An error has occurred. Error code: HttpRequestFailure Conversation Id: e3QGxxxxxx01NA-us Time (UTC): 2025-06-01T16:14:05.372Z.

 

Troubleshooting MS Copilot Studio HTTP Request Failures: A Practical Solution

The Problem Description

If you're working with MS Copilot Studio, you've likely encountered this frustrating error:

MS Copilot Studio -- 

An error has occurred. Error code: HttpRequestFailure Conversation Id: e3QGxxxxxx01NA-us Time (UTC): 2025-06-01T16:14:05.372Z.

This is a common issue that occurs frequently with MS Copilot Studio, though not consistently. Based on my experience, this isn't a code issue but rather a configuration issue related to the MS environment.

What We Discovered

When we enabled the Continue on Error feature in Copilot Studio, we encountered an HTTP 408 error (Request Timeout). This means the server didn't receive a complete request from the client within the expected timeframe.

After researching and contacting our support counterpart, they provided the following stacktrace:

CorrelationId: xxxx-b674-4c2a-xxxx-184197387367
Exception: Microsoft.IdentityModel.S2S.S2SAuthenticationException: S2xx2099: 
An exception has been caught while validating the request. 
Exception: [PII of type 'System.AggregateException' is hidden]

---> System.AggregateException: S2xx2096: Microsoft.IdentityModel.S2S.JwtAuthenticationHandler 
caught exceptions when validating the token. See AuthenticationResult.InboundPolicyEvaluationResults 
for additional details. (S2xx2086: An exception has been caught while validating the request 
applying the policy with id : 'User'. 

Exception: Microsoft.IdentityModel.Tokens.SecurityTokenInvalidAudienceException: IDXxx214: 
Audience validation failed. Audiences: 'xxx-xxx-4af1-b9a8-09a648fb6699'. 
Did not match: validationParameters.ValidAudience: 'null' or validationParameters.ValidAudiences:

Unfortunately, the issue remains unresolved as of when I write this post.

Our Temporary Solution: Retry Logic

As a quick fix, we implemented retry logic in the Copilot Studio workflow UI using the Goto Step feature for HTTP nodes, with a maximum retry count of 3.

Implementation Code

Here's the complete code snippet for our temporary fix:

1. Initialize Retry Counter

- kind: SetVariable
  id: setVariable_btVmH4
  displayName: retryCount
  variable: Topic.retryCount
  value: 0

2. HTTP Request with Error Handling

- kind: HttpRequestAction
  id: JDNAtp
  displayName: PF - HTTP Request
  method: Post
  url: https://pf-end-point-autoendpoint.eastus.inference.ml.azure.com/score
  headers:
    Authorization: Bearer 6mIiASFPiZKeaRxxUk4JQQJ99BGAAAAAAAAAAAAINFRAZML2PC6
    azureml-model-deployment: auto-20250708-551705
    Content-Type: application/json

  body:
    kind: JsonRequestContent
    content: |
      ={
          question:Topic.UserQuery,
          chat_history:Global.VarHistory
      }

  errorHandling:
    kind: ContinueOnErrorBehavior
    statusCode: Topic.ErrorStatusCode

  requestTimeoutInMilliseconds: 30000
  response: Topic.KBAresponse
  responseSchema: Any
  responseHeaders: Topic.ResponseHeader

3. Error Status Logging

- kind: SendActivity
  id: sendActivity_dxnBNR
  activity: After HTTP request --- Error Code--- {Topic.ErrorStatusCode}

4. Retry Logic Implementation

- kind: ConditionGroup
  id: conditionGroup_cN6dbL
  conditions:
    - id: conditionItem_xH0b5H
      condition: =!IsBlank(Topic.ErrorStatusCode)
      displayName: Condition to try Retry Logic
      actions:
        - kind: SetVariable
          id: setVariable_9Lszte
          variable: Topic.retryCount
          value: =Topic.retryCount + 1

        - kind: ConditionGroup
          id: conditionGroup_UA3fsX
          conditions:
            - id: conditionItem_itQSEP
              condition: =Topic.retryCount < 3
              actions:
                - kind: SendActivity
                  id: sendActivity_Y0iihp
                  activity: ---->{Topic.retryCount}---

                - kind: GotoAction
                  id: S4S1LT
                  actionId: JDNAtp

        - kind: SendActivity
          id: sendActivity_vOX9b5
          activity: Errorred --{Topic.retryCount}

How It Works

1. Initialize a retry counter to 0
2. Execute the HTTP request with error handling enabled
3. Check if an error occurred (ErrorStatusCode is not blank)
4. Increment the retry counter
5. Retry up to 3 times using the GotoAction to jump back to the HTTP request
6. Log the final error state if all retries fail

Key Takeaways

• This appears to be an authentication/token validation issue on Microsoft's end
• The Continue on Error feature is essential for implementing retry logic
• Retry logic provides a practical workaround while waiting for Microsoft to resolve the underlying issue
• The GotoAction feature in Copilot Studio makes implementing retry patterns straightforward

Conclusion

While this isn't a permanent solution, it significantly improves the reliability of HTTP requests in MS Copilot Studio workflows. If you're experiencing similar issues, consider implementing this retry pattern until Microsoft addresses the root cause.

Have you encountered similar issues with MS Copilot Studio? Share your experiences and solutions in the comments below!

---

Tags: #MSCopilotStudio #Azure #HTTPErrors #RetryLogic #Troubleshooting #Microsoft