Merge branch 'main' into ci-ui-tests

.github/TRIAGERS.md

@@ -1,2 +1,2 @@
 # This file documents Triage members in the Llama Stack community
- @bbrowning @franciscojavierarceo @leseb
+ @franciscojavierarceo

docs/source/contributing/index.md

@@ -23,12 +23,7 @@ new_vector_database
 ```{include} ../../../tests/README.md
 ```
 
-## Benchmarking
-
-```{include} ../../../docs/source/distributions/k8s-benchmark/README.md
-```
-
-### Advanced Topics
+## Advanced Topics
 
 For developers who need deeper understanding of the testing system internals:
 
@@ -37,3 +32,8 @@ For developers who need deeper understanding of the testing system internals:
 
 testing/record-replay
 ```
+
+### Benchmarking
+
+```{include} ../../../docs/source/distributions/k8s-benchmark/README.md
+```

llama_stack/core/build_conda_env.sh

@@ -1,207 +0,0 @@
-#!/bin/bash
-
-# 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.
-
-LLAMA_STACK_DIR=${LLAMA_STACK_DIR:-}
-LLAMA_STACK_CLIENT_DIR=${LLAMA_STACK_CLIENT_DIR:-}
-TEST_PYPI_VERSION=${TEST_PYPI_VERSION:-}
-PYPI_VERSION=${PYPI_VERSION:-}
-# This timeout (in seconds) is necessary when installing PyTorch via uv since it's likely to time out
-# Reference: https://github.com/astral-sh/uv/pull/1694
-UV_HTTP_TIMEOUT=${UV_HTTP_TIMEOUT:-500}
-
-set -euo pipefail
-
-# Define color codes
-RED='\033[0;31m'
-GREEN='\033[0;32m'
-NC='\033[0m' # No Color
-
-SCRIPT_DIR=$(dirname "$(readlink -f "$0")")
-source "$SCRIPT_DIR/common.sh"
-
-# Usage function
-usage() {
-  echo "Usage: $0 --env-name <conda_env_name> --build-file-path <build_file_path> --normal-deps <pip_dependencies> [--external-provider-deps <external_provider_deps>] [--optional-deps <special_pip_deps>]"
-  echo "Example: $0 --env-name my-conda-env --build-file-path ./my-stack-build.yaml --normal-deps 'numpy pandas scipy' --external-provider-deps 'foo' --optional-deps 'bar'"
-  exit 1
-}
-
-# Parse arguments
-env_name=""
-build_file_path=""
-normal_deps=""
-external_provider_deps=""
-optional_deps=""
-
-while [[ $# -gt 0 ]]; do
-  key="$1"
-  case "$key" in
-    --env-name)
-      if [[ -z "$2" || "$2" == --* ]]; then
-        echo "Error: --env-name requires a string value" >&2
-        usage
-      fi
-      env_name="$2"
-      shift 2
-      ;;
-    --build-file-path)
-      if [[ -z "$2" || "$2" == --* ]]; then
-        echo "Error: --build-file-path requires a string value" >&2
-        usage
-      fi
-      build_file_path="$2"
-      shift 2
-      ;;
-    --normal-deps)
-      if [[ -z "$2" || "$2" == --* ]]; then
-        echo "Error: --normal-deps requires a string value" >&2
-        usage
-      fi
-      normal_deps="$2"
-      shift 2
-      ;;
-    --external-provider-deps)
-      if [[ -z "$2" || "$2" == --* ]]; then
-        echo "Error: --external-provider-deps requires a string value" >&2
-        usage
-      fi
-      external_provider_deps="$2"
-      shift 2
-      ;;
-    --optional-deps)
-      if [[ -z "$2" || "$2" == --* ]]; then
-        echo "Error: --optional-deps requires a string value" >&2
-        usage
-      fi
-      optional_deps="$2"
-      shift 2
-      ;;
-    *)
-      echo "Unknown option: $1" >&2
-      usage
-      ;;
-  esac
-done
-
-# Check required arguments
-if [[ -z "$env_name" || -z "$build_file_path" || -z "$normal_deps" ]]; then
-  echo "Error: --env-name, --build-file-path, and --normal-deps are required." >&2
-  usage
-fi
-
-if [ -n "$LLAMA_STACK_DIR" ]; then
-  echo "Using llama-stack-dir=$LLAMA_STACK_DIR"
-fi
-if [ -n "$LLAMA_STACK_CLIENT_DIR" ]; then
-  echo "Using llama-stack-client-dir=$LLAMA_STACK_CLIENT_DIR"
-fi
-
-ensure_conda_env_python310() {
-  # Use only global variables set by flag parser
-  local python_version="3.12"
-
-  if ! is_command_available conda; then
-    printf "${RED}Error: conda command not found. Is Conda installed and in your PATH?${NC}" >&2
-    exit 1
-  fi
-
-  if conda env list | grep -q "^${env_name} "; then
-    printf "Conda environment '${env_name}' exists. Checking Python version...\n"
-    current_version=$(conda run -n "${env_name}" python --version 2>&1 | cut -d' ' -f2 | cut -d'.' -f1,2)
-    if [ "$current_version" = "$python_version" ]; then
-      printf "Environment '${env_name}' already has Python ${python_version}. No action needed.\n"
-    else
-      printf "Updating environment '${env_name}' to Python ${python_version}...\n"
-      conda install -n "${env_name}" python="${python_version}" -y
-    fi
-  else
-    printf "Conda environment '${env_name}' does not exist. Creating with Python ${python_version}...\n"
-    conda create -n "${env_name}" python="${python_version}" -y
-  fi
-
-  eval "$(conda shell.bash hook)"
-  conda deactivate && conda activate "${env_name}"
-  "$CONDA_PREFIX"/bin/pip install uv
-
-  if [ -n "$TEST_PYPI_VERSION" ]; then
-    uv pip install fastapi libcst
-    uv pip install --extra-index-url https://test.pypi.org/simple/ \
-      llama-stack=="$TEST_PYPI_VERSION" \
-      "$normal_deps"
-    if [ -n "$optional_deps" ]; then
-      IFS='#' read -ra parts <<<"$optional_deps"
-      for part in "${parts[@]}"; do
-        echo "$part"
-        uv pip install $part
-      done
-    fi
-    if [ -n "$external_provider_deps" ]; then
-      IFS='#' read -ra parts <<<"$external_provider_deps"
-      for part in "${parts[@]}"; do
-        echo "$part"
-        uv pip install "$part"
-      done
-    fi
-  else
-    if [ -n "$LLAMA_STACK_DIR" ]; then
-      if [ ! -d "$LLAMA_STACK_DIR" ]; then
-        printf "${RED}Warning: LLAMA_STACK_DIR is set but directory does not exist: $LLAMA_STACK_DIR${NC}\n" >&2
-        exit 1
-      fi
-      printf "Installing from LLAMA_STACK_DIR: $LLAMA_STACK_DIR\n"
-      uv pip install --no-cache-dir -e "$LLAMA_STACK_DIR"
-    else
-      PYPI_VERSION="${PYPI_VERSION:-}"
-      if [ -n "$PYPI_VERSION" ]; then
-        SPEC_VERSION="llama-stack==${PYPI_VERSION}"
-      else
-        SPEC_VERSION="llama-stack"
-      fi
-      uv pip install --no-cache-dir "$SPEC_VERSION"
-    fi
-    if [ -n "$LLAMA_STACK_CLIENT_DIR" ]; then
-      if [ ! -d "$LLAMA_STACK_CLIENT_DIR" ]; then
-        printf "${RED}Warning: LLAMA_STACK_CLIENT_DIR is set but directory does not exist: $LLAMA_STACK_CLIENT_DIR${NC}\n" >&2
-        exit 1
-      fi
-      printf "Installing from LLAMA_STACK_CLIENT_DIR: $LLAMA_STACK_CLIENT_DIR\n"
-      uv pip install --no-cache-dir -e "$LLAMA_STACK_CLIENT_DIR"
-    fi
-    printf "Installing pip dependencies\n"
-    uv pip install $normal_deps
-    if [ -n "$optional_deps" ]; then
-      IFS='#' read -ra parts <<<"$optional_deps"
-      for part in "${parts[@]}"; do
-        echo "$part"
-        uv pip install $part
-      done
-    fi
-    if [ -n "$external_provider_deps" ]; then
-      IFS='#' read -ra parts <<<"$external_provider_deps"
-      for part in "${parts[@]}"; do
-        echo "Getting provider spec for module: $part and installing dependencies"
-        package_name=$(echo "$part" | sed 's/[<>=!].*//')
-        python3 -c "
-import importlib
-import sys
-try:
-    module = importlib.import_module(f'$package_name.provider')
-    spec = module.get_provider_spec()
-    if hasattr(spec, 'pip_packages') and spec.pip_packages:
-        print('\\n'.join(spec.pip_packages))
-except Exception as e:
-    print(f'Error getting provider spec for $package_name: {e}', file=sys.stderr)
-" | uv pip install -r -
-      done
-    fi
-  fi
-  mv "$build_file_path" "$CONDA_PREFIX"/llamastack-build.yaml
-  echo "Build spec configuration saved at $CONDA_PREFIX/llamastack-build.yaml"
-}
-
-ensure_conda_env_python310 "$env_name" "$build_file_path" "$normal_deps" "$optional_deps" "$external_provider_deps"

llama_stack/log.py

@@ -7,13 +7,11 @@
 import logging
 import os
 import re
-import sys
 from logging.config import dictConfig
 
 from rich.console import Console
 from rich.errors import MarkupError
 from rich.logging import RichHandler
-from termcolor import cprint
 
 from llama_stack.core.datatypes import LoggingConfig
 
@@ -66,7 +64,6 @@ def config_to_category_levels(category: str, level: str):
         category_levels["root"] = level_value
     elif category in CATEGORIES:
         category_levels[category] = level_value
-        logging.info(f"Setting '{category}' category to level '{level}'.")
     else:
         logging.warning(f"Unknown logging category: {category}. No changes made.")
     return category_levels
@@ -256,7 +253,6 @@ def get_logger(
 
 env_config = os.environ.get("LLAMA_STACK_LOGGING", "")
 if env_config:
-    cprint(f"Environment variable LLAMA_STACK_LOGGING found: {env_config}", color="yellow", file=sys.stderr)
     _category_levels.update(parse_environment_config(env_config))
 
 log_file = os.environ.get("LLAMA_STACK_LOG_FILE")

llama_stack/providers/utils/inference/openai_compat.py

@@ -31,9 +31,15 @@ from openai.types.chat import (
 from openai.types.chat import (
     ChatCompletionContentPartTextParam as OpenAIChatCompletionContentPartTextParam,
 )
+
+try:
     from openai.types.chat import (
         ChatCompletionMessageFunctionToolCall as OpenAIChatCompletionMessageFunctionToolCall,
     )
+except ImportError:
+    from openai.types.chat.chat_completion_message_tool_call import (
+        ChatCompletionMessageToolCall as OpenAIChatCompletionMessageFunctionToolCall,
+    )
 from openai.types.chat import (
     ChatCompletionMessageParam as OpenAIChatCompletionMessage,
 )

llama_stack/providers/utils/kvstore/config.py

@@ -75,6 +75,8 @@ class PostgresKVStoreConfig(CommonConfig):
     db: str = "llamastack"
     user: str
     password: str | None = None
+    ssl_mode: str | None = None
+    ca_cert_path: str | None = None
     table_name: str = "llamastack_kvstore"
 
     @classmethod

llama_stack/providers/utils/kvstore/postgres/postgres.py

@@ -30,6 +30,8 @@ class PostgresKVStoreImpl(KVStore):
                 database=self.config.db,
                 user=self.config.user,
                 password=self.config.password,
+                sslmode=self.config.ssl_mode,
+                sslrootcert=self.config.ca_cert_path,
             )
             self.conn.autocommit = True
             self.cursor = self.conn.cursor(cursor_factory=DictCursor)

pyproject.toml

@@ -33,7 +33,7 @@ dependencies = [
     "jsonschema",
     "llama-stack-client>=0.2.17",
     "llama-api-client>=0.1.2",
-    "openai>=1.99.6",
+    "openai>=1.99.6,<1.100.0",
     "prompt-toolkit",
     "python-dotenv",
     "python-jose[cryptography]",

scripts/integration-tests.sh

@@ -133,6 +133,10 @@ else
     EXTRA_PARAMS=""
 fi
 
+THIS_DIR=$(dirname "$0")
+ROOT_DIR="$THIS_DIR/.."
+cd $ROOT_DIR
+
 # Set recording directory
 if [[ "$RUN_VISION_TESTS" == "true" ]]; then
     export LLAMA_STACK_TEST_RECORDING_DIR="tests/integration/recordings/vision"
@@ -140,10 +144,27 @@ else
     export LLAMA_STACK_TEST_RECORDING_DIR="tests/integration/recordings"
 fi
 
+# check if "llama" and "pytest" are available. this script does not use `uv run` given
+# it can be used in a pre-release environment where we have not been able to tell
+# uv about pre-release dependencies properly (yet).
+if ! command -v llama &> /dev/null; then
+    echo "llama could not be found, ensure llama-stack is installed"
+    exit 1
+fi
+
+if ! command -v pytest &> /dev/null; then
+    echo "pytest could not be found, ensure pytest is installed"
+    exit 1
+fi
+
 # Start Llama Stack Server if needed
 if [[ "$STACK_CONFIG" == *"server:"* ]]; then
+    # check if server is already running
+    if curl -s http://localhost:8321/v1/health 2>/dev/null | grep -q "OK"; then
+        echo "Llama Stack Server is already running, skipping start"
+    else
         echo "=== Starting Llama Stack Server ==="
-    nohup uv run llama stack run ci-tests --image-type venv > server.log 2>&1 &
+        nohup llama stack run ci-tests --image-type venv > server.log 2>&1 &
 
         echo "Waiting for Llama Stack Server to start..."
         for i in {1..30}; do
@@ -161,6 +182,7 @@ if [[ "$STACK_CONFIG" == *"server:"* ]]; then
         done
         echo ""
     fi
+fi
 
 # Run tests
 echo "=== Running Integration Tests ==="
@@ -180,7 +202,7 @@ fi
 if [[ "$RUN_VISION_TESTS" == "true" ]]; then
     echo "Running vision tests..."
     set +e
-    uv run pytest -s -v tests/integration/inference/test_vision_inference.py \
+    pytest -s -v tests/integration/inference/test_vision_inference.py \
         --stack-config="$STACK_CONFIG" \
         -k "$PYTEST_PATTERN" \
         --vision-model=ollama/llama3.2-vision:11b \
@@ -248,7 +270,7 @@ echo "=== Running all collected tests in a single pytest command ==="
 echo "Total test files: $(echo $TEST_FILES | wc -w)"
 
 set +e
-uv run pytest -s -v $TEST_FILES \
+pytest -s -v $TEST_FILES \
     --stack-config="$STACK_CONFIG" \
     -k "$PYTEST_PATTERN" \
     --text-model="$TEXT_MODEL" \

uv.lock

@@ -1856,7 +1856,7 @@ requires-dist = [
     { name = "llama-api-client", specifier = ">=0.1.2" },
     { name = "llama-stack-client", specifier = ">=0.2.17" },
     { name = "llama-stack-client", marker = "extra == 'ui'", specifier = ">=0.2.17" },
-    { name = "openai", specifier = ">=1.99.6" },
+    { name = "openai", specifier = ">=1.99.6,<1.100.0" },
     { name = "opentelemetry-exporter-otlp-proto-http", specifier = ">=1.30.0" },
     { name = "opentelemetry-sdk", specifier = ">=1.30.0" },
     { name = "pandas", marker = "extra == 'ui'" },