diff --git a/apps/desktop/src/app/desktop-controller.tsx b/apps/desktop/src/app/desktop-controller.tsx
index e071a2a0ce6..45251ceef9b 100644
--- a/apps/desktop/src/app/desktop-controller.tsx
+++ b/apps/desktop/src/app/desktop-controller.tsx
@@ -711,7 +711,9 @@ export function DesktopController() {
     }
 
     lastGatewayProfileRef.current = activeGatewayProfile
-    void refreshCurrentModel()
+    // Force: the new profile has its own default, so reseed even if the composer
+    // already shows the previous profile's model.
+    void refreshCurrentModel(true)
     void refreshActiveProfile()
   }, [activeGatewayProfile, refreshCurrentModel])
 
diff --git a/apps/desktop/src/app/session/hooks/use-model-controls.test.tsx b/apps/desktop/src/app/session/hooks/use-model-controls.test.tsx
index 612290800e0..f7765de04c5 100644
--- a/apps/desktop/src/app/session/hooks/use-model-controls.test.tsx
+++ b/apps/desktop/src/app/session/hooks/use-model-controls.test.tsx
@@ -130,7 +130,6 @@ describe('useModelControls', () => {
     await expect(
       controls.selectModel({
         model: 'claude-sonnet-4.6',
-        persistGlobal: false,
         provider: 'anthropic'
       })
     ).resolves.toBe(true)
@@ -143,26 +142,57 @@ describe('useModelControls', () => {
     expect(requestGateway).not.toHaveBeenCalledWith('slash.exec', expect.anything())
   })
 
-  it('keeps the global path on setGlobalModel when there is no active session', async () => {
-    setGlobalModel.mockResolvedValue(undefined)
+  it('stores a no-session pick as UI state with no gateway or global write', async () => {
+    const requestGateway = vi.fn()
     let controls!: Controls
 
     render(
       <Harness
         activeSessionId={null}
         onReady={value => (controls = value)}
-        requestGateway={vi.fn()}
+        requestGateway={requestGateway}
       />
     )
 
     await expect(
       controls.selectModel({
         model: 'claude-sonnet-4.6',
-        persistGlobal: false,
         provider: 'anthropic'
       })
     ).resolves.toBe(true)
 
-    expect(setGlobalModel).toHaveBeenCalledWith('anthropic', 'claude-sonnet-4.6')
+    // The pick is plain UI state; session.create ships it later. Nothing touches
+    // the gateway or the profile default here.
+    expect($currentModel.get()).toBe('claude-sonnet-4.6')
+    expect($currentProvider.get()).toBe('anthropic')
+    expect(requestGateway).not.toHaveBeenCalled()
+    expect(setGlobalModel).not.toHaveBeenCalled()
+  })
+
+  it('seeds an empty composer model from global but never clobbers a pick', async () => {
+    vi.mocked(getGlobalModelInfo).mockResolvedValue({ model: 'openai/gpt-5.5', provider: 'openai-codex' })
+
+    const { result } = renderHook(() =>
+      useModelControls({
+        activeSessionId: null,
+        queryClient: new QueryClient(),
+        requestGateway: vi.fn()
+      })
+    )
+
+    // Empty → seeds the default.
+    await result.current.refreshCurrentModel()
+    expect($currentModel.get()).toBe('openai/gpt-5.5')
+
+    // A user pick must survive the lifecycle refreshes that fire on boot / fresh
+    // draft / session events.
+    setCurrentModel('anthropic/claude-sonnet-4.6')
+    setCurrentProvider('anthropic')
+    await result.current.refreshCurrentModel()
+    expect($currentModel.get()).toBe('anthropic/claude-sonnet-4.6')
+
+    // A profile swap forces a reseed to the new profile's default.
+    await result.current.refreshCurrentModel(true)
+    expect($currentModel.get()).toBe('openai/gpt-5.5')
   })
 })
diff --git a/apps/desktop/src/app/session/hooks/use-model-controls.ts b/apps/desktop/src/app/session/hooks/use-model-controls.ts
index 681eac871a2..50788b1e0be 100644
--- a/apps/desktop/src/app/session/hooks/use-model-controls.ts
+++ b/apps/desktop/src/app/session/hooks/use-model-controls.ts
@@ -1,7 +1,7 @@
 import { type QueryClient } from '@tanstack/react-query'
 import { useCallback } from 'react'
 
-import { getGlobalModelInfo, setGlobalModel } from '@/hermes'
+import { getGlobalModelInfo } from '@/hermes'
 import { useI18n } from '@/i18n'
 import { notifyError } from '@/store/notifications'
 import {
@@ -15,7 +15,6 @@ import type { ModelOptionsResponse } from '@/types/hermes'
 
 interface ModelSelection {
   model: string
-  persistGlobal: boolean
   provider: string
 }
 
@@ -28,6 +27,7 @@ interface ModelControlsOptions {
 export function useModelControls({ activeSessionId, queryClient, requestGateway }: ModelControlsOptions) {
   const { t } = useI18n()
   const copy = t.desktop
+
   const updateModelOptionsCache = useCallback(
     (provider: string, model: string, includeGlobal: boolean) => {
       const patch = (prev: ModelOptionsResponse | undefined) => ({ ...(prev ?? {}), provider, model })
@@ -41,14 +41,24 @@ export function useModelControls({ activeSessionId, queryClient, requestGateway
     [activeSessionId, queryClient]
   )
 
-  const refreshCurrentModel = useCallback(async () => {
+  // Seed the composer's model state from the profile default. `force` reseeds
+  // for a profile swap (the new profile has its own default); otherwise this
+  // only fills an EMPTY selection so a user's pick (plain UI state in
+  // $currentModel) survives the lifecycle refreshes that fire on boot / fresh
+  // draft / session events. A live session owns the footer, so skip entirely.
+  const refreshCurrentModel = useCallback(async (force = false) => {
     try {
+      if ($activeSessionId.get()) {
+        return
+      }
+
+      if (!force && $currentModel.get()) {
+        return
+      }
+
       const result = await getGlobalModelInfo()
 
-      // A resumed/live session owns the footer model state. Global config
-      // refreshes (gateway boot, profile swap, settings save) must not clobber
-      // the active chat's runtime model/provider in the status bar.
-      if ($activeSessionId.get()) {
+      if ($activeSessionId.get() || (!force && $currentModel.get())) {
         return
       }
 
@@ -64,12 +74,14 @@ export function useModelControls({ activeSessionId, queryClient, requestGateway
     }
   }, [])
 
-  // Returns whether the switch succeeded so callers can await it before
-  // applying follow-up changes (e.g. editing a model's reasoning/fast must land
-  // on the right active model — bail rather than write to the previous one).
+  // Returns whether the switch succeeded so callers can await it before applying
+  // follow-up changes. The composer model is plain UI state: with no live
+  // session it's just stored (and shipped on the next session.create); with one
+  // it's scoped to that session via config.set. It NEVER writes the profile
+  // default — that lives in Settings → Model — so picking a model here can't
+  // silently mutate global config.
   const selectModel = useCallback(
     async (selection: ModelSelection): Promise<boolean> => {
-      const includeGlobal = selection.persistGlobal || !activeSessionId
       // Snapshot for rollback: the switch is applied optimistically, so a
       // failure must restore the prior model/provider (store + query cache)
       // rather than leave the UI showing a model the backend never selected.
@@ -78,42 +90,34 @@ export function useModelControls({ activeSessionId, queryClient, requestGateway
 
       setCurrentModel(selection.model)
       setCurrentProvider(selection.provider)
-      updateModelOptionsCache(selection.provider, selection.model, includeGlobal)
+      updateModelOptionsCache(selection.provider, selection.model, !activeSessionId)
+
+      // No live session yet: the pick is pure UI state. session.create reads
+      // $currentModel/$currentProvider and applies it as that session's override.
+      if (!activeSessionId) {
+        return true
+      }
 
       try {
-        if (activeSessionId) {
-          await requestGateway('config.set', {
-            session_id: activeSessionId,
-            key: 'model',
-            value: `${selection.model} --provider ${selection.provider}${selection.persistGlobal ? ' --global' : ''}`
-          })
+        await requestGateway('config.set', {
+          session_id: activeSessionId,
+          key: 'model',
+          value: `${selection.model} --provider ${selection.provider}`
+        })
 
-          if (selection.persistGlobal) {
-            void refreshCurrentModel()
-          }
-
-          void queryClient.invalidateQueries({
-            queryKey: selection.persistGlobal ? ['model-options'] : ['model-options', activeSessionId]
-          })
-
-          return true
-        }
-
-        await setGlobalModel(selection.provider, selection.model)
-        void refreshCurrentModel()
-        void queryClient.invalidateQueries({ queryKey: ['model-options'] })
+        void queryClient.invalidateQueries({ queryKey: ['model-options', activeSessionId] })
 
         return true
       } catch (err) {
         setCurrentModel(prevModel)
         setCurrentProvider(prevProvider)
-        updateModelOptionsCache(prevProvider, prevModel, includeGlobal)
+        updateModelOptionsCache(prevProvider, prevModel, !activeSessionId)
         notifyError(err, copy.modelSwitchFailed)
 
         return false
       }
     },
-    [activeSessionId, copy.modelSwitchFailed, queryClient, refreshCurrentModel, requestGateway, updateModelOptionsCache]
+    [activeSessionId, copy.modelSwitchFailed, queryClient, requestGateway, updateModelOptionsCache]
   )
 
   return { refreshCurrentModel, selectModel, updateModelOptionsCache }
diff --git a/apps/desktop/src/app/session/hooks/use-session-actions.ts b/apps/desktop/src/app/session/hooks/use-session-actions.ts
index 50b6bb0d270..6f7a779e8ea 100644
--- a/apps/desktop/src/app/session/hooks/use-session-actions.ts
+++ b/apps/desktop/src/app/session/hooks/use-session-actions.ts
@@ -15,6 +15,10 @@ import { requestDesktopOnboarding } from '@/store/onboarding'
 import { $activeGatewayProfile, $newChatProfile, $profiles, ensureGatewayProfile, normalizeProfileKey } from '@/store/profile'
 import {
   $currentCwd,
+  $currentFastMode,
+  $currentModel,
+  $currentProvider,
+  $currentReasoningEffort,
   $messages,
   $sessions,
   $yoloActive,
@@ -407,13 +411,13 @@ export function useSessionActions({
       })
       setSessionStartedAt(null)
       setTurnStartedAt(null)
-      // New chats start in the configured default project dir when set,
-      // otherwise the sticky last-used workspace (PR #37586).
-      setCurrentModel('')
-      setCurrentProvider('')
-      setCurrentReasoningEffort('')
+      // The composer's model/effort/fast is sticky UI state (persisted in
+      // localStorage) — a new chat FOLLOWS your last pick instead of snapping
+      // back to the profile default, so we deliberately don't reset it here. The
+      // profile default still owns first-run seeding and profile switches (see
+      // refreshCurrentModel). Only $currentServiceTier (a live-session mirror)
+      // is cleared.
       setCurrentServiceTier('')
-      setCurrentFastMode(false)
       setYoloActive(false)
       setCurrentCwd(workspaceCwdForNewSession())
       setCurrentBranch('')
@@ -443,11 +447,23 @@ export function useSessionActions({
         const newChatProfile = $newChatProfile.get() ?? normalizeProfileKey($activeGatewayProfile.get())
         await ensureGatewayProfile(newChatProfile)
         const cwd = $currentCwd.get().trim() || workspaceCwdForNewSession()
+        // The composer's model/effort/fast is sticky UI state ($currentModel,
+        // $currentProvider, $currentReasoningEffort, $currentFastMode). Ship it
+        // with every session.create so the new chat opens on whatever the picker
+        // shows — applied as per-session overrides, never written to the profile
+        // default (that lives in Settings → Model).
+        const uiModel = $currentModel.get().trim()
+        const uiProvider = $currentProvider.get().trim()
+        const uiEffort = $currentReasoningEffort.get().trim()
+        const uiFast = $currentFastMode.get()
 
         const created = await requestGateway<SessionCreateResponse>('session.create', {
           cols: 96,
           ...(cwd && { cwd }),
-          ...(newChatProfile ? { profile: newChatProfile } : {})
+          ...(newChatProfile ? { profile: newChatProfile } : {}),
+          ...(uiModel ? { model: uiModel, ...(uiProvider ? { provider: uiProvider } : {}) } : {}),
+          ...(uiEffort ? { reasoning_effort: uiEffort } : {}),
+          ...(uiFast ? { fast: true } : {})
         })
 
         const stored = created.stored_session_id ?? null
diff --git a/apps/desktop/src/app/shell/model-menu-panel.tsx b/apps/desktop/src/app/shell/model-menu-panel.tsx
index c0c6936175e..b87b1a030d1 100644
--- a/apps/desktop/src/app/shell/model-menu-panel.tsx
+++ b/apps/desktop/src/app/shell/model-menu-panel.tsx
@@ -43,7 +43,7 @@ import { ModelEditSubmenu, resolveFastControl } from './model-edit-submenu'
 
 interface ModelMenuPanelProps {
   gateway?: HermesGateway
-  onSelectModel: (selection: { model: string; persistGlobal: boolean; provider: string }) => Promise<boolean> | void
+  onSelectModel: (selection: { model: string; provider: string }) => Promise<boolean> | void
   requestGateway: <T>(method: string, params?: Record<string, unknown>) => Promise<T>
 }
 
@@ -95,8 +95,10 @@ export function ModelMenuPanel({ gateway, onSelectModel, requestGateway }: Model
     [visibleModels, providers]
   )
 
-  const switchTo = (model: string, provider: string) =>
-    onSelectModel({ model, persistGlobal: !activeSessionId, provider })
+  // The composer picker never persists the profile default. With a session it
+  // scopes the switch to that session; with none it's UI state shipped on the
+  // next session.create (see selectModel). The default lives in Settings → Model.
+  const switchTo = (model: string, provider: string) => onSelectModel({ model, provider })
 
   // Selecting a model row restores that model's remembered preset onto the
   // session (effort/fast), gated by capability. Unset → Hermes defaults.
diff --git a/apps/desktop/src/components/model-picker.tsx b/apps/desktop/src/components/model-picker.tsx
index d65bf7f89a7..be941e23d06 100644
--- a/apps/desktop/src/components/model-picker.tsx
+++ b/apps/desktop/src/components/model-picker.tsx
@@ -11,7 +11,6 @@ import { startManualOnboarding } from '../store/onboarding'
 
 import { InlineNotice } from './notifications'
 import { Button } from './ui/button'
-import { Checkbox } from './ui/checkbox'
 import { Command, CommandEmpty, CommandGroup, CommandInput, CommandItem, CommandList } from './ui/command'
 import { Dialog, DialogContent, DialogDescription, DialogFooter, DialogHeader, DialogTitle } from './ui/dialog'
 import { Skeleton } from './ui/skeleton'
@@ -23,7 +22,7 @@ interface ModelPickerDialogProps {
   sessionId?: string | null
   currentModel: string
   currentProvider: string
-  onSelect: (selection: { provider: string; model: string; persistGlobal: boolean }) => void
+  onSelect: (selection: { provider: string; model: string }) => void
   /**
    * Optional class to apply to DialogContent. Use to override z-index when
    * stacking the picker on top of another fixed overlay (e.g. the desktop
@@ -45,7 +44,6 @@ export function ModelPickerDialog({
 }: ModelPickerDialogProps) {
   const { t } = useI18n()
   const copy = t.modelPicker
-  const [persistGlobal, setPersistGlobal] = useState(!sessionId)
   // Own the search term so we can filter manually. cmdk's built-in
   // shouldFilter reorders items by its fuzzy-match score (≈alphabetical with
   // an empty query), which destroys the backend's curated order. We disable
@@ -79,11 +77,7 @@ export function ModelPickerDialog({
     : null
 
   const selectModel = (provider: ModelOptionProvider, model: string) => {
-    onSelect({
-      provider: provider.slug,
-      model,
-      persistGlobal: persistGlobal || !sessionId
-    })
+    onSelect({ provider: provider.slug, model })
     onOpenChange(false)
   }
 
@@ -128,24 +122,13 @@ export function ModelPickerDialog({
           </CommandList>
         </Command>
 
-        <DialogFooter className="flex-row items-center justify-between gap-3 bg-card p-3 sm:justify-between">
-          <label className="flex cursor-pointer select-none items-center gap-2 text-xs text-muted-foreground">
-            <Checkbox
-              checked={persistGlobal || !sessionId}
-              disabled={!sessionId}
-              onCheckedChange={checked => setPersistGlobal(checked === true)}
-            />
-            {sessionId ? copy.persistGlobalSession : copy.persistGlobal}
-          </label>
-
-          <div className="flex items-center gap-2">
-            <Button onClick={addProvider} variant="ghost">
-              {copy.addProvider}
-            </Button>
-            <Button onClick={() => onOpenChange(false)} variant="outline">
-              {t.common.cancel}
-            </Button>
-          </div>
+        <DialogFooter className="flex-row items-center justify-end gap-2 bg-card p-3">
+          <Button onClick={addProvider} variant="ghost">
+            {copy.addProvider}
+          </Button>
+          <Button onClick={() => onOpenChange(false)} variant="outline">
+            {t.common.cancel}
+          </Button>
         </DialogFooter>
       </DialogContent>
     </Dialog>
diff --git a/apps/desktop/src/i18n/en.ts b/apps/desktop/src/i18n/en.ts
index 2710f8273f6..c1fbf90bcb7 100644
--- a/apps/desktop/src/i18n/en.ts
+++ b/apps/desktop/src/i18n/en.ts
@@ -1503,8 +1503,6 @@ export const en: Translations = {
     unknown: '(unknown)',
     search: 'Filter providers and models...',
     noModels: 'No models found.',
-    persistGlobalSession: 'Persist globally (otherwise this session only)',
-    persistGlobal: 'Persist globally',
     addProvider: 'Add provider',
     loadFailed: 'Could not load models',
     noAuthenticatedProviders: 'No authenticated providers.',
diff --git a/apps/desktop/src/i18n/ja.ts b/apps/desktop/src/i18n/ja.ts
index 4f56ed46b65..f26508e5897 100644
--- a/apps/desktop/src/i18n/ja.ts
+++ b/apps/desktop/src/i18n/ja.ts
@@ -1637,8 +1637,6 @@ export const ja = defineLocale({
     unknown: '(不明)',
     search: 'プロバイダーとモデルをフィルター...',
     noModels: 'モデルが見つかりません。',
-    persistGlobalSession: 'グローバルに保持（それ以外はこのセッションのみ）',
-    persistGlobal: 'グローバルに保持',
     addProvider: 'プロバイダーを追加',
     loadFailed: 'モデルを読み込めませんでした',
     noAuthenticatedProviders: '認証済みプロバイダーがありません。',
diff --git a/apps/desktop/src/i18n/types.ts b/apps/desktop/src/i18n/types.ts
index 58d78d4a384..cc76b30d346 100644
--- a/apps/desktop/src/i18n/types.ts
+++ b/apps/desktop/src/i18n/types.ts
@@ -1145,8 +1145,6 @@ export interface Translations {
     unknown: string
     search: string
     noModels: string
-    persistGlobalSession: string
-    persistGlobal: string
     addProvider: string
     loadFailed: string
     noAuthenticatedProviders: string
diff --git a/apps/desktop/src/i18n/zh-hant.ts b/apps/desktop/src/i18n/zh-hant.ts
index f01c94de738..6f964c071f2 100644
--- a/apps/desktop/src/i18n/zh-hant.ts
+++ b/apps/desktop/src/i18n/zh-hant.ts
@@ -1581,8 +1581,6 @@ export const zhHant = defineLocale({
     unknown: '（未知）',
     search: '篩選提供方和模型...',
     noModels: '找不到模型。',
-    persistGlobalSession: '全域儲存（否則僅限此工作階段）',
-    persistGlobal: '全域儲存',
     addProvider: '新增提供方',
     loadFailed: '無法載入模型',
     noAuthenticatedProviders: '沒有已驗證的提供方。',
diff --git a/apps/desktop/src/i18n/zh.ts b/apps/desktop/src/i18n/zh.ts
index ea24026a5b1..0387a6be5bc 100644
--- a/apps/desktop/src/i18n/zh.ts
+++ b/apps/desktop/src/i18n/zh.ts
@@ -1683,8 +1683,6 @@ export const zh: Translations = {
     unknown: '(未知)',
     search: '筛选提供方和模型...',
     noModels: '未找到模型。',
-    persistGlobalSession: '全局保存 (否则仅当前会话)',
-    persistGlobal: '全局保存',
     addProvider: '添加提供方',
     loadFailed: '无法加载模型',
     noAuthenticatedProviders: '没有已认证的提供方。',
diff --git a/apps/desktop/src/store/session.ts b/apps/desktop/src/store/session.ts
index f1e1e2ee617..e40484cfec1 100644
--- a/apps/desktop/src/store/session.ts
+++ b/apps/desktop/src/store/session.ts
@@ -4,13 +4,23 @@ import { lastVisibleMessageIsUser } from '@/app/chat/thread-loading'
 import type { ContextSuggestion } from '@/app/types'
 import type { HermesConnection } from '@/global'
 import type { ChatMessage } from '@/lib/chat-messages'
-import { persistString, storedString } from '@/lib/storage'
+import { persistBoolean, persistString, storedBoolean, storedString } from '@/lib/storage'
 import type { SessionInfo, UsageStats } from '@/types/hermes'
 
 type Updater<T> = T | ((current: T) => T)
 
 const WORKSPACE_CWD_KEY = 'hermes.desktop.workspace-cwd'
 
+// The composer's model/effort/fast is sticky UI state, NOT the profile default
+// (that lives in Settings → Model). Persisting it in localStorage makes a pick
+// follow across Cmd+N and app restarts instead of snapping back to the default.
+// It's deliberately global (not per-profile): a profile switch force-reseeds to
+// that profile's default, while within a profile new chats keep your last pick.
+const COMPOSER_MODEL_KEY = 'hermes.desktop.composer.model'
+const COMPOSER_PROVIDER_KEY = 'hermes.desktop.composer.provider'
+const COMPOSER_EFFORT_KEY = 'hermes.desktop.composer.reasoning-effort'
+const COMPOSER_FAST_KEY = 'hermes.desktop.composer.fast'
+
 let configuredDefaultProjectDir = ''
 
 function workspaceCwdKey(connection: HermesConnection | null = $connection.get()): string {
@@ -208,11 +218,11 @@ export const $lastVisibleMessageIsUser = computed($messages, lastVisibleMessageI
 export const $freshDraftReady = atom(false)
 export const $busy = atom(false)
 export const $awaitingResponse = atom(false)
-export const $currentModel = atom('')
-export const $currentProvider = atom('')
-export const $currentReasoningEffort = atom('')
+export const $currentModel = atom(storedString(COMPOSER_MODEL_KEY) ?? '')
+export const $currentProvider = atom(storedString(COMPOSER_PROVIDER_KEY) ?? '')
+export const $currentReasoningEffort = atom(storedString(COMPOSER_EFFORT_KEY) ?? '')
 export const $currentServiceTier = atom('')
-export const $currentFastMode = atom(false)
+export const $currentFastMode = atom(storedBoolean(COMPOSER_FAST_KEY, false))
 // Effective approval-bypass state mirrored from the gateway (session.info).
 // Persistence lives in the backend config (approvals.mode), so this is a plain
 // reflection of the truth the gateway reports rather than its own store.
@@ -254,11 +264,29 @@ export const setMessages = (next: Updater<ChatMessage[]>) => updateAtom($message
 export const setFreshDraftReady = (next: Updater<boolean>) => updateAtom($freshDraftReady, next)
 export const setBusy = (next: Updater<boolean>) => updateAtom($busy, next)
 export const setAwaitingResponse = (next: Updater<boolean>) => updateAtom($awaitingResponse, next)
-export const setCurrentModel = (next: Updater<string>) => updateAtom($currentModel, next)
-export const setCurrentProvider = (next: Updater<string>) => updateAtom($currentProvider, next)
-export const setCurrentReasoningEffort = (next: Updater<string>) => updateAtom($currentReasoningEffort, next)
+
+export const setCurrentModel = (next: Updater<string>) => {
+  updateAtom($currentModel, next)
+  persistString(COMPOSER_MODEL_KEY, $currentModel.get() || null)
+}
+
+export const setCurrentProvider = (next: Updater<string>) => {
+  updateAtom($currentProvider, next)
+  persistString(COMPOSER_PROVIDER_KEY, $currentProvider.get() || null)
+}
+
+export const setCurrentReasoningEffort = (next: Updater<string>) => {
+  updateAtom($currentReasoningEffort, next)
+  persistString(COMPOSER_EFFORT_KEY, $currentReasoningEffort.get() || null)
+}
+
 export const setCurrentServiceTier = (next: Updater<string>) => updateAtom($currentServiceTier, next)
-export const setCurrentFastMode = (next: Updater<boolean>) => updateAtom($currentFastMode, next)
+
+export const setCurrentFastMode = (next: Updater<boolean>) => {
+  updateAtom($currentFastMode, next)
+  persistBoolean(COMPOSER_FAST_KEY, $currentFastMode.get())
+}
+
 export const setYoloActive = (next: Updater<boolean>) => updateAtom($yoloActive, next)
 
 export const setCurrentCwd = (next: Updater<string>) => {
diff --git a/apps/desktop/src/store/updates.test.ts b/apps/desktop/src/store/updates.test.ts
index 01f78bc08dc..913e4fb11ee 100644
--- a/apps/desktop/src/store/updates.test.ts
+++ b/apps/desktop/src/store/updates.test.ts
@@ -5,6 +5,9 @@ import type { DesktopUpdateStatus } from '@/global'
 const storage = new Map<string, string>()
 
 vi.mock('@/lib/storage', () => ({
+  persistBoolean: (key: string, value: boolean) => {
+    storage.set(key, String(value))
+  },
   persistString: (key: string, value: null | string) => {
     if (value === null) {
       storage.delete(key)
@@ -12,6 +15,11 @@ vi.mock('@/lib/storage', () => ({
       storage.set(key, value)
     }
   },
+  storedBoolean: (key: string, fallback: boolean) => {
+    const value = storage.get(key)
+
+    return value === undefined ? fallback : value === 'true'
+  },
   storedString: (key: string) => storage.get(key) ?? null
 }))
 
diff --git a/tests/test_tui_gateway_server.py b/tests/test_tui_gateway_server.py
index 2b37b5788bb..77884c5920e 100644
--- a/tests/test_tui_gateway_server.py
+++ b/tests/test_tui_gateway_server.py
@@ -1851,8 +1851,10 @@ def test_ensure_session_db_row_persists_explicit_cwd(monkeypatch, tmp_path):
     created = []
 
     class _FakeDB:
-        def create_session(self, key, source=None, model=None, cwd=None):
-            created.append({"key": key, "source": source, "model": model, "cwd": cwd})
+        def create_session(self, key, source=None, model=None, model_config=None, cwd=None):
+            created.append(
+                {"key": key, "source": source, "model": model, "model_config": model_config, "cwd": cwd}
+            )
 
     monkeypatch.setattr(server, "_get_db", lambda: _FakeDB())
     monkeypatch.setattr(server, "_resolve_model", lambda: "test-model")
@@ -1860,7 +1862,7 @@ def test_ensure_session_db_row_persists_explicit_cwd(monkeypatch, tmp_path):
     server._ensure_session_db_row({"session_key": "k1", "cwd": str(tmp_path), "explicit_cwd": True})
 
     assert created == [
-        {"key": "k1", "source": "tui", "model": "test-model", "cwd": str(tmp_path)}
+        {"key": "k1", "source": "tui", "model": "test-model", "model_config": None, "cwd": str(tmp_path)}
     ]
 
 
@@ -1870,15 +1872,74 @@ def test_ensure_session_db_row_defaults_to_no_workspace(monkeypatch, tmp_path):
     created = []
 
     class _FakeDB:
-        def create_session(self, key, source=None, model=None, cwd=None):
-            created.append({"key": key, "source": source, "model": model, "cwd": cwd})
+        def create_session(self, key, source=None, model=None, model_config=None, cwd=None):
+            created.append(
+                {"key": key, "source": source, "model": model, "model_config": model_config, "cwd": cwd}
+            )
 
     monkeypatch.setattr(server, "_get_db", lambda: _FakeDB())
     monkeypatch.setattr(server, "_resolve_model", lambda: "test-model")
 
     server._ensure_session_db_row({"session_key": "k1", "cwd": str(tmp_path)})
 
-    assert created == [{"key": "k1", "source": "tui", "model": "test-model", "cwd": None}]
+    assert created == [
+        {"key": "k1", "source": "tui", "model": "test-model", "model_config": None, "cwd": None}
+    ]
+
+
+def test_ensure_session_db_row_persists_session_model_override(monkeypatch):
+    """The session's composer pick (model + effort + fast) must own the DB row.
+
+    Regression for the "switched to gpt-5.5, reconnect snapped back to opus"
+    bug: the row was created with the global default and won the INSERT-OR-IGNORE
+    race, so resume rebuilt from the global model and silently reverted the
+    chat. The override model + a model_config carrying provider/reasoning/
+    service_tier must be persisted so session.resume restores all three.
+    """
+    created = []
+
+    class _FakeDB:
+        def create_session(self, key, source=None, model=None, model_config=None, cwd=None):
+            created.append(
+                {"key": key, "model": model, "model_config": model_config, "cwd": cwd}
+            )
+
+    monkeypatch.setattr(server, "_get_db", lambda: _FakeDB())
+    monkeypatch.setattr(server, "_resolve_model", lambda: "global/default")
+
+    server._ensure_session_db_row(
+        {
+            "session_key": "k1",
+            "model_override": {"model": "openai/gpt-5.5", "provider": "openrouter"},
+            "create_reasoning_override": {"effort": "high"},
+            "create_service_tier_override": "priority",
+        }
+    )
+
+    assert len(created) == 1
+    row = created[0]
+    assert row["model"] == "openai/gpt-5.5"
+    assert row["model_config"]["model"] == "openai/gpt-5.5"
+    assert row["model_config"]["provider"] == "openrouter"
+    assert row["model_config"]["reasoning_config"] == {"effort": "high"}
+    assert row["model_config"]["service_tier"] == "priority"
+
+
+def test_ensure_session_db_row_no_override_uses_global(monkeypatch):
+    """A chat that made no explicit pick falls back to the global model and
+    writes no model_config (so it tracks the profile default)."""
+    created = []
+
+    class _FakeDB:
+        def create_session(self, key, source=None, model=None, model_config=None, cwd=None):
+            created.append({"model": model, "model_config": model_config})
+
+    monkeypatch.setattr(server, "_get_db", lambda: _FakeDB())
+    monkeypatch.setattr(server, "_resolve_model", lambda: "global/default")
+
+    server._ensure_session_db_row({"session_key": "k1", "model_override": None})
+
+    assert created == [{"model": "global/default", "model_config": None}]
 
 
 def test_session_title_clears_pending_after_persist(monkeypatch):
@@ -7485,3 +7546,97 @@ def test_reap_idle_sessions_closes_only_evictable(monkeypatch):
         assert closed == [("stale", "idle_timeout")]
     finally:
         server._sessions.clear()
+
+
+def test_session_create_records_ui_model_as_session_override(monkeypatch):
+    """The desktop composer owns its model as plain UI state and ships it on
+    session.create. The gateway must record it as a PER-SESSION override (built
+    into the agent), never a global config write — picking a model for a new chat
+    must not mutate the profile default.
+    """
+    monkeypatch.setattr(server, "_enable_gateway_prompts", lambda: None)
+    # Don't run the real deferred build in this storage-focused test.
+    monkeypatch.setattr(server, "_start_agent_build", lambda *a, **k: None)
+    try:
+        resp = server._methods["session.create"](
+            "r1",
+            {
+                "cols": 80,
+                "model": "claude-sonnet-4.6",
+                "provider": "anthropic",
+                "reasoning_effort": "high",
+                "fast": True,
+            },
+        )
+        sid = resp["result"]["session_id"]
+        sess = server._sessions[sid]
+        assert sess["model_override"] == {"model": "claude-sonnet-4.6", "provider": "anthropic"}
+        assert sess["create_reasoning_override"] is not None
+        assert sess["create_service_tier_override"] == "priority"
+        # The immediate response reflects the override (not the global default) so
+        # the client never clobbers its sticky pick before the build lands.
+        assert resp["result"]["info"]["model"] == "claude-sonnet-4.6"
+        assert resp["result"]["info"]["provider"] == "anthropic"
+
+        # No knobs → no overrides; the session builds from the profile default.
+        plain = server._methods["session.create"]("r2", {"cols": 80})
+        plain_sess = server._sessions[plain["result"]["session_id"]]
+        assert plain_sess["model_override"] is None
+        assert plain_sess["create_reasoning_override"] is None
+        assert plain_sess["create_service_tier_override"] is None
+    finally:
+        server._sessions.clear()
+
+
+def test_start_agent_build_passes_session_model_override(monkeypatch):
+    """A model staged on the session (e.g. by session.create from the desktop
+    composer) must reach _make_agent so the first build runs on it directly —
+    no global config, no build-then-switch.
+    """
+    captured = {}
+
+    class FakeWorker:
+        def __init__(self, *_a, **_k):
+            pass
+
+        def close(self):
+            pass
+
+    def fake_make_agent(sid, key, session_id=None, session_db=None, **kwargs):
+        captured.update(kwargs)
+        return types.SimpleNamespace(model="claude-sonnet-4.6")
+
+    monkeypatch.setattr(server, "_set_session_context", lambda target: [])
+    monkeypatch.setattr(server, "_clear_session_context", lambda tokens: None)
+    monkeypatch.setattr(server, "_make_agent", fake_make_agent)
+    monkeypatch.setattr(server, "_SlashWorker", FakeWorker)
+    monkeypatch.setattr(server, "_attach_worker", lambda *a, **k: None)
+    monkeypatch.setattr(server, "_wire_callbacks", lambda _sid: None)
+    monkeypatch.setattr(server, "_emit", lambda *a, **k: None)
+    monkeypatch.setattr(server, "_session_info", lambda *a, **k: {})
+    monkeypatch.setattr(server, "_start_notification_poller", lambda *a, **k: None)
+    monkeypatch.setattr(server, "_notify_session_boundary", lambda *a, **k: None)
+    monkeypatch.setattr(server, "_probe_config_health", lambda *_a: None)
+
+    sid = "build-sid"
+    override = {"model": "claude-sonnet-4.6", "provider": "anthropic"}
+    reasoning = {"enabled": True, "effort": "high"}
+    session = {
+        "agent": None,
+        "agent_ready": threading.Event(),
+        "session_key": "k1",
+        "profile_home": None,
+        "model_override": override,
+        "create_reasoning_override": reasoning,
+        "create_service_tier_override": "priority",
+    }
+    server._sessions[sid] = session
+    try:
+        server._start_agent_build(sid, session)
+        assert session["agent_ready"].wait(timeout=3), "agent build did not finish"
+        assert captured.get("model_override") == override
+        assert captured.get("reasoning_config_override") == reasoning
+        assert captured.get("service_tier_override") == "priority"
+        assert session["agent"].model == "claude-sonnet-4.6"
+    finally:
+        server._sessions.clear()
diff --git a/tui_gateway/server.py b/tui_gateway/server.py
index 4d12a1a417b..d0e52635e7c 100644
--- a/tui_gateway/server.py
+++ b/tui_gateway/server.py
@@ -946,6 +946,15 @@ def _start_agent_build(sid: str, session: dict) -> None:
                 kw = {"session_db": session_db}
                 if resume_sid := current.get("resume_session_id"):
                     kw["session_id"] = resume_sid
+                # Model/effort/fast the desktop picked for a brand-new chat ride
+                # in as per-session overrides so the first build uses them
+                # directly (no global config, no build-then-switch).
+                if override := current.get("model_override"):
+                    kw["model_override"] = override
+                if (reasoning := current.get("create_reasoning_override")) is not None:
+                    kw["reasoning_config_override"] = reasoning
+                if (tier := current.get("create_service_tier_override")) is not None:
+                    kw["service_tier_override"] = tier
                 agent = _make_agent(sid, key, **kw)
             finally:
                 _clear_session_context(tokens)
@@ -1174,11 +1183,38 @@ def _ensure_session_db_row(session: dict) -> None:
         close_db = False
     if db is None:
         return
+    # The session's own model/effort/fast pick — the composer override shipped on
+    # session.create, or a restored /model switch — must own the row's model +
+    # model_config. The agent isn't built yet at first prompt.submit, so derive
+    # the row from the live override dict; fall back to the global resolved model
+    # only when this chat made no explicit pick. Writing the global default here
+    # used to win the INSERT-OR-IGNORE race against the agent's own correct
+    # lazy-create, so a reconnect/resume rebuilt from the global model and
+    # silently reverted the chat (e.g. picked gpt-5.5, reconnect snapped back to
+    # the profile default). model_config carries provider/reasoning/service_tier
+    # so resume restores effort + fast too, not just the model name.
+    override = session.get("model_override")
+    override = override if isinstance(override, dict) else {}
+    row_model = str(override.get("model") or "").strip() or _resolve_model()
+    model_config: dict = {}
+    for src_key, cfg_key in (
+        ("model", "model"),
+        ("provider", "provider"),
+        ("base_url", "base_url"),
+        ("api_mode", "api_mode"),
+    ):
+        if val := override.get(src_key):
+            model_config[cfg_key] = str(val)
+    if (reasoning := session.get("create_reasoning_override")) is not None:
+        model_config["reasoning_config"] = reasoning
+    if tier := session.get("create_service_tier_override"):
+        model_config["service_tier"] = tier
     try:
         db.create_session(
             key,
             source="tui",
-            model=_resolve_model(),
+            model=row_model,
+            model_config=model_config or None,
             cwd=_session_cwd(session) if session.get("explicit_cwd") else None,
         )
     except Exception:
@@ -3887,6 +3923,29 @@ def _(rid, params: dict) -> dict:
     profile = (params.get("profile") or "").strip() or None
     profile_home = _profile_home(profile)
 
+    # The desktop composer owns its model/effort/fast as plain UI state and ships
+    # it on every session.create. Honor each as a PER-SESSION override (built into
+    # the agent below) — never a global config write, so picking a model/effort
+    # for a new chat can't mutate the profile default. provider is optional
+    # (resolved at build).
+    create_model = str(params.get("model") or "").strip()
+    session_model_override = (
+        {"model": create_model, "provider": str(params.get("provider") or "").strip() or None}
+        if create_model
+        else None
+    )
+    create_reasoning_override = None
+    if effort := str(params.get("reasoning_effort") or "").strip():
+        try:
+            from hermes_constants import parse_reasoning_effort
+
+            create_reasoning_override = parse_reasoning_effort(effort)
+        except Exception:
+            create_reasoning_override = None
+    # Only pin "fast" when explicitly requested; leaving it None lets the build
+    # fall back to the profile default service tier rather than forcing normal.
+    create_service_tier_override = "priority" if params.get("fast") else None
+
     ready = threading.Event()
     now = time.time()
     lease, limit_message = _claim_active_session_slot(key, live_session_id=sid)
@@ -3912,6 +3971,9 @@ def _(rid, params: dict) -> dict:
             "cwd": resolved_cwd,
             "inflight_turn": None,
             "last_active": now,
+            "model_override": session_model_override,
+            "create_reasoning_override": create_reasoning_override,
+            "create_service_tier_override": create_service_tier_override,
             "pending_title": title or None,
             "profile_home": str(profile_home) if profile_home is not None else None,
             "running": False,
@@ -3951,7 +4013,20 @@ def _(rid, params: dict) -> dict:
             "message_count": len(history),
             "messages": _history_to_messages(history),
             "info": {
-                "model": _resolve_model(),
+                # Reflect the per-session model override (desktop composer pick)
+                # in the immediate response so the client doesn't briefly clobber
+                # its sticky pick with the global default before the deferred
+                # build's session.info lands.
+                "model": (
+                    session_model_override.get("model")
+                    if session_model_override
+                    else _resolve_model()
+                ),
+                **(
+                    {"provider": session_model_override["provider"]}
+                    if session_model_override and session_model_override.get("provider")
+                    else {}
+                ),
                 "tools": {},
                 "skills": {},
                 "cwd": _sessions[sid]["cwd"],
diff --git a/website/docs/user-guide/desktop.md b/website/docs/user-guide/desktop.md
index 5f132793f21..87639ce3818 100644
--- a/website/docs/user-guide/desktop.md
+++ b/website/docs/user-guide/desktop.md
@@ -50,11 +50,18 @@ The center of the app. You get:
 
 The bar along the bottom of the chat shows live session state and exposes quick controls without opening Settings:
 
-- **Inline model picker** — switch the model for the active session straight from the status bar.
 - **Per-session YOLO toggle** — flip YOLO on or off for just this session (matching the TUI). YOLO bypasses the dangerous-command approval prompts, so know what you're turning off — see [Security → YOLO Mode](./security.md#yolo-mode).
 
 Chatting against a Hermes instance on another machine instead of the bundled local backend? See [Connecting to a remote backend](#connecting-to-a-remote-backend) below — and for the full picture of how the remote-hosted dashboard connection works (the auth gate, the `/api/ws` chat socket, and WebSocket close-code triage), see [Web Dashboard → Connecting Hermes Desktop to a remote backend](./features/web-dashboard.md#connecting-hermes-desktop-to-a-remote-backend).
 
+#### Choosing a model
+
+The model picker lives in the **composer**, just left of the microphone. Click it to switch the model, reasoning effort, and fast mode from one dropdown.
+
+- **The composer picker is sticky UI state and never touches your default.** It's remembered locally (per device) and **follows** across new chats and restarts instead of snapping back to the default — pick a model once and the next `Cmd/Ctrl+N` opens on it. With a live chat, switching models scopes the change to that **current chat**; either way the selection rides along when the session is created/switched and is **never** written to the profile default. (Switching [profiles](#sessions--profiles) reseeds to that profile's own default.)
+- **Set the default in Settings → Model.** That "main" model is your **per-profile global default** — it's what new chats, crons, subagents, and auxiliary tasks start from, and it's the only place that writes it. Each [profile](#sessions--profiles) keeps its own default.
+- **Per-model effort/fast presets.** Each model remembers its own reasoning effort and fast-mode choice in the desktop app, re-applied to the session whenever you pick that model. These presets are a desktop convenience and don't change crons or subagents.
+
 ### File browser
 
 Explore and preview the working directory without leaving the app — useful for following along as the agent reads, writes, and edits files. Set the initial project directory with `hermes desktop --cwd <path>` (or the `HERMES_DESKTOP_CWD` environment variable).