert sum(b['api']['requests'] + b['local']['requests'] for b in result['series']) == result['request_count']
+    filtered = aggregate(start, start + timedelta(days=2), source='local', timezone_offset=480)
+    assert all(b['api']['requests'] == 0 for b in filtered['series'])
+    assert len(aggregate(start, start + timedelta(days=3660))['series']) <= 90
+
+
+def test_model_series_partitions_match_source_totals_and_cache_rate():
+    start = datetime(2026, 9, 1, tzinfo=timezone.utc)
+    for model, count in [('model-a', 100), ('model-b', 200)]:
+        attempt = UsageAttempt('p', model, 'openai_compatible')
+        attempt.started_at = start.isoformat()
+        attempt.observe({'usage': {'prompt_tokens': count, 'completion_tokens': 0, 'prompt_cache_hit_tokens': 20, 'prompt_cache_miss_tokens': count - 20}})
+        attempt.persist()
+    result = aggregate(start, start + timedelta(days=1))
+    api = result['series'][0]['api']
+    assert [part['model'] for part in api['models']] == ['model-a', 'model-b']
+    assert sum(part['totals']['input_tokens'] for part in api['models']) == api['totals']['input_tokens'] == 300
+    assert result['totals']['cache_hit_tokens'] == 40
+    assert result['totals']['cache_miss_tokens'] == 260
+    assert result['cache_hit_rate'] == pytest.approx(40/300)

backend/tests/test_workspace.py

@@ -114,3 +114,34 @@ def test_workspace_openapi_paths_are_published() -> None:
         "/api/workspace/folders/delete",
         "/api/notes/{note_id}/rename",
     } <= paths.keys()
+
+def test_external_files_are_registered_and_removed_without_vector_wait(monkeypatch) -> None:
+    from app.services import index_service
+    scheduled = []
+    monkeypatch.setattr(index_service, 'schedule_workspace_rebuild', lambda: scheduled.append(True))
+    vault = get_settings().vault_path
+    vault.mkdir(parents=True, exist_ok=True)
+    external = vault / 'external.md'
+    external.write_text('# External\n', encoding='utf-8')
+    tree = asyncio.run(get_workspace_tree())
+    assert tree[0].note_id is not None
+    external.rename(vault / 'renamed.md')
+    tree = asyncio.run(get_workspace_tree())
+    assert [item.name for item in tree] == ['renamed.md']
+    (vault / 'renamed.md').unlink()
+    assert asyncio.run(get_workspace_tree()) == []
+    assert len(scheduled) == 3
+
+
+def test_save_rejects_external_content_change() -> None:
+    import hashlib
+    from app.contracts import NoteUpdateRequest
+    from app.routes import update_note
+    original = '# Original\n'
+    note = asyncio.run(create_note(NoteCreateRequest(title='Conflict', markdown=original)))
+    disk = get_settings().vault_path / note.file_path
+    disk.write_text('# External\n', encoding='utf-8')
+    with pytest.raises(ApiError) as error:
+        asyncio.run(update_note(note.note_id, NoteUpdateRequest(markdown='# Editor\n', expected_content_hash=hashlib.sha256(original.encode()).hexdigest())))
+    assert error.value.code == 'NOTE_CONTENT_CONFLICT'
+    assert disk.read_text(encoding='utf-8') == '# External\n'

backend/tests/test_workspace_background.py

@@ -0,0 +1,131 @@
+import asyncio
+
+from app import repository
+from app.config import get_settings
+from app.services import index_service, workspace_service
+
+
+def test_open_returns_before_vectors_and_deduplicates_background(monkeypatch):
+    async def scenario():
+        started, release = asyncio.Event(), asyncio.Event()
+        original = index_service.prepare_note_index
+        calls = 0
+        async def slow(*args, **kwargs):
+            nonlocal calls
+            calls += 1
+            started.set()
+            await release.wait()
+            return await original(*args, **kwargs)
+        monkeypatch.setattr(index_service, 'prepare_note_index', slow)
+        vault = get_settings().vault_path
+        vault.mkdir(parents=True, exist_ok=True)
+        (vault / 'demo.md').write_text('# Demo\n\nsearchable content', encoding='utf-8')
+        try:
+            snapshot = await asyncio.wait_for(workspace_service.open_workspace(None), 1)
+            assert snapshot.items[0].note_id
+            await asyncio.wait_for(started.wait(), 1)
+            task = index_service._background_task
+            await asyncio.wait_for(workspace_service.open_workspace(None), 1)
+            assert index_service._background_task is task
+            assert index_service.get_status().status == 'running'
+            # A mutation still completes while the model is waiting.
+            await asyncio.wait_for(workspace_service.create_folder('/', 'new-folder'), 1)
+            assert repository.list_note_locations()[0].note_id == snapshot.items[0].note_id
+            release.set()
+            await asyncio.wait_for(task, 2)
+            assert calls == 1
+            assert not index_service.get_status().vector_refresh_required
+        finally:
+            release.set()
+            await index_service.shutdown()
+    asyncio.run(scenario())
+
+
+def test_background_retries_changed_snapshot_without_overwriting(monkeypatch):
+    async def scenario():
+        started, release = asyncio.Event(), asyncio.Event()
+        original = index_service.prepare_note_index
+        calls = 0
+        async def slow(*args, **kwargs):
+            nonlocal calls
+            calls += 1
+            if calls == 1:
+                started.set()
+                await release.wait()
+            return await original(*args, **kwargs)
+        monkeypatch.setattr(index_service, 'prepare_note_index', slow)
+        vault = get_settings().vault_path
+        vault.mkdir(parents=True, exist_ok=True)
+        path = vault / 'demo.md'
+        path.write_text('# Before\n\nold', encoding='utf-8')
+        try:
+            await workspace_service.open_workspace(None)
+            await asyncio.wait_for(started.wait(), 1)
+            path.write_text('# After\n\nnew', encoding='utf-8')
+            release.set()
+            await asyncio.wait_for(index_service._background_task, 4)
+            assert calls == 2
+            assert repository.list_note_locations()[0].title == 'After'
+            assert not index_service.get_status().vector_refresh_required
+        finally:
+            release.set()
+            await index_service.shutdown()
+    asyncio.run(scenario())
+
+
+def test_save_returns_while_vectors_wait_and_latest_revision_wins(monkeypatch):
+    from app.services import note_service
+    async def scenario():
+        note = await note_service.create_note(title='Draft', markdown='# Draft\n\ninitial', folder=None, tags=[])
+        started, release = asyncio.Event(), asyncio.Event()
+        original = index_service.prepare_note_index
+        calls = 0
+        async def slow(*args, **kwargs):
+            nonlocal calls
+            calls += 1
+            if calls == 1:
+                started.set()
+                await release.wait()
+            return await original(*args, **kwargs)
+        monkeypatch.setattr(index_service, 'prepare_note_index', slow)
+        try:
+            await asyncio.wait_for(note_service.update_note(note.note_id, markdown='# First\n\none', defer_vectors=True), 1)
+            await asyncio.wait_for(started.wait(), 1)
+            await asyncio.wait_for(note_service.update_note(note.note_id, title='Custom title', tags=['kept'], markdown='# Latest\n\ntwo', defer_vectors=True), 1)
+            assert (await note_service.get_note(note.note_id)).markdown == '# Latest\n\ntwo'
+            assert index_service.get_status().vector_refresh_required
+            release.set()
+            await asyncio.wait_for(index_service._background_task, 3)
+            current = repository.get_note_record(note.note_id)
+            assert current.title == 'Custom title'
+            assert current.tags == ['kept']
+            assert calls == 2
+            assert not index_service.get_status().vector_refresh_required
+        finally:
+            release.set()
+            await index_service.shutdown()
+    asyncio.run(scenario())
+
+
+def test_failed_vectors_do_not_undo_save_and_pending_work_can_resume(monkeypatch):
+    from app.services import note_service
+    async def scenario():
+        note = await note_service.create_note(title='Draft', markdown='# Draft', folder=None, tags=[])
+        original = index_service.prepare_note_index
+        async def fail(*args, **kwargs):
+            raise RuntimeError('model unavailable')
+        monkeypatch.setattr(index_service, 'prepare_note_index', fail)
+        try:
+            await note_service.update_note(note.note_id, markdown='# Saved', defer_vectors=True)
+            await index_service._background_task
+            assert (await note_service.get_note(note.note_id)).markdown == '# Saved'
+            assert index_service.get_status().status == 'failed'
+            assert index_service.get_status().vector_refresh_required
+            await index_service.shutdown()
+            monkeypatch.setattr(index_service, 'prepare_note_index', original)
+            await workspace_service.open_workspace(None)
+            await index_service._background_task
+            assert not index_service.get_status().vector_refresh_required
+        finally:
+            await index_service.shutdown()
+    asyncio.run(scenario())