Merge remote-tracking branch 'origin/master' into feat/sandbox

# Conflicts:
#	src/langbot/pkg/api/http/controller/groups/plugins.py
#	src/langbot/pkg/core/app.py
#	src/langbot/pkg/core/stages/build_app.py
#	src/langbot/templates/config.yaml
#	uv.lock
#	web/src/app/home/components/home-sidebar/HomeSidebar.tsx
#	web/src/app/home/components/home-sidebar/SidebarDataContext.tsx
#	web/src/app/home/layout.tsx
#	web/src/app/home/plugins/components/plugin-market/PluginMarketComponent.tsx
#	web/src/i18n/locales/en-US.ts
#	web/src/i18n/locales/es-ES.ts
#	web/src/i18n/locales/ja-JP.ts
#	web/src/i18n/locales/th-TH.ts
#	web/src/i18n/locales/vi-VN.ts
#	web/src/i18n/locales/zh-Hans.ts
#	web/src/i18n/locales/zh-Hant.ts
#	web/src/router.tsx
This commit is contained in:
Junyan Qin
2026-05-05 14:05:53 +08:00
90 changed files with 7488 additions and 871 deletions

View File

@@ -0,0 +1,106 @@
from __future__ import annotations
from datetime import datetime, timedelta
from importlib import import_module
from pathlib import Path
from types import SimpleNamespace
from unittest.mock import AsyncMock, Mock
import pytest
import yaml
def _preproc_module():
# Import pipelinemgr first so pipeline stages are registered without tripping
# the stage <-> core.app circular import during isolated test collection.
import_module('langbot.pkg.pipeline.pipelinemgr')
return import_module('langbot.pkg.pipeline.preproc.preproc')
def _entities_module():
return import_module('langbot.pkg.pipeline.entities')
def _conversation(created_at: datetime, updated_at: datetime | None = None):
prompt = Mock()
prompt.messages = []
prompt.copy = Mock(return_value=Mock(messages=[]))
return SimpleNamespace(
uuid='existing-conversation-uuid',
create_time=created_at,
update_time=updated_at,
prompt=prompt,
messages=[],
)
def _prompt_preprocessing_context(default_prompt=None, prompt=None):
ctx = Mock()
ctx.event.default_prompt = default_prompt or []
ctx.event.prompt = prompt or []
return ctx
async def _run_preprocessor(mock_app, sample_query, conversation):
session = SimpleNamespace(launcher_type=sample_query.launcher_type, launcher_id=sample_query.launcher_id)
mock_app.sess_mgr.get_session = AsyncMock(return_value=session)
mock_app.sess_mgr.get_conversation = AsyncMock(return_value=conversation)
mock_app.plugin_connector.emit_event = AsyncMock(return_value=_prompt_preprocessing_context())
sample_query.pipeline_config = {
'ai': {
'runner': {'runner': 'local-agent', 'expire-time': 60},
'local-agent': {'model': {'primary': '', 'fallbacks': []}, 'prompt': []},
},
'trigger': {'misc': {'combine-quote-message': False}},
'output': {'misc': {'exception-handling': 'show-hint'}},
}
return await _preproc_module().PreProcessor(mock_app).process(sample_query, 'PreProcessor')
@pytest.mark.asyncio
async def test_preprocessor_expires_conversation_from_last_update_time(mock_app, sample_query):
conversation = _conversation(
created_at=datetime.now() - timedelta(seconds=10),
updated_at=datetime.now() - timedelta(seconds=120),
)
result = await _run_preprocessor(mock_app, sample_query, conversation)
assert result.result_type == _entities_module().ResultType.CONTINUE
assert conversation.uuid is None
assert conversation.update_time > datetime.now() - timedelta(seconds=5)
assert result.new_query.variables['conversation_id'] is None
@pytest.mark.asyncio
async def test_preprocessor_keeps_conversation_when_last_update_is_not_expired(mock_app, sample_query):
conversation = _conversation(
created_at=datetime.now() - timedelta(seconds=120),
updated_at=datetime.now() - timedelta(seconds=30),
)
result = await _run_preprocessor(mock_app, sample_query, conversation)
assert result.result_type == _entities_module().ResultType.CONTINUE
assert conversation.uuid == 'existing-conversation-uuid'
assert conversation.update_time > datetime.now() - timedelta(seconds=5)
assert result.new_query.variables['conversation_id'] == 'existing-conversation-uuid'
def test_expire_time_metadata_lives_under_ai_runner_not_safety():
metadata_dir = Path('src/langbot/templates/metadata/pipeline')
ai_meta = yaml.safe_load((metadata_dir / 'ai.yaml').read_text())
safety_meta = yaml.safe_load((metadata_dir / 'safety.yaml').read_text())
ai_stage_names = [stage['name'] for stage in ai_meta['stages']]
assert 'session-limit' not in ai_stage_names
assert 'session-limit' not in [stage['name'] for stage in safety_meta['stages']]
runner_stage = next(stage for stage in ai_meta['stages'] if stage['name'] == 'runner')
expire_time = next(item for item in runner_stage['config'] if item['name'] == 'expire-time')
assert 'Conversation expire time' in expire_time['label']['en_US']
assert 'Session validity' not in expire_time['label']['en_US']

View File

@@ -0,0 +1 @@

View File

@@ -0,0 +1,173 @@
from __future__ import annotations
from types import SimpleNamespace
from unittest.mock import AsyncMock, Mock
import pytest
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
import langbot_plugin.api.entities.builtin.platform.entities as platform_entities
import langbot_plugin.api.entities.builtin.platform.events as platform_events
import langbot_plugin.api.entities.builtin.platform.message as platform_message
import langbot_plugin.api.entities.builtin.provider.session as provider_session
from langbot.pkg.api.http.service.model import _runtime_model_data
from langbot.pkg.entity.persistence import model as persistence_model
from langbot.pkg.pipeline.preproc.preproc import PreProcessor
from langbot.pkg.provider.modelmgr import requester
from langbot.pkg.provider.modelmgr.modelmgr import ModelManager
from langbot.pkg.provider.runners.localagent import LocalAgentRunner
def test_runtime_llm_model_data_preserves_uuid_after_update_payload_uuid_removed():
update_payload = {
'name': 'Qwen3.5-27B',
'provider_uuid': 'provider-uuid',
'abilities': [],
'extra_args': {},
}
runtime_entity = persistence_model.LLMModel(**_runtime_model_data('model-uuid', update_payload))
assert runtime_entity.uuid == 'model-uuid'
assert runtime_entity.name == 'Qwen3.5-27B'
def test_runtime_embedding_model_data_preserves_uuid_after_update_payload_uuid_removed():
update_payload = {
'name': 'embedding-model',
'provider_uuid': 'provider-uuid',
'extra_args': {},
}
runtime_entity = persistence_model.EmbeddingModel(**_runtime_model_data('embedding-uuid', update_payload))
assert runtime_entity.uuid == 'embedding-uuid'
assert runtime_entity.name == 'embedding-model'
def test_runtime_rerank_model_data_preserves_uuid_after_update_payload_uuid_removed():
update_payload = {
'name': 'rerank-model',
'provider_uuid': 'provider-uuid',
'extra_args': {},
}
runtime_entity = persistence_model.RerankModel(**_runtime_model_data('rerank-uuid', update_payload))
assert runtime_entity.uuid == 'rerank-uuid'
assert runtime_entity.name == 'rerank-model'
@pytest.mark.asyncio
async def test_updated_llm_model_is_immediately_usable_by_local_agent_pipeline():
from langbot.pkg.api.http.service.model import LLMModelsService
model_uuid = 'qwen-model-uuid'
provider_uuid = 'ollama-provider-uuid'
ap = SimpleNamespace()
ap.logger = Mock()
ap.persistence_mgr = SimpleNamespace(execute_async=AsyncMock())
ap.tool_mgr = SimpleNamespace(get_all_tools=AsyncMock(return_value=[]))
ap.plugin_connector = SimpleNamespace(
emit_event=AsyncMock(return_value=SimpleNamespace(event=SimpleNamespace(default_prompt=[], prompt=[])))
)
ap.model_mgr = ModelManager(ap)
runtime_provider = Mock()
ap.model_mgr.provider_dict = {provider_uuid: runtime_provider}
ap.model_mgr.llm_models = [
requester.RuntimeLLMModel(
model_entity=persistence_model.LLMModel(
uuid=model_uuid,
name='old-qwen-name',
provider_uuid=provider_uuid,
abilities=[],
extra_args={},
),
provider=runtime_provider,
)
]
await LLMModelsService(ap).update_llm_model(
model_uuid,
{
'name': 'Qwen3.5-27B',
'provider_uuid': provider_uuid,
'abilities': [],
'extra_args': {},
},
)
runtime_model = await ap.model_mgr.get_model_by_uuid(model_uuid)
assert runtime_model.model_entity.uuid == model_uuid
assert runtime_model.model_entity.name == 'Qwen3.5-27B'
session = SimpleNamespace(
launcher_type=provider_session.LauncherTypes.PERSON,
launcher_id=12345,
)
conversation = SimpleNamespace(
uuid='conversation-uuid',
create_time=None,
update_time=None,
prompt=SimpleNamespace(messages=[], copy=Mock(return_value=SimpleNamespace(messages=[]))),
messages=[],
)
ap.sess_mgr = SimpleNamespace(
get_session=AsyncMock(return_value=session),
get_conversation=AsyncMock(return_value=conversation),
)
message_chain = platform_message.MessageChain([platform_message.Plain(text='hello')])
sender = platform_entities.Friend(id=12345, nickname='Tester', remark=None)
message_event = platform_events.FriendMessage(
type='FriendMessage',
sender=sender,
message_chain=message_chain,
time=1710000000,
)
pipeline_config = {
'ai': {
'runner': {'runner': 'local-agent'},
'local-agent': {
'model': {'primary': model_uuid, 'fallbacks': []},
'prompt': [],
'knowledge-bases': [],
},
},
'trigger': {'misc': {'combine-quote-message': False}},
'output': {'misc': {'remove-think': False}},
}
query = pipeline_query.Query.model_construct(
query_id='query-id',
launcher_type=provider_session.LauncherTypes.PERSON,
launcher_id=12345,
sender_id=12345,
message_chain=message_chain,
message_event=message_event,
adapter=AsyncMock(),
pipeline_uuid='pipeline-uuid',
bot_uuid='bot-uuid',
pipeline_config=pipeline_config,
session=None,
prompt=None,
messages=[],
user_message=None,
use_funcs=[],
use_llm_model_uuid=None,
variables={},
resp_messages=[],
resp_message_chain=None,
current_stage_name=None,
)
result = await PreProcessor(ap).process(query, 'PreProcessor')
processed_query = result.new_query
assert processed_query.use_llm_model_uuid == model_uuid
runner = SimpleNamespace(ap=ap, pipeline_config=pipeline_config)
candidates = await LocalAgentRunner._get_model_candidates(runner, processed_query)
assert [model.model_entity.uuid for model in candidates] == [model_uuid]

View File

@@ -0,0 +1,181 @@
"""
PoC test for CWE-22 path traversal in LocalStorageProvider.
The LocalStorageProvider uses os.path.join(LOCAL_STORAGE_PATH, key) without
validating that the resulting path stays inside LOCAL_STORAGE_PATH.
When `key` is an absolute path (e.g. '/etc/passwd'), os.path.join discards
all previous components and returns the absolute path directly, allowing
arbitrary file reads, writes, and deletes.
This test must FAIL before the fix and PASS after.
"""
import os
import pytest
from unittest.mock import Mock, patch
from langbot.pkg.storage.providers.localstorage import LocalStorageProvider
@pytest.fixture
def storage_provider(tmp_path):
"""Create a LocalStorageProvider with a temporary storage path."""
storage_path = str(tmp_path / "storage")
with patch("langbot.pkg.storage.providers.localstorage.LOCAL_STORAGE_PATH", storage_path):
mock_app = Mock()
provider = LocalStorageProvider(mock_app)
yield provider, storage_path
class TestPathTraversalPrevention:
"""Test that LocalStorageProvider rejects path traversal attempts."""
@pytest.mark.asyncio
async def test_absolute_path_save_rejected(self, storage_provider, tmp_path):
"""Saving with an absolute path key must be blocked."""
provider, storage_path = storage_provider
target_file = str(tmp_path / "pwned.txt")
with patch("langbot.pkg.storage.providers.localstorage.LOCAL_STORAGE_PATH", storage_path):
with pytest.raises((ValueError, PermissionError)):
await provider.save(target_file, b"malicious content")
# The file must NOT exist outside the storage directory
assert not os.path.exists(target_file), (
f"Path traversal succeeded: file was written outside storage to {target_file}"
)
@pytest.mark.asyncio
async def test_absolute_path_load_rejected(self, storage_provider, tmp_path):
"""Loading with an absolute path key must be blocked."""
provider, storage_path = storage_provider
# Create a file outside the storage directory
target_file = str(tmp_path / "secret.txt")
with open(target_file, "wb") as f:
f.write(b"secret data")
with patch("langbot.pkg.storage.providers.localstorage.LOCAL_STORAGE_PATH", storage_path):
with pytest.raises((ValueError, PermissionError, FileNotFoundError)):
data = await provider.load(target_file)
assert data != b"secret data", (
"Path traversal succeeded: read file outside storage"
)
@pytest.mark.asyncio
async def test_absolute_path_exists_rejected(self, storage_provider, tmp_path):
"""Exists check with an absolute path key must be blocked or return False."""
provider, storage_path = storage_provider
target_file = str(tmp_path / "check_me.txt")
with open(target_file, "wb") as f:
f.write(b"data")
with patch("langbot.pkg.storage.providers.localstorage.LOCAL_STORAGE_PATH", storage_path):
try:
result = await provider.exists(target_file)
assert result is False, (
"Path traversal succeeded: exists() returned True for file outside storage"
)
except (ValueError, PermissionError):
pass # Expected
@pytest.mark.asyncio
async def test_absolute_path_delete_rejected(self, storage_provider, tmp_path):
"""Deleting with an absolute path key must be blocked."""
provider, storage_path = storage_provider
target_file = str(tmp_path / "do_not_delete.txt")
with open(target_file, "wb") as f:
f.write(b"important data")
with patch("langbot.pkg.storage.providers.localstorage.LOCAL_STORAGE_PATH", storage_path):
with pytest.raises((ValueError, PermissionError, FileNotFoundError)):
await provider.delete(target_file)
assert os.path.exists(target_file), (
"Path traversal succeeded: file outside storage was deleted"
)
@pytest.mark.asyncio
async def test_absolute_path_size_rejected(self, storage_provider, tmp_path):
"""Size check with an absolute path key must be blocked."""
provider, storage_path = storage_provider
target_file = str(tmp_path / "measure_me.txt")
with open(target_file, "wb") as f:
f.write(b"some data")
with patch("langbot.pkg.storage.providers.localstorage.LOCAL_STORAGE_PATH", storage_path):
with pytest.raises((ValueError, PermissionError, FileNotFoundError)):
await provider.size(target_file)
@pytest.mark.asyncio
async def test_dot_dot_path_traversal_rejected(self, storage_provider, tmp_path):
"""Relative path traversal with '..' must be blocked."""
provider, storage_path = storage_provider
target_file = str(tmp_path / "above_storage.txt")
with open(target_file, "wb") as f:
f.write(b"above storage secret")
with patch("langbot.pkg.storage.providers.localstorage.LOCAL_STORAGE_PATH", storage_path):
relative_key = os.path.join("..", "above_storage.txt")
with pytest.raises((ValueError, PermissionError, FileNotFoundError)):
data = await provider.load(relative_key)
assert data != b"above storage secret"
@pytest.mark.asyncio
async def test_delete_dir_recursive_traversal_rejected(self, storage_provider, tmp_path):
"""delete_dir_recursive with traversal path must be blocked."""
provider, storage_path = storage_provider
outside_dir = tmp_path / "outside_dir"
outside_dir.mkdir()
(outside_dir / "file.txt").write_text("important")
with patch("langbot.pkg.storage.providers.localstorage.LOCAL_STORAGE_PATH", storage_path):
with pytest.raises((ValueError, PermissionError)):
await provider.delete_dir_recursive(str(outside_dir))
assert outside_dir.exists(), (
"Path traversal succeeded: directory outside storage was deleted"
)
@pytest.mark.asyncio
async def test_legitimate_key_works(self, storage_provider):
"""Normal keys without traversal must still work."""
provider, storage_path = storage_provider
with patch("langbot.pkg.storage.providers.localstorage.LOCAL_STORAGE_PATH", storage_path):
key = "test_image_abc123.png"
content = b"PNG image data"
await provider.save(key, content)
assert await provider.exists(key) is True
loaded = await provider.load(key)
assert loaded == content
size = await provider.size(key)
assert size == len(content)
await provider.delete(key)
assert await provider.exists(key) is False
@pytest.mark.asyncio
async def test_legitimate_subdirectory_key_works(self, storage_provider):
"""Keys with legitimate subdirectories must still work."""
provider, storage_path = storage_provider
with patch("langbot.pkg.storage.providers.localstorage.LOCAL_STORAGE_PATH", storage_path):
key = "bot_log_images/img_001.png"
content = b"PNG image data"
await provider.save(key, content)
assert await provider.exists(key) is True
loaded = await provider.load(key)
assert loaded == content
await provider.delete(key)
if __name__ == "__main__":
pytest.main([__file__, "-v"])