📝 feat: Agents maxRecursionLimit, Config Version Update, Agent Chain And Missing Artifacts Info (#264)

* 📝 feat: Update agent capabilities to include 'artifacts' and 'chain'

* 📝 feat: Add Agent Chain capability and Advanced Settings documentation

* 📝 feat: Add maxRecursionLimit option to agents configuration and update documentation

* 📝 feat: Update agents configuration with maxRecursionLimit and enhance capabilities documentation

* feat: Update Agent Chain documentation to include beta status and maximum agent limit

components/changelog/content/config_v1.2.3.mdx

@@ -0,0 +1,17 @@
+- Added `maxRecursionLimit` to [Agents Endpoint](/docs/configuration/librechat_yaml/object_structure/agents#maxrecursionlimit)
+  - Sets the absolute maximum number of steps an agent can take in a run
+  - Defines the upper limit for `recursionLimit` that can be set from the UI
+  - If omitted, defaults to the value of `recursionLimit` or 25 if `recursionLimit` is also omitted
+  - For more information about agent steps, see [Max Agent Steps](/docs/features/agents#max-agent-steps)
+- Updated `recursionLimit` in [Agents Endpoint](/docs/configuration/librechat_yaml/object_structure/agents#recursionlimit)
+  - Now represents the default number of steps an agent can take in a run
+  - This value can be configured from the UI up to the `maxRecursionLimit` (if one is provided)
+  - For more information about agent steps, see [Max Agent Steps](/docs/features/agents#max-agent-steps)
+- Added `artifacts` to [Agent Capabilities](/docs/configuration/librechat_yaml/object_structure/agents#capabilities)
+  - Enables agents to generate and display interactive content, such as React components, HTML code, and Mermaid diagrams
+  - For more information, see [Artifacts](/docs/features/artifacts)
+- Added `chain` to [Agent Capabilities](/docs/configuration/librechat_yaml/object_structure/agents#capabilities)
+  - Enables a Mixture-of-Agents (MoA) approach for complex tasks
+  - Allows creation of chains of specialized agents that work together
+  - Each agent in the chain can access outputs from previous agents
+  - For more information, see [Agent Chain](/docs/features/agents#agent-chain)

pages/changelog/config_v1.2.3.mdx

@@ -0,0 +1,13 @@
+---
+date: 2025/3/17
+title: ⚙️ Config v1.2.3
+---
+
+import { ChangelogHeader } from '@/components/changelog/ChangelogHeader'
+import Content from '@/components/changelog/content/config_v1.2.3.mdx'
+
+<ChangelogHeader />
+
+---
+
+<Content />

pages/docs/configuration/librechat_yaml/object_structure/agents.mdx

@@ -8,9 +8,10 @@ This page applies to the [`agents`](/docs/features/agents) endpoint.
 endpoints:
   agents:
     recursionLimit: 50
+    maxRecursionLimit: 100
     disableBuilder: false
     # (optional) Agent Capabilities available to all users. Omit the ones you wish to exclude. Defaults to list below.
-    # capabilities: ["execute_code", "file_search", "actions", "tools", "ocr"]
+    # capabilities: ["execute_code", "file_search", "actions", "tools", "artifacts", "ocr", "chain"]
 ```
 > This configuration enables the builder interface for agents.
 
@@ -18,7 +19,7 @@ endpoints:
 
 <OptionTable
   options={[
-    ['recursionLimit', 'Number', 'Sets the maximum number of super-steps the graph can execute during a single execution.', 'Controls recursion depth to prevent infinite loops. When limit is reached, raises GraphRecursionError.'],
+    ['recursionLimit', 'Number', 'Sets the default number of steps an agent can take in a run.', 'Controls recursion depth to prevent infinite loops. When limit is reached, raises GraphRecursionError. This value can be configured from the UI up to the maxRecursionLimit.'],
   ]}
 />
 
@@ -29,6 +30,25 @@ endpoints:
 recursionLimit: 50
 ```
 
+For more information about agent steps, see [Max Agent Steps](/docs/features/agents#max-agent-steps).
+
+## maxRecursionLimit
+
+<OptionTable
+  options={[
+    ['maxRecursionLimit', 'Number', 'Sets the absolute maximum number of steps an agent can take in a run.', 'Defines the upper limit for the recursionLimit that can be set from the UI. This prevents users from setting excessively high values.'],
+  ]}
+/>
+
+**Default:** If omitted, defaults to the value of recursionLimit or 25 if recursionLimit is also omitted.
+
+**Example:**
+```yaml filename="endpoints / agents / maxRecursionLimit"
+maxRecursionLimit: 100
+```
+
+For more information about agent steps, see [Max Agent Steps](/docs/features/agents#max-agent-steps).
+
 ## disableBuilder
 
 <OptionTable
@@ -52,7 +72,7 @@ disableBuilder: false
   ]}
 />
 
-**Default:** `["execute_code", "file_search", "actions", "tools", "ocr"]`
+**Default:** `["execute_code", "file_search", "actions", "tools", "artifacts", "ocr", "chain"]`
 
 **Example:**
 ```yaml filename="endpoints / agents / capabilities"
@@ -61,7 +81,9 @@ capabilities:
   - "file_search"
   - "actions"
   - "tools"
+  - "artifacts"
   - "ocr"
+  - "chain"
 ```
 **Note:** This field is optional. If omitted, the default behavior is to include all the capabilities listed in the default.
 
@@ -88,6 +110,7 @@ endpoints:
     capabilities:
       - "execute_code"
       - "actions"
+      - "artifacts"
       - "ocr"
 ```
 

pages/docs/features/agents.mdx

@@ -39,6 +39,8 @@ The model parameters interface allows fine-tuning of your agent's responses:
 
 ## Agent Capabilities
 
+> **Note:** All capabilities can be toggled via the `librechat.yaml` configuration file. See [docs/configuration/librechat_yaml/object_structure/agents#capabilities](/docs/configuration/librechat_yaml/object_structure/agents#capabilities) for more information.
+
 ### Code Interpreter
 
 When enabled, the Code Interpreter capability allows your agent to:
@@ -69,6 +71,40 @@ The File Context (OCR) capability allows your agent to extract and process text
 - [More info about OCR](/docs/features/ocr)
   - **Currently uses Mistral OCR API which may incur costs**
 
+### Artifacts
+
+The Artifacts capability enables your agent to generate and display interactive content:
+
+- Create React components, HTML code, and Mermaid diagrams
+- Display content in a separate UI window for clarity and interaction
+- Configure artifact-specific instructions at the agent level
+- [More info about Artifacts](/docs/features/artifacts)
+
+When enabled, additional instructions specific to the use of artifacts are added by default. Options include:
+
+- **Enable shadcn/ui instructions**: Adds instructions for using shadcn/ui components (a collection of re-usable components built using Radix UI and Tailwind CSS)
+- **Custom Prompt Mode**: When enabled, the default artifacts system prompt will not be included, allowing you to provide your own custom instructions
+
+Configuring artifacts at the agent level is the preferred approach, as it allows for more granular control compared to the legacy app-wide configuration.
+
+If you enable Custom Prompt Mode, you should include at minimum the basic artifact format in your instructions. Here's a simple example of the minimum instructions needed:
+
+```
+When creating content that should be displayed as an artifact, use the following format:
+
+:::artifact{identifier="unique-identifier" type="mime-type" title="Artifact Title"}
+```
+Your artifact content here
+```
+:::
+
+For the type attribute, use one of:
+- "text/html" for HTML content
+- "application/vnd.mermaid" for Mermaid diagrams
+- "application/vnd.react" for React components
+- "image/svg+xml" for SVG images
+```
+
 ### Tools
 
 Agents can also be enhanced with various built-in tools:
@@ -104,6 +140,37 @@ Note that you can add add the 'x-strict': true flag at operation-level in the Op
 If using an OpenAI model supporting it, this will automatically generate function calls with 'strict' mode enabled.
 Strict mode supports only a partial subset of json. Read https://platform.openai.com/docs/guides/structured-outputs/some-type-specific-keywords-are-not-yet-supported for details.
 
+### Agent Chain
+
+The Agent Chain capability enables a Mixture-of-Agents (MoA) approach, allowing you to create a sequence of agents that work together:
+
+- Create chains of specialized agents for complex tasks
+- Each agent in the chain can access outputs from previous agents
+- Configure the maximum number of steps for the agent chain
+- **Note:** Access this feature from the Advanced Settings panel in the Agent Builder
+- **Note:** This feature is currently in beta and may be subject to change
+  - The current maximum of agents that can be chained is 10, but this may be configurable in the future
+
+![Agent Chain](/images/agents/agent_chain.png)
+
+This feature introduces a layered Mixture-of-Agents architecture to LibreChat, where each agent takes all the outputs from agents in the previous layer as auxiliary information in generating its response, as described in [the eponymous "Mixture-of-Agents" paper](https://arxiv.org/abs/2406.04692).
+
+### Advanced Settings
+
+Advanced settings for your agent (found in the Advanced view of the Agent form) outside of "capabilities."
+
+#### Max Agent Steps
+
+This setting allows you to limit the number of steps an agent can take in a "run," which refers to the agent loop before a final response is given.
+
+If left unconfigured, the default is 25 steps, but you can adjust this to suit your needs. For admins, you can set a global default as well as a global maximum in the [`librechat.yaml`](/docs/configuration/librechat_yaml/object_structure/agents#recursionlimit) file.
+
+A "step" refers to either an AI API request or a round of tool usage (1 or many tools, depending on how many tool calls the LLM provides from a single request).
+
+A single, non-tool response is 1 step. A singular round of tool usage is usually 3 steps:
+
+1. API Request -> 2. Tool Usage (1 or many tools) -> 3. Follow-up API Request
+
 ### Model Context Protocol (MCP)
 
 MCP is an open protocol that standardizes how applications provide context to Large Language Models (LLMs), acting like a universal adapter for AI tools and data sources.

pages/docs/features/artifacts.mdx

@@ -8,6 +8,9 @@ description: Discover LibreChat's revolutionary Artifacts feature for instant cr
 - **Generative UI:** Create React components, HTML code, and Mermaid diagrams
 - **Flexible Integration:** Use any model you have set up
 - **Iterative Design:** Rapidly improve and refine generated outputs
+- **Agent Integration:** Configure artifacts at the agent level (recommended approach)
+
+> **Note:** The preferred way to use artifacts is now through the [Agents feature](/docs/features/agents#artifacts), which allows for more granular control by enabling/disabling artifacts at the agent level rather than app-wide.
 
 <div align="center">
   <iframe width="560" height="315" src="https://www.youtube.com/embed/GfTj7O4gmd0?si=NrtqGoodGpfANBfT" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen="true"></iframe>