From f8fb5ce172b1f173ea60936ec1ed7280d5f213b0 Mon Sep 17 00:00:00 2001
From: vikingowl <christian@nachtigall.dev>
Date: Sun, 4 Jan 2026 00:41:42 +0100
Subject: [PATCH] fix: keep processing indicator visible until LLM starts
 streaming

Clear 'Processing...' text only when first token arrives, not before
the LLM request. This keeps the indicator visible during prompt
resolution, RAG retrieval, and LLM initialization.
---
 .../src/lib/components/chat/ChatWindow.svelte    | 16 ++++++++++++----
 frontend/src/routes/+page.svelte                 | 16 ++++++++++++----
 2 files changed, 24 insertions(+), 8 deletions(-)

diff --git a/frontend/src/lib/components/chat/ChatWindow.svelte b/frontend/src/lib/components/chat/ChatWindow.svelte
index 160f350..3df5299 100644
--- a/frontend/src/lib/components/chat/ChatWindow.svelte
+++ b/frontend/src/lib/components/chat/ChatWindow.svelte
@@ -577,10 +577,8 @@
 		const assistantMessageId = existingMessageId || chatState.startStreaming();
 		abortController = new AbortController();
 
-		// Clear any existing content (e.g., "Processing..." text) before LLM starts streaming
-		if (existingMessageId) {
-			chatState.setStreamContent('');
-		}
+		// Track if we need to clear the "Processing..." text on first token
+		let needsClearOnFirstToken = !!existingMessageId;
 
 		// Start streaming metrics tracking
 		streamingMetricsState.startStream();
@@ -669,6 +667,11 @@
 				},
 				{
 					onThinkingToken: (token) => {
+						// Clear "Processing..." on first token
+						if (needsClearOnFirstToken) {
+							chatState.setStreamContent('');
+							needsClearOnFirstToken = false;
+						}
 						// Accumulate thinking and update the message
 						if (!streamingThinking) {
 							// Start the thinking block
@@ -680,6 +683,11 @@
 						streamingMetricsState.incrementTokens();
 					},
 					onToken: (token) => {
+						// Clear "Processing..." on first token
+						if (needsClearOnFirstToken) {
+							chatState.setStreamContent('');
+							needsClearOnFirstToken = false;
+						}
 						// Close thinking block when content starts
 						if (streamingThinking && !thinkingClosed) {
 							chatState.appendToStreaming('</think>\n\n');
diff --git a/frontend/src/routes/+page.svelte b/frontend/src/routes/+page.svelte
index 212d5ac..2d53211 100644
--- a/frontend/src/routes/+page.svelte
+++ b/frontend/src/routes/+page.svelte
@@ -234,10 +234,8 @@
 			assistantMessageId = chatState.startStreaming();
 		}
 
-		// Clear any existing content (e.g., "Processing..." text) before LLM starts streaming
-		if (hadProcessingMessage) {
-			chatState.setStreamContent('');
-		}
+		// Track if we need to clear the "Processing..." text on first token
+		let needsClearOnFirstToken = hadProcessingMessage;
 
 		// Start streaming metrics tracking
 		streamingMetricsState.startStream();
@@ -297,6 +295,11 @@
 				{ model: chatModel, messages, tools, think: useNativeThinking, options: settingsState.apiParameters },
 				{
 					onThinkingToken: (token) => {
+						// Clear "Processing..." on first token
+						if (needsClearOnFirstToken) {
+							chatState.setStreamContent('');
+							needsClearOnFirstToken = false;
+						}
 						// Accumulate thinking and update the message
 						if (!streamingThinking) {
 							// Start the thinking block
@@ -307,6 +310,11 @@
 						streamingMetricsState.incrementTokens();
 					},
 					onToken: (token) => {
+						// Clear "Processing..." on first token
+						if (needsClearOnFirstToken) {
+							chatState.setStreamContent('');
+							needsClearOnFirstToken = false;
+						}
 						// Close thinking block when content starts
 						if (streamingThinking && !thinkingClosed) {
 							chatState.appendToStreaming('</think>\n\n');