Agents for Amazon Bedrock Update: Features: Add inline code node to prompt flow

Author: AWS

.attach_pid890

@@ -0,0 +1,6 @@
+{
+    "type": "feature",
+    "category": "Agents for Amazon Bedrock",
+    "contributor": "",
+    "description": "Features: Add inline code node to prompt flow"
+}

.changes/next-release/feature-AgentsforAmazonBedrock-cc4fd29.json

@@ -1686,7 +1686,7 @@
         },
         "parentActionGroupSignatureParams":{
           "shape":"ActionGroupSignatureParams",
-          "documentation":"<p>The configuration settings for a computer use action.</p> <important> <p> Computer use is a new Anthropic Claude model capability (in beta) available with Claude 3.7 Sonnet and Claude 3.5 Sonnet v2 only. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/agent-computer-use.html\">Configure an Amazon Bedrock Agent to complete tasks with computer use tools</a>. </p> </important>"
+          "documentation":"<p>The configuration settings for a computer use action.</p> <important> <p> Computer use is a new Anthropic Claude model capability (in beta) available with Claude 3.7 Sonnet and Claude 3.5 Sonnet v2 only. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/agents-computer-use.html\">Configure an Amazon Bedrock Agent to complete tasks with computer use tools</a>. </p> </important>"
         },
         "parentActionSignature":{
           "shape":"ActionGroupSignature",
@@ -2854,11 +2854,11 @@
         },
         "parentActionGroupSignature":{
           "shape":"ActionGroupSignature",
-          "documentation":"<p>Specify a built-in or computer use action for this action group. If you specify a value, you must leave the <code>description</code>, <code>apiSchema</code>, and <code>actionGroupExecutor</code> fields empty for this action group. </p> <ul> <li> <p>To allow your agent to request the user for additional information when trying to complete a task, set this field to <code>AMAZON.UserInput</code>. </p> </li> <li> <p>To allow your agent to generate, run, and troubleshoot code when trying to complete a task, set this field to <code>AMAZON.CodeInterpreter</code>.</p> </li> <li> <p>To allow your agent to use an Anthropic computer use tool, specify one of the following values. </p> <important> <p> Computer use is a new Anthropic Claude model capability (in beta) available with Anthropic Claude 3.7 Sonnet and Claude 3.5 Sonnet v2 only. When operating computer use functionality, we recommend taking additional security precautions, such as executing computer actions in virtual environments with restricted data access and limited internet connectivity. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/agent-computer-use.html\">Configure an Amazon Bedrock Agent to complete tasks with computer use tools</a>. </p> </important> <ul> <li> <p> <code>ANTHROPIC.Computer</code> - Gives the agent permission to use the mouse and keyboard and take screenshots.</p> </li> <li> <p> <code>ANTHROPIC.TextEditor</code> - Gives the agent permission to view, create and edit files.</p> </li> <li> <p> <code>ANTHROPIC.Bash</code> - Gives the agent permission to run commands in a bash shell.</p> </li> </ul> </li> </ul>"
+          "documentation":"<p>Specify a built-in or computer use action for this action group. If you specify a value, you must leave the <code>description</code>, <code>apiSchema</code>, and <code>actionGroupExecutor</code> fields empty for this action group. </p> <ul> <li> <p>To allow your agent to request the user for additional information when trying to complete a task, set this field to <code>AMAZON.UserInput</code>. </p> </li> <li> <p>To allow your agent to generate, run, and troubleshoot code when trying to complete a task, set this field to <code>AMAZON.CodeInterpreter</code>.</p> </li> <li> <p>To allow your agent to use an Anthropic computer use tool, specify one of the following values. </p> <important> <p> Computer use is a new Anthropic Claude model capability (in beta) available with Anthropic Claude 3.7 Sonnet and Claude 3.5 Sonnet v2 only. When operating computer use functionality, we recommend taking additional security precautions, such as executing computer actions in virtual environments with restricted data access and limited internet connectivity. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/agents-computer-use.html\">Configure an Amazon Bedrock Agent to complete tasks with computer use tools</a>. </p> </important> <ul> <li> <p> <code>ANTHROPIC.Computer</code> - Gives the agent permission to use the mouse and keyboard and take screenshots.</p> </li> <li> <p> <code>ANTHROPIC.TextEditor</code> - Gives the agent permission to view, create and edit files.</p> </li> <li> <p> <code>ANTHROPIC.Bash</code> - Gives the agent permission to run commands in a bash shell.</p> </li> </ul> </li> </ul>"
         },
         "parentActionGroupSignatureParams":{
           "shape":"ActionGroupSignatureParams",
-          "documentation":"<p>The configuration settings for a computer use action.</p> <important> <p> Computer use is a new Anthropic Claude model capability (in beta) available with Anthropic Claude 3.7 Sonnet and Claude 3.5 Sonnet v2 only. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/agent-computer-use.html\">Configure an Amazon Bedrock Agent to complete tasks with computer use tools</a>. </p> </important>"
+          "documentation":"<p>The configuration settings for a computer use action.</p> <important> <p> Computer use is a new Anthropic Claude model capability (in beta) available with Anthropic Claude 3.7 Sonnet and Claude 3.5 Sonnet v2 only. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/agents-computer-use.html\">Configure an Amazon Bedrock Agent to complete tasks with computer use tools</a>. </p> </important>"
         }
       }
     },
@@ -4865,7 +4865,11 @@
         },
         "condition":{
           "shape":"ConditionFlowNodeConfiguration",
-          "documentation":"<p>Contains configurations for a Condition node in your flow. Defines conditions that lead to different branches of the flow.</p>"
+          "documentation":"<p>Contains configurations for a condition node in your flow. Defines conditions that lead to different branches of the flow.</p>"
+        },
+        "inlineCode":{
+          "shape":"InlineCodeFlowNodeConfiguration",
+          "documentation":"<p>Contains configurations for an inline code node in your flow. Inline code nodes let you write and execute code directly within your flow, enabling data transformations, custom logic, and integrations without needing an external Lambda function.</p>"
         },
         "input":{
           "shape":"InputFlowNodeConfiguration",
@@ -4897,11 +4901,11 @@
         },
         "retrieval":{
           "shape":"RetrievalFlowNodeConfiguration",
-          "documentation":"<p>Contains configurations for a Retrieval node in your flow. Retrieves data from an Amazon S3 location and returns it as the output.</p>"
+          "documentation":"<p>Contains configurations for a retrieval node in your flow. Retrieves data from an Amazon S3 location and returns it as the output.</p>"
         },
         "storage":{
           "shape":"StorageFlowNodeConfiguration",
-          "documentation":"<p>Contains configurations for a Storage node in your flow. Stores an input in an Amazon S3 location.</p>"
+          "documentation":"<p>Contains configurations for a storage node in your flow. Stores an input in an Amazon S3 location.</p>"
         }
       },
       "documentation":"<p>Contains configurations for a node in your flow. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/flows-nodes.html\">Node types in Amazon Bedrock works</a> in the Amazon Bedrock User Guide.</p>",
@@ -5002,7 +5006,8 @@
         "Agent",
         "Retrieval",
         "Iterator",
-        "Collector"
+        "Collector",
+        "InlineCode"
       ]
     },
     "FlowNodes":{
@@ -6078,7 +6083,7 @@
         },
         "topP":{
           "shape":"TopP",
-          "documentation":"<p>While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for <code>Top P</code> determines the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set <code>topP</code> to 80, the model only selects the next token from the top 80% of the probability distribution of next tokens.</p>"
+          "documentation":"<p>While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for <code>Top P</code> determines the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set <code>topP</code> to 0.8, the model only selects the next token from the top 80% of the probability distribution of next tokens.</p>"
         }
       },
       "documentation":"<p>Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the <code>promptType</code>. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html\">Inference parameters for foundation models</a>.</p>"
@@ -6342,6 +6347,30 @@
       },
       "documentation":"<p>Contains details about a data ingestion job.</p>"
     },
+    "InlineCode":{
+      "type":"string",
+      "max":5000000,
+      "min":1,
+      "sensitive":true
+    },
+    "InlineCodeFlowNodeConfiguration":{
+      "type":"structure",
+      "required":[
+        "code",
+        "language"
+      ],
+      "members":{
+        "code":{
+          "shape":"InlineCode",
+          "documentation":"<p>The code that's executed in your inline code node. The code can access input data from previous nodes in the flow, perform operations on that data, and produce output that can be used by other nodes in your flow.</p> <p>The code must be valid in the programming <code>language</code> that you specify.</p>"
+        },
+        "language":{
+          "shape":"SupportedLanguages",
+          "documentation":"<p>The programming language used by your inline code node.</p> <p>The code must be valid in the programming <code>language</code> that you specify. Currently, only Python 3 (<code>Python_3</code>) is supported.</p>"
+        }
+      },
+      "documentation":"<p>Contains configurations for an inline code node in your flow. Inline code nodes let you write and execute code directly within your flow, enabling data transformations, custom logic, and integrations without needing an external Lambda function.</p>"
+    },
     "InlineContent":{
       "type":"structure",
       "required":["type"],
@@ -8222,7 +8251,7 @@
         },
         "promptState":{
           "shape":"PromptState",
-          "documentation":"<p>Specifies whether to allow the agent to carry out the step specified in the <code>promptType</code>. If you set this value to <code>DISABLED</code>, the agent skips that step. The default state for each <code>promptType</code> is as follows.</p> <ul> <li> <p> <code>PRE_PROCESSING</code> – <code>ENABLED</code> </p> </li> <li> <p> <code>ORCHESTRATION</code> – <code>ENABLED</code> </p> </li> <li> <p> <code>KNOWLEDGE_BASE_RESPONSE_GENERATION</code> – <code>ENABLED</code> </p> </li> <li> <p> <code>POST_PROCESSING</code> – <code>DISABLED</code> </p> </li> </ul>"
+          "documentation":"<p>Specifies whether to allow the agent to carry out the step specified in the <code>promptType</code>. If you set this value to <code>DISABLED</code>, the agent skips that step. The default state for each <code>promptType</code> is as follows.</p> <ul> <li> <p> <code>PRE_PROCESSING</code> – <code>DISABLED</code> </p> </li> <li> <p> <code>ORCHESTRATION</code> – <code>ENABLED</code> </p> </li> <li> <p> <code>KNOWLEDGE_BASE_RESPONSE_GENERATION</code> – <code>ENABLED</code> </p> </li> <li> <p> <code>POST_PROCESSING</code> – <code>DISABLED</code> </p> </li> </ul>"
         },
         "promptType":{
           "shape":"PromptType",
@@ -9357,7 +9386,7 @@
     "SessionTTL":{
       "type":"integer",
       "box":true,
-      "max":3600,
+      "max":5400,
       "min":60
     },
     "SharePointAuthType":{
@@ -9691,6 +9720,10 @@
       "max":1,
       "min":1
     },
+    "SupportedLanguages":{
+      "type":"string",
+      "enum":["Python_3"]
+    },
     "SystemContentBlock":{
       "type":"structure",
       "members":{
@@ -10197,11 +10230,11 @@
         },
         "parentActionGroupSignature":{
           "shape":"ActionGroupSignature",
-          "documentation":"<p>Update the built-in or computer use action for this action group. If you specify a value, you must leave the <code>description</code>, <code>apiSchema</code>, and <code>actionGroupExecutor</code> fields empty for this action group. </p> <ul> <li> <p>To allow your agent to request the user for additional information when trying to complete a task, set this field to <code>AMAZON.UserInput</code>. </p> </li> <li> <p>To allow your agent to generate, run, and troubleshoot code when trying to complete a task, set this field to <code>AMAZON.CodeInterpreter</code>.</p> </li> <li> <p>To allow your agent to use an Anthropic computer use tool, specify one of the following values. </p> <important> <p> Computer use is a new Anthropic Claude model capability (in beta) available with Anthropic Claude 3.7 Sonnet and Claude 3.5 Sonnet v2 only. When operating computer use functionality, we recommend taking additional security precautions, such as executing computer actions in virtual environments with restricted data access and limited internet connectivity. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/agent-computer-use.html\">Configure an Amazon Bedrock Agent to complete tasks with computer use tools</a>. </p> </important> <ul> <li> <p> <code>ANTHROPIC.Computer</code> - Gives the agent permission to use the mouse and keyboard and take screenshots.</p> </li> <li> <p> <code>ANTHROPIC.TextEditor</code> - Gives the agent permission to view, create and edit files.</p> </li> <li> <p> <code>ANTHROPIC.Bash</code> - Gives the agent permission to run commands in a bash shell.</p> </li> </ul> </li> </ul> <p>During orchestration, if your agent determines that it needs to invoke an API in an action group, but doesn't have enough information to complete the API request, it will invoke this action group instead and return an <a href=\"https://docs.aws.amazon.com/bedrock/latest/APIReference/API_agent-runtime_Observation.html\">Observation</a> reprompting the user for more information.</p>"
+          "documentation":"<p>Update the built-in or computer use action for this action group. If you specify a value, you must leave the <code>description</code>, <code>apiSchema</code>, and <code>actionGroupExecutor</code> fields empty for this action group. </p> <ul> <li> <p>To allow your agent to request the user for additional information when trying to complete a task, set this field to <code>AMAZON.UserInput</code>. </p> </li> <li> <p>To allow your agent to generate, run, and troubleshoot code when trying to complete a task, set this field to <code>AMAZON.CodeInterpreter</code>.</p> </li> <li> <p>To allow your agent to use an Anthropic computer use tool, specify one of the following values. </p> <important> <p> Computer use is a new Anthropic Claude model capability (in beta) available with Anthropic Claude 3.7 Sonnet and Claude 3.5 Sonnet v2 only. When operating computer use functionality, we recommend taking additional security precautions, such as executing computer actions in virtual environments with restricted data access and limited internet connectivity. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/agents-computer-use.html\">Configure an Amazon Bedrock Agent to complete tasks with computer use tools</a>. </p> </important> <ul> <li> <p> <code>ANTHROPIC.Computer</code> - Gives the agent permission to use the mouse and keyboard and take screenshots.</p> </li> <li> <p> <code>ANTHROPIC.TextEditor</code> - Gives the agent permission to view, create and edit files.</p> </li> <li> <p> <code>ANTHROPIC.Bash</code> - Gives the agent permission to run commands in a bash shell.</p> </li> </ul> </li> </ul> <p>During orchestration, if your agent determines that it needs to invoke an API in an action group, but doesn't have enough information to complete the API request, it will invoke this action group instead and return an <a href=\"https://docs.aws.amazon.com/bedrock/latest/APIReference/API_agent-runtime_Observation.html\">Observation</a> reprompting the user for more information.</p>"
         },
         "parentActionGroupSignatureParams":{
           "shape":"ActionGroupSignatureParams",
-          "documentation":"<p>The configuration settings for a computer use action.</p> <important> <p> Computer use is a new Anthropic Claude model capability (in beta) available with Claude 3.7 Sonnet and Claude 3.5 Sonnet v2 only. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/agent-computer-use.html\">Configure an Amazon Bedrock Agent to complete tasks with computer use tools</a>. </p> </important>"
+          "documentation":"<p>The configuration settings for a computer use action.</p> <important> <p> Computer use is a new Anthropic Claude model capability (in beta) available with Claude 3.7 Sonnet and Claude 3.5 Sonnet v2 only. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/agents-computer-use.html\">Configure an Amazon Bedrock Agent to complete tasks with computer use tools</a>. </p> </important>"
         }
       }
     },