Fix typos and formatting issues

Author: jubarbot-cisco

docs/pages/connect.md

@@ -1,10 +1,10 @@
-# Agent Connect Protocol 
+# Agent Connect Protocol
 
 ## Introduction
 
 Existing Multi-Agent Systems (MAS) provide convenient ways to build Multi-Agent Applications (MAAs) that combine various agents and enable them to communicate with each other. Such communication occurs within the MAS using internal mechanisms and APIs.
 
-Building the Internet of Agents (IoA) requires agents built by different parties, potentially for different MAS and potentially running in different locations to interact. 
+Building the Internet of Agents (IoA) requires agents built by different parties, potentially for different MAS and potentially running in different locations to interact.
 
 While interaction between co-located agents implemented through the same MAS is trivial, it is harder in case the agents are not natively compatible or in case they run in different locations.
 
@@ -21,11 +21,11 @@ Agent Connect Protocol needs to formally specify the network interactions needed
 * **Authentication**: Define how caller authenticates with an agent and what its permissions are.
 * **Configuration**: Define how to configure a remote agent.
 * **Invocation**: Define how to invoke a remote agent providing input for its execution.
-* **Output retrieval and interrupt Handling**: Define how to retrieve the result of an agent invocation. Different interaction modes should be supported: 
+* **Output retrieval and interrupt Handling**: Define how to retrieve the result of an agent invocation. Different interaction modes should be supported:
     * Synchronous
     * Asynchronous
     * Streaming
-    
+
     This should include interrupt handling. That is, how agents notify the caller about execution suspension to ask for additional input.
 * **Capabilities and Schema definitions**: Retrieve details about the agent supported capabilities and the data structures definitions for configuration, input, and output.
 * **Error definitions**: Receive error notifications with meaningful error codes and explanations.
@@ -43,7 +43,7 @@ For the reason above, ACP must define an endpoint that does not require authenti
 <a id="configuration"></a>
 ### Configuration
 
-Agents may support configuration. 
+Agents may support configuration.
 
 Configuration is meant to provide parameters needed by the agent to function and to flavor their behavior.
 
@@ -73,10 +73,10 @@ The invocation endpoint must accept the following parameters:
 * **Optional configuration**
 
     When provided, this configuration is valid only for this invocation. Alternatively, the invocation endpoint must accept the identifier of a previously configured instance of an agent. For more information, see [Configuration](#configuration).
- 
+
 * **Optional callback**
-    
-    When provided, the output of the invocation is provided asynchronously through the provided callback. For more information. For more information, see [Output Retrieval and Interrupt Handling](#output).
+
+    When provided, the output of the invocation is provided asynchronously through the provided callback. For more information, see [Output Retrieval and Interrupt Handling](#output).
 
 * **Optional execution identifier**
 
@@ -113,23 +113,23 @@ The ACP must define an endpoint that provides schema definitions for configurati
 
 Different agents may implement different parts of the protocol. For example: an agent may support streaming, while another may only support full responses. An agent may support threads while another may not.
 
-The ACP must define and endpoint that provides details about the specific capabilities that the agent supports.
+The ACP must define an endpoint that provides details about the specific capabilities that the agent supports.
 
 Schemas, agent capabilities, and other essential information that describe an agent are also needed in what we call the [Agent Manifest](manifest.md). 
 
 <a id="errors"></a>
 ### Error Definitions
 
-Each of the operations offered by the ACP can produce an error. 
+Each of the operations offered by the ACP can produce an error.
 
 Errors can be provided synchronously by each of the invoked endpoints or asynchronously when they occur during an execution that supports asynchronous output.
 
-The ACP must define errors for the most common error conditions. 
+The ACP must define errors for the most common error conditions.
 
 Each definition must include the following details:
 * Error code.
 * Description of the error condition.
 * A flag that says if the error is transient or permanent.
 * An optional schema definition of additional information that the error can be associated with.
 
-The ACP also allows agents to provide definitions of errors specific for that agent. For this purpose, the ACP must define an endpoint that provides schema definitions for all agent specific errors that are not included in the ACP specification.
+The ACP also allows agents to provide definitions of errors specific for that agent. For this purpose, the ACP must define an endpoint that provides schema definitions for all agent specific errors that are not included in the ACP specification.

docs/pages/introduction.md

@@ -1,23 +1,23 @@
 ## Introduction
 
-The AGNTCY is an open source collective building the infrastructure for The Internet of Agents: an open, interoperable internet for agent to agent collaboration. 
+The AGNTCY is an open source collective building the infrastructure for The Internet of Agents: an open, interoperable internet for agent to agent collaboration.
 
 ### Vision
 
 Agentic AI will accelerate all of human work. Enterprises must create agentic workflows and applications combining internal and 3rd party agents to fully leverage the power of AI, accelerate their business and unlock new step-change in productivity.
-We believe that an open, interoperable Internet of Agents is the key to enabling the best possible path forward to accelerate innovation and create the most value for all participants, from builders to operators, developers to consumers across all industries and businesses. 
+We believe that an open, interoperable Internet of Agents is the key to enabling the best possible path forward to accelerate innovation and create the most value for all participants, from builders to operators, developers to consumers across all industries and businesses.
 
 ### Mission
 
-We are an open source collective that will build the Internet of Agents to be accessible for all: A diverse, collaborative space to innovate, develop, and maintain software components and services that solve key problems in the domain of agentic workflows and multi-agent applications. 
+We are an open source collective that will build the Internet of Agents to be accessible for all: A diverse, collaborative space to innovate, develop, and maintain software components and services that solve key problems in the domain of agentic workflows and multi-agent applications.
 
 ### Capabilities
 
-Based on advanced protocols, frameworks and components, the goal of IoA software infrastructure enables and simplify the creation of multi-agent applications through the following steps:
-1. DISCOVER: Find and evaluate the best agents for the job.
-1. COMPOSE: Connect agents into effective workflows across any framework or vendor.
-1. DEPLOY: Run multi-agent systems at scale, securely. 
-1. EVALUATE: Monitor performance and improve efficiency and efficacy over time.
+Based on advanced protocols, frameworks and components, the goal of IoA software infrastructure is to enables and simplify the creation of multi-agent applications through the following steps:
+1. **DISCOVER**: Find and evaluate the best agents for the job.
+1. **COMPOSE**: Connect agents into effective workflows across any framework or vendor.
+1. **DEPLOY**: Run multi-agent systems at scale, securely.
+1. **EVALUATE**: Monitor performance and improve efficiency and efficacy over time.
 
 ### Technical Objectives
 
@@ -28,7 +28,7 @@ Based on advanced protocols, frameworks and components, the goal of IoA software
 
 ### Core Components
 
-The initial set of IoA components and architecture is described below. As a very first step, we are sharing 2 important specifications: OASF and ACP. In a few weeks the collective will release code and documentation for most of the components. This is a starting point - as new members join and bring their contributions, the collective will continue to evolve and expand the IoA architecture, components and interfaces.   
+The initial set of IoA components and architecture is described below. As a very first step, we are sharing 2 important specifications: OASF and ACP. In a few weeks the collective will release code and documentation for most of the components. This is a starting point - as new members join and bring their contributions, the collective will continue to evolve and expand the IoA architecture, components and interfaces.
 
 ```{image} ../_static/ioa_stack.png
 :alt: Simplified Internet of Agent Stack
@@ -42,7 +42,7 @@ The initial set of IoA components and architecture is described below. As a very
 1. **Agent Connect Protocol (ACP)**: A protocol that defines a standard interface to invoke agents, configure them, provide input, and retrieve output. Current ACP spec can be found [here](https://spec.acp.agntcy.org/).
 1. **Multi-Agent Application Toolkit**: A set of agents and software libraries that support seamless creation of Multi-Agent workflows. 
 1. **Agent Workflow Server**: A server that leverages ACP to manage and executes workflows involving multiple AI agents, ensuring coordinated and efficient task execution.
-1. **Agent Manifest**: A standard format to describes agents, their capabilities, their dependencies, and how to deploy or consume them. The manifest is designed to be used by ACP and the Workflow Server and stored in the Agent Directory with the corresponding OASF extensions.  
+1. **Agent Manifest**: A standard format to describes agents, their capabilities, their dependencies, and how to deploy or consume them. The manifest is designed to be used by ACP and the Workflow Server and stored in the Agent Directory with the corresponding OASF extensions.
 1. **Agent Gateway Protocol (AGP)**: A protocol that defines the standards and guidelines for secure and efficient network-level communication between AI agents. AGP ensures interoperability and seamless data exchange by specifying message formats, transport mechanisms, and interaction patterns.
 1. **Agent Observability**: Tools and techniques for monitoring and analyzing the behavior and performance of AI agents, providing insights into their operations and interactions.
 
@@ -61,4 +61,3 @@ The following diagram shows a simplified architecture of the core components des
 2. **Improved Efficiency**: Standardized protocols and frameworks reduce the complexity of integrating diverse AI agents, resulting in faster development and deployment of AI-driven applications.
 3. **Increased Security**: Robust security mechanisms ensure that interactions between agents are secure, protecting sensitive data and preventing unauthorized access.
 4. **Future-Proof Architecture**: The scalable and flexible design of IoA ensures that the ecosystem can grow and adapt to future advancements in AI technology.
-

docs/pages/manifest.md

@@ -8,7 +8,7 @@ An Agent Manifest is a document that describes in detail the following:
 * How the agent can be deployed if provided as a deployable artifact.
 * What are the dependencies of the agent, that is, which other agents it relies on.
 
-The manifest is designed to be used by [Agent Connect Protocol](connect.md) and the Workflow Server and stored in the Agent Directory with the corresponding OASF extensions.  
+The manifest is designed to be used by [Agent Connect Protocol](connect.md) and the Workflow Server and stored in the Agent Directory with the corresponding OASF extensions.
 
 This document describes the principles of the Agent Manifest definition.
 
@@ -23,7 +23,7 @@ Agent Manifest includes the following sections:
 <a id="agent-identification-and-metadataidentification"></a>
 ### Agent Identification and Metadata
 
-Agent Manifest must uniquely identify an agent within the namespace it is part of. This is done through a unique name and a version. 
+Agent Manifest must uniquely identify an agent within the namespace it is part of. This is done through a unique name and a version.
 
 Agent Manifest must include a natural language description that describes what the agent is capable of doing. This allows user and potentially other agents to select the agent that best fits a given task.
 
@@ -35,20 +35,20 @@ Agents willing to interoperate with other agents expose an interface that allow
 
 Agent Connect Protocol specifies a standard for this interface. However, it specifies methods to configure and invoke agents, but it does not specify the format of the data structures that an agent expects and produces for such configurations and invocations.
 
-The specification of these data structures is included in the what we call the Agent ACP descriptor, which can be provided by ACP itself, but it is also defined as part of the Agent Manifest.  
+The specification of these data structures is included in what we call the Agent ACP descriptor, which can be provided by ACP itself, but it is also defined as part of the Agent Manifest.
 
 Agent ACP descriptor must include an interface data structure specification section that provides schema definitions for the following data structures:
-* **Configuration**: The data structure used to provide agent configuration. 
+* **Configuration**: The data structure used to provide agent configuration.
 * **Input**: The data structures used to provide agent input.
 * **Output**: The data structure used to retrieve agent output.
 
-If an agent supports interrupts, meaning its execution can be interrupted to request additional input and then resumed, the Agent Manifest needs to define the types of interrupts that can possibly occur. 
+If an agent supports interrupts, meaning its execution can be interrupted to request additional input and then resumed, the Agent Manifest needs to define the types of interrupts that can possibly occur.
 
 For each of the interrupts it must define the following:
 * **Interrupt Output**: The format of the output provided by the specific interrupt.
 * **Resume Input**: The input expected by the agent to resume its execution when this specific interrupt occurs.
 
-All schema definitions must include natural language description of the data structure, natural language description of each data structure element, and valid examples of correctly populated data structures. 
+All schema definitions must include natural language description of the data structure, natural language description of each data structure element, and valid examples of correctly populated data structures.
 
 <a id="agent-deployment-and-consumption"></a>
 ### Agent Deployment and Consumption
@@ -67,7 +67,7 @@ The Agent Manifest must include a list of all the possible deployment modes supp
 <a id="agent-dependencies"></a>
 ### Agent Dependencies
 
-An agent may depend on other agents, which means that at some point of its execution it needs to invoke them to accomplish its tasks. We refer to these other agents as **sub-agents**.  A user who wants to use the agent, needs to know this information and check that the dependencies are satisfied, that is, make sure that the sub-agents are available. 
+An agent may depend on other agents, which means that at some point of its execution it needs to invoke them to accomplish its tasks. We refer to these other agents as **sub-agents**.  A user who wants to use the agent, needs to know this information and check that the dependencies are satisfied, that is, make sure that the sub-agents are available.
 This may imply simply checking that sub-agents are reachable or deploying them, according to the deployment modes they support.
 
 The Agent Manifest must include a list of all sub-agents in the form of a list of references to their manifests.