fix(gateway): support image_url in OpenAI chat completions (#34068)

* fix(gateway): parse image_url in openai chat completions

* test(gateway): cover openai chat completions image_url flows

* docs(changelog): note openai image_url chat completions fix (#17685)

* fix(gateway): harden openai image_url parsing and limits

* test(gateway): add openai image_url regression coverage

* docs(changelog): expand #17685 openai chat completions note

* Gateway: make OpenAI image_url URL fetch opt-in and configurable

* Diagnostics: redact image base64 payload data in trace logs

* Changelog: note OpenAI image_url hardening follow-ups

* Gateway: enforce OpenAI image_url total budget incrementally

* Gateway: scope OpenAI image_url extraction to the active turn

* Update CHANGELOG.md

src/gateway/server-http.ts

@@ -509,6 +509,7 @@ export function createGatewayHttpServer(opts: {
   controlUiBasePath: string;
   controlUiRoot?: ControlUiRootState;
   openAiChatCompletionsEnabled: boolean;
+  openAiChatCompletionsConfig?: import("../config/types.gateway.js").GatewayHttpChatCompletionsConfig;
   openResponsesEnabled: boolean;
   openResponsesConfig?: import("../config/types.gateway.js").GatewayHttpResponsesConfig;
   strictTransportSecurityHeader?: string;
@@ -527,6 +528,7 @@ export function createGatewayHttpServer(opts: {
     controlUiBasePath,
     controlUiRoot,
     openAiChatCompletionsEnabled,
+    openAiChatCompletionsConfig,
     openResponsesEnabled,
     openResponsesConfig,
     strictTransportSecurityHeader,
@@ -610,6 +612,7 @@ export function createGatewayHttpServer(opts: {
           run: () =>
             handleOpenAiHttpRequest(req, res, {
               auth: resolvedAuth,
+              config: openAiChatCompletionsConfig,
               trustedProxies,
               allowRealIpFallback,
               rateLimiter,