feat: squash merge all changes from develop-0.1.75

Squash of 124 commits from the legacy develop branch (develop-0.1.75)
onto a clean v0.1.75 upstream base, to simplify future upstream merges.

Key changes included:
- Refactor scope-level rate limiting to model-level rate limiting
- Antigravity gateway service improvements (smart retry, error policy)
- Digest session store (flat cache replacing Trie-based store)
- Client disconnect detection during streaming
- Gemini messages compatibility service enhancements
- Scheduler shuffle for thundering herd prevention
- Session hash generation improvements
- Frontend customizations (WeChat service, HomeView, etc.)
- Ops monitoring scope cleanup

backend/internal/handler/dto/types.go

@@ -2,11 +2,6 @@ package dto
 
 import "time"
 
-type ScopeRateLimitInfo struct {
-	ResetAt      time.Time `json:"reset_at"`
-	RemainingSec int64     `json:"remaining_sec"`
-}
-
 type User struct {
 	ID            int64     `json:"id"`
 	Email         string    `json:"email"`
@@ -126,9 +121,6 @@ type Account struct {
 	RateLimitResetAt *time.Time `json:"rate_limit_reset_at"`
 	OverloadUntil    *time.Time `json:"overload_until"`
 
-	// Antigravity scope 级限流状态（从 extra 提取）
-	ScopeRateLimits map[string]ScopeRateLimitInfo `json:"scope_rate_limits,omitempty"`
-
 	TempUnschedulableUntil  *time.Time `json:"temp_unschedulable_until"`
 	TempUnschedulableReason string     `json:"temp_unschedulable_reason"`
 

backend/internal/handler/gateway_handler.go

@@ -13,6 +13,7 @@ import (
 	"time"
 
 	"github.com/Wei-Shaw/sub2api/internal/config"
+	"github.com/Wei-Shaw/sub2api/internal/domain"
 	"github.com/Wei-Shaw/sub2api/internal/pkg/antigravity"
 	"github.com/Wei-Shaw/sub2api/internal/pkg/claude"
 	"github.com/Wei-Shaw/sub2api/internal/pkg/ctxkey"
@@ -114,7 +115,7 @@ func (h *GatewayHandler) Messages(c *gin.Context) {
 
 	setOpsRequestContext(c, "", false, body)
 
-	parsedReq, err := service.ParseGatewayRequest(body)
+	parsedReq, err := service.ParseGatewayRequest(body, domain.PlatformAnthropic)
 	if err != nil {
 		h.errorResponse(c, http.StatusBadRequest, "invalid_request_error", "Failed to parse request body")
 		return
@@ -203,6 +204,11 @@ func (h *GatewayHandler) Messages(c *gin.Context) {
 	}
 
 	// 计算粘性会话hash
+	parsedReq.SessionContext = &service.SessionContext{
+		ClientIP:  ip.GetClientIP(c),
+		UserAgent: c.GetHeader("User-Agent"),
+		APIKeyID:  apiKey.ID,
+	}
 	sessionHash := h.gatewayService.GenerateSessionHash(parsedReq)
 
 	// 获取平台：优先使用强制平台（/antigravity 路由，中间件已设置 request.Context），否则使用分组平台
@@ -335,7 +341,7 @@ func (h *GatewayHandler) Messages(c *gin.Context) {
 				if errors.As(err, &failoverErr) {
 					failedAccountIDs[account.ID] = struct{}{}
 					lastFailoverErr = failoverErr
-					if failoverErr.ForceCacheBilling {
+					if needForceCacheBilling(hasBoundSession, failoverErr) {
 						forceCacheBilling = true
 					}
 					if switchCount >= maxAccountSwitches {
@@ -344,6 +350,11 @@ func (h *GatewayHandler) Messages(c *gin.Context) {
 					}
 					switchCount++
 					log.Printf("Account %d: upstream error %d, switching account %d/%d", account.ID, failoverErr.StatusCode, switchCount, maxAccountSwitches)
+					if account.Platform == service.PlatformAntigravity {
+						if !sleepFailoverDelay(c.Request.Context(), switchCount) {
+							return
+						}
+					}
 					continue
 				}
 				// 错误响应已在Forward中处理，这里只记录日志
@@ -530,7 +541,7 @@ func (h *GatewayHandler) Messages(c *gin.Context) {
 				if errors.As(err, &failoverErr) {
 					failedAccountIDs[account.ID] = struct{}{}
 					lastFailoverErr = failoverErr
-					if failoverErr.ForceCacheBilling {
+					if needForceCacheBilling(hasBoundSession, failoverErr) {
 						forceCacheBilling = true
 					}
 					if switchCount >= maxAccountSwitches {
@@ -539,6 +550,11 @@ func (h *GatewayHandler) Messages(c *gin.Context) {
 					}
 					switchCount++
 					log.Printf("Account %d: upstream error %d, switching account %d/%d", account.ID, failoverErr.StatusCode, switchCount, maxAccountSwitches)
+					if account.Platform == service.PlatformAntigravity {
+						if !sleepFailoverDelay(c.Request.Context(), switchCount) {
+							return
+						}
+					}
 					continue
 				}
 				// 错误响应已在Forward中处理，这里只记录日志
@@ -801,6 +817,27 @@ func (h *GatewayHandler) handleConcurrencyError(c *gin.Context, err error, slotT
 		fmt.Sprintf("Concurrency limit exceeded for %s, please retry later", slotType), streamStarted)
 }
 
+// needForceCacheBilling 判断 failover 时是否需要强制缓存计费
+// 粘性会话切换账号、或上游明确标记时，将 input_tokens 转为 cache_read 计费
+func needForceCacheBilling(hasBoundSession bool, failoverErr *service.UpstreamFailoverError) bool {
+	return hasBoundSession || (failoverErr != nil && failoverErr.ForceCacheBilling)
+}
+
+// sleepFailoverDelay 账号切换线性递增延时：第1次0s、第2次1s、第3次2s…
+// 返回 false 表示 context 已取消。
+func sleepFailoverDelay(ctx context.Context, switchCount int) bool {
+	delay := time.Duration(switchCount-1) * time.Second
+	if delay <= 0 {
+		return true
+	}
+	select {
+	case <-ctx.Done():
+		return false
+	case <-time.After(delay):
+		return true
+	}
+}
+
 func (h *GatewayHandler) handleFailoverExhausted(c *gin.Context, failoverErr *service.UpstreamFailoverError, platform string, streamStarted bool) {
 	statusCode := failoverErr.StatusCode
 	responseBody := failoverErr.ResponseBody
@@ -934,7 +971,7 @@ func (h *GatewayHandler) CountTokens(c *gin.Context) {
 
 	setOpsRequestContext(c, "", false, body)
 
-	parsedReq, err := service.ParseGatewayRequest(body)
+	parsedReq, err := service.ParseGatewayRequest(body, domain.PlatformAnthropic)
 	if err != nil {
 		h.errorResponse(c, http.StatusBadRequest, "invalid_request_error", "Failed to parse request body")
 		return
@@ -962,6 +999,11 @@ func (h *GatewayHandler) CountTokens(c *gin.Context) {
 	}
 
 	// 计算粘性会话 hash
+	parsedReq.SessionContext = &service.SessionContext{
+		ClientIP:  ip.GetClientIP(c),
+		UserAgent: c.GetHeader("User-Agent"),
+		APIKeyID:  apiKey.ID,
+	}
 	sessionHash := h.gatewayService.GenerateSessionHash(parsedReq)
 
 	// 选择支持该模型的账号

backend/internal/handler/gemini_v1beta_handler.go

@@ -14,6 +14,7 @@ import (
 	"strings"
 	"time"
 
+	"github.com/Wei-Shaw/sub2api/internal/domain"
 	"github.com/Wei-Shaw/sub2api/internal/pkg/antigravity"
 	"github.com/Wei-Shaw/sub2api/internal/pkg/ctxkey"
 	"github.com/Wei-Shaw/sub2api/internal/pkg/gemini"
@@ -30,13 +31,6 @@ import (
 // 匹配格式: /Users/xxx/.gemini/tmp/[64位十六进制哈希]
 var geminiCLITmpDirRegex = regexp.MustCompile(`/\.gemini/tmp/([A-Fa-f0-9]{64})`)
 
-func isGeminiCLIRequest(c *gin.Context, body []byte) bool {
-	if strings.TrimSpace(c.GetHeader("x-gemini-api-privileged-user-id")) != "" {
-		return true
-	}
-	return geminiCLITmpDirRegex.Match(body)
-}
-
 // GeminiV1BetaListModels proxies:
 // GET /v1beta/models
 func (h *GatewayHandler) GeminiV1BetaListModels(c *gin.Context) {
@@ -239,7 +233,14 @@ func (h *GatewayHandler) GeminiV1BetaModels(c *gin.Context) {
 	sessionHash := extractGeminiCLISessionHash(c, body)
 	if sessionHash == "" {
 		// Fallback: 使用通用的会话哈希生成逻辑（适用于其他客户端）
-		parsedReq, _ := service.ParseGatewayRequest(body)
+		parsedReq, _ := service.ParseGatewayRequest(body, domain.PlatformGemini)
+		if parsedReq != nil {
+			parsedReq.SessionContext = &service.SessionContext{
+				ClientIP:  ip.GetClientIP(c),
+				UserAgent: c.GetHeader("User-Agent"),
+				APIKeyID:  apiKey.ID,
+			}
+		}
 		sessionHash = h.gatewayService.GenerateSessionHash(parsedReq)
 	}
 	sessionKey := sessionHash
@@ -258,6 +259,7 @@ func (h *GatewayHandler) GeminiV1BetaModels(c *gin.Context) {
 	var geminiDigestChain string
 	var geminiPrefixHash string
 	var geminiSessionUUID string
+	var matchedDigestChain string
 	useDigestFallback := sessionBoundAccountID == 0
 
 	if useDigestFallback {
@@ -284,13 +286,14 @@ func (h *GatewayHandler) GeminiV1BetaModels(c *gin.Context) {
 				)
 
 				// 查找会话
-				foundUUID, foundAccountID, found := h.gatewayService.FindGeminiSession(
+				foundUUID, foundAccountID, foundMatchedChain, found := h.gatewayService.FindGeminiSession(
 					c.Request.Context(),
 					derefGroupID(apiKey.GroupID),
 					geminiPrefixHash,
 					geminiDigestChain,
 				)
 				if found {
+					matchedDigestChain = foundMatchedChain
 					sessionBoundAccountID = foundAccountID
 					geminiSessionUUID = foundUUID
 					log.Printf("[Gemini] Digest fallback matched: uuid=%s, accountID=%d, chain=%s",
@@ -316,7 +319,6 @@ func (h *GatewayHandler) GeminiV1BetaModels(c *gin.Context) {
 
 	// 判断是否真的绑定了粘性会话：有 sessionKey 且已经绑定到某个账号
 	hasBoundSession := sessionKey != "" && sessionBoundAccountID > 0
-	isCLI := isGeminiCLIRequest(c, body)
 	cleanedForUnknownBinding := false
 
 	maxAccountSwitches := h.maxAccountSwitchesGemini
@@ -344,10 +346,10 @@ func (h *GatewayHandler) GeminiV1BetaModels(c *gin.Context) {
 			log.Printf("[Gemini] Sticky session account switched: %d -> %d, cleaning thoughtSignature", sessionBoundAccountID, account.ID)
 			body = service.CleanGeminiNativeThoughtSignatures(body)
 			sessionBoundAccountID = account.ID
-		} else if sessionKey != "" && sessionBoundAccountID == 0 && isCLI && !cleanedForUnknownBinding && bytes.Contains(body, []byte(`"thoughtSignature"`)) {
-			// 无缓存绑定但请求里已有 thoughtSignature：常见于缓存丢失/TTL 过期后，CLI 继续携带旧签名。
+		} else if sessionKey != "" && sessionBoundAccountID == 0 && !cleanedForUnknownBinding && bytes.Contains(body, []byte(`"thoughtSignature"`)) {
+			// 无缓存绑定但请求里已有 thoughtSignature：常见于缓存丢失/TTL 过期后，客户端继续携带旧签名。
 			// 为避免第一次转发就 400，这里做一次确定性清理，让新账号重新生成签名链路。
-			log.Printf("[Gemini] Sticky session binding missing for CLI request, cleaning thoughtSignature proactively")
+			log.Printf("[Gemini] Sticky session binding missing, cleaning thoughtSignature proactively")
 			body = service.CleanGeminiNativeThoughtSignatures(body)
 			cleanedForUnknownBinding = true
 			sessionBoundAccountID = account.ID
@@ -422,7 +424,7 @@ func (h *GatewayHandler) GeminiV1BetaModels(c *gin.Context) {
 			var failoverErr *service.UpstreamFailoverError
 			if errors.As(err, &failoverErr) {
 				failedAccountIDs[account.ID] = struct{}{}
-				if failoverErr.ForceCacheBilling {
+				if needForceCacheBilling(hasBoundSession, failoverErr) {
 					forceCacheBilling = true
 				}
 				if switchCount >= maxAccountSwitches {
@@ -433,6 +435,11 @@ func (h *GatewayHandler) GeminiV1BetaModels(c *gin.Context) {
 				lastFailoverErr = failoverErr
 				switchCount++
 				log.Printf("Gemini account %d: upstream error %d, switching account %d/%d", account.ID, failoverErr.StatusCode, switchCount, maxAccountSwitches)
+				if account.Platform == service.PlatformAntigravity {
+					if !sleepFailoverDelay(c.Request.Context(), switchCount) {
+						return
+					}
+				}
 				continue
 			}
 			// ForwardNative already wrote the response
@@ -453,6 +460,7 @@ func (h *GatewayHandler) GeminiV1BetaModels(c *gin.Context) {
 				geminiDigestChain,
 				geminiSessionUUID,
 				account.ID,
+				matchedDigestChain,
 			); err != nil {
 				log.Printf("[Gemini] Failed to save digest session: %v", err)
 			}