refactor: unify reasoning handling via backend reasoning_content, drop frontend tag parsing

- Updated the chat message component to surface backend-supplied reasoning via message.thinking while showing the raw assistant content without inline tag scrubbing
- Simplified chat streaming to append content chunks directly, stream reasoning into the message model, and persist any partial reasoning when generation stops
- Refactored the chat service SSE handler to rely on server-provided reasoning_content, removing legacy <think> parsing logic
- Refreshed Storybook data and streaming flows to populate the thinking field explicitly for static and streaming assistant messages

Author: ServeurpersoCom

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

@@ -1,7 +1,6 @@
 <script lang="ts">
 	import { getDeletionInfo } from '$lib/stores/chat.svelte';
 	import { copyToClipboard } from '$lib/utils/copy';
-	import { parseThinkingContent } from '$lib/utils/thinking';
 	import ChatMessageAssistant from './ChatMessageAssistant.svelte';
 	import ChatMessageUser from './ChatMessageUser.svelte';
 
@@ -47,25 +46,13 @@
 
 	let thinkingContent = $derived.by(() => {
 		if (message.role === 'assistant') {
-			if (message.thinking) {
-				return message.thinking;
-			}
-
-			const parsed = parseThinkingContent(message.content);
-
-			return parsed.thinking;
+			const trimmedThinking = message.thinking?.trim();
+			return trimmedThinking ? trimmedThinking : null;
 		}
 		return null;
 	});
 
-	let messageContent = $derived.by(() => {
-		if (message.role === 'assistant') {
-			const parsed = parseThinkingContent(message.content);
-			return parsed.cleanContent?.replace('<|channel|>analysis', '');
-		}
-
-		return message.content?.replace('<|channel|>analysis', '');
-	});
+	let messageContent = $derived.by(() => message.content);
 
 	function handleCancelEdit() {
 		isEditing = false;

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

@@ -256,10 +256,8 @@ export class ChatService {
 		}
 
 		const decoder = new TextDecoder();
-		let fullResponse = '';
+		let aggregatedContent = '';
 		let fullReasoningContent = '';
-		let regularContent = '';
-		let insideThinkTag = false;
 		let hasReceivedData = false;
 		let lastTimings: ChatMessageTimings | undefined;
 
@@ -277,7 +275,7 @@ export class ChatService {
 					if (line.startsWith('data: ')) {
 						const data = line.slice(6);
 						if (data === '[DONE]') {
-							if (!hasReceivedData && fullResponse.length === 0) {
+							if (!hasReceivedData && aggregatedContent.length === 0) {
 								const contextError = new Error(
 									'The request exceeds the available context size. Try increasing the context size or enable context shift.'
 								);
@@ -286,7 +284,7 @@ export class ChatService {
 								return;
 							}
 
-							onComplete?.(regularContent, fullReasoningContent || undefined, lastTimings);
+							onComplete?.(aggregatedContent, fullReasoningContent || undefined, lastTimings);
 
 							return;
 						}
@@ -308,44 +306,25 @@ export class ChatService {
 								}
 							}
 
-							if (content) {
-								hasReceivedData = true;
-								fullResponse += content;
-
-								// Track the regular content before processing this chunk
-								const regularContentBefore = regularContent;
-
-								// Process content character by character to handle think tags
-								insideThinkTag = this.processContentForThinkTags(
-									content,
-									insideThinkTag,
-									() => {
-										// Think content is ignored - we don't include it in API requests
-									},
-									(regularChunk) => {
-										regularContent += regularChunk;
-									}
-								);
-
-								const newRegularContent = regularContent.slice(regularContentBefore.length);
-								if (newRegularContent) {
-									onChunk?.(newRegularContent);
-								}
-							}
-
-							if (reasoningContent) {
-								hasReceivedData = true;
-								fullReasoningContent += reasoningContent;
-								onReasoningChunk?.(reasoningContent);
-							}
+                                                        if (content) {
+                                                                hasReceivedData = true;
+                                                                aggregatedContent += content;
+                                                                onChunk?.(content);
+                                                        }
+
+                                                        if (reasoningContent) {
+                                                                hasReceivedData = true;
+                                                                fullReasoningContent += reasoningContent;
+                                                                onReasoningChunk?.(reasoningContent);
+                                                        }
 						} catch (e) {
 							console.error('Error parsing JSON chunk:', e);
 						}
 					}
 				}
 			}
 
-			if (!hasReceivedData && fullResponse.length === 0) {
+			if (!hasReceivedData && aggregatedContent.length === 0) {
 				const contextError = new Error(
 					'The request exceeds the available context size. Try increasing the context size or enable context shift.'
 				);
@@ -552,51 +531,6 @@ export class ChatService {
 		}
 	}
 
-	/**
-	 * Processes content to separate thinking tags from regular content.
-	 * Parses <think> and </think> tags to route content to appropriate handlers.
-	 *
-	 * @param content - The content string to process
-	 * @param currentInsideThinkTag - Current state of whether we're inside a think tag
-	 * @param addThinkContent - Callback to handle content inside think tags
-	 * @param addRegularContent - Callback to handle regular content outside think tags
-	 * @returns Boolean indicating if we're still inside a think tag after processing
-	 * @private
-	 */
-	private processContentForThinkTags(
-		content: string,
-		currentInsideThinkTag: boolean,
-		addThinkContent: (chunk: string) => void,
-		addRegularContent: (chunk: string) => void
-	): boolean {
-		let i = 0;
-		let insideThinkTag = currentInsideThinkTag;
-
-		while (i < content.length) {
-			if (!insideThinkTag && content.substring(i, i + 7) === '<think>') {
-				insideThinkTag = true;
-				i += 7; // Skip the <think> tag
-				continue;
-			}
-
-			if (insideThinkTag && content.substring(i, i + 8) === '</think>') {
-				insideThinkTag = false;
-				i += 8; // Skip the </think> tag
-				continue;
-			}
-
-			if (insideThinkTag) {
-				addThinkContent(content[i]);
-			} else {
-				addRegularContent(content[i]);
-			}
-
-			i++;
-		}
-
-		return insideThinkTag;
-	}
-
 	/**
 	 * Aborts any ongoing chat completion request.
 	 * Cancels the current request and cleans up the abort controller.

tools/server/webui/src/lib/stores/chat.svelte.ts

@@ -5,7 +5,6 @@ import { config } from '$lib/stores/settings.svelte';
 import { filterByLeafNodeId, findLeafNode, findDescendantMessages } from '$lib/utils/branching';
 import { browser } from '$app/environment';
 import { goto } from '$app/navigation';
-import { extractPartialThinking } from '$lib/utils/thinking';
 
 /**
  * ChatStore - Central state management for chat conversations and AI interactions
@@ -341,12 +340,9 @@ class ChatStore {
 				streamedContent += chunk;
 				this.currentResponse = streamedContent;
 
-				captureModelIfNeeded();
-
-				const partialThinking = extractPartialThinking(streamedContent);
 				const messageIndex = this.findMessageIndex(assistantMessage.id);
 				this.updateMessageAtIndex(messageIndex, {
-					content: partialThinking.remainingContent || streamedContent
+					content: streamedContent
 				});
 			},
 
@@ -694,18 +690,18 @@ class ChatStore {
 
 		if (lastMessage && lastMessage.role === 'assistant') {
 			try {
-				const partialThinking = extractPartialThinking(this.currentResponse);
+				const contentToSave = this.currentResponse;
 
 				const updateData: {
 					content: string;
 					thinking?: string;
 					timings?: ChatMessageTimings;
 				} = {
-					content: partialThinking.remainingContent || this.currentResponse
+					content: contentToSave
 				};
 
-				if (partialThinking.thinking) {
-					updateData.thinking = partialThinking.thinking;
+				if (lastMessage.thinking?.trim()) {
+					updateData.thinking = lastMessage.thinking;
 				}
 
 				const lastKnownState = await slotsService.getCurrentState();
@@ -725,7 +721,10 @@ class ChatStore {
 
 				await DatabaseStore.updateMessage(lastMessage.id, updateData);
 
-				lastMessage.content = partialThinking.remainingContent || this.currentResponse;
+				lastMessage.content = contentToSave;
+				if (updateData.thinking !== undefined) {
+					lastMessage.thinking = updateData.thinking;
+				}
 				if (updateData.timings) {
 					lastMessage.timings = updateData.timings;
 				}