@clawpump/claw-agent 0.1.5 → 0.1.6

package/agent/apps/desktop/src/app/session/hooks/use-route-resume.test.tsx

@@ -2,6 +2,8 @@ import { cleanup, render } from '@testing-library/react'
 import type { MutableRefObject } from 'react'
 import { afterEach, describe, expect, it, vi } from 'vitest'
 
+import { $resumeExhaustedSessionId, setResumeExhaustedSessionId } from '@/store/session'
+
 import { useRouteResume } from './use-route-resume'
 
 interface HarnessProps {
@@ -13,6 +15,8 @@ interface HarnessProps {
   gatewayState: string
   locationPathname: string
   resumeSession: (sessionId: string, focus: boolean) => Promise<unknown>
+  resumeFailedSessionId?: null | string
+  resumeExhaustedSessionId?: null | string
   routedSessionId: null | string
   runtimeIdByStoredSessionIdRef: MutableRefObject<Map<string, string>>
   selectedStoredSessionId: null | string
@@ -20,8 +24,12 @@ interface HarnessProps {
   startFreshSessionDraft: (focus: boolean) => unknown
 }
 
-function RouteResumeHarness(props: HarnessProps) {
-  useRouteResume(props)
+function RouteResumeHarness({
+  resumeFailedSessionId = null,
+  resumeExhaustedSessionId = null,
+  ...props
+}: HarnessProps) {
+  useRouteResume({ ...props, resumeExhaustedSessionId, resumeFailedSessionId })
 
   return null
 }
@@ -84,6 +92,60 @@ describe('useRouteResume', () => {
     expect(resumeSession).not.toHaveBeenCalled()
   })
 
+  it('self-heals a stranded routed session (null selected/active, same pathname, not a fresh draft)', () => {
+    const resumeSession = vi.fn(async () => undefined)
+    const startFreshSessionDraft = vi.fn()
+    const activeSessionIdRef: MutableRefObject<null | string> = { current: 'runtime-1' }
+    const creatingSessionRef = { current: false }
+    const runtimeIdByStoredSessionIdRef = { current: new Map([['session-1', 'runtime-1']]) }
+    const selectedStoredSessionIdRef: MutableRefObject<null | string> = { current: 'session-1' }
+
+    const { rerender } = render(
+      <RouteResumeHarness
+        activeSessionId="runtime-1"
+        activeSessionIdRef={activeSessionIdRef}
+        creatingSessionRef={creatingSessionRef}
+        currentView="chat"
+        freshDraftReady={false}
+        gatewayState="open"
+        locationPathname="/session-1"
+        resumeSession={resumeSession}
+        routedSessionId="session-1"
+        runtimeIdByStoredSessionIdRef={runtimeIdByStoredSessionIdRef}
+        selectedStoredSessionId="session-1"
+        selectedStoredSessionIdRef={selectedStoredSessionIdRef}
+        startFreshSessionDraft={startFreshSessionDraft}
+      />
+    )
+
+    expect(resumeSession).not.toHaveBeenCalled()
+
+    // A create/stream race nulls selected/active but the route stays on the
+    // session and freshDraftReady is false (NOT a new-chat transition).
+    activeSessionIdRef.current = null
+    selectedStoredSessionIdRef.current = null
+    rerender(
+      <RouteResumeHarness
+        activeSessionId={null}
+        activeSessionIdRef={activeSessionIdRef}
+        creatingSessionRef={creatingSessionRef}
+        currentView="chat"
+        freshDraftReady={false}
+        gatewayState="open"
+        locationPathname="/session-1"
+        resumeSession={resumeSession}
+        routedSessionId="session-1"
+        runtimeIdByStoredSessionIdRef={runtimeIdByStoredSessionIdRef}
+        selectedStoredSessionId={null}
+        selectedStoredSessionIdRef={selectedStoredSessionIdRef}
+        startFreshSessionDraft={startFreshSessionDraft}
+      />
+    )
+
+    expect(resumeSession).toHaveBeenCalledTimes(1)
+    expect(resumeSession).toHaveBeenCalledWith('session-1', true)
+  })
+
   it('resumes when pathname changes to a routed session', () => {
     const resumeSession = vi.fn(async () => undefined)
     const startFreshSessionDraft = vi.fn()
@@ -133,4 +195,281 @@ describe('useRouteResume', () => {
     expect(resumeSession).toHaveBeenCalledTimes(1)
     expect(resumeSession).toHaveBeenCalledWith('session-2', true)
   })
+
+  it('resumes the selected route again when the gateway reconnects', () => {
+    const resumeSession = vi.fn(async () => undefined)
+    const startFreshSessionDraft = vi.fn()
+    const activeSessionIdRef: MutableRefObject<null | string> = { current: 'runtime-1' }
+    const creatingSessionRef = { current: false }
+    const runtimeIdByStoredSessionIdRef = { current: new Map([['session-1', 'runtime-1']]) }
+    const selectedStoredSessionIdRef: MutableRefObject<null | string> = { current: 'session-1' }
+
+    const { rerender } = render(
+      <RouteResumeHarness
+        activeSessionId="runtime-1"
+        activeSessionIdRef={activeSessionIdRef}
+        creatingSessionRef={creatingSessionRef}
+        currentView="chat"
+        freshDraftReady={false}
+        gatewayState="open"
+        locationPathname="/session-1"
+        resumeSession={resumeSession}
+        routedSessionId="session-1"
+        runtimeIdByStoredSessionIdRef={runtimeIdByStoredSessionIdRef}
+        selectedStoredSessionId="session-1"
+        selectedStoredSessionIdRef={selectedStoredSessionIdRef}
+        startFreshSessionDraft={startFreshSessionDraft}
+      />
+    )
+
+    expect(resumeSession).not.toHaveBeenCalled()
+
+    rerender(
+      <RouteResumeHarness
+        activeSessionId="runtime-1"
+        activeSessionIdRef={activeSessionIdRef}
+        creatingSessionRef={creatingSessionRef}
+        currentView="chat"
+        freshDraftReady={false}
+        gatewayState="closed"
+        locationPathname="/session-1"
+        resumeSession={resumeSession}
+        routedSessionId="session-1"
+        runtimeIdByStoredSessionIdRef={runtimeIdByStoredSessionIdRef}
+        selectedStoredSessionId="session-1"
+        selectedStoredSessionIdRef={selectedStoredSessionIdRef}
+        startFreshSessionDraft={startFreshSessionDraft}
+      />
+    )
+
+    rerender(
+      <RouteResumeHarness
+        activeSessionId="runtime-1"
+        activeSessionIdRef={activeSessionIdRef}
+        creatingSessionRef={creatingSessionRef}
+        currentView="chat"
+        freshDraftReady={false}
+        gatewayState="open"
+        locationPathname="/session-1"
+        resumeSession={resumeSession}
+        routedSessionId="session-1"
+        runtimeIdByStoredSessionIdRef={runtimeIdByStoredSessionIdRef}
+        selectedStoredSessionId="session-1"
+        selectedStoredSessionIdRef={selectedStoredSessionIdRef}
+        startFreshSessionDraft={startFreshSessionDraft}
+      />
+    )
+
+    expect(resumeSession).toHaveBeenCalledTimes(1)
+    expect(resumeSession).toHaveBeenCalledWith('session-1', true)
+  })
+})
+
+describe('useRouteResume bounded auto-retry after a failed resume', () => {
+  afterEach(() => {
+    cleanup()
+    vi.useRealTimers()
+    vi.restoreAllMocks()
+    setResumeExhaustedSessionId(null)
+  })
+
+  // Common stranded-window props: gateway open, route on the session, no runtime
+  // yet, and the ref already synced to the route (resumeSession sets it at entry
+  // before failing) — the exact state that defeats the main effect's self-heal.
+  function strandedProps(resumeSession: (sid: string, focus: boolean) => Promise<unknown>) {
+    return {
+      activeSessionId: null,
+      activeSessionIdRef: { current: null } as MutableRefObject<null | string>,
+      creatingSessionRef: { current: false },
+      currentView: 'chat',
+      freshDraftReady: false,
+      gatewayState: 'open',
+      locationPathname: '/session-1',
+      resumeSession,
+      routedSessionId: 'session-1',
+      runtimeIdByStoredSessionIdRef: { current: new Map<string, string>() },
+      selectedStoredSessionId: 'session-1',
+      // Synced to the route by the failed resume's synchronous entry-write.
+      selectedStoredSessionIdRef: { current: 'session-1' } as MutableRefObject<null | string>,
+      startFreshSessionDraft: vi.fn()
+    }
+  }
+
+  it('retries the resume on backoff when the routed session is flagged as failed', () => {
+    vi.useFakeTimers()
+    const resumeSession = vi.fn(async () => undefined)
+
+    render(<RouteResumeHarness {...strandedProps(resumeSession)} resumeFailedSessionId="session-1" />)
+
+    // The main effect fires one resume on mount (pathname-changed). Clear it so
+    // we assert purely the bounded-retry effect's scheduled retry below.
+    resumeSession.mockClear()
+
+    // No immediate fire — the retry is scheduled behind the backoff timer.
+    expect(resumeSession).not.toHaveBeenCalled()
+
+    // First backoff window (1s) elapses → one retry.
+    vi.advanceTimersByTime(1_000)
+    expect(resumeSession).toHaveBeenCalledTimes(1)
+    expect(resumeSession).toHaveBeenCalledWith('session-1', true)
+  })
+
+  it('does NOT retry a failed session that is not the routed one', () => {
+    vi.useFakeTimers()
+    const resumeSession = vi.fn(async () => undefined)
+
+    // The failure flag points at a different session than the route.
+    render(<RouteResumeHarness {...strandedProps(resumeSession)} resumeFailedSessionId="other-session" />)
+    resumeSession.mockClear() // drop the mount resume
+
+    vi.advanceTimersByTime(10_000)
+    expect(resumeSession).not.toHaveBeenCalled()
+  })
+
+  it('skips the scheduled retry if the session already recovered when the timer fires', () => {
+    vi.useFakeTimers()
+    const resumeSession = vi.fn(async () => undefined)
+    const props = strandedProps(resumeSession)
+
+    render(<RouteResumeHarness {...props} resumeFailedSessionId="session-1" />)
+    resumeSession.mockClear() // drop the mount resume
+
+    // A resume landed while we waited: runtime is now bound.
+    props.activeSessionIdRef.current = 'runtime-1'
+
+    vi.advanceTimersByTime(8_000)
+    expect(resumeSession).not.toHaveBeenCalled()
+  })
+
+  it('stops retrying after MAX_RESUME_RETRIES consecutive failures', () => {
+    vi.useFakeTimers()
+    const resumeSession = vi.fn(async () => undefined)
+    const props = strandedProps(resumeSession)
+
+    // Model the real re-arm loop: resumeSession clears $resumeFailedSessionId at
+    // entry (null) and a repeat failure re-sets it ('session-1'). That null->id
+    // toggle is what re-runs the effect and advances the bounded counter. The
+    // routed session never changes, so the counter is NOT reset between cycles.
+    const { rerender } = render(<RouteResumeHarness {...props} resumeFailedSessionId="session-1" />)
+    resumeSession.mockClear() // drop the mount resume; count only the retries
+
+    for (let i = 0; i < 8; i += 1) {
+      vi.advanceTimersByTime(8_000) // fire the scheduled retry (if any)
+      rerender(<RouteResumeHarness {...props} resumeFailedSessionId={null} />) // cleared at entry
+      rerender(<RouteResumeHarness {...props} resumeFailedSessionId="session-1" />) // re-armed on failure
+    }
+
+    // Capped at MAX_RESUME_RETRIES (4): a persistently dead backend can't
+    // hot-loop the resume forever.
+    expect(resumeSession.mock.calls.length).toBe(4)
+
+    // Once auto-retry gives up, the exhausted latch is armed for the routed
+    // session so the chat view can swap the perpetual loader for an explicit
+    // error + manual Retry instead of spinning forever.
+    expect($resumeExhaustedSessionId.get()).toBe('session-1')
+  })
+
+  it('does not arm the exhausted latch while retries remain', () => {
+    vi.useFakeTimers()
+    const resumeSession = vi.fn(async () => undefined)
+    const props = strandedProps(resumeSession)
+
+    const { rerender } = render(<RouteResumeHarness {...props} resumeFailedSessionId="session-1" />)
+    resumeSession.mockClear()
+
+    // Two failure cycles — still under the 4-retry cap, so the latch must stay
+    // clear and the loader keeps spinning (auto-recovery hasn't given up yet).
+    for (let i = 0; i < 2; i += 1) {
+      vi.advanceTimersByTime(8_000)
+      rerender(<RouteResumeHarness {...props} resumeFailedSessionId={null} />)
+      rerender(<RouteResumeHarness {...props} resumeFailedSessionId="session-1" />)
+    }
+
+    expect($resumeExhaustedSessionId.get()).toBeNull()
+  })
+
+  it('clears a stale exhausted latch when the route moves off the stranded session', () => {
+    vi.useFakeTimers()
+    const resumeSession = vi.fn(async () => undefined)
+    const props = strandedProps(resumeSession)
+
+    // Pre-arm the latch as if this session had exhausted its retries.
+    setResumeExhaustedSessionId('session-1')
+
+    // Route is now on a different, healthy session that is not flagged as
+    // failed — the retry effect's "route moved off" branch clears the latch.
+    render(
+      <RouteResumeHarness
+        {...props}
+        activeSessionId="runtime-2"
+        activeSessionIdRef={{ current: 'runtime-2' }}
+        locationPathname="/session-2"
+        resumeFailedSessionId={null}
+        routedSessionId="session-2"
+        selectedStoredSessionId="session-2"
+        selectedStoredSessionIdRef={{ current: 'session-2' }}
+      />
+    )
+
+    expect($resumeExhaustedSessionId.get()).toBeNull()
+  })
+
+  it('resets the retry counter for a fresh backoff cycle when the exhausted latch clears (manual retry, same session)', () => {
+    vi.useFakeTimers()
+    const resumeSession = vi.fn(async () => undefined)
+    const props = strandedProps(resumeSession)
+
+    // Phase A — exhaust the bounded auto-retry (counter → MAX) like a dead
+    // backend. The resumeExhaustedSessionId prop stays null here: the hook sets
+    // the store, which doesn't feed back into the prop in this harness.
+    const { rerender } = render(<RouteResumeHarness {...props} resumeFailedSessionId="session-1" />)
+    resumeSession.mockClear()
+    for (let i = 0; i < 8; i += 1) {
+      vi.advanceTimersByTime(8_000)
+      rerender(<RouteResumeHarness {...props} resumeFailedSessionId={null} />)
+      rerender(<RouteResumeHarness {...props} resumeFailedSessionId="session-1" />)
+    }
+    expect(resumeSession.mock.calls.length).toBe(4) // capped
+    expect($resumeExhaustedSessionId.get()).toBe('session-1')
+
+    // Phase B — user clicks Retry on the SAME stranded session. resumeSession
+    // clears both latches at entry; the exhausted latch's armed->cleared edge
+    // must reset the attempt counter so a fresh bounded cycle runs, not a single
+    // one-shot attempt that immediately re-arms the error. Model the prop
+    // transitions: reflect the armed latch, then clear it (retry), then re-arm
+    // the failure latch on the fresh failure.
+    resumeSession.mockClear()
+    rerender(<RouteResumeHarness {...props} resumeExhaustedSessionId="session-1" resumeFailedSessionId="session-1" />)
+    rerender(<RouteResumeHarness {...props} resumeExhaustedSessionId={null} resumeFailedSessionId={null} />)
+    rerender(<RouteResumeHarness {...props} resumeExhaustedSessionId={null} resumeFailedSessionId="session-1" />)
+
+    // A real retry fires again instead of staying pinned at MAX (which would
+    // dispatch nothing). Without the reset the counter stays >= MAX and this
+    // advance dispatches zero resumes.
+    vi.advanceTimersByTime(8_000)
+    expect(resumeSession.mock.calls.length).toBeGreaterThan(0)
+  })
+
+  it('does not burn retry attempts on unrelated re-renders during the backoff window', () => {
+    vi.useFakeTimers()
+    const props = strandedProps(vi.fn())
+
+    // Mount schedules the first backoff timer. Then re-render repeatedly with a
+    // fresh resumeSession identity (referential instability — a real dep change
+    // for the retry effect) WITHOUT ever letting the timer fire. The old code
+    // incremented the attempt counter at schedule time, so >= MAX re-renders
+    // armed the exhausted error with zero resumes actually dispatched. The fix
+    // only advances the counter when a timer truly fires, so the latch stays
+    // clear no matter how many spurious re-renders happen mid-backoff.
+    const { rerender } = render(
+      <RouteResumeHarness {...props} resumeFailedSessionId="session-1" resumeSession={vi.fn(async () => undefined)} />
+    )
+    for (let j = 0; j < 8; j += 1) {
+      rerender(
+        <RouteResumeHarness {...props} resumeFailedSessionId="session-1" resumeSession={vi.fn(async () => undefined)} />
+      )
+    }
+
+    expect($resumeExhaustedSessionId.get()).toBeNull()
+  })
 })

package/agent/apps/desktop/src/app/session/hooks/use-route-resume.ts

@@ -1,6 +1,7 @@
 import { type MutableRefObject, useEffect, useRef } from 'react'
 
 import { isNewChatRoute } from '@/app/routes'
+import { setResumeExhaustedSessionId } from '@/store/session'
 
 interface RouteResumeOptions {
   activeSessionId: string | null
@@ -11,6 +12,17 @@ interface RouteResumeOptions {
   gatewayState: string | undefined
   locationPathname: string
   resumeSession: (sessionId: string, focus: boolean) => Promise<unknown>
+  // Stored-session id whose most recent resume failed terminally (set by
+  // useSessionActions, mirrored from $resumeFailedSessionId). While this equals
+  // routedSessionId the window would otherwise latch on the loader forever, so
+  // the bounded-retry effect below re-attempts the resume.
+  resumeFailedSessionId: string | null
+  // Stored-session id whose bounded auto-retry has EXHAUSTED (mirrored from
+  // $resumeExhaustedSessionId). Only resumeSession clears this latch (manual
+  // Retry / reconnect / reselect) — the auto-retry loop never does — so its
+  // armed->cleared edge is an unambiguous "give me a fresh backoff cycle"
+  // signal the effect below uses to reset the attempt counter.
+  resumeExhaustedSessionId: string | null
   routedSessionId: string | null
   runtimeIdByStoredSessionIdRef: MutableRefObject<Map<string, string>>
   selectedStoredSessionId: string | null
@@ -18,6 +30,19 @@ interface RouteResumeOptions {
   startFreshSessionDraft: (focus: boolean) => unknown
 }
 
+// Bounded auto-retry for a stranded session window. A resume can fail terminally
+// (gateway RPC reject + REST fallback failure) on a transiently wedged backend —
+// dead provider key, a runaway turn hogging the dispatcher, flaky DNS. Without a
+// retry the loader latches forever. We retry with backoff, capped, so a
+// genuinely dead backend doesn't hot-loop the resume.
+const MAX_RESUME_RETRIES = 4
+const RESUME_RETRY_BASE_MS = 1_000
+const RESUME_RETRY_MAX_MS = 8_000
+
+function resumeRetryDelayMs(attempt: number): number {
+  return Math.min(RESUME_RETRY_MAX_MS, RESUME_RETRY_BASE_MS * 2 ** attempt)
+}
+
 // HashRouter boot edge case: pathname briefly reads `/` before the hash is
 // parsed. If the hash references a real session, defer; resume picks it up
 // next tick. Without this, ctrl+R on `#/:sessionId` flashes 5 loading states.
@@ -49,6 +74,8 @@ export function useRouteResume({
   gatewayState,
   locationPathname,
   resumeSession,
+  resumeFailedSessionId,
+  resumeExhaustedSessionId,
   routedSessionId,
   runtimeIdByStoredSessionIdRef,
   selectedStoredSessionId,
@@ -56,13 +83,29 @@ export function useRouteResume({
   startFreshSessionDraft
 }: RouteResumeOptions) {
   const lastPathnameRef = useRef<string | null>(null)
+  const seenGatewayStateRef = useRef(false)
   const wasGatewayOpenRef = useRef(false)
+  // Per-session retry bookkeeping for the bounded auto-retry effect below. Keyed
+  // by the session id we're retrying so switching chats resets the counter.
+  const retrySessionIdRef = useRef<string | null>(null)
+  const retryAttemptRef = useRef(0)
+  // Tracks the previous exhausted-latch value so we can detect its armed->cleared
+  // edge. resumeSession clears $resumeExhaustedSessionId on a manual Retry /
+  // reconnect / reselect; that transition is our cue to reset the attempt counter
+  // for a fresh backoff cycle on the SAME session (the auto-retry loop itself
+  // never touches this latch, so it can't spuriously trigger the reset).
+  const prevResumeExhaustedRef = useRef<string | null>(null)
 
   useEffect(() => {
     const gatewayOpen = gatewayState === 'open'
     const pathnameChanged = lastPathnameRef.current !== locationPathname
-    const gatewayBecameOpen = !wasGatewayOpenRef.current && gatewayOpen
+    // Fire only on a genuine closed->open transition (a reconnect). seenGatewayStateRef
+    // stays false until the first effect run, so a session that mounts with the gateway
+    // already open is not mistaken for "became open" and does not double-resume with the
+    // pathname-driven initial resume below.
+    const gatewayBecameOpen = seenGatewayStateRef.current && !wasGatewayOpenRef.current && gatewayOpen
     lastPathnameRef.current = locationPathname
+    seenGatewayStateRef.current = true
     wasGatewayOpenRef.current = gatewayOpen
 
     if (currentView !== 'chat' || !gatewayOpen) {
@@ -77,12 +120,33 @@ export function useRouteResume({
         Boolean(cachedRuntime) &&
         cachedRuntime === activeSessionIdRef.current
 
-      // Resume only when the route meaningfully changed (or gateway just opened).
-      // This avoids a transient /:sid re-resume during "new chat" state clears
+      // Self-heal a desynced view: the route points at a session that isn't the
+      // loaded one. A create/stream race can leave selected/active null while
+      // the route stays on /:sid (symptom: brand-new chat shows "Thinking" then
+      // an empty transcript even though the turn completed and persisted). The
+      // pathname didn't change, so the normal gate would skip and the view stays
+      // stuck empty forever. selectedStoredSessionIdRef is set synchronously at
+      // resume entry, so this can't loop; the resume's cached fast-path restores
+      // the already-streamed messages without a refetch.
+      //
+      // Crucially this must NOT fire during a /:sid -> /new transition, where
+      // startFreshSessionDraft nulls selected/active one render before the
+      // pathname flips to / (same null+/:sid signature). freshDraftReady is the
+      // discriminator: it's true while heading into a blank new chat, false when
+      // genuinely stranded on a routed session.
+      const stuckOnRoutedSession = routedSessionId !== selectedStoredSessionIdRef.current && !freshDraftReady
+
+      // Resume when the route meaningfully changed, the gateway just opened, or
+      // we're stranded on a routed session that never loaded. The first two
+      // guard against a transient /:sid re-resume during "new chat" state clears
       // before the pathname updates from /:sid -> /.
-      const shouldResume = pathnameChanged || gatewayBecameOpen
+      const shouldResume = pathnameChanged || gatewayBecameOpen || stuckOnRoutedSession
 
-      if (!alreadyActive && shouldResume && !creatingSessionRef.current) {
+      // On a reconnect (gatewayBecameOpen) re-resume even when the route looks
+      // `alreadyActive`: the cached runtime id can be stale once the gateway
+      // rebinds/reaps the session on its side, and trusting it strands Desktop on
+      // a dead id ("session not found"). Otherwise keep skipping when already active.
+      if ((gatewayBecameOpen || !alreadyActive) && shouldResume && !creatingSessionRef.current) {
         void resumeSession(routedSessionId, true)
       }
 
@@ -112,4 +176,111 @@ export function useRouteResume({
     selectedStoredSessionIdRef,
     startFreshSessionDraft
   ])
+
+  // Bounded auto-retry: when the routed session's resume failed terminally
+  // (resumeFailedSessionId matches the route), schedule a backoff retry so the
+  // window recovers on its own instead of latching the loader forever. This is
+  // the safety net the main effect above can't provide: after a failed resume,
+  // selectedStoredSessionIdRef.current already equals the route (resumeSession
+  // sets it synchronously at entry) and the pathname/gateway are unchanged, so
+  // none of stuckOnRoutedSession / pathnameChanged / gatewayBecameOpen fire
+  // again. resumeSession clears resumeFailedSessionId on its next attempt; a
+  // success keeps it clear (the effect's guard then no-ops), a repeat failure
+  // re-arms it and we back off further, capped at MAX_RESUME_RETRIES.
+  useEffect(() => {
+    // Detect the exhausted-latch armed->cleared edge for the current route. Only
+    // resumeSession clears $resumeExhaustedSessionId (manual Retry / reconnect /
+    // reselect) — the auto-retry loop never touches it — so this transition
+    // uniquely means "the user asked for another go." Reset the attempt counter
+    // for a fresh bounded backoff cycle on the SAME session. Without this,
+    // retryAttemptRef stays pinned at MAX after exhaustion (the !stranded reset
+    // below only fires on a route CHANGE to a different session), so a manual
+    // retry on the same stranded session would get exactly ONE attempt and then
+    // immediately re-arm the exhausted error — never the renewed backoff cycle
+    // the store/session.ts + use-session-actions.ts comments promise. (Point 2)
+    const wasExhausted = prevResumeExhaustedRef.current
+    prevResumeExhaustedRef.current = resumeExhaustedSessionId
+    if (wasExhausted && wasExhausted === routedSessionId && resumeExhaustedSessionId !== wasExhausted) {
+      retrySessionIdRef.current = routedSessionId
+      retryAttemptRef.current = 0
+    }
+
+    if (currentView !== 'chat' || gatewayState !== 'open') {
+      return
+    }
+
+    const stranded =
+      Boolean(routedSessionId) &&
+      resumeFailedSessionId === routedSessionId &&
+      !creatingSessionRef.current
+
+    if (!stranded) {
+      // Route moved off the stranded session (or it recovered) — reset the
+      // counter so a future failure on another session starts fresh, and clear
+      // any exhausted-latch armed for a session we're no longer viewing (never
+      // the current route: that's the error state we want to keep showing).
+      // resumeSession also clears it on a fresh attempt; this covers a plain
+      // route-change away from the stranded window.
+      if (retrySessionIdRef.current !== routedSessionId) {
+        retrySessionIdRef.current = null
+        retryAttemptRef.current = 0
+        setResumeExhaustedSessionId(current => (current && current !== routedSessionId ? null : current))
+      }
+
+      return
+    }
+
+    // New stranded session id → reset the attempt counter.
+    if (retrySessionIdRef.current !== routedSessionId) {
+      retrySessionIdRef.current = routedSessionId
+      retryAttemptRef.current = 0
+    }
+
+    if (retryAttemptRef.current >= MAX_RESUME_RETRIES) {
+      // Give up auto-retrying a persistently dead backend; the user can still
+      // reconnect / reselect (which resets the counter via the branch above).
+      // Surface an explicit error + manual Retry in the chat view instead of
+      // spinning the loader forever — resumeSession (manual Retry / reconnect /
+      // reselect) clears this latch and resets the counter for a fresh cycle.
+      setResumeExhaustedSessionId(routedSessionId)
+
+      return
+    }
+
+    const attempt = retryAttemptRef.current
+    const sessionId = routedSessionId as string
+
+    const timer = setTimeout(() => {
+      // Re-check liveness at fire time: a resume may have landed while we waited.
+      if (
+        creatingSessionRef.current ||
+        selectedStoredSessionIdRef.current !== sessionId ||
+        activeSessionIdRef.current !== null
+      ) {
+        return
+      }
+
+      // Consume an attempt ONLY now that a resume is actually dispatching.
+      // Incrementing at schedule time (the old behavior) let unrelated dep
+      // changes during the 1s–8s backoff window — a transient gatewayState
+      // flip, a non-referentially-stable resumeSession — clear the pending
+      // timer and re-run the effect, burning an attempt without any resume
+      // having fired. A flapping backend could then hit MAX in a couple of
+      // re-renders with far fewer than MAX real attempts. (Point 3)
+      retryAttemptRef.current += 1
+      void resumeSession(sessionId, true)
+    }, resumeRetryDelayMs(attempt))
+
+    return () => clearTimeout(timer)
+  }, [
+    activeSessionIdRef,
+    creatingSessionRef,
+    currentView,
+    gatewayState,
+    resumeSession,
+    resumeFailedSessionId,
+    resumeExhaustedSessionId,
+    routedSessionId,
+    selectedStoredSessionIdRef
+  ])
 }