Merge branch 'ggml-org:master' into mradermacher

Author: nicoboss

.github/workflows/docker.yml

@@ -89,12 +89,15 @@ jobs:
               TYPE="-${{ matrix.config.tag }}"
           fi
           PREFIX="ghcr.io/${REPO_OWNER}/${REPO_NAME}:"
+          CACHETAGS="${PREFIX}buildcache${TYPE}"
           FULLTAGS="${PREFIX}full${TYPE},${PREFIX}full${TYPE}-${{ steps.srctag.outputs.name }}"
           LIGHTTAGS="${PREFIX}light${TYPE},${PREFIX}light${TYPE}-${{ steps.srctag.outputs.name }}"
           SERVERTAGS="${PREFIX}server${TYPE},${PREFIX}server${TYPE}-${{ steps.srctag.outputs.name }}"
+          echo "cache_output_tags=$CACHETAGS" >> $GITHUB_OUTPUT
           echo "full_output_tags=$FULLTAGS" >> $GITHUB_OUTPUT
           echo "light_output_tags=$LIGHTTAGS" >> $GITHUB_OUTPUT
           echo "server_output_tags=$SERVERTAGS" >> $GITHUB_OUTPUT
+          echo "cache_output_tags=$CACHETAGS"  # print out for debugging
           echo "full_output_tags=$FULLTAGS"  # print out for debugging
           echo "light_output_tags=$LIGHTTAGS"  # print out for debugging
           echo "server_output_tags=$SERVERTAGS"  # print out for debugging
@@ -131,11 +134,14 @@ jobs:
           target: full
           provenance: false
           # using github experimental cache
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
+          #cache-from: type=gha
+          #cache-to: type=gha,mode=max
           # return to this if the experimental github cache is having issues
           #cache-to: type=local,dest=/tmp/.buildx-cache
           #cache-from: type=local,src=/tmp/.buildx-cache
+          # using registry cache (no storage limit)
+          cache-from: type=registry,ref=${{ steps.tag.outputs.cache_output_tags }}
+          cache-to: type=registry,ref=${{ steps.tag.outputs.cache_output_tags }},mode=max
 
       - name: Build and push Light Docker image (tagged + versioned)
         if: ${{ (github.event_name == 'push' || github.event_name == 'schedule' || github.event_name == 'workflow_dispatch') && matrix.config.light == true }}
@@ -150,11 +156,14 @@ jobs:
           target: light
           provenance: false
           # using github experimental cache
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
+          #cache-from: type=gha
+          #cache-to: type=gha,mode=max
           # return to this if the experimental github cache is having issues
           #cache-to: type=local,dest=/tmp/.buildx-cache
           #cache-from: type=local,src=/tmp/.buildx-cache
+          # using registry cache (no storage limit)
+          cache-from: type=registry,ref=${{ steps.tag.outputs.cache_output_tags }}
+          cache-to: type=registry,ref=${{ steps.tag.outputs.cache_output_tags }},mode=max
 
       - name: Build and push Server Docker image (tagged + versioned)
         if: ${{ (github.event_name == 'push' || github.event_name == 'schedule' || github.event_name == 'workflow_dispatch') && matrix.config.server == true }}
@@ -169,11 +178,14 @@ jobs:
           target: server
           provenance: false
           # using github experimental cache
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
+          #cache-from: type=gha
+          #cache-to: type=gha,mode=max
           # return to this if the experimental github cache is having issues
           #cache-to: type=local,dest=/tmp/.buildx-cache
           #cache-from: type=local,src=/tmp/.buildx-cache
+          # using registry cache (no storage limit)
+          cache-from: type=registry,ref=${{ steps.tag.outputs.cache_output_tags }}
+          cache-to: type=registry,ref=${{ steps.tag.outputs.cache_output_tags }},mode=max
 
   create_tag:
     name: Create and push git tag

tools/server/public/index.html.gz

@@ -3,12 +3,14 @@
 	import { useProcessingState } from '$lib/hooks/use-processing-state.svelte';
 	import { isLoading } from '$lib/stores/chat.svelte';
 	import { fade } from 'svelte/transition';
-	import { Check, X } from '@lucide/svelte';
+	import { Check, Copy, Package, X } from '@lucide/svelte';
 	import { Button } from '$lib/components/ui/button';
 	import { Checkbox } from '$lib/components/ui/checkbox';
 	import { INPUT_CLASSES } from '$lib/constants/input-classes';
 	import ChatMessageActions from './ChatMessageActions.svelte';
 	import Label from '$lib/components/ui/label/label.svelte';
+	import { config } from '$lib/stores/settings.svelte';
+	import { copyToClipboard } from '$lib/utils/copy';
 
 	interface Props {
 		class?: string;
@@ -136,6 +138,23 @@
 		</div>
 	{/if}
 
+	{#if config().showModelInfo && message.model}
+		<span class="mt-6 mb-4 inline-flex items-center gap-1 text-xs text-muted-foreground">
+			<Package class="h-3.5 w-3.5" />
+
+			<span>Model used:</span>
+
+			<button
+				class="inline-flex cursor-pointer items-center gap-1 rounded-sm bg-muted-foreground/15 px-1.5 py-0.75"
+				onclick={() => copyToClipboard(message.model)}
+			>
+				{message.model}
+
+				<Copy class="ml-1 h-3 w-3 " />
+			</button>
+		</span>
+	{/if}
+
 	{#if message.timestamp && !isEditing}
 		<ChatMessageActions
 			role="assistant"

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

@@ -75,6 +75,11 @@
 					key: 'pdfAsImage',
 					label: 'Parse PDF as image',
 					type: 'checkbox'
+				},
+				{
+					key: 'showModelInfo',
+					label: 'Show model information',
+					type: 'checkbox'
 				}
 			]
 		},

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

@@ -34,7 +34,7 @@
 			{size}
 			{disabled}
 			{onclick}
-			class="h-6 w-6 p-0 {className}"
+			class="h-6 w-6 p-0 {className} flex"
 			aria-label={ariaLabel || tooltip}
 		>
 			{@const IconComponent = icon}

tools/server/webui/src/lib/components/app/misc/ActionButton.svelte

@@ -10,6 +10,7 @@ export const SETTING_CONFIG_DEFAULT: Record<string, string | number | boolean> =
 	askForTitleConfirmation: false,
 	pasteLongTextToFileLen: 2500,
 	pdfAsImage: false,
+	showModelInfo: false,
 	// make sure these default values are in sync with `common.h`
 	samplers: 'top_k;typ_p;top_p;min_p;temperature',
 	temperature: 0.8,
@@ -79,6 +80,7 @@ export const SETTING_CONFIG_INFO: Record<string, string> = {
 	askForTitleConfirmation:
 		'Ask for confirmation before automatically changing conversation title when editing the first message.',
 	pdfAsImage: 'Parse PDF as image instead of text (requires vision-capable model).',
+	showModelInfo: 'Display the model name used to generate each message below the message content.',
 	pyInterpreterEnabled:
 		'Enable Python interpreter using Pyodide. Allows running Python code in markdown code blocks.'
 };

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

@@ -353,7 +353,6 @@ class ChatStore {
 
 				await DatabaseStore.updateCurrentNode(this.activeConversation!.id, assistantMessage.id);
 				this.activeConversation!.currNode = assistantMessage.id;
-
 				await this.refreshActiveMessages();
 
 				if (onComplete) {
@@ -479,6 +478,9 @@ class ChatStore {
 	private async createAssistantMessage(parentId?: string): Promise<DatabaseMessage | null> {
 		if (!this.activeConversation) return null;
 
+		// Capture the current model name when creating the assistant message
+		const currentModelName = serverStore.modelName;
+
 		return await DatabaseStore.createMessageBranch(
 			{
 				convId: this.activeConversation.id,
@@ -487,7 +489,8 @@ class ChatStore {
 				content: '',
 				timestamp: Date.now(),
 				thinking: '',
-				children: []
+				children: [],
+				model: currentModelName || undefined
 			},
 			parentId || null
 		);
@@ -1138,7 +1141,8 @@ class ChatStore {
 						role: messageToEdit.role,
 						content: newContent,
 						thinking: messageToEdit.thinking || '',
-						children: []
+						children: [],
+						model: messageToEdit.model // Preserve original model info when branching
 					},
 					messageToEdit.parent!
 				);
@@ -1213,7 +1217,8 @@ class ChatStore {
 					content: newContent,
 					thinking: messageToEdit.thinking || '',
 					children: [],
-					extra: messageToEdit.extra ? JSON.parse(JSON.stringify(messageToEdit.extra)) : undefined
+					extra: messageToEdit.extra ? JSON.parse(JSON.stringify(messageToEdit.extra)) : undefined,
+					model: messageToEdit.model // Preserve original model info when branching
 				},
 				parentId
 			);
@@ -1274,6 +1279,9 @@ class ChatStore {
 			this.isLoading = true;
 			this.currentResponse = '';
 
+			// Capture the current model name when creating the assistant message
+			const currentModelName = serverStore.modelName;
+
 			const newAssistantMessage = await DatabaseStore.createMessageBranch(
 				{
 					convId: this.activeConversation.id,
@@ -1282,7 +1290,8 @@ class ChatStore {
 					role: 'assistant',
 					content: '',
 					thinking: '',
-					children: []
+					children: [],
+					model: currentModelName || undefined
 				},
 				parentMessage.id
 			);
@@ -1329,6 +1338,9 @@ class ChatStore {
 				false
 			) as DatabaseMessage[];
 
+			// Capture the current model name when creating the assistant message
+			const currentModelName = serverStore.modelName;
+
 			// Create new assistant message branch
 			const assistantMessage = await DatabaseStore.createMessageBranch(
 				{
@@ -1338,7 +1350,8 @@ class ChatStore {
 					role: 'assistant',
 					content: '',
 					thinking: '',
-					children: []
+					children: [],
+					model: currentModelName || undefined
 				},
 				userMessageId
 			);

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

@@ -52,4 +52,5 @@ export interface DatabaseMessage {
 	children: string[];
 	extra?: DatabaseMessageExtra[];
 	timings?: ChatMessageTimings;
+	model?: string;
 }