Merge branch 'main' into milvus-files-api

tests/integration/README.md

@@ -9,7 +9,9 @@ pytest --help
 ```
 
 Here are the most important options:
-- `--stack-config`: specify the stack config to use. You have three ways to point to a stack:
+- `--stack-config`: specify the stack config to use. You have four ways to point to a stack:
+  - **`server:<config>`** - automatically start a server with the given config (e.g., `server:fireworks`). This provides one-step testing by auto-starting the server if the port is available, or reusing an existing server if already running.
+  - **`server:<config>:<port>`** - same as above but with a custom port (e.g., `server:together:8322`)
   - a URL which points to a Llama Stack distribution server
   - a template (e.g., `fireworks`, `together`) or a path to a `run.yaml` file
   - a comma-separated list of api=provider pairs, e.g. `inference=fireworks,safety=llama-guard,agents=meta-reference`. This is most useful for testing a single API surface.
@@ -26,12 +28,39 @@ Model parameters can be influenced by the following options:
 Each of these are comma-separated lists and can be used to generate multiple parameter combinations. Note that tests will be skipped
 if no model is specified.
 
-Experimental, under development, options:
-- `--record-responses`: record new API responses instead of using cached ones
-
-
 ## Examples
 
+### Testing against a Server
+
+Run all text inference tests by auto-starting a server with the `fireworks` config:
+
+```bash
+pytest -s -v tests/integration/inference/test_text_inference.py \
+   --stack-config=server:fireworks \
+   --text-model=meta-llama/Llama-3.1-8B-Instruct
+```
+
+Run tests with auto-server startup on a custom port:
+
+```bash
+pytest -s -v tests/integration/inference/ \
+   --stack-config=server:together:8322 \
+   --text-model=meta-llama/Llama-3.1-8B-Instruct
+```
+
+Run multiple test suites with auto-server (eliminates manual server management):
+
+```bash
+# Auto-start server and run all integration tests
+export FIREWORKS_API_KEY=<your_key>
+
+pytest -s -v tests/integration/inference/ tests/integration/safety/ tests/integration/agents/ \
+   --stack-config=server:fireworks \
+   --text-model=meta-llama/Llama-3.1-8B-Instruct
+```
+
+### Testing with Library Client
+
 Run all text inference tests with the `together` distribution:
 
 ```bash

tests/integration/fixtures/common.py

@@ -6,9 +6,13 @@
 
 import inspect
 import os
+import socket
+import subprocess
 import tempfile
+import time
 
 import pytest
+import requests
 import yaml
 from llama_stack_client import LlamaStackClient
 from openai import OpenAI
@@ -17,6 +21,60 @@ from llama_stack import LlamaStackAsLibraryClient
 from llama_stack.distribution.stack import run_config_from_adhoc_config_spec
 from llama_stack.env import get_env_or_fail
 
+DEFAULT_PORT = 8321
+
+
+def is_port_available(port: int, host: str = "localhost") -> bool:
+    """Check if a port is available for binding."""
+    try:
+        with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock:
+            sock.bind((host, port))
+            return True
+    except OSError:
+        return False
+
+
+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]
+    devnull = open(os.devnull, "w")
+    process = subprocess.Popen(
+        cmd,
+        stdout=devnull,  # redirect stdout to devnull to prevent deadlock
+        stderr=devnull,  # redirect stderr to devnull to prevent deadlock
+        text=True,
+        env={**os.environ, "LLAMA_STACK_LOG_FILE": "server.log"},
+    )
+    return process
+
+
+def wait_for_server_ready(base_url: str, timeout: int = 30, process: subprocess.Popen | None = None) -> bool:
+    """Wait for the server to be ready by polling the health endpoint."""
+    health_url = f"{base_url}/v1/health"
+    start_time = time.time()
+
+    while time.time() - start_time < timeout:
+        if process and process.poll() is not None:
+            print(f"Server process terminated with return code: {process.returncode}")
+            return False
+
+        try:
+            response = requests.get(health_url, timeout=5)
+            if response.status_code == 200:
+                return True
+        except (requests.exceptions.ConnectionError, requests.exceptions.Timeout):
+            pass
+
+        # Print progress every 5 seconds
+        elapsed = time.time() - start_time
+        if int(elapsed) % 5 == 0 and elapsed > 0:
+            print(f"Waiting for server at {base_url}... ({elapsed:.1f}s elapsed)")
+
+        time.sleep(0.5)
+
+    print(f"Server failed to respond within {timeout} seconds")
+    return False
+
 
 @pytest.fixture(scope="session")
 def provider_data():
@@ -122,6 +180,41 @@ def llama_stack_client(request, provider_data):
     if not config:
         raise ValueError("You must specify either --stack-config or LLAMA_STACK_CONFIG")
 
+    # Handle server:<config_name> format or server:<config_name>:<port>
+    if config.startswith("server:"):
+        parts = config.split(":")
+        config_name = parts[1]
+        port = int(parts[2]) if len(parts) > 2 else int(os.environ.get("LLAMA_STACK_PORT", DEFAULT_PORT))
+        base_url = f"http://localhost:{port}"
+
+        # Check if port is available
+        if is_port_available(port):
+            print(f"Starting llama stack server with config '{config_name}' on port {port}...")
+
+            # Start server
+            server_process = start_llama_stack_server(config_name)
+
+            # Wait for server to be ready
+            if not wait_for_server_ready(base_url, timeout=30, process=server_process):
+                print("Server failed to start within timeout")
+                server_process.terminate()
+                raise RuntimeError(
+                    f"Server failed to start within timeout. Check that config '{config_name}' exists and is valid. "
+                    f"See server.log for details."
+                )
+
+            print(f"Server is ready at {base_url}")
+
+            # Store process for potential cleanup (pytest will handle termination at session end)
+            request.session._llama_stack_server_process = server_process
+        else:
+            print(f"Port {port} is already in use, assuming server is already running...")
+
+        return LlamaStackClient(
+            base_url=base_url,
+            provider_data=provider_data,
+        )
+
     # check if this looks like a URL
     if config.startswith("http") or "//" in config:
         return LlamaStackClient(
@@ -151,3 +244,31 @@ def llama_stack_client(request, provider_data):
 def openai_client(client_with_models):
     base_url = f"{client_with_models.base_url}/v1/openai/v1"
     return OpenAI(base_url=base_url, api_key="fake")
+
+
+@pytest.fixture(scope="session", autouse=True)
+def cleanup_server_process(request):
+    """Cleanup server process at the end of the test session."""
+    yield  # Run tests
+
+    if hasattr(request.session, "_llama_stack_server_process"):
+        server_process = request.session._llama_stack_server_process
+        if server_process:
+            if server_process.poll() is None:
+                print("Terminating llama stack server process...")
+            else:
+                print(f"Server process already terminated with return code: {server_process.returncode}")
+                return
+            try:
+                server_process.terminate()
+                server_process.wait(timeout=10)
+                print("Server process terminated gracefully")
+            except subprocess.TimeoutExpired:
+                print("Server process did not terminate gracefully, killing it")
+                server_process.kill()
+                server_process.wait()
+                print("Server process killed")
+            except Exception as e:
+                print(f"Error during server cleanup: {e}")
+        else:
+            print("Server process not found - won't be able to cleanup")