📘 docs: Add Actions Object Structure and update Agents configuration (#…

…182)

components/changelog/content/config_v1.1.9.mdx

@@ -1,3 +1,4 @@
 - Added [Agents](/docs/features/agents) related configurations:
   - [Interface-level toggle for Agents](/docs/configuration/librechat_yaml/object_structure/interface#agents), enabling/disabling Agents for all users
   - [Agent Endpoint-level configuration](/docs/configuration/librechat_yaml/object_structure/agents) for Agent options and capabilities
+  - [Actions Object Structure](/docs/configuration/librechat_yaml/object_structure/actions) for specifying allowed domains for agent/assistant actions

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

@@ -0,0 +1,35 @@
+# Actions Object Structure
+
+Actions can be used to dynamically create tools from OpenAPI specs. The `actions` object structure allows you to specify allowed domains for agent/assistant actions.
+
+More info: [Agents - Actions](/docs/features/agents#actions)
+
+## Example
+
+```yaml filename="Actions Object Structure"
+# Example Actions Object Structure
+actions:
+  allowedDomains:
+    - "swapi.dev"
+    - "librechat.ai"
+    - "google.com"
+```
+
+## allowedDomains
+
+**Key:**
+<OptionTable
+  options={[
+    ['allowedDomains', 'Array of Strings', 'A list specifying allowed domains for agent/assistant actions.', 'Actions with domains not listed will be restricted from executing.'],
+  ]}
+/>
+
+**Required**
+
+**Example:**
+```yaml filename="actions / allowedDomains"
+allowedDomains:
+  - "swapi.dev"
+  - "librechat.ai"
+  - "google.com"
+```

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

@@ -204,6 +204,26 @@ see also:
 - [alloweddomains](/docs/configuration/librechat_yaml/object_structure/registration#alloweddomains),
 - [Registration Object Structure](/docs/configuration/librechat_yaml/object_structure/registration)
 
+## actions
+
+**Key:**
+<OptionTable
+  options={[
+    ['actions', 'Object', 'Configures actions-related settings, used by Agents and Assistants', ''],
+  ]}
+/>
+
+**Subkeys:**
+<OptionTable
+  options={[
+    ['allowedDomains', '', 'Specifies allowed domains for actions.', ''],
+  ]}
+/>
+
+see also: 
+- [alloweddomains](/docs/configuration/librechat_yaml/object_structure/actions#alloweddomains),
+- [Actions Object Structure](/docs/configuration/librechat_yaml/object_structure/actions)
+
 ## interface
 
 **Key:**

pages/docs/features/agents.mdx

@@ -41,7 +41,7 @@ The model parameters interface allows fine-tuning of your agent's responses:
 
 ### Code Interpreter
 
-When enabled, Code Interpreter allows your agent to:
+When enabled, the Code Interpreter capability allows your agent to:
 - Execute code in multiple languages, including:
   - Python, JavaScript, TypeScript, Go, C, C++, Java, PHP, Rust, and Fortran
 - Process files securely through the LibreChat Code Interpreter API
@@ -50,15 +50,15 @@ When enabled, Code Interpreter allows your agent to:
 - [More info about the Code Interpreter API](/docs/features/code_interpreter)
   - **Requires an API Subscription from [code.librechat.ai](https://code.librechat.ai/pricing)**
 
-### File Search Capabilities
+### File Search
 
-The File Search feature enables:
+The File Search capability enables:
 - RAG (Retrieval-Augmented Generation) functionality
 - Semantic search across uploaded documents
 - Context-aware responses based on file contents
 - File attachment support at both agent and chat thread levels
 
-### Tools Integration
+### Tools
 
 Agents can also be enhanced with various built-in tools:
 
@@ -71,7 +71,24 @@ Agents can also be enhanced with various built-in tools:
 - **Traversaal**: A robust search API for LLM Agents
 - **Wolfram**: Computational and mathematical capabilities
 
-More tool integrations are planned, including [Model Context Provider](https://github.com/danny-avila/LibreChat/issues/4876) support.
+- More tool integrations are planned, including [Model Context Provider](https://github.com/danny-avila/LibreChat/issues/4876) support.
+- Tools can be disabled using the [`librechat.yaml`](/docs/configuration/librechat_yaml) configuration file:
+  - [More info](/docs/configuration/librechat_yaml/object_structure/agents#capabilities)
+
+### Actions
+
+With the Actions capability, you can dynamically create tools from OpenAPI specs to add to your Agents.
+
+![Agents - Endpoints Menu](/images/agents/actions.png)
+
+**Clicking the button above will open a form where you can input the OpenAPI spec URL and create an action:**
+
+![Agents - Endpoints Menu](/images/agents/actions_panel.png)
+
+- Actions can be disabled using the [`librechat.yaml`](/docs/configuration/librechat_yaml) configuration file:
+  - [More info](/docs/configuration/librechat_yaml/object_structure/agents#capabilities)
+- Individual domains can be whitelisted for agent actions:
+  - [More info](/docs/configuration/librechat_yaml/object_structure/actions#alloweddomains)
 
 ## File Management