Understand error codes

AIModelActionBadRequest

Error messages:

• The output of the prompt evaluated to {ActualType} but expected {ExpectedType}.

• The input parameter {ParameterName} for prompt {PromptName} is missing.

• The input parameter {ParameterName} for prompt {PromptName} is blank but is required.

• Expected: {ExpectedType}. Actual: {ActualType}.

Resolution: This error occurs if a prompt action receives incorrect input or returns unexpected output types. To resolve the problem, take one of the following actions, based on the error:

• Type mismatch: Check your prompt configuration to make sure that the output schema matches the expected variable type.
• Missing required input: Verify that all required inputs are connected to variables that have values.
• Blank required value: Make sure that the variable has a value before you call the prompt.

For more information, see Create a prompt action.

AIModelActionRequestTimeout

Error message: The prompt prompt-name execution timed out.

Resolution: Make sure that the call to the AI Builder model doesn't exceed 100 seconds.

AIPluginOperationNotFound

Error message: Sorry, the bot can't talk for a while. It's something the bot's owner needs to address.

Resolution: Republish the agent. This error can occur when an agent is published through an import or a solution deployment.

AsyncResponsePayloadTooLarge

Error message: The output returned from the connector was too large to be handled by the agent. Try reducing its size by utilizing available connector filters or by limiting the number of configured action outputs.

Resolution: One of the agent's real-time connectors is returning a payload that's larger than the agent can handle. For more information about the payload limit, see Copilot Studio web app limits.

AuthenticationNotConfigured

Error messages:

• Authentication is not configured for this bot.

• The bot requires sign in, but is not configured for authentication. Please update the authentication method for the bot.

• Integrated authentication is not supported in channel {channel}.

Resolution: This error occurs if your agent uses actions or features that require user authentication, but authentication isn't configured. To resolve the problem:

1. In your agent, go to Settings > Security > Authentication.
2. Select an appropriate authentication method: Authenticate with Microsoft for Microsoft 365 users, or Authenticate manually for custom OAuth providers.
3. If the error mentions a specific channel, verify that the channel supports the authentication method that you're using. Some channels don't support integrated authentication.

For more information, see Configure user authentication.

BindingKeyNotFoundError

Error messages:

• Binding '{0}' is not found, refresh this flow to get the latest bindings
• Input binding '{0}' is not found, refresh this flow to get the latest bindings
• Output binding '{0}' is not found, refresh this flow to get the latest bindings

Resolution: Check that the agent flow inputs and outputs are set up correctly. Try refreshing the inputs or outputs to resolve this issue. If that doesn't work, try setting up the agent flow again.

To get the latest inputs and outputs, remove and readd the agent flow.

BingSearchFailed

Error message: This is a system issue on our side. Nothing you need to fix. Error details: Platform runtime - BingSearchFailed.

Resolution: A platform-side Bing search failure can cause this issue. Retry later. If the issue continues, contact support.

ConnectedAgentAuthMismatch

Error message: Your connected agent with schema name {AgentSchemaName} has an authentication mismatch with the main agent.

Resolution: The orchestrator agent and connected subagent have different authentication configurations. For multi-agent orchestration to work, both agents must use compatible authentication settings. To resolve the problem:

1. Open both agents, and go to Settings > Security > Authentication.
2. Make sure that both agents use the same authentication method (for example, both use Authenticate with Microsoft).
3. If you're using manual authentication, make sure that both agents are configured to use the same OAuth provider and settings.

The following authentication compatibility rules apply:

• If the connected agent has No authentication configured, any orchestrator authentication is acceptable.
• If the connected agent requires authentication, the orchestrator must use the same authentication method.
• Manual authentication (Generic OAuth2) on the orchestrator isn't compatible with connected agents that require authentication. Both agents must use the same manual authentication configuration, or the connected agent must have no authentication requirement.

For more information, see Configure user authentication and Use agents as actions in other agents (preview).

ConnectedAgentBotNotFound

Error message: Connected agent with schema name {AgentSchemaName} not found.

Resolution: This error occurs in multi-agent orchestration if the orchestrator agent can't find a connected subagent. To resolve the problem:

1. Verify that the connected agent exists in the same environment as the orchestrator agent.
2. Make sure that the connected agent's schema name is spelled correctly in the orchestrator configuration.
3. Check that you have access permissions to the connected agent.
4. If the connected agent was recently created, wait a few minutes, and then try again.

For more information, see Use agents as actions in other agents (preview).

ConnectedAgentBotNotPublished

Error message: Connected agent with schema name {AgentSchemaName} needs to be published to be invoked.

Resolution: The connected subagent must be published before the orchestrator agent can invoke it. To resolve the problem:

1. Open the connected agent in Copilot Studio.
2. Publish the agent.
3. Return to the orchestrator agent, and test again.

For more information, see Use agents as actions in other agents (preview).

ConnectedAgentChainingNotSupported

Error message: Agent chaining detected. Your agent cannot be connected to agent with schema name {AgentSchemaName} as it already has a connected agent.

Resolution: Multi-level agent chaining isn't supported. An orchestrator agent can connect to subagents, but those subagents can't have their own connected agents. To resolve the problem:

1. Review your agent architecture, and flatten the hierarchy.
2. Move the functionality from deeply nested agents into either the orchestrator or first-level connected agents.
3. Consider using topics or actions instead of more connected agents.

For more information, see Use agents as actions in other agents (preview).

ConnectedAgentGptComponentNotFound

Error message: No GPT component found for connected agent with schema name {AgentSchemaName}.

Resolution: The connected agent is missing a required description or instructions. The orchestrator needs that information to know when to call the connected agent. To resolve the problem:

1. Open the connected agent in Copilot Studio.
2. Go to the agent's Overview page.
3. Make sure that the agent has a clear Description and Instructions configured.
4. After you make changes, publish the connected agent.
5. Return to the orchestrator agent, and test again.

For more information, see Use agents as actions in other agents (preview).

ConnectorPowerFxError

Error message: Power Fx expression evaluation failed: {ErrorDetails}

Resolution: A Power Fx expression that's used in a connector action wasn't evaluated correctly. To resolve the problem:

1. Open the topic that contains the connector action.
2. Review the Power Fx expressions in the action's input parameters.
3. Test the expressions by using sample data to determine the issue.
4. Use the formula bar's error indicators to locate specific problems.

Common causes include:

• Syntax errors.
• Type mismatches, such as comparing text to numbers without conversion.
• Null or blank values. For handling, use functions such as IsBlank(), Coalesce(), or IfError().
• Invalid function usage.

For more information, see Use Power Fx in Copilot Studio.

ConsentNotProvidedByUser

Error message: No consent provided for SSO connection.

Resolution: The user who's interacting with the agent must verify the connection by using the agent's single sign-on (SSO) connection prompt.

ContentError

Error message: This error produces dynamic messages based on the context of the error.

Resolution: This message is a catch-all error for problems that are related to your agent's content. The error message provides more details.

Common problems include:

• A node is missing required properties.
• Invalid YAML was added by using the code editor.
• A Power Fx formula contains an error.

ConversationStateTooLarge

Error message: Conversation state size exceeds the maximum allowed limit.

Resolution: The conversation accumulates too much data in its state, exceeding the allowed size limits. To resolve the problem:

1. Reduce variable data by reviewing your topics and reducing the amount of data stored in variables during the conversation.
2. Clear unused variables by setting them to blank if they're no longer needed.
3. Simplify conversation flows by breaking complex conversations into smaller, more focused interactions.
4. Avoid storing large JSON objects, arrays, or text blocks in conversation variables.

To prevent this error:

• Use variables only for data that has to persist across topics.
• Consider using Power Automate flows to store and retrieve large data from external sources instead of keeping it in conversation state.

For more information, see Copilot Studio quotas and limits.

DataLossPreventionViolation

Error message: This environment requires users to sign in before they can use the agent. Go to Manage > Security > Authentication and select the option that requires users to sign in.

Resolution

• Your environment's data policies require that users sign in. See Add user authentication with the Sign in system topic.
• One or more connectors that you use in the agent aren't in the same data group. See Copilot Studio connectors.
• The tenant administrator blocked one or more connectors that you use in the agent.

DataverseFileAttachment429

Error message: SharePoint is limiting requests right now. Try again later. Error details: DataverseFiles429.

Resolution: Service throttling can cause this error. Wait and retry.

DataverseSearchFailed

Error message: This is a system issue on our side. Nothing you need to fix. Error details: Platform runtime - DataverseSearchFailed.

Resolution: Dataverse knowledge search failures, such as user connection errors, can cause this issue. To resolve the problem:

1. Open the agent knowledge source settings, and reauthenticate the Dataverse connection.
2. Verify that the user has valid licensing and permissions for the Dataverse knowledge source.
3. If the issue persists after reauthentication, contact support.

DataverseStructured401

Error message: Search ran into an authentication issue. This usually resolves on its own. Nothing to fix on your side. Error details: Dataverse401.

Resolution: This error can indicate missing permissions for the agent's identity or user account. To resolve the problem:

1. Grant the required Dataverse knowledge search permissions to the agent's service principal.
2. Verify that the knowledge source environment matches the agent's environment.
3. Retry after permission updates.

For more information, see Troubleshoot enterprise knowledge sources.

DataverseStructured429

Error message: Dataverse is limiting requests right now. Try again later. Error details: Dataverse429.

Resolution: The service was throttled or timed out. To reduce recurrence:

1. Retry with exponential backoff.
2. Reduce knowledge source size where possible.
3. Spread large query loads over time.

For more information, see Microsoft Graph throttling guidance.

DataverseStructured500

Error message: This isn't a configuration problem. The owning service needs to investigate. Error details: Dataverse500.

Resolution: A service-side issue can cause this error. Retry later. If the issue continues, contact support.

DataverseStructured503

Error message: This isn't a configuration problem. The owning service needs to investigate. Error details: Dataverse503.

Resolution: Temporary service unavailability can cause this error. Retry later.

EnforcementMessageC2

Error message: This agent is currently unavailable. It has reached its usage limit. Please try again later.

Resolution: This message appears if an agent reaches its message capacity or the pay-as-you-go meter reaches its limit. To resolve the problem, add more prepaid capacity or create a pay-as-you-go billing plan. The agent chat should then resume working within five minutes. For more information, see Overage Enforcement.

ExecutionTimeout

Error message: This tool call timed out. The operation took too long to complete. Error details: Timeout · execution.

Resolution: Long-running execution paths can cause this error. To resolve the problem:

1. Break large workflows into smaller steps.
2. Optimize query and transformation logic.
3. Remove unnecessary actions from the critical path.
4. Validate loops and branching conditions for inefficiencies.

FlowActionBadRequest

Error messages:

• The parameter with name {KeyName} on flow {FlowName} ({FlowId}) is declared to be of type {ItemTypeKind}. This type isn't supported when invoking Power Automate. Currently, only Text, Boolean and Numbers are supported.
• The parameter with name {ItemKey} on flow {FlowName} ({FlowId}) is missing in the 'Call Flow' action.
• The parameter with name {KeyName} on flow {FlowName} ({FlowId}) evaluated to type {ResolveType}, expected type {ExpectedType}.
• The flow {FlowName} ({FlowId}) failed to run with response code {ResponseCode}, error code: {FlowErrorCode}.

Resolution: Verify that the base type of any variables that you pass to the flow matches the parameter type. For more information, see FlowActionBadRequest agent error in channels

FlowActionException

Error messages:

• No output was received from flow {FlowName} ({FlowId}), even though output was expected as per the agent definition.
• The output parameter with name {ItemKey} on flow {FlowName} ({FlowId}) is missing from the response data. Refresh the flow, or ensure the flow returns this value.
• The output parameter with name {ItemKey} on flow {FlowName} ({FlowId}) is missing from the output schema. Please refresh the flow.

Resolution: Check the flow for errors.

FlowActionTimedOut

Error message: The flow with id {FlowId} has timed out. Error Code: {FlowErrorCode}

Resolution: Check the flow for errors to understand why the cloud flow took more than 100 seconds to run before it returned to your agent. Try to optimize the query and the data that you return from the back-end system. If some of the cloud flow logic can continue to run after a result is sent to the agent, put these actions after the "Return value(s) to Copilot Studio" step in your cloud flow.

FlowMakerConnectionBlocked

Error message: The flow with name {FlowName} is using a maker connection, which isn't allowed. Error Code: {FlowMakerConnectionBlocked}

Resolution: The administrator prevents using maker credentials in a connection invoked from the agent flow. Open the flow in Power Automate and share the cloud flow by using run-only permissions.

FoundryIQSearchFailed

Error message: This is a system issue on our side. Nothing you need to fix. Error details: Platform runtime - FoundryIQSearchFailed.

Resolution: A platform-side Foundry IQ search failure can cause this issue. Retry later. If the issue continues, contact support.

GenAISearchandSummarizeRateLimitReached

Error message: The usage limit for search and summarize has been reached. Please try again later.

Resolution: The agent returns this message if it reaches its generative AI limit to search and summarize sources. For more information, see Resolve throttling errors in agents.

GenAIToolPlannerRateLimitReached

Error message: The usage limit for generative orchestration has been reached. Please try again later.

Resolution: The agent returns this message if it reaches its generative orchestration limit. For more information, see Resolve throttling errors in agents.

HTTP400BadRequest

Error message: Bad Request.

Resolution: Malformed payloads or invalid parameters can cause this error. To resolve the problem:

1. Verify that all required parameters are present.
2. Confirm that data types match the action schema.
3. Test with known-good sample data.
4. Validate the JSON formatting for complex payloads.

HTTP401Unauthorized

Error message: Unauthorized.

Resolution: This error can be caused by missing or expired authentication credentials. To resolve the problem:

1. Verify that the connector is configured correctly in Copilot Studio.
2. Check whether the OAuth token expired, and reauthenticate the connection.
3. Validate the API key or connection settings.
4. Test the connection before deploying.
5. If you use service principal authentication, verify that the credentials weren't rotated.

HTTP403Forbidden

Error message: Forbidden.

Resolution: This error can be caused by missing permissions in the target system. To resolve the problem:

1. Verify that the user or app has the required roles and permissions.
2. Check app registration permissions and admin consent requirements.
3. Verify resource-level sharing and delegation settings.
4. Confirm that tenant and environment scoping are correct.

HTTP404NotFound

Error message: Not Found.

Resolution: Missing or incorrect resource identifiers can cause this error. To resolve the problem:

1. Verify that the resource ID or URL is correct.
2. Confirm that the resource still exists.
3. Verify that the environment and tenant selection are correct.
4. Prefer dynamic resource selection over manually typed IDs.

HTTP408RequestTimeout

Error message: This tool call timed out. The operation took too long to complete. Error details: Timeout · execution.

Resolution: Exceeding client or network time limits can cause this error. To resolve the problem:

1. Check network stability and latency.
2. Reduce payload size where possible.
3. Add retries with incremental backoff.
4. Use asynchronous patterns for long-running operations.

HTTP422UnprocessableEntity

Error message: Unprocessable Entity.

Resolution: Semantic validation failures can cause this error. To resolve the problem:

1. Validate field-level formats and allowed values.
2. Add data validation before the tool call.
3. Check business rule constraints.
4. Retry with known-good sample data.

HTTP429TooManyRequests

Error message: Too Many Requests.

Resolution: Throttling limits can cause this error. To resolve the problem:

1. Add delays between calls.
2. Implement exponential backoff retries.
3. Limit concurrency for batch operations.
4. Respect Retry-After headers when present.
5. Monitor usage and throttling in analytics.

HTTP500InternalServerError

Error message: This tool is temporarily unavailable. The service didn't respond or is currently unavailable. Error details: Service availability · 5xx.

Resolution: A service-side issue can cause this error. To resolve the problem:

1. Retry the request because transient failures are common.
2. Check connector and service health dashboards for active incidents.
3. Add a retry policy with exponential backoff.
4. If the issue persists, collect request timestamp and correlation details, and contact support.

HTTP502BadGateway

Error message: This tool is temporarily unavailable. The service didn't respond or is currently unavailable. Error details: Service availability · 5xx.

Resolution: Invalid responses from upstream dependencies can cause this error. To resolve the problem:

1. Wait, and retry after a short delay.
2. Validate the endpoint URL and connector configuration.
3. Add retries with exponential backoff.
4. If the issue persists, check vendor status pages and connector documentation.

HTTP503ServiceUnavailable

Error message: This tool is temporarily unavailable. The service didn't respond or is currently unavailable. Error details: Service availability · 5xx.

Resolution: This error can be caused by temporary service outages or overload. To resolve the problem:

1. Retry later with longer backoff.
2. Check service health for planned maintenance or incidents.
3. Defer noncritical operations until the service stabilizes.
4. Implement circuit-breaker style controls for repeated failures.

HTTP504GatewayTimeout

Error message: This tool is temporarily unavailable. The service didn't respond or is currently unavailable. Error details: Service availability · 5xx.

Resolution: Slow upstream processing or network latency can cause this error. To resolve the problem:

1. Retry the operation, and verify whether the back-end service completed the work despite the timeout.
2. Reduce payload size, and optimize expensive queries.
3. Break large operations into smaller batches.
4. Increase the configured timeout where supported.

InfiniteLoopInBotContent

Error message: Action {DialogId}.{TriggerId}.{ActionId} was executed more than {MaxTurnCount} times in a row. This indicates a cycle in execution of the dialog and hence dialog execution will be terminated.

Resolution: Make sure that the topic ends correctly and links to other topics that end correctly, such as the Escalate system topic.

InvalidAuthenticationToken

Error message: InvalidAuthenticationToken.

Resolution: Malformed or stale token data can cause this error. To resolve the problem:

1. Remove and recreate the connection.
2. Reauthenticate the connector.
3. Clear the browser or app cache if applicable.
4. Retry the flow.

InvalidContent

Error message: A total of {TotalComponents} component(s) exist in the agent, but none are valid.

Resolution: Open the code editor to review problems that affect the content.

LatestPublishedVersionNotFound

Error message: Unable to retrieve the latest published version of the agent.

Resolution: Publish the agent.

MsalUiException

Error message: MsalUiException.

Resolution: This error can be caused when silent token acquisition fails and interactive sign-in is required. To resolve the problem:

1. Sign out, and sign in again to refresh your token.
2. Complete any interactive authentication prompts.
3. Retry the tool call after authentication completes.

OpenAIHate

Error message: The content was filtered due to Responsible AI restrictions.

A Responsible AI check blocks the content that's considered to be hateful. Hateful content refers to any content that attacks or uses discriminatory language against a person or identity group based on certain differentiating attributes of these groups.

This restriction includes, but isn't limited to, content about:

• Race, ethnicity, nationality
• Gender identity groups and expression
• Sexual orientation
• Religion
• Personal appearance and body size
• Disability status
• Harassment and bullying

Resolution: To avoid this situation, reinforce responsible AI guidelines together with your agent users. You can also update the agent content moderation policies.

OpenAIJailBreak

Error message: The content was filtered due to Responsible AI restrictions.

A security check blocks the content of a jailbreak attempt. A jailbreak attempt is a user prompt attack that ignores system prompts and tries to alter the intended agent behavior. These attacks include attempts to change system rules, embedding a conversation mockup to confuse the model, role-play, and encoding attacks. For more information, see Prompt Shields in Azure AI Content Safety.

Resolution: To avoid this situation, reinforce responsible AI guidelines together with your agent users. You can also update the agent content moderation policies.

OpenAIndirectAttack

Error message: The content was filtered due to Responsible AI restrictions.

An attack was detected from information that's not directly supplied by the agent author or the user, such as external documents. Attackers try to embed instructions in grounded data that's provided by the user to maliciously gain control of the system by:

• Manipulating content
• Intrusion
• Unauthorized data exfiltration or data removal from a system
• Blocking system capabilities
• Fraud
• Code execution and infecting other systems

For more information, see Prompt Shields for documents.

Resolution: If you're testing, and you didn't intend the test to be an attack, make sure that your instructions align with what you want the agent to be able to do. Otherwise, reinforce responsible AI guidelines together with your agent users to avoid this situation.

OpenAIRateLimitReached

Error message: An error has occurred.

Resolution: Your agent reached the maximum number of generative answer responses. Review your message capacity, and review the information in Resolve throttling errors in agents.

OpenAISelfHarm

Error message: The content was filtered due to Responsible AI restrictions.

A Responsible AI check blocked content that's related to self-harm. Self-harm describes language that's related to physical actions that are intended to purposely hurt, injure, damage one's body, or kill oneself.

This restriction includes, but isn't limited to, content about:

• Eating disorders
• Bullying and intimidation

Resolution: To avoid this situation, reinforce responsible AI guidelines together with your agent users. You can also update the agent content moderation policies.

OpenAISexual

Error message: The content was filtered due to Responsible AI restrictions.

A Responsible AI check blocked content that's considered to be sexual. Sexual content describes language that's related to anatomical organs and genitals, romantic relationships, sexual acts, and acts that are portrayed in erotic or affectionate terms, including those portrayed as an assault or an act of sexual violence.

This restriction includes, but isn't limited to, content about:

• Vulgar content
• Prostitution
• Nudity and pornography
• Abuse
• Child exploitation, child abuse, child grooming

Resolution: To avoid this situation, reinforce responsible AI guidelines together with your agent users. You can also update the agent content moderation policies.

OpenAIViolence

Error message: The content was filtered due to Responsible AI restrictions.

A Responsible AI check blocked content that's considered to be violent. Violent content describes language that's related to physical actions that are intended to hurt, injure, damage, or kill someone or something. It also describes weapons, guns, and related entities.

This restriction includes, but isn't limited to, content about:

• Weapons
• Bullying and intimidation
• Terrorist and violent extremism
• Stalking

Resolution: To avoid this situation, reinforce responsible AI guidelines together with your agent users. You can also update the agent content moderation policies.

OperationTimeout

Error message: This tool call timed out. The operation took too long to complete. Error details: Timeout · execution.

Resolution: Operation-level timeouts in dependent services can cause this error. To resolve the problem:

1. Narrow query scope, and add filtering.
2. Add retry with backoff for transient timeouts.
3. Use pagination for large result sets.
4. Review target service performance and request limits.

OutgoingMessageSizeTooBig

Error message: Outgoing message size too large.

Resolution: Depending on the channel that you use to transfer files, such as Direct Line or Facebook, you might receive the following error message: "The request content length exceeded limit of 262,144 bytes." The channel imposes these limits, not Copilot Studio.

In this scenario, consider a few options. One option is to provide a link to the resource as an internet attachment. Another option is to review your nodes to make sure that none of them use a variable that contains a large volume of text, such as a JSON.stringify() static method. If you use this method or a variable that contains a large volume of text, modify the node to pass only the portion of text that's necessary. For example, if you use an Adaptive Card to pass data to another topic, update the variable to pass only the necessary property.

For more information, see Maximum channel data message size limits when using Copilot Studio in Omnichannel.

QuotaExceeded

Error message: QuotaExceeded.

Resolution: Exhausted monthly, daily, or concurrency entitlements can cause this error. To resolve the problem:

1. Check usage in admin analytics.
2. Reduce unnecessary tool calls.
3. Consolidate operations where possible.
4. Review and upgrade licensing or quota plans if needed.

RedirectToDisabledDialog

Error message: The Dialog with Id {DialogId} is disabled in the definition. Please enable the Dialog before using it.

Resolution: Re-enable the topic or remove the redirect node.

RedirectToNonExistentDialog

Error message: The Dialog with Id {DialogId} wasn't found in the definition. Please check that the Dialog is present and that the Id is correct.

Resolution: Create a new topic to redirect to, or remove the redirect node.

SharePoint429

Error message: SharePoint is limiting requests right now. Try again later. Error details: SharePoint429.

Resolution: Service throttling can cause this error. Wait and retry.

SharePoint500

Error message: This isn't a configuration problem. The owning service needs to investigate. Error details: SharePoint500.

Resolution: A service-side issue can cause this error. Retry later. If the issue continues, contact support.

SharePoint503

Error message: This isn't a configuration problem. The owning service needs to investigate. Error details: SharePoint503.

Resolution: Temporary service unavailability can cause this error. Retry later.

SharePointSearchFailed

Error message: This is a system issue on our side. Nothing you need to fix. Error details: Platform runtime - SharePointSearchFailed.

Resolution: A platform-side SharePoint search failure can cause this issue. Retry later. If the issue continues, contact support.

SystemError

Error message: This error doesn't produce an error message.

Resolution: Contact customer support.

TooMuchDataToHandle

Error message: The request is resulting in too much data to handle, please evaluate the amount of data being returned by your actions.

Resolution: This error indicates that the request that was sent to OpenAI exceeds the maximum request size that's allowed. The request includes the user input, output from previous actions, tools that were called, and conversation history. Review the tools that you use. If it's possible, scope down their output to only the necessary fields. For more information, see Create a Power Automate flow and Call a Power Automate flow as an action.