phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: add support for require_approval argument when creating response

Browse source 
Signed-off-by: Gordon Sim <gsim@redhat.com>
This commit is contained in:
Gordon Sim 2025-09-26 20:36:42 +01:00
parent 7c466a7ec5
commit 449177d316
11 changed files with 362 additions and 36 deletions
Download patch file Download diff file Expand all files Collapse all files

24
docs/docs/providers/agents/index.mdx
View file

@ -1,12 +1,12 @@
---
description: "Agents API for creating and interacting with agentic systems.
Main functionalities provided by this API:
- Create agents with specific instructions and ability to use tools.
- Interactions with agents are grouped into sessions (\"threads\"), and each interaction is called a \"turn\".
- Agents can be provided with various tools (see the ToolGroups and ToolRuntime APIs for more details).
- Agents can be provided with various shields (see the Safety API for more details).
- Agents can also use Memory to retrieve information from knowledge bases. See the RAG Tool and Vector IO APIs for more details."
Main functionalities provided by this API:
- Create agents with specific instructions and ability to use tools.
- Interactions with agents are grouped into sessions (\"threads\"), and each interaction is called a \"turn\".
- Agents can be provided with various tools (see the ToolGroups and ToolRuntime APIs for more details).
- Agents can be provided with various shields (see the Safety API for more details).
- Agents can also use Memory to retrieve information from knowledge bases. See the RAG Tool and Vector IO APIs for more details."
sidebar_label: Agents
title: Agents
---
@ -17,11 +17,11 @@ title: Agents
Agents API for creating and interacting with agentic systems.
Main functionalities provided by this API:
- Create agents with specific instructions and ability to use tools.
- Interactions with agents are grouped into sessions ("threads"), and each interaction is called a "turn".
- Agents can be provided with various tools (see the ToolGroups and ToolRuntime APIs for more details).
- Agents can be provided with various shields (see the Safety API for more details).
- Agents can also use Memory to retrieve information from knowledge bases. See the RAG Tool and Vector IO APIs for more details.
Main functionalities provided by this API:
- Create agents with specific instructions and ability to use tools.
- Interactions with agents are grouped into sessions ("threads"), and each interaction is called a "turn".
- Agents can be provided with various tools (see the ToolGroups and ToolRuntime APIs for more details).
- Agents can be provided with various shields (see the Safety API for more details).
- Agents can also use Memory to retrieve information from knowledge bases. See the RAG Tool and Vector IO APIs for more details.
This section contains documentation for all available providers for the **agents** API.

24
docs/docs/providers/batches/index.mdx
View file

@ -1,14 +1,14 @@
---
description: "The Batches API enables efficient processing of multiple requests in a single operation,
particularly useful for processing large datasets, batch evaluation workflows, and
cost-effective inference at scale.
particularly useful for processing large datasets, batch evaluation workflows, and
cost-effective inference at scale.
The API is designed to allow use of openai client libraries for seamless integration.
The API is designed to allow use of openai client libraries for seamless integration.
This API provides the following extensions:
- idempotent batch creation
This API provides the following extensions:
- idempotent batch creation
Note: This API is currently under active development and may undergo changes."
Note: This API is currently under active development and may undergo changes."
sidebar_label: Batches
title: Batches
---
@ -18,14 +18,14 @@ title: Batches
## Overview
The Batches API enables efficient processing of multiple requests in a single operation,
particularly useful for processing large datasets, batch evaluation workflows, and
cost-effective inference at scale.
particularly useful for processing large datasets, batch evaluation workflows, and
cost-effective inference at scale.
The API is designed to allow use of openai client libraries for seamless integration.
The API is designed to allow use of openai client libraries for seamless integration.
This API provides the following extensions:
- idempotent batch creation
This API provides the following extensions:
- idempotent batch creation
Note: This API is currently under active development and may undergo changes.
Note: This API is currently under active development and may undergo changes.
This section contains documentation for all available providers for the **batches** API.

12
docs/docs/providers/inference/index.mdx
View file

@ -1,9 +1,9 @@
---
description: "Llama Stack Inference API for generating completions, chat completions, and embeddings.
This API provides the raw interface to the underlying models. Two kinds of models are supported:
- LLM models: these models generate \"raw\" and \"chat\" (conversational) completions.
- Embedding models: these models generate embeddings to be used for semantic search."
This API provides the raw interface to the underlying models. Two kinds of models are supported:
- LLM models: these models generate \"raw\" and \"chat\" (conversational) completions.
- Embedding models: these models generate embeddings to be used for semantic search."
sidebar_label: Inference
title: Inference
---
@ -14,8 +14,8 @@ title: Inference
Llama Stack Inference API for generating completions, chat completions, and embeddings.
This API provides the raw interface to the underlying models. Two kinds of models are supported:
- LLM models: these models generate "raw" and "chat" (conversational) completions.
- Embedding models: these models generate embeddings to be used for semantic search.
This API provides the raw interface to the underlying models. Two kinds of models are supported:
- LLM models: these models generate "raw" and "chat" (conversational) completions.
- Embedding models: these models generate embeddings to be used for semantic search.
This section contains documentation for all available providers for the **inference** API.

74
docs/static/llama-stack-spec.html vendored
View file

@ -8614,6 +8614,12 @@
{
"$ref": "#/components/schemas/OpenAIResponseInputFunctionToolCallOutput"
},
{
"$ref": "#/components/schemas/OpenAIResponseMCPApprovalRequest"
},
{
"$ref": "#/components/schemas/OpenAIResponseMCPApprovalResponse"
},
{
"$ref": "#/components/schemas/OpenAIResponseMessage"
}
@ -9031,6 +9037,68 @@
"title": "OpenAIResponseInputToolWebSearch",
"description": "Web search tool configuration for OpenAI response inputs."
},
"OpenAIResponseMCPApprovalRequest": {
"type": "object",
"properties": {
"arguments": {
"type": "string"
},
"id": {
"type": "string"
},
"name": {
"type": "string"
},
"server_label": {
"type": "string"
},
"type": {
"type": "string",
"const": "mcp_approval_request",
"default": "mcp_approval_request"
}
},
"additionalProperties": false,
"required": [
"arguments",
"id",
"name",
"server_label",
"type"
],
"title": "OpenAIResponseMCPApprovalRequest",
"description": "A request for human approval of a tool invocation."
},
"OpenAIResponseMCPApprovalResponse": {
"type": "object",
"properties": {
"approval_request_id": {
"type": "string"
},
"approve": {
"type": "boolean"
},
"type": {
"type": "string",
"const": "mcp_approval_response",
"default": "mcp_approval_response"
},
"id": {
"type": "string"
},
"reason": {
"type": "string"
}
},
"additionalProperties": false,
"required": [
"approval_request_id",
"approve",
"type"
],
"title": "OpenAIResponseMCPApprovalResponse",
"description": "A response to an MCP approval request."
},
"OpenAIResponseMessage": {
"type": "object",
"properties": {
@ -9539,6 +9607,9 @@
},
{
"$ref": "#/components/schemas/OpenAIResponseOutputMessageMCPListTools"
},
{
"$ref": "#/components/schemas/OpenAIResponseMCPApprovalRequest"
}
],
"discriminator": {
@ -9549,7 +9620,8 @@
"file_search_call": "#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall",
"function_call": "#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall",
"mcp_call": "#/components/schemas/OpenAIResponseOutputMessageMCPCall",
"mcp_list_tools": "#/components/schemas/OpenAIResponseOutputMessageMCPListTools"
"mcp_list_tools": "#/components/schemas/OpenAIResponseOutputMessageMCPListTools",
"mcp_approval_request": "#/components/schemas/OpenAIResponseMCPApprovalRequest"
}
}
},

51
docs/static/llama-stack-spec.yaml vendored
View file

@ -6254,6 +6254,8 @@ components:
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
- $ref: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput'
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalRequest'
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalResponse'
- $ref: '#/components/schemas/OpenAIResponseMessage'
"OpenAIResponseInputFunctionToolCallOutput":
type: object
@ -6548,6 +6550,53 @@ components:
title: OpenAIResponseInputToolWebSearch
description: >-
Web search tool configuration for OpenAI response inputs.
OpenAIResponseMCPApprovalRequest:
type: object
properties:
arguments:
type: string
id:
type: string
name:
type: string
server_label:
type: string
type:
type: string
const: mcp_approval_request
default: mcp_approval_request
additionalProperties: false
required:
- arguments
- id
- name
- server_label
- type
title: OpenAIResponseMCPApprovalRequest
description: >-
A request for human approval of a tool invocation.
OpenAIResponseMCPApprovalResponse:
type: object
properties:
approval_request_id:
type: string
approve:
type: boolean
type:
type: string
const: mcp_approval_response
default: mcp_approval_response
id:
type: string
reason:
type: string
additionalProperties: false
required:
- approval_request_id
- approve
- type
title: OpenAIResponseMCPApprovalResponse
description: A response to an MCP approval request.
OpenAIResponseMessage:
type: object
properties:
@ -6944,6 +6993,7 @@ components:
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalRequest'
discriminator:
propertyName: type
mapping:
@ -6953,6 +7003,7 @@ components:
function_call: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
mcp_call: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
mcp_list_tools: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
mcp_approval_request: '#/components/schemas/OpenAIResponseMCPApprovalRequest'
OpenAIResponseOutputMessageMCPCall:
type: object
properties: