W-21433121 agent network 2.0 content ie#660
Open
IsaacEldridge wants to merge 35 commits into
Open
Conversation
…nent Split the af-* pages into a new agent-network Antora component with 1.0 and 2.0 versions so 2.0 can evolve independently while 1.0 stays frozen. Add page-aliases on 2.0 to redirect existing anypoint-code-builder::af-* URLs to the latest version. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…eferences. Update navigation to include new references and clarify deployment target requirements for CloudHub 2.0. Adjust language for consistency across documentation.
- Introduced a new page detailing the process of building an IT Investigation Broker using MuleSoft Vibes, including phases from input requirements to final topology review. - Updated navigation to include a reference to the new example page. - Added a new workflow diagram image for the IT Investigation Broker. - Updated the existing agent fabric architecture image.
…JSON formatting - Updated the navigation to correct the reference to the IT Investigation Broker example. - Reformatted the JSON structure in the af-example-it-investigation-broker.adoc for improved readability and clarity. - Organized the project structure section for better visual representation.
- Introduced new partial documentation for creating agent networks, including prerequisites, platform requirements, and task overviews. - Detailed steps for setting up agent networks, creating projects, defining specifications, publishing assets, and deploying instances. - Ensured consistency in language and structure across both versions to facilitate user understanding.
…nd default URLs for OpenAI and Gemini. Added references for better clarity and user guidance.
…`on_exit` property across various node types, specifying that if `on_exit` is not defined, the graph ends when the agentic node loop concludes, and that only `transition_to` statements are permitted in the procedure.
…delines for publishing project assets. Added a note on using version groups instead of semantic versions to prevent unintended major upgrades. Enhanced language for consistency and clarity in the publishing process using MuleSoft Vibes and Anypoint Code Builder.
…-reference.adoc, specifying that if `on_exit` is not defined, the graph ends when the agentic node or executor ends, rather than when the node loop concludes. This update enhances the accuracy of the documentation regarding node execution behavior.
… configurations. Changed specific mention of `broker1.agent` files to `.agent` files for clarity and consistency in documentation regarding multi-agent orchestration.
…ructions for project asset publishing. Clarified that Exchange automatically increments the version upon changes, enhancing the documentation's clarity and accuracy regarding version group usage.
…configuration instructions. Updated descriptions for using MuleSoft Vibes and Anypoint Code Builder, clarified file structures, and improved prompt examples for better user guidance. Added notes on utilizing the visual canvas alongside code editing for effective network management.
…, capabilities, and transport types. Updated sections on project creation, asset management, and deployment processes in Anypoint Code Builder for improved clarity and user guidance.
…ructure, replacing references from `/agent-script` to `/brokers` for improved clarity in navigating broker configurations.
…ference.adoc by specifying the use of authorization headers in OBO authentication scenarios, enhancing the understanding of custom header requirements for external system connections.
…Network version from a quoted string to a numeric value for improved clarity and consistency.
… instructions and correct A2A protocol version from 0.3.0 to 1.0.0, enhancing clarity and accuracy in troubleshooting guidance.
…on.adoc that was wrapping the rest of the page in an example block, causing all subsequent headings to render as literal AsciiDoc syntax.
…affic, and data by the Omni Gateway in shared and private space configurations.
…diagram. Update documentation to reflect changes in architecture and clarify Omni Gateway usage in shared and private space configurations.
…jects. Clarify the process for referencing assets from different business groups and provide a complete example of `exchange.json` and `agent-network.yaml` configurations to improve user understanding.
…exchange-dependencies-to-agent-network-file-ie W-22730742 example adding exchange asset
…structions for enabling logging in CloudHub 2.0 and Runtime Fabric. Include important notes on the use of `INSECURE-LOGGING` to ensure user awareness of potential sensitive information exposure during debugging.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…w sections on common issues and errors, including deployment problems, registry key conflicts, and broker response behaviors. Provide detailed resolutions and best practices to improve user understanding and troubleshooting efficiency.
… gateway:: component Applies the W-22727519 fix to the versioned 1.0 and 2.0 copies of af-agent-networks.adoc, since the original file was relocated on this branch and would otherwise drop the upstream xref correction.
…twork-2.0-content-ie
valkyrie69
reviewed
Jun 15, 2026
| [[agent-network-2-0-yaml-reference]] | ||
| = Agent Network (2.0) YAML Reference | ||
|
|
||
| The agent-network.yaml details the required structure and properties that define your project's assets, connections, and policies. |
Contributor
There was a problem hiding this comment.
Suggested change
| The agent-network.yaml details the required structure and properties that define your project's assets, connections, and policies. | |
| The `agent-network.yaml` details the required structure and properties that define your project's assets, connections, and policies. |
| [[agent-network-section]] | ||
| == Agent Network Section | ||
|
|
||
| This is the root section of the agent network. Must include at least one of `registry`, `context`, or `brokers` must be present. |
Contributor
There was a problem hiding this comment.
Suggested change
| This is the root section of the agent network. Must include at least one of `registry`, `context`, or `brokers` must be present. | |
| This is the root section of the agent network. Must include at least one of `registry`, `context`, or `brokers`. |
valkyrie69
reviewed
Jun 15, 2026
| Brokers in Agent Network 2.0 architecture leverage a hybrid deterministic approach by separating steps requiring probabilistic LLM reasoning from those requiring deterministic control-flow logic. | ||
|
|
||
| * Probabilistic (LLM-based) nodes handle complex, open-ended decisions that require nuanced judgment, such as classification or AI-powered thinking. | ||
| * Deterministic nodes manage all remaining predefined execution paths, ensuring a fixed and guaranteed workflow once a key probabilistic judgment has been finalized. |
Contributor
There was a problem hiding this comment.
Suggested change
| * Deterministic nodes manage all remaining predefined execution paths, ensuring a fixed and guaranteed workflow once a key probabilistic judgment has been finalized. | |
| * Deterministic nodes manage all remaining predefined execution paths, ensuring a fixed and guaranteed workflow after a key probabilistic judgment has been finalized. |
| [[agent-network-components]] | ||
| == Agent Network Components | ||
|
|
||
| An agent network is a collection of agents, brokers, LLMs, and MCP servers that are connected to each other. Agent networks use LLMs for reasoning and planning capabilities and integrate with Anypoint Connector for MCP (Model Context Protocol) and Anypoint Connector for Agent2Agent (A2A) communication. |
Contributor
There was a problem hiding this comment.
This first line is a repeat of the intro. You could probably delete it.
| Transitions from node to node. Input data enters the node and output data exits the node. | ||
|
|
||
| Agent:: | ||
| An autonomous software component that uses goals, context, and available tools, often via a large language model (LLM), to decide and execute actions on behalf of a user or system. |
Contributor
There was a problem hiding this comment.
Suggested change
| An autonomous software component that uses goals, context, and available tools, often via a large language model (LLM), to decide and execute actions on behalf of a user or system. | |
| An autonomous software component that uses goals, context, and available tools, often via a LLM, to decide and execute actions on behalf of a user or system. |
Contributor
There was a problem hiding this comment.
Salesforce style has that as an acronym we don't spell out.
…s' instead of 'protocol' and 'card'. Update agent definitions for hr-system-agent and salesforce-agent to include versioning and capabilities. Enhance documentation for agent properties and connection policies.
valkyrie69
reviewed
Jun 15, 2026
|
|
||
| You define your agent network in a simple, human-readable YAML file in Anypoint Code Builder. This approach abstracts away the underlying technical complexities, allowing you to focus on the business constraints and context of your process without needing to understand the inner workings of the orchestration engine. | ||
|
|
||
| At the start of a new agent network project, we provide a YAML template and Agent Script file to give you a head start. You can use MuleSoft Vibes to configure your network, publish the assets to Anypoint Exchange, and deploy your agent network instance. |
Contributor
There was a problem hiding this comment.
Suggested change
| At the start of a new agent network project, we provide a YAML template and Agent Script file to give you a head start. You can use MuleSoft Vibes to configure your network, publish the assets to Anypoint Exchange, and deploy your agent network instance. | |
| At the start of a new agent network project, MuleSoft provides a YAML template and Agent Script file to give you a head start. You can use MuleSoft Vibes to configure your network, publish the assets to Anypoint Exchange, and deploy your agent network instance. |
| [[hybrid-determinism]] | ||
| == The Hybrid Determinism Pattern | ||
|
|
||
| Brokers in Agent Network 2.0 architecture leverage a hybrid deterministic approach by separating steps requiring probabilistic LLM reasoning from those requiring deterministic control-flow logic. |
Contributor
There was a problem hiding this comment.
Suggested change
| Brokers in Agent Network 2.0 architecture leverage a hybrid deterministic approach by separating steps requiring probabilistic LLM reasoning from those requiring deterministic control-flow logic. | |
| Brokers in Agent Network 2.0 architecture use a hybrid deterministic approach by separating steps requiring probabilistic LLM reasoning from those requiring deterministic control-flow logic. |
Contributor
There was a problem hiding this comment.
Are we capitalizing agent network? I think Melissa decided not to but if you decided differently, that's fine with me. Just checking.
| Broker:: | ||
| An intelligent routing service that coordinates task delegation across A2A-compliant agents in your enterprise. | ||
| You define a broker and its nodes in Agent Script. | ||
| Nodes are connected in a graph that encapsulates all steps that describe the orchestration of agents, tools, and large language models. |
Contributor
There was a problem hiding this comment.
Suggested change
| Nodes are connected in a graph that encapsulates all steps that describe the orchestration of agents, tools, and large language models. | |
| Nodes are connected in a graph that encapsulates all steps that describe the orchestration of agents, tools, and LLMs. |
| [[agent-network-architecture]] | ||
| == Agent Network Architecture | ||
|
|
||
| This diagram shows an agent network deployed to a shared space in CloudHub 2 using a single mni Gateway for ingress and egress. The network includes agents and MCP servers and is observed in Anypoint Monitoring. |
Contributor
There was a problem hiding this comment.
Suggested change
| This diagram shows an agent network deployed to a shared space in CloudHub 2 using a single mni Gateway for ingress and egress. The network includes agents and MCP servers and is observed in Anypoint Monitoring. | |
| This diagram shows an agent network deployed to a shared space in CloudHub 2.0 using a single Omni Gateway for ingress and egress. The network includes agents and MCP servers and is observed in Anypoint Monitoring. |
| [[exchange-assets]] | ||
| == Agent Network Assets in Anypoint Exchange | ||
|
|
||
| The following agent network asset types are supported in Exchange: |
Contributor
There was a problem hiding this comment.
Suggested change
| The following agent network asset types are supported in Exchange: | |
| Agent network projects support these asset types in Exchange: |
|
|
||
| In a multi-agent network, a client sends a request to Broker_1 and Broker_1 generates the necessary IDs for that request. When Broker_1 sends a new request to the next broker or non-broker agent in line, that broker or non-broker agent establishes a unique `contextId` and `taskId` for the new request. | ||
|
|
||
| NOTE: It is not mandatory for non-broker agents to generate a `contextId` and `taskId` when receiving requests from a client. |
Contributor
There was a problem hiding this comment.
Suggested change
| NOTE: It is not mandatory for non-broker agents to generate a `contextId` and `taskId` when receiving requests from a client. | |
| NOTE: Non-broker agents don't have to generate a `contextId` and `taskId` when receiving requests from a client. |
|
|
||
| == See Also | ||
|
|
||
| * xref:af-get-started.adoc[] |
Contributor
There was a problem hiding this comment.
Add more links to See Also?
- xref:af-create-agent-network.adoc[]
- xref:af-project-files.adoc[]
- xref:af-agent-script-reference.adoc[]
Maybe add a link to https://docs.mulesoft.com/general/agent-fabric-overview?
valkyrie69
reviewed
Jun 15, 2026
|
|
||
| === System Section | ||
|
|
||
| This section defines the `instructions` attribute, which acts as a default system prompt that will be used whenever an agentic node doesn't define a `system.instructions` of its own. |
Contributor
There was a problem hiding this comment.
Suggested change
| This section defines the `instructions` attribute, which acts as a default system prompt that will be used whenever an agentic node doesn't define a `system.instructions` of its own. | |
| This section defines the `instructions` attribute, which acts as a default system prompt used whenever an agentic node doesn't define its own `system.instructions`. |
| |Yes | ||
|
|
||
| |`reasoning_effort` | ||
| |Constrains effort on reasoning for reasoning models. gpt-5.1 defaults to NONE, previous ones default to MEDIUM |
Contributor
There was a problem hiding this comment.
Suggested change
| |Constrains effort on reasoning for reasoning models. gpt-5.1 defaults to NONE, previous ones default to MEDIUM | |
| |Constrains effort on reasoning for reasoning models. GPT-5.2 defaults to `NONE`; earlier models default to `MEDIUM`. |
| |Yes | ||
|
|
||
| |`kind` | ||
| |Constant indicating this will invoke an MCP tool |
Contributor
There was a problem hiding this comment.
Suggested change
| |Constant indicating this will invoke an MCP tool | |
| |Constant indicating that this invokes an MCP tool |
|
|
||
| === Router Node | ||
|
|
||
| The router node performs dynamic transitions based on deterministic conditions. This node does not support transition to in its on_exit attribute. Use this node for branching based on structured output from a previous node. |
Contributor
There was a problem hiding this comment.
Suggested change
| The router node performs dynamic transitions based on deterministic conditions. This node does not support transition to in its on_exit attribute. Use this node for branching based on structured output from a previous node. | |
| The router node performs dynamic transitions based on deterministic conditions. This node doesn't support `transition to` in its `on_exit` attribute. Use this node for branching based on structured output from a previous node. |
|
|
||
| === Echo Node | ||
|
|
||
| The echo node sends a response back to the client. The number of responses depends on the trigger interface and its configuration. Use this node for the end of a workflow, or anytime you want to emit a response. Currently only supports `a2a:response` (non-streaming). |
Contributor
There was a problem hiding this comment.
Suggested change
| The echo node sends a response back to the client. The number of responses depends on the trigger interface and its configuration. Use this node for the end of a workflow, or anytime you want to emit a response. Currently only supports `a2a:response` (non-streaming). | |
| The echo node sends a response back to the client. The number of responses depends on the trigger interface and its configuration. Use this node for the end of a workflow, or anytime you want to emit a response. Agent networks currently support `a2a:response` (non-streaming) only. |
| [[a2a-namespace-functions]] | ||
| == A2A Namespace Functions | ||
|
|
||
| The `a2a` namespace provides a set of functions that support A2A Task object creation. Do not prefix these functions with `@` as it's reserved for references such as `@variables`, `@actions`, `@request`, and `@orchestrator.<nodeId>`. |
Contributor
There was a problem hiding this comment.
Suggested change
| The `a2a` namespace provides a set of functions that support A2A Task object creation. Do not prefix these functions with `@` as it's reserved for references such as `@variables`, `@actions`, `@request`, and `@orchestrator.<nodeId>`. | |
| The `a2a` namespace provides a set of functions that support A2A Task object creation. Do not prefix these functions with `@` as it's reserved for references such as `@variables`, `@actions`, `@request`, and `@orchestrator.<nodeId>`. |
|
|
||
| Use the `outputs` field to define the expected shape of the agent's response using a schema notation similar to a JSON schema. When provided, the agent produces output matching the defined structure for downstream parsing and processing. | ||
|
|
||
| Each property maps to a field in the agent's output. The following types are supported. |
Contributor
There was a problem hiding this comment.
Suggested change
| Each property maps to a field in the agent's output. The following types are supported. | |
| Each property maps to a field in the agent's output. These types are supported. |
| * `description`: A human-readable explanation of the property's purpose. | ||
| * `default`: A default value if the property is omitted. | ||
|
|
||
| The `outputs` definition does not support the following: |
Contributor
There was a problem hiding this comment.
Suggested change
| The `outputs` definition does not support the following: | |
| The `outputs` definition doesn't support: |
|
|
||
| Nodes access data from other parts of the workflow using expressions. | ||
|
|
||
| The following references are used. |
Contributor
There was a problem hiding this comment.
Suggested change
| The following references are used. | |
| These references are used. |
valkyrie69
reviewed
Jun 15, 2026
|
|
||
| Install the Anypoint CLI Agent Fabric plugin by running this command in a terminal window: | ||
|
|
||
| `npm i mulesoft-anypoint-cli-agent-fabric-plugin` |
Contributor
There was a problem hiding this comment.
Suggested change
| `npm i mulesoft-anypoint-cli-agent-fabric-plugin` | |
| [source,shell] | |
| ---- | |
| npm install mulesoft-anypoint-cli-agent-fabric-plugin | |
| ---- |
|
|
||
| You can authenticate to Anypoint Platform through the command line by running the `anypoint-cli-agent-fabric-plugin` command with a combination of parameters. | ||
|
|
||
| Or, you can set a combination of environment variables before running the `anypoint-cli-agent-fabric-plugin` command. For more information, see link:https://docs.mulesoft.com/anypoint-cli/latest/auth#command-line-parameters[Command-Line Parameters and Environment Variables]. |
Contributor
There was a problem hiding this comment.
Suggested change
| Or, you can set a combination of environment variables before running the `anypoint-cli-agent-fabric-plugin` command. For more information, see link:https://docs.mulesoft.com/anypoint-cli/latest/auth#command-line-parameters[Command-Line Parameters and Environment Variables]. | |
| Or, you can set a combination of environment variables before running the `anypoint-cli-agent-fabric-plugin` command. For more information, see https://docs.mulesoft.com/anypoint-cli/latest/auth#command-line-parameters[Command-Line Parameters and Environment Variables]. |
|
|
||
| include::anypoint-cli::partial$agent-fabric.adoc[tag=summary] | ||
|
|
||
| include::anypoint-cli::partial$agent-fabric.adoc[tag=commands] |
Contributor
There was a problem hiding this comment.
Add a "See Also" section?
valkyrie69
reviewed
Jun 15, 2026
| = Create Agent Networks | ||
| :page-aliases: anypoint-code-builder::af-create-agent-network.adoc | ||
|
|
||
| Whether you use MuleSoft Vibes or the visual canvas and code editor, Anypoint Code Builder includes the agent network functionality you need to get started. |
Contributor
There was a problem hiding this comment.
Suggestion for short description:
Create an agent network to connect brokers, agents, MCP servers, and LLMs into a coordinated workflow. Choose from MuleSoft Vibes, the visual canvas and code editor in Anypoint Code Builder, or the Anypoint CLI for CI/CD environments.
| [[create-dev-agent]] | ||
| == Create a Network Using MuleSoft Vibes | ||
|
|
||
| You can use natural language prompts in MuleSoft Vibes to create your project. For more information, see xref:anypoint-code-builder::api-ai-create-spec.adoc[]. |
Contributor
There was a problem hiding this comment.
Suggested change
| You can use natural language prompts in MuleSoft Vibes to create your project. For more information, see xref:anypoint-code-builder::api-ai-create-spec.adoc[]. | |
| Use natural language prompts in MuleSoft Vibes to create your project. For more information, see xref:anypoint-code-builder::api-ai-create-spec.adoc[]. |
| . Select the business group associated with the target space you created in xref:af-get-started.adoc[Get Started with Agent Networks]. The business group you select must be the same business group you selected when you created the target space. | ||
| . Select *Create Project*. | ||
|
|
||
| When the project opens, the `agent-network.yaml` file opens in the code view editor. You can open the graph canvas from the action bar. For more information, see xref:af-define-your-agent-network-specification.adoc[Define Your Agent Network]. |
Contributor
There was a problem hiding this comment.
Suggested change
| When the project opens, the `agent-network.yaml` file opens in the code view editor. You can open the graph canvas from the action bar. For more information, see xref:af-define-your-agent-network-specification.adoc[Define Your Agent Network]. | |
| When the project opens, the `agent-network.yaml` file opens in the code view editor. Open the graph canvas from the action bar. For more information, see xref:af-define-your-agent-network-specification.adoc[Define Your Agent Network]. |
| [[project-files]] | ||
| == Agent Network Project Files | ||
|
|
||
| Anypoint Code Builder creates the following files and directories as part of your agent network project. Together, these files define the brokers, nodes, assets, connections, and policies that make up your agent network. For full schema details, see xref:af-project-files.adoc[Agent Network Project File Reference]. |
Contributor
There was a problem hiding this comment.
Suggested change
| Anypoint Code Builder creates the following files and directories as part of your agent network project. Together, these files define the brokers, nodes, assets, connections, and policies that make up your agent network. For full schema details, see xref:af-project-files.adoc[Agent Network Project File Reference]. | |
| Anypoint Code Builder creates these files and directories as part of your agent network project. Together, these files define the brokers, nodes, assets, connections, and policies that make up your agent network. For full schema details, see xref:af-project-files.adoc[Agent Network Project File Reference]. |
|
|
||
| * `exchange.json` | ||
| + | ||
| The Anypoint Exchange manifest for the project. This file lists the project's metadata and the Exchange assets added as dependencies. When you publish your project, Exchange uses this file to register the assets. When you add an Exchange asset to your project, its asset ID and version are recorded here. |
Contributor
There was a problem hiding this comment.
Suggested change
| The Anypoint Exchange manifest for the project. This file lists the project's metadata and the Exchange assets added as dependencies. When you publish your project, Exchange uses this file to register the assets. When you add an Exchange asset to your project, its asset ID and version are recorded here. | |
| The Anypoint Exchange manifest for the project. This file lists the project's metadata and the Exchange assets added as dependencies. When you publish your project, Exchange uses this file to register the assets. When you add an Exchange asset to your project, its asset ID and version are recorded in this file. |
| [[create-cli]] | ||
| == Create a Network Using the Anypoint CLI | ||
|
|
||
| If you run operations within a CI/CD environment, you can use Anypoint CLI's plugin to set up, create, build, publish, and deploy agent networks. For more information, see xref:af-build-agent-networks-in-a-ci-cd-environment.adoc[]. |
Contributor
There was a problem hiding this comment.
Suggested change
| If you run operations within a CI/CD environment, you can use Anypoint CLI's plugin to set up, create, build, publish, and deploy agent networks. For more information, see xref:af-build-agent-networks-in-a-ci-cd-environment.adoc[]. | |
| If you run operations within a CI/CD environment, use Anypoint CLI's plugin to set up, create, build, publish, and deploy agent networks. For more information, see xref:af-build-agent-networks-in-a-ci-cd-environment.adoc[]. |
valkyrie69
reviewed
Jun 15, 2026
| [[define-acb-ide]] | ||
| == Define Your Network in Anypoint Code Builder | ||
|
|
||
| Use the code view editor and the visual canvas together to define your agent network. The canvas is read-only and syncs automatically as you make changes to the code. Essentially, make all changes in the project files and use the canvas to navigate, verify the shape of your network, and jump back to the lines you need to edit. |
Contributor
There was a problem hiding this comment.
Suggested change
| Use the code view editor and the visual canvas together to define your agent network. The canvas is read-only and syncs automatically as you make changes to the code. Essentially, make all changes in the project files and use the canvas to navigate, verify the shape of your network, and jump back to the lines you need to edit. | |
| Use the code view editor and the visual canvas together to define your agent network. The canvas is read-only and syncs automatically as you make changes to the code. Make all changes in the project files and use the canvas to navigate, verify the shape of your network, and jump back to the lines you need to edit. |
| [[before-you-begin]] | ||
| == Before You Begin | ||
|
|
||
| Make sure you review the xref:af-get-started.adoc#before-you-begin[prerequisites] and that you have created an agent network project. See xref:af-create-agent-network.adoc[Create Agent Networks]. |
Contributor
There was a problem hiding this comment.
Suggested change
| Make sure you review the xref:af-get-started.adoc#before-you-begin[prerequisites] and that you have created an agent network project. See xref:af-create-agent-network.adoc[Create Agent Networks]. | |
| Review the xref:af-get-started.adoc#before-you-begin[prerequisites] and make sure that you've created an agent network project. See xref:af-create-agent-network.adoc[Create Agent Networks]. |
|
|
||
| [NOTE] | ||
| ==== | ||
| Using the visual canvas is optional. If you prefer a code-only workflow, you can edit `agent-network.yaml`, the `.agent` files under `/brokers`, and `exchange.json` directly without ever opening the canvas. Auto-completion menus in Anypoint Code Builder work the same way in both workflows. For more information, see xref:anypoint-code-builder::start-discover-ui.adoc#use-autocomplete[Use Auto-Completion Menus]. |
Contributor
There was a problem hiding this comment.
Suggested change
| Using the visual canvas is optional. If you prefer a code-only workflow, you can edit `agent-network.yaml`, the `.agent` files under `/brokers`, and `exchange.json` directly without ever opening the canvas. Auto-completion menus in Anypoint Code Builder work the same way in both workflows. For more information, see xref:anypoint-code-builder::start-discover-ui.adoc#use-autocomplete[Use Auto-Completion Menus]. | |
| Using the visual canvas is optional. If you prefer a code-only workflow, edit `agent-network.yaml`, the `.agent` files under `/brokers`, and `exchange.json` directly without ever opening the canvas. Auto-completion menus in Anypoint Code Builder work the same way in both workflows. For more information, see xref:anypoint-code-builder::start-discover-ui.adoc#use-autocomplete[Use Auto-Completion Menus]. |
| . In the Explorer, navigate to the `/brokers` directory and open the `.agent` file for the broker you want to edit (for example, `broker1.agent`). Edit the `.agent` file to define the broker, its nodes (trigger, subagent, orchestrator, generator, executor, echo, router), and the transitions between them. | ||
| + | ||
| To understand the schema and expected values for each file, see xref:af-project-files.adoc[Agent Network Project File Reference]. | ||
| . Update `exchange.json` to manage Anypoint Exchange dependencies. You typically update this file by using the *Add Exchange Assets* action rather than editing it by hand. See <<add-exchange-assets>>. |
Contributor
There was a problem hiding this comment.
Suggested change
| . Update `exchange.json` to manage Anypoint Exchange dependencies. You typically update this file by using the *Add Exchange Assets* action rather than editing it by hand. See <<add-exchange-assets>>. | |
| . Update `exchange.json` to manage Anypoint Exchange dependencies by using the *Add Exchange Assets* action rather than editing it by hand. See <<add-exchange-assets>>. |
|
|
||
| ==== Adjust the Canvas View | ||
|
|
||
| You can adjust nodes on the canvas view while you edit your project. |
Contributor
There was a problem hiding this comment.
Suggested change
| You can adjust nodes on the canvas view while you edit your project. | |
| Adjust nodes on the canvas view while you edit your project. |
| [[manage-project-assets]] | ||
| == Manage Project Assets | ||
|
|
||
| The *Project Assets* view lists every asset (agent, LLM, MCP server, or policy) you declared in the *registry* section of `agent-network.yaml`. Here you can manage those assets or add new dependencies from Anypoint Exchange. |
Contributor
There was a problem hiding this comment.
Suggested change
| The *Project Assets* view lists every asset (agent, LLM, MCP server, or policy) you declared in the *registry* section of `agent-network.yaml`. Here you can manage those assets or add new dependencies from Anypoint Exchange. | |
| The *Project Assets* view lists every asset (agent, LLM, MCP server, or policy) you declared in the *registry* section of `agent-network.yaml`. Use this view to manage those assets or add new dependencies from Anypoint Exchange. |
| ** *Imported from Exchange* | ||
| + | ||
| Lists Exchange assets you added as dependencies via `exchange.json`. Each card shows the asset type icon, the asset name, and the version. | ||
| . Use the *search* and *filter* controls at the top of the Asset Registry to find assets across both sections. |
Contributor
There was a problem hiding this comment.
Suggested change
| . Use the *search* and *filter* controls at the top of the Asset Registry to find assets across both sections. | |
| . Use the *search* and *filter* controls at the top of the Project Assets view to find assets across both sections. |
|
|
||
| === Add Assets Using MuleSoft Vibes | ||
|
|
||
| Use natural language prompts to let MuleSoft Vibes add Exchange assets to your project for you. |
Contributor
There was a problem hiding this comment.
Suggested change
| Use natural language prompts to let MuleSoft Vibes add Exchange assets to your project for you. | |
| se natural language prompts in MuleSoft Vibes to add Exchange assets to your project. |
| . Search for the asset you want to add, select it, and choose the version to import. | ||
| . Click *Add to Project*. | ||
| + | ||
| The asset is added to the `dependencies` attribute in `exchange.json` and appears in the *Imported from Exchange* section of the Asset Registry. |
Contributor
There was a problem hiding this comment.
Asset Registry or Project Assets?
| . In *Add Exchange Assets to Project*, search for and select the asset. | ||
| . Click *Add to Project*. | ||
|
|
||
| After you add dependencies, they're available as values in auto-completion menus in the code editor. For example, after you add `test-agent` to `exchange.json`, the value `test-agent` is available in auto-completion menus in `agent-network.yaml` when you reference an agent. |
Contributor
There was a problem hiding this comment.
Suggested change
| After you add dependencies, they're available as values in auto-completion menus in the code editor. For example, after you add `test-agent` to `exchange.json`, the value `test-agent` is available in auto-completion menus in `agent-network.yaml` when you reference an agent. | |
| After you add dependencies, their asset names are available as values in auto-completion menus in the code editor. For example, after you add `test-agent` to `exchange.json`, the value `test-agent` is available in auto-completion menus in `agent-network.yaml` when you reference an agent. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
IMPORTANT: for agent network v2 release--GA 6/30
Summary:
Adds new agent-network/2.0/ Antora component with full 2.0 documentation: overview, get-started, create, deploy, publish, troubleshoot, CI/CD, plus full agent-network.yaml and Agent Script references
Splits prior content into a versioned agent-network/1.0/ component and removes the old top-level modules/ROOT/ agent-network pages
Adds new architecture diagrams, IT Investigation Broker example, and updated assets