fix(desktop): queue prompts during context compaction (#69783)

apps/desktop/e2e/fixtures.ts

@@ -141,22 +141,29 @@ export function createSandbox(prefix: string): Sandbox {
  * mock inference server. The provider is set as the active model provider so
  * the desktop app skips onboarding and boots straight to the chat UI.
  *
- * @param extraConfig  optional YAML lines appended to the `display:` section,
- *   used by the interim-message e2e test to toggle
- *   `display.interim_assistant_messages`.
+ * @param extraDisplayConfig optional YAML lines appended to the `display:`
+ *   section, used by the interim-message e2e test.
+ * @param extraConfig optional top-level YAML sections for a test scenario.
+ * @param modelContextLength optional primary-model context limit.
  */
-export function writeMockProviderConfig(hermesHome: string, mockUrl: string, extraConfig?: string): void {
+export function writeMockProviderConfig(
+  hermesHome: string,
+  mockUrl: string,
+  extraDisplayConfig?: string,
+  extraConfig?: string,
+  modelContextLength?: number,
+): void {
   const configPath = path.join(hermesHome, 'config.yaml')
 
-  const displaySection = extraConfig
-    ? `\ndisplay:\n${extraConfig}\n`
+  const displaySection = extraDisplayConfig
+    ? `\ndisplay:\n${extraDisplayConfig}\n`
     : ''
 
   const config = `# Auto-generated by E2E test fixtures
 model:
   default: mock-model
   provider: mock
-providers:
+${modelContextLength ? `  context_length: ${modelContextLength}\n` : ''}providers:
   mock:
     api: ${mockUrl}/v1
     name: Mock
@@ -165,7 +172,7 @@ providers:
     models:
       mock-model: {}
     context_length: 4096
-${displaySection}`
+${displaySection}${extraConfig ? `\n${extraConfig.trim()}\n` : ''}`
 
   fs.writeFileSync(configPath, config, 'utf8')
 }
@@ -339,6 +346,10 @@ export interface MockBackendOptions {
    * `display.interim_assistant_messages`.
    */
   extraDisplayConfig?: string
+  /** Additional top-level config.yaml sections for an E2E scenario. */
+  extraConfig?: string
+  /** Override the mock model's context window for compression scenarios. */
+  modelContextLength?: number
 }
 
 /**
@@ -358,7 +369,13 @@ export async function setupMockBackend(options: MockBackendOptions = {}): Promis
 
   // 2. Create sandbox + write config
   const sandbox = createSandbox('mock')
-  writeMockProviderConfig(sandbox.hermesHome, mock.url, options.extraDisplayConfig)
+  writeMockProviderConfig(
+    sandbox.hermesHome,
+    mock.url,
+    options.extraDisplayConfig,
+    options.extraConfig,
+    options.modelContextLength,
+  )
   writeEnvFile(sandbox.hermesHome)
 
   // 3. Build env + launch

apps/desktop/e2e/mock-server.ts

@@ -23,6 +23,8 @@ export const MOCK_REPLY = 'Hello from the mock inference server! The full boot c
 export interface MockServerOptions {
   /** Pause the matching stream after its first token for session-switch E2E coverage. */
   holdFirstStreamForPrompt?: string
+  /** Pause the first completion whose request JSON contains this text. */
+  holdFirstCompletionContaining?: string
 }
 
 export interface MockServer {
@@ -30,7 +32,9 @@ export interface MockServer {
   url: string
   receivedPrompts: string[]
   waitForHeldStream: () => Promise<void>
+  waitForHeldCompletion: () => Promise<void>
   releaseHeldStream: () => void
+  heldCompletionCount: () => number
   close: () => Promise<void>
 }
 
@@ -248,6 +252,7 @@ export function startMockServer(options: MockServerOptions = {}): Promise<MockSe
     const receivedPrompts: string[] = []
     let resolveHeldStreamStarted: (() => void) | null = null
     let releaseHeldStream: (() => void) | null = null
+    let heldCompletionCount = 0
     const heldStreamStarted = new Promise<void>(resolveHeld => {
       resolveHeldStreamStarted = resolveHeld
     })
@@ -313,6 +318,11 @@ export function startMockServer(options: MockServerOptions = {}): Promise<MockSe
 
           const stream = parsed.stream === true
           const model = parsed.model || 'mock-model'
+          const holdThisCompletion = Boolean(
+            options.holdFirstCompletionContaining &&
+            heldCompletionCount === 0 &&
+            JSON.stringify(parsed).includes(options.holdFirstCompletionContaining),
+          )
 
           // Detect the interim-message test trigger: the user's message
           // contains a specific keyword. The mock walks through the
@@ -405,12 +415,21 @@ export function startMockServer(options: MockServerOptions = {}): Promise<MockSe
               options.holdFirstStreamForPrompt && typeof lastUserMessage?.content === 'string' &&
                 lastUserMessage.content.includes(options.holdFirstStreamForPrompt),
             )
-            streamTextResponse(res, model, MOCK_REPLY, holdThisStream ? () => {
+            streamTextResponse(res, model, MOCK_REPLY, holdThisStream || holdThisCompletion ? () => {
+              if (holdThisCompletion) {
+                heldCompletionCount++
+              }
               resolveHeldStreamStarted?.()
               return heldStreamReleased
             } : undefined)
           } else {
-            nonStreamingTextResponse(res, model, MOCK_REPLY)
+            if (holdThisCompletion) {
+              heldCompletionCount++
+              resolveHeldStreamStarted?.()
+              void heldStreamReleased.then(() => nonStreamingTextResponse(res, model, MOCK_REPLY))
+            } else {
+              nonStreamingTextResponse(res, model, MOCK_REPLY)
+            }
           }
         })
 
@@ -443,7 +462,9 @@ export function startMockServer(options: MockServerOptions = {}): Promise<MockSe
         url,
         receivedPrompts,
         waitForHeldStream: () => heldStreamStarted,
+        waitForHeldCompletion: () => heldStreamStarted,
         releaseHeldStream: () => releaseHeldStream?.(),
+        heldCompletionCount: () => heldCompletionCount,
         close: () =>
           new Promise((resolveClose, rejectClose) => {
             server.close((err) => {

apps/desktop/e2e/session-compression-and-queue-stop.spec.ts

@@ -9,15 +9,23 @@ import {
   setupMockBackend,
   waitForAppReady,
 } from './fixtures'
-import { receivedUserTexts, restartMockServer } from './mock-server'
+import { MOCK_REPLY, receivedUserTexts, restartMockServer } from './mock-server'
 
-async function send(page: Page, text: string): Promise<void> {
+async function send(page: Page, text: string, delay = 15): Promise<void> {
   const composer = page.locator('[contenteditable="true"]').first()
   await composer.click()
-  await composer.type(text, { delay: 15 })
+  await composer.type(text, { delay })
   await page.keyboard.press('Enter')
 }
 
+async function pasteAndSend(page: Page, text: string): Promise<void> {
+  const composer = page.locator('[contenteditable="true"]').first()
+  await composer.click()
+  await page.keyboard.insertText(text)
+  await page.keyboard.press('Enter')
+}
+
+
 async function waitForTranscript(page: Page, text: string, timeout = 90_000): Promise<void> {
   await page.waitForFunction(
     expected => document.querySelector('[data-slot="aui_thread-viewport"]')?.textContent?.includes(expected) ?? false,
@@ -81,3 +89,58 @@ test.describe('session compression', () => {
     await page.screenshot({ path: 'test-results/session-compression-continuation.png' })
   })
 })
+
+test.describe('session compression in progress', () => {
+  let fixture: MockBackendFixture
+
+  test.beforeAll(async () => {
+    fixture = await setupMockBackend({
+      modelContextLength: 64_000,
+      extraConfig: `compression:
+  threshold_tokens: 22000
+  protect_first_n: 0
+  protect_last_n: 1
+auxiliary:
+  compression:
+    provider: custom
+    model: mock-model`,
+      mockServer: {
+        holdFirstCompletionContaining: 'You are a summarization agent creating a context checkpoint.',
+      }
+    })
+    await waitForAppReady(fixture, 120_000)
+  })
+
+  test.afterAll(async () => {
+    await fixture?.cleanup()
+  })
+
+  test('queues an Enter-submitted draft instead of steering while compaction is active', async ({}, testInfo) => {
+    const { page } = fixture
+    const queued = 'E2E_QUEUED_DURING_COMPACTION'
+
+    // A normal message crosses the tiny configured context budget. The mock
+    // blocks only the resulting summary request, so these assertions run
+    // during automatic compaction rather than a slash-command path.
+    await pasteAndSend(page, 'E2E_COMPACTION_HISTORY_ONE '.repeat(5))
+    await waitForTranscript(page, MOCK_REPLY)
+    await pasteAndSend(page, 'E2E_COMPACTION_HISTORY_TWO '.repeat(5))
+    await waitForTranscript(page, MOCK_REPLY)
+    await pasteAndSend(page, 'E2E_TRIGGER_AUTOMATIC_COMPACTION '.repeat(500))
+    await fixture.mock.waitForHeldCompletion()
+    await expect(page.getByRole('status', { name: 'Summarizing thread' }).last()).toBeVisible()
+
+    const primary = page.locator('[data-slot="composer-root"] button[type="submit"]')
+    await expect(primary).toHaveAttribute('aria-label', 'Queue message')
+
+    await send(page, queued)
+    await expect(page.getByText('1 Queued')).toBeVisible()
+    expect(fixture.mock.heldCompletionCount()).toBe(1)
+    expect(receivedUserTexts()).not.toContain(queued)
+    await page.screenshot({ path: testInfo.outputPath('queued-during-compaction.png') })
+
+    fixture.mock.releaseHeldStream()
+    await expect.poll(() => receivedUserTexts().filter(text => text === queued).length).toBe(1)
+    expect(fixture.mock.heldCompletionCount()).toBe(1)
+  })
+})

apps/desktop/src/app/chat/composer/hooks/use-composer-submit.test.tsx

@@ -8,10 +8,11 @@ import { useComposerSubmit } from './use-composer-submit'
 interface SubmitHarnessOptions {
   attachments?: ComposerAttachment[]
   busy?: boolean
+  compacting?: boolean
   text?: string
 }
 
-function renderSubmitHook({ attachments = [], busy = false, text = '' }: SubmitHarnessOptions = {}) {
+function renderSubmitHook({ attachments = [], busy = false, compacting = false, text = '' }: SubmitHarnessOptions = {}) {
   const draftRef = { current: text }
   const editor = document.createElement('div')
   editor.dataset.slot = 'composer-rich-input'
@@ -33,6 +34,7 @@ function renderSubmitHook({ attachments = [], busy = false, text = '' }: SubmitH
       activeQueueSessionKeyRef: { current: 'stored-session' },
       attachments,
       busy,
+      compacting,
       clearDraft,
       disabled: false,
       draftRef,
@@ -79,6 +81,23 @@ describe('useComposerSubmit busy-turn routing', () => {
     expect(onSubmit).not.toHaveBeenCalled()
   })
 
+  it('queues a plain-text follow-up while the active turn is compacting', () => {
+    const { hook, onCancel, onSteer, onSubmit, queueCurrentDraft } = renderSubmitHook({
+      busy: true,
+      compacting: true,
+      text: 'wait for the summary'
+    })
+
+    act(() => {
+      hook.result.current.submitDraft()
+    })
+
+    expect(queueCurrentDraft).toHaveBeenCalledTimes(1)
+    expect(onSteer).not.toHaveBeenCalled()
+    expect(onSubmit).not.toHaveBeenCalled()
+    expect(onCancel).not.toHaveBeenCalled()
+  })
+
   it('runs slash commands immediately while busy', async () => {
     const { clearDraft, hook, onCancel, onSteer, onSubmit, queueCurrentDraft } = renderSubmitHook({
       busy: true,

apps/desktop/src/app/chat/composer/hooks/use-composer-submit.ts

@@ -17,6 +17,7 @@ interface UseComposerSubmitArgs {
   activeQueueSessionKeyRef: RefObject<string | null>
   attachments: ComposerAttachment[]
   busy: boolean
+  compacting: boolean
   clearDraft: () => void
   disabled: boolean
   draftRef: RefObject<string>
@@ -51,6 +52,7 @@ export function useComposerSubmit({
   activeQueueSessionKeyRef,
   attachments,
   busy,
+  compacting,
   clearDraft,
   disabled,
   draftRef,
@@ -149,7 +151,7 @@ export function useComposerSubmit({
         triggerHaptic('submit')
         clearDraft()
         dispatchSubmit(text)
-      } else if (!attachments.length && text.trim()) {
+      } else if (!compacting && !attachments.length && text.trim()) {
         // Cursor-style stop-and-correct: interrupt the live turn and redirect
         // it with this text. redirect() preserves the shown reasoning/work; if
         // the turn already ended, steerDraft re-queues so nothing is lost.

apps/desktop/src/app/chat/composer/index.tsx

@@ -11,6 +11,7 @@ import { sanitizeComposerInput } from '@/lib/composer-input-sanitize'
 import { DATA_IMAGE_URL_RE } from '@/lib/embedded-images'
 import { triggerHaptic } from '@/lib/haptics'
 import { cn } from '@/lib/utils'
+import { $compactionActive } from '@/store/compaction'
 import { browseBackward, browseForward, deriveUserHistory, isBrowsingHistory } from '@/store/composer-input-history'
 import { POPOUT_WIDTH_REM } from '@/store/composer-popout'
 import { parkQueuedPrompts, removeQueuedPrompt, unparkQueuedPrompts } from '@/store/composer-queue'
@@ -104,6 +105,7 @@ export function ChatBar({
   // focus-bus key, and awaiting-input edge. Main scope = the legacy globals.
   const scope = useComposerScope()
   const attachments = useStore(scope.attachments.$attachments)
+  const compacting = useStore($compactionActive)
   const scrolledUp = useStore($threadScrolledUp)
   const autoSpeak = useStore($autoSpeakReplies)
   // The turn is parked on the user (clarify / approval / sudo / secret). Esc must
@@ -230,11 +232,15 @@ export function ChatBar({
 
   // Steer only makes sense mid-turn, text-only (the gateway can't carry images
   // into a tool result) and never for a slash command (those execute inline).
-  const canSteer = busy && !!onSteer && attachments.length === 0 && isSteerableText
+  const canSteer = busy && !compacting && !!onSteer && attachments.length === 0 && isSteerableText
 
   // While busy: text redirects the live turn (Cursor-style stop-and-correct),
   // attachments queue for the next turn, an empty composer stops.
-  const busyAction: 'steer' | 'queue' | 'stop' = canSteer ? 'steer' : hasComposerPayload ? 'queue' : 'stop'
+  const busyAction: 'steer' | 'queue' | 'stop' = canSteer
+    ? 'steer'
+    : compacting || hasComposerPayload
+      ? 'queue'
+      : 'stop'
 
   // The submit engine — the orchestration seam where draft + queue meet. Owns
   // the submit decision tree, the send-with-restore primitive, and steer.
@@ -243,6 +249,7 @@ export function ChatBar({
     activeQueueSessionKeyRef,
     attachments,
     busy,
+    compacting,
     clearDraft,
     disabled,
     draftRef,