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/concurrency_service.go

@@ -35,6 +35,7 @@ type ConcurrencyCache interface {
 
 	// 批量负载查询（只读）
 	GetAccountsLoadBatch(ctx context.Context, accounts []AccountWithConcurrency) (map[int64]*AccountLoadInfo, error)
+	GetUsersLoadBatch(ctx context.Context, users []UserWithConcurrency) (map[int64]*UserLoadInfo, error)
 
 	// 清理过期槽位（后台任务）
 	CleanupExpiredAccountSlots(ctx context.Context, accountID int64) error
@@ -77,6 +78,11 @@ type AccountWithConcurrency struct {
 	MaxConcurrency int
 }
 
+type UserWithConcurrency struct {
+	ID             int64
+	MaxConcurrency int
+}
+
 type AccountLoadInfo struct {
 	AccountID          int64
 	CurrentConcurrency int
@@ -84,6 +90,13 @@ type AccountLoadInfo struct {
 	LoadRate           int // 0-100+ (percent)
 }
 
+type UserLoadInfo struct {
+	UserID             int64
+	CurrentConcurrency int
+	WaitingCount       int
+	LoadRate           int // 0-100+ (percent)
+}
+
 // AcquireAccountSlot attempts to acquire a concurrency slot for an account.
 // If the account is at max concurrency, it waits until a slot is available or timeout.
 // Returns a release function that MUST be called when the request completes.
@@ -253,6 +266,14 @@ func (s *ConcurrencyService) GetAccountsLoadBatch(ctx context.Context, accounts
 	return s.cache.GetAccountsLoadBatch(ctx, accounts)
 }
 
+// GetUsersLoadBatch returns load info for multiple users.
+func (s *ConcurrencyService) GetUsersLoadBatch(ctx context.Context, users []UserWithConcurrency) (map[int64]*UserLoadInfo, error) {
+	if s.cache == nil {
+		return map[int64]*UserLoadInfo{}, nil
+	}
+	return s.cache.GetUsersLoadBatch(ctx, users)
+}
+
 // CleanupExpiredAccountSlots removes expired slots for one account (background task).
 func (s *ConcurrencyService) CleanupExpiredAccountSlots(ctx context.Context, accountID int64) error {
 	if s.cache == nil {