fix(desktop): show the real effort on the composer pill

The pill hardcoded 'Med' whenever the surface had no explicit effort, so
a profile configured for high advertised a level the agent would not
use. Take the profile default as a fallback and drop the now-unused
shell.modelMenu.medium key across the locales.

apps/desktop/src/app/chat/composer/model-pill.tsx

@@ -11,7 +11,7 @@ import { useI18n } from '@/i18n'
 import { ChevronDown } from '@/lib/icons'
 import { formatModelStatusLabel } from '@/lib/model-status-label'
 import { cn } from '@/lib/utils'
-import { $currentModelSource, setModelPickerOpen } from '@/store/session'
+import { $currentModelSource, $defaultReasoningEffort, setModelPickerOpen } from '@/store/session'
 
 import type { ChatBarState } from './types'
 
@@ -48,6 +48,7 @@ export function ModelPill({
   const fastMode = useStore(view.$fast)
   const reasoningEffort = useStore(view.$reasoningEffort)
   const modelSource = useStore($currentModelSource)
+  const defaultEffort = useStore($defaultReasoningEffort)
   const runtimeId = useStore(view.$runtimeId)
   const [open, setOpen] = useState(false)
 
@@ -68,7 +69,9 @@ export function ModelPill({
   ) : (
     <>
       {currentModel.trim() ? (
-        <span className="truncate">{formatModelStatusLabel(currentModel, { fastMode, reasoningEffort })}</span>
+        <span className="truncate">
+          {formatModelStatusLabel(currentModel, { defaultEffort, fastMode, reasoningEffort })}
+        </span>
       ) : (
         <GlyphSpinner className="opacity-50" spinner="braille" />
       )}

apps/desktop/src/i18n/ar.ts

@@ -1986,8 +1986,7 @@ export const ar = defineLocale({
       noModels: 'لا توجد نماذج',
       editModels: 'تحرير النماذج',
       refreshModels: 'تحديث النماذج',
-      fast: 'سريع',
-      medium: 'متوسط'
+      fast: 'سريع'
     },
     modelOptions: {
       noOptions: 'لا توجد خيارات لهذا النموذج',

apps/desktop/src/i18n/en.ts

@@ -2306,8 +2306,7 @@ export const en: Translations = {
       noModels: 'No models found',
       editModels: 'Edit Models…',
       refreshModels: 'Refresh Models',
-      fast: 'Fast',
-      medium: 'Med'
+      fast: 'Fast'
     },
     modelOptions: {
       noOptions: 'No options for this model',

apps/desktop/src/i18n/ja.ts

@@ -2178,8 +2178,7 @@ export const ja = defineLocale({
       noModels: 'モデルが見つかりません',
       editModels: 'モデルを編集…',
       refreshModels: 'モデルを更新',
-      fast: '高速',
-      medium: '中'
+      fast: '高速'
     },
     modelOptions: {
       noOptions: 'このモデルにはオプションがありません',

apps/desktop/src/i18n/types.ts

@@ -1915,7 +1915,6 @@ export interface Translations {
       editModels: string
       refreshModels: string
       fast: string
-      medium: string
     }
     modelOptions: {
       noOptions: string

apps/desktop/src/i18n/zh-hant.ts

@@ -2105,8 +2105,7 @@ export const zhHant = defineLocale({
       noModels: '找不到模型',
       editModels: '編輯模型…',
       refreshModels: '重新整理模型',
-      fast: '快速',
-      medium: '中'
+      fast: '快速'
     },
     modelOptions: {
       noOptions: '此模型沒有可用選項',

apps/desktop/src/i18n/zh.ts

@@ -2483,8 +2483,7 @@ export const zh: Translations = {
       noModels: '未找到模型',
       editModels: '编辑模型…',
       refreshModels: '刷新模型',
-      fast: '快速',
-      medium: '中'
+      fast: '快速'
     },
     modelOptions: {
       noOptions: '此模型没有可用选项',

apps/desktop/src/lib/model-status-label.test.ts

@@ -34,9 +34,16 @@ describe('model-status-label', () => {
     )
   })
 
-  it('always surfaces the effort (default medium) so the level is visible', () => {
+  it('falls back to the profile default effort, then to medium', () => {
     expect(formatModelStatusLabel('openai/gpt-5.5', { reasoningEffort: 'medium' })).toBe('GPT-5.5 · Med')
     expect(formatModelStatusLabel('openai/gpt-5.5')).toBe('GPT-5.5 · Med')
+    // No session-level effort → the configured profile default is advertised,
+    // not Hermes' built-in medium.
+    expect(formatModelStatusLabel('openai/gpt-5.5', { defaultEffort: 'high' })).toBe('GPT-5.5 · High')
+    // An explicit session effort still wins over the profile default.
+    expect(formatModelStatusLabel('openai/gpt-5.5', { defaultEffort: 'high', reasoningEffort: 'low' })).toBe(
+      'GPT-5.5 · Low'
+    )
   })
 
   it('returns just the placeholder name when there is no model', () => {

apps/desktop/src/lib/model-status-label.ts

@@ -99,10 +99,12 @@ export function displayModelName(model: string): string {
   return modelDisplayParts(model).name
 }
 
-/** Status bar trigger label — model name plus the live session state (effort/fast). */
+/** Status bar trigger label — model name plus the live session state (effort/fast).
+ *  `defaultEffort` is the profile's configured level, used when the surface has
+ *  no explicit effort so the label never advertises a default the agent won't use. */
 export function formatModelStatusLabel(
   model: string,
-  options?: { fastMode?: boolean; reasoningEffort?: string }
+  options?: { defaultEffort?: string; fastMode?: boolean; reasoningEffort?: string }
 ): string {
   const name = displayModelName(model)
 
@@ -118,9 +120,9 @@ export function formatModelStatusLabel(
     parts.push('Fast')
   }
 
-  // Always surface the effort (empty = Hermes default of medium) so the
-  // current reasoning level is visible at a glance, not just when non-default.
-  parts.push(reasoningEffortLabel(options?.reasoningEffort ?? '') || 'Med')
+  // Always surface the effort so the current reasoning level is visible at a
+  // glance, not just when non-default.
+  parts.push(reasoningEffortLabel(options?.reasoningEffort || options?.defaultEffort || 'medium'))
 
   return `${name} · ${parts.join(' ')}`
 }