Merge branch 'main' into pr1573

docs/_static/llama-stack-spec.html

@@ -4354,24 +4354,6 @@
                         "type": "string",
                         "description": "Unique identifier for the tool call this response is for"
                     },
-                    "tool_name": {
-                        "oneOf": [
-                            {
-                                "type": "string",
-                                "enum": [
-                                    "brave_search",
-                                    "wolfram_alpha",
-                                    "photogen",
-                                    "code_interpreter"
-                                ],
-                                "title": "BuiltinTool"
-                            },
-                            {
-                                "type": "string"
-                            }
-                        ],
-                        "description": "Name of the tool that was called"
-                    },
                     "content": {
                         "$ref": "#/components/schemas/InterleavedContent",
                         "description": "The response content from the tool"
@@ -4381,7 +4363,6 @@
                 "required": [
                     "role",
                     "call_id",
-                    "tool_name",
                     "content"
                 ],
                 "title": "ToolResponseMessage",

docs/_static/llama-stack-spec.yaml

@@ -2947,17 +2947,6 @@ components:
           type: string
           description: >-
             Unique identifier for the tool call this response is for
-        tool_name:
-          oneOf:
-            - type: string
-              enum:
-                - brave_search
-                - wolfram_alpha
-                - photogen
-                - code_interpreter
-              title: BuiltinTool
-            - type: string
-          description: Name of the tool that was called
         content:
           $ref: '#/components/schemas/InterleavedContent'
           description: The response content from the tool
@@ -2965,7 +2954,6 @@ components:
       required:
         - role
         - call_id
-        - tool_name
         - content
       title: ToolResponseMessage
       description: >-

docs/source/distributions/self_hosted_distro/passthrough.md

@@ -0,0 +1,42 @@
+---
+orphan: true
+---
+<!-- This file was auto-generated by distro_codegen.py, please edit source -->
+# Passthrough Distribution
+
+```{toctree}
+:maxdepth: 2
+:hidden:
+
+self
+```
+
+The `llamastack/distribution-passthrough` distribution consists of the following provider configurations.
+
+| API | Provider(s) |
+|-----|-------------|
+| agents | `inline::meta-reference` |
+| datasetio | `remote::huggingface`, `inline::localfs` |
+| eval | `inline::meta-reference` |
+| inference | `remote::passthrough`, `inline::sentence-transformers` |
+| safety | `inline::llama-guard` |
+| scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
+| telemetry | `inline::meta-reference` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `remote::wolfram-alpha`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |
+| vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
+
+
+### Environment Variables
+
+The following environment variables can be configured:
+
+- `LLAMA_STACK_PORT`: Port for the Llama Stack distribution server (default: `5001`)
+- `PASSTHROUGH_API_KEY`: Passthrough API Key (default: ``)
+- `PASSTHROUGH_URL`: Passthrough URL (default: ``)
+
+### Models
+
+The following models are available by default:
+
+- `llama3.1-8b-instruct `
+- `llama3.2-11b-vision-instruct `