mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
840ad75fe9
# What does this PR do? Extract API definitions and provider specifications into a standalone llama-stack-api package that can be published to PyPI independently of the main llama-stack server. see: https://github.com/llamastack/llama-stack/pull/2978 and https://github.com/llamastack/llama-stack/pull/2978#issuecomment-3145115942 Motivation External providers currently import from llama-stack, which overrides the installed version and causes dependency conflicts. This separation allows external providers to: - Install only the type definitions they need without server dependencies - Avoid version conflicts with the installed llama-stack package - Be versioned and released independently This enables us to re-enable external provider module tests that were previously blocked by these import conflicts. Changes - Created llama-stack-api package with minimal dependencies (pydantic, jsonschema) - Moved APIs, providers datatypes, strong_typing, and schema_utils - Updated all imports from llama_stack.* to llama_stack_api.* - Configured local editable install for development workflow - Updated linting and type-checking configuration for both packages Next Steps - Publish llama-stack-api to PyPI - Update external provider dependencies - Re-enable external provider module tests Pre-cursor PRs to this one: - #4093 - #3954 - #4064 These PRs moved key pieces _out_ of the Api pkg, limiting the scope of change here. relates to #3237 ## Test Plan Package builds successfully and can be imported independently. All pre-commit hooks pass with expected exclusions maintained. --------- Signed-off-by: Charlie Doern <cdoern@redhat.com>
122 lines
3.7 KiB
Python
122 lines
3.7 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
import asyncio
|
|
import logging # allow-direct-logging
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
|
|
import pytest
|
|
from llama_stack_api import PaginatedResponse
|
|
|
|
from llama_stack.core.server.server import create_dynamic_typed_route, create_sse_event, sse_generator
|
|
|
|
|
|
@pytest.fixture
|
|
def suppress_sse_errors(caplog):
|
|
"""Suppress expected ERROR logs for tests that deliberately trigger SSE errors"""
|
|
caplog.set_level(logging.CRITICAL, logger="llama_stack.core.server.server")
|
|
|
|
|
|
async def test_sse_generator_basic():
|
|
# An AsyncIterator wrapped in an Awaitable, just like our web methods
|
|
async def async_event_gen():
|
|
async def event_gen():
|
|
yield "Test event 1"
|
|
yield "Test event 2"
|
|
|
|
return event_gen()
|
|
|
|
sse_gen = sse_generator(async_event_gen())
|
|
assert sse_gen is not None
|
|
|
|
# Test that the events are streamed correctly
|
|
seen_events = []
|
|
async for event in sse_gen:
|
|
seen_events.append(event)
|
|
assert len(seen_events) == 2
|
|
assert seen_events[0] == create_sse_event("Test event 1")
|
|
assert seen_events[1] == create_sse_event("Test event 2")
|
|
|
|
|
|
async def test_sse_generator_client_disconnected():
|
|
# An AsyncIterator wrapped in an Awaitable, just like our web methods
|
|
async def async_event_gen():
|
|
async def event_gen():
|
|
yield "Test event 1"
|
|
# Simulate a client disconnect before emitting event 2
|
|
raise asyncio.CancelledError()
|
|
|
|
return event_gen()
|
|
|
|
sse_gen = sse_generator(async_event_gen())
|
|
assert sse_gen is not None
|
|
|
|
seen_events = []
|
|
async for event in sse_gen:
|
|
seen_events.append(event)
|
|
|
|
# We should see 1 event before the client disconnected
|
|
assert len(seen_events) == 1
|
|
assert seen_events[0] == create_sse_event("Test event 1")
|
|
|
|
|
|
async def test_sse_generator_client_disconnected_before_response_starts():
|
|
# Disconnect before the response starts
|
|
async def async_event_gen():
|
|
raise asyncio.CancelledError()
|
|
|
|
sse_gen = sse_generator(async_event_gen())
|
|
assert sse_gen is not None
|
|
|
|
seen_events = []
|
|
async for event in sse_gen:
|
|
seen_events.append(event)
|
|
|
|
# No events should be seen since the client disconnected immediately
|
|
assert len(seen_events) == 0
|
|
|
|
|
|
async def test_sse_generator_error_before_response_starts(suppress_sse_errors):
|
|
# Raise an error before the response starts
|
|
async def async_event_gen():
|
|
raise Exception("Test error")
|
|
|
|
sse_gen = sse_generator(async_event_gen())
|
|
assert sse_gen is not None
|
|
|
|
seen_events = []
|
|
async for event in sse_gen:
|
|
seen_events.append(event)
|
|
|
|
# We should have 1 error event
|
|
assert len(seen_events) == 1
|
|
assert 'data: {"error":' in seen_events[0]
|
|
|
|
|
|
async def test_paginated_response_url_setting():
|
|
"""Test that PaginatedResponse gets url set to route path."""
|
|
|
|
async def mock_api_method():
|
|
return PaginatedResponse(data=[], has_more=False, url=None)
|
|
|
|
route_handler = create_dynamic_typed_route(mock_api_method, "get", "/test/route")
|
|
|
|
# Mock minimal request with proper state object
|
|
request = MagicMock()
|
|
request.scope = {"user_attributes": {}, "principal": ""}
|
|
request.headers = {}
|
|
request.body = AsyncMock(return_value=b"")
|
|
|
|
# Create a simple state object without auto-generating attributes
|
|
class MockState:
|
|
pass
|
|
|
|
request.state = MockState()
|
|
|
|
result = await route_handler(request)
|
|
|
|
assert isinstance(result, PaginatedResponse)
|
|
assert result.url == "/test/route"
|