oadmin/sub2api
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Merge pull request #285 from IanShaw027/fix/ops-bug

Browse Source 
feat(ops): 增强错误日志管理、告警静默和前端 UI 优化
This commit is contained in:
Wesley Liddick
2026-01-15 11:26:16 +08:00
committed by GitHub
parent 28de614dfb 5354ba3662
commit 27214f8657
42 changed files with 4039 additions and 1065 deletions
Download Patch File Download Diff File Expand all files Collapse all files

229
frontend/src/i18n/locales/en.ts
View File

@@ -129,6 +129,8 @@ export default {
all: 'All',
none: 'None',
noData: 'No data',
expand: 'Expand',
collapse: 'Collapse',
success: 'Success',
error: 'Error',
critical: 'Critical',
@@ -150,12 +152,13 @@ export default {
invalidEmail: 'Please enter a valid email address',
optional: 'optional',
selectOption: 'Select an option',
searchPlaceholder: 'Search...',
noOptionsFound: 'No options found',
noGroupsAvailable: 'No groups available',
unknownError: 'Unknown error occurred',
saving: 'Saving...',
selectedCount: '({count} selected)', refresh: 'Refresh',
searchPlaceholder: 'Search...',
noOptionsFound: 'No options found',
noGroupsAvailable: 'No groups available',
unknownError: 'Unknown error occurred',
saving: 'Saving...',
selectedCount: '({count} selected)',
refresh: 'Refresh',
settings: 'Settings',
notAvailable: 'N/A',
now: 'Now',
@@ -1882,10 +1885,8 @@ export default {
noSystemMetrics: 'No system metrics collected yet.',
collectedAt: 'Collected at:',
window: 'window',
cpu: 'CPU',
memory: 'Memory',
db: 'DB',
redis: 'Redis',
goroutines: 'Goroutines',
jobs: 'Jobs',
jobsHelp: 'Click “Details” to view job heartbeats and recent errors',
@@ -1911,7 +1912,7 @@ export default {
totalRequests: 'Total Requests',
avgQps: 'Avg QPS',
avgTps: 'Avg TPS',
avgLatency: 'Avg Latency',
avgLatency: 'Avg Request Duration',
avgTtft: 'Avg TTFT',
exceptions: 'Exceptions',
requestErrors: 'Request Errors',
@@ -1923,7 +1924,7 @@ export default {
errors: 'Errors',
errorRate: 'error_rate:',
upstreamRate: 'upstream_rate:',
latencyDuration: 'Latency (duration_ms)',
latencyDuration: 'Request Duration (ms)',
ttftLabel: 'TTFT (first_token_ms)',
p50: 'p50:',
p90: 'p90:',
@@ -1931,7 +1932,6 @@ export default {
p99: 'p99:',
avg: 'avg:',
max: 'max:',
qps: 'QPS',
requests: 'Requests',
requestsTitle: 'Requests',
upstream: 'Upstream',
@@ -1943,7 +1943,7 @@ export default {
failedToLoadData: 'Failed to load ops data.',
failedToLoadOverview: 'Failed to load overview',
failedToLoadThroughputTrend: 'Failed to load throughput trend',
failedToLoadLatencyHistogram: 'Failed to load latency histogram',
failedToLoadLatencyHistogram: 'Failed to load request duration histogram',
failedToLoadErrorTrend: 'Failed to load error trend',
failedToLoadErrorDistribution: 'Failed to load error distribution',
failedToLoadErrorDetail: 'Failed to load error detail',
@@ -1951,7 +1951,7 @@ export default {
tpsK: 'TPS (K)',
top: 'Top:',
throughputTrend: 'Throughput Trend',
latencyHistogram: 'Latency Histogram',
latencyHistogram: 'Request Duration Histogram',
errorTrend: 'Error Trend',
errorDistribution: 'Error Distribution',
// Health Score & Diagnosis
@@ -1966,7 +1966,9 @@ export default {
'30m': 'Last 30 minutes',
'1h': 'Last 1 hour',
'6h': 'Last 6 hours',
'24h': 'Last 24 hours'
'24h': 'Last 24 hours',
'7d': 'Last 7 days',
'30d': 'Last 30 days'
},
fullscreen: {
enter: 'Enter Fullscreen'
@@ -1995,14 +1997,7 @@ export default {
memoryHigh: 'Memory usage elevated ({usage}%)',
memoryHighImpact: 'Memory pressure is high, needs attention',
memoryHighAction: 'Monitor memory trends, check for memory leaks',
// Latency diagnostics
latencyCritical: 'Response latency critically high ({latency}ms)',
latencyCriticalImpact: 'User experience extremely poor, many requests timing out',
latencyCriticalAction: 'Check slow queries, database indexes, network latency, and upstream services',
latencyHigh: 'Response latency elevated ({latency}ms)',
latencyHighImpact: 'User experience degraded, needs optimization',
latencyHighAction: 'Analyze slow request logs, optimize database queries and business logic',
ttftHigh: 'Time to first byte elevated ({ttft}ms)',
ttftHigh: 'Time to first token elevated ({ttft}ms)',
ttftHighImpact: 'User perceived latency increased',
ttftHighAction: 'Optimize request processing flow, reduce pre-processing time',
// Error rate diagnostics
@@ -2038,27 +2033,106 @@ export default {
// Error Log
errorLog: {
timeId: 'Time / ID',
commonErrors: {
contextDeadlineExceeded: 'context deadline exceeded',
connectionRefused: 'connection refused',
rateLimit: 'rate limit'
},
time: 'Time',
type: 'Type',
context: 'Context',
platform: 'Platform',
model: 'Model',
group: 'Group',
user: 'User',
userId: 'User ID',
account: 'Account',
accountId: 'Account ID',
status: 'Status',
message: 'Message',
latency: 'Latency',
latency: 'Request Duration',
action: 'Action',
noErrors: 'No errors in this window.',
grp: 'GRP:',
acc: 'ACC:',
details: 'Details',
phase: 'Phase'
phase: 'Phase',
id: 'ID:',
typeUpstream: 'Upstream',
typeRequest: 'Request',
typeAuth: 'Auth',
typeRouting: 'Routing',
typeInternal: 'Internal'
},
// Error Details Modal
errorDetails: {
upstreamErrors: 'Upstream Errors',
requestErrors: 'Request Errors',
unresolved: 'Unresolved',
resolved: 'Resolved',
viewErrors: 'Errors',
viewExcluded: 'Excluded',
statusCodeOther: 'Other',
owner: {
provider: 'Provider',
client: 'Client',
platform: 'Platform'
},
phase: {
request: 'Request',
auth: 'Auth',
routing: 'Routing',
upstream: 'Upstream',
network: 'Network',
internal: 'Internal'
},
total: 'Total:',
searchPlaceholder: 'Search request_id / client_request_id / message',
accountIdPlaceholder: 'account_id'
},
// Error Detail Modal
errorDetail: {
title: 'Error Detail',
titleWithId: 'Error #{id}',
noErrorSelected: 'No error selected.',
resolution: 'Resolved:',
pinnedToOriginalAccountId: 'Pinned to original account_id',
missingUpstreamRequestBody: 'Missing upstream request body',
failedToLoadRetryHistory: 'Failed to load retry history',
failedToUpdateResolvedStatus: 'Failed to update resolved status',
unsupportedRetryMode: 'Unsupported retry mode',
classificationKeys: {
phase: 'Phase',
owner: 'Owner',
source: 'Source',
retryable: 'Retryable',
resolvedAt: 'Resolved At',
resolvedBy: 'Resolved By',
resolvedRetryId: 'Resolved Retry',
retryCount: 'Retry Count'
},
source: {
upstream_http: 'Upstream HTTP'
},
upstreamKeys: {
status: 'Status',
message: 'Message',
detail: 'Detail',
upstreamErrors: 'Upstream Errors'
},
upstreamEvent: {
account: 'Account',
status: 'Status',
requestId: 'Request ID'
},
responsePreview: {
expand: 'Response (click to expand)',
collapse: 'Response (click to collapse)'
},
retryMeta: {
used: 'Used',
success: 'Success',
pinned: 'Pinned'
},
loading: 'Loading…',
requestId: 'Request ID',
time: 'Time',
@@ -2068,8 +2142,10 @@ export default {
basicInfo: 'Basic Info',
platform: 'Platform',
model: 'Model',
latency: 'Latency',
ttft: 'TTFT',
group: 'Group',
user: 'User',
account: 'Account',
latency: 'Request Duration',
businessLimited: 'Business Limited',
requestPath: 'Request Path',
timings: 'Timings',
@@ -2077,6 +2153,8 @@ export default {
routing: 'Routing',
upstream: 'Upstream',
response: 'Response',
classification: 'Classification',
notRetryable: 'Not recommended to retry',
retry: 'Retry',
retryClient: 'Retry (Client)',
retryUpstream: 'Retry (Upstream pinned)',
@@ -2088,7 +2166,6 @@ export default {
confirmRetry: 'Confirm Retry',
retrySuccess: 'Retry succeeded',
retryFailed: 'Retry failed',
na: 'N/A',
retryHint: 'Retry will resend the request with the same parameters',
retryClientHint: 'Use client retry (no account pinning)',
retryUpstreamHint: 'Use upstream pinned retry (pin to the error account)',
@@ -2096,8 +2173,33 @@ export default {
retryNote1: 'Retry will use the same request body and parameters',
retryNote2: 'If the original request failed due to account issues, pinned retry may still fail',
retryNote3: 'Client retry will reselect an account',
retryNote4: 'You can force retry for non-retryable errors, but it is not recommended',
confirmRetryMessage: 'Confirm retry this request?',
confirmRetryHint: 'Will resend with the same request parameters'
confirmRetryHint: 'Will resend with the same request parameters',
forceRetry: 'I understand and want to force retry',
forceRetryHint: 'This error usually cannot be fixed by retry; check to proceed',
forceRetryNeedAck: 'Please check to force retry',
markResolved: 'Mark resolved',
markUnresolved: 'Mark unresolved',
viewRetries: 'Retry history',
retryHistory: 'Retry History',
tabOverview: 'Overview',
tabRetries: 'Retries',
tabRequest: 'Request',
tabResponse: 'Response',
responseBody: 'Response',
compareA: 'Compare A',
compareB: 'Compare B',
retrySummary: 'Retry Summary',
responseHintSucceeded: 'Showing succeeded retry response_preview (#{id})',
responseHintFallback: 'No succeeded retry found; showing stored error_body',
suggestion: 'Suggestion',
suggestUpstreamResolved: '✓ Upstream error resolved by retry; no action needed',
suggestUpstream: 'Upstream instability: check account status, consider switching accounts, or retry',
suggestRequest: 'Client request error: ask customer to fix request parameters',
suggestAuth: 'Auth failed: verify API key/credentials',
suggestPlatform: 'Platform error: prioritize investigation and fix',
suggestGeneric: 'See details for more context'
},
requestDetails: {
title: 'Request Details',
@@ -2133,13 +2235,46 @@ export default {
loading: 'Loading...',
empty: 'No alert events',
loadFailed: 'Failed to load alert events',
status: {
firing: 'FIRING',
resolved: 'RESOLVED',
manualResolved: 'MANUAL RESOLVED'
},
detail: {
title: 'Alert Detail',
loading: 'Loading detail...',
empty: 'No detail',
loadFailed: 'Failed to load alert detail',
manualResolve: 'Mark as Resolved',
manualResolvedSuccess: 'Marked as manually resolved',
manualResolvedFailed: 'Failed to mark as manually resolved',
silence: 'Ignore Alert',
silenceSuccess: 'Alert silenced',
silenceFailed: 'Failed to silence alert',
viewRule: 'View Rule',
viewLogs: 'View Logs',
firedAt: 'Fired At',
resolvedAt: 'Resolved At',
ruleId: 'Rule ID',
dimensions: 'Dimensions',
historyTitle: 'History',
historyHint: 'Recent events with same rule + dimensions',
historyLoading: 'Loading history...',
historyEmpty: 'No history'
},
table: {
time: 'Time',
status: 'Status',
severity: 'Severity',
platform: 'Platform',
ruleId: 'Rule ID',
title: 'Title',
duration: 'Duration',
metric: 'Metric / Threshold',
email: 'Email Sent'
dimensions: 'Dimensions',
email: 'Email Sent',
emailSent: 'Sent',
emailIgnored: 'Ignored'
}
},
alertRules: {
@@ -2253,7 +2388,6 @@ export default {
title: 'Alert Silencing (Maintenance Mode)',
enabled: 'Enable silencing',
globalUntil: 'Silence until (RFC3339)',
untilPlaceholder: '2026-01-05T00:00:00Z',
untilHint: 'Leave empty to only toggle silencing without an expiry (not recommended).',
reason: 'Reason',
reasonPlaceholder: 'e.g., planned maintenance',
@@ -2293,7 +2427,11 @@ export default {
lockKeyRequired: 'Distributed lock key is required when lock is enabled',
lockKeyPrefix: 'Distributed lock key must start with "{prefix}"',
lockKeyHint: 'Recommended: start with "{prefix}" to avoid conflicts',
lockTtlRange: 'Distributed lock TTL must be between 1 and 86400 seconds'
lockTtlRange: 'Distributed lock TTL must be between 1 and 86400 seconds',
slaMinPercentRange: 'SLA minimum percentage must be between 0 and 100',
ttftP99MaxRange: 'TTFT P99 maximum must be a number ≥ 0',
requestErrorRateMaxRange: 'Request error rate maximum must be between 0 and 100',
upstreamErrorRateMaxRange: 'Upstream error rate maximum must be between 0 and 100'
}
},
email: {
@@ -2358,8 +2496,6 @@ export default {
metricThresholdsHint: 'Configure alert thresholds for metrics, values exceeding thresholds will be displayed in red',
slaMinPercent: 'SLA Minimum Percentage',
slaMinPercentHint: 'SLA below this value will be displayed in red (default: 99.5%)',
latencyP99MaxMs: 'Latency P99 Maximum (ms)',
latencyP99MaxMsHint: 'Latency P99 above this value will be displayed in red (default: 2000ms)',
ttftP99MaxMs: 'TTFT P99 Maximum (ms)',
ttftP99MaxMsHint: 'TTFT P99 above this value will be displayed in red (default: 500ms)',
requestErrorRateMaxPercent: 'Request Error Rate Maximum (%)',
@@ -2378,9 +2514,28 @@ export default {
aggregation: 'Pre-aggregation Tasks',
enableAggregation: 'Enable Pre-aggregation',
aggregationHint: 'Pre-aggregation improves query performance for long time windows',
errorFiltering: 'Error Filtering',
ignoreCountTokensErrors: 'Ignore count_tokens errors',
ignoreCountTokensErrorsHint: 'When enabled, errors from count_tokens requests will not be written to the error log.',
ignoreContextCanceled: 'Ignore client disconnect errors',
ignoreContextCanceledHint: 'When enabled, client disconnect (context canceled) errors will not be written to the error log.',
ignoreNoAvailableAccounts: 'Ignore no available accounts errors',
ignoreNoAvailableAccountsHint: 'When enabled, "No available accounts" errors will not be written to the error log (not recommended; usually a config issue).',
autoRefresh: 'Auto Refresh',
enableAutoRefresh: 'Enable auto refresh',
enableAutoRefreshHint: 'Automatically refresh dashboard data at a fixed interval.',
refreshInterval: 'Refresh Interval',
refreshInterval15s: '15 seconds',
refreshInterval30s: '30 seconds',
refreshInterval60s: '60 seconds',
autoRefreshCountdown: 'Auto refresh: {seconds}s',
validation: {
title: 'Please fix the following issues',
retentionDaysRange: 'Retention days must be between 1-365 days'
retentionDaysRange: 'Retention days must be between 1-365 days',
slaMinPercentRange: 'SLA minimum percentage must be between 0 and 100',
ttftP99MaxRange: 'TTFT P99 maximum must be a number ≥ 0',
requestErrorRateMaxRange: 'Request error rate maximum must be between 0 and 100',
upstreamErrorRateMaxRange: 'Upstream error rate maximum must be between 0 and 100'
}
},
concurrency: {
@@ -2418,7 +2573,7 @@ export default {
tooltips: {
totalRequests: 'Total number of requests (including both successful and failed requests) in the selected time window.',
throughputTrend: 'Requests/QPS + Tokens/TPS in the selected window.',
latencyHistogram: 'Latency distribution (duration_ms) for successful requests.',
latencyHistogram: 'Request duration distribution (ms) for successful requests.',
errorTrend: 'Error counts over time (SLA scope excludes business limits; upstream excludes 429/529).',
errorDistribution: 'Error distribution by status code.',
goroutines:
@@ -2433,7 +2588,7 @@ export default {
sla: 'Service Level Agreement success rate, excluding business limits (e.g., insufficient balance, quota exceeded).',
errors: 'Error statistics, including total errors, error rate, and upstream error rate.',
upstreamErrors: 'Upstream error statistics, excluding rate limit errors (429/529).',
latency: 'Request latency statistics, including p50, p90, p95, p99 percentiles.',
latency: 'Request duration statistics, including p50, p90, p95, p99 percentiles.',
ttft: 'Time To First Token, measuring the speed of first byte return in streaming responses.',
health: 'System health score (0-100), considering SLA, error rate, and resource usage.'
},