outputType Not Supported When Using Agent with ai-sdk/anthropic #185
Description
Please read this first
- Have you read the docs? Agents SDK docs ✅
- Have you searched for related issues? Others may have faced similar issues. ✅
Describe the bug
When using an agent with the @ai-sdk/anthropic provider, setting the outputType option results in an error instead of formatting the output as expected. The agent throws the following error:
{
"error": "Error: Invalid output type"
}And in @ai-sdk/[email protected] is working but it fall to loop and here is the console.log output:
{
"content": [
{
"type": "text",
"text": "{\"capital\":\"Berlin\",\"country\":\"Germany\"}"
}
],
"finishReason": "stop",
"usage": {
"inputTokens": 430,
"outputTokens": 50,
"totalTokens": 480,
"cachedInputTokens": 0
},
"request": {
"body": {
"model": "claude-3-7-sonnet-20250219",
"max_tokens": 4096,
"system": [
{
"type": "text",
"text": "You are a helpful assistant."
}
],
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "What is the capital of Germany?"
}
]
}
],
"tools": [
{
"name": "json",
"description": "Respond with a JSON object.",
"input_schema": {
"type": "object",
"properties": {
"capital": {
"type": "string"
},
"country": {
"type": "string"
}
},
"required": ["capital", "country"],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
],
"tool_choice": {
"type": "tool",
"name": "json"
}
}
},
"response": {
"id": "msg_01BW6WewTgJy1gvFRbo5i7pj",
"modelId": "claude-3-7-sonnet-20250219",
"body": {
"id": "msg_01BW6WewTgJy1gvFRbo5i7pj",
"type": "message",
"role": "assistant",
"model": "claude-3-7-sonnet-20250219",
"content": [
{
"type": "tool_use",
"id": "toolu_012AH8c9JbrY3EzQRdJWRLD1",
"name": "json",
"input": {
"capital": "Berlin",
"country": "Germany"
}
}
],
"stop_reason": "tool_use",
"stop_sequence": null,
"usage": {
"input_tokens": 430,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0,
"output_tokens": 50,
"service_tier": "standard"
}
}
},
"warnings": [],
"providerMetadata": {
"anthropic": {
"cacheCreationInputTokens": 0
}
}
}Debug information
- Agents SDK version:
v0.0.10 - Runtime environment
Node.js 22.16.0 - @ai-sdk/anthropic:
1.2.12
Repro steps
import { anthropic } from '@ai-sdk/anthropic';
import { aisdk } from '@openai/agents-extensions';
const model = aisdk(anthropic('claude-3-7-sonnet-20250219'));
function agent() {
const agent = new Agent({
name: 'Test Agent',
instructions: `You are a helpful assistant.`,
model,
outputType: z.object({
message: z.string(),
}),
});
}Expected behavior
An appropriate warning logs could be useful.