Merge e0dda3bb06 into sapling-pr-archive-ehhuang

README.md

@@ -92,7 +92,7 @@ As more providers start supporting Llama 4, you can use them in Llama Stack as w
 To try Llama Stack locally, run:
 
 ```bash
-curl -LsSf https://github.com/meta-llama/llama-stack/raw/main/scripts/install.sh | bash
+curl -LsSf https://github.com/llamastack/llama-stack/raw/main/scripts/install.sh | bash
 ```
 
 ### Overview

docs/docs/advanced_apis/post_training.mdx

@@ -51,8 +51,9 @@ device: cpu
 You can access the HuggingFace trainer via the `starter` distribution:
 
 ```bash
-llama stack build --distro starter --image-type venv
-llama stack run ~/.llama/distributions/starter/starter-run.yaml
+uv pip install llama-stack
+llama stack list-deps starter | xargs -L1 uv pip install
+llama stack run starter
 ```
 
 ### Usage Example

docs/docs/building_applications/playground.mdx

@@ -175,8 +175,8 @@ llama-stack-client benchmarks register \
 **1. Start the Llama Stack API Server**
 
 ```bash
-# Build and run a distribution (example: together)
-llama stack build --distro together --image-type venv
+uv pip install llama-stack
+llama stack list-deps together | xargs -L1 uv pip install
 llama stack run together
 ```
 
@@ -209,7 +209,8 @@ The playground works with any Llama Stack distribution. Popular options include:
 <TabItem value="together" label="Together AI">
 
 ```bash
-llama stack build --distro together --image-type venv
+uv pip install llama-stack
+llama stack list-deps together | xargs -L1 uv pip install
 llama stack run together
 ```
 
@@ -222,7 +223,8 @@ llama stack run together
 <TabItem value="ollama" label="Ollama (Local)">
 
 ```bash
-llama stack build --distro ollama --image-type venv
+uv pip install llama-stack
+llama stack list-deps ollama | xargs -L1 uv pip install
 llama stack run ollama
 ```
 
@@ -235,7 +237,8 @@ llama stack run ollama
 <TabItem value="meta-reference" label="Meta Reference">
 
 ```bash
-llama stack build --distro meta-reference --image-type venv
+uv pip install llama-stack
+llama stack list-deps meta-reference | xargs -L1 uv pip install
 llama stack run meta-reference
 ```
 

docs/docs/building_applications/rag.mdx

@@ -20,7 +20,9 @@ RAG enables your applications to reference and recall information from external
 In one terminal, start the Llama Stack server:
 
 ```bash
-uv run llama stack build --distro starter --image-type venv --run
+uv pip install llama-stack
+llama stack list-deps starter | xargs -L1 uv pip install
+llama stack run starter
 ```
 
 ### 2. Connect with OpenAI Client

docs/docs/contributing/new_api_provider.mdx

@@ -67,7 +67,7 @@ def get_base_url(self) -> str:
 
 ## Testing the Provider
 
-Before running tests, you must have required dependencies installed. This depends on the providers or distributions you are testing. For example, if you are testing the `together` distribution, you should install dependencies via `llama stack build --distro together`.
+Before running tests, you must have required dependencies installed. This depends on the providers or distributions you are testing. For example, if you are testing the `together` distribution, install its dependencies with `llama stack list-deps together | xargs -L1 uv pip install`.
 
 ### 1. Integration Testing
 

docs/docs/distributions/importing_as_library.mdx

@@ -12,7 +12,7 @@ This avoids the overhead of setting up a server.
 ```bash
 # setup
 uv pip install llama-stack
-llama stack build --distro starter --image-type venv
+llama stack list-deps starter | xargs -L1 uv pip install
 ```
 
 ```python

docs/docs/distributions/ondevice_distro/android_sdk.md

@@ -59,7 +59,7 @@ Start a Llama Stack server on localhost. Here is an example of how you can do th
 uv venv starter --python 3.12
 source starter/bin/activate  # On Windows: starter\Scripts\activate
 pip install --no-cache llama-stack==0.2.2
-llama stack build --distro starter --image-type venv
+llama stack list-deps starter | xargs -L1 uv pip install
 export FIREWORKS_API_KEY=<SOME_KEY>
 llama stack run starter --port 5050
 ```

docs/docs/distributions/self_hosted_distro/dell.md

@@ -166,10 +166,11 @@ docker run \
 
 ### Via venv
 
-Make sure you have done `pip install llama-stack` and have the Llama Stack CLI available.
+Install the package and distribution dependencies before launching:
 
 ```bash
-llama stack build --distro dell --image-type venv
+uv pip install llama-stack
+llama stack list-deps dell | xargs -L1 uv pip install
 INFERENCE_MODEL=$INFERENCE_MODEL \
 DEH_URL=$DEH_URL \
 CHROMA_URL=$CHROMA_URL \

docs/docs/distributions/self_hosted_distro/meta-reference-gpu.md

@@ -81,10 +81,11 @@ docker run \
 
 ### Via venv
 
-Make sure you have done `uv pip install llama-stack` and have the Llama Stack CLI available.
+Install the package and this distribution’s dependencies into your active virtualenv:
 
 ```bash
-llama stack build --distro meta-reference-gpu --image-type venv
+uv pip install llama-stack
+llama stack list-deps meta-reference-gpu | xargs -L1 uv pip install
 INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
 llama stack run distributions/meta-reference-gpu/run.yaml \
   --port 8321

docs/docs/distributions/self_hosted_distro/nvidia.md

@@ -136,11 +136,12 @@ docker run \
 
 ### Via venv
 
-If you've set up your local development environment, you can also build the image using your local virtual environment.
+If you've set up your local development environment, you can install this distribution into your virtualenv:
 
 ```bash
+uv pip install llama-stack
+llama stack list-deps nvidia | xargs -L1 uv pip install
 INFERENCE_MODEL=meta-llama/Llama-3.1-8B-Instruct
-llama stack build --distro nvidia --image-type venv
 NVIDIA_API_KEY=$NVIDIA_API_KEY \
 INFERENCE_MODEL=$INFERENCE_MODEL \
 llama stack run ./run.yaml \

docs/docs/providers/external/external-providers-guide.mdx

@@ -240,6 +240,6 @@ additional_pip_packages:
 - sqlalchemy[asyncio]
 ```
 
-No other steps are required other than `llama stack build` and `llama stack run`. The build process will use `module` to install all of the provider dependencies, retrieve the spec, etc.
+No other steps are required beyond installing dependencies with `llama stack list-deps <distro> | xargs -L1 uv pip install` and then running `llama stack run`. The CLI will use `module` to install the provider dependencies, retrieve the spec, etc.
 
 The provider will now be available in Llama Stack with the type `remote::ramalama`.

docs/getting_started.ipynb

@@ -123,7 +123,9 @@
     "  del os.environ[\"UV_SYSTEM_PYTHON\"]\n",
     "\n",
     "# this command installs all the dependencies needed for the llama stack server with the together inference provider\n",
-        "!uv run --with llama-stack llama stack build --distro together\n",
+    "!uv pip install llama-stack\n",
+    "llama stack list-deps together | xargs -L1 uv pip install\n",
+    "llama stack run together\n",
     "\n",
     "def run_llama_stack_server_background():\n",
     "    log_file = open(\"llama_stack_server.log\", \"w\")\n",

docs/getting_started_llama4.ipynb

@@ -233,7 +233,9 @@
     "  del os.environ[\"UV_SYSTEM_PYTHON\"]\n",
     "\n",
     "# this command installs all the dependencies needed for the llama stack server\n",
-        "!uv run --with llama-stack llama stack build --distro meta-reference-gpu\n",
+    "!uv pip install llama-stack\n",
+    "llama stack list-deps meta-reference-gpu | xargs -L1 uv pip install\n",
+    "llama stack run meta-reference-gpu\n",
     "\n",
     "def run_llama_stack_server_background():\n",
     "    log_file = open(\"llama_stack_server.log\", \"w\")\n",

docs/getting_started_llama_api.ipynb

@@ -223,7 +223,9 @@
     "  del os.environ[\"UV_SYSTEM_PYTHON\"]\n",
     "\n",
     "# this command installs all the dependencies needed for the llama stack server\n",
-        "!uv run --with llama-stack llama stack build --distro llama_api\n",
+    "!uv pip install llama-stack\n",
+    "llama stack list-deps llama_api | xargs -L1 uv pip install\n",
+    "llama stack run llama_api\n",
     "\n",
     "def run_llama_stack_server_background():\n",
     "    log_file = open(\"llama_stack_server.log\", \"w\")\n",

docs/notebooks/Alpha_Llama_Stack_Post_Training.ipynb

@@ -2864,7 +2864,8 @@
     }
    ],
    "source": [
-    "!llama stack build --distro experimental-post-training --image-type venv --image-name __system__"
+    "!uv pip install llama-stack\n",
+    "llama stack list-deps experimental-post-training | xargs -L1 uv pip install --image-name __system__\n"
    ]
   },
   {

docs/notebooks/Llama_Stack_Agent_Workflows.ipynb

@@ -38,7 +38,8 @@
    "source": [
     "# NBVAL_SKIP\n",
     "!pip install -U llama-stack\n",
-    "!UV_SYSTEM_PYTHON=1 llama stack build --distro fireworks --image-type venv"
+    "!UV_SYSTEM_PYTHON=1 uv pip install llama-stack\n",
+    "llama stack list-deps fireworks | xargs -L1 uv pip install\n"
    ]
   },
   {

docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb

@@ -57,7 +57,8 @@
    "outputs": [],
    "source": [
     "# NBVAL_SKIP\n",
-        "!UV_SYSTEM_PYTHON=1 llama stack build --distro together --image-type venv"
+    "!UV_SYSTEM_PYTHON=1 uv pip install llama-stack\n",
+    "llama stack list-deps together | xargs -L1 uv pip install\n"
    ]
   },
   {

docs/notebooks/crewai/Llama_Stack_CrewAI.ipynb

@@ -136,7 +136,9 @@
     "    \"\"\"Build and run LlamaStack server in one step using --run flag\"\"\"\n",
     "    log_file = open(\"llama_stack_server.log\", \"w\")\n",
     "    process = subprocess.Popen(\n",
-    "        \"uv run --with llama-stack llama stack build --distro starter --image-type venv --run\",\n",
+    "        \"uv pip install llama-stack\n",
+    "llama stack list-deps starter | xargs -L1 uv pip install\n",
+    "llama stack run starter --image-type venv --run\",\n",
     "        shell=True,\n",
     "        stdout=log_file,\n",
     "        stderr=log_file,\n",
@@ -172,7 +174,7 @@
     "\n",
     "def kill_llama_stack_server():\n",
     "    # Kill any existing llama stack server processes using pkill command\n",
-    "    os.system(\"pkill -f llama_stack.core.server.server\")"
+    "    os.system(\"pkill -f llama_stack.core.server.server\")\n"
    ]
   },
   {

docs/notebooks/langchain/Llama_Stack_LangChain.ipynb

@@ -105,7 +105,9 @@
     "    \"\"\"Build and run LlamaStack server in one step using --run flag\"\"\"\n",
     "    log_file = open(\"llama_stack_server.log\", \"w\")\n",
     "    process = subprocess.Popen(\n",
-    "        \"uv run --with llama-stack llama stack build --distro starter --image-type venv --run\",\n",
+    "        \"uv pip install llama-stack\n",
+    "llama stack list-deps starter | xargs -L1 uv pip install\n",
+    "llama stack run starter --image-type venv --run\",\n",
     "        shell=True,\n",
     "        stdout=log_file,\n",
     "        stderr=log_file,\n",
@@ -141,7 +143,7 @@
     "\n",
     "def kill_llama_stack_server():\n",
     "    # Kill any existing llama stack server processes using pkill command\n",
-    "    os.system(\"pkill -f llama_stack.core.server.server\")"
+    "    os.system(\"pkill -f llama_stack.core.server.server\")\n"
    ]
   },
   {

docs/notebooks/nvidia/beginner_e2e/Llama_Stack_NVIDIA_E2E_Flow.ipynb

@@ -91,9 +91,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "```bash\n",
-    "LLAMA_STACK_DIR=$(pwd) llama stack build --distro nvidia --image-type venv\n",
-    "```"
+    "```bash\nuv pip install llama-stack\nllama stack list-deps nvidia | xargs -L1 uv pip install\n```\n"
    ]
   },
   {

docs/notebooks/nvidia/tool_calling/1_data_preparation.ipynb

@@ -80,9 +80,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "```bash\n",
-    "LLAMA_STACK_DIR=$(pwd) llama stack build --distro nvidia --image-type venv\n",
-    "```"
+    "```bash\nuv pip install llama-stack\nllama stack list-deps nvidia | xargs -L1 uv pip install\n```\n"
    ]
   },
   {

docs/quick_start.ipynb

@@ -145,7 +145,9 @@
     "  del os.environ[\"UV_SYSTEM_PYTHON\"]\n",
     "\n",
     "# this command installs all the dependencies needed for the llama stack server with the ollama inference provider\n",
-        "!uv run --with llama-stack llama stack build --distro starter\n",
+    "!uv pip install llama-stack\n",
+    "llama stack list-deps starter | xargs -L1 uv pip install\n",
+    "llama stack run starter\n",
     "\n",
     "def run_llama_stack_server_background():\n",
     "    log_file = open(\"llama_stack_server.log\", \"w\")\n",

docs/src/pages/index.js

@@ -47,11 +47,12 @@ function QuickStart() {
               <pre><code>{`# Install uv and start Ollama
 ollama run llama3.2:3b --keepalive 60m
 
+# Install server dependencies
+uv pip install llama-stack
+llama stack list-deps starter | xargs -L1 uv pip install
+
 # Run Llama Stack server
-OLLAMA_URL=http://localhost:11434 \\
-  uv run --with llama-stack \\
-  llama stack build --distro starter \\
-  --image-type venv --run
+OLLAMA_URL=http://localhost:11434 llama stack run starter
 
 # Try the Python SDK
 from llama_stack_client import LlamaStackClient

docs/zero_to_hero_guide/README.md

@@ -78,17 +78,15 @@ If you're looking for more specific topics, we have a [Zero to Hero Guide](#next
 
 ## Build, Configure, and Run Llama Stack
 
-1. **Build the Llama Stack**:
-   Build the Llama Stack using the `starter` template:
+1. **Install Llama Stack and dependencies**:
    ```bash
-   uv run --with llama-stack llama stack build --distro starter --image-type venv
+   uv pip install llama-stack
+   llama stack list-deps starter | xargs -L1 uv pip install
    ```
-   **Expected Output:**
+
+2. **Start the distribution**:
    ```bash
-   ...
-   Build Successful!
-   You can find the newly-built template here: ~/.llama/distributions/starter/starter-run.yaml
-   You can run the new Llama Stack Distro via: uv run --with llama-stack llama stack run starter
+   llama stack run starter
    ```
 
 3. **Set the ENV variables by exporting them to the terminal**:

llama_stack/ui/package.json

@@ -43,16 +43,16 @@
     "@testing-library/dom": "^10.4.1",
     "@testing-library/jest-dom": "^6.8.0",
     "@testing-library/react": "^16.3.0",
-    "@types/jest": "^29.5.14",
+    "@types/jest": "^30.0.0",
     "@types/node": "^24",
     "@types/react": "^19",
     "@types/react-dom": "^19",
     "eslint": "^9",
-    "eslint-config-next": "15.5.2",
+    "eslint-config-next": "15.5.6",
     "eslint-config-prettier": "^10.1.8",
     "eslint-plugin-prettier": "^5.5.4",
-    "jest": "^29.7.0",
-    "jest-environment-jsdom": "^30.1.2",
+    "jest": "^30.2.0",
+    "jest-environment-jsdom": "^30.2.0",
     "prettier": "3.6.2",
     "tailwindcss": "^4",
     "ts-node": "^10.9.2",

scripts/install.sh

@@ -5,10 +5,10 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-[ -z "$BASH_VERSION" ] && {
-  echo "This script must be run with bash" >&2
-  exit 1
-}
+[ -z "${BASH_VERSION:-}" ] && exec /usr/bin/env bash "$0" "$@"
+if set -o | grep -Eq 'posix[[:space:]]+on'; then
+  exec /usr/bin/env bash "$0" "$@"
+fi
 
 set -Eeuo pipefail
 
@@ -18,12 +18,110 @@ MODEL_ALIAS="llama3.2:3b"
 SERVER_IMAGE="docker.io/llamastack/distribution-starter:latest"
 WAIT_TIMEOUT=30
 TEMP_LOG=""
+WITH_TELEMETRY=true
+TELEMETRY_SERVICE_NAME="llama-stack"
+TELEMETRY_SINKS="otel_trace,otel_metric"
+OTEL_EXPORTER_OTLP_ENDPOINT="http://otel-collector:4318"
+TEMP_TELEMETRY_DIR=""
+
+materialize_telemetry_configs() {
+  local dest="$1"
+  mkdir -p "$dest"
+  local otel_cfg="${dest}/otel-collector-config.yaml"
+  local prom_cfg="${dest}/prometheus.yml"
+  local graf_cfg="${dest}/grafana-datasources.yaml"
+
+  for asset in "$otel_cfg" "$prom_cfg" "$graf_cfg"; do
+    if [ -e "$asset" ]; then
+      die "Telemetry asset ${asset} already exists; refusing to overwrite"
+    fi
+  done
+
+  cat <<'EOF' > "$otel_cfg"
+receivers:
+  otlp:
+    protocols:
+      grpc:
+        endpoint: 0.0.0.0:4317
+      http:
+        endpoint: 0.0.0.0:4318
+
+processors:
+  batch:
+    timeout: 1s
+    send_batch_size: 1024
+
+exporters:
+  # Export traces to Jaeger
+  otlp/jaeger:
+    endpoint: jaeger:4317
+    tls:
+      insecure: true
+
+  # Export metrics to Prometheus
+  prometheus:
+    endpoint: 0.0.0.0:9464
+    namespace: llama_stack
+
+  # Debug exporter for troubleshooting
+  debug:
+    verbosity: detailed
+
+service:
+  pipelines:
+    traces:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [otlp/jaeger, debug]
+
+    metrics:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [prometheus, debug]
+EOF
+
+  cat <<'EOF' > "$prom_cfg"
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+
+scrape_configs:
+  - job_name: 'prometheus'
+    static_configs:
+      - targets: ['localhost:9090']
+
+  - job_name: 'otel-collector'
+    static_configs:
+      - targets: ['otel-collector:9464']
+EOF
+
+  cat <<'EOF' > "$graf_cfg"
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    type: prometheus
+    access: proxy
+    url: http://prometheus:9090
+    isDefault: true
+    editable: true
+
+  - name: Jaeger
+    type: jaeger
+    access: proxy
+    url: http://jaeger:16686
+    editable: true
+EOF
+}
 
 # Cleanup function to remove temporary files
 cleanup() {
   if [ -n "$TEMP_LOG" ] && [ -f "$TEMP_LOG" ]; then
     rm -f "$TEMP_LOG"
   fi
+  if [ -n "$TEMP_TELEMETRY_DIR" ] && [ -d "$TEMP_TELEMETRY_DIR" ]; then
+    rm -rf "$TEMP_TELEMETRY_DIR"
+  fi
 }
 
 # Set up trap to clean up on exit, error, or interrupt
@@ -32,7 +130,7 @@ trap cleanup EXIT ERR INT TERM
 log(){ printf "\e[1;32m%s\e[0m\n" "$*"; }
 die(){
   printf "\e[1;31m❌ %s\e[0m\n" "$*" >&2
-  printf "\e[1;31m🐛 Report an issue @ https://github.com/meta-llama/llama-stack/issues if you think it's a bug\e[0m\n" >&2
+  printf "\e[1;31m🐛 Report an issue @ https://github.com/llamastack/llama-stack/issues if you think it's a bug\e[0m\n" >&2
   exit 1
 }
 
@@ -89,6 +187,12 @@ Options:
     -m, --model MODEL          Model alias to use (default: ${MODEL_ALIAS})
     -i, --image IMAGE          Server image (default: ${SERVER_IMAGE})
     -t, --timeout SECONDS      Service wait timeout in seconds (default: ${WAIT_TIMEOUT})
+    --with-telemetry           Provision Jaeger, OTEL Collector, Prometheus, and Grafana (default: enabled)
+    --no-telemetry, --without-telemetry
+                              Skip provisioning the telemetry stack
+    --telemetry-service NAME   Service name reported to telemetry (default: ${TELEMETRY_SERVICE_NAME})
+    --telemetry-sinks SINKS    Comma-separated telemetry sinks (default: ${TELEMETRY_SINKS})
+    --otel-endpoint URL        OTLP endpoint provided to Llama Stack (default: ${OTEL_EXPORTER_OTLP_ENDPOINT})
     -h, --help                 Show this help message
 
 For more information:
@@ -127,6 +231,26 @@ while [[ $# -gt 0 ]]; do
             WAIT_TIMEOUT="$2"
             shift 2
             ;;
+        --with-telemetry)
+            WITH_TELEMETRY=true
+            shift
+            ;;
+        --no-telemetry|--without-telemetry)
+            WITH_TELEMETRY=false
+            shift
+            ;;
+        --telemetry-service)
+            TELEMETRY_SERVICE_NAME="$2"
+            shift 2
+            ;;
+        --telemetry-sinks)
+            TELEMETRY_SINKS="$2"
+            shift 2
+            ;;
+        --otel-endpoint)
+            OTEL_EXPORTER_OTLP_ENDPOINT="$2"
+            shift 2
+            ;;
         *)
             die "Unknown option: $1"
             ;;
@@ -171,7 +295,11 @@ if [ "$ENGINE" = "podman" ] && [ "$(uname -s)" = "Darwin" ]; then
 fi
 
 # Clean up any leftovers from earlier runs
-for name in ollama-server llama-stack; do
+containers=(ollama-server llama-stack)
+if [ "$WITH_TELEMETRY" = true ]; then
+  containers+=(jaeger otel-collector prometheus grafana)
+fi
+for name in "${containers[@]}"; do
   ids=$($ENGINE ps -aq --filter "name=^${name}$")
   if [ -n "$ids" ]; then
     log "⚠️  Found existing container(s) for '${name}', removing..."
@@ -191,6 +319,64 @@ if ! $ENGINE network inspect llama-net >/dev/null 2>&1; then
   fi
 fi
 
+###############################################################################
+# Telemetry Stack
+###############################################################################
+if [ "$WITH_TELEMETRY" = true ]; then
+  TEMP_TELEMETRY_DIR="$(mktemp -d)"
+  TELEMETRY_ASSETS_DIR="$TEMP_TELEMETRY_DIR"
+  log "🧰 Materializing telemetry configs..."
+  materialize_telemetry_configs "$TELEMETRY_ASSETS_DIR"
+
+  log "📡 Starting telemetry stack..."
+
+  if ! execute_with_log $ENGINE run -d "${PLATFORM_OPTS[@]}" --name jaeger \
+    --network llama-net \
+    -e COLLECTOR_ZIPKIN_HOST_PORT=:9411 \
+    -p 16686:16686 \
+    -p 14250:14250 \
+    -p 9411:9411 \
+    docker.io/jaegertracing/all-in-one:latest > /dev/null 2>&1; then
+    die "Jaeger startup failed"
+  fi
+
+  if ! execute_with_log $ENGINE run -d "${PLATFORM_OPTS[@]}" --name otel-collector \
+    --network llama-net \
+    -p 4318:4318 \
+    -p 4317:4317 \
+    -p 9464:9464 \
+    -p 13133:13133 \
+    -v "${TELEMETRY_ASSETS_DIR}/otel-collector-config.yaml:/etc/otel-collector-config.yaml:Z" \
+    docker.io/otel/opentelemetry-collector-contrib:latest \
+    --config /etc/otel-collector-config.yaml > /dev/null 2>&1; then
+    die "OpenTelemetry Collector startup failed"
+  fi
+
+  if ! execute_with_log $ENGINE run -d "${PLATFORM_OPTS[@]}" --name prometheus \
+    --network llama-net \
+    -p 9090:9090 \
+    -v "${TELEMETRY_ASSETS_DIR}/prometheus.yml:/etc/prometheus/prometheus.yml:Z" \
+    docker.io/prom/prometheus:latest \
+    --config.file=/etc/prometheus/prometheus.yml \
+    --storage.tsdb.path=/prometheus \
+    --web.console.libraries=/etc/prometheus/console_libraries \
+    --web.console.templates=/etc/prometheus/consoles \
+    --storage.tsdb.retention.time=200h \
+    --web.enable-lifecycle > /dev/null 2>&1; then
+    die "Prometheus startup failed"
+  fi
+
+  if ! execute_with_log $ENGINE run -d "${PLATFORM_OPTS[@]}" --name grafana \
+    --network llama-net \
+    -p 3000:3000 \
+    -e GF_SECURITY_ADMIN_PASSWORD=admin \
+    -e GF_USERS_ALLOW_SIGN_UP=false \
+    -v "${TELEMETRY_ASSETS_DIR}/grafana-datasources.yaml:/etc/grafana/provisioning/datasources/datasources.yaml:Z" \
+    docker.io/grafana/grafana:11.0.0 > /dev/null 2>&1; then
+    die "Grafana startup failed"
+  fi
+fi
+
 ###############################################################################
 # 1. Ollama
 ###############################################################################
@@ -218,9 +404,19 @@ fi
 ###############################################################################
 # 2. Llama‑Stack
 ###############################################################################
+server_env_opts=()
+if [ "$WITH_TELEMETRY" = true ]; then
+  server_env_opts+=(
+    -e TELEMETRY_SINKS="${TELEMETRY_SINKS}"
+    -e OTEL_EXPORTER_OTLP_ENDPOINT="${OTEL_EXPORTER_OTLP_ENDPOINT}"
+    -e OTEL_SERVICE_NAME="${TELEMETRY_SERVICE_NAME}"
+  )
+fi
+
 cmd=( run -d "${PLATFORM_OPTS[@]}" --name llama-stack \
       --network llama-net \
       -p "${PORT}:${PORT}" \
+      "${server_env_opts[@]}" \
       -e OLLAMA_URL="http://ollama-server:${OLLAMA_PORT}" \
       "${SERVER_IMAGE}" --port "${PORT}")
 
@@ -244,5 +440,12 @@ log "👉  API endpoint: http://localhost:${PORT}"
 log "📖 Documentation: https://llamastack.github.io/latest/references/api_reference/index.html"
 log "💻 To access the llama stack CLI, exec into the container:"
 log "   $ENGINE exec -ti llama-stack bash"
+if [ "$WITH_TELEMETRY" = true ]; then
+  log "📡 Telemetry dashboards:"
+  log "   Jaeger UI:      http://localhost:16686"
+  log "   Prometheus UI:  http://localhost:9090"
+  log "   Grafana UI:     http://localhost:3000 (admin/admin)"
+  log "   OTEL Collector: http://localhost:4318"
+fi
 log "🐛 Report an issue @ https://github.com/llamastack/llama-stack/issues if you think it's a bug"
 log ""