🌊 feat: Add Disable Streaming Toggle (#8177)

* 🌊 feat: Add Disable Streaming Option in Configuration

- Introduced a new setting to disable streaming responses in openAI, Azure, and custom endpoint parameter panels.
- Updated translation files to include labels and descriptions for the disable streaming feature.
- Modified relevant schemas and parameter settings to support the new disable streaming functionality.

* 🔧 fix: disableStreaming state not persisting when returning to a conversation

- Added disableStreaming field to the IPreset interface and conversationPreset.
- Moved toggles and sliders around for nicer left-right UI split in parameters panel.
- Removed old reference to 'grounding' ub conversationPreset (now web_search) and added web_search to IPreset.

client/src/locales/en/translation.json

@@ -231,6 +231,7 @@
   "com_endpoint_openai_reasoning_summary": "Responses API only: A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. Set to none,auto, concise, or detailed.",
   "com_endpoint_openai_resend": "Resend all previously attached images. Note: this can significantly increase token cost and you may experience errors with many image attachments.",
   "com_endpoint_openai_resend_files": "Resend all previously attached files. Note: this will increase token cost and you may experience errors with many attachments.",
+  "com_endpoint_disable_streaming": "Disable streaming responses and receive the complete response at once. Useful for models like o3 that require organization verification for streaming",
   "com_endpoint_openai_stop": "Up to 4 sequences where the API will stop generating further tokens.",
   "com_endpoint_openai_temp": "Higher values = more random, while lower values = more focused and deterministic. We recommend altering this or Top P but not both.",
   "com_endpoint_openai_topp": "An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We recommend altering this or temperature but not both.",
@@ -239,6 +240,7 @@
   "com_endpoint_output": "Output",
   "com_endpoint_plug_image_detail": "Image Detail",
   "com_endpoint_plug_resend_files": "Resend Files",
+  "com_endpoint_disable_streaming_label": "Disable Streaming",
   "com_endpoint_plug_set_custom_instructions_for_gpt_placeholder": "Set custom instructions to include in System Message. Default: none",
   "com_endpoint_plug_skip_completion": "Skip Completion",
   "com_endpoint_plug_use_functions": "Use Functions",

packages/data-provider/src/parameterSettings.ts

@@ -284,6 +284,19 @@ const openAIParams: Record<string, SettingDefinition> = {
     optionType: 'model',
     columnSpan: 4,
   },
+  disableStreaming: {
+    key: 'disableStreaming',
+    label: 'com_endpoint_disable_streaming_label',
+    labelCode: true,
+    description: 'com_endpoint_disable_streaming',
+    descriptionCode: true,
+    type: 'boolean',
+    default: false,
+    component: 'switch',
+    optionType: 'model',
+    showDefault: false,
+    columnSpan: 2,
+  } as const,
 };
 
 const anthropic: Record<string, SettingDefinition> = {
@@ -626,6 +639,7 @@ const openAI: SettingsConfiguration = [
   openAIParams.reasoning_effort,
   openAIParams.useResponsesApi,
   openAIParams.reasoning_summary,
+  openAIParams.disableStreaming,
 ];
 
 const openAICol1: SettingsConfiguration = [
@@ -648,6 +662,7 @@ const openAICol2: SettingsConfiguration = [
   openAIParams.reasoning_summary,
   openAIParams.useResponsesApi,
   openAIParams.web_search,
+  openAIParams.disableStreaming,
 ];
 
 const anthropicConfig: SettingsConfiguration = [

packages/data-provider/src/schemas.ts

@@ -639,6 +639,8 @@ export const tConversationSchema = z.object({
   useResponsesApi: z.boolean().optional(),
   /* OpenAI Responses API / Anthropic API / Google API */
   web_search: z.boolean().optional(),
+  /* disable streaming */
+  disableStreaming: z.boolean().optional(),
   /* assistant */
   assistant_id: z.string().optional(),
   /* agents */
@@ -743,6 +745,8 @@ export const tQueryParamsSchema = tConversationSchema
     useResponsesApi: true,
     /** @endpoints openAI, anthropic, google */
     web_search: true,
+    /** @endpoints openAI, custom, azureOpenAI */
+    disableStreaming: true,
     /** @endpoints google, anthropic, bedrock */
     topP: true,
     /** @endpoints google, anthropic */
@@ -1075,6 +1079,7 @@ export const openAIBaseSchema = tConversationSchema.pick({
   reasoning_summary: true,
   useResponsesApi: true,
   web_search: true,
+  disableStreaming: true,
 });
 
 export const openAISchema = openAIBaseSchema

packages/data-schemas/src/schema/defaults.ts

@@ -134,12 +134,11 @@ export const conversationPreset = {
   useResponsesApi: {
     type: Boolean,
   },
-  /** OpenAI Responses API / Anthropic API */
+  /** OpenAI Responses API / Anthropic API / Google API */
   web_search: {
     type: Boolean,
   },
-  /** Google */
+  disableStreaming: {
-  grounding: {
     type: Boolean,
   },
   /** Reasoning models only */

packages/data-schemas/src/schema/preset.ts

@@ -48,6 +48,8 @@ export interface IPreset extends Document {
   reasoning_effort?: string;
   reasoning_summary?: string;
   useResponsesApi?: boolean;
+  web_search?: boolean;
+  disableStreaming?: boolean;
   // end of additional fields
   agentOptions?: unknown;
 }

packages/data-schemas/src/types/convo.ts

@@ -48,6 +48,7 @@ export interface IConversation extends Document {
   reasoning_summary?: string;
   useResponsesApi?: boolean;
   web_search?: boolean;
+  disableStreaming?: boolean;
   // Additional fields
   files?: string[];
   expiredAt?: Date;