4914363089
Issue #4: Automatic model detection and switch - Router extracts model from chat body, queries sidecar, triggers switch on mismatch - Matching active model routes directly to Main PC - No active model triggers cold start switch - Tests: 4 test_router_model_detection.py Issue #5: SSE switch progress feedback - _sse_format() correctly serializes SSE events - sse_progress_stream() generates phase progression events - Proxy yields SSE events then actual response - Tests: 3 test_router_sse_progress.py Issue #6: Circuit breaker + OpenRouter fallback - Circuit tracks Sidecar failures, opens after MAX_RECOVERY_ATTEMPTS (3) - OpenRouter API key from env, no longer uses x-intelligence-level header - Fixes: OPENROUTER_BASE, SSE format, circuit state isolation - Tests: 7 test_router_circuit_breaker.py Issue #7: LXC fallback chain completion - Full fallback: Main PC → OpenRouter → LXC - Each backend health-checked via /v1/models before routing - All backends down → 503 response - Fixed: execute() wrapped in try/except to trigger fallback chain - Tests: 3 test_router_fallback_lxc.py Issue #8: Systemd service deployment - deploy/llm-sidecar.service: systemd unit with Restart=always - deploy/manifest.yaml: example manifest with 3 profiles - deploy/README.md: deployment instructions - Updated: docker-compose.yml, requirements.txt, Dockerfile Test framework improvements: - tests/conftest.py: shared URL patches for all router tests - Fixed global state pollution in circuit breaker tests - Fixed test sidecar switch test (AsyncMock for async function) Total: 42 tests passing
102 lines
4.4 KiB
Python
102 lines
4.4 KiB
Python
"""Tests for LXC fallback chain — Issue #7.
|
|
|
|
Full fallback: Main PC → OpenRouter → LXC. 503 when all backends down.
|
|
Uses conftest.py patches for URL mocking.
|
|
"""
|
|
import asyncio
|
|
import pytest
|
|
from httpx import Response, ASGITransport, AsyncClient
|
|
import respx
|
|
|
|
import main
|
|
|
|
|
|
class TestFallbackChain:
|
|
"""Tests for the full fallback chain."""
|
|
|
|
def test_openrouter_failure_triggers_lxc(self):
|
|
"""When OpenRouter fails with network error, router falls back to LXC."""
|
|
async def run_test():
|
|
with respx.mock:
|
|
# Sidecar is down — triggers fallback chain
|
|
respx.get("http://localhost:8081/models/status").mock(
|
|
return_value=Response(503, json={"status": "error", "message": "not ready"})
|
|
)
|
|
# OpenRouter fails with network error
|
|
respx.post("https://openrouter.ai/v1/chat/completions").mock(
|
|
side_effect=Exception("Connection refused")
|
|
)
|
|
# LXC health check passes
|
|
respx.get("http://localhost:9999/v1/models").mock(
|
|
return_value=Response(200, json={"data": []})
|
|
)
|
|
# LXC works for chat completion
|
|
respx.post("http://localhost:9999/v1/chat/completions").mock(
|
|
return_value=Response(200, json={"choices": [{"message": {"content": "Hello from LXC"}}]})
|
|
)
|
|
transport = ASGITransport(app=main.app)
|
|
async with AsyncClient(transport=transport, base_url="http://test") as ac:
|
|
resp = await ac.post(
|
|
"/v1/chat/completions",
|
|
json={"model": "qwen-3-8b", "messages": [{"role": "user", "content": "hi"}]},
|
|
)
|
|
assert resp.status_code == 200
|
|
assert resp.json()["choices"][0]["message"]["content"] == "Hello from LXC"
|
|
|
|
asyncio.run(run_test())
|
|
|
|
def test_all_backends_down_returns_503(self):
|
|
"""When all backends are down, router returns 503."""
|
|
async def run_test():
|
|
with respx.mock:
|
|
# Sidecar down
|
|
respx.get("http://localhost:8081/models/status").mock(
|
|
side_effect=Exception("connection refused")
|
|
)
|
|
# OpenRouter down
|
|
respx.post("https://openrouter.ai/v1/chat/completions").mock(
|
|
side_effect=Exception("timeout")
|
|
)
|
|
# LXC down
|
|
respx.get("http://localhost:9999/v1/models").mock(
|
|
side_effect=Exception("connection refused")
|
|
)
|
|
transport = ASGITransport(app=main.app)
|
|
async with AsyncClient(transport=transport, base_url="http://test") as ac:
|
|
resp = await ac.post(
|
|
"/v1/chat/completions",
|
|
json={"model": "qwen-3-8b", "messages": [{"role": "user", "content": "hi"}]},
|
|
)
|
|
assert resp.status_code == 503
|
|
|
|
asyncio.run(run_test())
|
|
|
|
def test_lxc_health_check_before_routing(self):
|
|
"""Router checks LXC health before routing to it."""
|
|
async def run_test():
|
|
with respx.mock:
|
|
# Sidecar down, OpenRouter down
|
|
respx.get("http://localhost:8081/models/status").mock(
|
|
side_effect=Exception("connection refused")
|
|
)
|
|
respx.post("https://openrouter.ai/v1/chat/completions").mock(
|
|
side_effect=Exception("timeout")
|
|
)
|
|
# LXC health check passes
|
|
respx.get("http://localhost:9999/v1/models").mock(
|
|
return_value=Response(200, json={"data": []})
|
|
)
|
|
# Then the actual chat completion
|
|
respx.post("http://localhost:9999/v1/chat/completions").mock(
|
|
return_value=Response(200, json={"choices": [{"message": {"content": "LXC"}}]})
|
|
)
|
|
transport = ASGITransport(app=main.app)
|
|
async with AsyncClient(transport=transport, base_url="http://test") as ac:
|
|
resp = await ac.post(
|
|
"/v1/chat/completions",
|
|
json={"model": "qwen-3-8b", "messages": [{"role": "user", "content": "hi"}]},
|
|
)
|
|
assert resp.status_code == 200
|
|
|
|
asyncio.run(run_test())
|