feat: add chat token usage indicator

Show a neutral token usage ring in ChatUI when the current model has context-window metadata.

dashboard/src/components/chat/Chat.vue

@@ -357,6 +357,7 @@
             :is-running="
               Boolean(currSessionId && isSessionRunning(currSessionId))
             "
+            :token-usage="tokenUsageIndicator"
             :session-id="currSessionId || null"
             :current-session="currentSession"
             :reply-to="chatInputReplyTarget"
@@ -440,6 +441,7 @@
             :is-running="
               Boolean(currSessionId && isSessionRunning(currSessionId))
             "
+            :token-usage="tokenUsageIndicator"
             :session-id="currSessionId || null"
             :current-session="currentSession"
             :reply-to="chatInputReplyTarget"
@@ -561,7 +563,7 @@ import {
   Sun,
   Trash2,
 } from "@lucide/vue";
-import { chatApi } from "@/api/v1";
+import { chatApi, providerApi } from "@/api/v1";
 import StyledMenu from "@/components/shared/StyledMenu.vue";
 import ProjectDialog, {
   type ProjectFormData,
@@ -597,6 +599,12 @@ import {
 } from "@/i18n/composables";
 import type { Locale } from "@/i18n/types";
 import { askForConfirmation, useConfirmDialog } from "@/utils/confirmDialog";
+import {
+  contextLimit,
+  formatTokenCount,
+  type ProviderModelMetadata,
+  type ProviderMetadataSource,
+} from "@/utils/providerMetadata";
 import { useToast } from "@/utils/toast";
 
 const props = withDefaults(defineProps<{ chatboxMode?: boolean; active?: boolean }>(), {
@@ -652,6 +660,11 @@ const {
 
 type WorkspaceView = "chat" | "providers";
 
+interface TokenProviderConfig extends ProviderMetadataSource {
+  id: string;
+  enable?: boolean;
+}
+
 const activeWorkspace = ref<WorkspaceView>("chat");
 const projectDialogOpen = ref(false);
 const editingProject = ref<Project | null>(null);
@@ -670,6 +683,9 @@ const projectSessionsById = ref<Record<string, Session[]>>({});
 const loadingProjectSessionIds = ref<string[]>([]);
 const loadingSessions = ref(false);
 const draft = ref("");
+const tokenProviderConfigs = ref<TokenProviderConfig[]>([]);
+const tokenModelMetadata = ref<Record<string, ProviderModelMetadata>>({});
+const selectedTokenProviderId = ref("");
 const messagesContainer = ref<HTMLElement | null>(null);
 const inputRef = ref<InstanceType<typeof ChatInput> | null>(null);
 const shouldStickToBottom = ref(true);
@@ -841,15 +857,58 @@ const chatInputReplyTarget = computed(() =>
         selectedText: replyPreview(replyTarget.value.id, ""),
       },
 );
+const currentTokenProvider = computed(() => {
+  const selectedProvider = tokenProviderConfigs.value.find(
+    (provider) => provider.id === selectedTokenProviderId.value,
+  );
+  return selectedProvider || tokenProviderConfigs.value[0] || null;
+});
+const currentTokenMetadata = computed(() => {
+  const model = currentTokenProvider.value?.model;
+  return model ? tokenModelMetadata.value[model] || null : null;
+});
+const latestTokenUsageTotal = computed(() => {
+  for (let index = activeMessages.value.length - 1; index >= 0; index -= 1) {
+    const message = activeMessages.value[index];
+    if (isUserMessage(message)) continue;
+    const usage = message.content?.agentStats?.token_usage;
+    if (!usage) continue;
+    return (
+      readTokenCount(usage.input_other) +
+      readTokenCount(usage.input_cached) +
+      readTokenCount(usage.output)
+    );
+  }
+  return 0;
+});
+const tokenUsageIndicator = computed(() => {
+  const used = latestTokenUsageTotal.value;
+  const limit = contextLimit(currentTokenProvider.value, currentTokenMetadata.value);
+  if (used <= 0 || limit <= 0) return null;
+
+  const percent = (used / limit) * 100;
+  return {
+    used,
+    limit,
+    percent: Math.min(100, Math.max(0, percent)),
+    tooltip: tm("tokenUsage.tooltip", {
+      used: formatTokenCount(used),
+      limit: formatTokenCount(limit),
+      percent: formatUsagePercent(percent),
+    }),
+  };
+});
 
 function getSelectedProviderSelection() {
   const inputSelection = inputRef.value?.getCurrentSelection();
   if (inputSelection?.providerId) {
+    selectedTokenProviderId.value = inputSelection.providerId;
     return inputSelection;
   }
   if (typeof window === "undefined") {
     return { providerId: "", modelName: "" };
   }
+  syncSelectedTokenProvider();
   return {
     providerId: localStorage.getItem("selectedProvider") || "",
     modelName: localStorage.getItem("selectedProviderModel") || "",
@@ -869,7 +928,7 @@ watch(
 onMounted(async () => {
   loadingSessions.value = true;
   try {
-    await Promise.all([getSessions(), getProjects()]);
+    await Promise.all([getSessions(), getProjects(), loadTokenProviders()]);
     const routeSessionId = getRouteSessionId();
     if (routeSessionId === "models") {
       activeWorkspace.value = "providers";
@@ -954,6 +1013,40 @@ function sessionTitle(session: Session) {
   return session.display_name?.trim() || tm("conversation.newConversation");
 }
 
+function syncSelectedTokenProvider() {
+  if (typeof window === "undefined") return;
+  selectedTokenProviderId.value = localStorage.getItem("selectedProvider") || "";
+}
+
+async function loadTokenProviders() {
+  syncSelectedTokenProvider();
+  try {
+    const response = await providerApi.listByProviderType("chat_completion");
+    if (response.data.status === "ok") {
+      tokenModelMetadata.value = (
+        (response.data as any).model_metadata || {}
+      ) as Record<string, ProviderModelMetadata>;
+      tokenProviderConfigs.value = (
+        (response.data.data || []) as unknown as TokenProviderConfig[]
+      ).filter((provider) => provider.enable !== false);
+    }
+  } catch (error) {
+    console.error("Failed to load provider context metadata:", error);
+  }
+}
+
+function readTokenCount(value: unknown) {
+  const count = Number(value || 0);
+  return Number.isFinite(count) && count > 0 ? count : 0;
+}
+
+function formatUsagePercent(value: number) {
+  if (!Number.isFinite(value) || value <= 0) return "0";
+  if (value >= 10) return String(Math.round(value));
+  if (value >= 1) return String(Math.round(value * 10) / 10);
+  return String(Math.round(value * 100) / 100);
+}
+
 async function startNewChat() {
   showChatWorkspace();
   selectedProjectId.value = null;

dashboard/src/components/chat/ChatInput.vue

@@ -242,6 +242,27 @@
             class="mr-1"
             width="1.5"
           />
+          <v-tooltip
+            v-if="tokenUsageVisible"
+            location="top"
+            max-width="320"
+          >
+            <template #activator="{ props: tokenTooltipProps }">
+              <span
+                v-bind="tokenTooltipProps"
+                class="token-usage-indicator"
+                :style="{ '--token-usage-color': tokenUsageColor }"
+              >
+                <v-progress-circular
+                  :model-value="tokenUsagePercent"
+                  size="24"
+                  width="2.5"
+                  class="token-usage-progress"
+                />
+              </span>
+            </template>
+            <span>{{ props.tokenUsage?.tooltip }}</span>
+          </v-tooltip>
           <!-- <v-btn @click="$emit('openLiveMode')"
                         icon
                         variant="text"
@@ -332,6 +353,13 @@ interface ReplyInfo {
   selectedText?: string;
 }
 
+interface TokenUsageInfo {
+  used: number;
+  limit: number;
+  percent: number;
+  tooltip: string;
+}
+
 interface Props {
   prompt: string;
   stagedImagesUrl: string[];
@@ -347,6 +375,7 @@ interface Props {
   replyTo?: ReplyInfo | null;
   sendShortcut?: "enter" | "shift_enter";
   showProviderSelector?: boolean;
+  tokenUsage?: TokenUsageInfo | null;
 }
 
 const props = withDefaults(defineProps<Props>(), {
@@ -357,6 +386,7 @@ const props = withDefaults(defineProps<Props>(), {
   replyTo: null,
   sendShortcut: "shift_enter",
   showProviderSelector: true,
+  tokenUsage: null,
 });
 
 const emit = defineEmits<{
@@ -569,6 +599,29 @@ function handleReplyAfterLeave() {
 
 const { mobile } = useDisplay();
 
+const tokenUsageVisible = computed(() => {
+  const usage = props.tokenUsage;
+  return Boolean(
+    usage &&
+      Number.isFinite(usage.used) &&
+      Number.isFinite(usage.limit) &&
+      usage.used > 0 &&
+      usage.limit > 0,
+  );
+});
+
+const tokenUsagePercent = computed(() => {
+  const percent = props.tokenUsage?.percent || 0;
+  if (!Number.isFinite(percent)) return 0;
+  return Math.min(100, Math.max(0, percent));
+});
+
+const tokenUsageColor = computed(() =>
+  isDark.value
+    ? "rgba(var(--v-theme-on-surface), 0.82)"
+    : "rgba(var(--v-theme-on-surface), 0.72)",
+);
+
 // Auto-resize textarea
 function autoResize() {
   const el = inputField.value;
@@ -996,6 +1049,31 @@ defineExpose({
   background: rgba(var(--v-theme-on-surface), 0.04) !important;
 }
 
+.token-usage-indicator {
+  width: 24px;
+  height: 24px;
+  display: inline-flex;
+  align-items: center;
+  justify-content: center;
+  flex: 0 0 24px;
+  border-radius: 50%;
+  color: var(--token-usage-color);
+}
+
+.token-usage-progress {
+  color: currentColor;
+}
+
+.token-usage-progress :deep(.v-progress-circular__underlay) {
+  color: rgba(var(--v-theme-on-surface), 0.18);
+  stroke: currentColor;
+  opacity: 0.24;
+}
+
+.token-usage-progress :deep(.v-progress-circular__overlay) {
+  stroke: currentColor;
+}
+
 .input-outline-control {
   width: 36px !important;
   height: 36px !important;

dashboard/src/i18n/locales/en-US/features/chat.json

@@ -156,6 +156,9 @@
     "duration": "Duration",
     "ttft": "Time to First Token"
   },
+  "tokenUsage": {
+    "tooltip": "{used} / {limit} tokens ({percent}%)"
+  },
   "refs": {
     "title": "References",
     "sources": "Sources"

dashboard/src/i18n/locales/ru-RU/features/chat.json

@@ -156,6 +156,9 @@
     "duration": "Время",
     "ttft": "Время до первого токена"
   },
+  "tokenUsage": {
+    "tooltip": "{used} / {limit} токенов ({percent}%)"
+  },
   "refs": {
     "title": "Ссылки",
     "sources": "Источники"

dashboard/src/i18n/locales/zh-CN/features/chat.json

@@ -156,6 +156,9 @@
     "duration": "耗时",
     "ttft": "首字时间"
   },
+  "tokenUsage": {
+    "tooltip": "{used} / {limit} tokens（{percent}%）"
+  },
   "refs": {
     "title": "引用",
     "sources": "来源"

dashboard/src/utils/providerMetadata.ts

@@ -19,15 +19,28 @@ export interface ProviderCapabilityBadge {
   tooltip: string
 }
 
+export function contextLimit(
+  provider: ProviderMetadataSource | null | undefined,
+  metadata?: ProviderModelMetadata | null
+): number {
+  const context = Number(metadata?.limit?.context || provider?.max_context_tokens || 0)
+  return Number.isFinite(context) && context > 0 ? context : 0
+}
+
+export function formatTokenCount(value: number): string {
+  if (!Number.isFinite(value)) return ''
+  const absValue = Math.abs(value)
+  if (absValue >= 1_000_000) return `${formatCompactNumber(value / 1_000_000)}M`
+  if (absValue >= 1_000) return `${formatCompactNumber(value / 1_000)}K`
+  return `${Math.round(value)}`
+}
+
 export function formatContextLimit(
   provider: ProviderMetadataSource | null | undefined,
   metadata?: ProviderModelMetadata | null
 ): string {
-  const context = metadata?.limit?.context || provider?.max_context_tokens
-  if (!context || typeof context !== 'number') return ''
-  if (context >= 1_000_000) return `${Math.round(context / 1_000_000)}M`
-  if (context >= 1_000) return `${Math.round(context / 1_000)}K`
-  return `${context}`
+  const context = contextLimit(provider, metadata)
+  return context ? formatTokenCount(context) : ''
 }
 
 export function providerCapabilityBadges(
@@ -81,3 +94,9 @@ export function providerCapabilityBadges(
           : tm('models.metadata.enabled', { capability: item.label })
     }))
 }
+
+function formatCompactNumber(value: number): string {
+  const absValue = Math.abs(value)
+  const rounded = absValue >= 10 ? Math.round(value) : Math.round(value * 10) / 10
+  return String(rounded).replace(/\.0$/, '')
+}