debug: say goodbye to curl -N, hello one-click raw stream

- adds a new checkbox in the WebUI to display raw LLM output without backend parsing or frontend Markdown rendering

Author: ServeurpersoCom

tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageAssistant.svelte

@@ -131,7 +131,11 @@
 			</div>
 		</div>
 	{:else if message.role === 'assistant'}
-		<MarkdownContent content={messageContent || ''} />
+		{#if config().disableReasoningFormat}
+			<pre class="raw-output">{messageContent || ''}</pre>
+		{:else}
+			<MarkdownContent content={messageContent || ''} />
+		{/if}
 	{:else}
 		<div class="text-sm whitespace-pre-wrap">
 			{messageContent}
@@ -203,4 +207,22 @@
 			background-position: -200% 0;
 		}
 	}
+
+	.raw-output {
+		width: 100%;
+		max-width: 48rem;
+		margin-top: 1.5rem;
+		padding: 1rem 1.25rem;
+		border-radius: 1rem;
+		background: hsl(var(--muted) / 0.3);
+		color: var(--foreground);
+		font-family:
+			ui-monospace, SFMono-Regular, 'SF Mono', Monaco, 'Cascadia Code', 'Roboto Mono', Consolas,
+			'Liberation Mono', Menlo, monospace;
+		font-size: 0.875rem;
+		line-height: 1.6;
+		white-space: pre-wrap;
+		word-break: break-word;
+	}
+
 </style>

tools/server/webui/src/lib/components/app/chat/ChatSettings/ChatSettingsDialog.svelte

@@ -148,6 +148,11 @@
 					key: 'showThoughtInProgress',
 					label: 'Show thought in progress',
 					type: 'checkbox'
+				},
+				{
+					key: 'disableReasoningFormat',
+					label: 'Show raw LLM output without backend parsing and frontend Markdown rendering to inspect streaming across different models.',
+					type: 'checkbox'
 				}
 			]
 		},

tools/server/webui/src/lib/constants/settings-config.ts

@@ -6,6 +6,7 @@ export const SETTING_CONFIG_DEFAULT: Record<string, string | number | boolean> =
 	theme: 'system',
 	showTokensPerSecond: false,
 	showThoughtInProgress: false,
+	disableReasoningFormat: false,
 	keepStatsVisible: false,
 	askForTitleConfirmation: false,
 	pasteLongTextToFileLen: 2500,
@@ -76,6 +77,8 @@ export const SETTING_CONFIG_INFO: Record<string, string> = {
 	custom: 'Custom JSON parameters to send to the API. Must be valid JSON format.',
 	showTokensPerSecond: 'Display generation speed in tokens per second during streaming.',
 	showThoughtInProgress: 'Expand thought process by default when generating messages.',
+	disableReasoningFormat:
+		'Show raw LLM output without backend parsing and frontend Markdown rendering to inspect streaming across different models.',
 	keepStatsVisible: 'Keep processing statistics visible after generation finishes.',
 	askForTitleConfirmation:
 		'Ask for confirmation before automatically changing conversation title when editing the first message.',

tools/server/webui/src/lib/services/chat.ts

@@ -79,6 +79,8 @@ export class ChatService {
 			timings_per_token
 		} = options;
 
+		const currentConfig = config();
+
 		// Cancel any ongoing request and create a new abort controller
 		this.abort();
 		this.abortController = new AbortController();
@@ -123,7 +125,7 @@ export class ChatService {
 			requestBody.model = activeModel;
 		}
 
-		requestBody.reasoning_format = 'auto';
+		requestBody.reasoning_format = currentConfig.disableReasoningFormat ? 'none' : 'auto';
 
 		if (temperature !== undefined) requestBody.temperature = temperature;
 		// Set max_tokens to -1 (infinite) if not provided or empty
@@ -167,7 +169,6 @@ export class ChatService {
 		}
 
 		try {
-			const currentConfig = config();
 			const apiKey = currentConfig.apiKey?.toString().trim();
 
 			const response = await fetch(`./v1/chat/completions`, {