Agent Max Tokens Invalid Input Range

### Severity

P3 - Medium (Minor functionality affected)

### Describe the Bug with repro steps

Excepted Behavior:
- MAX Tokens will be reflective of the MAX Tokens limits for the model selected in the agent configuration. For gpt-4o - 16k and for gpt-4.1 32k
Actual Behaviour:
- UI is limiting the MAX Tokens to 8192

Steps to Reproduce:
- in the azure portal create an autonomous agent
- configure the agent
- select GPT-4o or GPT-4.1
- Advanced Parameters -> MAX TOKENS (max limit is always 8192 regardless of the model selected)

### What type of Logic App Is this happening in?

Standard (Portal)

### Are you experiencing a regression?

_No response_

### Which operating system are you using?

Windows

### Did you refer to the TSG before filing this issue? https://aka.ms/lauxtsg

Yes

### Workflow JSON

```json
{
"definition": {
"$schema": "https://schema.management.azure.com/providers/Microsoft.Logic/schemas/2016-06-01/workflowdefinition.json#",
"contentVersion": "1.0.0.0",
"actions": {
"Agent": {
"type": "Agent",
"inputs": {
"parameters": {
"deploymentId": "gpt-4.1",
"messages": [
{
"role": "system",
"content": "test"
}
],
"agentModelType": "AzureOpenAI",
"agentModelSettings": {
"agentHistoryReductionSettings": {
"agentHistoryReductionType": "maximumTokenCountReduction",
"maximumTokenCount": 128000
},
"deploymentModelProperties": {
"name": "gpt-4.1",
"format": "OpenAI",
"version": "2025-04-14"
}
}
},
"modelConfigurations": {
"model1": {
"referenceName": "agent"
}
}
},
"tools": {},
"runAfter": {},
"limit": {
"count": 100
}
}
},
"outputs": {},
"triggers": {
"When_an_HTTP_request_is_received": {
"type": "Request",
"kind": "Http"
}
}
},
"kind": "Stateful"
}
```

### Screenshots or Videos

_No response_

### Environment

- Microsoft Edge for Business Version 146.0.3856.84

### Additional context

when using the agentic activity we are encountering token limits; this is resulting in us having to use the Azure Open AI - Get Chat Completions call where we are able to set the MAX Tokens value to the desired upper limit