com um clique
add-message-handler
Add a handler for a new WebSocket message type
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Menu
Add a handler for a new WebSocket message type
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
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 diagrams
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, App Config, CardAPI MCP), asks "what gets deployed", "what services does this use", "help me onboard", "set up the deployment", "guide me through azd up", "which components do I need", or wants to enable optional pieces (phone number, EasyAuth, data seeding). Acts as the entry point an agent hooks into to assess current state, present the catalog, and onboard each component. DO NOT USE FOR: deep azd hook/flow internals or model-availability checks (use deployment-guide); runtime failure diagnosis (use troubleshoot); telemetry/log analysis (use observability-insights).
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
Require relevant tests and documentation updates for any code or config change, and report what was run.
Create or update evaluation scenarios for the tests/evaluation framework, including session-based scenarios and A/B comparisons
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
| name | add-message-handler |
| description | Add a handler for a new WebSocket message type |
Add handlers for new WebSocket message types in the frontend.
interface MessageEnvelope {
type: string; // Message type identifier
sender: string; // "Assistant" | "User" | "System"
payload: object; // Actual message content
ts: string; // ISO 8601 timestamp
session_id: string; // Session identifier
topic?: string; // Optional routing topic
}
Add to message handler switch in hooks/useWebSocket.js or App.jsx:
const handleMessage = useCallback((event) => {
const envelope = JSON.parse(event.data);
switch (envelope.type) {
// ... existing cases ...
case 'my_new_type':
handleMyNewType(envelope.payload);
break;
default:
console.log('Unknown message type:', envelope.type);
}
}, []);
const handleMyNewType = useCallback((payload) => {
// Extract data from payload
const { field1, field2 } = payload;
// Update state
setMyState(prev => ({
...prev,
field1,
field2,
}));
// Optional: trigger side effects
if (field1) {
onFieldUpdate?.(field1);
}
}, [onFieldUpdate]);
const [myState, setMyState] = useState({
field1: null,
field2: null,
});
| Type | Payload | Handler Action |
|---|---|---|
assistant_streaming | { content, streaming } | Append to message buffer |
assistant | { content } | Finalize message |
event | { event_type, event_data } | Route to event handler |
tool_start | { tool_name, tool_call_id } | Show tool indicator |
tool_end | { tool_name, result, error } | Hide indicator, log result |
audio_data | { data, sample_rate } | Send to AudioWorklet |
// State
const [activeTools, setActiveTools] = useState(new Map());
// Handler
const handleToolProgress = useCallback((envelope) => {
const { tool_name, tool_call_id, pct } = envelope.payload;
setActiveTools(prev => {
const next = new Map(prev);
if (envelope.type === 'tool_start') {
next.set(tool_call_id, { name: tool_name, progress: 0 });
} else if (envelope.type === 'tool_progress') {
const tool = next.get(tool_call_id);
if (tool) next.set(tool_call_id, { ...tool, progress: pct });
} else if (envelope.type === 'tool_end') {
next.delete(tool_call_id);
}
return next;
});
}, []);
// In switch
case 'tool_start':
case 'tool_progress':
case 'tool_end':
handleToolProgress(envelope);
break;
const handleEventMessage = useCallback((payload) => {
const { event_type, event_data } = payload;
switch (event_type) {
case 'agent_change':
setActiveAgent(event_data.active_agent_label);
break;
case 'session_updated':
setSession(prev => ({ ...prev, ...event_data }));
break;
case 'call_connected':
setCallStatus('connected');
break;
default:
console.log('Unhandled event:', event_type);
}
}, []);
// Text message envelope
const sendTextMessage = (text) => {
socket.send(JSON.stringify({
type: 'user_message',
sender: 'User',
payload: { text },
ts: new Date().toISOString(),
session_id: sessionId,
}));
};
// Binary audio data (no envelope)
const sendAudioData = (pcmSamples) => {
socket.send(pcmSamples.buffer);
};