From 49131c47c514466e460c251c8e021e6f642cb087 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Wed, 29 Jul 2026 14:23:03 +0800 Subject: [PATCH] fix(web): address model retry review feedback --- ...-21-bounded-llm-request-recovery.i18n.yaml | 4 +- ...2026-06-21-bounded-llm-request-recovery.md | 4 +- ...6-06-21-bounded-llm-request-recovery.zh.md | 4 +- apps/web/tests/session-title.snapshot.ts | 25 ++++ .../tests/snapshots/model-retry-cancel.json | 5 + .../client/connection/src/client/fixture.ts | 18 +++ .../client/connection/tests/fixture.spec.ts | 6 + packages/client/runtime/README.i18n.yaml | 4 +- packages/client/runtime/README.md | 2 +- packages/client/runtime/README.zh.md | 2 +- packages/client/runtime/package.json | 1 + .../src/client/sessions/conversation.ts | 5 + .../runtime/src/client/sessions/session.ts | 73 +++++++++--- packages/client/runtime/tests/event-script.ts | 2 +- packages/client/runtime/tests/session.spec.ts | 112 +++++++++++++++--- .../client/ui-conversation/README.i18n.yaml | 4 +- packages/client/ui-conversation/README.md | 2 +- packages/client/ui-conversation/README.zh.md | 2 +- .../src/client/chat/ChatView.tsx | 2 +- .../src/client/chat/MessageItem.tsx | 16 ++- .../tests/chat-branch-tails.spec.tsx | 27 ++++- .../ui-conversation/tests/chat-view.spec.tsx | 15 ++- .../client/ui-trajectory/README.i18n.yaml | 6 +- packages/client/ui-trajectory/README.md | 2 +- packages/client/ui-trajectory/README.zh.md | 2 +- .../client/ui-trajectory/src/client/spans.ts | 7 +- .../client/ui-trajectory/tests/views.spec.tsx | 7 +- pnpm-lock.yaml | 3 + 28 files changed, 301 insertions(+), 61 deletions(-) create mode 100644 apps/web/tests/snapshots/model-retry-cancel.json diff --git a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml index f6dee03e61..8193e5e839 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md -2026-06-21-bounded-llm-request-recovery.md: aadd73bc921e942f523c26027e8fc06aaea38be7 -2026-06-21-bounded-llm-request-recovery.zh.md: 847e20a39bcee697fe61329b68964364c057f666 +2026-06-21-bounded-llm-request-recovery.md: 5c76ed5d754ea40f41dff78cb56ee7fc139a32b1 +2026-06-21-bounded-llm-request-recovery.zh.md: 1fa56f3fe0405cab663c2843d423a78d910170dd diff --git a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md index aadd73bc92..5c76ed5d75 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md +++ b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md @@ -82,7 +82,7 @@ Boundary tests prove termination at both actual transports. The hand-written ada ### Keep attempts separate in the existing log -A failed attempt may leave `assistant/chunk` events in its closed step, but it never appends `assistant/message` and never dispatches a tool. A retry closes the failed turn, opens the next numbered turn, reconstructs the request from the durable surface, and produces its own chunks. UIs may render live chunks while a step is open, then mark or clear that transient view when `llm/retry` identifies the failed step or `turn/end` records failure. Web clears the failed partial at `llm/retry`, projects consecutive retry-turn events into one stable row updated to the latest attempt, counts its delay down in ceiling-rounded seconds with a one-second floor, animates only while unresolved, and keeps exact latest failure details collapsed behind the row. Message derivation continues to ignore the failed chunks, and Web applies the same projection during history rebuild so refreshing cannot resurrect discarded partials or duplicate retry rows. +A failed attempt may leave `assistant/chunk` events in its closed step, but it never appends `assistant/message` and never dispatches a tool. A retry closes the failed turn, opens the next numbered turn, reconstructs the request from the durable surface, and produces its own chunks. UIs may render live chunks while a step is open, then mark or clear that transient view when `llm/retry` identifies the failed step or `turn/end` records failure. Web validates the complete retry payload contract, clears the failed partial at `llm/retry`, projects consecutive retry-turn events into one stable row updated to the latest attempt, and derives scheduled, started, or cancelled status from subsequent turn facts. Its countdown anchors the scheduled delay to browser receipt rather than the Host event clock, uses ceiling-rounded seconds with a one-second floor, animates only while unresolved, and keeps exact latest failure details collapsed behind the row. Retry nodes anchor their own trajectory turn even when the failed attempt has no assistant node. Message derivation continues to ignore the failed chunks, and Web applies the same projection during history rebuild so refreshing cannot resurrect discarded partials or duplicate retry rows. If recovery is exhausted, the final failure is stored once on `turn/end.reason` with the structured facts. If transient recovery continues, `llm/retry` is the durable home for that attempt's failure and delay. No standalone final-error event or response-id vocabulary is added. @@ -116,7 +116,7 @@ If recovery is exhausted, the final failure is stored once on `turn/end.reason` - Pure unit tests cover transient-code selection, exponential backoff and jitter bounds, valid and over-cap `Retry-After`, exhausted budgets, deterministic timer/random seams, and abort during backoff. - Real agent-loop tests cover failure before chunks, partial chunks then failure, thrown and in-band failures, retry to success in a new turn, exhaustion to structured `turn/end.reason`, and composition with `dsh-compact-basic` context-overflow recovery. - The partial-chunk integration test proves failed chunks remain attributed to the failed step, no assistant message or tool side effect is committed for that step, and the successful retry has distinct provenance. -- The plugin-owned `llm/retry` event is non-surface, survives JSONL and SQLite round trips, is ignored by message derivation, and drives TUI and Web retraction plus scheduled-retry rendering. Keyless UI snapshots cover Web scheduling and success, a real Web composition test covers partial transport failure through recovery, and ACP automation snapshots confirm that a discarded attempt stays off the wire while the recovered reply is emitted. +- The plugin-owned `llm/retry` event is non-surface, survives JSONL and SQLite round trips, is ignored by message derivation, and drives TUI and Web retraction plus scheduled-retry rendering. Client tests cover complete wire validation, clock-independent countdown, cancellation versus completed retry labels, and trajectory attribution; keyless UI snapshots cover Web scheduling and success, a real Web composition test covers partial transport failure through recovery, and ACP automation snapshots confirm that a discarded attempt stays off the wire while the recovered reply is emitted. - Idle-watchdog tests prove the stable signal is rearmed only while `next()` is outstanding, disarmed during consumer think time and in `finally`, and classified separately from a total-call deadline and an earlier caller abort; adapter tests prove the signal stops the underlying request rather than merely detaching it. - Direct `ctx.llm.stream()` callers remain single-attempt and receive the same structured failure facts. diff --git a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md index 847e20a39b..1fa56f3fe0 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md @@ -82,7 +82,7 @@ agent-spine 演示组合包加载该插件，因此共享的 stdio/TUI、一次 ### 在现有日志中分隔尝试 -一次失败尝试可以在已关闭的步骤中留下 `assistant/chunk` 事件，但绝不会追加 `assistant/message`，也不会分发工具。重试会关闭失败轮次，开启下一个编号轮次，从持久表层重建请求，并生成自己的分片。步骤仍处于打开状态时，UI 可以渲染实时分片；当 `llm/retry` 标识失败步骤，或 `turn/end` 记录失败时，UI 再标记或清除这份暂时视图。Web 会在 `llm/retry` 到达时清除失败的部分输出，将连续重试轮次的事件投影为稳定的一行，并用最新一次尝试更新该行；它按向上取整且不低于 1 秒的秒数对延迟倒计时，仅在重试尚未结束时显示动画，并把最近一次失败的准确详情折叠在该行之后。消息派生仍会忽略失败分片；Web 在重建历史时也会应用同一投影，因此刷新页面不会让已丢弃的部分输出重新出现，也不会生成重复的重试行。 +一次失败尝试可以在已关闭的步骤中留下 `assistant/chunk` 事件，但绝不会追加 `assistant/message`，也不会分发工具。重试会关闭失败轮次，开启下一个编号轮次，从持久表层重建请求，并生成自己的分片。步骤仍处于打开状态时，UI 可以渲染实时分片；当 `llm/retry` 标识失败步骤，或 `turn/end` 记录失败时，UI 再标记或清除这份暂时视图。Web 会验证完整的重试载荷契约，在 `llm/retry` 到达时清除失败的部分输出，将连续重试轮次的事件投影为稳定的一行，并用最新一次尝试更新该行，再从后续轮次事实派生 scheduled、started 或 cancelled 状态。倒计时以浏览器收到事件的时刻为计划延迟的起点，而不是使用 Host 事件时钟；它按向上取整且不低于 1 秒的秒数显示，仅在重试尚未结束时显示动画，并把最近一次失败的准确详情折叠在该行之后。即使失败尝试没有 assistant 节点，重试节点也会锚定自身的轨迹轮次。消息派生仍会忽略失败分片；Web 在重建历史时也会应用同一投影，因此刷新页面不会让已丢弃的部分输出重新出现，也不会生成重复的重试行。 如果恢复预算耗尽，最终失败会连同结构化事实在 `turn/end.reason` 中存储一次。如果暂时性恢复继续，`llm/retry` 就是该次尝试的失败与延迟的持久归属位置。本决策不增加独立的最终错误事件或响应 id 词汇。 @@ -116,7 +116,7 @@ agent-spine 演示组合包加载该插件，因此共享的 stdio/TUI、一次 - 纯单元测试覆盖暂时性 code 选择、指数退避和抖动边界、有效及超出上限的 `Retry-After`、耗尽的预算、确定性定时器／随机数 seam，以及退避期间中止。 - 真实 agent-loop 测试覆盖分片前失败、部分分片后失败、抛出及带内失败、在新轮次中重试至成功、耗尽后写入结构化 `turn/end.reason`，以及与 `dsh-compact-basic` 上下文溢出恢复的组合。 - 部分分片集成测试证明：失败分片仍归属于失败步骤，该步骤不会提交 assistant 消息或工具副作用，成功的重试具有不同的来源信息。 -- 插件拥有的不进入表层的 `llm/retry` 事件可在 JSONL 和 SQLite 往返后保留，被消息派生忽略，并驱动 TUI 和 Web 撤回及计划重试渲染。无密钥 UI 快照覆盖 Web 的调度与成功，真实 Web 组合测试覆盖部分传输失败直至恢复，ACP 自动化快照确认，被丢弃的尝试不会通过协议发出，而恢复后的回复会正常发出。 +- 插件拥有的不进入表层的 `llm/retry` 事件可在 JSONL 和 SQLite 往返后保留，被消息派生忽略，并驱动 TUI 和 Web 撤回及计划重试渲染。客户端测试覆盖完整的 wire 验证、独立于时钟的倒计时、已取消与已完成重试标签的区别以及轨迹归属；无密钥 UI 快照覆盖 Web 的调度与成功，真实 Web 组合测试覆盖部分传输失败直至恢复，ACP 自动化快照确认，被丢弃的尝试不会通过协议发出，而恢复后的回复会正常发出。 - 空闲看门狗测试证明：只有 `next()` 尚未完成时才会重新布防稳定信号；在消费方思考期间及 `finally` 中会解除布防；它与总调用 deadline 以及更早发生的调用方中止分开分类。适配器测试证明该信号会终止底层请求，而不只是与其脱离。 - `ctx.llm.stream()` 的直接调用方仍只尝试一次，并收到相同的结构化失败事实。 diff --git a/apps/web/tests/session-title.snapshot.ts b/apps/web/tests/session-title.snapshot.ts index b77f82edd5..849ea4a879 100644 --- a/apps/web/tests/session-title.snapshot.ts +++ b/apps/web/tests/session-title.snapshot.ts @@ -33,6 +33,7 @@ interface FixtureTiming { appendTitle(id: string, title: string): void beginModelRetry(id: string): void scheduleModelRetry(id: string, retry?: number, delayMs?: number): void + cancelModelRetryDuringBackoff(id: string, delayMs?: number): void completeModelRetry(id: string): void } @@ -216,3 +217,27 @@ it('retracts a failed stream at llm/retry and retains the durable notice after r await expect(`${JSON.stringify({ beforeRetry, firstRetry, scheduled, expanded, completed }, null, 2)}\n`) .toMatchFileSnapshot('./snapshots/model-retry.json') }) + +it('labels a retry cancelled during backoff without claiming that it started', async () => { + bootFixtureApp() + await selectFixtureSession() + const timing = (globalThis as Record).__fxTiming as FixtureTiming + + act(() => { timing.beginModelRetry('fx-alpha') }) + await screen.findByText('应撤回的半截回复') + act(() => { timing.cancelModelRetryDuringBackoff('fx-alpha', 1_500) }) + + const notice = await screen.findByRole('status') + await waitFor(() => { expect(notice.textContent).toContain('重试已取消') }) + await waitFor(() => { expect(screen.queryByText('应撤回的半截回复')).toBeNull() }) + const disclosure = notice.closest('details') + if (disclosure === null) throw new Error('cancelled retry disclosure missing') + const cancelled = { + notice: notice.textContent, + partialVisible: screen.queryByText('应撤回的半截回复') !== null, + animated: disclosure.dataset.active === 'true', + } + + await expect(`${JSON.stringify(cancelled, null, 2)}\n`) + .toMatchFileSnapshot('./snapshots/model-retry-cancel.json') +}) diff --git a/apps/web/tests/snapshots/model-retry-cancel.json b/apps/web/tests/snapshots/model-retry-cancel.json new file mode 100644 index 0000000000..a61756904b --- /dev/null +++ b/apps/web/tests/snapshots/model-retry-cancel.json @@ -0,0 +1,5 @@ +{ + "notice": "模型请求重试已取消（1/2） · 2s", + "partialVisible": false, + "animated": false +} diff --git a/packages/client/connection/src/client/fixture.ts b/packages/client/connection/src/client/fixture.ts index 1ba6d84173..269203b4ce 100644 --- a/packages/client/connection/src/client/fixture.ts +++ b/packages/client/connection/src/client/fixture.ts @@ -792,6 +792,24 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy { scenario.turn = next scenario.stepStarted = false }, + /** Record one retry decision, then cancel its source turn before the retry starts. */ + cancelModelRetryDuringBackoff(id: string, 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 failure = { code: 'TRANSPORT', message: '连接被重置' } + append(sessionId, { + type: 'llm/retry', + data: { + turn: scenario.turn, step: 1, + provider: 'fixture', mode: 'normal', policyKey: 'fixture-normal', + retry: 1, maxRetries: 2, delayMs, failure, + }, + }) + append(sessionId, { type: 'turn/end', data: { turn: scenario.turn, reason: { kind: 'aborted' } } }) + retryScenarios.delete(sessionId) + setRunning(sessionId, false) + }, /** Finish the timing-hook retry with a finalized response in the open retry turn. */ completeModelRetry(id: string): void { const sessionId = sid(id) diff --git a/packages/client/connection/tests/fixture.spec.ts b/packages/client/connection/tests/fixture.spec.ts index beb855597a..1734f540b3 100644 --- a/packages/client/connection/tests/fixture.spec.ts +++ b/packages/client/connection/tests/fixture.spec.ts @@ -21,6 +21,7 @@ interface TimingHooks { appendTitle(id: string, title: string): void beginModelRetry(id: string): void scheduleModelRetry(id: string, retry?: number, delayMs?: number): void + cancelModelRetryDuringBackoff(id: string, delayMs?: number): void completeModelRetry(id: string): void appendSilent(id: string, msg: string): void breakStreams(): void @@ -630,10 +631,15 @@ describe('createFixtureApi', () => { hooks.beginModelRetry('fx-alpha') hooks.scheduleModelRetry('fx-alpha') hooks.completeModelRetry('fx-alpha') + hooks.beginModelRetry('fx-alpha') + hooks.cancelModelRetryDuringBackoff('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/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' + && f.event.type === 'turn/end' + && f.event.data.reason.kind === 'aborted')).toBe(true) expect(seen.some(f => f.type === 'session/projection' && f.key === 'title' && f.value === 'Fixture 修订标题')).toBe(true) }) expect(seen.some(f => f.type === 'session/event' && JSON.stringify(f.event.data).includes('静默丢帧'))).toBe(false) diff --git a/packages/client/runtime/README.i18n.yaml b/packages/client/runtime/README.i18n.yaml index 6e00fb6c7b..1cf0e42f7b 100644 --- a/packages/client/runtime/README.i18n.yaml +++ b/packages/client/runtime/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/runtime/README.md -README.md: 4f4a957baa8e8e24486318d3ffde235155b5cf73 -README.zh.md: 51f8bc91d59b6971d4a3ff9dfe3d0edd210d2557 +README.md: 45cc032db81aee79061fc2f6a9d9062513629000 +README.zh.md: a769661f6e4f7b1eb6d9872c5b979a871aba3eba diff --git a/packages/client/runtime/README.md b/packages/client/runtime/README.md index 4f4a957baa..45cc032db8 100644 --- a/packages/client/runtime/README.md +++ b/packages/client/runtime/README.md @@ -26,7 +26,7 @@ SlotsService gives the renderer separate bare observables for `useSessions` and ## Model retry projection -The Session object validates plugin-owned, provider-routed `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. Normal-mode notices carry their finite maximum; always-mode notices remain explicitly unbounded. 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. +The Session object validates plugin-owned, provider-routed `llm/retry` payloads at the event wire boundary against the producer's complete field contract, including timer, integer, status, provider-delay, and non-empty diagnostic bounds. A valid event removes the matching failed step's streaming partial and inserts a durable retry notice at the event's sequence position. The notice is `scheduled` until a following retry turn starts; an aborted or disposed source turn marks it `cancelled`, while the retry turn marks it `started`. Normal-mode notices carry their finite maximum; always-mode notices remain explicitly unbounded. 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. ## Session model selection diff --git a/packages/client/runtime/README.zh.md b/packages/client/runtime/README.zh.md index 51f8bc91d5..a769661f6e 100644 --- a/packages/client/runtime/README.zh.md +++ b/packages/client/runtime/README.zh.md @@ -26,7 +26,7 @@ SlotsService 分别为 renderer 提供 `useSessions` 与 `useWorkspaces` 的裸 ## 模型重试投影 -Session 对象会在事件 wire 边界验证由插件负责、按提供方路由的 `llm/retry` 载荷。有效事件会移除对应失败步骤的流式输出片段，并在该事件的序列位置插入一条持久的重试提示。normal mode 提示携带其有限上限；always mode 提示则保持显式无界。窗口重建与历史回放应用相同的投影，因此刷新后，来自已丢弃尝试的日志分片绝不会重新显示为中断回复。没有 `llm/retry` 的终止轮次保留现有行为：可见但尚未定稿的输出会冻结为中断的 assistant 节点。 +Session 对象会在事件 wire 边界依据生产方的完整字段契约，验证由插件负责、按提供方路由的 `llm/retry` 载荷，包括计时器、整数、状态、提供方延迟和非空诊断字段的边界。有效事件会移除对应失败步骤的流式输出片段，并在该事件的序列位置插入一条持久的重试提示。该提示在后续重试轮次开始前为 `scheduled`；源轮次中止或释放会将其标记为 `cancelled`，重试轮次则会将其标记为 `started`。normal mode 提示携带其有限上限；always mode 提示则保持显式无界。窗口重建与历史回放应用相同的投影，因此刷新后，来自已丢弃尝试的日志分片绝不会重新显示为中断回复。没有 `llm/retry` 的终止轮次保留现有行为：可见但尚未定稿的输出会冻结为中断的 assistant 节点。 ## 会话模型选择 diff --git a/packages/client/runtime/package.json b/packages/client/runtime/package.json index 850b504fb3..a3897e9523 100644 --- a/packages/client/runtime/package.json +++ b/packages/client/runtime/package.json @@ -50,6 +50,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-invariants": "workspace:^", + "@deepseek-ai/dsh-timeout": "workspace:^", "@types/react": "~18.3.1", "cordis": "^4.0.0-rc.7" }, diff --git a/packages/client/runtime/src/client/sessions/conversation.ts b/packages/client/runtime/src/client/sessions/conversation.ts index 6d1a448685..530d47f197 100644 --- a/packages/client/runtime/src/client/sessions/conversation.ts +++ b/packages/client/runtime/src/client/sessions/conversation.ts @@ -97,6 +97,11 @@ export type ModelRetryNode = LlmRetryEventData & { seq: number /** Unix epoch ms from the llm/retry session event. */ time: number + /** + * Client-derived lifecycle: scheduled until a retry turn starts, started + * once it does, or cancelled when the failed turn aborts first. + */ + retryState: 'scheduled' | 'started' | 'cancelled' } /** A tool result paired (when in-window) with its call head. */ diff --git a/packages/client/runtime/src/client/sessions/session.ts b/packages/client/runtime/src/client/sessions/session.ts index d8e0bb7978..9be61438d1 100644 --- a/packages/client/runtime/src/client/sessions/session.ts +++ b/packages/client/runtime/src/client/sessions/session.ts @@ -13,8 +13,8 @@ import type { import { transportError } from '@deepseek-ai/dsh-host-apiproxy/api' import type { SessionFace } from '../contract/session.ts' import type { - CodeSubCall, ComposerPhase, ConversationNode, ConversationSnapshot, OpenState, - PromptError, QueuedMessage, RunningToolCall, + CodeSubCall, ComposerPhase, ConversationNode, ConversationSnapshot, ModelRetryNode, + OpenState, PromptError, QueuedMessage, RunningToolCall, } from './conversation.ts' import type { PendingInteraction } from './pending.ts' import { PendingWait } from './pending.ts' @@ -27,6 +27,10 @@ import type { ProjectionsBaseline } from './projection-store.ts' /** Messages requested per history page. */ export const PAGE_MESSAGES = 50 +// Browser bundles cannot value-import the host timeout library. This protocol +// bound is pinned to @deepseek-ai/dsh-timeout's MAX_TIMER_DELAY_MS in tests. +const MAX_RETRY_DELAY_MS = 2_147_483_647 + /** Manager-owned observers of a Session object's local state edges. */ export interface SessionOptions { /** @@ -637,6 +641,7 @@ export class Session implements SessionFace { kind: 'model-retry', seq: event.seq, time: event.time, + retryState: 'scheduled', ...data, }) this.derivedRev++ @@ -702,6 +707,10 @@ export class Session implements SessionFace { return } switch (event.type) { + case 'turn/start': { + if (event.data.trigger.kind === 'retry') this.settleScheduledRetry('started') + return + } case 'assistant/chunk': { const { turn, step, chunk } = event.data if (this.partial === null || this.partial.turn !== turn || this.partial.step !== step) { @@ -730,6 +739,9 @@ export class Session implements SessionFace { return } case 'turn/end': { + if (event.data.reason.kind === 'aborted' || event.data.reason.kind === 'disposed') { + this.settleScheduledRetry('cancelled', event.data.turn) + } // Aborted turns never finalize. The accumulated partial is VALUE, not residue: freeze it // into an interrupted terminal node (pulse stops, text survives) instead of deleting it. // Shared by live and window-replay paths, so a refresh reconstructs the same frozen node @@ -771,6 +783,27 @@ export class Session implements SessionFace { } } + /** + * Settle the newest scheduled retry, optionally restricted to its failed turn. + * @param retryState - next client projection state to publish. + * @param turn - failed turn required for cancellation; omitted for the next retry turn start. + */ + private settleScheduledRetry( + retryState: Exclude, + turn?: number, + ): void { + const index = this.derivedNodes.findLastIndex(node => + node.kind === 'model-retry' + && node.retryState === 'scheduled' + && (turn === undefined || node.turn === turn)) + if (index < 0) return + const node = this.derivedNodes[index] + /* v8 ignore next -- findLastIndex's predicate narrows the indexed node only at runtime. */ + if (node?.kind !== 'model-retry') return + this.derivedNodes[index] = { ...node, retryState } + this.derivedRev++ + } + /** Re-derive state (partial/openCalls/derivedNodes) from raw window events after a rebuild — keeps * paging/stitching consistent, and makes live handling and history replay converge on the same * retry notices and interrupted nodes. */ @@ -854,37 +887,49 @@ function parseRetryEventData(value: unknown): LlmRetryEventData | null { const failure = data.failure if (failure === null || typeof failure !== 'object') return null const failureData = failure as Record - if (!nonNegativeInteger(data.turn) - || !nonNegativeInteger(data.step) + if (!nonNegativeSafeInteger(data.turn) + || !nonNegativeSafeInteger(data.step) || typeof data.provider !== 'string' || data.provider.length === 0 || typeof data.policyKey !== 'string' || data.policyKey.length === 0 - || !positiveInteger(data.retry) + || !positiveSafeInteger(data.retry) || typeof data.delayMs !== 'number' || !Number.isFinite(data.delayMs) || data.delayMs < 0 + || data.delayMs > MAX_RETRY_DELAY_MS || typeof failureData.message !== 'string' - || typeof failureData.code !== 'string') return null + || failureData.message.length === 0 + || typeof failureData.code !== 'string' + || failureData.code.length === 0) return null if (data.mode === 'normal') { - if (!positiveInteger(data.maxRetries) || data.retry > data.maxRetries) return null + if (!positiveSafeInteger(data.maxRetries) || data.retry > data.maxRetries) return null } else if (data.mode === 'always') { if ('maxRetries' in data) return null } else { 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 + if (failureData.status !== undefined + && (typeof failureData.status !== 'number' + || !Number.isInteger(failureData.status) + || failureData.status < 100 + || failureData.status > 599)) return null + if (failureData.providerRetryAfterMs !== undefined + && (typeof failureData.providerRetryAfterMs !== 'number' + || !Number.isFinite(failureData.providerRetryAfterMs) + || failureData.providerRetryAfterMs <= 0)) return null + if (failureData.requestId !== undefined + && (typeof failureData.requestId !== 'string' + || failureData.requestId.length === 0)) 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 nonNegativeSafeInteger(value: unknown): value is number { + return typeof value === 'number' && Number.isSafeInteger(value) && value >= 0 } -function positiveInteger(value: unknown): value is number { - return nonNegativeInteger(value) && value > 0 +function positiveSafeInteger(value: unknown): value is number { + return nonNegativeSafeInteger(value) && value > 0 } /** diff --git a/packages/client/runtime/tests/event-script.ts b/packages/client/runtime/tests/event-script.ts index d77c3a7251..b96fffaae9 100644 --- a/packages/client/runtime/tests/event-script.ts +++ b/packages/client/runtime/tests/event-script.ts @@ -81,7 +81,7 @@ export const ev = { failure: { code: 'TRANSPORT', message }, }, }), - turnEnd: (seq: number, turn: number, reason: 'completed' | 'cancelled' = 'completed'): SessionEvent => + turnEnd: (seq: number, turn: number, reason: 'completed' | 'aborted' | 'disposed' = 'completed'): SessionEvent => at(seq, { type: 'turn/end', data: { turn, reason: { kind: reason } } }), commandRun: (seq: number, commandId: string, name: string, args = ''): SessionEvent => at(seq, { type: 'command/run', data: { commandId, name, args, source: { kind: 'user' } } }), diff --git a/packages/client/runtime/tests/session.spec.ts b/packages/client/runtime/tests/session.spec.ts index 99bd9bf0c3..df465b063f 100644 --- a/packages/client/runtime/tests/session.spec.ts +++ b/packages/client/runtime/tests/session.spec.ts @@ -8,6 +8,7 @@ import { describe, expect, it, vi } from 'vitest' import type { SessionEvent } from '@deepseek-ai/dsh-session/types' +import { MAX_TIMER_DELAY_MS } from '@deepseek-ai/dsh-timeout' import type { SessionId } from '@deepseek-ai/dsh-client-connection/client' import { Session } from '../src/client/sessions/session.ts' import { FakeApiClient, deferred, err, ok } from './fake-api.ts' @@ -179,6 +180,7 @@ describe('live event path', () => { expect(snapshot.partial).toBeNull() expect(snapshot.nodes.at(-1)).toMatchObject({ kind: 'model-retry', + retryState: 'scheduled', turn: 1, step: 0, provider: 'fake', @@ -194,6 +196,7 @@ describe('live event path', () => { 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(-2)).toMatchObject({ kind: 'model-retry', retryState: 'started' }) expect(snapshot.nodes.at(-1)).toMatchObject({ kind: 'assistant', blocks: [{ kind: 'text', text: '完整回复' }] }) const replay = makeSession() @@ -203,31 +206,88 @@ describe('live event path', () => { expect(replay.session.getSnapshot().partial).toBeNull() }) - it('ignores malformed retry payloads without retracting the current partial', async () => { + it('rejects retry payloads outside the producer contract 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 valid = { + turn: 1, step: 0, + provider: 'fake', mode: 'normal', policyKey: 'fake-normal', + retry: 1, maxRetries: 2, delayMs: 500, + failure: { code: 'TRANSPORT', message: 'temporary failure' }, + } + const invalid = [ + { ...valid, turn: Number.MAX_SAFE_INTEGER + 1 }, + { ...valid, step: Number.MAX_SAFE_INTEGER + 1 }, + { ...valid, provider: '' }, + { ...valid, policyKey: '' }, + { ...valid, retry: Number.MAX_SAFE_INTEGER + 1 }, + { ...valid, maxRetries: Number.MAX_SAFE_INTEGER + 1 }, + { ...valid, delayMs: -1 }, + { ...valid, delayMs: Number.POSITIVE_INFINITY }, + { ...valid, delayMs: MAX_TIMER_DELAY_MS + 1 }, + { ...valid, failure: { ...valid.failure, message: '' } }, + { ...valid, failure: { ...valid.failure, code: '' } }, + { ...valid, failure: { ...valid.failure, status: '429' } }, + { ...valid, failure: { ...valid.failure, status: 99 } }, + { ...valid, failure: { ...valid.failure, status: 429.5 } }, + { ...valid, failure: { ...valid.failure, status: 600 } }, + { ...valid, failure: { ...valid.failure, providerRetryAfterMs: 0 } }, + { ...valid, failure: { ...valid.failure, providerRetryAfterMs: Number.POSITIVE_INFINITY } }, + { ...valid, failure: { ...valid.failure, requestId: 1 } }, + { ...valid, failure: { ...valid.failure, requestId: '' } }, + ] const errorSpy = vi.spyOn(console, 'error').mockImplementation(() => undefined) try { - feed(at(9, { - type: 'llm/retry', - data: { - turn: 1, step: 0, - provider: 'fake', mode: 'normal', policyKey: 'fake-normal', - retry: 3, maxRetries: 2, delayMs: 500, - failure: { code: 'TRANSPORT', message: 'bad budget' }, - }, - })) + for (const [index, data] of invalid.entries()) { + feed(at(9 + index, { type: 'llm/retry', data })) + } 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).toHaveBeenCalledTimes(invalid.length) expect(errorSpy).toHaveBeenCalledWith('[web-runtime] ignored malformed llm/retry event at seq 9') } finally { errorSpy.mockRestore() } }) + it('accepts complete retry payloads at the producer field boundaries', async () => { + const { session } = await opened() + session.handleMuxEnvelope('r' as never, { + type: 'session/event', + sessionId: SID, + event: at(6, { + type: 'llm/retry', + data: { + turn: Number.MAX_SAFE_INTEGER, + step: Number.MAX_SAFE_INTEGER, + provider: 'fake', + mode: 'normal', + policyKey: 'fake-normal', + retry: Number.MAX_SAFE_INTEGER, + maxRetries: Number.MAX_SAFE_INTEGER, + delayMs: MAX_TIMER_DELAY_MS, + failure: { + code: 'RATE_LIMIT', + message: 'provider busy', + status: 599, + providerRetryAfterMs: Number.MIN_VALUE, + requestId: 'req-1', + }, + }, + }), + }) + expect(session.getSnapshot().nodes.at(-1)).toMatchObject({ + kind: 'model-retry', + retryState: 'scheduled', + retry: Number.MAX_SAFE_INTEGER, + delayMs: MAX_TIMER_DELAY_MS, + failure: { status: 599, providerRetryAfterMs: Number.MIN_VALUE, requestId: 'req-1' }, + }) + }) + it('projects always-mode retries and rejects mode-specific maximums or unknown modes', async () => { const { session } = await opened() const feed = (event: SessionEvent) => { session.handleMuxEnvelope('r' as never, { type: 'session/event', sessionId: SID, event }) } @@ -244,6 +304,7 @@ describe('live event path', () => { })) expect(session.getSnapshot().nodes.at(-1)).toMatchObject({ kind: 'model-retry', + retryState: 'scheduled', mode: 'always', retry: 3, }) @@ -273,6 +334,27 @@ describe('live event path', () => { } }) + it.each(['aborted', 'disposed'] as const)( + 'marks a scheduled retry as cancelled when its failed turn ends %s', + async (reason) => { + 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.retry(7, 1)) + expect(session.getSnapshot().nodes.at(-1)).toMatchObject({ + kind: 'model-retry', + retryState: 'scheduled', + }) + feed(ev.turnEnd(8, 1, reason)) + expect(session.getSnapshot().nodes.at(-1)).toMatchObject({ + kind: 'model-retry', + retryState: 'cancelled', + }) + }, + ) + 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 }) } @@ -280,7 +362,7 @@ describe('live event path', () => { feed(ev.user(7, '要被打断的')) feed(ev.chunkStart(8, 1)) feed(ev.chunkText(9, 1, '说到一半')) - feed(ev.turnEnd(10, 1, 'cancelled')) // no assistant/message ever arrives + feed(ev.turnEnd(10, 1, 'aborted')) // no assistant/message ever arrives const snapshot = session.getSnapshot() expect(snapshot.partial).toBeNull() const frozen = snapshot.nodes.at(-1) @@ -299,7 +381,7 @@ describe('live event path', () => { expect(session.getSnapshot().runningCalls).toEqual([]) // Second call never resolves: turn/end freezes it as an error card. feed(ev.toolCall(9, 1, 'c2', 'slow_tool', '{}')) - feed(ev.turnEnd(10, 1, 'cancelled')) + feed(ev.turnEnd(10, 1, 'aborted')) const snapshot = session.getSnapshot() expect(snapshot.runningCalls).toEqual([]) expect(snapshot.nodes.at(-1)).toMatchObject({ @@ -615,7 +697,7 @@ describe('remaining branches', () => { 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)) // empty text block only, no delta - feed(ev.turnEnd(8, 1, 'cancelled')) + feed(ev.turnEnd(8, 1, 'aborted')) const snapshot = session.getSnapshot() expect(snapshot.partial).toBeNull() expect(snapshot.nodes.filter(n => n.kind === 'assistant' && (n as { interrupted?: true }).interrupted)).toEqual([]) @@ -629,7 +711,7 @@ describe('remaining branches', () => { feed(ev.turnStart(6, 1)) feed(ev.toolCall(7, 1, 'turn1-call', 'echo', '{}')) feed(ev.toolCall(8, 2, 'turn2-call', 'echo', '{}')) // stray call attributed to a later turn - feed(ev.turnEnd(9, 1, 'cancelled')) + feed(ev.turnEnd(9, 1, 'aborted')) const snapshot = session.getSnapshot() expect(snapshot.runningCalls.map(c => c.callId)).toEqual(['turn2-call']) expect(snapshot.nodes.at(-1)).toMatchObject({ kind: 'tool-result', callId: 'turn1-call', isError: true }) @@ -723,7 +805,7 @@ describe('remaining branches', () => { const feed = (event: SessionEvent) => { session.handleMuxEnvelope('r' as never, { type: 'session/event', sessionId: SID, event }) } feed(ev.turnStart(6, 1)) feed(at(7, { type: 'assistant/chunk', data: { turn: 1, step: 0, chunk: { type: 'tool-call-delta', index: 0, id: 'c1', name: 'echo', argumentsDelta: '{' } } })) - feed(ev.turnEnd(8, 1, 'cancelled')) + feed(ev.turnEnd(8, 1, 'aborted')) const frozen = session.getSnapshot().nodes.at(-1) expect(frozen).toMatchObject({ kind: 'assistant', interrupted: true, blocks: [{ kind: 'tool-call', callId: 'c1' }] }) }) diff --git a/packages/client/ui-conversation/README.i18n.yaml b/packages/client/ui-conversation/README.i18n.yaml index ffc82ea731..4e7f3e017e 100644 --- a/packages/client/ui-conversation/README.i18n.yaml +++ b/packages/client/ui-conversation/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/ui-conversation/README.md -README.md: cd72aaca7c82a02777ededdf542bf5272359fb77 -README.zh.md: ffbeace6d5b7c6af8b4ce6e50e643ea65f446584 +README.md: 408a76ed86c6a48762db2bae8534e950219c816a +README.zh.md: 68128c7a4c271b491e4a1463e3c7ce4a4e86b1eb diff --git a/packages/client/ui-conversation/README.md b/packages/client/ui-conversation/README.md index cd72aaca7c..408a76ed86 100644 --- a/packages/client/ui-conversation/README.md +++ b/packages/client/ui-conversation/README.md @@ -10,7 +10,7 @@ The view ring IS a slot: the conversation registration declares the `'conversati Generic tool rows classify the built-in bash, read, search, write, edit, and run_code names into dedicated visual variants. The filesystem variants render the edit icon and a path summary; that path is a hover-underline link that opens the file with the host OS default application (`host.openPath`, relative paths resolve against the session cwd). Tool rows are not whole-row click targets and do not open the details panel. The code variant summarizes with the model-authored `description` and expands to the program itself; its logged sub-dispatches render as always-visible nested rows through the SAME keyed toolview hole (custom registrations and the GenericToolCard fallback apply to sub-rows unchanged). Cordis lifecycle tools reuse those generic variants while presenting `Inspect`, `Mount temporary Plugin`, and `Unmount temporary Plugin` with a shared Cordis accent; mount keeps the code variant's expandable source rendering. -The chat flow projects consecutive model-retry nodes across retry turns 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. Normal policy rows show the finite retry maximum; always policy rows show `∞`. 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. +The chat flow projects consecutive model-retry nodes across retry turns 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 anchors the scheduled delay to client receipt, avoiding host/browser clock skew, rounds remaining time up to seconds, and has a one-second floor. The latest unresolved retry uses a left-to-right text shimmer. Subsequent turn facts distinguish an attempt that started from one cancelled during backoff, while the Host running bit only controls the live animation; the row then shows a static completed or cancelled label. Normal policy rows show the finite retry maximum; always policy rows show `∞`. 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`/`openFile`) and `ToolRowProps` pre-composes it with the session standard kit. A registrant is a plain plugin: `ctx.slots.register({ name: 'conversation.chat.toolview', key: '', 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). diff --git a/packages/client/ui-conversation/README.zh.md b/packages/client/ui-conversation/README.zh.md index ffbeace6d5..68128c7a4c 100644 --- a/packages/client/ui-conversation/README.zh.md +++ b/packages/client/ui-conversation/README.zh.md @@ -10,7 +10,7 @@ 通用工具行把内置的 bash、read、search、write、edit 和 run_code 名称归入专用视觉变体。文件系统变体会渲染 edit 图标和路径摘要；该路径是悬停下划线链接，点击后通过宿主操作系统的默认应用打开文件（`host.openPath`，相对路径相对会话 cwd 解析）。工具行不再是整行点击目标，也不会打开 details 面板。code 变体以模型撰写的 `description` 作摘要，展开后显示程序本身；其已记录的子调用经由同一个键控 toolview 空位渲染为始终可见的嵌套行（自定义注册和 GenericToolCard fallback 原样适用于子行）。Cordis 生命周期工具复用这些通用变体，同时以统一的 Cordis 强调色呈现 `Inspect`、`Mount temporary Plugin` 和 `Unmount temporary Plugin`；mount 行保留 code 变体的可展开源码渲染。 -聊天流会将跨重试轮次连续出现的模型重试节点投影为一个稳定的弱化状态行，并用最新一次尝试更新该行；每个重试事件仍保留在运行时快照与会话日志中。前端倒计时由计划延迟派生，剩余时间向上取整到秒，且下限为 1 秒。最近一次尚未完成的重试会显示从左到右的文字渐变动画，完成后则稳定显示为静态的已完成标签。normal 策略行显示有限重试上限；always 策略行显示 `∞`。激活该行会显示最近一次重试的精确延迟和失败消息。客户端运行时会在相应重试节点到达前移除每个失败步骤的流式输出尾部；后续某次尝试成功后，该状态仍保持可见。 +聊天流会将跨重试轮次连续出现的模型重试节点投影为一个稳定的弱化状态行，并用最新一次尝试更新该行；每个重试事件仍保留在运行时快照与会话日志中。前端倒计时以客户端收到事件的时刻为计划延迟的起点，避免 Host 与浏览器的时钟偏差；剩余时间向上取整到秒，且下限为 1 秒。最近一次尚未完成的重试会显示从左到右的文字渐变动画。后续轮次事实用于区分已开始的尝试与在退避期间取消的尝试，Host 的 running 位只控制实时动画；随后该行会显示静态的已完成或已取消标签。normal 策略行显示有限重试上限；always 策略行显示 `∞`。激活该行会显示最近一次重试的精确延迟和失败消息。客户端运行时会在相应重试节点到达前移除每个失败步骤的流式输出尾部；后续某次尝试成功后，该状态仍保持可见。 工具行同样是 slot：独立工具环（`ToolViewRegistry`／`ctx.toolviews`／outlet）已经退役。聊天配置项声明键控的 `'conversation.chat.toolview'` 空位（Session scope；key 空间在运行时开放）；其渲染点逐行通过 `entryKey: toolName` 分发，并以 `GenericToolCard` 作为调用点 `fallback`。owner 载荷是统一的 `ToolRowOwnerProps`（`callId`／`toolName`／`block`／`openFile`），`ToolRowProps` 则预先将其与 Session 标准工具包组合。注册方只是普通插件：`ctx.slots.register({ name: 'conversation.chat.toolview', key: '', inject? }, Row)`，以 `inject: ['slots', 'conversation']` 作为加载顺序 seam（apply 在聊天注册后挂载 ConversationService，因此服务存在即可保证 slot 已声明）；Session 区分在组件内部完成（`useSessions` 读取 `parentId`，bash 示例是第三方姿态的范例）。Trajectory/waterfall 工具视图 slot 共享此形状，并随各自的渲染点落地（RendersCheck 会拒绝没有任何渲染方的声明）。 diff --git a/packages/client/ui-conversation/src/client/chat/ChatView.tsx b/packages/client/ui-conversation/src/client/chat/ChatView.tsx index c45c6f1c8c..cafbf4dfcd 100644 --- a/packages/client/ui-conversation/src/client/chat/ChatView.tsx +++ b/packages/client/ui-conversation/src/client/chat/ChatView.tsx @@ -50,7 +50,7 @@ function activeRetrySeq(nodes: readonly ConversationNode[], running: boolean): n for (let index = nodes.length - 1; index >= 0; index -= 1) { const node = nodes[index] if (node === undefined) continue - if (node.kind === 'model-retry') return node.seq + if (node.kind === 'model-retry') return node.retryState === 'cancelled' ? null : node.seq if (node.kind === 'assistant' || node.kind === 'user') return null } return null diff --git a/packages/client/ui-conversation/src/client/chat/MessageItem.tsx b/packages/client/ui-conversation/src/client/chat/MessageItem.tsx index cdd0efacad..5c3c99d1e0 100644 --- a/packages/client/ui-conversation/src/client/chat/MessageItem.tsx +++ b/packages/client/ui-conversation/src/client/chat/MessageItem.tsx @@ -4,7 +4,7 @@ // off the snapshot cache; memo holds across streaming because unchanged nodes // keep their references. -import { memo, useCallback, useEffect, useState, type ReactNode } from 'react' +import { memo, useCallback, useEffect, useMemo, useState, type ReactNode } from 'react' import type { ContextMessageNode, ModelRetryNode, SteeringMessageNode, UnknownSurfaceNode, UserMessageNode, } from '@deepseek-ai/dsh-client-runtime/client' @@ -40,7 +40,9 @@ interface RetryCountdown { } function ModelRetryItem({ node, active }: { node: ModelRetryNode; active: boolean }) { - const deadline = node.time + node.delayMs + // Anchor the host-scheduled delay to this browser's first render of the + // retry node. Host event time and Date.now() may belong to different clocks. + const deadline = useMemo(() => Date.now() + node.delayMs, [node.delayMs, node.seq]) const scheduledSeconds = retrySeconds(node.delayMs) const maximum = node.mode === 'normal' ? node.maxRetries : '∞' const [countdown, setCountdown] = useState(() => ({ @@ -69,11 +71,19 @@ function ModelRetryItem({ node, active }: { node: ModelRetryNode; active: boolea return () => { window.clearInterval(timer) } }, [active, deadline]) + const label = active + ? '正在重试模型请求' + : node.retryState === 'cancelled' + ? '模型请求重试已取消' + : node.retryState === 'started' + ? '已重试模型请求' + : '等待重试模型请求' + return (
- {active ? '正在重试' : '已重试'}模型请求（{node.retry}/{maximum}） · {active ? remainingSeconds : scheduledSeconds}s + {label}（{node.retry}/{maximum}） · {active ? remainingSeconds : scheduledSeconds}s
diff --git a/packages/client/ui-conversation/tests/chat-branch-tails.spec.tsx b/packages/client/ui-conversation/tests/chat-branch-tails.spec.tsx index 7eda67ba91..502602c073 100644 --- a/packages/client/ui-conversation/tests/chat-branch-tails.spec.tsx +++ b/packages/client/ui-conversation/tests/chat-branch-tails.spec.tsx @@ -125,6 +125,7 @@ describe('MessageItem arms', () => { kind: 'model-retry', seq: 5, time: 10_000, + retryState: 'scheduled', turn: 1, step: 0, provider: 'mock', @@ -157,6 +158,7 @@ describe('MessageItem arms', () => { kind: 'model-retry', seq: 6, time: 12_100, + retryState: 'scheduled', turn: 2, step: 0, provider: 'mock', @@ -180,6 +182,7 @@ describe('MessageItem arms', () => { kind: 'model-retry', seq: 6, time: 12_100, + retryState: 'started', turn: 2, step: 0, provider: 'mock', @@ -200,6 +203,7 @@ describe('MessageItem arms', () => { kind: 'model-retry', seq: 7, time: 12_100, + retryState: 'started', turn: 3, step: 0, provider: 'mock', @@ -212,6 +216,26 @@ describe('MessageItem arms', () => { />, ) expect(view.getByRole('status').textContent).toBe('已重试模型请求（3/∞） · 4s') + + view.rerender( + , + ) + expect(view.getByRole('status').textContent).toBe('模型请求重试已取消（1/2） · 4s') }) it('synchronizes the countdown when an inactive retry becomes active at the one-second floor', () => { @@ -221,6 +245,7 @@ describe('MessageItem arms', () => { kind: 'model-retry', seq: 5, time: 10_000, + retryState: 'scheduled', turn: 1, step: 0, provider: 'mock', @@ -232,7 +257,7 @@ describe('MessageItem arms', () => { failure: { code: 'TRANSPORT', message: '连接被重置' }, } as const const view = render() - expect(view.getByRole('status').textContent).toBe('已重试模型请求（1/2） · 5s') + expect(view.getByRole('status').textContent).toBe('等待重试模型请求（1/2） · 5s') act(() => { vi.advanceTimersByTime(4_200) }) view.rerender() diff --git a/packages/client/ui-conversation/tests/chat-view.spec.tsx b/packages/client/ui-conversation/tests/chat-view.spec.tsx index 9ae2a6519d..8bc196aa80 100644 --- a/packages/client/ui-conversation/tests/chat-view.spec.tsx +++ b/packages/client/ui-conversation/tests/chat-view.spec.tsx @@ -67,6 +67,7 @@ const assistant = (seq: number, text: string): AssistantMessageNode => ({ }) const retry = (seq: number): ModelRetryNode => ({ kind: 'model-retry', seq, time: seq * 1_000, turn: 1, step: 0, + retryState: 'scheduled', provider: 'mock', mode: 'normal', policyKey: 'mock-normal', retry: 1, maxRetries: 2, delayMs: 450, failure: { code: 'TRANSPORT', message: '连接被重置' }, @@ -232,15 +233,25 @@ describe('ChatView', () => { 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')] }) + h.set({ + nodes: [ + user(1, 'try'), + retryNode, + { ...nextRetry, retryState: 'started' }, + context, + assistant(5, 'done'), + ], + running: false, + }) }) 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 }) + h.set({ nodes: [user(1, 'try'), { ...retry(6), retryState: 'cancelled' }], running: true }) }) expect(disclosure?.dataset.active).toBeUndefined() + expect(view.getByRole('status').textContent).toContain('重试已取消') }) it('renders assistant Markdown across history, streaming, final, and interrupted states while user text stays literal', () => { diff --git a/packages/client/ui-trajectory/README.i18n.yaml b/packages/client/ui-trajectory/README.i18n.yaml index b07fe7a1fd..57cff40b19 100644 --- a/packages/client/ui-trajectory/README.i18n.yaml +++ b/packages/client/ui-trajectory/README.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -README.md: 9e7dee8d5572baad13d7598d1fbde7b042dd5ab4 -README.zh.md: da14d5265c16acb4e75d21bc445ef9702c83e697 +# pnpm run verify-translation-pairing --write packages/client/ui-trajectory/README.md +README.md: fa8dee1b40c661f46a8e9962bd4606267b030a23 +README.zh.md: 0e4c6071d7cff04d2f1b40945332d9b66ca2da1b diff --git a/packages/client/ui-trajectory/README.md b/packages/client/ui-trajectory/README.md index 9e7dee8d55..fa8dee1b40 100644 --- a/packages/client/ui-trajectory/README.md +++ b/packages/client/ui-trajectory/README.md @@ -2,7 +2,7 @@ English | [中文](README.zh.md) -Trajectory turn-list chrome (sticky Turn / Message·Step groups / step cells) plus Waterfall placeholder; the pure-consumer minimal plugin exemplar (registers two view tabs into the conversation's `'conversation.view'` slot ring, provides no service, declares no Context merge). Contract: api-contracts v3 §8. +Trajectory turn-list chrome (sticky Turn / Message·Step groups / step cells) plus Waterfall placeholder; the pure-consumer minimal plugin exemplar (registers two view tabs into the conversation's `'conversation.view'` slot ring, provides no service, declares no Context merge). Conversation nodes carrying a turn, including model-retry notices without assistant output, anchor their own trajectory span instead of inheriting the preceding turn. Contract: api-contracts v3 §8. ## Model Experience diff --git a/packages/client/ui-trajectory/README.zh.md b/packages/client/ui-trajectory/README.zh.md index da14d5265c..0e4c6071d7 100644 --- a/packages/client/ui-trajectory/README.zh.md +++ b/packages/client/ui-trajectory/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -轨迹轮次列表 chrome（吸顶 Turn／Message·Step 分组／步骤单元格）及 Waterfall 占位符；这是纯消费方最小插件范例（向会话的 `'conversation.view'` slot 环注册两个视图标签页，不提供服务，也不声明 Context 合并）。契约：api-contracts v3 §8。 +轨迹轮次列表 chrome（吸顶 Turn／Message·Step 分组／步骤单元格）及 Waterfall 占位符；这是纯消费方最小插件范例（向会话的 `'conversation.view'` slot 环注册两个视图标签页，不提供服务，也不声明 Context 合并）。携带轮次的会话节点（包括没有 assistant 输出的模型重试提示）会锚定自身的轨迹区段，而不会继承前一个轮次。契约：api-contracts v3 §8。 ## 模型体验 diff --git a/packages/client/ui-trajectory/src/client/spans.ts b/packages/client/ui-trajectory/src/client/spans.ts index 585a336333..e52c152725 100644 --- a/packages/client/ui-trajectory/src/client/spans.ts +++ b/packages/client/ui-trajectory/src/client/spans.ts @@ -43,8 +43,9 @@ export interface SpanStats { /** * Fold snapshot nodes into per-turn spans. Only assistant nodes carry a turn - * number; user/steering/context/tool nodes attach to the turn last seen in - * sequence order (turn 0 collects the pre-assistant prologue). + * number; retry and steering nodes also carry their owning turn, while + * user/context/tool nodes attach to the turn last seen in sequence order + * (turn 0 collects the pre-assistant prologue). * @param nodes - snapshot nodes in surface order. * @returns spans ordered by first appearance. */ @@ -85,7 +86,7 @@ export function deriveSpanStats(spans: readonly TurnSpan[]): SpanStats { } function hasTurn(node: ConversationNode): node is ConversationNode & { turn: number } { - return node.kind === 'assistant' || node.kind === 'steering' + return node.kind === 'assistant' || node.kind === 'steering' || node.kind === 'model-retry' } /** diff --git a/packages/client/ui-trajectory/tests/views.spec.tsx b/packages/client/ui-trajectory/tests/views.spec.tsx index 917beaccc6..432b06ccc1 100644 --- a/packages/client/ui-trajectory/tests/views.spec.tsx +++ b/packages/client/ui-trajectory/tests/views.spec.tsx @@ -208,18 +208,21 @@ describe('tab switching in ConversationRoot', () => { }) describe('span derivation', () => { - it('attributes prologue to turn 0 and follows steering turn tags', () => { + it('attributes prologue to turn 0 and follows steering and retry turn tags', () => { const nodes = [ { kind: 'user', seq: 1 }, { kind: 'steering', seq: 2, turn: 5 }, { kind: 'user', seq: 3 }, + { kind: 'model-retry', seq: 4, turn: 6 }, + { kind: 'user', seq: 5 }, ] as unknown as ConversationSnapshot['nodes'] const spans = deriveSpans(nodes) expect(spans).toEqual([ { turn: 0, steps: 0, calls: 0, nodes: 1 }, { turn: 5, steps: 0, calls: 0, nodes: 2 }, + { turn: 6, steps: 0, calls: 0, nodes: 2 }, ]) - expect(deriveSpanStats(spans)).toEqual({ turns: 2, steps: 0, calls: 0 }) + expect(deriveSpanStats(spans)).toEqual({ turns: 3, steps: 0, calls: 0 }) }) it('empty inputs produce zero stats and standalone components render their empty forms', () => { diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 3bbb55d747..430dac9073 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -935,6 +935,9 @@ importers: '@deepseek-ai/dsh-invariants': specifier: workspace:^ version: link:../../support/invariants + '@deepseek-ai/dsh-timeout': + specifier: workspace:^ + version: link:../../util/timeout '@types/react': specifier: ~18.3.1 version: 18.3.31