fix(history): retry failed session tree removals

Tombstoned session trees whose removal fails transiently (e.g., EBUSY
under Windows AV) are now re-queued in-process with bounded exponential
backoff instead of sitting until the next HistoryManager construction.
Prevents a single stuck tree from blocking the entire Orca process.

src/main/daemon/terminal-history-session-tombstone-retry.test.ts

@@ -0,0 +1,77 @@
+import { mkdirSync, mkdtempSync, rmSync, writeFileSync } from 'node:fs'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
+
+const { removeHostTreeMock } = vi.hoisted(() => ({
+  removeHostTreeMock: vi.fn<(dir: string) => Promise<void>>()
+}))
+
+vi.mock('../host-tree-removal', () => ({
+  removeHostTree: removeHostTreeMock
+}))
+
+import { getHistorySessionDirName } from './history-paths'
+import {
+  cancelPendingSessionTreeRemovalRetries,
+  removeTerminalHistorySessionTrees,
+  SESSION_TREE_REMOVAL_RETRY_DELAYS_MS
+} from './terminal-history-session-tombstone'
+
+/** Mirrors the worktree-level tombstone retry: a session tree whose rm fails must be re-queued
+ *  in-process instead of waiting for the next HistoryManager construction. */
+describe('tombstoned session tree removal retries', () => {
+  let basePath: string
+
+  beforeEach(() => {
+    basePath = mkdtempSync(join(tmpdir(), 'orca-session-tombstone-retry-'))
+    removeHostTreeMock.mockReset()
+    vi.useFakeTimers()
+  })
+
+  afterEach(() => {
+    cancelPendingSessionTreeRemovalRetries()
+    vi.useRealTimers()
+    rmSync(basePath, { recursive: true, force: true })
+  })
+
+  function seedSession(sessionId: string): void {
+    const dir = join(basePath, getHistorySessionDirName(sessionId))
+    mkdirSync(dir, { recursive: true })
+    writeFileSync(join(dir, 'segment-0.log'), 'x')
+  }
+
+  it('re-queues a tombstone whose removal failed, then stops after the last attempt', async () => {
+    seedSession('session-busy')
+    removeHostTreeMock.mockRejectedValue(
+      Object.assign(new Error('resource busy'), { code: 'EBUSY' })
+    )
+
+    await removeTerminalHistorySessionTrees(basePath, 'session-busy')
+    await vi.advanceTimersByTimeAsync(0)
+    expect(removeHostTreeMock).toHaveBeenCalledTimes(1)
+
+    for (const [index, retryDelayMs] of SESSION_TREE_REMOVAL_RETRY_DELAYS_MS.entries()) {
+      await vi.advanceTimersByTimeAsync(retryDelayMs)
+      expect(removeHostTreeMock).toHaveBeenCalledTimes(index + 2)
+    }
+
+    // Bounded: a permanently wedged tree waits for the next construction's drain.
+    await vi.advanceTimersByTimeAsync(60 * 60_000)
+    expect(removeHostTreeMock).toHaveBeenCalledTimes(
+      SESSION_TREE_REMOVAL_RETRY_DELAYS_MS.length + 1
+    )
+    expect(removeHostTreeMock).toHaveBeenLastCalledWith(expect.stringContaining('.pending-delete'))
+  })
+
+  it('does not re-arm a retry after the removal succeeds', async () => {
+    seedSession('session-clean')
+    removeHostTreeMock.mockResolvedValue(undefined)
+
+    await removeTerminalHistorySessionTrees(basePath, 'session-clean')
+    await vi.advanceTimersByTimeAsync(0)
+    await vi.advanceTimersByTimeAsync(SESSION_TREE_REMOVAL_RETRY_DELAYS_MS[0])
+
+    expect(removeHostTreeMock).toHaveBeenCalledTimes(1)
+  })
+})

src/main/daemon/terminal-history-session-tombstone.ts

@@ -12,6 +12,11 @@ import { getTerminalHistoryQuarantineOwnerDir } from './terminal-history-recover
 const PENDING_DELETE_DIR_NAME = '.pending-delete'
 
 const pendingSessionTreeRemovals = new Map<string, Promise<void>>()
+// Why: a tombstone whose rm fails once (Windows EBUSY under AV) would otherwise sit on disk until the
+// next HistoryManager construction. Bounded so a genuinely wedged tree stops burning timers.
+export const SESSION_TREE_REMOVAL_RETRY_DELAYS_MS = [30_000, 120_000]
+const sessionTreeRemovalAttempts = new Map<string, number>()
+const sessionTreeRemovalRetryTimers = new Map<string, ReturnType<typeof setTimeout>>()
 
 export function isTerminalHistoryPendingDeleteEntry(name: string): boolean {
   return name === PENDING_DELETE_DIR_NAME
@@ -33,15 +38,42 @@ function tombstoneSessionTree(basePath: string, dir: string): string | null {
   }
 }
 
+function scheduleSessionTreeRemovalRetry(dir: string): void {
+  const attempt = sessionTreeRemovalAttempts.get(dir) ?? 0
+  const retryDelayMs = SESSION_TREE_REMOVAL_RETRY_DELAYS_MS[attempt]
+  if (retryDelayMs === undefined) {
+    // Out of in-process attempts: the tombstone stays queued for the next construction's drain.
+    sessionTreeRemovalAttempts.delete(dir)
+    return
+  }
+  sessionTreeRemovalAttempts.set(dir, attempt + 1)
+  const timer = setTimeout(() => {
+    sessionTreeRemovalRetryTimers.delete(dir)
+    scheduleSessionTreeRemoval(dir)
+  }, retryDelayMs)
+  timer.unref?.()
+  sessionTreeRemovalRetryTimers.set(dir, timer)
+}
+
 function scheduleSessionTreeRemoval(dir: string): void {
   if (pendingSessionTreeRemovals.has(dir)) {
     return
   }
+  // A rescan (startup drain) hitting the same tombstone supersedes its pending retry.
+  const pendingRetry = sessionTreeRemovalRetryTimers.get(dir)
+  if (pendingRetry) {
+    clearTimeout(pendingRetry)
+    sessionTreeRemovalRetryTimers.delete(dir)
+  }
   const removal = removeHostTree(dir)
+    .then(() => {
+      sessionTreeRemovalAttempts.delete(dir)
+    })
     .catch((err: unknown) => {
       console.warn(
         `[history] Failed to delete tombstoned session tree: ${err instanceof Error ? err.message : String(err)}`
       )
+      scheduleSessionTreeRemovalRetry(dir)
     })
     .finally(() => {
       if (pendingSessionTreeRemovals.get(dir) === removal) {
@@ -91,6 +123,15 @@ export function schedulePendingSessionTreeRemovals(basePath: string): void {
   }
 }
 
+/** Drop every armed retry timer so a fixture teardown cannot resurrect a removal. Tests only. */
+export function cancelPendingSessionTreeRemovalRetries(): void {
+  for (const timer of sessionTreeRemovalRetryTimers.values()) {
+    clearTimeout(timer)
+  }
+  sessionTreeRemovalRetryTimers.clear()
+  sessionTreeRemovalAttempts.clear()
+}
+
 /** Await the in-flight tombstone removals. Tests only — production reclaims off the critical path and
  *  re-queues whatever a quit interrupted on the next HistoryManager construction. */
 export async function flushPendingSessionTreeRemovals(): Promise<void> {

src/main/ipc/worktrees.test.ts

@@ -8245,8 +8245,10 @@ describe('registerWorktreeHandlers', () => {
     ])
     // Why order matters: linked-path deletion is destructive, so PTYs must release every handle
     // before Windows or WSL filesystem cleanup starts (mirrors the runtime removal path).
-    expect(killAllProcessesForWorktreeMock.mock.invocationCallOrder[0]).toBeLessThan(
-      removeWorktreeLinkedPathsMock.mock.invocationCallOrder[0]
+    expect(killAllProcessesForWorktreeMock).toHaveBeenCalled()
+    // Latest PTY sweep vs earliest deletion: a later sweep would mean handles were still open.
+    expect(Math.max(...killAllProcessesForWorktreeMock.mock.invocationCallOrder)).toBeLessThan(
+      Math.min(...removeWorktreeLinkedPathsMock.mock.invocationCallOrder)
     )
   })