Adds markdown-link-check and fixes a broken link

Signed-off-by: Adrian Cole <adrian.cole@elastic.co>

.pre-commit-config.yaml

@@ -51,3 +51,9 @@ repos:
 #   hooks:
 #     - id: pydoclint
 #       args: [--config=pyproject.toml]
+
+- repo: https://github.com/tcort/markdown-link-check
+  rev: v3.11.2
+  hooks:
+    - id: markdown-link-check
+      args: ['--quiet']

docs/cli_reference.md

@@ -5,7 +5,7 @@ The `llama` CLI tool helps you setup and use the Llama toolchain & agentic syste
 ### Subcommands
 1. `download`: `llama` cli tools supports downloading the model from Meta or Hugging Face.
 2. `model`: Lists available models and their properties.
-3. `stack`: Allows you to build and run a Llama Stack server. You can read more about this [here](/docs/cli_reference.md#step-3-building-configuring-and-running-llama-stack-servers).
+3. `stack`: Allows you to build and run a Llama Stack server. You can read more about this [here](cli_reference.md#step-3-building-and-configuring-llama-stack-distributions).
 
 ### Sample Usage
 

llama_stack/providers/registry/inference.py

@@ -98,9 +98,7 @@ def available_providers() -> List[ProviderSpec]:
             api=Api.inference,
             adapter=AdapterSpec(
                 adapter_id="bedrock",
-                pip_packages=[
-                    "boto3"
-                ],
+                pip_packages=["boto3"],
                 module="llama_stack.providers.adapters.inference.bedrock",
                 config_class="llama_stack.providers.adapters.inference.bedrock.BedrockConfig",
             ),

llama_stack/providers/utils/inference/augment_messages.py

@@ -34,7 +34,8 @@ def augment_messages_for_tools(request: ChatCompletionRequest) -> List[Message]:
         return request.messages
 
     if model.model_family == ModelFamily.llama3_1 or (
-        model.model_family == ModelFamily.llama3_2 and is_multimodal(model.core_model_id)
+        model.model_family == ModelFamily.llama3_2
+        and is_multimodal(model.core_model_id)
     ):
         # llama3.1 and llama3.2 multimodal models follow the same tool prompt format
         return augment_messages_for_tools_llama_3_1(request)