feat(web): retry transient model requests

2026-07-26 14:09:31 +08:00
parent 84be7cc622
commit a430207427
32 changed files with 791 additions and 46 deletions
--- a/packages/client/connection/src/client/fixture.ts
+++ b/packages/client/connection/src/client/fixture.ts
@@ -425,6 +425,8 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy {
  let failNextHistory = false
  /** Force-enders for currently open stream generators (timing hook: simulated connection loss). */
  const streamBreakers = new Set<() => void>()
+  /** Retry scenarios opened by timing hooks and completed in a later browser assertion phase. */
+  const retryScenarios = new Map<SessionId, { turn: number; failedStep: number }>()

  // Timing-acceptance hooks (browser test backdoor): the in-memory fixture is ideally timed, which
  // is exactly what masked the open-window and reconnect-gap bugs (audit S1/S3). These let
@@ -448,6 +450,61 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy {
      const messageSeqs = log.filter(event => event.type === 'user/message').map(event => event.seq)
      append(sid(id), { type: 'session/title', data: { title, messageSeqs, source: { kind: 'provider', provider: 'fixture' } } })
    },
+    /** Open one failed model step whose partial remains visible until llm/retry arrives. */
+    beginModelRetry(id: string): void {
+      const sessionId = sid(id)
+      const turn = nextTurn.get(sessionId) ?? 0
+      nextTurn.set(sessionId, turn + 1)
+      retryScenarios.set(sessionId, { turn, failedStep: 0 })
+      setRunning(sessionId, true)
+      append(sessionId, { type: 'turn/start', data: { turn, trigger: { kind: 'message', source: { kind: 'user' } } } })
+      append(sessionId, { type: 'user/message', surfaceOp: 'append', data: { content: text('请重试这个请求'), source: { kind: 'user' } } })
+      append(sessionId, { type: 'step/start', data: { turn, step: 0 } })
+      append(sessionId, { type: 'assistant/chunk', data: { turn, step: 0, chunk: { type: 'block-start', index: 0, blockType: 'text' } } })
+      append(sessionId, { type: 'assistant/chunk', data: { turn, step: 0, chunk: { type: 'text-delta', index: 0, text: '应撤回的半截回复' } } })
+      append(sessionId, { type: 'step/end', data: { turn, step: 0 } })
+    },
+    /** Record one retry decision, synthesizing the later failed step when needed. */
+    scheduleModelRetry(id: string, retry = 1, delayMs = 450): void {
+      const sessionId = sid(id)
+      const scenario = retryScenarios.get(sessionId)
+      if (scenario === undefined) throw new Error(`fixture: no model retry scenario for ${id}`)
+      const failedStep = retry - 1
+      if (failedStep > scenario.failedStep) {
+        append(sessionId, { type: 'step/start', data: { turn: scenario.turn, step: failedStep } })
+        append(sessionId, { type: 'assistant/chunk', data: { turn: scenario.turn, step: failedStep, chunk: { type: 'block-start', index: 0, blockType: 'text' } } })
+        append(sessionId, { type: 'assistant/chunk', data: { turn: scenario.turn, step: failedStep, chunk: { type: 'text-delta', index: 0, text: `第 ${String(retry)} 次应撤回的回复` } } })
+        append(sessionId, { type: 'step/end', data: { turn: scenario.turn, step: failedStep } })
+        scenario.failedStep = failedStep
+      }
+      append(sessionId, {
+        type: 'llm/retry',
+        data: {
+          turn: scenario.turn, step: failedStep, retry, maxRetries: 2, delayMs,
+          failure: { code: 'TRANSPORT', message: '连接被重置' },
+        },
+      })
+    },
+    /** Finish the timing-hook retry with a finalized response on the next step. */
+    completeModelRetry(id: string): void {
+      const sessionId = sid(id)
+      const scenario = retryScenarios.get(sessionId)
+      if (scenario === undefined) throw new Error(`fixture: no model retry scenario for ${id}`)
+      retryScenarios.delete(sessionId)
+      const step = scenario.failedStep + 1
+      append(sessionId, { type: 'step/start', data: { turn: scenario.turn, step } })
+      append(sessionId, {
+        type: 'assistant/message',
+        surfaceOp: 'append',
+        data: {
+          turn: scenario.turn, step, content: text('重试后的完整回复'),
+          provenance: { provider: 'fixture', model: 'fx-1' },
+        },
+      })
+      append(sessionId, { type: 'step/end', data: { turn: scenario.turn, step } })
+      append(sessionId, { type: 'turn/end', data: { turn: scenario.turn, reason: { kind: 'completed' } } })
+      setRunning(sessionId, false)
+    },
    /** Log append WITHOUT the mux emit: a frame lost in transit — history still serves it, the client must repull. */
    appendSilent(id: string, msg: string): void {
      const log = logOf(sid(id))
--- a/packages/client/connection/tests/fixture.spec.ts
+++ b/packages/client/connection/tests/fixture.spec.ts
@@ -19,6 +19,9 @@ interface TimingHooks {
  failNextHistory(): void
  appendUser(id: string, msg: string): void
  appendTitle(id: string, title: string): void
+  beginModelRetry(id: string): void
+  scheduleModelRetry(id: string, retry?: number, delayMs?: number): void
+  completeModelRetry(id: string): void
  appendSilent(id: string, msg: string): void
  breakStreams(): void
 }
@@ -489,9 +492,14 @@ describe('createFixtureApi', () => {
    hooks.appendSilent('fx-alpha', '静默丢帧')
    hooks.appendUser('fx-alpha', '正常直播')
    hooks.appendTitle('fx-alpha', 'Fixture 修订标题')
+    hooks.beginModelRetry('fx-alpha')
+    hooks.scheduleModelRetry('fx-alpha')
+    hooks.completeModelRetry('fx-alpha')
    await vi.waitFor(() => {
      expect(seen.some(f => f.type === 'session/event' && JSON.stringify(f.event.data).includes('正常直播'))).toBe(true)
      expect(seen.some(f => f.type === 'session/title' && f.title === 'Fixture 修订标题')).toBe(true)
+      expect(seen.some(f => f.type === 'session/event' && (f.event as { type: string }).type === 'llm/retry')).toBe(true)
+      expect(seen.some(f => f.type === 'session/event' && JSON.stringify(f.event.data).includes('重试后的完整回复'))).toBe(true)
    })
    expect(seen.some(f => f.type === 'session/event' && JSON.stringify(f.event.data).includes('静默丢帧'))).toBe(false)
    const rawTitleIndex = seen.findIndex(f => f.type === 'session/event' && (f.event as { type: string }).type === 'session/title')
--- a/packages/client/runtime/README.md
+++ b/packages/client/runtime/README.md
@@ -16,6 +16,10 @@ SlotsService gives the renderer separate bare observables for `useSessions` and

 `SessionManager` retains the latest validated `session/title` control snapshot independently of list and session-instance arrival. Newer event seqs replace older snapshots, title timestamps contribute to list recency, and a subscription baseline discards any retained title beyond its `lastSeq` before the optional folded title arrives. Explicit session removal also clears the retained title. The client-facing `SessionSummary.title` is therefore only the actual durable title; `displayTitle` is always present and falls back through the cwd basename and session id. A cold persisted session keeps that fallback until opening or resuming it causes the host to fold and project its log-backed title.

+## Model retry projection
+
+The Session object validates plugin-owned `llm/retry` payloads at the event wire boundary. A valid event removes the matching failed step's streaming partial and inserts a durable retry notice at the event's sequence position. Window rebuild and history replay apply the same projection, so logged chunks from the discarded attempt never reappear as an interrupted reply after refresh. A terminal turn without `llm/retry` retains the existing behavior: visible unfinalized output is frozen as an interrupted assistant node.
+
 ## Model Experience

 None, as the client runtime hosts browser-side services and the session object layer; nothing here reaches a model request.
--- a/packages/client/runtime/package.json
+++ b/packages/client/runtime/package.json
@@ -35,6 +35,7 @@
    "@deepseek-ai/dsh-client-ui-slots": "workspace:^",
    "@deepseek-ai/dsh-host-apiproxy": "workspace:^",
    "@deepseek-ai/dsh-llm": "workspace:^",
+    "@deepseek-ai/dsh-llm-retry": "workspace:^",
    "@deepseek-ai/dsh-session": "workspace:^",
    "immer": "^10.1.1",
    "react": "^18.2.0",
--- a/packages/client/runtime/src/client/index.ts
+++ b/packages/client/runtime/src/client/index.ts
@@ -25,7 +25,7 @@ export type {
 } from './contract/store.ts'
 export type {
  AssistantBlock, AssistantMessageNode, ComposerPhase, ContextMessageNode, ConversationNode,
-  ConversationSnapshot, PendingPrompt, RunningToolCall, SessionIntentSnapshot, SessionIntentTarget,
+  ConversationSnapshot, ModelRetryNode, PendingPrompt, RunningToolCall, SessionIntentSnapshot, SessionIntentTarget,
  SteeringMessageNode, ToolResultNode, UnknownSurfaceNode, UserMessageNode,
 } from './sessions/conversation.ts'
 export { PendingWait } from './sessions/pending.ts'
--- a/packages/client/runtime/src/client/sessions/conversation.ts
+++ b/packages/client/runtime/src/client/sessions/conversation.ts
@@ -4,6 +4,7 @@
 // string here (narrow to real brands when convenient).

 import type { ContentBlock } from '@deepseek-ai/dsh-llm/types'
+import type { LlmRetryEventData } from '@deepseek-ai/dsh-llm-retry/types'
 import type {
  RpcError, SessionId, ToolCallView, ToolResultView, WorkspaceId,
 } from '@deepseek-ai/dsh-client-connection/client'
@@ -87,6 +88,20 @@ export interface ContextMessageNode {
  meta?: unknown
 }

+/** Durable notice that a closed failed step is waiting for a model-request retry. */
+export interface ModelRetryNode {
+  kind: 'model-retry'
+  seq: number
+  /** Unix epoch ms from the llm/retry session event. */
+  time: number
+  turn: number
+  step: number
+  retry: number
+  maxRetries: number
+  delayMs: number
+  failure: LlmRetryEventData['failure']
+}
+
 /** A tool result paired (when in-window) with its call head. */
 export interface ToolResultNode {
  kind: 'tool-result'
@@ -124,6 +139,7 @@ export type ConversationNode =
  | AssistantMessageNode
  | SteeringMessageNode
  | ContextMessageNode
+  | ModelRetryNode
  | ToolResultNode
  | UnknownSurfaceNode

@@ -206,7 +222,7 @@ export interface PendingPrompt {
 /** The immutable snapshot contract Session hands to uSES (see the web client architecture RFC). */
 export interface ConversationSnapshot {
  sessionId: SessionId
-  /** Surface fold product (finalized conversation nodes in surface order). */
+  /** Finalized surface events and durable operational notices in event order. */
  nodes: readonly ConversationNode[]
  /** Fold degradation flag (cross-window replace defense): when true, nodes come from the lenient linear scan. */
  foldDegraded: boolean
--- a/packages/client/runtime/src/client/sessions/session.ts
+++ b/packages/client/runtime/src/client/sessions/session.ts
@@ -1,6 +1,7 @@
 // Sessions remain resident after creation so they continue consuming mux frames off-screen.

 import type { ContentBlock } from '@deepseek-ai/dsh-llm/types'
+import type { LlmRetryEventData } from '@deepseek-ai/dsh-llm-retry/types'
 import type { SessionEvent } from '@deepseek-ai/dsh-session/types'
 import type {
  HistoryEntry, IApiClient, MuxFrame, RpcError, RpcId, RpcResult,
@@ -52,9 +53,9 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
  private readonly foldAdapter = new FoldAdapter()
  private partial: PartialAccumulator | null = null
  private openCalls = new Map<string, RunningToolCall>()
-  /** Interrupted-turn terminal nodes (frozen partial text / aborted tool cards), merged into the flow by seq.
-   *  Derived from window events (turn/end sweep) — rebuilt by rebuildDerivedFromWindow like partial/openCalls. */
-  private frozenNodes: ConversationNode[] = []
+  /** Operational notices and interrupted-turn terminal nodes merged into the flow by seq.
+   *  Derived from window events — rebuilt by rebuildDerivedFromWindow like partial/openCalls. */
+  private derivedNodes: ConversationNode[] = []
  private pending = new Map<string, PendingInteraction>()
  // Revision counters preserve array identity when derived content is unchanged, so
  // React.memo children survive unrelated snapshot swaps (chunk storms must not re-render every
@@ -64,8 +65,8 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
  private callsCache: { rev: number; value: RunningToolCall[] } | null = null
  private pendingRev = 0
  private pendingCache: { rev: number; value: PendingInteraction[] } | null = null
-  private frozenRev = 0
-  private nodesCache: { folded: readonly ConversationNode[]; frozenRev: number; value: readonly ConversationNode[] } | null = null
+  private derivedRev = 0
+  private nodesCache: { folded: readonly ConversationNode[]; derivedRev: number; value: readonly ConversationNode[] } | null = null
  private running = false
  /**
   * Sticky send marker, private input of the composerPhase derivation: set
@@ -609,8 +610,27 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
  }

  /** Per-event side effects (right column of the §A.9 dispatch table):
-   *  chunk accumulation / partial clear on finalize / openCalls add-remove. */
+   *  chunk/retry projection and openCalls add-remove. */
  private applyEventSideEffects(event: SessionEvent, view?: ToolEventView): void {
+    const eventType: string = event.type
+    if (eventType === 'llm/retry') {
+      const data = parseRetryEventData(event.data)
+      if (data === null) {
+        console.error(`[web-runtime] ignored malformed llm/retry event at seq ${event.seq}`)
+        return
+      }
+      if (this.partial !== null && this.partial.turn === data.turn && this.partial.step === data.step) {
+        this.partial = null
+      }
+      this.derivedNodes.push({
+        kind: 'model-retry',
+        seq: event.seq,
+        time: event.time,
+        ...data,
+      })
+      this.derivedRev++
+      return
+    }
    switch (event.type) {
      case 'assistant/chunk': {
        const { turn, step, chunk } = event.data
@@ -649,12 +669,12 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
          const visible = blocks.some(b => (b.kind === 'text' || b.kind === 'reasoning' ? b.text !== '' : true))
          if (visible) {
            // Fractional seq: strictly after every event of this turn (all < turn/end seq), before the next turn.
-            this.frozenNodes.push({
+            this.derivedNodes.push({
              kind: 'assistant', seq: event.seq - 0.9, time: event.time,
              turn: this.partial.turn, step: this.partial.step,
              blocks, interrupted: true,
            })
-            this.frozenRev++
+            this.derivedRev++
          }
          this.partial = null
        }
@@ -664,7 +684,7 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
          this.openCalls.delete(callId)
          this.callsRev++
          // The spinner card becomes an interrupted terminal card (never vanishes mid-flow).
-          this.frozenNodes.push({
+          this.derivedNodes.push({
            kind: 'tool-result', seq: event.seq - 0.8 + callOffset++ * 0.01, time: event.time,
            callId,
            call: { name: call.name, argsRaw: call.argsRaw },
@@ -672,7 +692,7 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
            content: [], isError: true, error: { name: 'Interrupted', code: 'interrupted' },
            callView: call.callView, resultView: null,
          })
-          this.frozenRev++
+          this.derivedRev++
        }
        return
      }
@@ -681,15 +701,15 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
    }
  }

-  /** Re-derive state (partial/openCalls/frozenNodes) from raw window events after a rebuild — keeps
+  /** Re-derive state (partial/openCalls/derivedNodes) from raw window events after a rebuild — keeps
   *  paging/stitching consistent, and makes the live freeze and the history replay converge on the
-   *  same interrupted nodes (chunks are logged, so the replayed sweep re-freezes identical text). */
+   *  same retry notices and interrupted nodes. */
  private rebuildDerivedFromWindow(): void {
    this.partial = null
    this.openCalls.clear()
    this.callsRev++
-    this.frozenNodes = []
-    this.frozenRev++
+    this.derivedNodes = []
+    this.derivedRev++
    for (let i = 0; i < this.events.length; i++) {
      const event = this.events[i]
      /* v8 ignore next -- dense-array guard: i stays within events.length, so the undefined arm needs a sparse array no caller builds. */
@@ -704,17 +724,17 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {

  private buildSnapshot(): ConversationSnapshot {
    const { nodes: folded, degraded } = this.foldAdapter.nodes()
-    // Frozen interrupted nodes ride fractional seqs: a stable merge keeps them in flow order.
-    // The merged array is cached on (folded reference, frozenRev) so an unchanged flow keeps its
+    // Derived nodes use their event seq or a nearby fractional seq: a stable merge keeps flow order.
+    // The merged array is cached on (folded reference, derivedRev) so an unchanged flow keeps its
    // reference across snapshot swaps (§A.9.4).
    let nodes: readonly ConversationNode[]
-    if (this.nodesCache !== null && this.nodesCache.folded === folded && this.nodesCache.frozenRev === this.frozenRev) {
+    if (this.nodesCache !== null && this.nodesCache.folded === folded && this.nodesCache.derivedRev === this.derivedRev) {
      nodes = this.nodesCache.value
    } else {
-      nodes = this.frozenNodes.length === 0
+      nodes = this.derivedNodes.length === 0
        ? folded
-        : [...folded, ...this.frozenNodes].sort((a, b) => a.seq - b.seq)
-      this.nodesCache = { folded, frozenRev: this.frozenRev, value: nodes }
+        : [...folded, ...this.derivedNodes].sort((a, b) => a.seq - b.seq)
+      this.nodesCache = { folded, derivedRev: this.derivedRev, value: nodes }
    }
    if (this.callsCache === null || this.callsCache.rev !== this.callsRev) {
      this.callsCache = { rev: this.callsRev, value: [...this.openCalls.values()] }
@@ -752,6 +772,37 @@ function rpcErrorMessage(error: RpcError): string {
  return `${error.code}: ${error.message}`
 }

+/** Validate the plugin-owned payload at the session-event wire boundary. */
+function parseRetryEventData(value: unknown): LlmRetryEventData | null {
+  if (value === null || typeof value !== 'object') return null
+  const data = value as Record<string, unknown>
+  const failure = data.failure
+  if (failure === null || typeof failure !== 'object') return null
+  const failureData = failure as Record<string, unknown>
+  if (!nonNegativeInteger(data.turn)
+    || !nonNegativeInteger(data.step)
+    || !positiveInteger(data.retry)
+    || !positiveInteger(data.maxRetries)
+    || data.retry > data.maxRetries
+    || typeof data.delayMs !== 'number'
+    || !Number.isFinite(data.delayMs)
+    || data.delayMs < 0
+    || typeof failureData.message !== 'string'
+    || typeof failureData.code !== 'string') return null
+  const optionalNumbers = [failureData.status, failureData.providerRetryAfterMs]
+  if (optionalNumbers.some(item => item !== undefined && (typeof item !== 'number' || !Number.isFinite(item)))) return null
+  if (failureData.requestId !== undefined && typeof failureData.requestId !== 'string') return null
+  return data as unknown as LlmRetryEventData
+}
+
+function nonNegativeInteger(value: unknown): value is number {
+  return typeof value === 'number' && Number.isInteger(value) && value >= 0
+}
+
+function positiveInteger(value: unknown): value is number {
+  return nonNegativeInteger(value) && value > 0
+}
+
 /**
 * The composerPhase judgment — the single site that knows the predicate
 * (consumers switch on the result, never re-derive). Monotone per session
--- a/packages/client/runtime/tests/event-script.ts
+++ b/packages/client/runtime/tests/event-script.ts
@@ -28,6 +28,22 @@ export const ev = {
    at(seq, { type: 'tool/result', surfaceOp: 'append', data: { turn, step, callId, content: text(body), isError: false } }),
  stepEnd: (seq: number, turn: number, step = 0): SessionEvent =>
    at(seq, { type: 'step/end', data: { turn, step } }),
+  retry: (
+    seq: number,
+    turn: number,
+    step = 0,
+    retry = 1,
+    maxRetries = 2,
+    delayMs = 500,
+    message = 'temporary transport failure',
+  ): SessionEvent =>
+    at(seq, {
+      type: 'llm/retry',
+      data: {
+        turn, step, retry, maxRetries, delayMs,
+        failure: { code: 'TRANSPORT', message },
+      },
+    }),
  turnEnd: (seq: number, turn: number, reason: 'completed' | 'cancelled' = 'completed'): SessionEvent =>
    at(seq, { type: 'turn/end', data: { turn, reason: { kind: reason } } }),
 }
--- a/packages/client/runtime/tests/session.spec.ts
+++ b/packages/client/runtime/tests/session.spec.ts
@@ -119,6 +119,72 @@ describe('live event path', () => {
    expect((last as { interrupted?: true }).interrupted).toBeUndefined()
  })

+  it('retracts the failed step partial on retry and keeps a replayable notice before the recovered response', async () => {
+    const { session } = await opened()
+    const feed = (event: SessionEvent) => { session.handleMuxEnvelope('r' as never, { type: 'session/event', sessionId: SID, event }) }
+    const retryTurn = [
+      ev.turnStart(6, 1),
+      ev.user(7, '请重试'),
+      ev.stepStart(8, 1),
+      ev.chunkStart(9, 1),
+      ev.chunkText(10, 1, '不完整回复'),
+      ev.stepEnd(11, 1),
+      ev.retry(12, 1, 0, 1, 2, 450, '连接被重置'),
+      ev.stepStart(13, 1, 1),
+      ev.assistant(14, 1, '完整回复', 1),
+      ev.stepEnd(15, 1, 1),
+      ev.turnEnd(16, 1),
+    ]
+    for (const event of retryTurn.slice(0, 7)) feed(event)
+
+    let snapshot = session.getSnapshot()
+    expect(snapshot.partial).toBeNull()
+    expect(snapshot.nodes.at(-1)).toMatchObject({
+      kind: 'model-retry',
+      turn: 1,
+      step: 0,
+      retry: 1,
+      maxRetries: 2,
+      delayMs: 450,
+      failure: { code: 'TRANSPORT', message: '连接被重置' },
+    })
+    expect(JSON.stringify(snapshot.nodes)).not.toContain('不完整回复')
+
+    for (const event of retryTurn.slice(7)) feed(event)
+    snapshot = session.getSnapshot()
+    expect(snapshot.nodes.slice(-2).map(node => node.kind)).toEqual(['model-retry', 'assistant'])
+    expect(snapshot.nodes.at(-1)).toMatchObject({ kind: 'assistant', blocks: [{ kind: 'text', text: '完整回复' }] })
+
+    const replay = makeSession()
+    replay.api.onHistory = () => histResponse([...plainTurn(0, 0, 'a', 'b'), ...retryTurn])
+    await replay.session.open()
+    expect(replay.session.getSnapshot().nodes).toEqual(snapshot.nodes)
+    expect(replay.session.getSnapshot().partial).toBeNull()
+  })
+
+  it('ignores malformed retry payloads without retracting the current partial', async () => {
+    const { session } = await opened()
+    const feed = (event: SessionEvent) => { session.handleMuxEnvelope('r' as never, { type: 'session/event', sessionId: SID, event }) }
+    feed(ev.turnStart(6, 1))
+    feed(ev.chunkStart(7, 1))
+    feed(ev.chunkText(8, 1, '仍在生成'))
+    const errorSpy = vi.spyOn(console, 'error').mockImplementation(() => undefined)
+    try {
+      feed(at(9, {
+        type: 'llm/retry',
+        data: {
+          turn: 1, step: 0, retry: 3, maxRetries: 2, delayMs: 500,
+          failure: { code: 'TRANSPORT', message: 'bad budget' },
+        },
+      }))
+      expect(session.getSnapshot().partial?.blocks).toEqual([{ kind: 'text', text: '仍在生成' }])
+      expect(session.getSnapshot().nodes.filter(node => node.kind === 'model-retry')).toEqual([])
+      expect(errorSpy).toHaveBeenCalledWith('[web-runtime] ignored malformed llm/retry event at seq 9')
+    } finally {
+      errorSpy.mockRestore()
+    }
+  })
+
  it('freezes an unfinalized partial into an interrupted node on turn/end (cancel path)', async () => {
    const { session } = await opened()
    const feed = (event: SessionEvent) => { session.handleMuxEnvelope('r' as never, { type: 'session/event', sessionId: SID, event }) }
--- a/packages/client/runtime/tsconfig.json
+++ b/packages/client/runtime/tsconfig.json
@@ -26,6 +26,9 @@
    {
      "path": "../../llm/llm"
    },
+    {
+      "path": "../../llm/llm-retry"
+    },
    {
      "path": "../../support/invariants"
    }
--- a/packages/client/ui-conversation/README.md
+++ b/packages/client/ui-conversation/README.md
@@ -8,6 +8,8 @@ The view ring IS a slot: the conversation registration declares the `'conversati

 Generic tool rows classify the built-in bash, read, search, write, and edit names into dedicated visual variants. The filesystem variants render the edit icon and `Write · <path>` or `Edit · <path>` summary while retaining the shared row-to-details interaction.

+The chat flow projects consecutive model-retry nodes from one turn into one stable, muted status row updated to the latest attempt; every retry event remains in the runtime snapshot and session log. Its frontend countdown derives from the scheduled delay, rounds remaining time up to seconds, and has a one-second floor. The latest unresolved retry uses a left-to-right text shimmer, then settles to a static completed label. Activating the row reveals the latest exact retry delay and failure message. The client runtime removes each failed step's streaming tail before its retry node arrives, while the status remains visible after a later attempt succeeds.
+
 Tool rows are slots too — the standalone tool ring (`ToolViewRegistry`/`ctx.toolviews`/outlet) is retired. The chat entry declares the keyed `'conversation.chat.toolview'` hole (session scope; the key space is runtime-open); its render site dispatches per row via `entryKey: toolName` with `GenericToolCard` as the call-site `fallback`. The owner payload is the uniform `ToolRowOwnerProps` (`callId`/`toolName`/`block`/`openDetails`) and `ToolRowProps` pre-composes it with the session standard kit. A registrant is a plain plugin: `ctx.slots.register({ name: 'conversation.chat.toolview', key: '<tool>', inject? }, Row)` with `inject: ['slots', 'conversation']` as the load-order seam (apply mounts ConversationService after the chat registration, so the service being present guarantees the slot is declared); session differentiation happens inside the component (`useSessions` reading `parentId` — the bash sample is the third-party-posture exemplar). Trajectory/waterfall toolview slots share this shape and land with their own render sites (RendersCheck rejects a declaration nobody renders).

 Per-session UI state (selection, ordinary composer draft, active view) lives in the declared chat store (`stores.ts` `createChatStore`): apply constructs one handle and passes it to the conversation, chat-view, and details registrations, so the session slots share one instance per session (selection written by the chat view, read by details) and the framework owns instance lifecycle and draft persistence. The frontend Session Intent comes from the Session list projection; after publication, any retained prompt comes from that Session's conversation snapshot. Components are pure — the framework standard kit (`useSession`/`sessionId` when session-scoped, plus global `useSessions`/`useWorkspaces`) and the store faces (`useStore`/`actions`) arrive automatically from the registration declaration; inject factories contribute plain data and callbacks for runtime Session actions, send/stop, tabs, details, and paging.
--- a/packages/client/ui-conversation/src/client/chat/ChatView.tsx
+++ b/packages/client/ui-conversation/src/client/chat/ChatView.tsx
@@ -45,6 +45,16 @@ type RenderToolRow = ChatViewSlotProps['renderSlot']
 *  chat view narrows once to the runtime snapshot the binding actually feeds. */
 type UseConversation = SnapshotSelectorHook<ConversationSnapshot>

+function activeRetrySeq(nodes: readonly ConversationNode[], running: boolean): number | null {
+  if (!running) return null
+  for (let index = nodes.length - 1; index >= 0; index -= 1) {
+    const node = nodes[index]!
+    if (node.kind === 'model-retry') return node.seq
+    if (node.kind === 'assistant' || node.kind === 'user') return null
+  }
+  return null
+}
+
 /** One tool call row (result or running): dispatches through the keyed
 *  toolview slot with the owner payload; unregistered tools fall back to
 *  GenericToolCard at this render site. */
@@ -115,6 +125,7 @@ function StreamingTail({ useSession, onGrow }: {
 /** The chat view slot entry: pure component over the composed props (tool rows render through the declared keyed hole's renderSlot share). */
 export function ChatView({ useSession, useStore, renderSlot, openDetails, loadOlder }: ChatViewSlotProps) {
  const nodes = useSession((s) => s.nodes)
+  const running = useSession((s) => s.running)
  const runningCalls = useSession((s) => s.runningCalls)
  const pending = useSession((s) => s.pending)
  const openState = useSession((s) => s.openState)
@@ -124,6 +135,7 @@ export function ChatView({ useSession, useStore, renderSlot, openDetails, loadOl
  const selectedCallId = useStore((s) => s.selection?.callId)

  const items = useMemo(() => deriveChatFlow(nodes), [nodes])
+  const activeRetry = useMemo(() => activeRetrySeq(nodes, running), [nodes, running])

  const listRef = useRef<HTMLDivElement | null>(null)
  const atBottomRef = useRef(true)
@@ -220,7 +232,13 @@ export function ChatView({ useSession, useStore, renderSlot, openDetails, loadOl
    }
    /* v8 ignore next -- tool-result never reaches here: deriveChatFlow folds them into groups. */
    if (node.kind === 'tool-result') return null
-    return <MessageItem key={item.key} node={node} />
+    return (
+      <MessageItem
+        key={item.key}
+        node={node}
+        retryActive={node.kind === 'model-retry' && node.seq === activeRetry}
+      />
+    )
  }

  return (
--- a/packages/client/ui-conversation/src/client/chat/MessageItem.module.css
+++ b/packages/client/ui-conversation/src/client/chat/MessageItem.module.css
@@ -32,3 +32,103 @@
 .contextRow {
  padding: 2px 0;
 }
+
+.retryRow {
+  color: var(--dsw-alias-label-tertiary);
+  font-size: 13px;
+  line-height: 20px;
+}
+
+.retrySummary {
+  display: inline-flex;
+  align-items: center;
+  width: fit-content;
+  padding: 2px 0;
+  gap: 7px;
+  border-radius: 3px;
+  color: inherit;
+  cursor: pointer;
+  list-style: none;
+  user-select: none;
+}
+
+.retrySummary::-webkit-details-marker {
+  display: none;
+}
+
+.retrySummary::after {
+  width: 6px;
+  height: 6px;
+  border-right: 1.5px solid currentcolor;
+  border-bottom: 1.5px solid currentcolor;
+  content: '';
+  opacity: 0.8;
+  transform: rotate(-45deg);
+  transition: transform 120ms ease;
+}
+
+.retrySummary:hover {
+  color: var(--dsw-alias-label-secondary);
+}
+
+.retrySummary:focus-visible {
+  outline: 1.5px solid var(--dsw-alias-button-info-fill);
+  outline-offset: 2px;
+}
+
+.retryText {
+  color: inherit;
+}
+
+.retryRow[data-active] .retryText {
+  background:
+    linear-gradient(
+      90deg,
+      var(--dsw-alias-label-tertiary) 0%,
+      var(--dsw-alias-label-tertiary) 40%,
+      var(--dsw-alias-label-secondary) 50%,
+      var(--dsw-alias-label-tertiary) 60%,
+      var(--dsw-alias-label-tertiary) 100%
+    );
+  background-position: 100% 50%;
+  background-size: 200% 100%;
+  background-clip: text;
+  color: transparent;
+  animation: retry-shimmer 1.6s ease-in-out infinite;
+}
+
+.retryRow[open] .retrySummary::after {
+  transform: rotate(45deg);
+}
+
+.retryDetails {
+  display: grid;
+  gap: 2px;
+  margin-top: 3px;
+  padding-left: 14px;
+  overflow-wrap: anywhere;
+  font-size: 12px;
+  line-height: 18px;
+}
+
+.retryDetailLabel {
+  color: var(--dsw-alias-label-secondary);
+}
+
+@keyframes retry-shimmer {
+  from {
+    background-position: 100% 50%;
+  }
+
+  to {
+    background-position: 0 50%;
+  }
+}
+
+@media (prefers-reduced-motion: reduce) {
+  .retryRow[data-active] .retryText {
+    background: none;
+    color: inherit;
+    animation: none;
+  }
+}
--- a/packages/client/ui-conversation/src/client/chat/MessageItem.tsx
+++ b/packages/client/ui-conversation/src/client/chat/MessageItem.tsx
@@ -1,17 +1,18 @@
-// MessageItem: the four simple node kinds — user bubble (right-aligned),
-// steering (badged bubble), context injection and unknown-surface JSON rows.
+// MessageItem: simple chat nodes — user bubble (right-aligned), steering
+// (badged bubble), context injection, retry disclosure and unknown JSON rows.
 // Props are frozen node slices off the snapshot cache; memo holds across
 // streaming because unchanged nodes keep their references.

-import { memo } from 'react'
+import { memo, useEffect, useState } from 'react'
 import type {
-  ContextMessageNode, SteeringMessageNode, UnknownSurfaceNode, UserMessageNode,
+  ContextMessageNode, ModelRetryNode, SteeringMessageNode, UnknownSurfaceNode, UserMessageNode,
 } from '@deepseek-ai/dsh-client-runtime/client'
 import { JsonBlock, MessageText } from '@deepseek-ai/dsh-client-ui-primitives'
 import css from './MessageItem.module.css'

 export interface MessageItemProps {
-  node: UserMessageNode | SteeringMessageNode | ContextMessageNode | UnknownSurfaceNode
+  node: UserMessageNode | SteeringMessageNode | ContextMessageNode | ModelRetryNode | UnknownSurfaceNode
+  retryActive?: boolean
 }

 function contentText(content: readonly unknown[]): { text: string; rest: unknown[] } {
@@ -25,7 +26,56 @@ function contentText(content: readonly unknown[]): { text: string; rest: unknown
  return { text: texts.join(''), rest }
 }

-export const MessageItem = memo(function MessageItem({ node }: MessageItemProps) {
+function retrySeconds(milliseconds: number): number {
+  return Math.max(1, Math.ceil(milliseconds / 1_000))
+}
+
+interface RetryCountdown {
+  deadline: number
+  seconds: number
+}
+
+function ModelRetryItem({ node, active }: { node: ModelRetryNode; active: boolean }) {
+  const deadline = node.time + node.delayMs
+  const scheduledSeconds = retrySeconds(node.delayMs)
+  const [countdown, setCountdown] = useState<RetryCountdown>(() => ({
+    deadline,
+    seconds: retrySeconds(deadline - Date.now()),
+  }))
+  const remainingSeconds = countdown.deadline === deadline
+    ? countdown.seconds
+    : retrySeconds(deadline - Date.now())
+
+  useEffect(() => {
+    if (!active || retrySeconds(deadline - Date.now()) === 1) return
+    const timer = window.setInterval(() => {
+      const next = retrySeconds(deadline - Date.now())
+      setCountdown(current => (
+        current.deadline === deadline && current.seconds === next
+          ? current
+          : { deadline, seconds: next }
+      ))
+      if (next === 1) window.clearInterval(timer)
+    }, 250)
+    return () => { window.clearInterval(timer) }
+  }, [active, deadline])
+
+  return (
+    <details className={css.retryRow} data-active={active || undefined}>
+      <summary className={css.retrySummary}>
+        <span className={css.retryText} role="status">
+          {active ? '正在重试' : '已重试'}模型请求（{node.retry}/{node.maxRetries}） · {active ? remainingSeconds : scheduledSeconds}s
+        </span>
+      </summary>
+      <div className={css.retryDetails}>
+        <div><span className={css.retryDetailLabel}>重试延迟：</span>{Math.round(node.delayMs)}ms</div>
+        <div><span className={css.retryDetailLabel}>失败原因：</span>{node.failure.message}</div>
+      </div>
+    </details>
+  )
+}
+
+export const MessageItem = memo(function MessageItem({ node, retryActive = false }: MessageItemProps) {
  switch (node.kind) {
    case 'user':
    case 'steering': {
@@ -46,6 +96,8 @@ export const MessageItem = memo(function MessageItem({ node }: MessageItemProps)
          <JsonBlock label="上下文注入" payload={{ content: node.content, meta: node.meta }} />
        </div>
      )
+    case 'model-retry':
+      return <ModelRetryItem node={node} active={retryActive} />
    default:
      return (
        <div className={css.contextRow}>
--- a/packages/client/ui-conversation/src/client/chat/chat-flow.ts
+++ b/packages/client/ui-conversation/src/client/chat/chat-flow.ts
@@ -1,7 +1,8 @@
 /**
 * Chat flow derivation: ConversationSnapshot nodes -> render items. Tool
 * results group into consecutive-run tool groups (figma step-summary flow,
- * VERTICAL gap10) alternating with narration; everything else passes through.
+ * VERTICAL gap10) alternating with narration. Consecutive retry notices from
+ * one turn reuse the first notice's row while projecting the latest attempt.
 * Item identity keys are stable across snapshots so the list parent can
 * subscribe to keys only while rows subscribe to content.
 */
@@ -15,7 +16,7 @@ export type ChatFlowItem =
 /**
 * Group finalized nodes into the step-summary flow.
 * @param nodes - snapshot nodes (surface order).
- * @returns flow items; consecutive tool-results merged into one group keyed by the first seq.
+ * @returns flow items; consecutive tool results and same-turn retry notices reuse their first key.
 */
 export function deriveChatFlow(nodes: readonly ConversationNode[]): ChatFlowItem[] {
  const items: ChatFlowItem[] = []
@@ -28,6 +29,18 @@ export function deriveChatFlow(nodes: readonly ConversationNode[]): ChatFlowItem
      } else {
        group.push(node)
      }
+    } else if (node.kind === 'model-retry') {
+      group = null
+      const previous = items[items.length - 1]
+      if (
+        previous?.kind === 'node'
+        && previous.node.kind === 'model-retry'
+        && previous.node.turn === node.turn
+      ) {
+        items[items.length - 1] = { ...previous, node }
+      } else {
+        items.push({ kind: 'node', key: `n${node.seq}`, node })
+      }
    } else {
      group = null
      items.push({ kind: 'node', key: `n${node.seq}`, node })
--- a/packages/client/ui-conversation/tests/chat-branch-tails.spec.tsx
+++ b/packages/client/ui-conversation/tests/chat-branch-tails.spec.tsx
@@ -5,7 +5,7 @@
 // machinery specs since the tool ring dissolved into renderSlot.)

 import { afterEach, describe, expect, it, vi } from 'vitest'
-import { cleanup, render } from '@testing-library/react'
+import { act, cleanup, fireEvent, render } from '@testing-library/react'
 import { RpcId } from '@deepseek-ai/dsh-client-connection/client'
 import type { SessionId } from '@deepseek-ai/dsh-client-runtime/client'
 import { PendingWait } from '@deepseek-ai/dsh-client-runtime/client'
@@ -15,7 +15,10 @@ import { PendingCard } from '../src/client/chat/PendingCard.tsx'
 import { AssistantMarkdown } from '../src/client/chat/AssistantMarkdown.tsx'
 import { StatsLine, type StatsLineProps } from '../src/client/chat/StatsLine.tsx'

-afterEach(cleanup)
+afterEach(() => {
+  cleanup()
+  vi.useRealTimers()
+})

 describe('MessageItem arms', () => {
  it('steering bubbles carry the interjection badge and non-text rest blocks', () => {
@@ -41,6 +44,78 @@ describe('MessageItem arms', () => {
    )
    expect(unknownView.getByText(/未知 surface 事件：surface\/next/)).toBeTruthy()
  })
+
+  it('collapses retry details behind the durable model retry status', () => {
+    vi.useFakeTimers()
+    vi.setSystemTime(10_000)
+    const view = render(
+      <MessageItem
+        retryActive
+        node={{
+          kind: 'model-retry',
+          seq: 5,
+          time: 10_000,
+          turn: 1,
+          step: 0,
+          retry: 1,
+          maxRetries: 2,
+          delayMs: 2_500.4,
+          failure: { code: 'TRANSPORT', message: '连接被重置' },
+        }}
+      />,
+    )
+    const details = view.container.querySelector('details')
+    const summary = view.container.querySelector('summary')
+    expect(details?.open).toBe(false)
+    expect(details?.dataset.active).toBe('true')
+    expect(view.getByRole('status').textContent).toBe('正在重试模型请求（1/2） · 3s')
+    expect(view.getByText('重试延迟：').parentElement?.textContent).toBe('重试延迟：2500ms')
+    expect(view.getByText('失败原因：').parentElement?.textContent).toBe('失败原因：连接被重置')
+
+    act(() => { vi.advanceTimersByTime(1_100) })
+    expect(view.getByRole('status').textContent).toBe('正在重试模型请求（1/2） · 2s')
+    act(() => { vi.advanceTimersByTime(1_000) })
+    expect(view.getByRole('status').textContent).toBe('正在重试模型请求（1/2） · 1s')
+
+    view.rerender(
+      <MessageItem
+        retryActive
+        node={{
+          kind: 'model-retry',
+          seq: 6,
+          time: 12_100,
+          turn: 1,
+          step: 1,
+          retry: 2,
+          maxRetries: 2,
+          delayMs: 3_500.4,
+          failure: { code: 'TRANSPORT', message: '再次断开' },
+        }}
+      />,
+    )
+    expect(view.getByRole('status').textContent).toBe('正在重试模型请求（2/2） · 4s')
+
+    if (summary === null) throw new Error('retry summary missing')
+    fireEvent.click(summary)
+    expect(details?.open).toBe(true)
+
+    view.rerender(
+      <MessageItem node={{
+        kind: 'model-retry',
+        seq: 6,
+        time: 12_100,
+        turn: 1,
+        step: 1,
+        retry: 2,
+        maxRetries: 2,
+        delayMs: 3_500.4,
+        failure: { code: 'TRANSPORT', message: '再次断开' },
+      }}
+      />,
+    )
+    expect(details?.dataset.active).toBeUndefined()
+    expect(view.getByRole('status').textContent).toBe('已重试模型请求（2/2） · 4s')
+  })
 })

 describe('small branch tails', () => {
--- a/packages/client/ui-conversation/tests/chat-view.spec.tsx
+++ b/packages/client/ui-conversation/tests/chat-view.spec.tsx
@@ -7,7 +7,7 @@ import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
 import { Profiler } from 'react'
 import { act, cleanup, fireEvent, render } from '@testing-library/react'
 import type {
-  AssistantMessageNode, ConversationNode, ConversationSnapshot, RunningToolCall, SessionId, SessionListState, ToolResultNode, UserMessageNode, WorkspaceListState,
+  AssistantMessageNode, ConversationNode, ConversationSnapshot, ModelRetryNode, RunningToolCall, SessionId, SessionListState, ToolResultNode, UserMessageNode, WorkspaceListState,
 } from '@deepseek-ai/dsh-client-runtime/client'
 import { bindSnapshotSelector } from '@deepseek-ai/dsh-client-web-react'
 import { createSnapshotStore, PendingWait } from '@deepseek-ai/dsh-client-runtime/client'
@@ -59,6 +59,11 @@ const user = (seq: number, text: string): UserMessageNode => ({
 const assistant = (seq: number, text: string): AssistantMessageNode => ({
  kind: 'assistant', seq, time: seq * 1_000, turn: 1, step: 1, blocks: [{ kind: 'text', text }],
 })
+const retry = (seq: number): ModelRetryNode => ({
+  kind: 'model-retry', seq, time: seq * 1_000, turn: 1, step: 0,
+  retry: 1, maxRetries: 2, delayMs: 450,
+  failure: { code: 'TRANSPORT', message: '连接被重置' },
+})
 const toolResult = (seq: number, callId: string, name = 'bash'): ToolResultNode => ({
  kind: 'tool-result', seq, time: seq * 1_000, callId,
  call: { name, argsRaw: `{"command":"cmd-${callId}","description":"run ${callId}"}` },
@@ -128,6 +133,17 @@ describe('chat-flow derivation', () => {
    expect(flowKeys(items)).toBe('n1|n2|g3|n5|g6')
    expect(flowKeys(deriveChatFlow([...nodes, toolResult(7, 'd')]))).toBe('n1|n2|g3|n5|g6')
  })
+
+  it('reuses one stable row for consecutive retries in the same turn', () => {
+    const first = retry(2)
+    const second = { ...retry(3), step: 1, retry: 2 }
+    const initial = deriveChatFlow([user(1, 'try'), first])
+    const updated = deriveChatFlow([user(1, 'try'), first, second])
+    expect(flowKeys(initial)).toBe('n1|n2')
+    expect(flowKeys(updated)).toBe('n1|n2')
+    expect(updated).toHaveLength(2)
+    expect(updated[1]?.kind === 'node' && updated[1].node).toBe(second)
+  })
 })

 describe('ChatView', () => {
@@ -168,6 +184,31 @@ describe('ChatView', () => {
    expect(view.getByText('run a')).toBeTruthy()
  })

+  it('animates only the latest unresolved model retry', () => {
+    const retryNode = retry(2)
+    const nextRetry = { ...retry(3), step: 1, retry: 2 }
+    const context = {
+      kind: 'context', seq: 4, time: 4_000, content: [], source: null,
+    } as const satisfies ConversationNode
+    const h = makeHarness({ nodes: [user(1, 'try'), retryNode], running: true })
+    const view = render(<h.ChatView {...h.props} />)
+    const disclosure = view.container.querySelector('details')
+    expect(disclosure?.dataset.active).toBe('true')
+    expect(view.getByRole('status').textContent).toBe('正在重试模型请求（1/2） · 1s')
+
+    act(() => h.set({ nodes: [user(1, 'try'), retryNode, nextRetry] }))
+    expect(view.getAllByRole('status')).toHaveLength(1)
+    expect(view.container.querySelector('details')).toBe(disclosure)
+    expect(view.getByRole('status').textContent).toBe('正在重试模型请求（2/2） · 1s')
+
+    act(() => h.set({ nodes: [user(1, 'try'), retryNode, nextRetry, context, assistant(5, 'done')] }))
+    expect(disclosure?.dataset.active).toBeUndefined()
+    expect(view.getByRole('status').textContent).toBe('已重试模型请求（2/2） · 1s')
+
+    act(() => h.set({ nodes: [user(1, 'try'), retry(6)], running: false }))
+    expect(disclosure?.dataset.active).toBeUndefined()
+  })
+
  it('renders assistant Markdown across history, streaming, final, and interrupted states while user text stays literal', () => {
    const markdown = '# Rendered\n\n- **one**\n- `two`'
    const h = makeHarness({ nodes: [user(1, markdown), assistant(2, markdown)] })