Update reasoning effort parameter values to include 'none'

Author: mkht

Docs/New-Assistant.md

@@ -93,9 +93,8 @@ Position: Named
 ```
 
 ### -ReasoningEffort
-**o1 and o3-mini models only**  
 Constrains effort on reasoning for reasoning models.  
-Currently supported values are `low`, `medium`, and `high`.  
+Supported values are `none`, `low`, `medium`, and `high`.  
 Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
 
 ```yaml

Docs/Request-ChatCompletion.md

@@ -429,7 +429,7 @@ Default value: medium
 ```
 
 ### -ReasoningEffort
-Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high.  
+Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `low`, `medium`, and `high`.  
 Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
 
 ```yaml

Docs/Request-Response.md

@@ -877,7 +877,7 @@ Default value: medium
 ```
 
 ### -ReasoningEffort
-Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high.
+Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `low`, `medium`, and `high`.
 
 ```yaml
 Type: String

Docs/Set-Assistant.md

@@ -105,9 +105,8 @@ Position: Named
 ```
 
 ### -ReasoningEffort
-**o1 and o3-mini models only**  
 Constrains effort on reasoning for reasoning models.  
-Currently supported values are `low`, `medium`, and `high`.  
+Supported values are `none`, `low`, `medium`, and `high`.
 Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
 
 ```yaml

Docs/Start-ThreadRun.md

@@ -144,9 +144,8 @@ Position: Named
 
 
 ### -ReasoningEffort
-**o1 and o3-mini models only**  
 Constrains effort on reasoning for reasoning models.  
-Currently supported values are `low`, `medium`, and `high`.  
+Supported values are `none`, `low`, `medium`, and `high`.
 Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
 
 ```yaml

Public/Assistants/New-Assistant.ps1

@@ -47,8 +47,8 @@ function New-Assistant {
 
         [Parameter()]
         [Alias('reasoning_effort')]
-        [Completions('minimal', 'low', 'medium', 'high')]
-        [string]$ReasoningEffort = 'medium',
+        [Completions('none', 'minimal', 'low', 'medium', 'high')]
+        [string]$ReasoningEffort,
 
         [Parameter()]
         [switch]$UseCodeInterpreter,

Public/Assistants/Set-Assistant.ps1

@@ -48,8 +48,8 @@ function Set-Assistant {
 
         [Parameter()]
         [Alias('reasoning_effort')]
-        [Completions('minimal', 'low', 'medium', 'high')]
-        [string]$ReasoningEffort = 'medium',
+        [Completions('none', 'minimal', 'low', 'medium', 'high')]
+        [string]$ReasoningEffort,
 
         [Parameter()]
         [switch]$UseCodeInterpreter,

Public/Batch/Start-Batch.ps1

@@ -17,7 +17,8 @@ function Start-Batch {
             '/v1/responses',
             '/v1/chat/completions',
             '/v1/embeddings',
-            '/v1/completions'
+            '/v1/completions',
+            '/v1/moderations'
         )]
         [string][LowerCaseTransformation()]$Endpoint = '/v1/chat/completions',
 

Public/Chat/Request-ChatCompletion.ps1

@@ -165,8 +165,8 @@ function Request-ChatCompletion {
 
         [Parameter()]
         [Alias('reasoning_effort')]
-        [Completions('minimal', 'low', 'medium', 'high')]
-        [string]$ReasoningEffort = 'medium',
+        [Completions('none', 'minimal', 'low', 'medium', 'high')]
+        [string]$ReasoningEffort,
 
         [Parameter()]
         [System.Collections.IDictionary]$MetaData,

Public/Responses/Request-Response.ps1

@@ -385,7 +385,7 @@ function Request-Response {
 
         #region Reasoning
         [Parameter()]
-        [Completions('minimal', 'low', 'medium', 'high')]
+        [Completions('none', 'minimal', 'low', 'medium', 'high')]
         [string]$ReasoningEffort,
 
         [Parameter()]