Consider it done. The open-source AI agent that works out of the box · 想到,就能做到。开源、开箱即用的 AI Agent。
TypeScript agentai-agentai-assistantandroidclaude-codecodexelectroniosllmmacosreact-nativetypescriptwindows
fix(provider-group): 组内电脑连不上时先按退避重试 5 次,恢复了留在原电脑继续,都不行再换
Lizifa58757f32e7
diff --git a/apps/desktop/src/main/maker-ipc/__tests__/agent-input-coordinator.test.ts b/apps/desktop/src/main/maker-ipc/__tests__/agent-input-coordinator.test.tsindex 581780268b..b26c794785 100644--- a/apps/desktop/src/main/maker-ipc/__tests__/agent-input-coordinator.test.ts+++ b/apps/desktop/src/main/maker-ipc/__tests__/agent-input-coordinator.test.ts@@ -13978,7 +13978,7 @@ describe('provider group computer switch hold', () => {sessionTotal: 0,};- async function failWhileSwitching(sid: string, cause: 'usage-limit' | null = 'usage-limit') {+ async function failWhileSwitching(sid: string, cause: 'usage-limit' | 'unavailable' | null = 'usage-limit') {const candidate = vi.fn<NonNullable<AgentInputCoordinatorDeps['providerGroupSwitchCandidate']>>(() => cause,);@@ -14070,4 +14070,52 @@ describe('provider group computer switch hold', () => {// 错误已不是当前状态:结算只清登记,不再弹横幅。expect(h.coordinator.releaseProviderGroupSwitchHold(sid, holdId)).toBe(false);});++ it('shows "reconnecting n/5" while waiting for the original computer, and "switching" once it gives up', async () => {+ const sid = 'group-hold-reconnect';+ const { h } = await failWhileSwitching(sid, 'unavailable');+ const holdId = h.coordinator.getProviderGroupSwitchHoldId(sid)!;+ expect(h.coordinator.setProviderGroupSwitchHoldProgress(sid, holdId + 1, { attempt: 1, maxAttempts: 5 })).toBe(false);+ expect(h.coordinator.setProviderGroupSwitchHoldProgress(sid, holdId, { attempt: 2, maxAttempts: 5 })).toBe(true);+ // 一次普通的重连:新旧端都显示「重新连接中 2/5」,不带 groupSwitchPending;错误仍不呈现。+ expect(latestProjection(h.projections).error).toBeNull();+ expect(latestProjection(h.projections).autoResumePending).toEqual({+ error: MESSAGE,+ attempt: 2,+ maxAttempts: 5,+ sessionTotal: 0,+ });+ expect(h.coordinator.setProviderGroupSwitchHoldProgress(sid, holdId, null)).toBe(true);+ expect(latestProjection(h.projections).autoResumePending).toMatchObject({+ attempt: 0,+ groupSwitchPending: { cause: 'unavailable' },+ });+ // 放出来之后不再改。+ expect(h.coordinator.releaseProviderGroupSwitchHold(sid, holdId)).toBe(true);+ expect(h.coordinator.setProviderGroupSwitchHoldProgress(sid, holdId, { attempt: 3, maxAttempts: 5 })).toBe(false);+ expect(latestProjection(h.projections).error).toBe(MESSAGE);+ expect(latestProjection(h.projections).autoResumePending).toBeUndefined();+ });++ it('shows progress on a message that has not gone out while the group waits before sending', async () => {+ const h = createHarness();+ const sid = 'group-send-reconnect';+ const send = deferred<AgentInputSendResult>();+ h.sendToAgent.mockImplementationOnce(async () => send.promise);+ h.coordinator.enqueue(sid, makeItem('q-1', 'hello'));+ await flush();+ h.coordinator.setProviderGroupSendReconnect(sid, { attempt: 1, maxAttempts: 5 });+ expect(latestProjection(h.projections).autoResumePending).toEqual({ attempt: 1, maxAttempts: 5, sessionTotal: 0 });+ h.coordinator.setProviderGroupSendReconnect(sid, 'switching');+ expect(latestProjection(h.projections).autoResumePending).toMatchObject({+ groupSwitchPending: { cause: 'unavailable' },+ });+ h.coordinator.setProviderGroupSendReconnect(sid, null);+ expect(latestProjection(h.projections).autoResumePending).toBeUndefined();+ // 派出去之后不再挂到这一轮上。+ send.resolve(sendSuccess());+ await flush();+ h.coordinator.setProviderGroupSendReconnect(sid, { attempt: 2, maxAttempts: 5 });+ expect(latestProjection(h.projections).autoResumePending).toBeUndefined();+ });});diff --git a/apps/desktop/src/main/maker-ipc/__tests__/makerSendTransaction.test.ts b/apps/desktop/src/main/maker-ipc/__tests__/makerSendTransaction.test.tsindex e915b6ed98..4591cfc3a7 100644--- a/apps/desktop/src/main/maker-ipc/__tests__/makerSendTransaction.test.ts+++ b/apps/desktop/src/main/maker-ipc/__tests__/makerSendTransaction.test.ts@@ -3308,6 +3308,31 @@ describe('session-agent-switch handoff injection', () => {expect(bootstrapOpts.resumeSessionId).toBeUndefined();});+ it('发送前的准备期间被停止(如供应商组在等原电脑恢复)→ 不再打开会话,按「派发前取消」返回', async () => {+ const controller = new AbortController();+ const getSession = vi.fn((): MakerSendTransactionSession | null => null);+ const bootstrapSession = vi.fn(async (): Promise<never> => {+ throw new Error('must not open a session after the send was stopped');+ });+ const { deps } = createDeps({+ getSession,+ bootstrapSession,+ applyPendingAgentSwitch: vi.fn(async () => {+ controller.abort();+ }),+ });+ const transaction = createMakerSendTransaction(deps);+ const result = await transaction.sendToAgentAccepted(+ 'session-1',+ { type: 'user', content: 'hi' },+ { agentKind: 'claude-code', workingDir: 'C:\Users\admin\AppData\Local\Temp\w' },+ { signal: controller.signal },+ );+ expect(result).toMatchObject({ accepted: false, reason: 'cancelled-before-dispatch' });+ expect(getSession).not.toHaveBeenCalled();+ expect(bootstrapSession).not.toHaveBeenCalled();+ });+it('排队 drain 端到端:切换在派发时刻落实(关旧引擎)→ createOpts 按 DB 对齐新引擎 → 交接注入新引擎首条 + scheduler origin 透传', async () => {// 复刻 coordinator drain 一条排队 scheduler 心跳时对 sendToAgentAccepted 的调用:// 入队的是裸 prompt(不含交接)+ 旧引擎(claude-code)createOpts。drain 时会话已diff --git a/apps/desktop/src/main/maker-ipc/agent-input-coordinator.ts b/apps/desktop/src/main/maker-ipc/agent-input-coordinator.tsindex 182fb65d7d..537dc668fd 100644--- a/apps/desktop/src/main/maker-ipc/agent-input-coordinator.ts+++ b/apps/desktop/src/main/maker-ipc/agent-input-coordinator.ts@@ -667,6 +667,11 @@ interface ActiveTurn {* `undefined` 表示当前没有待回滚的采纳。*/preContinuationVendorTurnGeneration?: number | null;+ /**+ * 供应商组在发送前等原电脑恢复(这条还没派出去,provider-groups.md §6.1):投影的进行中行显示+ * 「重新连接中 n/5」。挂在这一轮上,轮次结束或换掉即一起消失。+ */+ providerGroupReconnect?: AutoResumeInfo;}interface PendingCompactRequest {@@ -766,6 +771,8 @@ interface SessionInputState {/** 每次登记唯一:host 暂存的 error 行与结算都按它对号,迟到的旧结算不会碰到下一次失败。 */id: number;recovery: NonNullable<AgentInputRecovery>;+ cause: AutoResumeAgentSwitchCause;+ /** 投影里的进行中行:换电脑时「正在换一台电脑继续」,先等原电脑恢复时「重新连接中 n/5」。 */info: AutoResumeInfo;} | null;recovery: AgentInputRecovery;@@ -913,6 +920,22 @@ function isUsageLimitWaitLive(state: SessionInputState, token?: number): booleanreturn state.usageLimitWait?.resumeAt != null && isUsageLimitCandidateCurrent(state, token);}+/**+ * 换电脑期间进行中行的内容。`error` 只用来让 renderer 认出随后到达的终态 event 是同一次失败的回声(不再点亮+ * 横幅)。换电脑时次数都给 0(不是重连),旧端按普通的「重新连接中」显示、不带次数;先等原电脑恢复时就是一次+ * 普通的重连:不带 groupSwitchPending,新旧端都显示「重新连接中 n/5」,展开看原因。+ */+function providerGroupSwitchHoldInfo(+ cause: AutoResumeAgentSwitchCause,+ error: string | undefined,+ progress: { attempt: number; maxAttempts: number } | null,+): AutoResumeInfo {+ const base = error ? { error } : {};+ return progress+ ? { ...base, attempt: progress.attempt, maxAttempts: progress.maxAttempts, sessionTotal: 0 }+ : { ...base, attempt: 0, maxAttempts: 0, sessionTotal: 0, groupSwitchPending: { cause } };+}+/** 换电脑期间先不呈现的那次错误仍是当前状态:登记时的 recovery 没被换掉、错误仍在、没有别的自愈接管。 */function isProviderGroupSwitchHoldLive(state: SessionInputState): boolean {const hold = state.providerGroupSwitchHold;@@ -4306,9 +4329,9 @@ export class AgentInputCoordinator {const autoResumePending = state.autoResumePending ?? (groupSwitchHeld? state.providerGroupSwitchHold!.info- : state.activeTurn?.item?.autoResume &&- state.activeTurn.dispatchLifecycle !== 'dispatched'- ? state.activeTurn.item.autoResumeInfo+ : state.activeTurn && state.activeTurn.dispatchLifecycle !== 'dispatched'+ ? state.activeTurn.providerGroupReconnect ??+ (state.activeTurn.item?.autoResume ? state.activeTurn.item.autoResumeInfo : undefined): undefined);const recovery: AgentInputRecovery =@@ -6571,18 +6594,51 @@ export class AgentInputCoordinator {state.providerGroupSwitchHold = {id: ++this.providerGroupSwitchHoldSeq,recovery: state.recovery!,- info: {- // 只用来让 renderer 认出随后到达的终态 event 是同一次失败的回声(不再点亮横幅),行内不显示它。- ...(message ? { error: message } : {}),- // 不是重连:次数都给 0,旧端按普通的「重新连接中」显示、不带次数。- attempt: 0,- maxAttempts: 0,- sessionTotal: 0,- groupSwitchPending: { cause },- },+ cause,+ info: providerGroupSwitchHoldInfo(cause, message, null),};}+ /**+ * 换电脑这一趟先等原电脑恢复(那台连不上):进行中行改为「重新连接中 attempt/maxAttempts」;传 null 回到+ * 「正在换一台电脑继续」。只认仍有效的那次登记;返回是否更新了。+ */+ setProviderGroupSwitchHoldProgress(+ sessionId: string,+ id: number,+ progress: { attempt: number; maxAttempts: number } | null,+ ): boolean {+ const state = this.states.get(sessionId);+ const hold = state?.providerGroupSwitchHold;+ if (!state || !hold || hold.id !== id || !isProviderGroupSwitchHoldLive(state)) return false;+ hold.info = providerGroupSwitchHoldInfo(hold.cause, hold.info.error, progress);+ this.emit(sessionId);+ return true;+ }++ /**+ * 供应商组在发送前等原电脑恢复(这条还没派出去):进行中行显示「重新连接中 attempt/maxAttempts」,没等到、开始换电脑+ * 时(`switching`)显示「正在换一台电脑继续」,传 null 撤掉。只挂在还没派发的这一轮上;没有这样的一轮时不做什么。+ */+ setProviderGroupSendReconnect(+ sessionId: string,+ progress: { attempt: number; maxAttempts: number } | 'switching' | null,+ ): void {+ const active = this.states.get(sessionId)?.activeTurn;+ if (!active || active.dispatchLifecycle === 'dispatched') return;+ if (!progress && !active.providerGroupReconnect) return;+ if (progress) {+ active.providerGroupReconnect = providerGroupSwitchHoldInfo(+ 'unavailable',+ undefined,+ progress === 'switching' ? null : progress,+ );+ } else {+ delete active.providerGroupReconnect;+ }+ this.emit(sessionId);+ }+/*** 这次错误正因供应商组换电脑而先不呈现时返回那次登记的 id(host 据此暂不落 error 行、不弹 Agent Island,* 并按 id 结算);没有返回 null。diff --git a/apps/desktop/src/main/maker-ipc/makerSendTransaction.ts b/apps/desktop/src/main/maker-ipc/makerSendTransaction.tsindex 5e6c40a631..fd3e639ac5 100644--- a/apps/desktop/src/main/maker-ipc/makerSendTransaction.ts+++ b/apps/desktop/src/main/maker-ipc/makerSendTransaction.ts@@ -488,9 +488,10 @@ export interface MakerSendTransactionDeps {* session-agent-switch:turn 运行中登记的切换意图在**发送时刻**执行(先于* getSession——apply 会 close 旧引擎,随后本事务按 DB 新值 lazy-create 新引擎,* 交接注入走下面的 pending handoff 通道)。apply 内部自查 turn 空闲,仍在跑则- * 保留意图本次不动。undefined = 不启用(测试最小 harness)。+ * 保留意图本次不动。undefined = 不启用(测试最小 harness)。`signal` 是这次发送的取消信号:+ * 供应商组在这里等原电脑恢复时,发送被停止就不再等、不再换电脑。*/- applyPendingAgentSwitch?(sessionId: string): Promise<void>;+ applyPendingAgentSwitch?(sessionId: string, options?: { signal?: AbortSignal }): Promise<void>;/*** 发送前换窗:必须在 getSession 之前。prepare 会关掉不健康的 live handle,* 随后本事务按空 session 走 lazy-create,避免 peek 之后对已关闭对象 send。@@ -986,7 +987,20 @@ export function createMakerSendTransaction(deps: MakerSendTransactionDeps): Make// session-agent-switch:pending 切换在发送时刻生效(用户语义:「消息真正发出// 去时才切」)。必须在 getSession 之前——apply 会 close 旧引擎的 live session,// 让下方走 lazy-create 按 DB 新值 spawn 新引擎。- await deps.applyPendingAgentSwitch?.(sessionId);+ await deps.applyPendingAgentSwitch?.(+ sessionId,+ requestedSendOpts.signal ? { signal: requestedSendOpts.signal } : undefined,+ );+ // 发送前的准备期间就被停止(如供应商组正在等原电脑恢复):不再打开会话、不再派发,与 Session 在派发前+ // 收到取消是同一个结果,由调用方按「派发前取消」收尾。+ if (requestedSendOpts.signal?.aborted) {+ return toCompatibleMakerSendResult(+ toDesktopSessionDispatchOutcome(+ { accepted: false, reason: 'cancelled-before-dispatch' },+ { source: 'maker-ipc', context: `SEND/${sessionId}/before-session` },+ ),+ );+ }await deps.prepareUnhealthySession?.(sessionId);let sess = deps.getSession(sessionId);// Maker keeps a failed Session registered until its real handle cleanupdiff --git a/apps/desktop/src/main/maker-ipc/register.ts b/apps/desktop/src/main/maker-ipc/register.tsindex e3294c28b5..cef34acedc 100644--- a/apps/desktop/src/main/maker-ipc/register.ts+++ b/apps/desktop/src/main/maker-ipc/register.ts@@ -9717,6 +9717,11 @@ export function registerMakerIpc(maker: Maker, options: RegisterMakerIpcOptions)await withSendToSessionLock(sessionId, run);},isTurnRunning: (sessionId) => maker.getSession(sessionId)?.isTurnRunning() ?? false,+ // 没有开着的会话(或已出错)时这次发送要重新打开 Agent 所在电脑上的会话:发送前现读那台的状态。+ hasLiveSession: (sessionId) => {+ const live = maker.getSession(sessionId);+ return live?.getStatus() === 'active';+ },// 分享来的供应商被分享者建成了组:组所在电脑发来「需要换一台」时自动交接(provider-groups.md §6.1)。guestSwitch: getProviderGroupGuestSwitch(),continueSession: async (sessionId, token, info) =>@@ -15472,14 +15477,20 @@ export function registerMakerIpc(maker: Maker, options: RegisterMakerIpcOptions)// 调用方自报;与手机说明同层(只进 wire 消息)。isCindyMakeSession: async (sessionId) =>(await readSessionSource(sessionId)) === CINDY_MAKE_SESSION_SOURCE,- applyPendingAgentSwitch: async (sessionId) => {+ applyPendingAgentSwitch: async (sessionId, options) => {await applyPendingAgentSwitchIfIdle(agentSwitchDeps, sessionId);- // 已归组的任务所在那台现在不能用时,先换到组里下一台再发(失败不影响这次发送)。- await providerGroupService?.beforeSend(sessionId).catch((error) => {+ // 已归组的任务所在那台现在不能用时,先换到组里下一台再发(失败不影响这次发送);离线时先等它恢复,+ // 等的时候进行中行显示「重新连接中 n/5」。+ await providerGroupService?.beforeSend(sessionId, {+ ...(options?.signal ? { signal: options.signal } : {}),+ progress: (state) => agentInputCoordinatorHolder?.setProviderGroupSendReconnect(sessionId, state),+ }).catch((error) => {log.warn('provider group: pre-send check failed', {sessionId,error: error instanceof Error ? error.message : String(error),});+ }).finally(() => {+ agentInputCoordinatorHolder?.setProviderGroupSendReconnect(sessionId, null);});},prepareUnhealthySession: (sessionId) =>@@ -16653,15 +16664,30 @@ export function registerMakerIpc(maker: Maker, options: RegisterMakerIpcOptions)let hooks: ProviderGroupTurnErrorHooks | undefined;let holdTimer: ReturnType<typeof setTimeout> | undefined;if (holdId !== null) {+ // 久久没有结局时到点放出来。每次重试、开始换电脑时重新计时:等原电脑恢复本身就可能要一两分钟,+ // 不让等的时间吃掉换电脑的时间(到点放出会把协同 Worker 的异常终止回报给 Lead)。+ const armHoldTimer = () => {+ clearTimeout(holdTimer);+ holdTimer = setTimeout(+ () => releaseProviderGroupHeld(sessionId, holdId),+ PROVIDER_GROUP_SWITCH_HOLD_MAX_MS,+ );+ };// 协同 Worker 的终态与 error 行按同一次登记结算:换成了不回报这次异常终止,没换成才回报给 Lead。hooks = {beforeFallback: () => releaseProviderGroupHeld(sessionId, holdId),resumed: () => discardProviderGroupHeld(sessionId, holdId),+ // 先等原电脑恢复时进行中行显示「重新连接中 n/5」,开始换电脑时改回「正在换一台电脑继续」。+ reconnecting: (attempt, maxAttempts) => {+ armHoldTimer();+ inputCoordinator.setProviderGroupSwitchHoldProgress(sessionId, holdId, { attempt, maxAttempts });+ },+ switching: () => {+ armHoldTimer();+ inputCoordinator.setProviderGroupSwitchHoldProgress(sessionId, holdId, null);+ },};- holdTimer = setTimeout(- () => releaseProviderGroupHeld(sessionId, holdId),- PROVIDER_GROUP_SWITCH_HOLD_MAX_MS,- );+ armHoldTimer();}void providerGroupService.onTurnError(sessionId, signals, candidateToken, hooks)diff --git a/apps/desktop/src/main/provider-group/__tests__/directory.test.ts b/apps/desktop/src/main/provider-group/__tests__/directory.test.tsindex ab9f105990..d5420818a3 100644--- a/apps/desktop/src/main/provider-group/__tests__/directory.test.ts+++ b/apps/desktop/src/main/provider-group/__tests__/directory.test.ts@@ -227,3 +227,55 @@ describe('resolveMembers', () => {expect(d.readDeviceProviders).toHaveBeenCalledTimes(2);});});++describe('probe (waiting for a computer to come back, §6.1)', () => {+ it('tells apart a computer that cannot be reached from one whose provider cannot be used', async () => {+ const directory = createProviderGroupDirectory(deps());+ expect(await directory.probe('mini', 'anthropic-1a2b3c4d')).toBe('ok');+ expect(await directory.probe('off', 'anthropic')).toBe('offline');+ expect(await directory.probe('mini', 'gone')).toBe('unavailable');+ expect(await directory.probe('share:s1', 'anthropic')).toBe('ok');+ expect(await directory.probe('share:s2', 'anthropic')).toBe('unavailable');+ });++ it('does not wait for a computer that is online but turned off remote control', async () => {+ const directory = createProviderGroupDirectory(deps({+ listDevices: async () => [device('mini', { remoteControlEnabled: false })],+ }));+ expect(await directory.probe('mini', 'anthropic-1a2b3c4d')).toBe('unavailable');+ });++ it('reads a shared computer directly instead of trusting the periodically refreshed online flag', async () => {+ const directory = createProviderGroupDirectory(deps({+ listReceivedShares: () => [share('s1', { hostOnline: false })],+ }));+ // 快照还说离线,其实已经能读到那台的目录:按恢复算。+ expect(await directory.probe('share:s1', 'anthropic')).toBe('ok');+ // 真读不到时仍是离线。+ const unreachable = createProviderGroupDirectory(deps({+ listReceivedShares: () => [share('s1', { hostOnline: false })],+ readDeviceProviders: async () => {+ throw new Error('unreachable');+ },+ }));+ expect(await unreachable.probe('share:s1', 'anthropic')).toBe('offline');+ });++ it('reads the current state instead of the cached one', async () => {+ let miniOnline = true;+ const d = deps({ listDevices: async () => [device('self', { isSelf: true }), device('mini', { online: miniOnline })] });+ const directory = createProviderGroupDirectory(d);+ const config: ProviderGroupConfig = {+ strategy: 'least',+ autoSwitch: true,+ members: [{ key: 'device:mini:anthropic-1a2b3c4d', kind: 'device', agentDeviceId: 'mini', providerId: 'anthropic-1a2b3c4d', limit: 4, weight: 1, paused: false }],+ };+ await directory.resolveMembers('anthropic', config);+ miniOnline = false;+ expect(await directory.probe('mini', 'anthropic-1a2b3c4d')).toBe('offline');+ miniOnline = true;+ expect(await directory.probe('mini', 'anthropic-1a2b3c4d')).toBe('ok');+ // 那台的目录也现读,不用短时缓存。+ expect(d.readDeviceProviders).toHaveBeenCalledTimes(2);+ });+});diff --git a/apps/desktop/src/main/provider-group/__tests__/remoteGroup.test.ts b/apps/desktop/src/main/provider-group/__tests__/remoteGroup.test.tsindex ed40ca48cc..61a11fd05c 100644--- a/apps/desktop/src/main/provider-group/__tests__/remoteGroup.test.ts+++ b/apps/desktop/src/main/provider-group/__tests__/remoteGroup.test.ts@@ -8,12 +8,13 @@ import { describe, expect, it, vi } from 'vitest';import type { ProviderGroupConfig, ProviderGroupMember, ProviderGroupView } from '../../../shared/providerGroup';import type { ProviderGroupBinding, ProviderGroupRef } from '../bindings';-import type { ProviderGroupDirectory } from '../directory';+import type { ProviderGroupDirectory, ResolvedMemberState } from '../directory';import { createProviderGroupRouter } from '../router';import {createProviderGroupService,PROVIDER_GROUP_ADOPT_TIMEOUT_MS,PROVIDER_GROUP_BEFORE_SEND_TIMEOUT_MS,+ PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS,PROVIDER_GROUP_UNAVAILABLE_ERROR,type ProviderGroupRemoteGroups,type ProviderGroupServiceDeps,@@ -47,10 +48,13 @@ function harness(options: {const bindings = new Map<string, ProviderGroupBinding>();/** 因组内电脑被移出或组被删除而解除过的任务 → 那个组。 */const released = new Map<string, ProviderGroupRef>();+ // 现读那台的状态(等它恢复时用):默认一直连不上,单测按需逐次指定。+ const probe = vi.fn(async (_agentDeviceId: string, _providerId: string): Promise<ResolvedMemberState> => 'offline');const directory: ProviderGroupDirectory = {resolveMembers: async () => [],listCandidates: async () => [],readDeviceCatalog: async () => [],+ probe,memberLabel: (m) => m.label ?? m.key,invalidate: vi.fn(),};@@ -136,9 +140,11 @@ function harness(options: {fallback: vi.fn(),readResetAt: vi.fn((): number | null => 5_000),now: () => 1_000,+ // 等原电脑恢复时的退避不真等。+ sleep: vi.fn(async (_ms: number) => {}),log: { info: vi.fn(), warn: vi.fn() },} satisfies ProviderGroupServiceDeps;- return { service: createProviderGroupService(deps), deps, remote, row, bindings, released };+ return { service: createProviderGroupService(deps), deps, remote, row, bindings, released, probe };}async function flush() {@@ -299,12 +305,63 @@ describe('switching computers within a group on another computer', () => {it('only avoids an unreachable computer itself instead of cooling it for the whole group', async () => {const h = bound({ picks: [SELF] });- h.service.onTurnError('s1', { message: '[REMOTE_AGENT_DEVICE_UNREACHABLE] gone' }, 3);- await flush();+ await h.service.onTurnError('s1', { message: '[REMOTE_AGENT_DEVICE_UNREACHABLE] gone' }, 3);+ // 先等它恢复:本机现读那台(组内电脑坐标照本机的写法),重试用完才换。+ expect(h.probe).toHaveBeenCalledWith('studio', STUDIO.providerId);+ expect(h.deps.sleep).toHaveBeenCalledTimes(PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS);expect(h.remote.cool).not.toHaveBeenCalled();expect(h.deps.switchAgentLocation).toHaveBeenCalledWith('s1', expect.objectContaining({ agentDeviceId: null, providerId: 'anthropic' }), expect.anything());});+ it('continues on the same computer when it comes back, without asking the group computer for another', async () => {+ const h = bound({ picks: [SELF] });+ h.probe.mockResolvedValueOnce('offline').mockResolvedValueOnce('ok');+ await h.service.onTurnError('s1', { message: '[REMOTE_AGENT_DEVICE_UNREACHABLE] gone' }, 3);+ expect(h.remote.pick).not.toHaveBeenCalled();+ expect(h.deps.switchAgentLocation).not.toHaveBeenCalled();+ expect(h.bindings.get('s1')).toMatchObject({ memberKey: STUDIO.key, groupDeviceId: OWNER });+ expect(h.deps.continueSession).toHaveBeenCalledWith('s1', 7, expect.objectContaining({+ agentReconnect: { computer: 'Studio' },+ }));+ });++ it('still waits for its own computer when the group computer cannot be read, but cannot switch', async () => {+ // 常见是任务就跑在组所在电脑上、它自己断了:组读不到,只按任务记录里的位置等它恢复。+ const back = bound({ config: undefined });+ back.probe.mockResolvedValueOnce('offline').mockResolvedValueOnce('ok');+ await back.service.onTurnError('s1', { message: '[REMOTE_AGENT_DEVICE_UNREACHABLE] gone' }, 3);+ expect(back.probe).toHaveBeenCalledWith('studio', STUDIO.providerId);+ expect(back.deps.continueSession).toHaveBeenCalledWith('s1', 7, expect.objectContaining({+ agentReconnect: { computer: '' },+ }));+ expect(back.deps.fallback).not.toHaveBeenCalled();+ expect(back.deps.switchAgentLocation).not.toHaveBeenCalled();+ expect(back.bindings.has('s1')).toBe(true);++ // 等不到:换不了电脑,交回原有处理。+ const gone = bound({ config: undefined });+ await gone.service.onTurnError('s1', { message: '[REMOTE_AGENT_DEVICE_UNREACHABLE] gone' }, 3);+ expect(gone.deps.sleep).toHaveBeenCalledTimes(PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS);+ expect(gone.deps.fallback).toHaveBeenCalledTimes(1);+ expect(gone.deps.switchAgentLocation).not.toHaveBeenCalled();+ });++ it('waits before sending for its own computer when the group computer cannot be read and the session must be reopened', async () => {+ const reopen = bound({ config: undefined });+ Object.assign(reopen.deps, { hasLiveSession: () => false });+ const progress = vi.fn();+ await reopen.service.beforeSend('s1', { progress });+ expect(reopen.probe).toHaveBeenCalledWith('studio', STUDIO.providerId);+ expect(progress).toHaveBeenCalledTimes(PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS);+ expect(progress).not.toHaveBeenCalledWith('switching');+ expect(reopen.deps.switchAgentLocation).not.toHaveBeenCalled();++ // 会话还开着:照常发送,不现读。+ const live = bound({ config: undefined });+ await live.service.beforeSend('s1');+ expect(live.probe).not.toHaveBeenCalled();+ });+it('hands the error back when the group computer cannot be reached', async () => {const h = bound({ config: undefined });h.service.onTurnError('s1', { sdkError: 'rate_limit' }, 3);@@ -377,6 +434,9 @@ describe('switching computers within a group on another computer', () => {it('moves the task before sending when the group computer says its computer is offline', async () => {const h = bound({ view: { [STUDIO.key]: 'offline' }, picks: [SHARED] });await h.service.beforeSend('s1');+ // 现读一次仍离线,等满重试次数才换。+ expect(h.probe).toHaveBeenCalledWith('studio', STUDIO.providerId);+ expect(h.deps.sleep).toHaveBeenCalledTimes(PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS);expect(h.deps.switchAgentLocation).toHaveBeenCalledWith('s1',expect.objectContaining({ agentDeviceId: 'share:s1', providerId: 'anthropic' }),diff --git a/apps/desktop/src/main/provider-group/__tests__/remoteHandler.test.ts b/apps/desktop/src/main/provider-group/__tests__/remoteHandler.test.tsindex 00389e3004..bda34d3d9d 100644--- a/apps/desktop/src/main/provider-group/__tests__/remoteHandler.test.ts+++ b/apps/desktop/src/main/provider-group/__tests__/remoteHandler.test.ts@@ -175,6 +175,7 @@ describe('provider-group:remote', () => {},listCandidates: async () => [],readDeviceCatalog: async () => [],+ probe: async () => 'ok' as const,memberLabel: (m) => m.label ?? m.key,invalidate: vi.fn(),};diff --git a/apps/desktop/src/main/provider-group/__tests__/router.test.ts b/apps/desktop/src/main/provider-group/__tests__/router.test.tsindex 2392270bd2..68a3e89d40 100644--- a/apps/desktop/src/main/provider-group/__tests__/router.test.ts+++ b/apps/desktop/src/main/provider-group/__tests__/router.test.ts@@ -49,6 +49,9 @@ function harness(reported: Record<string, number>, bindings: Record<string, Provasync readDeviceCatalog() {return [];},+ async probe() {+ return 'ok' as const;+ },memberLabel: (m) => m.key,invalidate: () => undefined,};diff --git a/apps/desktop/src/main/provider-group/__tests__/service.test.ts b/apps/desktop/src/main/provider-group/__tests__/service.test.tsindex 1668de608d..621ae4bbb1 100644--- a/apps/desktop/src/main/provider-group/__tests__/service.test.ts+++ b/apps/desktop/src/main/provider-group/__tests__/service.test.ts@@ -9,11 +9,12 @@ import { describe, expect, it, vi } from 'vitest';import type { ProviderGroupConfig, ProviderGroupMember } from '../../../shared/providerGroup';import type { ProviderGroupBinding, ProviderGroupRef } from '../bindings';-import type { ProviderGroupDirectory, ResolvedProviderGroupMember } from '../directory';+import type { ProviderGroupDirectory, ResolvedMemberState, ResolvedProviderGroupMember } from '../directory';import { createProviderGroupGuestSwitch, PROVIDER_GROUP_SWITCH_OFFER_TTL_MS } from '../guestSwitch';import { createProviderGroupRouter, PROVIDER_GROUP_DEFAULT_COOLDOWN_MS } from '../router';import {createProviderGroupService,+ PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS,PROVIDER_GROUP_SUPERSEDED_ERROR,PROVIDER_GROUP_UNAVAILABLE_ERROR,type ProviderGroupServiceDeps,@@ -61,6 +62,11 @@ function harness(options: {const bindings = new Map<string, ProviderGroupBinding>();/** 因组内电脑被移出或组被删除而解除过的任务 → 那个组。 */const released = new Map<string, ProviderGroupRef>();+ // 现读那台的状态:默认与组内电脑状态同一份离线名单,单测按需逐次指定。+ const probe = vi.fn(async (agentDeviceId: string, providerId: string): Promise<ResolvedMemberState> => {+ const found = config.members.find((m) => m.agentDeviceId === agentDeviceId && m.providerId === providerId);+ return found && offline.has(found.key) ? 'offline' : 'ok';+ });const directory: ProviderGroupDirectory = {async resolveMembers(_providerId, current) {return current.members.map((m): ResolvedProviderGroupMember => offline.has(m.key)@@ -73,6 +79,7 @@ function harness(options: {async readDeviceCatalog() {return [];},+ probe,memberLabel: (m) => m.label ?? m.key,invalidate: vi.fn(),};@@ -126,14 +133,17 @@ function harness(options: {row.providerId = route.providerId;}),isTurnRunning: vi.fn(() => false),+ hasLiveSession: vi.fn((_id: string) => true),continueSession: vi.fn(async () => 'resumed' as const),fallback: vi.fn(),readResetAt: vi.fn(() => null),now: () => now,+ // 等原电脑恢复时的退避不真等。+ sleep: vi.fn(async (_ms: number) => {}),log: { info: vi.fn(), warn: vi.fn() },} satisfies ProviderGroupServiceDeps;const service = createProviderGroupService(deps);- return { service, deps, row, bindings, released, router, config, offline, advance: (ms: number) => { now += ms; } };+ return { service, deps, row, bindings, released, router, config, offline, probe, advance: (ms: number) => { now += ms; } };}async function flush() {@@ -550,11 +560,166 @@ describe('onTurnError (automatic switch)', () => {});});+describe('waiting for a computer that cannot be reached before switching (§6.1)', () => {+ const UNREACHABLE = { message: '[REMOTE_AGENT_DEVICE_UNREACHABLE] unreachable' };++ function onMini() {+ const h = harness({ members: [MINI, LOCAL], row: { agentDeviceId: 'mini', providerId: MINI.providerId } });+ h.bindings.set('s1', { providerId: 'anthropic', memberKey: MINI.key, at: 1 });+ const hooks = { reconnecting: vi.fn(), switching: vi.fn(), resumed: vi.fn(), beforeFallback: vi.fn() };+ return { ...h, hooks };+ }++ it('retries with backoff and continues on the same computer once it is back', async () => {+ const h = onMini();+ h.probe.mockResolvedValueOnce('offline').mockResolvedValueOnce('offline').mockResolvedValueOnce('ok');+ await h.service.onTurnError('s1', UNREACHABLE, 7, h.hooks);+ expect(h.hooks.reconnecting.mock.calls).toEqual([+ [1, PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS],+ [2, PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS],+ ]);+ // 退避:第二次比第一次等得久。+ const [first, second] = h.deps.sleep.mock.calls.map(([ms]) => ms);+ expect(second).toBeGreaterThan(first!);+ // 不交接、不冷却、绑定不动,在原电脑续跑,活动记录写「已重新连上」。+ expect(h.deps.switchAgentLocation).not.toHaveBeenCalled();+ expect(h.bindings.get('s1')?.memberKey).toBe(MINI.key);+ expect(h.router.coolingUntil('anthropic', MINI.key)).toBeNull();+ expect(h.deps.continueSession).toHaveBeenCalledWith('s1', 99, expect.objectContaining({+ agentReconnect: { computer: MINI.key },+ }));+ expect(h.hooks.resumed).toHaveBeenCalledTimes(1);+ expect(h.hooks.switching).not.toHaveBeenCalled();+ expect(h.deps.fallback).not.toHaveBeenCalled();+ });++ it('switches to the next computer after five failed retries, and says so before switching', async () => {+ const h = onMini();+ h.probe.mockResolvedValue('offline');+ await h.service.onTurnError('s1', UNREACHABLE, 7, h.hooks);+ expect(h.hooks.reconnecting).toHaveBeenCalledTimes(PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS);+ expect(h.deps.sleep).toHaveBeenCalledTimes(PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS);+ expect(h.hooks.switching).toHaveBeenCalledTimes(1);+ expect(h.hooks.switching.mock.invocationCallOrder[0]).toBeGreaterThan(+ h.hooks.reconnecting.mock.invocationCallOrder.at(-1)!,+ );+ expect(h.deps.switchAgentLocation).toHaveBeenCalledWith(+ 's1',+ expect.objectContaining({ agentDeviceId: null, providerId: 'anthropic' }),+ expect.anything(),+ );+ expect(h.deps.continueSession).toHaveBeenCalledWith('s1', 99, expect.objectContaining({+ agentSwitch: expect.objectContaining({ to: 'local-name', cause: 'unavailable' }),+ }));+ expect(h.hooks.resumed).toHaveBeenCalledTimes(1);+ });++ it('switches right away when the computer answers but the failure was not about the connection, or its provider cannot be used', async () => {+ // 远程那边没能启动 Agent 等:那台连得上,问题不在连接。+ const notConnection = { message: '[REMOTE_AGENT_UNAVAILABLE] the agent could not start' };+ for (const [signals, state] of [[notConnection, 'ok'], [UNREACHABLE, 'unavailable']] as const) {+ const h = onMini();+ h.probe.mockResolvedValue(state);+ await h.service.onTurnError('s1', signals, 7, h.hooks);+ expect(h.probe).toHaveBeenCalledTimes(1);+ expect(h.deps.sleep).not.toHaveBeenCalled();+ expect(h.hooks.reconnecting).not.toHaveBeenCalled();+ expect(h.hooks.switching).not.toHaveBeenCalled();+ expect(h.deps.switchAgentLocation).toHaveBeenCalledTimes(1);+ }+ });++ it('counts a dropped connection that is already back as one retry and continues on the same computer', async () => {+ for (const signals of [UNREACHABLE, { reason: 'remote_agent_closed', message: 'remote agent closed' }]) {+ const h = onMini();+ h.probe.mockResolvedValue('ok');+ await h.service.onTurnError('s1', signals, 7, h.hooks);+ expect(h.deps.sleep).not.toHaveBeenCalled();+ expect(h.hooks.reconnecting.mock.calls).toEqual([[1, PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS]]);+ expect(h.deps.switchAgentLocation).not.toHaveBeenCalled();+ expect(h.deps.continueSession).toHaveBeenCalledWith('s1', 99, expect.objectContaining({+ agentReconnect: { computer: MINI.key },+ }));+ }+ // 反复断:这一轮的次数用完就换,不会一直在原电脑上重来。+ const flapping = onMini();+ flapping.probe.mockResolvedValue('ok');+ for (let token = 1; token <= PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS + 1; token++) {+ await flapping.service.onTurnError('s1', UNREACHABLE, token, flapping.hooks);+ }+ expect(flapping.deps.switchAgentLocation).toHaveBeenCalledTimes(1);+ const reconnects = (flapping.deps.continueSession.mock.calls as unknown[][])+ .filter((call) => (call[2] as { agentReconnect?: unknown } | undefined)?.agentReconnect !== undefined);+ expect(reconnects).toHaveLength(PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS);+ });++ it('does not wait for this computer, or for failures that are not about reaching a computer', async () => {+ const local = harness();+ local.bindings.set('s1', { providerId: 'anthropic', memberKey: 'local', at: 1 });+ await local.service.onTurnError('s1', { message: '[REMOTE_AGENT_UNAVAILABLE] gone' }, 1);+ expect(local.probe).not.toHaveBeenCalled();+ expect(local.deps.switchAgentLocation).toHaveBeenCalledTimes(1);++ const limited = onMini();+ await limited.service.onTurnError('s1', { sdkError: 'rate_limit' }, 1, limited.hooks);+ expect(limited.probe).not.toHaveBeenCalled();+ expect(limited.hooks.reconnecting).not.toHaveBeenCalled();+ expect(limited.deps.switchAgentLocation).toHaveBeenCalledTimes(1);+ });++ it('stops waiting once the user takes over: no switch, no continue, no hand back', async () => {+ const h = onMini();+ h.probe.mockResolvedValue('offline');+ h.deps.sleep.mockImplementationOnce(async () => {+ h.service.noteUserAction('s1');+ });+ await h.service.onTurnError('s1', UNREACHABLE, 7, h.hooks);+ expect(h.hooks.reconnecting).toHaveBeenCalledTimes(1);+ expect(h.deps.switchAgentLocation).not.toHaveBeenCalled();+ expect(h.deps.continueSession).not.toHaveBeenCalled();+ expect(h.deps.fallback).not.toHaveBeenCalled();+ expect(h.hooks.beforeFallback).not.toHaveBeenCalled();+ });++ it('counts retries per round, so a computer that keeps dropping cannot hold the task forever', async () => {+ const h = onMini();+ h.probe.mockResolvedValueOnce('offline').mockResolvedValueOnce('offline').mockResolvedValueOnce('ok');+ await h.service.onTurnError('s1', UNREACHABLE, 7, h.hooks);+ // 同一轮里又掉线:接着上次的次数,用完就换。+ h.hooks.reconnecting.mockClear();+ h.probe.mockResolvedValue('offline');+ await h.service.onTurnError('s1', UNREACHABLE, 8, h.hooks);+ expect(h.hooks.reconnecting.mock.calls.map(([attempt]) => attempt)).toEqual([3, 4, 5]);+ expect(h.deps.switchAgentLocation).toHaveBeenCalledTimes(1);+ });++ it('starts counting again after the user takes over', async () => {+ const h = onMini();+ h.probe.mockResolvedValueOnce('offline').mockResolvedValueOnce('offline').mockResolvedValueOnce('ok');+ await h.service.onTurnError('s1', UNREACHABLE, 7, h.hooks);+ h.service.noteUserAction('s1');+ h.hooks.reconnecting.mockClear();+ h.probe.mockResolvedValueOnce('offline').mockResolvedValueOnce('offline').mockResolvedValueOnce('ok');+ await h.service.onTurnError('s1', UNREACHABLE, 8, h.hooks);+ expect(h.hooks.reconnecting.mock.calls.map(([attempt]) => attempt)).toEqual([1, 2]);+ expect(h.deps.switchAgentLocation).not.toHaveBeenCalled();+ });+});+describe('beforeSend', () => {- it('moves a task off a computer that went offline before sending, without an extra continue', async () => {+ it('moves a task off a computer that stays offline before sending, without an extra continue', async () => {const h = harness({ offline: [MINI.key], row: { agentDeviceId: 'mini', providerId: 'anthropic-1a2b3c4d', sdkSessionId: 'native' } });h.bindings.set('s1', { providerId: 'anthropic', memberKey: MINI.key, at: 1 });- await h.service.beforeSend('s1');+ const progress = vi.fn();+ await h.service.beforeSend('s1', { progress });+ // 先等它恢复:重试用完才换,换之前告诉调用方。+ expect(progress.mock.calls.map(([state]) => state)).toEqual([+ ...Array.from({ length: PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS }, (_, i) => ({+ attempt: i + 1,+ maxAttempts: PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS,+ })),+ 'switching',+ ]);expect(h.deps.switchAgentLocation).toHaveBeenCalledWith('s1',{ agentKind: 'claude-code', model: MODEL, providerId: 'anthropic', agentDeviceId: null },@@ -564,6 +729,87 @@ describe('beforeSend', () => {expect(h.deps.continueSession).not.toHaveBeenCalled();});+ it('waits for an offline computer before sending and sends there once it is back', async () => {+ const h = harness({ offline: [MINI.key], row: { agentDeviceId: 'mini', providerId: MINI.providerId, sdkSessionId: 'native' } });+ h.bindings.set('s1', { providerId: 'anthropic', memberKey: MINI.key, at: 1 });+ // 现读一次仍离线 → 第 1 次重试后仍离线 → 第 2 次重试后恢复。+ h.probe.mockResolvedValueOnce('offline').mockResolvedValueOnce('offline').mockResolvedValueOnce('ok');+ const progress = vi.fn();+ await h.service.beforeSend('s1', { progress });+ expect(progress.mock.calls).toEqual([+ [{ attempt: 1, maxAttempts: PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS }],+ [{ attempt: 2, maxAttempts: PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS }],+ ]);+ expect(h.deps.switchAgentLocation).not.toHaveBeenCalled();+ expect(h.bindings.get('s1')?.memberKey).toBe(MINI.key);+ });++ it('sends right away when a computer shown as offline has already come back', async () => {+ const h = harness({ offline: [MINI.key], row: { agentDeviceId: 'mini', providerId: MINI.providerId, sdkSessionId: 'native' } });+ h.bindings.set('s1', { providerId: 'anthropic', memberKey: MINI.key, at: 1 });+ h.probe.mockResolvedValue('ok');+ const progress = vi.fn();+ await h.service.beforeSend('s1', { progress });+ expect(h.probe).toHaveBeenCalledTimes(1);+ expect(progress).not.toHaveBeenCalled();+ expect(h.deps.switchAgentLocation).not.toHaveBeenCalled();+ });++ it('checks the computer freshly when the send has to reopen the session there', async () => {+ const options = { members: [MINI, LOCAL], row: { agentDeviceId: 'mini', providerId: MINI.providerId, sdkSessionId: 'native' } };+ const reopen = harness(options);+ reopen.bindings.set('s1', { providerId: 'anthropic', memberKey: MINI.key, at: 1 });+ reopen.deps.hasLiveSession.mockReturnValue(false);+ reopen.probe.mockResolvedValue('offline');+ await reopen.service.beforeSend('s1');+ expect(reopen.probe).toHaveBeenCalledWith('mini', MINI.providerId);+ expect(reopen.deps.switchAgentLocation).toHaveBeenCalledWith(+ 's1',+ expect.objectContaining({ agentDeviceId: null }),+ { beforeSend: true },+ );++ // 会话还开着:信缓存的状态,不现读。+ const live = harness(options);+ live.bindings.set('s1', { providerId: 'anthropic', memberKey: MINI.key, at: 1 });+ await live.service.beforeSend('s1');+ expect(live.probe).not.toHaveBeenCalled();+ expect(live.deps.switchAgentLocation).not.toHaveBeenCalled();+ });++ it('stops waiting without moving the task when the send is stopped', async () => {+ const h = harness({ offline: [MINI.key], members: [MINI, LOCAL], row: { agentDeviceId: 'mini', providerId: MINI.providerId } });+ h.bindings.set('s1', { providerId: 'anthropic', memberKey: MINI.key, at: 1 });+ const controller = new AbortController();+ h.deps.sleep.mockImplementationOnce(async () => {+ controller.abort();+ });+ const progress = vi.fn();+ await h.service.beforeSend('s1', { signal: controller.signal, progress });+ expect(progress).toHaveBeenCalledTimes(1);+ expect(progress).not.toHaveBeenCalledWith('switching');+ expect(h.deps.switchAgentLocation).not.toHaveBeenCalled();+ expect(h.bindings.get('s1')?.memberKey).toBe(MINI.key);+ });++ it('stops at once when the send is stopped in the middle of a backoff wait', async () => {+ const h = harness({ offline: [MINI.key], members: [MINI, LOCAL], row: { agentDeviceId: 'mini', providerId: MINI.providerId } });+ h.bindings.set('s1', { providerId: 'anthropic', memberKey: MINI.key, at: 1 });+ const controller = new AbortController();+ // 退避等很久(不结束):停止要立刻生效,不等到这次退避结束。+ h.deps.sleep.mockImplementation(() => new Promise<void>(() => undefined));+ const done = vi.fn();+ void h.service.beforeSend('s1', { signal: controller.signal }).then(done);+ await flush();+ expect(h.deps.sleep).toHaveBeenCalledTimes(1);+ expect(done).not.toHaveBeenCalled();+ controller.abort();+ await flush();+ expect(done).toHaveBeenCalledTimes(1);+ expect(h.probe).toHaveBeenCalledTimes(1);+ expect(h.deps.switchAgentLocation).not.toHaveBeenCalled();+ });+it('moves a task off a computer that is cooling down', async () => {const h = harness({ row: { sdkSessionId: 'native' } });h.bindings.set('s1', { providerId: 'anthropic', memberKey: 'local', at: 1 });diff --git a/apps/desktop/src/main/provider-group/__tests__/switchCause.test.ts b/apps/desktop/src/main/provider-group/__tests__/switchCause.test.tsindex fbdff64cf1..efdd448588 100644--- a/apps/desktop/src/main/provider-group/__tests__/switchCause.test.ts+++ b/apps/desktop/src/main/provider-group/__tests__/switchCause.test.ts@@ -3,7 +3,7 @@*/import { describe, expect, it } from 'vitest';-import { classifyProviderGroupSwitchCause } from '../switchCause';+import { classifyProviderGroupSwitchCause, isProviderGroupConnectionLoss } from '../switchCause';describe('classifyProviderGroupSwitchCause', () => {it('switches on usage limits, quota and billing depletion', () => {@@ -35,3 +35,20 @@ describe('classifyProviderGroupSwitchCause', () => {expect(classifyProviderGroupSwitchCause(undefined)).toBeNull();});});++describe('isProviderGroupConnectionLoss', () => {+ it('recognises failures that only say the connection to that computer dropped', () => {+ expect(isProviderGroupConnectionLoss({ reason: 'remote_agent_closed' })).toBe(true);+ expect(isProviderGroupConnectionLoss({ message: '[REMOTE_AGENT_DEVICE_UNREACHABLE] unreachable' })).toBe(true);+ expect(isProviderGroupConnectionLoss({ message: '[REMOTE_AGENT_EXPIRED] session expired' })).toBe(true);+ expect(isProviderGroupConnectionLoss({ message: '[REMOTE_AGENT_NOT_FOUND] no such session' })).toBe(true);+ });++ it('does not treat a reachable computer that refuses or cannot run the task as a dropped connection', () => {+ expect(isProviderGroupConnectionLoss({ message: '[REMOTE_AGENT_UNAVAILABLE] the agent could not start' })).toBe(false);+ expect(isProviderGroupConnectionLoss({ message: '[REMOTE_AGENT_PROVIDER_NOT_ALLOWED] not allowed' })).toBe(false);+ expect(isProviderGroupConnectionLoss({ message: '[REMOTE_AGENT_SHARE_PAUSED] paused' })).toBe(false);+ expect(isProviderGroupConnectionLoss({ sdkError: 'rate_limit' })).toBe(false);+ expect(isProviderGroupConnectionLoss(undefined)).toBe(false);+ });+});diff --git a/apps/desktop/src/main/provider-group/directory.ts b/apps/desktop/src/main/provider-group/directory.tsindex 951538526e..c00839dfac 100644--- a/apps/desktop/src/main/provider-group/directory.ts+++ b/apps/desktop/src/main/provider-group/directory.ts@@ -66,6 +66,11 @@ export interface ProviderGroupDirectory {listCandidates(providerId: string, config: ProviderGroupConfig | null): Promise<ProviderGroupCandidate[]>;/** 那台电脑允许被远程调用的供应商(与组内电脑状态共用同一份短时缓存);读不到时抛错。 */readDeviceCatalog(agentDeviceId: string): Promise<ProviderView[]>;+ /**+ * 本机现在连不连得上那台电脑上的这个供应商:不用缓存,现读设备列表与那台的目录(同账号电脑、分享来的电脑;+ * `agentDeviceId` 用任务记录里的写法)。自动换电脑前等那台恢复时用。+ */+ probe(agentDeviceId: string, providerId: string): Promise<ResolvedMemberState>;/*** 组员给人看的名字(换电脑的活动记录用):分享来的电脑只用分享者的昵称,不用电脑名* (provider-sharing.md §6),读不到这条分享时为空;其余沿用加入时的快照。@@ -139,7 +144,11 @@ export function createProviderGroupDirectory(deps: ProviderGroupDirectoryDeps):return reportedRunning === null ? resolved : { ...resolved, reportedRunning };}- async function resolveShare(member: ProviderGroupMember): Promise<ResolvedProviderGroupMember> {+ async function resolveShare(+ member: ProviderGroupMember,+ /** 不信分享列表里定时刷新的 hostOnline 快照,照样去读那台的目录(等它恢复时用)。 */+ options?: { readThroughOffline?: boolean },+ ): Promise<ResolvedProviderGroupMember> {const agentDeviceId = member.agentDeviceId!;const shareId = agentDeviceId.slice(PROVIDER_SHARE_AGENT_DEVICE_PREFIX.length);const share = deps.listReceivedShares().find((s) => s.shareId === shareId);@@ -149,7 +158,7 @@ export function createProviderGroupDirectory(deps: ProviderGroupDirectoryDeps):const ownerName = share.owner.displayName;const label = ownerName;if (share.status === 'paused') return { member, label, ownerName, state: 'unavailable', reason: 'share-paused' };- if (!share.hostOnline) return { member, label, ownerName, state: 'offline' };+ if (!share.hostOnline && !options?.readThroughOffline) return { member, label, ownerName, state: 'offline' };let views: ProviderView[];try {views = await readCatalog(agentDeviceId);@@ -241,6 +250,28 @@ export function createProviderGroupDirectory(deps: ProviderGroupDirectoryDeps):readDeviceCatalog: readCatalog,+ async probe(agentDeviceId, providerId) {+ catalogs.delete(agentDeviceId);+ const share = isProviderShareAgentDeviceId(agentDeviceId);+ const member: ProviderGroupMember = {+ key: providerGroupMemberKey(agentDeviceId, providerId),+ kind: share ? 'share' : 'device',+ agentDeviceId,+ providerId,+ limit: 1,+ weight: 1,+ paused: false,+ };+ // 分享来的电脑:hostOnline 是定时刷新的快照,等它恢复时不只看它,直接读那台的目录。+ if (share) return (await resolveShare(member, { readThroughOffline: true })).state;+ devices = null;+ const deviceList = await readDevices().catch(() => null);+ const device = deviceList?.find((d) => d.deviceId === agentDeviceId);+ // 在线却关了远程控制或远程调用:是有意的设置,不是断线,不用等它恢复。+ if (device?.online && !isControllable(device)) return 'unavailable';+ return (await resolveDevice(member, deviceList)).state;+ },+memberLabel(member) {if (member.kind !== 'share') return member.label ?? member.key;const shareId = member.agentDeviceId?.slice(PROVIDER_SHARE_AGENT_DEVICE_PREFIX.length) ?? '';diff --git a/apps/desktop/src/main/provider-group/runtime.ts b/apps/desktop/src/main/provider-group/runtime.tsindex 537829368e..29219c53ba 100644--- a/apps/desktop/src/main/provider-group/runtime.ts+++ b/apps/desktop/src/main/provider-group/runtime.ts@@ -66,6 +66,7 @@ const directoryFacade: ProviderGroupDirectory = {resolveMembers: (providerId, config) => runtimeForActiveOwner().directory.resolveMembers(providerId, config),listCandidates: (providerId, config) => runtimeForActiveOwner().directory.listCandidates(providerId, config),readDeviceCatalog: (agentDeviceId) => runtimeForActiveOwner().directory.readDeviceCatalog(agentDeviceId),+ probe: (agentDeviceId, providerId) => runtimeForActiveOwner().directory.probe(agentDeviceId, providerId),memberLabel: (member) => runtimeForActiveOwner().directory.memberLabel(member),invalidate: (agentDeviceId) => runtimeForActiveOwner().directory.invalidate(agentDeviceId),};diff --git a/apps/desktop/src/main/provider-group/service.ts b/apps/desktop/src/main/provider-group/service.tsindex 756b500b48..0d875a90e2 100644--- a/apps/desktop/src/main/provider-group/service.ts+++ b/apps/desktop/src/main/provider-group/service.ts@@ -4,8 +4,10 @@* 1. **分配**:新任务第一次启动 Agent 前(bootstrapSession),按组策略选一台组内电脑,把选择写回* 任务记录与绑定;Agent 还没开始运行就失败(连不上、登录失效、启动失败)时直接换下一台。* 2. **自动换电脑**:运行中因那台电脑的原因失败(终态错误)时,交接到组里下一台并继续这一轮;- * 同一轮每台最多试一次,全部失败才交回原有的报错 / 等额度重置流程。- * 3. **发送前**:已归组的任务所在那台现在不能用时,先交接到下一台,这条消息直接发到新电脑。+ * 同一轮每台最多试一次,全部失败才交回原有的报错 / 等额度重置流程。那台是连不上(离线、断线)时先等它+ * 恢复:按退避最多重试 5 次,恢复了就留在原电脑继续,都不行再换。别的电脑上的组读不到(常见是任务就在组所在+ * 电脑上、它自己断了)时换不了电脑,只等任务所在那台恢复。+ * 3. **发送前**:已归组的任务所在那台现在不能用时,先交接到下一台,这条消息直接发到新电脑;离线时同样先等。** 没归过组、但正用着组那一项的老任务(建组前就在用,或运行过之后才换到组那一项)在启动 Agent 前纳入组,* 不挪动它;当时没纳入的(一直开着、或启动时问不到组所在电脑)出错时再补上,然后照常换电脑。@@ -32,16 +34,24 @@ import type {} from '../../shared/providerGroup.js';import { providerGroupMemberKey } from '../../shared/providerGroup.js';import { isProviderShareAgentDeviceId } from '../../shared/providerShare.js';-import type { InterruptedTurnErrorSignals } from '../maker-ipc/interruptedTurnAutoResume.js';+import {+ interruptedTurnResumeDelayMs,+ type InterruptedTurnErrorSignals,+} from '../maker-ipc/interruptedTurnAutoResume.js';import type { ProviderGroupBinding, ProviderGroupRef } from './bindings.js';import type { ProviderGroupDirectory } from './directory.js';import type { ProviderGroupGuestSwitch } from './guestSwitch.js';import {PROVIDER_GROUP_DEFAULT_COOLDOWN_MS,PROVIDER_GROUP_FAILURE_COOLDOWN_MS,+ PROVIDER_GROUP_TURN_WINDOW_MS,type ProviderGroupRouter,} from './router.js';-import { classifyProviderGroupSwitchCause, type ProviderGroupSwitchCause } from './switchCause.js';+import {+ classifyProviderGroupSwitchCause,+ isProviderGroupConnectionLoss,+ type ProviderGroupSwitchCause,+} from './switchCause.js';/** 换电脑途中用户已接手:交接在改动之前停下(不是目标电脑的问题)。 */export const PROVIDER_GROUP_SUPERSEDED_ERROR = 'provider group: superseded by user action';@@ -169,6 +179,11 @@ export interface ProviderGroupServiceDeps {guestSwitch?: Pick<ProviderGroupGuestSwitch, 'hasOffer' | 'claim' | 'release' | 'drop'>;/** 这个任务现在是否正在运行一轮。 */isTurnRunning(sessionId: string): boolean;+ /**+ * 这个任务现在有没有开着、能直接发的会话;false = 这次发送要重新打开 Agent 所在电脑上的会话。+ * 不提供 = 不知道(发送前只看缓存的组内电脑状态)。+ */+ hasLiveSession?(sessionId: string): boolean;continueSession(sessionId: string,token: number,@@ -179,6 +194,8 @@ export interface ProviderGroupServiceDeps {/** 报错里的重置时刻(unix ms)。 */readResetAt(signals: InterruptedTurnErrorSignals): number | null;now(): number;+ /** 等原电脑恢复时两次重试之间的等待;不提供用定时器。 */+ sleep?(ms: number): Promise<void>;log: Logger;}@@ -213,24 +230,45 @@ export interface ProviderGroupService {): Promise<void>;/*** 发送前:已归组的任务所在那台现在不能用(离线、分享暂停、供应商关掉、冷却中)时,先交接到组里下一台,- * 这条消息直接发到新电脑。读不到状态或没有下一台时不动,照常发送。+ * 这条消息直接发到新电脑。离线时先等它恢复(与运行中失败同一套重试),恢复了照常发到原电脑。+ * 读不到状态或没有下一台时不动,照常发送。*/- beforeSend(sessionId: string): Promise<void>;+ beforeSend(sessionId: string, options?: ProviderGroupBeforeSendOptions): Promise<void>;/** 用户亲自接手:这一轮重新从头试。 */noteUserAction(sessionId: string): void;}+export interface ProviderGroupBeforeSendOptions {+ /** 这次发送被停止或取消:等原电脑恢复时就此停下,不再换电脑。 */+ signal?: AbortSignal;+ /** 等原电脑恢复的进度(第几次重试);`switching` = 没等到,开始换电脑。 */+ progress?(state: { attempt: number; maxAttempts: number } | 'switching'): void;+}+/** 一次终态错误的处理结局(调用方据此结算换电脑期间先不呈现的那次错误)。 */export interface ProviderGroupTurnErrorHooks {/** 不换了,马上交回原有处理(报错与额度重置后自动继续):先把错误放出来。 */beforeFallback?(): void;- /** 已换到另一台电脑并续上了这一轮。 */+ /** 已换到另一台电脑(或原电脑恢复后在原电脑)续上了这一轮。 */resumed?(): void;+ /** 原电脑连不上,先等它恢复:开始第 attempt 次重试(从 1 起)。 */+ reconnecting?(attempt: number, maxAttempts: number): void;+ /** 等过原电脑但没等到,开始换电脑。 */+ switching?(): void;}/** 发送前检查组内电脑状态的上限:读不到就照常发送,不让一台卡住的电脑拖慢每次发送。 */export const PROVIDER_GROUP_BEFORE_SEND_TIMEOUT_MS = 3_000;+/**+ * 那台连不上时,换电脑前先等它恢复:同一轮每台最多重试几次。两次之间的等待与中断自愈相同+ * (约 3、6、12、20、20 秒,合计约一分钟)。+ */+export const PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS = 5;++/** 现读那台状态的上限:读不到按连不上算。 */+export const PROVIDER_GROUP_PROBE_TIMEOUT_MS = 10_000;+/** 纳入老任务时问组所在电脑的上限:读不到就照常启动 / 交回原有处理,出错时再补。 */export const PROVIDER_GROUP_ADOPT_TIMEOUT_MS = 3_000;@@ -277,10 +315,139 @@ interface GroupSource {routeOf(member: ProviderGroupMember, localProviderId: string | null): ProviderGroupRoute;}+/**+ * 等原电脑恢复的结局:`reachable` 现读一次就连得上(不是连不上的问题,没等);`back` 等过之后恢复了;+ * `gone` 那台本身不能用了(供应商关掉、登录失效、分享暂停等)或重试用完;`stopped` 等的途中用户接手。+ */+type ReturnOutcome = 'reachable' | 'back' | 'gone' | 'stopped';+export function createProviderGroupService(deps: ProviderGroupServiceDeps): ProviderGroupService {const { router } = deps;/** 进行中的自动换电脑:用户亲自接手(发消息、重试、换模型)时标记作废。只在换电脑期间登记。 */const runningSwitches = new Map<string, Set<{ superseded: boolean }>>();+ /**+ * 这一轮等过原电脑几次:每台各算,运行中失败与发送前共用一份,那台反复掉线也不会无休止地等下去。+ * 用户接手即重新计;距上一次重试超过一轮的时限(30 分钟)也重新计。+ */+ const reconnects = new Map<string, { memberKey: string; used: number; at: number }>();+ const sleep = deps.sleep ?? ((ms: number) => new Promise<void>((resolve) => setTimeout(resolve, ms)));++ /** 等 `promise`,但发送被停止时立刻返回 undefined(不再干等退避或一次慢的现读)。 */+ function untilAborted<T>(promise: Promise<T>, signal: AbortSignal | undefined): Promise<T | undefined> {+ if (!signal) return promise;+ if (signal.aborted) return Promise.resolve(undefined);+ return new Promise<T | undefined>((resolve, reject) => {+ const onAbort = () => resolve(undefined);+ signal.addEventListener('abort', onAbort, { once: true });+ promise.then(+ (value) => {+ signal.removeEventListener('abort', onAbort);+ resolve(value);+ },+ (error: unknown) => {+ signal.removeEventListener('abort', onAbort);+ reject(error);+ },+ );+ });+ }++ /** 记一次等原电脑的重试,返回这是第几次;这一轮已用完返回 null。 */+ function nextReconnectAttempt(sessionId: string, memberKey: string): number | null {+ const now = deps.now();+ const previous = reconnects.get(sessionId);+ const used = previous && previous.memberKey === memberKey && now - previous.at <= PROVIDER_GROUP_TURN_WINDOW_MS+ ? previous.used+ : 0;+ if (used >= PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS) return null;+ reconnects.set(sessionId, { memberKey, used: used + 1, at: now });+ return used + 1;+ }++ /**+ * 那台连不上(离线、断线)时先等它恢复,不急着换电脑(§6.1):现读一次,确实连不上才等;按退避最多重试 5 次,+ * 每次现读那台的状态。本机这台没有「连不上」,直接 `gone`。`onAttempt` 在每次重试开始等之前调用。+ */+ async function awaitReturn(+ sessionId: string,+ route: ProviderGroupRoute,+ memberKey: string,+ isCurrent: () => boolean,+ onAttempt?: (attempt: number) => void,+ options?: {+ /** 调用方刚现读过、确认连不上,不再读第一次。 */+ knownOffline?: boolean;+ /**+ * 这次失败只是连接断了:现读第一次就已连得上,也算一次重试、留在原电脑继续(断线刚好已恢复),+ * 不当成「问题不在连接」直接换。次数照算,那台反复断也只这 5 次。+ */+ connectionLost?: boolean;+ /** 发送被停止:退避与现读都立刻停下。 */+ signal?: AbortSignal;+ },+ ): Promise<ReturnOutcome> {+ const { agentDeviceId, providerId } = route;+ if (!agentDeviceId || !providerId) return 'gone';+ const signal = options?.signal;+ const current = () => isCurrent() && signal?.aborted !== true;+ const probe = async () =>+ (await untilAborted(+ withTimeout(deps.directory.probe(agentDeviceId, providerId), PROVIDER_GROUP_PROBE_TIMEOUT_MS),+ signal,+ )) ?? 'offline';+ if (!options?.knownOffline) {+ const first = await probe();+ if (!current()) return 'stopped';+ if (first === 'unavailable') return 'gone';+ if (first === 'ok') {+ if (!options?.connectionLost) return 'reachable';+ const attempt = nextReconnectAttempt(sessionId, memberKey);+ if (attempt === null) return 'gone';+ onAttempt?.(attempt);+ deps.log.info('provider group: the connection is already back', { sessionId, member: memberKey, attempt });+ return 'back';+ }+ }+ for (;;) {+ if (!current()) return 'stopped';+ const attempt = nextReconnectAttempt(sessionId, memberKey);+ if (attempt === null) {+ deps.log.info('provider group: the computer did not come back; switching', { sessionId, member: memberKey });+ return 'gone';+ }+ onAttempt?.(attempt);+ await untilAborted(sleep(interruptedTurnResumeDelayMs(attempt)), signal);+ if (!current()) return 'stopped';+ const state = await probe();+ if (!current()) return 'stopped';+ if (state === 'ok') {+ deps.log.info('provider group: the computer came back', { sessionId, member: memberKey, attempt });+ return 'back';+ }+ if (state === 'unavailable') return 'gone';+ }+ }++ /** 这一轮结束(放弃换电脑、用户接手):下一轮重新从头试、重新等。 */+ function resetRound(sessionId: string): void {+ router.resetTurn(sessionId);+ reconnects.delete(sessionId);+ }++ /** 登记一段进行中的自动处理:用户亲自接手(发消息、重试、换模型)时 `superseded` 被置为 true。 */+ function trackRun(sessionId: string): { run: { superseded: boolean }; done(): void } {+ const run = { superseded: false };+ const runs = runningSwitches.get(sessionId) ?? new Set();+ runs.add(run);+ runningSwitches.set(sessionId, runs);+ return {+ run,+ done() {+ runs.delete(run);+ if (runs.size === 0 && runningSwitches.get(sessionId) === runs) runningSwitches.delete(sessionId);+ },+ };+ }function coolUntil(cause: ProviderGroupSwitchCause, resetAt: number | null): number {const now = deps.now();@@ -576,10 +743,7 @@ export function createProviderGroupService(deps: ProviderGroupServiceDeps): Provhooks: ProviderGroupTurnErrorHooks | undefined,body: (isCurrent: () => boolean, handBack: () => void) => Promise<void>,): Promise<void> {- const run = { superseded: false };- const runs = runningSwitches.get(sessionId) ?? new Set();- runs.add(run);- runningSwitches.set(sessionId, runs);+ const { run, done } = trackRun(sessionId);const isCurrent = () => !run.superseded && deps.isLeaseCurrent(sessionId, lease);const handBack = () => {if (!isCurrent()) return;@@ -593,8 +757,7 @@ export function createProviderGroupService(deps: ProviderGroupServiceDeps): Provdeps.log.warn('provider group: automatic switch failed', { sessionId, error: errorText(error) });handBack();} finally {- runs.delete(run);- if (runs.size === 0 && runningSwitches.get(sessionId) === runs) runningSwitches.delete(sessionId);+ done();}}@@ -611,7 +774,7 @@ export function createProviderGroupService(deps: ProviderGroupServiceDeps): Provreturn guestFailover(sessionId, signals, token, cause, hooks);}const bound = await loadBound(sessionId);- if (!bound) return false;+ if (!bound) return cause === 'unavailable' ? reconnectWithoutGroup(sessionId, signals, token, hooks) : false;const { binding, source, config } = bound;if (!config) {await releaseDeletedGroup(sessionId, groupOf(source, binding.providerId));@@ -627,12 +790,127 @@ export function createProviderGroupService(deps: ProviderGroupServiceDeps): Provconst lease = deps.leaseRecovery(sessionId, token);if (!lease) return true;const boundRow = { ...row, model: row.model };- await withSwitchRun(sessionId, signals, token, lease, hooks, (isCurrent, handBack) => switchUntilSettled({- sessionId, signals, cause, binding, source, config, row: boundRow, current, lease, isCurrent, handBack, hooks,- }));+ await withSwitchRun(sessionId, signals, token, lease, hooks, async (isCurrent, handBack) => {+ // 连不上先等那台恢复:恢复了留在原电脑继续这一轮(不交接),等不到再换。+ if (cause === 'unavailable') {+ let waited = false;+ const route = source.routeOf(current, row.providerId);+ const outcome = await awaitReturn(sessionId, route, current.key, isCurrent, (attempt) => {+ waited = true;+ hooks?.reconnecting?.(attempt, PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS);+ }, { connectionLost: isProviderGroupConnectionLoss(signals) });+ if (outcome === 'stopped') return;+ if (outcome === 'back') {+ await continueOnSameComputer(sessionId, deps.directory.memberLabel(current), lease, isCurrent, hooks);+ return;+ }+ if (waited) hooks?.switching?.();+ }+ await switchUntilSettled({+ sessionId, signals, cause, binding, source, config, row: boundRow, current, lease, isCurrent, handBack, hooks,+ });+ });return true;}+ /**+ * 原电脑等回来了:留在原电脑继续这一轮,不交接;活动记录写「已重新连上 {电脑},继续运行」(`computer` 为空时写+ * 「原来的电脑」)。+ */+ async function continueOnSameComputer(+ sessionId: string,+ computer: string,+ lease: object,+ isCurrent: () => boolean,+ hooks: ProviderGroupTurnErrorHooks | undefined,+ ): Promise<void> {+ if (!isCurrent()) return;+ const continueToken = deps.rearmContinue(sessionId, lease, deps.now());+ if (continueToken === null) return;+ const outcome = await deps.continueSession(sessionId, continueToken, {+ reason: USAGE_LIMIT_RESET_AUTO_RESUME_REASON,+ attempt: 1,+ maxAttempts: 1,+ sessionTotal: 0,+ agentReconnect: { computer },+ });+ if (outcome === 'resumed') hooks?.resumed?.();+ else deps.cancelContinue(sessionId, continueToken);+ }++ /**+ * 别的电脑上的组读不到(常见是任务就跑在组所在电脑上、它自己断了):换不了电脑,但仍先等任务所在那台恢复(§6.1)。+ * 恢复了在原电脑继续,等不到交回原有处理。位置取任务记录里的写法,不需要组设置。+ */+ async function reconnectWithoutGroup(+ sessionId: string,+ signals: InterruptedTurnErrorSignals,+ token: number,+ hooks: ProviderGroupTurnErrorHooks | undefined,+ ): Promise<boolean> {+ const binding = deps.readBinding(sessionId);+ if (!binding?.groupDeviceId || !deps.remote) return false;+ if (!(await deps.isFailoverEligible(sessionId))) return false;+ const row = await deps.readSessionRow(sessionId);+ if (!row?.model || row.remoteHostId || !row.agentDeviceId || !row.providerId) return false;+ const route = { agentDeviceId: row.agentDeviceId, providerId: row.providerId };+ const lease = deps.leaseRecovery(sessionId, token);+ if (!lease) return true;+ await withSwitchRun(sessionId, signals, token, lease, hooks, async (isCurrent, handBack) => {+ const outcome = await awaitReturn(sessionId, route, binding.memberKey, isCurrent, (attempt) => {+ hooks?.reconnecting?.(attempt, PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS);+ }, { connectionLost: isProviderGroupConnectionLoss(signals) });+ if (outcome === 'stopped') return;+ if (outcome === 'back') {+ await continueOnSameComputer(sessionId, '', lease, isCurrent, hooks);+ return;+ }+ deps.log.info('provider group: the group computer cannot be read; handing back', { sessionId });+ handBack();+ });+ return true;+ }++ /** 发送前等那台恢复(这条还没派出去):进度交给调用方显示;发送被停止或用户接手时停下。 */+ async function waitBeforeSend(+ sessionId: string,+ route: ProviderGroupRoute,+ memberKey: string,+ knownOffline: boolean,+ options: ProviderGroupBeforeSendOptions | undefined,+ ): Promise<ReturnOutcome> {+ const { run, done } = trackRun(sessionId);+ try {+ return await awaitReturn(sessionId, route, memberKey, () => !run.superseded, (attempt) => {+ options?.progress?.({ attempt, maxAttempts: PROVIDER_GROUP_RECONNECT_MAX_ATTEMPTS });+ }, { knownOffline, ...(options?.signal ? { signal: options.signal } : {}) });+ } finally {+ done();+ }+ }++ /**+ * 发送前读不到别的电脑上的组:换不了电脑,但这次要重新打开任务所在那台上的会话时,仍现读那台,离线先等它恢复,+ * 免得一打开就报错。位置取任务记录里的写法。+ */+ async function waitBeforeSendWithoutGroup(+ sessionId: string,+ options: ProviderGroupBeforeSendOptions | undefined,+ ): Promise<void> {+ const binding = deps.readBinding(sessionId);+ if (!binding?.groupDeviceId || !deps.remote || deps.hasLiveSession?.(sessionId) !== false) return;+ if (!(await deps.isFailoverEligible(sessionId))) return;+ const row = await deps.readSessionRow(sessionId).catch(() => null);+ if (!row?.agentDeviceId || !row.providerId || row.remoteHostId) return;+ await waitBeforeSend(+ sessionId,+ { agentDeviceId: row.agentDeviceId, providerId: row.providerId },+ binding.memberKey,+ false,+ options,+ );+ }+/*** 分享的人这边(§6.1):任务用的是分享来的供应商,分享者把它建成了组,实际运行的电脑由组所在电脑选,本机不知道* 是哪台。那台因电脑本身的原因失败时,组所在电脑先发来「需要换一台」凭证;本机交接(新建会话并带上交接上下文)@@ -728,7 +1006,7 @@ export function createProviderGroupService(deps: ProviderGroupServiceDeps): Provif (!isCurrent()) return;if (pick.kind !== 'member') {deps.log.info('provider group: no computer left to switch to', { sessionId, cause, tried: tried.size });- router.resetTurn(sessionId);+ resetRound(sessionId);handBack();return;}@@ -915,7 +1193,7 @@ export function createProviderGroupService(deps: ProviderGroupServiceDeps): Provexclude: tried,});if (pick.kind !== 'member') {- router.resetTurn(context.sessionId);+ resetRound(context.sessionId);return null;}const route = source.routeOf(pick.member, context.localProviderId);@@ -954,11 +1232,14 @@ export function createProviderGroupService(deps: ProviderGroupServiceDeps): Provdeps.fallback(sessionId, signals, token);},- async beforeSend(sessionId) {+ async beforeSend(sessionId, options) {if (!deps.readBinding(sessionId) || deps.isTurnRunning(sessionId)) return;// 读组设置也算进发送前检查的上限:组所在电脑断线或不响应时保留绑定、照常发送,不等默认的请求超时。const bound = await withTimeout(loadBound(sessionId), PROVIDER_GROUP_BEFORE_SEND_TIMEOUT_MS);- if (!bound) return;+ if (!bound) {+ await waitBeforeSendWithoutGroup(sessionId, options);+ return;+ }const { binding, source, config } = bound;if (!config) {await releaseDeletedGroup(sessionId, groupOf(source, binding.providerId));@@ -971,8 +1252,30 @@ export function createProviderGroupService(deps: ProviderGroupServiceDeps): Provconst current = await verifyBinding(sessionId, source, binding, config, row);// 暂停分配只影响新任务,已在那台的任务不挪走。if (!current || current.paused) return;- const verdict = await source.shouldMoveAway(binding.providerId, config, current.key);- if (!verdict) return;+ const cached = await source.shouldMoveAway(binding.providerId, config, current.key);+ if (cached === null) return;+ let reason = cached ? cached.reason : null;+ const currentRoute = source.routeOf(current, row.providerId);+ const { agentDeviceId, providerId } = currentRoute;+ // 离线的先现读一次(状态可能刚恢复);看着能用、但这次要重新打开那台电脑上的会话时也不信缓存,现读一次:+ // 连不上的话要到打开会话时才报错。+ const checkFresh = Boolean(agentDeviceId && providerId)+ && (reason === 'offline' || (reason === null && deps.hasLiveSession?.(sessionId) === false));+ if (checkFresh) {+ const fresh = (await untilAborted(+ withTimeout(deps.directory.probe(agentDeviceId!, providerId!), PROVIDER_GROUP_PROBE_TIMEOUT_MS),+ options?.signal,+ )) ?? 'offline';+ if (options?.signal?.aborted) return;+ reason = fresh === 'ok' ? null : fresh;+ }+ if (reason === null) return;+ // 离线先等它恢复(与运行中失败共用这一轮的重试次数):恢复了照常发到原电脑,等不到再换。+ if (reason === 'offline') {+ const outcome = await waitBeforeSend(sessionId, currentRoute, current.key, checkFresh, options);+ if (outcome !== 'gone') return;+ options?.progress?.('switching');+ }const tried = router.markTried(sessionId, current.key);const pick = await source.pick({sessionId,@@ -1000,7 +1303,7 @@ export function createProviderGroupService(deps: ProviderGroupServiceDeps): ProvsessionId,from: current.key,to: pick.member.key,- reason: verdict.reason,+ reason,});} catch (error) {await restoreBindingAfterFailedSwitch(sessionId, source, binding.providerId, config);@@ -1010,7 +1313,7 @@ export function createProviderGroupService(deps: ProviderGroupServiceDeps): ProvnoteUserAction(sessionId) {for (const run of runningSwitches.get(sessionId) ?? []) run.superseded = true;- router.resetTurn(sessionId);+ resetRound(sessionId);deps.guestSwitch?.drop(sessionId);},};diff --git a/apps/desktop/src/main/provider-group/switchCause.ts b/apps/desktop/src/main/provider-group/switchCause.tsindex 636f984f81..5290322d66 100644--- a/apps/desktop/src/main/provider-group/switchCause.ts+++ b/apps/desktop/src/main/provider-group/switchCause.ts@@ -40,3 +40,16 @@ export function classifyProviderGroupSwitchCause(}return null;}++/** 只说明连接断了的远程错误(那台本身没问题,断线、远程 Cindy 重启后会话没了)。 */+const REMOTE_CONNECTION_LOST = /\[REMOTE_AGENT_(?:DEVICE_UNREACHABLE|EXPIRED|NOT_FOUND)\]/;++/**+ * 这次失败只是和那台的连接断了:等它恢复时,现读第一次就已连得上,也算一次重试、留在原电脑继续(断线刚好已恢复),+ * 不急着换电脑。其余「连不上」(远程调用被关、分享暂停、Agent 没能启动等)现读连得上说明问题不在连接,直接换。+ */+export function isProviderGroupConnectionLoss(signals: InterruptedTurnErrorSignals | null | undefined): boolean {+ if (!signals) return false;+ const message = typeof signals.message === 'string' ? signals.message : '';+ return signals.reason === 'remote_agent_closed' || REMOTE_CONNECTION_LOST.test(message);+}diff --git a/apps/desktop/src/renderer/__tests__/autoResumePresentation.test.ts b/apps/desktop/src/renderer/__tests__/autoResumePresentation.test.tsindex 458f209867..3ec33ec94c 100644--- a/apps/desktop/src/renderer/__tests__/autoResumePresentation.test.ts+++ b/apps/desktop/src/renderer/__tests__/autoResumePresentation.test.ts@@ -141,4 +141,13 @@ describe('provider group switch presentation', () => {expect(readAutoResumeInfo({ reason: 'usage-limit-reset', groupSwitch: { cause: 'other' } })).toEqual({ usageLimitReset: true });});++ it('reads a reconnect to the original computer, with or without its name', () => {+ expect(readAutoResumeInfo({ reason: 'usage-limit-reset', agentReconnect: { computer: 'Mac mini' } }))+ .toEqual({ usageLimitReset: true, agentReconnect: { computer: 'Mac mini' } });+ expect(readAutoResumeInfo({ reason: 'usage-limit-reset', agentReconnect: {} }))+ .toEqual({ usageLimitReset: true, agentReconnect: { computer: '' } });+ expect(readAutoResumeInfo({ reason: 'usage-limit-reset', agentReconnect: 'Mac mini' }))+ .toEqual({ usageLimitReset: true });+ });});diff --git a/apps/desktop/src/renderer/__tests__/systemCardAutoResumeRow.test.tsx b/apps/desktop/src/renderer/__tests__/systemCardAutoResumeRow.test.tsxindex 117661c1ac..4d57ef2d81 100644--- a/apps/desktop/src/renderer/__tests__/systemCardAutoResumeRow.test.tsx+++ b/apps/desktop/src/renderer/__tests__/systemCardAutoResumeRow.test.tsx@@ -133,6 +133,32 @@ describe('SystemCard auto-resume 行', () => {expect(screen.queryByText('chat.systemCard.autoResumePending.label')).toBeNull();});+ it('供应商组等回原电脑后在原电脑继续 → 「已重新连上 {电脑},继续运行」,读不到名称时不写电脑名', () => {+ const { unmount } = render(+ <SystemCard+ cardType="auto-resume"+ data={{+ reason: 'usage-limit-reset',+ attempt: 1,+ maxAttempts: 1,+ sessionTotal: 0,+ agentReconnect: { computer: 'Mac mini' },+ }}+ />,+ );+ expect(+ screen.getByText('chat.systemCard.autoResume.agentReconnect.named({"computer":"Mac mini"})'),+ ).toBeTruthy();+ unmount();+ render(+ <SystemCard+ cardType="auto-resume"+ data={{ reason: 'usage-limit-reset', attempt: 1, maxAttempts: 1, sessionTotal: 0, agentReconnect: {} }}+ />,+ );+ expect(screen.getByText('chat.systemCard.autoResume.agentReconnect.unnamed')).toBeTruthy();+ });+it('已回填时 inFlight 不参与:终态优先,仍定格 ✓ / ✗', () => {render(<SystemCarddiff --git a/apps/desktop/src/renderer/components/chat/SystemCard.tsx b/apps/desktop/src/renderer/components/chat/SystemCard.tsxindex 6a9d4234eb..6478617489 100644--- a/apps/desktop/src/renderer/components/chat/SystemCard.tsx+++ b/apps/desktop/src/renderer/components/chat/SystemCard.tsx@@ -970,6 +970,10 @@ function AutoResumeActionRow({from: info.agentSwitch.from,to: info.agentSwitch.to,})+ : info.agentReconnect+ ? info.agentReconnect.computer+ ? t('chat.systemCard.autoResume.agentReconnect.named', { computer: info.agentReconnect.computer })+ : t('chat.systemCard.autoResume.agentReconnect.unnamed'): info.groupSwitch? t('chat.systemCard.autoResume.groupSwitch'): usageLimitResetdiff --git a/apps/desktop/src/renderer/i18n/locales/en/common.json b/apps/desktop/src/renderer/i18n/locales/en/common.jsonindex 0df4766794..e1d431a503 100644--- a/apps/desktop/src/renderer/i18n/locales/en/common.json+++ b/apps/desktop/src/renderer/i18n/locales/en/common.json@@ -10573,6 +10573,10 @@"unavailable": "Couldn’t reach {{from}}; continued on {{to}}","overload": "{{from}} was overloaded; continued on {{to}}"},+ "agentReconnect": {+ "named": "Reconnected to {{computer}}; continued there",+ "unnamed": "Reconnected to the original computer; continued there"+ },"groupSwitch": "Continued on another computer automatically"},"autoResumeSeparator": {diff --git a/apps/desktop/src/renderer/i18n/locales/ja/common.json b/apps/desktop/src/renderer/i18n/locales/ja/common.jsonindex 7abff5a418..2136c8930b 100644--- a/apps/desktop/src/renderer/i18n/locales/ja/common.json+++ b/apps/desktop/src/renderer/i18n/locales/ja/common.json@@ -10550,6 +10550,10 @@"unavailable": "{{from}} に接続できないため、{{to}} で続行しました","overload": "{{from}} のサービスが混雑しているため、{{to}} で続行しました"},+ "agentReconnect": {+ "named": "{{computer}} に再接続し、続行しました",+ "unnamed": "元のパソコンに再接続し、続行しました"+ },"groupSwitch": "別のパソコンに自動で切り替えて続行しました"},"autoResumeSeparator": {diff --git a/apps/desktop/src/renderer/i18n/locales/ko/common.json b/apps/desktop/src/renderer/i18n/locales/ko/common.jsonindex b8cb6106bd..0657a2a895 100644--- a/apps/desktop/src/renderer/i18n/locales/ko/common.json+++ b/apps/desktop/src/renderer/i18n/locales/ko/common.json@@ -10550,6 +10550,10 @@"unavailable": "{{from}}에 연결할 수 없어 {{to}}에서 이어서 진행했습니다","overload": "{{from}}의 서비스가 혼잡해 {{to}}에서 이어서 진행했습니다"},+ "agentReconnect": {+ "named": "{{computer}}에 다시 연결되어 이어서 진행했습니다",+ "unnamed": "원래 컴퓨터에 다시 연결되어 이어서 진행했습니다"+ },"groupSwitch": "다른 컴퓨터로 자동 전환해 이어서 진행했습니다"},"autoResumeSeparator": {diff --git a/apps/desktop/src/renderer/i18n/locales/zh-CN/common.json b/apps/desktop/src/renderer/i18n/locales/zh-CN/common.jsonindex 120d9b891f..35b658ff5c 100644--- a/apps/desktop/src/renderer/i18n/locales/zh-CN/common.json+++ b/apps/desktop/src/renderer/i18n/locales/zh-CN/common.json@@ -10550,6 +10550,10 @@"unavailable": "{{from}} 连不上,已换到 {{to}} 继续","overload": "{{from}} 的服务繁忙,已换到 {{to}} 继续"},+ "agentReconnect": {+ "named": "已重新连上 {{computer}},继续运行",+ "unnamed": "已重新连上原来的电脑,继续运行"+ },"groupSwitch": "已自动换一台电脑继续"},"autoResumeSeparator": {diff --git a/apps/desktop/src/renderer/i18n/locales/zh-TW/common.json b/apps/desktop/src/renderer/i18n/locales/zh-TW/common.jsonindex 97a1505a69..bd41eaf9e9 100644--- a/apps/desktop/src/renderer/i18n/locales/zh-TW/common.json+++ b/apps/desktop/src/renderer/i18n/locales/zh-TW/common.json@@ -10549,6 +10549,10 @@"unavailable": "{{from}} 連不上,已換到 {{to}} 繼續","overload": "{{from}} 的服務繁忙,已換到 {{to}} 繼續"},+ "agentReconnect": {+ "named": "已重新連上 {{computer}},繼續執行",+ "unnamed": "已重新連上原本的電腦,繼續執行"+ },"groupSwitch": "已自動換一台電腦繼續"},"autoResumeSeparator": {diff --git a/apps/desktop/src/renderer/lib/autoResumePresentation.ts b/apps/desktop/src/renderer/lib/autoResumePresentation.tsindex cf69d147db..07521947d3 100644--- a/apps/desktop/src/renderer/lib/autoResumePresentation.ts+++ b/apps/desktop/src/renderer/lib/autoResumePresentation.ts@@ -1,5 +1,6 @@import {USAGE_LIMIT_RESET_AUTO_RESUME_REASON,+ type AutoResumeAgentReconnect,type AutoResumeAgentSwitch,type AutoResumeAgentSwitchCause,type AutoResumeGroupSwitch,@@ -11,6 +12,8 @@ export interface AutoResumeCardInfo {usageLimitReset?: boolean;/** 供应商组自动换电脑后继续(与 usageLimitReset 同时出现)。 */agentSwitch?: AutoResumeAgentSwitch;+ /** 供应商组等原电脑恢复后在原电脑继续(与 usageLimitReset 同时出现)。 */+ agentReconnect?: AutoResumeAgentReconnect;/** 分享者的供应商组替分享的人换了一台电脑后继续(不知道是哪台,不显示电脑名称)。 */groupSwitch?: AutoResumeGroupSwitch;/** 进行中:供应商组正在为这次失败换电脑(错误先不呈现)。 */@@ -40,6 +43,9 @@ export function readAutoResumeInfo(data?: Record<string, unknown>): AutoResumeCareturn {...(data?.reason === USAGE_LIMIT_RESET_AUTO_RESUME_REASON ? { usageLimitReset: true } : {}),...(readAgentSwitch(data?.agentSwitch) ? { agentSwitch: readAgentSwitch(data?.agentSwitch)! } : {}),+ ...(readAgentReconnect(data?.agentReconnect)+ ? { agentReconnect: readAgentReconnect(data?.agentReconnect)! }+ : {}),...(readGroupSwitch(data?.groupSwitch) ? { groupSwitch: readGroupSwitch(data?.groupSwitch)! } : {}),...(readGroupSwitch(data?.groupSwitchPending)? { groupSwitchPending: readGroupSwitch(data?.groupSwitchPending)! }@@ -64,6 +70,12 @@ function readAgentSwitch(value: unknown): AutoResumeAgentSwitch | null {return { from: from.slice(0, 128), to: to.slice(0, 128), cause: cause as AutoResumeAgentSwitchCause };}+function readAgentReconnect(value: unknown): AutoResumeAgentReconnect | null {+ if (!value || typeof value !== 'object') return null;+ const { computer } = value as Record<string, unknown>;+ return { computer: typeof computer === 'string' ? computer.slice(0, 128) : '' };+}+function readGroupSwitch(value: unknown): AutoResumeGroupSwitch | null {if (!value || typeof value !== 'object') return null;const { cause } = value as Record<string, unknown>;diff --git a/apps/desktop/src/shared/agentInputQueue.ts b/apps/desktop/src/shared/agentInputQueue.tsindex 90a501f8a0..868e5cbac1 100644--- a/apps/desktop/src/shared/agentInputQueue.ts+++ b/apps/desktop/src/shared/agentInputQueue.ts@@ -209,6 +209,12 @@ export interface AutoResumeInfo {* 后的续跑同一条路径):活动行据此显示「{from} {原因},已换到 {to} 继续」。旧端忽略该字段。*/agentSwitch?: AutoResumeAgentSwitch;+ /**+ * 供应商组里任务所在的那台连不上,等它恢复后留在原电脑继续(reason 同样为 USAGE_LIMIT_RESET_AUTO_RESUME_REASON):+ * 活动行显示「{computer} 已重新连上,继续运行」,读不到名称时不写电脑名。旧端忽略该字段,显示成「用量已恢复,+ * 已自动继续」(与 agentSwitch 相同)。+ */+ agentReconnect?: AutoResumeAgentReconnect;/*** 分享的人这边的自动换电脑(分享者的供应商组替它换了一台,本机不知道是哪台):活动行显示「已自动换一台* 电脑继续」,不出现电脑名称(docs/product-rules/provider-groups.md §8)。旧端忽略该字段。@@ -236,6 +242,11 @@ export interface AutoResumeAgentSwitch {cause: AutoResumeAgentSwitchCause;}+export interface AutoResumeAgentReconnect {+ /** 重新连上的那台电脑的显示名;读不到时为空。 */+ computer: string;+}+/** 账号额度重置后自动继续时 `AutoResumeInfo.reason` 的取值(活动行据此换文案)。 */export const USAGE_LIMIT_RESET_AUTO_RESUME_REASON = 'usage-limit-reset';diff --git a/apps/mobile/src/__tests__/autoResumePresentation.test.ts b/apps/mobile/src/__tests__/autoResumePresentation.test.tsindex c6835e73fb..a508c13b84 100644--- a/apps/mobile/src/__tests__/autoResumePresentation.test.ts+++ b/apps/mobile/src/__tests__/autoResumePresentation.test.ts@@ -111,4 +111,13 @@ describe('provider group computer switch', () => {expect(readMobileAutoResumeInfo({ reason: 'usage-limit-reset', groupSwitch: {} })).toEqual({ usageLimitReset: true });});++ it('reads a reconnect to the original computer, with or without its name', () => {+ expect(readMobileAutoResumeInfo({ reason: 'usage-limit-reset', agentReconnect: { computer: 'Mac mini' } }))+ .toEqual({ usageLimitReset: true, agentReconnect: { computer: 'Mac mini' } });+ expect(readMobileAutoResumeInfo({ reason: 'usage-limit-reset', agentReconnect: {} }))+ .toEqual({ usageLimitReset: true, agentReconnect: { computer: '' } });+ expect(readMobileAutoResumeInfo({ reason: 'usage-limit-reset', agentReconnect: 'Mac mini' }))+ .toEqual({ usageLimitReset: true });+ });});diff --git a/apps/mobile/src/i18n/locales/en/message.json b/apps/mobile/src/i18n/locales/en/message.jsonindex 91623593c7..0b66fbb3b0 100644--- a/apps/mobile/src/i18n/locales/en/message.json+++ b/apps/mobile/src/i18n/locales/en/message.json@@ -273,6 +273,10 @@"unavailable": "Couldn’t reach {{from}}; continued on {{to}}","overload": "{{from}} was overloaded; continued on {{to}}"},+ "agentReconnect": {+ "named": "Reconnected to {{computer}}; continued there",+ "unnamed": "Reconnected to the original computer; continued there"+ },"groupSwitch": "Continued on another computer automatically"},"modelLabel": "Model",diff --git a/apps/mobile/src/i18n/locales/ja/message.json b/apps/mobile/src/i18n/locales/ja/message.jsonindex fd473b8c29..82cd310872 100644--- a/apps/mobile/src/i18n/locales/ja/message.json+++ b/apps/mobile/src/i18n/locales/ja/message.json@@ -273,6 +273,10 @@"unavailable": "{{from}} に接続できないため、{{to}} で続行しました","overload": "{{from}} のサービスが混雑しているため、{{to}} で続行しました"},+ "agentReconnect": {+ "named": "{{computer}} に再接続し、続行しました",+ "unnamed": "元のパソコンに再接続し、続行しました"+ },"groupSwitch": "別のパソコンに自動で切り替えて続行しました"},"modelLabel": "モデル",diff --git a/apps/mobile/src/i18n/locales/ko/message.json b/apps/mobile/src/i18n/locales/ko/message.jsonindex b70464ce92..2e4e1ab189 100644--- a/apps/mobile/src/i18n/locales/ko/message.json+++ b/apps/mobile/src/i18n/locales/ko/message.json@@ -273,6 +273,10 @@"unavailable": "{{from}}에 연결할 수 없어 {{to}}에서 이어서 진행했습니다","overload": "{{from}}의 서비스가 혼잡해 {{to}}에서 이어서 진행했습니다"},+ "agentReconnect": {+ "named": "{{computer}}에 다시 연결되어 이어서 진행했습니다",+ "unnamed": "원래 컴퓨터에 다시 연결되어 이어서 진행했습니다"+ },"groupSwitch": "다른 컴퓨터로 자동 전환해 이어서 진행했습니다"},"modelLabel": "모델",diff --git a/apps/mobile/src/i18n/locales/zh-CN/message.json b/apps/mobile/src/i18n/locales/zh-CN/message.jsonindex 37389b501e..7d7df206f8 100644--- a/apps/mobile/src/i18n/locales/zh-CN/message.json+++ b/apps/mobile/src/i18n/locales/zh-CN/message.json@@ -273,6 +273,10 @@"unavailable": "{{from}} 连不上,已换到 {{to}} 继续","overload": "{{from}} 的服务繁忙,已换到 {{to}} 继续"},+ "agentReconnect": {+ "named": "已重新连上 {{computer}},继续运行",+ "unnamed": "已重新连上原来的电脑,继续运行"+ },"groupSwitch": "已自动换一台电脑继续"},"modelLabel": "模型",diff --git a/apps/mobile/src/i18n/locales/zh-TW/message.json b/apps/mobile/src/i18n/locales/zh-TW/message.jsonindex 22b93ee13c..1ed97cb059 100644--- a/apps/mobile/src/i18n/locales/zh-TW/message.json+++ b/apps/mobile/src/i18n/locales/zh-TW/message.json@@ -273,6 +273,10 @@"unavailable": "{{from}} 連不上,已換到 {{to}} 繼續","overload": "{{from}} 的服務繁忙,已換到 {{to}} 繼續"},+ "agentReconnect": {+ "named": "已重新連上 {{computer}},繼續執行",+ "unnamed": "已重新連上原本的電腦,繼續執行"+ },"groupSwitch": "已自動換一台電腦繼續"},"modelLabel": "模型",diff --git a/apps/mobile/src/session/MessageRenderer.tsx b/apps/mobile/src/session/MessageRenderer.tsxindex 5de7204565..14f69a5802 100644--- a/apps/mobile/src/session/MessageRenderer.tsx+++ b/apps/mobile/src/session/MessageRenderer.tsx@@ -5330,6 +5330,10 @@ function MobileAutoResumeActionRow({from: info.agentSwitch.from,to: info.agentSwitch.to,})+ : info.agentReconnect+ ? info.agentReconnect.computer+ ? t('message.systemCard.autoResume.agentReconnect.named', { computer: info.agentReconnect.computer })+ : t('message.systemCard.autoResume.agentReconnect.unnamed'): info.groupSwitch? t('message.systemCard.autoResume.groupSwitch'): info.usageLimitResetdiff --git a/apps/mobile/src/session/autoResumePresentation.ts b/apps/mobile/src/session/autoResumePresentation.tsindex 545ea4a485..bcf35aeba3 100644--- a/apps/mobile/src/session/autoResumePresentation.ts+++ b/apps/mobile/src/session/autoResumePresentation.ts@@ -22,6 +22,17 @@ function readAgentSwitch(value: unknown): MobileAutoResumeAgentSwitch | undefinereturn { from: from.slice(0, 128), to: to.slice(0, 128), cause: cause as MobileAutoResumeAgentSwitchCause };}+/** 对齐桌面 AutoResumeAgentReconnect:供应商组等原电脑恢复后在原电脑继续(读不到名称时为空)。 */+export interface MobileAutoResumeAgentReconnect {+ computer: string;+}++function readAgentReconnect(value: unknown): MobileAutoResumeAgentReconnect | undefined {+ if (!value || typeof value !== 'object') return undefined;+ const { computer } = value as Record<string, unknown>;+ return { computer: typeof computer === 'string' ? computer.slice(0, 128) : '' };+}+/** 对齐桌面 AutoResumeGroupSwitch:分享者的供应商组替分享的人换了一台电脑(不显示电脑名称)。 */export interface MobileAutoResumeGroupSwitch {cause: MobileAutoResumeAgentSwitchCause;@@ -39,6 +50,8 @@ export interface MobileAutoResumeInfo {usageLimitReset?: boolean;/** 供应商组自动换电脑后继续(与 usageLimitReset 同时出现)。 */agentSwitch?: MobileAutoResumeAgentSwitch;+ /** 供应商组等原电脑恢复后在原电脑继续(与 usageLimitReset 同时出现)。 */+ agentReconnect?: MobileAutoResumeAgentReconnect;/** 分享的人这边的自动换电脑:活动行写「已自动换一台电脑继续」。 */groupSwitch?: MobileAutoResumeGroupSwitch;/** 进行中:供应商组正在为这次失败换电脑,错误先不呈现,写「正在换一台电脑继续」。 */@@ -68,11 +81,13 @@ export function readMobileAutoResumeInfo(data?: Record<string, unknown>): Mobileconst maxAttempts = usageLimitReset ? undefined : number(data?.maxAttempts);const sessionTotal = usageLimitReset ? undefined : number(data?.sessionTotal);const agentSwitch = readAgentSwitch(data?.agentSwitch);+ const agentReconnect = readAgentReconnect(data?.agentReconnect);const groupSwitch = readGroupSwitch(data?.groupSwitch);const groupSwitchPending = readGroupSwitch(data?.groupSwitchPending);return {...(usageLimitReset ? { usageLimitReset: true } : {}),...(agentSwitch ? { agentSwitch } : {}),+ ...(agentReconnect ? { agentReconnect } : {}),...(groupSwitch ? { groupSwitch } : {}),...(groupSwitchPending ? { groupSwitchPending } : {}),// 正在换电脑时错误先不呈现:行内不带原始错误。diff --git a/docs/dev-rules/protocol-compatibility.md b/docs/dev-rules/protocol-compatibility.mdindex 90eed9a64b..164382988c 100644--- a/docs/dev-rules/protocol-compatibility.md+++ b/docs/dev-rules/protocol-compatibility.md@@ -113,6 +113,12 @@ Claude Code 终态 error 事件可带 `usageResetAt`(unix ms)。服务端无并且不论哪种 Agent 都不再用这次终态 event 点亮横幅。换成了投影直接进入续跑;没换成投影恢复带 `error`。旧客户端忽略该字段,按普通「重新连接中」显示(不带次数);旧 Desktop 控制端对 Claude Code / Pi 仍会被终态 event 短暂点亮横幅,下一份投影即收回。只改投影内容,不新增 invoke 或推送通道,服务端无需改动。+连不上先等它恢复(2026-10-11):等原电脑恢复期间,`autoResumePending` 是一次普通的重连进度(`attempt` 1–5、+`maxAttempts` 5、`sessionTotal` 0,不带 `groupSwitchPending`),新旧端都显示「重新连接中 n/5」;发送前等的时候同样挂在+还没派出的这一轮上(不带 `error`)。开始换电脑时回到上面的 `groupSwitchPending`。恢复后在原电脑续跑,续跑记录的+`autoResumeInfo` 新增可选字段 `agentReconnect: { computer }`(读不到名称时为空串),新 Desktop 与 Mobile 显示+「已重新连上 {电脑},继续运行」;旧客户端忽略该字段,显示「用量已恢复,已自动继续」(与 `agentSwitch` 相同)。+同样只改投影与记录内容,服务端无需改动。## Agent 跨设备历史发现与搜索diff --git a/docs/product-rules/provider-groups.md b/docs/product-rules/provider-groups.mdindex 2dc0719020..6cdb5cd66d 100644--- a/docs/product-rules/provider-groups.md+++ b/docs/product-rules/provider-groups.md@@ -8,6 +8,7 @@> 统计(含自己用的、不经组的与替分享的人跑的),见 §5。> 2026-10-10 用户确认:**换电脑期间不报错**——组里还能换时不出错误卡、红色横幅与红点,只显示「正在换一台电脑继续」;> 组里都不能用才报错,见 §6.1。+> 2026-10-11 用户要求:任务所在那台**连不上时先等它恢复**——按退避重试 5 次,恢复了留在原电脑继续,都不行再换电脑,见 §6.1。> 实现进度见 §12:P1 已实现;P2 全部已实现:同账号直连与模型列表只显示组(P2a)、分享的人经组中转与启动阶段换电脑(P2b)、> 分享的人运行中换电脑与申请弹窗新说法(P2c);P3 未实现。> 交互设计稿见 [`docs/design-previews/provider-groups/index.html`](../design-previews/provider-groups/index.html)。@@ -179,6 +180,22 @@下一台:新建会话并带上交接上下文,然后继续这一轮——这一轮还没有产出就重发原消息,已经有产出就发续跑指令,与 [用量上限自动继续](usage-limit-auto-continue.md) 的续跑口径一致。消息流里显示一行活动记录「{原电脑} {原因},已换到 {新电脑} 继续」(受邀者那边写「已自动换一台电脑继续」,§8),不计为用户发送。+ - **连不上先等它恢复**(2026-10-11):那台是连不上(离线、断线)时先不换:现读一次那台的状态,确实连不上才等,+ 按退避(约 3、6、12、20、20 秒,与中断自愈相同)最多重试 5 次,每次现读。恢复了就留在原电脑继续这一轮(不交接、+ 不冷却,活动记录写「已重新连上 {电脑},继续运行」,读不到名称时写「原来的电脑」);5 次都不行才按上面的方式换到下一台。+ 等的期间错误同样先不呈现,消息流与输入框状态显示「重新连接中 n/5」,开始换电脑时改为「正在换一台电脑继续」。+ - 只是连接断了(断线、远程 Cindy 重启后会话没了)而现读第一次就已连得上:断线刚好已恢复,也算一次重试、留在原电脑+ 继续;同一轮次数照算,那台反复断也只这 5 次,用完就换。+ - 不等、直接换的情况:现读连得上但问题不在连接(如那台 Agent 起不来);那台本身不能用(供应商关掉、关闭了远程控制或+ 远程调用、分享暂停或删除等);本机这台;用量上限、登录失效、过载等不是连不上的原因。+ - 次数按一轮、按电脑计,自动续跑与运行中失败共用;用户亲自发消息、重试、换模型即开始新的一轮,重新计。+ - 发送前:已归组的任务所在那台显示离线、或这次发送要重新打开那台上的会话(会话没开着或不在运行态)时,现读一次那台的+ 状态;离线就同样先等(消息还没发出,进行中行显示「重新连接中 n/5」),恢复了照常发到原电脑,等不到再换到下一台+ 再发。用户停止这次发送时立刻停下:不再等、不再换,也不再去打开那台上的会话。+ - 别的电脑上的组读不到(常见是任务就跑在组所在电脑上、它自己断了):换不了电脑,但仍按任务记录里的位置先等那台恢复,+ 恢复了在原电脑继续(活动记录写「原来的电脑」),等不到照原有方式报错;发送前同理。+ - 已经发出却在那台上没确认收到的消息(如请求超时)不自动重发:可能已经在跑,重发会让同一条消息执行两次,照原有方式报错。+ - 下面「换电脑久久没有结局(3 分钟)先把错误放出来」的计时不吃掉等它恢复的时间:每次重试、开始换电脑时重新计时。- **换电脑期间不报错**(2026-10-10):这次失败会先试着换电脑时(已归组、自动换电脑开着、组里还有别的电脑;受邀者那边是收到了「需要换一台」凭证),失败那一刻就不呈现:没有红色横幅、不写错误卡、不亮红点、Agent Island 不提醒,消息流末尾只有一行「正在换一台电脑继续」,输入框上方的状态同样这样写。换成了,历史里只留上面那行换电脑的活动记录