Refactor

open-sse/handlers/chatCore.js

@@ -21,6 +21,9 @@ import { detectClientTool, isNativePassthrough } from "../utils/clientDetector.j
 import { dedupeTools } from "../utils/toolDeduper.js";
 import { injectCaveman } from "../rtk/caveman.js";
 import { compressMessages, formatRtkLog } from "../rtk/index.js";
+import { getCapabilitiesForModel } from "../providers/capabilities.js";
+import { stripUnsupportedModalities } from "../translator/concerns/modality.js";
+import { prefetchRemoteImages } from "../translator/concerns/prefetch.js";
 
 /**
  * Core chat handler - shared between SSE and Worker
@@ -91,6 +94,19 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
   // Expose raw client headers to translators/executors for session-id resolution
   if (credentials) credentials.rawHeaders = clientRawRequest?.headers || {};
 
+  // Auto-strip media blocks the model can't read (vision/audio/pdf) before translation.
+  if (!passthrough) {
+    const caps = getCapabilitiesForModel(provider, model);
+    if (stripUnsupportedModalities(body, sourceFormat, caps)) {
+      log?.debug?.("MODALITY", `stripped unsupported media for ${provider}/${model}`);
+    }
+    // Convert remote image URLs to base64 for targets that can't fetch URLs.
+    try {
+      const n = await prefetchRemoteImages(body, sourceFormat, targetFormat, { signal: undefined });
+      if (n > 0) log?.debug?.("MODALITY", `prefetched ${n} remote image(s) for ${targetFormat}`);
+    } catch (e) { log?.warn?.("MODALITY", `image prefetch failed: ${e.message}`); }
+  }
+
   let translatedBody;
   let toolNameMap;
   if (passthrough) {