Files
sub2api/backend/internal/service/model_rate_limit.go
T
li 02fbcbe3ad fix(ratelimit): 守卫按端点来源门控,并与冷却键对齐模型口径
上一版守卫只看模型类型,不区分请求从哪个端点进来。OAuth 账号的 /v1/images/*
上游同样是 Codex Responses(openai_images_responses.go → handleOpenAIImagesErrorResponse
→ handleOpenAIAccountUpstreamError → HandleUpstreamModelNotFound),所以专用生图
端点也会命中 plan-gated 分支。账号确实不具备生图能力时跳过冷却,会让调度层失去
唯一的刹车:每个请求都完整走一遍号池,对上游形成无上界的 400 放大。

改动:
- 新增 ctxkey.OpenAIImagesEndpoint 与 WithOpenAIImagesEndpoint /
  OpenAIImagesEndpointFromContext,在 handler/openai_images.go 入口置位;
  与 OpenAIImageGenerationIntent 区分——后者在 /v1/responses 带图片模型时也会置位。
- 守卫下移到 modelKey 计算之后,抽成 shouldSkipCodexPlanGatedImageModelCooldown,
  仅在 plan-gated 分支、且非 /v1/images/* 入站时生效。
- 同时判断 requestedModel 与最终 modelKey:冷却键走 account.GetMappedModel,
  账号可以把文本别名映射到 gpt-image-*,只判请求模型会漏掉这种形态。
2026-08-07 20:49:39 +08:00

190 lines
5.7 KiB
Go
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
package service
import (
"context"
"strings"
"time"
"github.com/Wei-Shaw/sub2api/internal/pkg/ctxkey"
)
const (
modelRateLimitsKey = "model_rate_limits"
antigravityGeminiModelRateLimitKey = "antigravity:gemini"
openAIImageGenerationRateLimitKey = "openai:image_generation"
// anthropicFableRateLimitKey 是 Anthropic 7d_oi(Fable 专属 7d 窗口)限流的
// 家族级 scope:命中后所有 Fable 变体(含 [1m] 等后缀)都不再调度到该账号。
anthropicFableRateLimitKey = "claude-fable-5"
)
// isRateLimitActiveForKey 检查指定 key 的限流是否生效
func (a *Account) isRateLimitActiveForKey(key string) bool {
resetAt := a.modelRateLimitResetAt(key)
return resetAt != nil && time.Now().Before(*resetAt)
}
// getRateLimitRemainingForKey 获取指定 key 的限流剩余时间,0 表示未限流或已过期
func (a *Account) getRateLimitRemainingForKey(key string) time.Duration {
resetAt := a.modelRateLimitResetAt(key)
if resetAt == nil {
return 0
}
remaining := time.Until(*resetAt)
if remaining > 0 {
return remaining
}
return 0
}
func (a *Account) isModelRateLimitedWithContext(ctx context.Context, requestedModel string) bool {
for _, key := range a.modelRateLimitKeysForRequest(ctx, requestedModel) {
if a.isRateLimitActiveForKey(key) {
return true
}
}
return false
}
// GetModelRateLimitRemainingTime 获取模型限流剩余时间
// 返回 0 表示未限流或已过期
func (a *Account) GetModelRateLimitRemainingTime(requestedModel string) time.Duration {
return a.GetModelRateLimitRemainingTimeWithContext(context.Background(), requestedModel)
}
func (a *Account) GetModelRateLimitRemainingTimeWithContext(ctx context.Context, requestedModel string) time.Duration {
remaining := time.Duration(0)
for _, key := range a.modelRateLimitKeysForRequest(ctx, requestedModel) {
if keyRemaining := a.getRateLimitRemainingForKey(key); keyRemaining > remaining {
remaining = keyRemaining
}
}
return remaining
}
func (a *Account) modelRateLimitKeysForRequest(ctx context.Context, requestedModel string) []string {
if a == nil {
return nil
}
modelKey := a.GetMappedModel(requestedModel)
if a.Platform == PlatformAntigravity {
modelKey = resolveFinalAntigravityModelKey(ctx, a, requestedModel)
}
modelKey = strings.TrimSpace(modelKey)
if modelKey == "" {
return nil
}
keys := []string{modelKey}
switch a.Platform {
case PlatformAntigravity:
if isAntigravityGeminiModel(modelKey) && modelKey != antigravityGeminiModelRateLimitKey {
keys = append(keys, antigravityGeminiModelRateLimitKey)
}
case PlatformOpenAI:
if openAIImageGenerationRateLimitApplies(ctx, requestedModel, modelKey) && modelKey != openAIImageGenerationRateLimitKey {
keys = append(keys, openAIImageGenerationRateLimitKey)
}
case PlatformAnthropic:
if isAnthropicFableModel(modelKey) && modelKey != anthropicFableRateLimitKey {
keys = append(keys, anthropicFableRateLimitKey)
}
}
return keys
}
// isAnthropicFableModel 判断是否为 Fable 模型家族(claude-fable-5、claude-fable-5[1m] 等变体)
func isAnthropicFableModel(model string) bool {
return strings.Contains(strings.ToLower(model), "fable")
}
func openAIImageGenerationRateLimitApplies(ctx context.Context, requestedModel, modelKey string) bool {
if isOpenAIImageGenerationModel(requestedModel) || isOpenAIImageGenerationModel(modelKey) {
return true
}
return OpenAIImageGenerationIntentFromContext(ctx)
}
func WithOpenAIImageGenerationIntent(ctx context.Context) context.Context {
if ctx == nil {
ctx = context.Background()
}
return context.WithValue(ctx, ctxkey.OpenAIImageGenerationIntent, true)
}
func OpenAIImageGenerationIntentFromContext(ctx context.Context) bool {
if ctx == nil {
return false
}
enabled, ok := ctx.Value(ctxkey.OpenAIImageGenerationIntent).(bool)
return ok && enabled
}
// WithOpenAIImagesEndpoint 标记请求从 /v1/images/* 专用生图端点入站。
func WithOpenAIImagesEndpoint(ctx context.Context) context.Context {
if ctx == nil {
ctx = context.Background()
}
return context.WithValue(ctx, ctxkey.OpenAIImagesEndpoint, true)
}
// OpenAIImagesEndpointFromContext 报告请求是否来自 /v1/images/*。
func OpenAIImagesEndpointFromContext(ctx context.Context) bool {
if ctx == nil {
return false
}
enabled, ok := ctx.Value(ctxkey.OpenAIImagesEndpoint).(bool)
return ok && enabled
}
func resolveFinalAntigravityModelKey(ctx context.Context, account *Account, requestedModel string) string {
modelKey := mapAntigravityModel(account, requestedModel)
if modelKey == "" {
return ""
}
// thinking 会影响 Antigravity 最终模型名(例如 claude-sonnet-4-5 -> claude-sonnet-4-5-thinking)
if enabled, ok := ThinkingEnabledFromContext(ctx); ok {
modelKey = applyThinkingModelSuffix(modelKey, enabled)
}
return modelKey
}
func isAntigravityGeminiModel(model string) bool {
return strings.HasPrefix(normalizeAntigravityModelName(model), "gemini-")
}
func antigravityModelRateLimitKeys(model string) []string {
model = strings.TrimSpace(model)
if model == "" {
return nil
}
keys := []string{model}
if isAntigravityGeminiModel(model) && model != antigravityGeminiModelRateLimitKey {
keys = append(keys, antigravityGeminiModelRateLimitKey)
}
return keys
}
func (a *Account) modelRateLimitResetAt(scope string) *time.Time {
if a == nil || a.Extra == nil || scope == "" {
return nil
}
rawLimits, ok := a.Extra[modelRateLimitsKey].(map[string]any)
if !ok {
return nil
}
rawLimit, ok := rawLimits[scope].(map[string]any)
if !ok {
return nil
}
resetAtRaw, ok := rawLimit["rate_limit_reset_at"].(string)
if !ok || strings.TrimSpace(resetAtRaw) == "" {
return nil
}
resetAt, err := time.Parse(time.RFC3339, resetAtRaw)
if err != nil {
return nil
}
return &resetAt
}