feat(antigravity): comprehensive enhancements - model mapping, rate limiting, scheduling & ops

Key changes:
- Upgrade model mapping: Opus 4.5 → Opus 4.6-thinking with precise matching
- Unified rate limiting: scope-level → model-level with Redis snapshot sync
- Load-balanced scheduling by call count with smart retry mechanism
- Force cache billing support
- Model identity injection in prompts with leak prevention
- Thinking mode auto-handling (max_tokens/budget_tokens fix)
- Frontend: whitelist mode toggle, model mapping validation, status indicators
- Gemini session fallback with Redis Trie O(L) matching
- Ops: enhanced concurrency monitoring, account availability, retry logic
- Migration scripts: 049-051 for model mapping unification

backend/internal/service/antigravity_quota_scope.go

@@ -1,6 +1,7 @@
 package service
 
 import (
+	"context"
 	"slices"
 	"strings"
 	"time"
@@ -57,15 +58,20 @@ func normalizeAntigravityModelName(model string) string {
 	return normalized
 }
 
-// IsSchedulableForModel 结合 Antigravity 配额域限流判断是否可调度
+// IsSchedulableForModel 结合 Antigravity 配额域限流判断是否可调度。
+// 保持旧签名以兼容既有调用方；默认使用 context.Background()。
 func (a *Account) IsSchedulableForModel(requestedModel string) bool {
+	return a.IsSchedulableForModelWithContext(context.Background(), requestedModel)
+}
+
+func (a *Account) IsSchedulableForModelWithContext(ctx context.Context, requestedModel string) bool {
 	if a == nil {
 		return false
 	}
 	if !a.IsSchedulable() {
 		return false
 	}
-	if a.isModelRateLimited(requestedModel) {
+	if a.isModelRateLimitedWithContext(ctx, requestedModel) {
 		return false
 	}
 	if a.Platform != PlatformAntigravity {
@@ -132,3 +138,43 @@ func (a *Account) GetAntigravityScopeRateLimits() map[string]int64 {
 	}
 	return result
 }
+
+// GetQuotaScopeRateLimitRemainingTime 获取模型域限流剩余时间
+// 返回 0 表示未限流或已过期
+func (a *Account) GetQuotaScopeRateLimitRemainingTime(requestedModel string) time.Duration {
+	if a == nil || a.Platform != PlatformAntigravity {
+		return 0
+	}
+	scope, ok := resolveAntigravityQuotaScope(requestedModel)
+	if !ok {
+		return 0
+	}
+	resetAt := a.antigravityQuotaScopeResetAt(scope)
+	if resetAt == nil {
+		return 0
+	}
+	if remaining := time.Until(*resetAt); remaining > 0 {
+		return remaining
+	}
+	return 0
+}
+
+// GetRateLimitRemainingTime 获取限流剩余时间（模型限流和模型域限流取最大值）
+// 返回 0 表示未限流或已过期
+func (a *Account) GetRateLimitRemainingTime(requestedModel string) time.Duration {
+	return a.GetRateLimitRemainingTimeWithContext(context.Background(), requestedModel)
+}
+
+// GetRateLimitRemainingTimeWithContext 获取限流剩余时间（模型限流和模型域限流取最大值）
+// 返回 0 表示未限流或已过期
+func (a *Account) GetRateLimitRemainingTimeWithContext(ctx context.Context, requestedModel string) time.Duration {
+	if a == nil {
+		return 0
+	}
+	modelRemaining := a.GetModelRateLimitRemainingTimeWithContext(ctx, requestedModel)
+	scopeRemaining := a.GetQuotaScopeRateLimitRemainingTime(requestedModel)
+	if modelRemaining > scopeRemaining {
+		return modelRemaining
+	}
+	return scopeRemaining
+}