Azure-Samples/art-voice-agent-accelerator

observability-insights

Read-only — assemble the wider runtime picture of a deployed voice app from azd deployment artifacts and Azure Monitor (Application Insights / Log Analytics) via Azure MCP or az CLI, then render it as KQL, call timelines, latency waterfalls, and mermaid…

原文语言：英语

service-catalog

Service catalog and guided onboarding for the azd deployment. USE WHEN the user wants to discover, install, set up, or be walked through the deployable components (Azure OpenAI/AI Foundry, Speech, ACS/telephony, Cosmos DB, Redis, Container Apps, Key Vault,…

原文语言：英语

troubleshoot

Agent-first, read-only diagnosis of the voice pipeline (deploy, telephony, STT, LLM, TTS, state) — gather evidence via Azure MCP / azd artifacts / CLI, probe the user for missing details, and recommend fixes without changing anything

原文语言：英语

test-and-document

Require relevant tests and documentation updates for any code or config change, and report what was run.

原文语言：英语

add-evaluation

Create or update evaluation scenarios for the tests/evaluation framework, including session-based scenarios and A/B comparisons

原文语言：英语

deployment-guide

Guide azd-based deployments, including where azure.yaml and azd hook scripts live, the current deployment flow, troubleshooting docs, and regional/model availability checks for Azure OpenAI

原文语言：英语

add-component

Add a new React component with Material UI

原文语言：英语

add-endpoint

Add a new FastAPI endpoint to the API

原文语言：英语

add-message-handler

Add a handler for a new WebSocket message type

原文语言：英语

add-tool

Add a new tool to the agent toolstore registry

原文语言：英语

add-voice-handler

Add a new voice handler or feature to the voice module

原文语言：英语

create-agent

Create a new voice agent with YAML configuration and prompt template

原文语言：英语