Feat/auto failover switch (#440)

* feat(failover): add auto-failover master switch with proxy integration

- Add persistent auto_failover_enabled setting in database
- Add get/set_auto_failover_enabled commands
- Provider router respects master switch state
- Proxy shutdown automatically disables failover
- Enabling failover auto-starts proxy server
- Optimistic updates for failover queue toggle

* feat(proxy): persist proxy takeover state across app restarts

- Add proxy_takeover_{app_type} settings for per-app state tracking
- Restore proxy takeover state automatically on app startup
- Preserve state on normal exit, clear on manual stop
- Add stop_with_restore_keep_state method for graceful shutdown

* fix(proxy): set takeover state for all apps in start_with_takeover

* fix(windows): hide console window when checking CLI versions

Add CREATE_NO_WINDOW flag to prevent command prompt from flashing
when detecting claude/codex/gemini CLI versions on Windows.

* refactor(failover): make auto-failover toggle per-app independent

- Change setting key from 'auto_failover_enabled' to 'auto_failover_enabled_{app_type}'
- Update provider_router to check per-app failover setting
- When failover disabled, use current provider only; when enabled, use queue order
- Add unit tests for failover enabled/disabled behavior

* feat(failover): auto-switch to higher priority provider on recovery

- After circuit breaker reset, check if recovered provider has higher priority
- Automatically switch back if queue_order is lower (higher priority)
- Stream health check now resets circuit breaker on success/degraded

* chore: remove unused start_proxy_with_takeover command

- Remove command registration from lib.rs
- Add comment clarifying failover queue is preserved on proxy stop

* feat(ui): integrate failover controls into provider cards

- Add failover toggle button to provider card actions
- Show priority badge (P1, P2, ...) for queued providers
- Highlight active provider with green border in failover mode
- Sync drag-drop order with failover queue
- Move per-app failover toggle to FailoverQueueManager
- Simplify SettingsPage failover section

* test(providers): add mocks for failover hooks in ProviderList tests

* refactor(failover): merge failover_queue table into providers

- Add in_failover_queue field to providers table
- Remove standalone failover_queue table and related indexes
- Simplify queue ordering by reusing sort_index field
- Remove reorder_failover_queue and set_failover_item_enabled commands
- Update frontend to use simplified FailoverQueueItem type

* fix(database): ensure in_failover_queue column exists for v2 databases

Add column check in create_tables to handle existing v2 databases
that were created before the failover queue refactor.

* fix(ui): differentiate active provider border color by proxy mode

- Use green border/gradient when proxy takeover is active
- Use blue border/gradient in normal mode (no proxy)
- Improves visual distinction between proxy and non-proxy states

* fix(database): clear provider health record when removing from failover queue

When a provider is removed from the failover queue, its health monitoring
is no longer needed. This change ensures the health record is also deleted
from the database to prevent stale data.

* fix(failover): improve cache cleanup for provider health and circuit breaker

- Use removeQueries instead of invalidateQueries when stopping proxy to
  completely clear health and circuit breaker caches
- Clear provider health and circuit breaker caches when removing from
  failover queue
- Refresh failover queue after drag-sort since queue order depends on
  sort_index
- Only show health badge when provider is in failover queue

* style: apply prettier formatting to App.tsx and ProviderList.tsx

* fix(proxy): handle missing health records and clear health on proxy stop

- Return default healthy state when provider health record not found
- Add clear_provider_health_for_app to clear health for specific app
- Clear app health records when stopping proxy takeover

* fix(proxy): track actual provider used in forwarding for accurate logging

Introduce ForwardResult and ForwardError structs to return the actual
provider that handled the request. This ensures usage statistics and
error logs reflect the correct provider after failover.
This commit is contained in:
YoVinchen
2025-12-23 12:37:36 +08:00
committed by GitHub
parent bf570b6d2a
commit 1586451862
38 changed files with 972 additions and 810 deletions
+30 -59
View File
@@ -47,10 +47,6 @@ import type { SettingsFormState } from "@/hooks/useSettings";
import { Switch } from "@/components/ui/switch";
import { Badge } from "@/components/ui/badge";
import { useProxyStatus } from "@/hooks/useProxyStatus";
import {
useAutoFailoverEnabled,
useSetAutoFailoverEnabled,
} from "@/lib/query/failover";
interface SettingsDialogProps {
open: boolean;
@@ -187,17 +183,9 @@ export function SettingsPage({
isPending: isProxyPending,
} = useProxyStatus();
// 使用持久化的自动故障转移开关状态
const { data: failoverEnabled = false } = useAutoFailoverEnabled();
const setAutoFailoverEnabled = useSetAutoFailoverEnabled();
const handleToggleProxy = async (checked: boolean) => {
try {
if (!checked) {
// 关闭代理时,同时关闭故障转移
if (failoverEnabled) {
setAutoFailoverEnabled.mutate(false);
}
await stopWithRestore();
} else {
await startProxyServer();
@@ -207,19 +195,6 @@ export function SettingsPage({
}
};
// 处理故障转移开关:开启时自动启动代理
const handleToggleFailover = async (checked: boolean) => {
try {
if (checked && !isRunning) {
// 开启故障转移时,先启动代理
await startProxyServer();
}
setAutoFailoverEnabled.mutate(checked);
} catch (error) {
console.error("Toggle failover failed:", error);
}
};
return (
<div className="mx-auto max-w-[56rem] flex flex-col h-[calc(100vh-8rem)] overflow-hidden px-6">
{isBusy ? (
@@ -380,37 +355,36 @@ export function SettingsPage({
<AccordionItem
value="failover"
className="rounded-xl glass-card overflow-hidden [&[data-state=open]>.accordion-header]:bg-muted/50"
className="rounded-xl glass-card overflow-hidden"
>
<AccordionPrimitive.Header className="accordion-header flex items-center justify-between px-6 py-4 hover:bg-muted/50">
<AccordionPrimitive.Trigger className="flex flex-1 items-center justify-between hover:no-underline [&[data-state=open]>svg]:rotate-180">
<div className="flex items-center gap-3">
<Activity className="h-5 w-5 text-orange-500" />
<div className="text-left">
<h3 className="text-base font-semibold">
{t("settings.advanced.failover.title")}
</h3>
<p className="text-sm text-muted-foreground font-normal">
{t("settings.advanced.failover.description")}
</p>
</div>
<AccordionTrigger className="px-6 py-4 hover:no-underline hover:bg-muted/50 data-[state=open]:bg-muted/50">
<div className="flex items-center gap-3">
<Activity className="h-5 w-5 text-orange-500" />
<div className="text-left">
<h3 className="text-base font-semibold">
{t("settings.advanced.failover.title")}
</h3>
<p className="text-sm text-muted-foreground font-normal">
{t("settings.advanced.failover.description")}
</p>
</div>
<ChevronDown className="h-4 w-4 shrink-0 transition-transform duration-200" />
</AccordionPrimitive.Trigger>
<div className="flex items-center gap-2 pl-4">
<Switch
checked={failoverEnabled && isRunning}
onCheckedChange={handleToggleFailover}
disabled={
setAutoFailoverEnabled.isPending || isProxyPending
}
/>
</div>
</AccordionPrimitive.Header>
</AccordionTrigger>
<AccordionContent className="px-6 pb-6 pt-4 border-t border-border/50">
<div className="space-y-6">
{/* 故障转移队列管理 */}
{/* 代理未运行时的提示 */}
{!isRunning && (
<div className="p-4 rounded-lg bg-yellow-500/10 border border-yellow-500/20">
<p className="text-sm text-yellow-600 dark:text-yellow-400">
{t("proxy.failover.proxyRequired", {
defaultValue:
"需要先启动代理服务才能配置故障转移",
})}
</p>
</div>
)}
{/* 故障转移队列管理 - 每个应用独立 */}
<div className="space-y-4">
<div>
<h4 className="text-sm font-semibold">
@@ -429,30 +403,27 @@ export function SettingsPage({
<TabsContent value="claude" className="mt-4">
<FailoverQueueManager
appType="claude"
disabled={!failoverEnabled || !isRunning}
disabled={!isRunning}
/>
</TabsContent>
<TabsContent value="codex" className="mt-4">
<FailoverQueueManager
appType="codex"
disabled={!failoverEnabled || !isRunning}
disabled={!isRunning}
/>
</TabsContent>
<TabsContent value="gemini" className="mt-4">
<FailoverQueueManager
appType="gemini"
disabled={!failoverEnabled || !isRunning}
disabled={!isRunning}
/>
</TabsContent>
</Tabs>
</div>
{/* 熔断器配置 */}
{/* 熔断器配置 - 全局共享 */}
<div className="border-t border-border/50 pt-6">
<AutoFailoverConfigPanel
enabled={failoverEnabled && isRunning}
onEnabledChange={handleToggleFailover}
/>
<AutoFailoverConfigPanel />
</div>
</div>
</AccordionContent>