fix(gateway): return 404 instead of fake 200 for unsupported count_tokens endpoint

PR #635 returned HTTP 200 with {"input_tokens": 0} when upstream doesn't
support count_tokens (404). This caused Claude Code CLI to trust the zero
value, believing context uses 0 tokens, so auto-compression never triggers.

Fix: return 404 with proper error body so CLI falls back to its local
tokenizer for accurate estimation. Return nil (not error) to avoid
polluting ops error metrics with expected 404s.

Affected paths:
- Passthrough APIKey accounts: upstream 404 now passed through as 404
- Antigravity accounts: same fix (was also returning fake 200)

backend/internal/service/gateway_service.go

@@ -6015,9 +6015,10 @@ func (s *GatewayService) ForwardCountTokens(ctx context.Context, c *gin.Context,
 		body, reqModel = normalizeClaudeOAuthRequestBody(body, reqModel, normalizeOpts)
 	}
 
-	// Antigravity 账户不支持 count_tokens 转发，直接返回空值
+	// Antigravity 账户不支持 count_tokens，返回 404 让客户端 fallback 到本地估算。
+	// 返回 nil 避免 handler 层记录为错误，也不设置 ops 上游错误上下文。
 	if account.Platform == PlatformAntigravity {
-		c.JSON(http.StatusOK, gin.H{"input_tokens": 0})
+		s.countTokensError(c, http.StatusNotFound, "not_found_error", "count_tokens endpoint is not supported for this platform")
 		return nil
 	}
 
@@ -6222,12 +6223,13 @@ func (s *GatewayService) forwardCountTokensAnthropicAPIKeyPassthrough(ctx contex
 		upstreamMsg := strings.TrimSpace(extractUpstreamErrorMessage(respBody))
 		upstreamMsg = sanitizeUpstreamErrorMessage(upstreamMsg)
 
-		// 中转站不支持 count_tokens 端点时（404），降级返回空值，客户端会 fallback 到本地估算。
+		// 中转站不支持 count_tokens 端点时（404），透传 404 让客户端 fallback 到本地估算。
+		// 返回 nil 避免 handler 层记录为错误，也不设置 ops 上游错误上下文。
 		if resp.StatusCode == http.StatusNotFound {
 			logger.LegacyPrintf("service.gateway",
-				"[count_tokens] Upstream does not support count_tokens (404), returning fallback: account=%d name=%s msg=%s",
+				"[count_tokens] Upstream does not support count_tokens (404), passing through: account=%d name=%s msg=%s",
 				account.ID, account.Name, truncateString(upstreamMsg, 512))
-			c.JSON(http.StatusOK, gin.H{"input_tokens": 0})
+			s.countTokensError(c, http.StatusNotFound, "not_found_error", "count_tokens endpoint is not supported by upstream")
 			return nil
 		}