list-flow-execution-events¶

Description¶

Lists events that occurred during a flow execution. Events provide detailed information about the execution progress, including node inputs and outputs, flow inputs and outputs, condition results, and failure events.

Note

Flow executions is in preview release for Amazon Bedrock and is subject to change.

Synopsis¶

  list-flow-execution-events
--flow-identifier <value>
--flow-alias-identifier <value>
--execution-identifier <value>
--event-type <value>
[--cli-input-json | --cli-input-yaml]
[--starting-token <value>]
[--page-size <value>]
[--max-items <value>]
[--generate-cli-skeleton <value>]
[--debug]
[--endpoint-url <value>]
[--no-verify-ssl]
[--no-paginate]
[--output <value>]
[--query <value>]
[--profile <value>]
[--region <value>]
[--version <value>]
[--color <value>]
[--no-sign-request]
[--ca-bundle <value>]
[--cli-read-timeout <value>]
[--cli-connect-timeout <value>]
[--cli-binary-format <value>]
[--no-cli-pager]
[--cli-auto-prompt]
[--no-cli-auto-prompt]

Options¶

--flow-identifier (string) [required]

The unique identifier of the flow.

Constraints:

min: 0

max: 2048

pattern: (arn:aws:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:flow/[0-9a-zA-Z]{10})|([0-9a-zA-Z]{10})

--flow-alias-identifier (string) [required]

The unique identifier of the flow alias used for the execution.

Constraints:

min: 0

max: 2048

pattern: (arn:aws:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:flow/[0-9a-zA-Z]{10}/alias/[0-9a-zA-Z]{10})|(\bTSTALIASID\b|[0-9a-zA-Z]+)

--execution-identifier (string) [required]

The unique identifier of the flow execution.

Constraints:

min: 0

max: 2048

pattern: [a-zA-Z0-9-]{1,36}$|^(arn:aws:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:flow/[0-9a-zA-Z]{10}/alias/[0-9a-zA-Z]{10}/execution/[a-zA-Z0-9-]{1,36})

--event-type (string) [required]

The type of events to retrieve. Specify Node for node-level events or Flow for flow-level events.

Possible values:

Node

Flow

--cli-input-json | --cli-input-yaml (string) Reads arguments from the JSON string provided. The JSON string follows the format provided by --generate-cli-skeleton. If other arguments are provided on the command line, those values will override the JSON-provided values. It is not possible to pass arbitrary binary values using a JSON-provided value as the string will be taken literally. This may not be specified along with --cli-input-yaml.

--starting-token (string)

A token to specify where to start paginating. This is the NextToken from a previously truncated response.

For usage examples, see Pagination in the AWS Command Line Interface User Guide .

--page-size (integer)

The size of each page to get in the AWS service call. This does not affect the number of items returned in the command’s output. Setting a smaller page size results in more calls to the AWS service, retrieving fewer items in each call. This can help prevent the AWS service calls from timing out.

For usage examples, see Pagination in the AWS Command Line Interface User Guide .

--max-items (integer)

The total number of items to return in the command’s output. If the total number of items available is more than the value specified, a NextToken is provided in the command’s output. To resume pagination, provide the NextToken value in the starting-token argument of a subsequent command. Do not use the NextToken response element directly outside of the AWS CLI.

For usage examples, see Pagination in the AWS Command Line Interface User Guide .

--generate-cli-skeleton (string) Prints a JSON skeleton to standard output without sending an API request. If provided with no value or the value input, prints a sample input JSON that can be used as an argument for --cli-input-json. Similarly, if provided yaml-input it will print a sample input YAML that can be used with --cli-input-yaml. If provided with the value output, it validates the command inputs and returns a sample output JSON for that command. The generated JSON skeleton is not stable between versions of the AWS CLI and there are no backwards compatibility guarantees in the JSON skeleton generated.

Global Options¶

--debug (boolean)

Turn on debug logging.

--endpoint-url (string)

Override command’s default URL with the given URL.

--no-verify-ssl (boolean)

By default, the AWS CLI uses SSL when communicating with AWS services. For each SSL connection, the AWS CLI will verify SSL certificates. This option overrides the default behavior of verifying SSL certificates.

--no-paginate (boolean)

Disable automatic pagination. If automatic pagination is disabled, the AWS CLI will only make one call, for the first page of results.

--output (string)

The formatting style for command output.

json
text
table
yaml
yaml-stream

--query (string)

A JMESPath query to use in filtering the response data.

--profile (string)

Use a specific profile from your credential file.

--region (string)

The region to use. Overrides config/env settings.

--version (string)

Display the version of this tool.

--color (string)

Turn on/off color output.

on
off
auto

--no-sign-request (boolean)

Do not sign requests. Credentials will not be loaded if this argument is provided.

--ca-bundle (string)

The CA certificate bundle to use when verifying SSL certificates. Overrides config/env settings.

--cli-read-timeout (int)

The maximum socket read time in seconds. If the value is set to 0, the socket read will be blocking and not timeout. The default value is 60 seconds.

--cli-connect-timeout (int)

The maximum socket connect time in seconds. If the value is set to 0, the socket connect will be blocking and not timeout. The default value is 60 seconds.

--cli-binary-format (string)

The formatting style to be used for binary blobs. The default format is base64. The base64 format expects binary blobs to be provided as a base64 encoded string. The raw-in-base64-out format preserves compatibility with AWS CLI V1 behavior and binary values must be passed literally. When providing contents from a file that map to a binary blob fileb:// will always be treated as binary and use the file contents directly regardless of the cli-binary-format setting. When using file:// the file contents will need to properly formatted for the configured cli-binary-format.

base64
raw-in-base64-out

--no-cli-pager (boolean)

Disable cli pager for output.

--cli-auto-prompt (boolean)

Automatically prompt for CLI input parameters.

--no-cli-auto-prompt (boolean)

Disable automatically prompt for CLI input parameters.

Output¶

flowExecutionEvents -> (list)

A list of events that occurred during the flow execution. Events can include node inputs and outputs, flow inputs and outputs, condition results, and failure events.

Constraints:

min: 0

max: 10

(tagged union structure)

Represents an event that occurred during an flow execution. This is a union type that can contain one of several event types, such as node input and output events; flow input and output events; condition node result events, or failure events.

Note
Flow executions is in preview release for Amazon Bedrock and is subject to change.

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: flowInputEvent, flowOutputEvent, nodeInputEvent, nodeOutputEvent, conditionResultEvent, nodeFailureEvent, flowFailureEvent, nodeActionEvent, nodeDependencyEvent.

flowInputEvent -> (structure)

Contains information about the inputs provided to the flow at the start of execution.

nodeName -> (string) [required]

The name of the node that receives the inputs.

Constraints:

pattern: [a-zA-Z]([_]?[0-9a-zA-Z]){0,99}

timestamp -> (timestamp) [required]

The timestamp when the inputs are provided.

fields -> (list) [required]

A list of input fields provided to the flow.

Constraints:

min: 1

max: 5

(structure)

Represents an input field provided to a flow during a flow execution.

Note
Flow executions is in preview release for Amazon Bedrock and is subject to change.

name -> (string) [required]

The name of the input field as defined in the flow’s input schema.

Constraints:

pattern: [a-zA-Z]([_]?[0-9a-zA-Z]){0,99}

content -> (tagged union structure) [required]

The content of the input field, which can contain text or structured data.

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: document.

document -> (document)

The document content of the field, which can contain text or structured data.

flowOutputEvent -> (structure)

Contains information about the outputs produced by the flow at the end of execution.

nodeName -> (string) [required]

The name of the node that produces the outputs.

Constraints:

pattern: [a-zA-Z]([_]?[0-9a-zA-Z]){0,99}

timestamp -> (timestamp) [required]

The timestamp when the outputs are produced.

fields -> (list) [required]

A list of output fields produced by the flow.

Constraints:

min: 1

max: 5

(structure)

Represents an output field produced by a flow during a flow execution.

Note
Flow executions is in preview release for Amazon Bedrock and is subject to change.

name -> (string) [required]

The name of the output field as defined in the flow’s output schema.

Constraints:

pattern: [a-zA-Z]([_]?[0-9a-zA-Z]){0,99}

content -> (tagged union structure) [required]

The content of the output field, which can contain text or structured data.

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: document.

document -> (document)

The document content of the field, which can contain text or structured data.

nodeInputEvent -> (structure)

Contains information about the inputs provided to a specific node during execution.

nodeName -> (string) [required]

The name of the node that received the inputs.

Constraints:

pattern: [a-zA-Z]([_]?[0-9a-zA-Z]){0,99}

timestamp -> (timestamp) [required]

The timestamp when the inputs were provided to the node.

fields -> (list) [required]

A list of input fields provided to the node.

Constraints:

min: 1

max: 5

(structure)

Represents an input field provided to a node during a flow execution.

name -> (string) [required]

The name of the input field as defined in the node’s input schema.

Constraints:

pattern: [a-zA-Z]([_]?[0-9a-zA-Z]){0,99}

content -> (tagged union structure) [required]

The content of the input field, which can contain text or structured data.

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: document.

document -> (document)

The document content of the field, which can contain text or structured data.

source -> (structure)

The source node that provides input data to this field.

nodeName -> (string) [required]

The name of the source node that provides the input data.

Constraints:

pattern: [a-zA-Z]([_]?[0-9a-zA-Z]){0,99}

outputFieldName -> (string) [required]

The name of the output field from the source node.

Constraints:

pattern: [a-zA-Z]([_]?[0-9a-zA-Z]){1,50}

expression -> (string) [required]

The expression used to extract data from the source.

Constraints:

min: 1

max: 64

type -> (string)

The data type of the input field for compatibility validation.

Possible values:

String

Number

Boolean

Object

Array

category -> (string)

The category of the input field.

Possible values:

LoopCondition

ReturnValueToLoopStart

ExitLoop

executionChain -> (list)

The execution path through nested nodes like iterators and loops.

(structure)

Represents an item in the execution chain for node input tracking.

nodeName -> (string) [required]

The name of the node in the execution chain.

Constraints:

pattern: [a-zA-Z]([_]?[0-9a-zA-Z]){0,99}

index -> (integer)

The index position of this item in the execution chain.

type -> (string) [required]

The type of execution chain item. Supported values are Iterator and Loop.

Possible values:

Iterator

Loop

nodeOutputEvent -> (structure)

Contains information about the outputs produced by a specific node during execution.

nodeName -> (string) [required]

The name of the node that produced the outputs.

Constraints:

pattern: [a-zA-Z]([_]?[0-9a-zA-Z]){0,99}

timestamp -> (timestamp) [required]

The timestamp when the outputs were produced by the node.

fields -> (list) [required]

A list of output fields produced by the node.

Constraints:

min: 1

max: 2

(structure)

Represents an output field produced by a node during a flow execution.

Note
Flow executions is in preview release for Amazon Bedrock and is subject to change.

name -> (string) [required]

The name of the output field as defined in the node’s output schema.

Constraints:

pattern: [a-zA-Z]([_]?[0-9a-zA-Z]){0,99}

content -> (tagged union structure) [required]

The content of the output field, which can contain text or structured data.

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: document.

document -> (document)

The document content of the field, which can contain text or structured data.

next -> (list)

The next node that receives output data from this field.

(structure)

Represents the next node that receives output data.

nodeName -> (string) [required]

The name of the next node that receives the output data.

Constraints:

pattern: [a-zA-Z]([_]?[0-9a-zA-Z]){0,99}

inputFieldName -> (string) [required]

The name of the input field in the next node that receives the data.

Constraints:

pattern: [a-zA-Z]([_]?[0-9a-zA-Z]){1,50}

type -> (string)

The data type of the output field for compatibility validation.

Possible values:

String

Number

Boolean

Object

Array

conditionResultEvent -> (structure)

Contains information about a condition evaluation result during the flow execution. This event is generated when a condition node in the flow evaluates its conditions.

nodeName -> (string) [required]

The name of the condition node that evaluated the conditions.

Constraints:

pattern: [a-zA-Z]([_]?[0-9a-zA-Z]){0,99}

timestamp -> (timestamp) [required]

The timestamp when the condition evaluation occurred.

satisfiedConditions -> (list) [required]

A list of conditions that were satisfied during the evaluation.

Constraints:

min: 1

max: 5

(structure)

Represents a condition that was satisfied during a condition node evaluation in a flow execution.

Note
Flow executions is in preview release for Amazon Bedrock and is subject to change.

conditionName -> (string) [required]

The name of the condition that was satisfied.

nodeFailureEvent -> (structure)

Contains information about a failure that occurred at a specific node during execution.

nodeName -> (string) [required]

The name of the node where the failure occurred.

Constraints:

pattern: [a-zA-Z]([_]?[0-9a-zA-Z]){0,99}

timestamp -> (timestamp) [required]

The timestamp when the node failure occurred.

errorCode -> (string) [required]

The error code that identifies the type of failure that occurred at the node.

Possible values:

VALIDATION

DEPENDENCY_FAILED

BAD_GATEWAY

INTERNAL_SERVER

errorMessage -> (string) [required]

A descriptive message that provides details about the node failure.

flowFailureEvent -> (structure)

Contains information about a failure that occurred at the flow level during execution.

timestamp -> (timestamp) [required]

The timestamp when the failure occurred.

errorCode -> (string) [required]

The error code that identifies the type of failure that occurred.

Possible values:

VALIDATION

INTERNAL_SERVER

NODE_EXECUTION_FAILED

errorMessage -> (string) [required]

A descriptive message that provides details about the failure.

nodeActionEvent -> (structure)

Contains information about an action (operation) called by a node during execution.

nodeName -> (string) [required]

The name of the node that called the operation.

Constraints:

pattern: [a-zA-Z]([_]?[0-9a-zA-Z]){0,99}

timestamp -> (timestamp) [required]

The date and time that the operation was called.

requestId -> (string) [required]

The ID of the request that the node made to the operation.

serviceName -> (string) [required]

The name of the service that the node called.

operationName -> (string) [required]

The name of the operation that the node called.

operationRequest -> (document)

The request payload sent to the downstream service.

operationResponse -> (document)

The response payload received from the downstream service.

nodeDependencyEvent -> (structure)

Contains information about an internal trace of a specific node during execution.

nodeName -> (string) [required]

The name of the node that generated the dependency trace.

Constraints:

pattern: [a-zA-Z]([_]?[0-9a-zA-Z]){0,99}

timestamp -> (timestamp) [required]

The date and time that the dependency trace was generated.

traceElements -> (tagged union structure) [required]

The trace elements containing detailed information about the node execution.

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: agentTraces.

agentTraces -> (list)

Agent trace information for the node execution.

(structure)

Contains information about the agent and session, alongside the agent’s reasoning process and results from calling API actions and querying knowledge bases and metadata about the trace. You can use the trace to understand how the agent arrived at the response it provided the customer. For more information, see Trace enablement .

sessionId -> (string)

The unique identifier of the session with the agent.

Constraints:

min: 2

max: 100

pattern: [0-9a-zA-Z._:-]+

trace -> (tagged union structure)

Contains one part of the agent’s reasoning process and results from calling API actions and querying knowledge bases. You can use the trace to understand how the agent arrived at the response it provided the customer. For more information, see Trace enablement .

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: guardrailTrace, preProcessingTrace, orchestrationTrace, postProcessingTrace, routingClassifierTrace, failureTrace, customOrchestrationTrace.

guardrailTrace -> (structure)

The trace details for a trace defined in the Guardrail filter.

action -> (string)

The trace action details used with the Guardrail.

Possible values:

INTERVENED

NONE

traceId -> (string)

The details of the trace Id used in the Guardrail Trace.

Constraints:

min: 2

max: 16

inputAssessments -> (list)

The details of the input assessments used in the Guardrail Trace.

(structure)

Assessment details of the content analyzed by Guardrails.

topicPolicy -> (structure)

Topic policy details of the Guardrail.

topics -> (list)

The topic details of the policy assessment used in the Guardrail.

(structure)

The details for a specific topic defined in the Guardrail.

name -> (string)

The name details on a specific topic in the Guardrail.

type -> (string)

The type details on a specific topic in the Guardrail.

Possible values:

DENY

action -> (string)

The action details on a specific topic in the Guardrail.

Possible values:

BLOCKED

contentPolicy -> (structure)

Content policy details of the Guardrail.

filters -> (list)

The filter details of the policy assessment used in the Guardrails filter.

(structure)

Details of the content filter used in the Guardrail.

type -> (string)

The type of content detected in the filter by the Guardrail.

Possible values:

INSULTS

HATE

SEXUAL

VIOLENCE

MISCONDUCT

PROMPT_ATTACK

confidence -> (string)

The confidence level regarding the content detected in the filter by the Guardrail.

Possible values:

NONE

LOW

MEDIUM

HIGH

action -> (string)

The action placed on the content by the Guardrail filter.

Possible values:

BLOCKED

wordPolicy -> (structure)

Word policy details of the Guardrail.

customWords -> (list)

The custom word details for words defined in the Guardrail filter.

(structure)

The custom word details for the filter in the Guardrail.

match -> (string)

The match details for the custom word filter in the Guardrail.

action -> (string)

The action details for the custom word filter in the Guardrail.

Possible values:

BLOCKED

managedWordLists -> (list)

The managed word lists for words defined in the Guardrail filter.

(structure)

The managed word details for the filter in the Guardrail.

match -> (string)

The match details for the managed word filter in the Guardrail.

type -> (string)

The type details for the managed word filter in the Guardrail.

Possible values:

PROFANITY

action -> (string)

The action details for the managed word filter in the Guardrail.

Possible values:

BLOCKED

sensitiveInformationPolicy -> (structure)

Sensitive Information policy details of Guardrail.

piiEntities -> (list)

The details of the PII entities used in the sensitive policy assessment for the Guardrail.

(structure)

The Guardrail filter to identify and remove personally identifiable information (PII).

type -> (string)

The type of PII the Guardrail filter has identified and removed.

Possible values:

ADDRESS

AGE

AWS_ACCESS_KEY

AWS_SECRET_KEY

CA_HEALTH_NUMBER

CA_SOCIAL_INSURANCE_NUMBER

CREDIT_DEBIT_CARD_CVV

CREDIT_DEBIT_CARD_EXPIRY

CREDIT_DEBIT_CARD_NUMBER

DRIVER_ID

EMAIL

INTERNATIONAL_BANK_ACCOUNT_NUMBER

IP_ADDRESS

LICENSE_PLATE

MAC_ADDRESS

NAME

PASSWORD

PHONE

PIN

SWIFT_CODE

UK_NATIONAL_HEALTH_SERVICE_NUMBER

UK_NATIONAL_INSURANCE_NUMBER

UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER

URL

USERNAME

US_BANK_ACCOUNT_NUMBER

US_BANK_ROUTING_NUMBER

US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER

US_PASSPORT_NUMBER

US_SOCIAL_SECURITY_NUMBER

VEHICLE_IDENTIFICATION_NUMBER

match -> (string)

The match to settings in the Guardrail filter to identify and remove PII.

action -> (string)

The action of the Guardrail filter to identify and remove PII.

Possible values:

BLOCKED

ANONYMIZED

regexes -> (list)

The details of the regexes used in the sensitive policy assessment for the Guardrail.

(structure)

The details for the regex filter used in the Guardrail.

name -> (string)

The name details for the regex filter used in the Guardrail.

regex -> (string)

The regex details for the regex filter used in the Guardrail.

match -> (string)

The match details for the regex filter used in the Guardrail.

action -> (string)

The action details for the regex filter used in the Guardrail.

Possible values:

BLOCKED

ANONYMIZED

outputAssessments -> (list)

The details of the output assessments used in the Guardrail Trace.

(structure)

Assessment details of the content analyzed by Guardrails.

topicPolicy -> (structure)

Topic policy details of the Guardrail.

topics -> (list)

The topic details of the policy assessment used in the Guardrail.

(structure)

The details for a specific topic defined in the Guardrail.

name -> (string)

The name details on a specific topic in the Guardrail.

type -> (string)

The type details on a specific topic in the Guardrail.

Possible values:

DENY

action -> (string)

The action details on a specific topic in the Guardrail.

Possible values:

BLOCKED

contentPolicy -> (structure)

Content policy details of the Guardrail.

filters -> (list)

The filter details of the policy assessment used in the Guardrails filter.

(structure)

Details of the content filter used in the Guardrail.

type -> (string)

The type of content detected in the filter by the Guardrail.

Possible values:

INSULTS

HATE

SEXUAL

VIOLENCE

MISCONDUCT

PROMPT_ATTACK

confidence -> (string)

The confidence level regarding the content detected in the filter by the Guardrail.

Possible values:

NONE

LOW

MEDIUM

HIGH

action -> (string)

The action placed on the content by the Guardrail filter.

Possible values:

BLOCKED

wordPolicy -> (structure)

Word policy details of the Guardrail.

customWords -> (list)

The custom word details for words defined in the Guardrail filter.

(structure)

The custom word details for the filter in the Guardrail.

match -> (string)

The match details for the custom word filter in the Guardrail.

action -> (string)

The action details for the custom word filter in the Guardrail.

Possible values:

BLOCKED

managedWordLists -> (list)

The managed word lists for words defined in the Guardrail filter.

(structure)

The managed word details for the filter in the Guardrail.

match -> (string)

The match details for the managed word filter in the Guardrail.

type -> (string)

The type details for the managed word filter in the Guardrail.

Possible values:

PROFANITY

action -> (string)

The action details for the managed word filter in the Guardrail.

Possible values:

BLOCKED

sensitiveInformationPolicy -> (structure)

Sensitive Information policy details of Guardrail.

piiEntities -> (list)

The details of the PII entities used in the sensitive policy assessment for the Guardrail.

(structure)

The Guardrail filter to identify and remove personally identifiable information (PII).

type -> (string)

The type of PII the Guardrail filter has identified and removed.

Possible values:

ADDRESS

AGE

AWS_ACCESS_KEY

AWS_SECRET_KEY

CA_HEALTH_NUMBER

CA_SOCIAL_INSURANCE_NUMBER

CREDIT_DEBIT_CARD_CVV

CREDIT_DEBIT_CARD_EXPIRY

CREDIT_DEBIT_CARD_NUMBER

DRIVER_ID

EMAIL

INTERNATIONAL_BANK_ACCOUNT_NUMBER

IP_ADDRESS

LICENSE_PLATE

MAC_ADDRESS

NAME

PASSWORD

PHONE

PIN

SWIFT_CODE

UK_NATIONAL_HEALTH_SERVICE_NUMBER

UK_NATIONAL_INSURANCE_NUMBER

UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER

URL

USERNAME

US_BANK_ACCOUNT_NUMBER

US_BANK_ROUTING_NUMBER

US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER

US_PASSPORT_NUMBER

US_SOCIAL_SECURITY_NUMBER

VEHICLE_IDENTIFICATION_NUMBER

match -> (string)

The match to settings in the Guardrail filter to identify and remove PII.

action -> (string)

The action of the Guardrail filter to identify and remove PII.

Possible values:

BLOCKED

ANONYMIZED

regexes -> (list)

The details of the regexes used in the sensitive policy assessment for the Guardrail.

(structure)

The details for the regex filter used in the Guardrail.

name -> (string)

The name details for the regex filter used in the Guardrail.

regex -> (string)

The regex details for the regex filter used in the Guardrail.

match -> (string)

The match details for the regex filter used in the Guardrail.

action -> (string)

The action details for the regex filter used in the Guardrail.

Possible values:

BLOCKED

ANONYMIZED

metadata -> (structure)

Contains information about the Guardrail output.

startTime -> (timestamp)

In the final response, startTime is the start time of the agent invocation operation.

endTime -> (timestamp)

In the final response, endTime is the end time of the agent invocation operation.

totalTimeMs -> (long)

The total execution time for the specific invocation being processed (model, knowledge base, guardrail, agent collaborator, or code interpreter). It represents how long the individual invocation took.

operationTotalTimeMs -> (long)

The total time it took for the agent to complete execution. This field is only set for the final response.

clientRequestId -> (string)

A unique identifier associated with the downstream invocation. This ID can be used for tracing, debugging, and identifying specific invocations in customer logs or systems.

usage -> (structure)

Specific to model invocation and contains details about the usage of a foundation model.

inputTokens -> (integer)

Contains information about the input tokens from the foundation model usage.

outputTokens -> (integer)

Contains information about the output tokens from the foundation model usage.

preProcessingTrace -> (tagged union structure)

Details about the pre-processing step, in which the agent contextualizes and categorizes user inputs.

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: modelInvocationInput, modelInvocationOutput.

modelInvocationInput -> (structure)

The input for the pre-processing step.

The type is PRE_PROCESSING .

The text contains the prompt.

The inferenceConfiguration , parserMode , and overrideLambda values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.

traceId -> (string)

The unique identifier of the trace.

Constraints:

min: 2

max: 16

text -> (string)

The text that prompted the agent at this step.

type -> (string)

The step in the agent sequence.

Possible values:

PRE_PROCESSING

ORCHESTRATION

KNOWLEDGE_BASE_RESPONSE_GENERATION

POST_PROCESSING

ROUTING_CLASSIFIER

overrideLambda -> (string)

The ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence.

promptCreationMode -> (string)

Specifies whether the default prompt template was OVERRIDDEN . If it was, the basePromptTemplate that was set in the PromptOverrideConfiguration object when the agent was created or updated is used instead.

Possible values:

DEFAULT

OVERRIDDEN

inferenceConfiguration -> (structure)

Specifications about the inference parameters that were provided alongside the prompt. These are specified in the PromptOverrideConfiguration object that was set when the agent was created or updated. For more information, see Inference parameters for foundation models .

temperature -> (float)

The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.

Constraints:

min: 0

max: 1

topP -> (float)

While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for Top P determines the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set topP to 0.8, the model only selects the next token from the top 80% of the probability distribution of next tokens.

Constraints:

min: 0

max: 1

topK -> (integer)

While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for topK is the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set topK to 50, the model selects the next token from among the top 50 most likely choices.

Constraints:

min: 0

max: 500

maximumLength -> (integer)

The maximum number of tokens allowed in the generated response.

Constraints:

min: 0

max: 8192

stopSequences -> (list)

A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.

Constraints:

min: 0

max: 4

(string)

parserMode -> (string)

Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the promptType .

Possible values:

DEFAULT

OVERRIDDEN

foundationModel -> (string)

The identifier of a foundation model.

Constraints:

min: 1

max: 2048

pattern: .*(^arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:(([0-9]{12}:custom-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}(([:][a-z0-9-]{1,63}){0,2})?/[a-z0-9]{12})|(:foundation-model/([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.]?[a-z0-9-]{1,63})([:][a-z0-9-]{1,63}){0,2})))|(([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.]?[a-z0-9-]{1,63})([:][a-z0-9-]{1,63}){0,2}))|(([0-9a-zA-Z][_-]?)+))$|(^arn:aws(|-us-gov|-cn|-iso|-iso-b):bedrock:(|[0-9a-z-]{1,20}):(|[0-9]{12}):inference-profile/[a-zA-Z0-9-:.]+)

modelInvocationOutput -> (structure)

The foundation model output from the pre-processing step.

traceId -> (string)

The unique identifier of the trace.

Constraints:

min: 2

max: 16

parsedResponse -> (structure)

Details about the response from the Lambda parsing of the output of the pre-processing step.

rationale -> (string)

The text returned by the parsing of the pre-processing step, explaining the steps that the agent plans to take in orchestration, if the user input is valid.

isValid -> (boolean)

Whether the user input is valid or not. If false , the agent doesn’t proceed to orchestration.

rawResponse -> (structure)

Details of the raw response from the foundation model output.

content -> (string)

The foundation model’s raw output content.

metadata -> (structure)

Contains information about the foundation model output from the pre-processing step.

startTime -> (timestamp)

In the final response, startTime is the start time of the agent invocation operation.

endTime -> (timestamp)

In the final response, endTime is the end time of the agent invocation operation.

totalTimeMs -> (long)

The total execution time for the specific invocation being processed (model, knowledge base, guardrail, agent collaborator, or code interpreter). It represents how long the individual invocation took.

operationTotalTimeMs -> (long)

The total time it took for the agent to complete execution. This field is only set for the final response.

clientRequestId -> (string)

A unique identifier associated with the downstream invocation. This ID can be used for tracing, debugging, and identifying specific invocations in customer logs or systems.

usage -> (structure)

Specific to model invocation and contains details about the usage of a foundation model.

inputTokens -> (integer)

Contains information about the input tokens from the foundation model usage.

outputTokens -> (integer)

Contains information about the output tokens from the foundation model usage.

reasoningContent -> (tagged union structure)

Contains content about the reasoning that the model made during the pre-processing step.

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: reasoningText, redactedContent.

reasoningText -> (structure)

Contains information about the reasoning that the model used to return the content in the content block.

text -> (string) [required]

Text describing the reasoning that the model used to return the content in the content block.

signature -> (string)

A hash of all the messages in the conversation to ensure that the content in the reasoning text block isn’t tampered with. You must submit the signature in subsequent Converse requests, in addition to the previous messages. If the previous messages are tampered with, the response throws an error.

redactedContent -> (blob)

The content in the reasoning that was encrypted by the model provider for trust and safety reasons.

orchestrationTrace -> (tagged union structure)

Details about the orchestration step, in which the agent determines the order in which actions are executed and which knowledge bases are retrieved.

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: rationale, invocationInput, observation, modelInvocationInput, modelInvocationOutput.

rationale -> (structure)

Details about the reasoning, based on the input, that the agent uses to justify carrying out an action group or getting information from a knowledge base.

traceId -> (string)

The unique identifier of the trace step.

Constraints:

min: 2

max: 16

text -> (string)

The reasoning or thought process of the agent, based on the input.

invocationInput -> (structure)

Contains information pertaining to the action group or knowledge base that is being invoked.

traceId -> (string)

The unique identifier of the trace.

Constraints:

min: 2

max: 16

invocationType -> (string)

Specifies whether the agent is invoking an action group or a knowledge base.

Possible values:

ACTION_GROUP

KNOWLEDGE_BASE

FINISH

ACTION_GROUP_CODE_INTERPRETER

AGENT_COLLABORATOR

actionGroupInvocationInput -> (structure)

Contains information about the action group to be invoked.

actionGroupName -> (string)

The name of the action group.

verb -> (string)

The API method being used, based off the action group.

apiPath -> (string)

The path to the API to call, based off the action group.

parameters -> (list)

The parameters in the Lambda input event.

(structure)

A parameter for the API request or function.

name -> (string)

The name of the parameter.

type -> (string)

The type of the parameter.

value -> (string)

The value of the parameter.

requestBody -> (structure)

The parameters in the request body for the Lambda input event.

content -> (map)

The content in the request body.

key -> (string)

value -> (list)

(structure)

A parameter for the API request or function.

name -> (string)

The name of the parameter.

type -> (string)

The type of the parameter.

value -> (string)

The value of the parameter.

function -> (string)

The function in the action group to call.

executionType -> (string)

How fulfillment of the action is handled. For more information, see Handling fulfillment of the action .

Possible values:

LAMBDA

RETURN_CONTROL

invocationId -> (string)

The unique identifier of the invocation. Only returned if the executionType is RETURN_CONTROL .

knowledgeBaseLookupInput -> (structure)

Contains details about the knowledge base to look up and the query to be made.

text -> (string)

The query made to the knowledge base.

knowledgeBaseId -> (string)

The unique identifier of the knowledge base to look up.

codeInterpreterInvocationInput -> (structure)

Contains information about the code interpreter to be invoked.

code -> (string)

The code for the code interpreter to use.

files -> (list)

Files that are uploaded for code interpreter to use.

(string)

agentCollaboratorInvocationInput -> (structure)

The collaborator’s invocation input.

agentCollaboratorName -> (string)

The collaborator’s name.

agentCollaboratorAliasArn -> (string)

The collaborator’s alias ARN.

Constraints:

min: 0

max: 2048

pattern: arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:agent-alias/[0-9a-zA-Z]{10}/[0-9a-zA-Z]{10}

input -> (structure)

Text or action invocation result input for the collaborator.

type -> (string)

The input type.

Possible values:

TEXT

RETURN_CONTROL

text -> (string)

Input text.

returnControlResults -> (structure)

An action invocation result.

invocationId -> (string)

The action’s invocation ID.

returnControlInvocationResults -> (list)

The action invocation result.

Constraints:

min: 1

max: 5

(tagged union structure)

A result from the invocation of an action. For more information, see Return control to the agent developer and Control session context .

This data type is used in the following API operations:

InvokeAgent request

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: apiResult, functionResult.

apiResult -> (structure)

The result from the API response from the action group invocation.

actionGroup -> (string) [required]

The action group that the API operation belongs to.

httpMethod -> (string)

The HTTP method for the API operation.

apiPath -> (string)

The path to the API operation.

confirmationState -> (string)

Controls the API operations or functions to invoke based on the user confirmation.

Possible values:

CONFIRM

DENY

responseState -> (string)

Controls the final response state returned to end user when API/Function execution failed. When this state is FAILURE, the request would fail with dependency failure exception. When this state is REPROMPT, the API/function response will be sent to model for re-prompt

Possible values:

FAILURE

REPROMPT

httpStatusCode -> (integer)

http status code from API execution response (for example: 200, 400, 500).

responseBody -> (map)

The response body from the API operation. The key of the object is the content type (currently, only TEXT is supported). The response may be returned directly or from the Lambda function.

key -> (string)

value -> (structure)

Contains the body of the API response.

This data type is used in the following API operations:

In the returnControlInvocationResults field of the InvokeAgent request

body -> (string)

The body of the API response.

images -> (list)

Lists details, including format and source, for the image in the response from the function call. You can specify only one image and the function in the returnControlInvocationResults must be a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools .

(structure)

Details about an image in the result from a function in the action group invocation. You can specify images only when the function is a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools .

format -> (string) [required]

The type of image in the result.

Possible values:

png

jpeg

gif

webp

source -> (tagged union structure) [required]

The source of the image in the result.

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: bytes.

bytes -> (blob)

The raw image bytes for the image. If you use an Amazon Web Services SDK, you don’t need to encode the image bytes in base64.

Constraints:

min: 1

agentId -> (string)

The agent’s ID.

functionResult -> (structure)

The result from the function from the action group invocation.

actionGroup -> (string) [required]

The action group that the function belongs to.

confirmationState -> (string)

Contains the user confirmation information about the function that was called.

Possible values:

CONFIRM

DENY

function -> (string)

The name of the function that was called.

responseBody -> (map)

The response from the function call using the parameters. The response might be returned directly or from the Lambda function. Specify TEXT or IMAGES . The key of the object is the content type. You can only specify one type. If you specify IMAGES , you can specify only one image. You can specify images only when the function in the returnControlInvocationResults is a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools .

key -> (string)

value -> (structure)

Contains the body of the API response.

This data type is used in the following API operations:

In the returnControlInvocationResults field of the InvokeAgent request

body -> (string)

The body of the API response.

images -> (list)

Lists details, including format and source, for the image in the response from the function call. You can specify only one image and the function in the returnControlInvocationResults must be a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools .

(structure)

Details about an image in the result from a function in the action group invocation. You can specify images only when the function is a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools .

format -> (string) [required]

The type of image in the result.

Possible values:

png

jpeg

gif

webp

source -> (tagged union structure) [required]

The source of the image in the result.

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: bytes.

bytes -> (blob)

The raw image bytes for the image. If you use an Amazon Web Services SDK, you don’t need to encode the image bytes in base64.

Constraints:

min: 1

responseState -> (string)

Controls the final response state returned to end user when API/Function execution failed. When this state is FAILURE, the request would fail with dependency failure exception. When this state is REPROMPT, the API/function response will be sent to model for re-prompt

Possible values:

FAILURE

REPROMPT

agentId -> (string)

The agent’s ID.

observation -> (structure)

Details about the observation (the output of the action group Lambda or knowledge base) made by the agent.

traceId -> (string)

The unique identifier of the trace.

Constraints:

min: 2

max: 16

type -> (string)

Specifies what kind of information the agent returns in the observation. The following values are possible.

ACTION_GROUP – The agent returns the result of an action group.

KNOWLEDGE_BASE – The agent returns information from a knowledge base.

FINISH – The agent returns a final response to the user with no follow-up.

ASK_USER – The agent asks the user a question.

REPROMPT – The agent prompts the user again for the same information.

Possible values:

ACTION_GROUP

AGENT_COLLABORATOR

KNOWLEDGE_BASE

FINISH

ASK_USER

REPROMPT

actionGroupInvocationOutput -> (structure)

Contains the JSON-formatted string returned by the API invoked by the action group.

text -> (string)

The JSON-formatted string returned by the API invoked by the action group.

metadata -> (structure)

Contains information about the action group output.

startTime -> (timestamp)

In the final response, startTime is the start time of the agent invocation operation.

endTime -> (timestamp)

In the final response, endTime is the end time of the agent invocation operation.

totalTimeMs -> (long)

The total execution time for the specific invocation being processed (model, knowledge base, guardrail, agent collaborator, or code interpreter). It represents how long the individual invocation took.

operationTotalTimeMs -> (long)

The total time it took for the agent to complete execution. This field is only set for the final response.

clientRequestId -> (string)

A unique identifier associated with the downstream invocation. This ID can be used for tracing, debugging, and identifying specific invocations in customer logs or systems.

usage -> (structure)

Specific to model invocation and contains details about the usage of a foundation model.

inputTokens -> (integer)

Contains information about the input tokens from the foundation model usage.

outputTokens -> (integer)

Contains information about the output tokens from the foundation model usage.

agentCollaboratorInvocationOutput -> (structure)

A collaborator’s invocation output.

agentCollaboratorName -> (string)

The output’s agent collaborator name.

agentCollaboratorAliasArn -> (string)

The output’s agent collaborator alias ARN.

Constraints:

min: 0

max: 2048

pattern: arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:agent-alias/[0-9a-zA-Z]{10}/[0-9a-zA-Z]{10}

output -> (structure)

The output’s output.

type -> (string)

The type of output.

Possible values:

TEXT

RETURN_CONTROL

text -> (string)

Text output.

returnControlPayload -> (structure)

An action invocation result.

invocationInputs -> (list)

A list of objects that contain information about the parameters and inputs that need to be sent into the API operation or function, based on what the agent determines from its session with the user.

Constraints:

min: 1

max: 5

(tagged union structure)

Contains details about the API operation or function that the agent predicts should be called.

This data type is used in the following API operations:

In the returnControl field of the InvokeAgent response

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: apiInvocationInput, functionInvocationInput.

apiInvocationInput -> (structure)

Contains information about the API operation that the agent predicts should be called.

actionGroup -> (string) [required]

The action group that the API operation belongs to.

httpMethod -> (string)

The HTTP method of the API operation.

apiPath -> (string)

The path to the API operation.

parameters -> (list)

The parameters to provide for the API request, as the agent elicited from the user.

(structure)

Information about a parameter to provide to the API request.

This data type is used in the following API operations:

InvokeAgent response

name -> (string)

The name of the parameter.

type -> (string)

The data type for the parameter.

value -> (string)

The value of the parameter.

requestBody -> (structure)

The request body to provide for the API request, as the agent elicited from the user.

content -> (map)

The content of the request body. The key of the object in this field is a media type defining the format of the request body.

key -> (string)

value -> (structure)

Contains the parameters in the request body.

properties -> (list)

A list of parameters in the request body.

(structure)

A parameter for the API request or function.

name -> (string)

The name of the parameter.

type -> (string)

The type of the parameter.

value -> (string)

The value of the parameter.

actionInvocationType -> (string)

Contains information about the API operation to invoke.

Possible values:

RESULT

USER_CONFIRMATION

USER_CONFIRMATION_AND_RESULT

agentId -> (string)

The agent’s ID.

collaboratorName -> (string)

The agent collaborator’s name.

Constraints:

pattern: ([0-9a-zA-Z][_-]?){1,100}

functionInvocationInput -> (structure)

Contains information about the function that the agent predicts should be called.

actionGroup -> (string) [required]

The action group that the function belongs to.

parameters -> (list)

A list of parameters of the function.

(structure)

Contains information about a parameter of the function.

This data type is used in the following API operations:

In the returnControl field of the InvokeAgent response

name -> (string)

The name of the parameter.

type -> (string)

The data type of the parameter.

value -> (string)

The value of the parameter.

function -> (string)

The name of the function.

actionInvocationType -> (string)

Contains information about the function to invoke,

Possible values:

RESULT

USER_CONFIRMATION

USER_CONFIRMATION_AND_RESULT

agentId -> (string)

The agent’s ID.

collaboratorName -> (string)

The collaborator’s name.

Constraints:

pattern: ([0-9a-zA-Z][_-]?){1,100}

invocationId -> (string)

The identifier of the action group invocation.

metadata -> (structure)

Contains information about the output from the agent collaborator.

startTime -> (timestamp)

In the final response, startTime is the start time of the agent invocation operation.

endTime -> (timestamp)

In the final response, endTime is the end time of the agent invocation operation.

totalTimeMs -> (long)

The total execution time for the specific invocation being processed (model, knowledge base, guardrail, agent collaborator, or code interpreter). It represents how long the individual invocation took.

operationTotalTimeMs -> (long)

The total time it took for the agent to complete execution. This field is only set for the final response.

clientRequestId -> (string)

A unique identifier associated with the downstream invocation. This ID can be used for tracing, debugging, and identifying specific invocations in customer logs or systems.

usage -> (structure)

Specific to model invocation and contains details about the usage of a foundation model.

inputTokens -> (integer)

Contains information about the input tokens from the foundation model usage.

outputTokens -> (integer)

Contains information about the output tokens from the foundation model usage.

knowledgeBaseLookupOutput -> (structure)

Contains details about the results from looking up the knowledge base.

retrievedReferences -> (list)

Contains metadata about the sources cited for the generated response.

(structure)

Contains metadata about a source cited for the generated response.

This data type is used in the following API operations:

RetrieveAndGenerate response – in the retrievedReferences field

InvokeAgent response – in the retrievedReferences field

content -> (structure)

Contains the cited text from the data source.

type -> (string)

The type of content in the retrieval result.

Possible values:

TEXT

IMAGE

ROW

text -> (string)

The cited text from the data source.

byteContent -> (string)

A data URI with base64-encoded content from the data source. The URI is in the following format: returned in the following format: data:image/jpeg;base64,${base64-encoded string} .

row -> (list)

Specifies information about the rows with the cells to return in retrieval.

(structure)

Contains information about a column with a cell to return in retrieval.

columnName -> (string)

The name of the column.

columnValue -> (string)

The value in the column.

type -> (string)

The data type of the value.

Possible values:

BLOB

BOOLEAN

DOUBLE

NULL

LONG

STRING

location -> (structure)

Contains information about the location of the data source.

type -> (string) [required]

The type of data source location.

Possible values:

S3

WEB

CONFLUENCE

SALESFORCE

SHAREPOINT

CUSTOM

KENDRA

SQL

s3Location -> (structure)

The S3 data source location.

uri -> (string)

The S3 URI for the data source location.

webLocation -> (structure)

The web URL/URLs data source location.

url -> (string)

The web URL/URLs for the data source location.

confluenceLocation -> (structure)

The Confluence data source location.

url -> (string)

The Confluence host URL for the data source location.

salesforceLocation -> (structure)

The Salesforce data source location.

url -> (string)

The Salesforce host URL for the data source location.

sharePointLocation -> (structure)

The SharePoint data source location.

url -> (string)

The SharePoint site URL for the data source location.

customDocumentLocation -> (structure)

Specifies the location of a document in a custom data source.

id -> (string)

The ID of the document.

kendraDocumentLocation -> (structure)

The location of a document in Amazon Kendra.

uri -> (string)

The document’s uri.

sqlLocation -> (structure)

Specifies information about the SQL query used to retrieve the result.

query -> (string)

The SQL query used to retrieve the result.

metadata -> (map)

Contains metadata attributes and their values for the file in the data source. For more information, see Metadata and filtering .

Constraints:

min: 1

key -> (string)

Constraints:

min: 1

max: 100

value -> (document)

metadata -> (structure)

Contains information about the knowledge base output.

startTime -> (timestamp)

In the final response, startTime is the start time of the agent invocation operation.

endTime -> (timestamp)

In the final response, endTime is the end time of the agent invocation operation.

totalTimeMs -> (long)

The total execution time for the specific invocation being processed (model, knowledge base, guardrail, agent collaborator, or code interpreter). It represents how long the individual invocation took.

operationTotalTimeMs -> (long)

The total time it took for the agent to complete execution. This field is only set for the final response.

clientRequestId -> (string)

A unique identifier associated with the downstream invocation. This ID can be used for tracing, debugging, and identifying specific invocations in customer logs or systems.

usage -> (structure)

Specific to model invocation and contains details about the usage of a foundation model.

inputTokens -> (integer)

Contains information about the input tokens from the foundation model usage.

outputTokens -> (integer)

Contains information about the output tokens from the foundation model usage.

finalResponse -> (structure)

Contains details about the response to the user.

text -> (string)

The text in the response to the user.

metadata -> (structure)

Contains information about the invoke agent operation.

startTime -> (timestamp)

In the final response, startTime is the start time of the agent invocation operation.

endTime -> (timestamp)

In the final response, endTime is the end time of the agent invocation operation.

totalTimeMs -> (long)

The total execution time for the specific invocation being processed (model, knowledge base, guardrail, agent collaborator, or code interpreter). It represents how long the individual invocation took.

operationTotalTimeMs -> (long)

The total time it took for the agent to complete execution. This field is only set for the final response.

clientRequestId -> (string)

A unique identifier associated with the downstream invocation. This ID can be used for tracing, debugging, and identifying specific invocations in customer logs or systems.

usage -> (structure)

Specific to model invocation and contains details about the usage of a foundation model.

inputTokens -> (integer)

Contains information about the input tokens from the foundation model usage.

outputTokens -> (integer)

Contains information about the output tokens from the foundation model usage.

repromptResponse -> (structure)

Contains details about the response to reprompt the input.

text -> (string)

The text reprompting the input.

source -> (string)

Specifies what output is prompting the agent to reprompt the input.

Possible values:

ACTION_GROUP

KNOWLEDGE_BASE

PARSER

codeInterpreterInvocationOutput -> (structure)

Contains the JSON-formatted string returned by the API invoked by the code interpreter.

executionOutput -> (string)

Contains the successful output returned from code execution

executionError -> (string)

Contains the error returned from code execution.

files -> (list)

Contains output files, if generated by code execution.

(string)

executionTimeout -> (boolean)

Indicates if the execution of the code timed out.

metadata -> (structure)

Contains information about the output from the code interpreter.

startTime -> (timestamp)

In the final response, startTime is the start time of the agent invocation operation.

endTime -> (timestamp)

In the final response, endTime is the end time of the agent invocation operation.

totalTimeMs -> (long)

The total execution time for the specific invocation being processed (model, knowledge base, guardrail, agent collaborator, or code interpreter). It represents how long the individual invocation took.

operationTotalTimeMs -> (long)

The total time it took for the agent to complete execution. This field is only set for the final response.

clientRequestId -> (string)

A unique identifier associated with the downstream invocation. This ID can be used for tracing, debugging, and identifying specific invocations in customer logs or systems.

usage -> (structure)

Specific to model invocation and contains details about the usage of a foundation model.

inputTokens -> (integer)

Contains information about the input tokens from the foundation model usage.

outputTokens -> (integer)

Contains information about the output tokens from the foundation model usage.

modelInvocationInput -> (structure)

The input for the orchestration step.

The type is ORCHESTRATION .

The text contains the prompt.

The inferenceConfiguration , parserMode , and overrideLambda values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.

traceId -> (string)

The unique identifier of the trace.

Constraints:

min: 2

max: 16

text -> (string)

The text that prompted the agent at this step.

type -> (string)

The step in the agent sequence.

Possible values:

PRE_PROCESSING

ORCHESTRATION

KNOWLEDGE_BASE_RESPONSE_GENERATION

POST_PROCESSING

ROUTING_CLASSIFIER

overrideLambda -> (string)

The ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence.

promptCreationMode -> (string)

Specifies whether the default prompt template was OVERRIDDEN . If it was, the basePromptTemplate that was set in the PromptOverrideConfiguration object when the agent was created or updated is used instead.

Possible values:

DEFAULT

OVERRIDDEN

inferenceConfiguration -> (structure)

Specifications about the inference parameters that were provided alongside the prompt. These are specified in the PromptOverrideConfiguration object that was set when the agent was created or updated. For more information, see Inference parameters for foundation models .

temperature -> (float)

The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.

Constraints:

min: 0

max: 1

topP -> (float)

While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for Top P determines the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set topP to 0.8, the model only selects the next token from the top 80% of the probability distribution of next tokens.

Constraints:

min: 0

max: 1

topK -> (integer)

While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for topK is the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set topK to 50, the model selects the next token from among the top 50 most likely choices.

Constraints:

min: 0

max: 500

maximumLength -> (integer)

The maximum number of tokens allowed in the generated response.

Constraints:

min: 0

max: 8192

stopSequences -> (list)

A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.

Constraints:

min: 0

max: 4

(string)

parserMode -> (string)

Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the promptType .

Possible values:

DEFAULT

OVERRIDDEN

foundationModel -> (string)

The identifier of a foundation model.

Constraints:

min: 1

max: 2048

pattern: .*(^arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:(([0-9]{12}:custom-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}(([:][a-z0-9-]{1,63}){0,2})?/[a-z0-9]{12})|(:foundation-model/([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.]?[a-z0-9-]{1,63})([:][a-z0-9-]{1,63}){0,2})))|(([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.]?[a-z0-9-]{1,63})([:][a-z0-9-]{1,63}){0,2}))|(([0-9a-zA-Z][_-]?)+))$|(^arn:aws(|-us-gov|-cn|-iso|-iso-b):bedrock:(|[0-9a-z-]{1,20}):(|[0-9]{12}):inference-profile/[a-zA-Z0-9-:.]+)

modelInvocationOutput -> (structure)

Contains information pertaining to the output from the foundation model that is being invoked.

traceId -> (string)

The unique identifier of the trace.

Constraints:

min: 2

max: 16

rawResponse -> (structure)

Contains details of the raw response from the foundation model output.

content -> (string)

The foundation model’s raw output content.

metadata -> (structure)

Contains information about the foundation model output from the orchestration step.

startTime -> (timestamp)

In the final response, startTime is the start time of the agent invocation operation.

endTime -> (timestamp)

In the final response, endTime is the end time of the agent invocation operation.

totalTimeMs -> (long)

The total execution time for the specific invocation being processed (model, knowledge base, guardrail, agent collaborator, or code interpreter). It represents how long the individual invocation took.

operationTotalTimeMs -> (long)

The total time it took for the agent to complete execution. This field is only set for the final response.

clientRequestId -> (string)

A unique identifier associated with the downstream invocation. This ID can be used for tracing, debugging, and identifying specific invocations in customer logs or systems.

usage -> (structure)

Specific to model invocation and contains details about the usage of a foundation model.

inputTokens -> (integer)

Contains information about the input tokens from the foundation model usage.

outputTokens -> (integer)

Contains information about the output tokens from the foundation model usage.

reasoningContent -> (tagged union structure)

Contains content about the reasoning that the model made during the orchestration step.

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: reasoningText, redactedContent.

reasoningText -> (structure)

Contains information about the reasoning that the model used to return the content in the content block.

text -> (string) [required]

Text describing the reasoning that the model used to return the content in the content block.

signature -> (string)

A hash of all the messages in the conversation to ensure that the content in the reasoning text block isn’t tampered with. You must submit the signature in subsequent Converse requests, in addition to the previous messages. If the previous messages are tampered with, the response throws an error.

redactedContent -> (blob)

The content in the reasoning that was encrypted by the model provider for trust and safety reasons.

postProcessingTrace -> (tagged union structure)

Details about the post-processing step, in which the agent shapes the response..

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: modelInvocationInput, modelInvocationOutput.

modelInvocationInput -> (structure)

The input for the post-processing step.

The type is POST_PROCESSING .

The text contains the prompt.

The inferenceConfiguration , parserMode , and overrideLambda values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.

traceId -> (string)

The unique identifier of the trace.

Constraints:

min: 2

max: 16

text -> (string)

The text that prompted the agent at this step.

type -> (string)

The step in the agent sequence.

Possible values:

PRE_PROCESSING

ORCHESTRATION

KNOWLEDGE_BASE_RESPONSE_GENERATION

POST_PROCESSING

ROUTING_CLASSIFIER

overrideLambda -> (string)

The ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence.

promptCreationMode -> (string)

Specifies whether the default prompt template was OVERRIDDEN . If it was, the basePromptTemplate that was set in the PromptOverrideConfiguration object when the agent was created or updated is used instead.

Possible values:

DEFAULT

OVERRIDDEN

inferenceConfiguration -> (structure)

Specifications about the inference parameters that were provided alongside the prompt. These are specified in the PromptOverrideConfiguration object that was set when the agent was created or updated. For more information, see Inference parameters for foundation models .

temperature -> (float)

The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.

Constraints:

min: 0

max: 1

topP -> (float)

While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for Top P determines the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set topP to 0.8, the model only selects the next token from the top 80% of the probability distribution of next tokens.

Constraints:

min: 0

max: 1

topK -> (integer)

While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for topK is the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set topK to 50, the model selects the next token from among the top 50 most likely choices.

Constraints:

min: 0

max: 500

maximumLength -> (integer)

The maximum number of tokens allowed in the generated response.

Constraints:

min: 0

max: 8192

stopSequences -> (list)

A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.

Constraints:

min: 0

max: 4

(string)

parserMode -> (string)

Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the promptType .

Possible values:

DEFAULT

OVERRIDDEN

foundationModel -> (string)

The identifier of a foundation model.

Constraints:

min: 1

max: 2048

pattern: .*(^arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:(([0-9]{12}:custom-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}(([:][a-z0-9-]{1,63}){0,2})?/[a-z0-9]{12})|(:foundation-model/([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.]?[a-z0-9-]{1,63})([:][a-z0-9-]{1,63}){0,2})))|(([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.]?[a-z0-9-]{1,63})([:][a-z0-9-]{1,63}){0,2}))|(([0-9a-zA-Z][_-]?)+))$|(^arn:aws(|-us-gov|-cn|-iso|-iso-b):bedrock:(|[0-9a-z-]{1,20}):(|[0-9]{12}):inference-profile/[a-zA-Z0-9-:.]+)

modelInvocationOutput -> (structure)

The foundation model output from the post-processing step.

traceId -> (string)

The unique identifier of the trace.

Constraints:

min: 2

max: 16

parsedResponse -> (structure)

Details about the response from the Lambda parsing of the output of the post-processing step.

text -> (string)

The text returned by the parser.

rawResponse -> (structure)

Details of the raw response from the foundation model output.

content -> (string)

The foundation model’s raw output content.

metadata -> (structure)

Contains information about the foundation model output from the post-processing step.

startTime -> (timestamp)

In the final response, startTime is the start time of the agent invocation operation.

endTime -> (timestamp)

In the final response, endTime is the end time of the agent invocation operation.

totalTimeMs -> (long)

The total execution time for the specific invocation being processed (model, knowledge base, guardrail, agent collaborator, or code interpreter). It represents how long the individual invocation took.

operationTotalTimeMs -> (long)

The total time it took for the agent to complete execution. This field is only set for the final response.

clientRequestId -> (string)

A unique identifier associated with the downstream invocation. This ID can be used for tracing, debugging, and identifying specific invocations in customer logs or systems.

usage -> (structure)

Specific to model invocation and contains details about the usage of a foundation model.

inputTokens -> (integer)

Contains information about the input tokens from the foundation model usage.

outputTokens -> (integer)

Contains information about the output tokens from the foundation model usage.

reasoningContent -> (tagged union structure)

Contains content about the reasoning that the model made during the post-processing step.

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: reasoningText, redactedContent.

reasoningText -> (structure)

Contains information about the reasoning that the model used to return the content in the content block.

text -> (string) [required]

Text describing the reasoning that the model used to return the content in the content block.

signature -> (string)

A hash of all the messages in the conversation to ensure that the content in the reasoning text block isn’t tampered with. You must submit the signature in subsequent Converse requests, in addition to the previous messages. If the previous messages are tampered with, the response throws an error.

redactedContent -> (blob)

The content in the reasoning that was encrypted by the model provider for trust and safety reasons.

routingClassifierTrace -> (tagged union structure)

A routing classifier’s trace.

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: invocationInput, observation, modelInvocationInput, modelInvocationOutput.

invocationInput -> (structure)

The classifier’s invocation input.

traceId -> (string)

The unique identifier of the trace.

Constraints:

min: 2

max: 16

invocationType -> (string)

Specifies whether the agent is invoking an action group or a knowledge base.

Possible values:

ACTION_GROUP

KNOWLEDGE_BASE

FINISH

ACTION_GROUP_CODE_INTERPRETER

AGENT_COLLABORATOR

actionGroupInvocationInput -> (structure)

Contains information about the action group to be invoked.

actionGroupName -> (string)

The name of the action group.

verb -> (string)

The API method being used, based off the action group.

apiPath -> (string)

The path to the API to call, based off the action group.

parameters -> (list)

The parameters in the Lambda input event.

(structure)

A parameter for the API request or function.

name -> (string)

The name of the parameter.

type -> (string)

The type of the parameter.

value -> (string)

The value of the parameter.

requestBody -> (structure)

The parameters in the request body for the Lambda input event.

content -> (map)

The content in the request body.

key -> (string)

value -> (list)

(structure)

A parameter for the API request or function.

name -> (string)

The name of the parameter.

type -> (string)

The type of the parameter.

value -> (string)

The value of the parameter.

function -> (string)

The function in the action group to call.

executionType -> (string)

How fulfillment of the action is handled. For more information, see Handling fulfillment of the action .

Possible values:

LAMBDA

RETURN_CONTROL

invocationId -> (string)

The unique identifier of the invocation. Only returned if the executionType is RETURN_CONTROL .

knowledgeBaseLookupInput -> (structure)

Contains details about the knowledge base to look up and the query to be made.

text -> (string)

The query made to the knowledge base.

knowledgeBaseId -> (string)

The unique identifier of the knowledge base to look up.

codeInterpreterInvocationInput -> (structure)

Contains information about the code interpreter to be invoked.

code -> (string)

The code for the code interpreter to use.

files -> (list)

Files that are uploaded for code interpreter to use.

(string)

agentCollaboratorInvocationInput -> (structure)

The collaborator’s invocation input.

agentCollaboratorName -> (string)

The collaborator’s name.

agentCollaboratorAliasArn -> (string)

The collaborator’s alias ARN.

Constraints:

min: 0

max: 2048

pattern: arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:agent-alias/[0-9a-zA-Z]{10}/[0-9a-zA-Z]{10}

input -> (structure)

Text or action invocation result input for the collaborator.

type -> (string)

The input type.

Possible values:

TEXT

RETURN_CONTROL

text -> (string)

Input text.

returnControlResults -> (structure)

An action invocation result.

invocationId -> (string)

The action’s invocation ID.

returnControlInvocationResults -> (list)

The action invocation result.

Constraints:

min: 1

max: 5

(tagged union structure)

A result from the invocation of an action. For more information, see Return control to the agent developer and Control session context .

This data type is used in the following API operations:

InvokeAgent request

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: apiResult, functionResult.

apiResult -> (structure)

The result from the API response from the action group invocation.

actionGroup -> (string) [required]

The action group that the API operation belongs to.

httpMethod -> (string)

The HTTP method for the API operation.

apiPath -> (string)

The path to the API operation.

confirmationState -> (string)

Controls the API operations or functions to invoke based on the user confirmation.

Possible values:

CONFIRM

DENY

responseState -> (string)

Controls the final response state returned to end user when API/Function execution failed. When this state is FAILURE, the request would fail with dependency failure exception. When this state is REPROMPT, the API/function response will be sent to model for re-prompt

Possible values:

FAILURE

REPROMPT

httpStatusCode -> (integer)

http status code from API execution response (for example: 200, 400, 500).

responseBody -> (map)

The response body from the API operation. The key of the object is the content type (currently, only TEXT is supported). The response may be returned directly or from the Lambda function.

key -> (string)

value -> (structure)

Contains the body of the API response.

This data type is used in the following API operations:

In the returnControlInvocationResults field of the InvokeAgent request

body -> (string)

The body of the API response.

images -> (list)

Lists details, including format and source, for the image in the response from the function call. You can specify only one image and the function in the returnControlInvocationResults must be a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools .

(structure)

Details about an image in the result from a function in the action group invocation. You can specify images only when the function is a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools .

format -> (string) [required]

The type of image in the result.

Possible values:

png

jpeg

gif

webp

source -> (tagged union structure) [required]

The source of the image in the result.

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: bytes.

bytes -> (blob)

The raw image bytes for the image. If you use an Amazon Web Services SDK, you don’t need to encode the image bytes in base64.

Constraints:

min: 1

agentId -> (string)

The agent’s ID.

functionResult -> (structure)

The result from the function from the action group invocation.

actionGroup -> (string) [required]

The action group that the function belongs to.

confirmationState -> (string)

Contains the user confirmation information about the function that was called.

Possible values:

CONFIRM

DENY

function -> (string)

The name of the function that was called.

responseBody -> (map)

The response from the function call using the parameters. The response might be returned directly or from the Lambda function. Specify TEXT or IMAGES . The key of the object is the content type. You can only specify one type. If you specify IMAGES , you can specify only one image. You can specify images only when the function in the returnControlInvocationResults is a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools .

key -> (string)

value -> (structure)

Contains the body of the API response.

This data type is used in the following API operations:

In the returnControlInvocationResults field of the InvokeAgent request

body -> (string)

The body of the API response.

images -> (list)

Lists details, including format and source, for the image in the response from the function call. You can specify only one image and the function in the returnControlInvocationResults must be a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools .

(structure)

Details about an image in the result from a function in the action group invocation. You can specify images only when the function is a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools .

format -> (string) [required]

The type of image in the result.

Possible values:

png

jpeg

gif

webp

source -> (tagged union structure) [required]

The source of the image in the result.

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: bytes.

bytes -> (blob)

The raw image bytes for the image. If you use an Amazon Web Services SDK, you don’t need to encode the image bytes in base64.

Constraints:

min: 1

responseState -> (string)

Controls the final response state returned to end user when API/Function execution failed. When this state is FAILURE, the request would fail with dependency failure exception. When this state is REPROMPT, the API/function response will be sent to model for re-prompt

Possible values:

FAILURE

REPROMPT

agentId -> (string)

The agent’s ID.

observation -> (structure)

The classifier’s observation.

traceId -> (string)

The unique identifier of the trace.

Constraints:

min: 2

max: 16

type -> (string)

Specifies what kind of information the agent returns in the observation. The following values are possible.

ACTION_GROUP – The agent returns the result of an action group.

KNOWLEDGE_BASE – The agent returns information from a knowledge base.

FINISH – The agent returns a final response to the user with no follow-up.

ASK_USER – The agent asks the user a question.

REPROMPT – The agent prompts the user again for the same information.

Possible values:

ACTION_GROUP

AGENT_COLLABORATOR

KNOWLEDGE_BASE

FINISH

ASK_USER

REPROMPT

actionGroupInvocationOutput -> (structure)

Contains the JSON-formatted string returned by the API invoked by the action group.

text -> (string)

The JSON-formatted string returned by the API invoked by the action group.

metadata -> (structure)

Contains information about the action group output.

startTime -> (timestamp)

In the final response, startTime is the start time of the agent invocation operation.

endTime -> (timestamp)

In the final response, endTime is the end time of the agent invocation operation.

totalTimeMs -> (long)

The total execution time for the specific invocation being processed (model, knowledge base, guardrail, agent collaborator, or code interpreter). It represents how long the individual invocation took.

operationTotalTimeMs -> (long)

The total time it took for the agent to complete execution. This field is only set for the final response.

clientRequestId -> (string)

A unique identifier associated with the downstream invocation. This ID can be used for tracing, debugging, and identifying specific invocations in customer logs or systems.

usage -> (structure)

Specific to model invocation and contains details about the usage of a foundation model.

inputTokens -> (integer)

Contains information about the input tokens from the foundation model usage.

outputTokens -> (integer)

Contains information about the output tokens from the foundation model usage.

agentCollaboratorInvocationOutput -> (structure)

A collaborator’s invocation output.

agentCollaboratorName -> (string)

The output’s agent collaborator name.

agentCollaboratorAliasArn -> (string)

The output’s agent collaborator alias ARN.

Constraints:

min: 0

max: 2048

pattern: arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:agent-alias/[0-9a-zA-Z]{10}/[0-9a-zA-Z]{10}

output -> (structure)

The output’s output.

type -> (string)

The type of output.

Possible values:

TEXT

RETURN_CONTROL

text -> (string)

Text output.

returnControlPayload -> (structure)

An action invocation result.

invocationInputs -> (list)

A list of objects that contain information about the parameters and inputs that need to be sent into the API operation or function, based on what the agent determines from its session with the user.

Constraints:

min: 1

max: 5

(tagged union structure)

Contains details about the API operation or function that the agent predicts should be called.

This data type is used in the following API operations:

In the returnControl field of the InvokeAgent response

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: apiInvocationInput, functionInvocationInput.

apiInvocationInput -> (structure)

Contains information about the API operation that the agent predicts should be called.

actionGroup -> (string) [required]

The action group that the API operation belongs to.

httpMethod -> (string)

The HTTP method of the API operation.

apiPath -> (string)

The path to the API operation.

parameters -> (list)

The parameters to provide for the API request, as the agent elicited from the user.

(structure)

Information about a parameter to provide to the API request.

This data type is used in the following API operations:

InvokeAgent response

name -> (string)

The name of the parameter.

type -> (string)

The data type for the parameter.

value -> (string)

The value of the parameter.

requestBody -> (structure)

The request body to provide for the API request, as the agent elicited from the user.

content -> (map)

The content of the request body. The key of the object in this field is a media type defining the format of the request body.

key -> (string)

value -> (structure)

Contains the parameters in the request body.

properties -> (list)

A list of parameters in the request body.

(structure)

A parameter for the API request or function.

name -> (string)

The name of the parameter.

type -> (string)

The type of the parameter.

value -> (string)

The value of the parameter.

actionInvocationType -> (string)

Contains information about the API operation to invoke.

Possible values:

RESULT

USER_CONFIRMATION

USER_CONFIRMATION_AND_RESULT

agentId -> (string)

The agent’s ID.

collaboratorName -> (string)

The agent collaborator’s name.

Constraints:

pattern: ([0-9a-zA-Z][_-]?){1,100}

functionInvocationInput -> (structure)

Contains information about the function that the agent predicts should be called.

actionGroup -> (string) [required]

The action group that the function belongs to.

parameters -> (list)

A list of parameters of the function.

(structure)

Contains information about a parameter of the function.

This data type is used in the following API operations:

In the returnControl field of the InvokeAgent response

name -> (string)

The name of the parameter.

type -> (string)

The data type of the parameter.

value -> (string)

The value of the parameter.

function -> (string)

The name of the function.

actionInvocationType -> (string)

Contains information about the function to invoke,

Possible values:

RESULT

USER_CONFIRMATION

USER_CONFIRMATION_AND_RESULT

agentId -> (string)

The agent’s ID.

collaboratorName -> (string)

The collaborator’s name.

Constraints:

pattern: ([0-9a-zA-Z][_-]?){1,100}

invocationId -> (string)

The identifier of the action group invocation.

metadata -> (structure)

Contains information about the output from the agent collaborator.

startTime -> (timestamp)

In the final response, startTime is the start time of the agent invocation operation.

endTime -> (timestamp)

In the final response, endTime is the end time of the agent invocation operation.

totalTimeMs -> (long)

The total execution time for the specific invocation being processed (model, knowledge base, guardrail, agent collaborator, or code interpreter). It represents how long the individual invocation took.

operationTotalTimeMs -> (long)

The total time it took for the agent to complete execution. This field is only set for the final response.

clientRequestId -> (string)

A unique identifier associated with the downstream invocation. This ID can be used for tracing, debugging, and identifying specific invocations in customer logs or systems.

usage -> (structure)

Specific to model invocation and contains details about the usage of a foundation model.

inputTokens -> (integer)

Contains information about the input tokens from the foundation model usage.

outputTokens -> (integer)

Contains information about the output tokens from the foundation model usage.

knowledgeBaseLookupOutput -> (structure)

Contains details about the results from looking up the knowledge base.

retrievedReferences -> (list)

Contains metadata about the sources cited for the generated response.

(structure)

Contains metadata about a source cited for the generated response.

This data type is used in the following API operations:

RetrieveAndGenerate response – in the retrievedReferences field

InvokeAgent response – in the retrievedReferences field

content -> (structure)

Contains the cited text from the data source.

type -> (string)

The type of content in the retrieval result.

Possible values:

TEXT

IMAGE

ROW

text -> (string)

The cited text from the data source.

byteContent -> (string)

A data URI with base64-encoded content from the data source. The URI is in the following format: returned in the following format: data:image/jpeg;base64,${base64-encoded string} .

row -> (list)

Specifies information about the rows with the cells to return in retrieval.

(structure)

Contains information about a column with a cell to return in retrieval.

columnName -> (string)

The name of the column.

columnValue -> (string)

The value in the column.

type -> (string)

The data type of the value.

Possible values:

BLOB

BOOLEAN

DOUBLE

NULL

LONG

STRING

location -> (structure)

Contains information about the location of the data source.

type -> (string) [required]

The type of data source location.

Possible values:

S3

WEB

CONFLUENCE

SALESFORCE

SHAREPOINT

CUSTOM

KENDRA

SQL

s3Location -> (structure)

The S3 data source location.

uri -> (string)

The S3 URI for the data source location.

webLocation -> (structure)

The web URL/URLs data source location.

url -> (string)

The web URL/URLs for the data source location.

confluenceLocation -> (structure)

The Confluence data source location.

url -> (string)

The Confluence host URL for the data source location.

salesforceLocation -> (structure)

The Salesforce data source location.

url -> (string)

The Salesforce host URL for the data source location.

sharePointLocation -> (structure)

The SharePoint data source location.

url -> (string)

The SharePoint site URL for the data source location.

customDocumentLocation -> (structure)

Specifies the location of a document in a custom data source.

id -> (string)

The ID of the document.

kendraDocumentLocation -> (structure)

The location of a document in Amazon Kendra.

uri -> (string)

The document’s uri.

sqlLocation -> (structure)

Specifies information about the SQL query used to retrieve the result.

query -> (string)

The SQL query used to retrieve the result.

metadata -> (map)

Contains metadata attributes and their values for the file in the data source. For more information, see Metadata and filtering .

Constraints:

min: 1

key -> (string)

Constraints:

min: 1

max: 100

value -> (document)

metadata -> (structure)

Contains information about the knowledge base output.

startTime -> (timestamp)

In the final response, startTime is the start time of the agent invocation operation.

endTime -> (timestamp)

In the final response, endTime is the end time of the agent invocation operation.

totalTimeMs -> (long)

The total execution time for the specific invocation being processed (model, knowledge base, guardrail, agent collaborator, or code interpreter). It represents how long the individual invocation took.

operationTotalTimeMs -> (long)

The total time it took for the agent to complete execution. This field is only set for the final response.

clientRequestId -> (string)

A unique identifier associated with the downstream invocation. This ID can be used for tracing, debugging, and identifying specific invocations in customer logs or systems.

usage -> (structure)

Specific to model invocation and contains details about the usage of a foundation model.

inputTokens -> (integer)

Contains information about the input tokens from the foundation model usage.

outputTokens -> (integer)

Contains information about the output tokens from the foundation model usage.

finalResponse -> (structure)

Contains details about the response to the user.

text -> (string)

The text in the response to the user.

metadata -> (structure)

Contains information about the invoke agent operation.

startTime -> (timestamp)

In the final response, startTime is the start time of the agent invocation operation.

endTime -> (timestamp)

In the final response, endTime is the end time of the agent invocation operation.

totalTimeMs -> (long)

The total execution time for the specific invocation being processed (model, knowledge base, guardrail, agent collaborator, or code interpreter). It represents how long the individual invocation took.

operationTotalTimeMs -> (long)

The total time it took for the agent to complete execution. This field is only set for the final response.

clientRequestId -> (string)

A unique identifier associated with the downstream invocation. This ID can be used for tracing, debugging, and identifying specific invocations in customer logs or systems.

usage -> (structure)

Specific to model invocation and contains details about the usage of a foundation model.

inputTokens -> (integer)

Contains information about the input tokens from the foundation model usage.

outputTokens -> (integer)

Contains information about the output tokens from the foundation model usage.

repromptResponse -> (structure)

Contains details about the response to reprompt the input.

text -> (string)

The text reprompting the input.

source -> (string)

Specifies what output is prompting the agent to reprompt the input.

Possible values:

ACTION_GROUP

KNOWLEDGE_BASE

PARSER

codeInterpreterInvocationOutput -> (structure)

Contains the JSON-formatted string returned by the API invoked by the code interpreter.

executionOutput -> (string)

Contains the successful output returned from code execution

executionError -> (string)

Contains the error returned from code execution.

files -> (list)

Contains output files, if generated by code execution.

(string)

executionTimeout -> (boolean)

Indicates if the execution of the code timed out.

metadata -> (structure)

Contains information about the output from the code interpreter.

startTime -> (timestamp)

In the final response, startTime is the start time of the agent invocation operation.

endTime -> (timestamp)

In the final response, endTime is the end time of the agent invocation operation.

totalTimeMs -> (long)

The total execution time for the specific invocation being processed (model, knowledge base, guardrail, agent collaborator, or code interpreter). It represents how long the individual invocation took.

operationTotalTimeMs -> (long)

The total time it took for the agent to complete execution. This field is only set for the final response.

clientRequestId -> (string)

A unique identifier associated with the downstream invocation. This ID can be used for tracing, debugging, and identifying specific invocations in customer logs or systems.

usage -> (structure)

Specific to model invocation and contains details about the usage of a foundation model.

inputTokens -> (integer)

Contains information about the input tokens from the foundation model usage.

outputTokens -> (integer)

Contains information about the output tokens from the foundation model usage.

modelInvocationInput -> (structure)

The classifier’s model invocation input.

traceId -> (string)

The unique identifier of the trace.

Constraints:

min: 2

max: 16

text -> (string)

The text that prompted the agent at this step.

type -> (string)

The step in the agent sequence.

Possible values:

PRE_PROCESSING

ORCHESTRATION

KNOWLEDGE_BASE_RESPONSE_GENERATION

POST_PROCESSING

ROUTING_CLASSIFIER

overrideLambda -> (string)

The ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence.

promptCreationMode -> (string)

Specifies whether the default prompt template was OVERRIDDEN . If it was, the basePromptTemplate that was set in the PromptOverrideConfiguration object when the agent was created or updated is used instead.

Possible values:

DEFAULT

OVERRIDDEN

inferenceConfiguration -> (structure)

Specifications about the inference parameters that were provided alongside the prompt. These are specified in the PromptOverrideConfiguration object that was set when the agent was created or updated. For more information, see Inference parameters for foundation models .

temperature -> (float)

The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.

Constraints:

min: 0

max: 1

topP -> (float)

While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for Top P determines the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set topP to 0.8, the model only selects the next token from the top 80% of the probability distribution of next tokens.

Constraints:

min: 0

max: 1

topK -> (integer)

While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for topK is the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set topK to 50, the model selects the next token from among the top 50 most likely choices.

Constraints:

min: 0

max: 500

maximumLength -> (integer)

The maximum number of tokens allowed in the generated response.

Constraints:

min: 0

max: 8192

stopSequences -> (list)

A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.

Constraints:

min: 0

max: 4

(string)

parserMode -> (string)

Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the promptType .

Possible values:

DEFAULT

OVERRIDDEN

foundationModel -> (string)

The identifier of a foundation model.

Constraints:

min: 1

max: 2048

pattern: .*(^arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:(([0-9]{12}:custom-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}(([:][a-z0-9-]{1,63}){0,2})?/[a-z0-9]{12})|(:foundation-model/([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.]?[a-z0-9-]{1,63})([:][a-z0-9-]{1,63}){0,2})))|(([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.]?[a-z0-9-]{1,63})([:][a-z0-9-]{1,63}){0,2}))|(([0-9a-zA-Z][_-]?)+))$|(^arn:aws(|-us-gov|-cn|-iso|-iso-b):bedrock:(|[0-9a-z-]{1,20}):(|[0-9]{12}):inference-profile/[a-zA-Z0-9-:.]+)

modelInvocationOutput -> (structure)

The classifier’s model invocation output.

traceId -> (string)

The invocation’s trace ID.

Constraints:

min: 2

max: 16

rawResponse -> (structure)

The invocation’s raw response.

content -> (string)

The foundation model’s raw output content.

metadata -> (structure)

The invocation’s metadata.

startTime -> (timestamp)

In the final response, startTime is the start time of the agent invocation operation.

endTime -> (timestamp)

In the final response, endTime is the end time of the agent invocation operation.

totalTimeMs -> (long)

The total execution time for the specific invocation being processed (model, knowledge base, guardrail, agent collaborator, or code interpreter). It represents how long the individual invocation took.

operationTotalTimeMs -> (long)

The total time it took for the agent to complete execution. This field is only set for the final response.

clientRequestId -> (string)

A unique identifier associated with the downstream invocation. This ID can be used for tracing, debugging, and identifying specific invocations in customer logs or systems.

usage -> (structure)

Specific to model invocation and contains details about the usage of a foundation model.

inputTokens -> (integer)

Contains information about the input tokens from the foundation model usage.

outputTokens -> (integer)

Contains information about the output tokens from the foundation model usage.

failureTrace -> (structure)

Contains information about the failure of the interaction.

traceId -> (string)

The unique identifier of the trace.

Constraints:

min: 2

max: 16

failureReason -> (string)

The reason the interaction failed.

failureCode -> (integer)

The failure code for the trace.

metadata -> (structure)

Information about the failure that occurred.

startTime -> (timestamp)

In the final response, startTime is the start time of the agent invocation operation.

endTime -> (timestamp)

In the final response, endTime is the end time of the agent invocation operation.

totalTimeMs -> (long)

The total execution time for the specific invocation being processed (model, knowledge base, guardrail, agent collaborator, or code interpreter). It represents how long the individual invocation took.

operationTotalTimeMs -> (long)

The total time it took for the agent to complete execution. This field is only set for the final response.

clientRequestId -> (string)

A unique identifier associated with the downstream invocation. This ID can be used for tracing, debugging, and identifying specific invocations in customer logs or systems.

usage -> (structure)

Specific to model invocation and contains details about the usage of a foundation model.

inputTokens -> (integer)

Contains information about the input tokens from the foundation model usage.

outputTokens -> (integer)

Contains information about the output tokens from the foundation model usage.

customOrchestrationTrace -> (structure)

Details about the custom orchestration step in which the agent determines the order in which actions are executed.

traceId -> (string)

The unique identifier of the trace.

Constraints:

min: 2

max: 16

event -> (structure)

The event details used with the custom orchestration.

text -> (string)

The text that prompted the event at this step.

callerChain -> (list)

The part’s caller chain.

(tagged union structure)

Details about a caller.

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: agentAliasArn.

agentAliasArn -> (string)

The caller’s agent alias ARN.

Constraints:

min: 0

max: 2048

pattern: arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:agent-alias/[0-9a-zA-Z]{10}/[0-9a-zA-Z]{10}

eventTime -> (timestamp)

The time of the trace.

collaboratorName -> (string)

The part’s collaborator name.

Constraints:

pattern: ([0-9a-zA-Z][_-]?){1,100}

agentId -> (string)

The unique identifier of the agent.

Constraints:

min: 0

max: 10

pattern: [0-9a-zA-Z]+

agentAliasId -> (string)

The unique identifier of the alias of the agent.

Constraints:

min: 0

max: 10

pattern: [0-9a-zA-Z]+

agentVersion -> (string)

The version of the agent.

Constraints:

min: 1

max: 5

pattern: (DRAFT|[0-9]{0,4}[1-9][0-9]{0,4})

nextToken -> (string)

A token to retrieve the next set of results. This value is returned if more results are available.

Constraints:

min: 1

max: 2048

pattern: \S*

Table of Contents

Feedback

User Guide

list-flow-execution-events¶

Description¶

Note

Synopsis¶

Options¶

Global Options¶

Output¶

Note

Note

Note

Note

Note

Note

Note

Note

Note

Note

Note

Note

Note

Note

Note

Note

Note

Note

Note

Note

Note

Note

Note

Note

Note

Note

Note

Note