fix(mobile): keep repeated-prefix chat replies streaming

Text alone can't tell "the transcript caught up with this stream" from
"a new reply repeats the previous turn's prefix", so the old suppress-on-
prefix rule swallowed genuine repeated replies. A stateful gate remembers
which transcript tail predates the current stream segment and hides the
bubble only when that tail moved during the segment, scoped to the active
host/workspace/tab/session so a swapped chat can't inherit a baseline.

Refs STA-3333.

mobile/src/session/MobileNativeChatOverlay.tsx

@@ -49,6 +49,7 @@ export function MobileNativeChatOverlay({
         agent={controller.nativeChatAgent}
         agentWorking={controller.nativeChatAgentWorking}
         streamingText={controller.nativeChatStreamingText}
+        streamIdentity={controller.nativeChatStreamIdentity}
         onStop={controller.handleNativeChatStop}
         ask={controller.nativeChatAsk}
         onAnswerAsk={controller.handleNativeChatAnswerAsk}

mobile/src/session/MobileNativeChatView.test.ts

@@ -1,6 +1,7 @@
 import { createElement } from 'react'
 import { act, create, type ReactTestInstance, type ReactTestRenderer } from 'react-test-renderer'
 import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
+import type { NativeChatMessage } from '../../../src/shared/native-chat-types'
 import { MobileNativeChatView } from './MobileNativeChatView'
 
 vi.mock('react-native', () => ({
@@ -58,6 +59,9 @@ vi.mock('./MobileNativeChatComposer', async () => {
 })
 
 type Overrides = {
+  messages?: Parameters<typeof MobileNativeChatView>[0]['messages']
+  streamingText?: string
+  streamIdentity?: string
   sendErrorMessage?: string | null
   onClearSendError?: () => void
   inputLockReason?: 'disconnected' | 'waiting' | null
@@ -75,6 +79,23 @@ function suppressRendererWarning(): () => void {
   return () => spy.mockRestore()
 }
 
+function assistantTurn(id: string, text: string): NativeChatMessage {
+  return { id, role: 'assistant', blocks: [{ type: 'text', text }], timestamp: 0, source: 'hook' }
+}
+
+function chatViewElement(overrides: Overrides): ReturnType<typeof createElement> {
+  return createElement(MobileNativeChatView, {
+    messages: [],
+    status: 'ready',
+    streamIdentity: 'test-stream',
+    onSend: vi.fn().mockResolvedValue(true),
+    pending: [],
+    composerText: '',
+    onComposerTextChange: vi.fn(),
+    ...overrides
+  })
+}
+
 describe('MobileNativeChatView send-error banner', () => {
   let renderer: ReactTestRenderer | null = null
 
@@ -91,23 +112,25 @@ describe('MobileNativeChatView send-error banner', () => {
     const restore = suppressRendererWarning()
     try {
       await act(async () => {
-        renderer = create(
-          createElement(MobileNativeChatView, {
-            messages: [],
-            status: 'ready',
-            onSend: overrides.onSend ?? vi.fn().mockResolvedValue(true),
-            pending: [],
-            composerText: '',
-            onComposerTextChange: vi.fn(),
-            ...overrides
-          })
-        )
+        renderer = create(chatViewElement(overrides))
       })
     } finally {
       restore()
     }
   }
 
+  async function update(overrides: Overrides = {}): Promise<void> {
+    await act(async () => {
+      renderer?.update(chatViewElement(overrides))
+    })
+  }
+
+  /** Ids of the rows the list is currently rendering. */
+  function listIds(): string[] {
+    const list = renderer!.root.find((node) => node.type === 'FlatList')
+    return (list.props.data as { id: string }[]).map((row) => row.id)
+  }
+
   function banners(): ReactTestInstance[] {
     return renderer!.root.findAll((node) => node.props.accessibilityRole === 'alert')
   }
@@ -161,4 +184,37 @@ describe('MobileNativeChatView send-error banner', () => {
 
     expect(onClearSendError).toHaveBeenCalledOnce()
   })
+
+  it('keeps streaming a reply that repeats the previous turn as a prefix', async () => {
+    const prior = [assistantTurn('a1', 'The tests pass.')]
+    await render({ messages: prior })
+    expect(listIds()).toEqual(['a1'])
+
+    await update({ messages: prior, streamingText: 'The tests' })
+
+    expect(listIds()).toEqual(['a1', 'streaming'])
+  })
+
+  it('drops the streaming bubble once the reply lands as its own turn', async () => {
+    const prior = [assistantTurn('a1', 'Done.')]
+    await render({ messages: prior })
+    await update({ messages: prior, streamingText: 'Done.' })
+    expect(listIds()).toEqual(['a1', 'streaming'])
+
+    await update({
+      messages: [...prior, assistantTurn('a2', 'Done.')],
+      streamingText: 'Done.'
+    })
+
+    expect(listIds()).toEqual(['a1', 'a2'])
+  })
+
+  it("does not carry one chat's baseline into another stream identity", async () => {
+    const prior = [assistantTurn('a1', 'Shared answer text')]
+    await render({ messages: prior, streamIdentity: 'tab-a' })
+
+    await update({ messages: prior, streamingText: 'Shared answer', streamIdentity: 'tab-b' })
+
+    expect(listIds()).toEqual(['a1'])
+  })
 })

mobile/src/session/MobileNativeChatView.tsx

@@ -21,6 +21,7 @@ import {
   type MobileNativeChatPendingItem
 } from './mobile-native-chat-render-data'
 import { useMobileNativeChatAskDismiss } from './use-mobile-native-chat-ask-dismiss'
+import { useMobileNativeChatStreamingBubble } from './use-mobile-native-chat-streaming-bubble'
 import { useMobileNativeChatPinchGesture } from './use-mobile-native-chat-pinch-gesture'
 import { MobileAgentWorkingIndicator } from './MobileAgentWorkingIndicator'
 import type { PendingNativeChatImage } from './mobile-native-chat-image-attachment'
@@ -50,6 +51,8 @@ type Props = {
   /** Live partial assistant text while a turn is still streaming (from the agent
    *  status hook). Shown as an in-progress bubble until the transcript catches up. */
   streamingText?: string
+  /** Scopes streaming catch-up state to the active host/workspace/tab/session. */
+  streamIdentity: string
   hasMore?: boolean
   loadingEarlier?: boolean
   onLoadEarlier?: () => void
@@ -108,6 +111,7 @@ export function MobileNativeChatView({
   agentWorking,
   onStop,
   streamingText,
+  streamIdentity,
   hasMore,
   loadingEarlier,
   onLoadEarlier,
@@ -166,9 +170,14 @@ export function MobileNativeChatView({
   // route-owned optimistic queued messages. Memoize on the same deps so the
   // downstream autoscroll effects/`renderItem` keep referential stability.
   const foldedMessages = useMemo(() => foldMobileNativeChatMessages(messages), [messages])
+  const streaming = useMobileNativeChatStreamingBubble(
+    foldedMessages,
+    streamingText,
+    streamIdentity
+  )
   const { data } = useMemo(
-    () => buildMobileNativeChatTransientData({ folded: foldedMessages, streamingText, pending }),
-    [foldedMessages, streamingText, pending]
+    () => buildMobileNativeChatTransientData({ folded: foldedMessages, streaming, pending }),
+    [foldedMessages, streaming, pending]
   )
 
   // Follow the tail as the conversation grows and keep the newest message above

mobile/src/session/mobile-native-chat-render-data.ts

@@ -7,6 +7,10 @@ import type { NativeChatMessage } from '../../../src/shared/native-chat-types'
 import { foldToolMessages } from './mobile-native-chat-blocks'
 import { normalizeImageTranscriptMessages } from './mobile-native-chat-image-transcript-markers'
 import { stripNoiseMessages } from './mobile-native-chat-noise'
+import {
+  createMobileNativeChatStreamingGate,
+  deriveMobileNativeChatStreaming
+} from './mobile-native-chat-streaming-gate'
 import type { MobileNativeChatStatus } from './use-mobile-native-chat-session'
 
 /** The centered empty-state copy for a chat with no messages, mirroring the
@@ -46,7 +50,9 @@ export type MobileNativeChatPendingItem = {
 /** Derive the list data from the raw transcript: fold tool turns into the
  *  assistant turn, optionally append a synthetic streaming bubble, then the
  *  route-owned optimistic "queued" messages at the tail. Returns the
- *  intermediate `folded`/`streaming` so the caller can memoize on them. */
+ *  intermediate `folded`/`streaming` so the caller can memoize on them.
+ *  One-shot form: derives the streaming bubble through a fresh gate (no
+ *  cross-tick memory); the live view threads its own gate instead. */
 export function buildMobileNativeChatData({
   messages,
   streamingText,
@@ -57,7 +63,12 @@ export function buildMobileNativeChatData({
   pending: MobileNativeChatPendingItem[]
 }): { folded: NativeChatMessage[]; streaming: string | null; data: NativeChatMessage[] } {
   const folded = foldMobileNativeChatMessages(messages)
-  return buildMobileNativeChatTransientData({ folded, streamingText, pending })
+  const { streaming } = deriveMobileNativeChatStreaming(
+    createMobileNativeChatStreamingGate(),
+    folded,
+    streamingText
+  )
+  return buildMobileNativeChatTransientData({ folded, streaming, pending })
 }
 
 export function foldMobileNativeChatMessages(messages: NativeChatMessage[]): NativeChatMessage[] {
@@ -68,16 +79,14 @@ export function foldMobileNativeChatMessages(messages: NativeChatMessage[]): Nat
 
 export function buildMobileNativeChatTransientData({
   folded,
-  streamingText,
+  streaming,
   pending
 }: {
   folded: NativeChatMessage[]
-  streamingText?: string
+  /** Streaming bubble text, already gated by `deriveMobileNativeChatStreaming`. */
+  streaming: string | null
   pending: MobileNativeChatPendingItem[]
 }): { folded: NativeChatMessage[]; streaming: string | null; data: NativeChatMessage[] } {
-  // Only show the streaming bubble while its text leads the transcript — once the
-  // real assistant turn lands with the same text, drop the synthetic one.
-  const streaming = deriveStreaming(folded, streamingText)
   const data: NativeChatMessage[] = [
     ...folded,
     ...(streaming
@@ -106,26 +115,3 @@ export function buildMobileNativeChatTransientData({
   ]
   return { folded, streaming, data }
 }
-
-function deriveStreaming(folded: NativeChatMessage[], streamingText?: string): string | null {
-  const text = streamingText?.trim()
-  if (!text) {
-    return null
-  }
-  const last = folded[folded.length - 1]
-  const lastText =
-    last?.role === 'assistant'
-      ? last.blocks
-          .filter((b) => b.type === 'text')
-          .map((b) => (b.type === 'text' ? b.text : ''))
-          .join('')
-          .trim()
-      : ''
-  // Hide the synthetic bubble only once the real turn has landed leading with the
-  // streamed text. A bare length compare would suppress a short new reply behind a
-  // longer previous turn; a completed prior turn won't start with the new prefix.
-  if (lastText.startsWith(text)) {
-    return null
-  }
-  return text
-}

mobile/src/session/mobile-native-chat-streaming-gate.test.ts

@@ -0,0 +1,138 @@
+import { describe, expect, it } from 'vitest'
+import type { NativeChatMessage } from '../../../src/shared/native-chat-types'
+import {
+  createMobileNativeChatStreamingGate,
+  deriveMobileNativeChatStreaming,
+  type MobileNativeChatStreamingGate
+} from './mobile-native-chat-streaming-gate'
+
+function assistant(id: string, text: string): NativeChatMessage {
+  return {
+    id,
+    role: 'assistant',
+    blocks: [{ type: 'text', text }],
+    timestamp: 0,
+    source: 'transcript'
+  }
+}
+
+/** Run a sequence of (folded, streamingText) ticks through one gate. */
+function run(ticks: { folded: NativeChatMessage[]; text?: string }[]): {
+  gate: MobileNativeChatStreamingGate
+  results: (string | null)[]
+} {
+  let gate = createMobileNativeChatStreamingGate()
+  const results: (string | null)[] = []
+  for (const tick of ticks) {
+    const step = deriveMobileNativeChatStreaming(gate, tick.folded, tick.text)
+    gate = step.gate
+    results.push(step.streaming)
+  }
+  return { gate, results }
+}
+
+describe('deriveMobileNativeChatStreaming', () => {
+  it('shows a genuine reply that repeats the previous turn as a prefix', () => {
+    const prior = [assistant('a1', 'The tests pass.')]
+    const { results } = run([
+      { folded: prior }, // idle tick anchors the pre-stream tail
+      { folded: prior, text: 'The' },
+      { folded: prior, text: 'The tests' },
+      { folded: prior, text: 'The tests pass.' }
+    ])
+    expect(results).toEqual([null, 'The', 'The tests', 'The tests pass.'])
+  })
+
+  it('hides the bubble once the real turn lands leading with the streamed text', () => {
+    const prior = [assistant('a1', 'earlier turn')]
+    const landed = [...prior, assistant('a2', 'fresh answer with a tail')]
+    const { results } = run([
+      { folded: prior },
+      { folded: prior, text: 'fresh answer' },
+      { folded: landed, text: 'fresh answer' }
+    ])
+    expect(results).toEqual([null, 'fresh answer', null])
+  })
+
+  it('suppresses an identical repeated reply once its own turn lands', () => {
+    const prior = [assistant('a1', 'Done.')]
+    const landed = [...prior, assistant('a2', 'Done.')]
+    const { results } = run([
+      { folded: prior },
+      { folded: prior, text: 'Done.' }, // repeated-prefix reply stays visible
+      { folded: landed, text: 'Done.' } // its own turn landed — hide
+    ])
+    expect(results).toEqual([null, 'Done.', null])
+  })
+
+  it('keeps hiding for the rest of a segment after the turn lands', () => {
+    const prior = [assistant('a1', 'earlier')]
+    const landed = [...prior, assistant('a2', 'answer body')]
+    const { results } = run([
+      { folded: prior },
+      { folded: prior, text: 'answer' },
+      { folded: landed, text: 'answer' },
+      { folded: landed, text: 'answer bo' }
+    ])
+    expect(results).toEqual([null, 'answer', null, null])
+  })
+
+  it('re-anchors when a new reply part replaces the stream mid-turn', () => {
+    const prior = [assistant('a1', 'context')]
+    const partOneLanded = [...prior, assistant('a2', 'part one full text')]
+    const { results } = run([
+      { folded: prior },
+      { folded: prior, text: 'part one' },
+      { folded: partOneLanded, text: 'part one' }, // caught up — hide
+      // Part two is not an extension of part one: new segment, new baseline.
+      { folded: partOneLanded, text: 'part' }
+    ])
+    expect(results).toEqual([null, 'part one', null, 'part'])
+  })
+
+  it('falls back to suppress-on-prefix when mounted mid-stream', () => {
+    // No idle tick ever observed: a duplicate bubble is worse than briefly
+    // hiding a mount-coincident repeated reply.
+    const landed = [assistant('a1', 'flushed part still streaming in status')]
+    const { results } = run([{ folded: landed, text: 'flushed part' }])
+    expect(results).toEqual([null])
+  })
+
+  it('is idempotent for a repeated tick', () => {
+    const prior = [assistant('a1', 'The tests pass.')]
+    const first = run([{ folded: prior }, { folded: prior, text: 'The tests' }])
+    const again = deriveMobileNativeChatStreaming(first.gate, prior, 'The tests')
+    expect(again.streaming).toBe('The tests')
+    expect(again.gate).toBe(first.gate)
+  })
+
+  it('drops a prior chat baseline when the stream identity changes', () => {
+    // The other chat's tail must not license showing a bubble here — a swapped
+    // scope resets to the mid-stream fallback rather than reusing its baseline.
+    const repeatedId = [assistant('a1', 'new answer landed')]
+    let gate = createMobileNativeChatStreamingGate('tab-a')
+    gate = deriveMobileNativeChatStreaming(gate, repeatedId, undefined, 'tab-a').gate
+
+    const switched = deriveMobileNativeChatStreaming(gate, repeatedId, 'new answer', 'tab-b')
+
+    expect(switched.streaming).toBeNull()
+    expect(switched.gate.scopeKey).toBe('tab-b')
+    expect(switched.gate.baselineTailId).toBeNull()
+  })
+
+  it('returns null for empty or whitespace streaming text', () => {
+    const prior = [assistant('a1', 'x')]
+    expect(run([{ folded: prior, text: '   ' }]).results).toEqual([null])
+    expect(run([{ folded: prior }]).results).toEqual([null])
+  })
+
+  it('shows the first reply of an empty chat and hides it once the turn lands', () => {
+    const landed = [assistant('a1', 'Hello there')]
+    const { results } = run([
+      { folded: [] },
+      { folded: [], text: 'Hello' },
+      { folded: landed, text: 'Hello' }
+    ])
+    expect(results).toEqual([null, 'Hello', null])
+  })
+})

mobile/src/session/mobile-native-chat-streaming-gate.ts

@@ -0,0 +1,82 @@
+import type { NativeChatMessage } from '../../../src/shared/native-chat-types'
+
+/** Decides whether the live streaming preview should render as a synthetic
+ *  bubble. Text alone can't tell "the transcript caught up with this stream"
+ *  from "a new reply happens to repeat the previous turn's prefix" — the old
+ *  prefix test swallowed genuine repeated-prefix replies. The gate keeps the
+ *  transcript tail observed when the current stream segment began: the bubble
+ *  hides only when the tail MOVED during the segment and leads with the
+ *  streamed text (the real turn landed), never for an older identical turn. */
+export type MobileNativeChatStreamingGate = {
+  /** Chat/session identity this baseline belongs to. */
+  scopeKey: string | null
+  /** Streamed text seen on the previous tick ('' while idle). */
+  prevText: string
+  /** Folded tail message id when the current segment began; null while the
+   *  gate has never observed an idle tick (mounted mid-stream), where the
+   *  legacy suppress-on-prefix rule applies. */
+  baselineTailId: string | null
+}
+
+export function createMobileNativeChatStreamingGate(
+  scopeKey: string | null = null
+): MobileNativeChatStreamingGate {
+  return { scopeKey, prevText: '', baselineTailId: null }
+}
+
+function assistantTailText(tail: NativeChatMessage | undefined): string {
+  if (!tail || tail.role !== 'assistant') {
+    return ''
+  }
+  return tail.blocks
+    .filter((block) => block.type === 'text')
+    .map((block) => (block.type === 'text' ? block.text : ''))
+    .join('')
+    .trim()
+}
+
+// Reuses the incoming gate object when nothing moved, so a caller can detect
+// "no change" by reference (and a render-time state adjustment can settle).
+function advanceGate(
+  gate: MobileNativeChatStreamingGate,
+  prevText: string,
+  baselineTailId: string | null
+): MobileNativeChatStreamingGate {
+  return gate.prevText === prevText && gate.baselineTailId === baselineTailId
+    ? gate
+    : { ...gate, prevText, baselineTailId }
+}
+
+/** Advance the gate one tick and derive the visible streaming text (null hides
+ *  the bubble). Pure and idempotent for a repeated (text, tail) pair, so a
+ *  re-render without new data cannot flip the decision. */
+export function deriveMobileNativeChatStreaming(
+  gate: MobileNativeChatStreamingGate,
+  folded: readonly NativeChatMessage[],
+  streamingText: string | undefined,
+  scopeKey: string | null = gate.scopeKey
+): { gate: MobileNativeChatStreamingGate; streaming: string | null } {
+  const scopedGate =
+    gate.scopeKey === scopeKey ? gate : createMobileNativeChatStreamingGate(scopeKey)
+  const text = streamingText?.trim() ?? ''
+  const tail = folded.at(-1)
+  const tailId = tail?.id ?? null
+  if (!text) {
+    // Idle: keep anchoring the baseline to the live tail so the next segment
+    // knows which tail predates it.
+    return { gate: advanceGate(scopedGate, '', tailId), streaming: null }
+  }
+  // A stream that is not an extension of the previous tick is a new segment
+  // (next reply part); re-anchor to the tail that predates it.
+  const segmentStart = scopedGate.prevText !== '' && !text.startsWith(scopedGate.prevText)
+  const baselineTailId = segmentStart ? tailId : scopedGate.baselineTailId
+  const tailLeadsWithStream = assistantTailText(tail).startsWith(text)
+  // baselineTailId === null: mounted mid-stream with no pre-stream observation —
+  // fall back to suppress-on-prefix (a duplicate bubble is worse than briefly
+  // hiding an improbable mount-coincident repeated reply).
+  const caughtUp = tailLeadsWithStream && (baselineTailId === null || tailId !== baselineTailId)
+  return {
+    gate: advanceGate(scopedGate, text, baselineTailId),
+    streaming: caughtUp ? null : text
+  }
+}

mobile/src/session/use-mobile-native-chat-controller.ts

@@ -49,6 +49,8 @@ export type MobileNativeChatController = {
   nativeChatSession: ReturnType<typeof useMobileNativeChatSession>
   nativeChatAgentWorking: boolean
   nativeChatStreamingText?: string
+  /** Host/workspace/tab/session identity for stateful streaming suppression. */
+  nativeChatStreamIdentity: string
   nativeChatPermission: ReturnType<typeof detectAgentPermission>
   nativeChatQuestion: ReturnType<typeof parseAgentQuestion>
   nativeChatAsk: ReturnType<typeof parseAskFromStatus>
@@ -273,6 +275,7 @@ export function useMobileNativeChatController(args: {
     nativeChatSession,
     nativeChatAgentWorking,
     nativeChatStreamingText,
+    nativeChatStreamIdentity: streamIdentity,
     nativeChatPermission,
     nativeChatQuestion,
     nativeChatAsk,

mobile/src/session/use-mobile-native-chat-streaming-bubble.ts

@@ -0,0 +1,24 @@
+import { useState } from 'react'
+import type { NativeChatMessage } from '../../../src/shared/native-chat-types'
+import {
+  createMobileNativeChatStreamingGate,
+  deriveMobileNativeChatStreaming
+} from './mobile-native-chat-streaming-gate'
+
+/** Live streaming-bubble text for the chat list. The gate remembers which
+ *  transcript tail predates the current stream segment, so a reply that repeats
+ *  the previous turn's prefix still shows while streaming. */
+export function useMobileNativeChatStreamingBubble(
+  folded: readonly NativeChatMessage[],
+  streamingText: string | undefined,
+  scopeKey: string
+): string | null {
+  const [gate, setGate] = useState(() => createMobileNativeChatStreamingGate(scopeKey))
+  const step = deriveMobileNativeChatStreaming(gate, folded, streamingText, scopeKey)
+  if (step.gate !== gate) {
+    // Render-time state adjustment (derived-state pattern): the advance is
+    // idempotent for a repeated (text, tail) pair, so this settles in one pass.
+    setGate(step.gate)
+  }
+  return step.streaming
+}