W-21433121 agent network 2.0 content ie by IsaacEldridge · Pull Request #660 · mulesoft/docs-code-builder

IsaacEldridge · 2026-06-12T17:00:26Z

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

…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.

…k documentation

…, 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>

…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

…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 · 2026-06-15T18:18:16Z

+[[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.


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.

Are we capitalizing agent network? I think Melissa decided not to but if you decided differently, that's fine with me. Just checking.

valkyrie69 · 2026-06-15T18:42:00Z

+|Yes
+
+|`reasoning_effort`
+|Constrains effort on reasoning for reasoning models. gpt-5.1 defaults to NONE, previous ones default to MEDIUM


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`.

valkyrie69 · 2026-06-15T18:43:17Z

+|Yes
+
+|`kind`
+|Constant indicating this will invoke an MCP tool


Suggested change

|Constant indicating this will invoke an MCP tool

|Constant indicating that this invokes an MCP tool

valkyrie69 · 2026-06-15T18:46:55Z

+
+=== 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). 


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.

valkyrie69 · 2026-06-16T17:53:41Z

+[[example-building-an-it-investigation-broker]]
+= Example: Building an IT Investigation Broker
+
+In this example, the goal is to use MuleSoft Vibes to build an IT Investigation agent that triages incoming support tickets, escalates critical issues, resolves common problems through cross-platform investigation, and handles licensing requests.


Suggested change

In this example, the goal is to use MuleSoft Vibes to build an IT Investigation agent that triages incoming support tickets, escalates critical issues, resolves common problems through cross-platform investigation, and handles licensing requests.

Use MuleSoft Vibes to build an IT Investigation agent that triages incoming support tickets, escalates critical issues, resolves common problems through cross-platform investigation, and handles licensing requests.

…ers. Replace `a2a:response` with `a2a:artifact_update_event` and `a2a:status_update_event`, and enhance examples and parameter descriptions for clarity. Add behavior tables for different client operations.

valkyrie69 · 2026-06-16T21:48:28Z

+= Agent Network 2.0 Project File Reference
+:page-aliases: anypoint-code-builder::af-project-files.adoc
+
+An agent network project defines a structured configuration for multi-agent systems, enabling orchestration of AI agents with external services, tools, and inter-agent communication. This format provides a declarative way to define agent capabilities, dependencies, and service integrations.


Suggested change

An agent network project defines a structured configuration for multi-agent systems, enabling orchestration of AI agents with external services, tools, and inter-agent communication. This format provides a declarative way to define agent capabilities, dependencies, and service integrations.

An agent network project defines a structured configuration for multi-agent systems, enabling orchestration of AI agents with external services, tools, and inter-agent communication. This project file format provides a declarative way to define agent capabilities, dependencies, and service integrations.

valkyrie69 · 2026-06-16T21:49:17Z

+* `exchange.json`: Contains asset metadata available in Anypoint Exchange after publishing your agent network assets.
+* `agent-network.yaml`: Contains a registry section that defines Exchange assets used in your project and a context section that defines connections and policies for the project.
+* `.agent` files: Contain broker and node definitions and configurations that enable multi-agent orchestration in your project.
+


For complete schema details, see:

IsaacEldridge and others added 30 commits May 20, 2026 11:15

W-21433033 Rename agent-network nav title to Building Agent Networks

ed234e4

Enhance agent network documentation by adding YAML and Agent Script r…

70f7efe

…eferences. Update navigation to include new references and clarify deployment target requirements for CloudHub 2.0. Adjust language for consistency across documentation.

Update agent network documentation to include configuration options a…

915403f

…nd default URLs for OpenAI and Gemini. Added references for better clarity and user guidance.

Update af-project-files.adoc to generalize file references for broker…

a88c7f3

… configurations. Changed specific mention of `broker1.agent` files to `.agent` files for clarity and consistency in documentation regarding multi-agent orchestration.

Update af-publish-agent-network-assets.adoc to refine versioning inst…

9cb0d61

…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.

change note to regular heading and prose

755946b

Add support status attribute to Antora configuration for agent networ…

58e183d

…k documentation

Enhance agent network documentation by adding descriptions for skills…

9b72088

…, capabilities, and transport types. Updated sections on project creation, asset management, and deployment processes in Anypoint Code Builder for improved clarity and user guidance.

Update agent network documentation to reflect changes in directory st…

aab071a

…ructure, replacing references from `/agent-script` to `/brokers` for improved clarity in navigating broker configurations.

Clarify documentation on setting action headers in af-agent-script-re…

67efdad

…ference.adoc by specifying the use of authorization headers in OBO authentication scenarios, enhancing the understanding of custom header requirements for external system connections.

Update agent network documentation to correct the format of the agent…

658f193

…Network version from a quoted string to a numeric value for improved clarity and consistency.

Update af-troubleshoot-agent-networks.adoc to remove outdated logging…

25ea733

… instructions and correct A2A protocol version from 0.3.0 to 1.0.0, enhancing clarity and accuracy in troubleshooting guidance.

Fix orphan ==== delimiter in af-define-your-agent-network-specificati…

0f342a2

…on.adoc that was wrapping the rest of the page in an example block, causing all subsequent headings to render as literal AsciiDoc syntax.

typo

969dbed

Update af-agent-networks.adoc to clarify the handling of policies, tr…

ec74d26

…affic, and data by the Omni Gateway in shared and private space configurations.

Add new agent fabric architecture diagram and image; remove outdated …

f9f05ee

…diagram. Update documentation to reflect changes in architecture and clarify Omni Gateway usage in shared and private space configurations.

Enhance documentation for adding Exchange assets in agent network pro…

e965e52

…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.

Merge pull request #656 from mulesoft/W-22730742--example-for-adding-…

3fc2bd3

…exchange-dependencies-to-agent-network-file-ie W-22730742 example adding exchange asset

Fix typo in 1.0 page notice banner URL (lastest -> latest)

d7a798a

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Fix 1.0 page notice banner URL to use correct Antora component path

a80ce72

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

IsaacEldridge added 2 commits June 9, 2026 16:01

remove issue

18cbf20

checking docs with super agent

fae8e63

IsaacEldridge added the DO NOT MERGE UNTIL RELEASE label Jun 12, 2026

IsaacEldridge requested a review from a team as a code owner June 12, 2026 17:00

IsaacEldridge added 2 commits June 12, 2026 10:29

Merge remote-tracking branch 'origin/latest' into W-21433121-agent-ne…

13d80b1

…twork-2.0-content-ie

valkyrie69 reviewed Jun 15, 2026

View reviewed changes

Comment thread agent-network/2.0/modules/ROOT/pages/af-agent-network-yaml-reference.adoc Outdated

Comment thread agent-network/2.0/modules/ROOT/pages/af-agent-network-yaml-reference.adoc Outdated

valkyrie69 reviewed Jun 15, 2026

View reviewed changes

Comment thread agent-network/2.0/modules/ROOT/pages/af-agent-networks.adoc Outdated

Comment thread agent-network/2.0/modules/ROOT/pages/af-agent-networks.adoc Outdated

Comment thread agent-network/2.0/modules/ROOT/pages/af-agent-networks.adoc Outdated

Refactor agent metadata structure in YAML reference to use 'interface…

e7f9d14

…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

View reviewed changes

valkyrie69 reviewed Jun 16, 2026

View reviewed changes

Update Echo Node documentation to reflect new event types and paramet…

c80c1dd

…ers. Replace `a2a:response` with `a2a:artifact_update_event` and `a2a:status_update_event`, and enhance examples and parameter descriptions for clarity. Add behavior tables for different client operations.

valkyrie69 reviewed Jun 16, 2026

View reviewed changes

Comment thread agent-network/2.0/modules/ROOT/pages/af-get-started.adoc Outdated

Comment thread agent-network/2.0/modules/ROOT/pages/af-get-started.adoc Outdated

IsaacEldridge added 2 commits June 16, 2026 12:00

change hybrid to guided

edd4ac2

replacing ACB screenshot

3a50244

valkyrie69 reviewed Jun 16, 2026

View reviewed changes

post-peer review edits

f586151

	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.

	\|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`.

	\|Constant indicating this will invoke an MCP tool
	\|Constant indicating that this invokes an MCP tool


		=== 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).

	In this example, the goal is to use MuleSoft Vibes to build an IT Investigation agent that triages incoming support tickets, escalates critical issues, resolves common problems through cross-platform investigation, and handles licensing requests.
	Use MuleSoft Vibes to build an IT Investigation agent that triages incoming support tickets, escalates critical issues, resolves common problems through cross-platform investigation, and handles licensing requests.

	An agent network project defines a structured configuration for multi-agent systems, enabling orchestration of AI agents with external services, tools, and inter-agent communication. This format provides a declarative way to define agent capabilities, dependencies, and service integrations.
	An agent network project defines a structured configuration for multi-agent systems, enabling orchestration of AI agents with external services, tools, and inter-agent communication. This project file format provides a declarative way to define agent capabilities, dependencies, and service integrations.

Conversation

IsaacEldridge commented Jun 12, 2026

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!