From 194abe773422cafd718c812eee64ac18c2d5bbe0 Mon Sep 17 00:00:00 2001 From: ehhuang Date: Thu, 31 Jul 2025 21:09:14 -0700 Subject: [PATCH] test: use llama stack build when starting server (#2999) # What does this PR do? This should be more robust as sometimes its run without running build first. ## Test Plan OLLAMA_URL=http://localhost:11434 LLAMA_STACK_TEST_INFERENCE_MODE=replay LLAMA_STACK_TEST_RECORDING_DIR=tests/integration/recordings LLAMA_STACK_CONFIG=server:starter uv run --with pytest-repeat pytest tests/integration/telemetry --text-model="ollama/llama3.2:3b-instruct-fp16" -vvs --- tests/integration/fixtures/common.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tests/integration/fixtures/common.py b/tests/integration/fixtures/common.py index bdbe0d66f..37c7474a0 100644 --- a/tests/integration/fixtures/common.py +++ b/tests/integration/fixtures/common.py @@ -6,6 +6,7 @@ import inspect import os +import shlex import signal import socket import subprocess @@ -38,10 +39,10 @@ def is_port_available(port: int, host: str = "localhost") -> bool: def start_llama_stack_server(config_name: str) -> subprocess.Popen: """Start a llama stack server with the given config.""" - cmd = ["llama", "stack", "run", config_name] + cmd = f"uv run --with llama-stack llama stack build --template {config_name} --image-type venv --run" devnull = open(os.devnull, "w") process = subprocess.Popen( - cmd, + shlex.split(cmd), stdout=devnull, # redirect stdout to devnull to prevent deadlock stderr=subprocess.PIPE, # keep stderr to see errors text=True,