fix: wire agents.defaults.imageModel into media understanding auto-discovery

resolveAutoEntries only checked a hardcoded list of providers
(openai, anthropic, google, minimax) when looking for an image model.
agents.defaults.imageModel was never consulted by the media understanding
pipeline — it was only wired into the explicit `image` tool.

Add resolveImageModelFromAgentDefaults that reads the imageModel config
(primary + fallbacks) and inserts it into the auto-discovery chain before
the hardcoded provider list.  runProviderEntry already falls back to
describeImageWithModel (via pi-ai) for providers not in the media
understanding registry, so no additional provider registration is needed.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

src/media-understanding/runner.ts

@@ -479,6 +479,44 @@ async function resolveKeyEntry(params: {
   return null;
 }
 
+function resolveImageModelFromAgentDefaults(cfg: OpenClawConfig): MediaUnderstandingModelConfig[] {
+  const imageModel = cfg.agents?.defaults?.imageModel as
+    | { primary?: string; fallbacks?: string[] }
+    | string
+    | undefined;
+  if (!imageModel) {
+    return [];
+  }
+  const refs: string[] = [];
+  if (typeof imageModel === "string") {
+    if (imageModel.trim()) {
+      refs.push(imageModel.trim());
+    }
+  } else {
+    if (imageModel.primary?.trim()) {
+      refs.push(imageModel.primary.trim());
+    }
+    for (const fb of imageModel.fallbacks ?? []) {
+      if (fb?.trim()) {
+        refs.push(fb.trim());
+      }
+    }
+  }
+  const entries: MediaUnderstandingModelConfig[] = [];
+  for (const ref of refs) {
+    const slashIdx = ref.indexOf("/");
+    if (slashIdx <= 0 || slashIdx >= ref.length - 1) {
+      continue;
+    }
+    entries.push({
+      type: "provider",
+      provider: ref.slice(0, slashIdx),
+      model: ref.slice(slashIdx + 1),
+    });
+  }
+  return entries;
+}
+
 async function resolveAutoEntries(params: {
   cfg: OpenClawConfig;
   agentDir?: string;
@@ -496,6 +534,12 @@ async function resolveAutoEntries(params: {
       return [localAudio];
     }
   }
+  if (params.capability === "image") {
+    const imageModelEntries = resolveImageModelFromAgentDefaults(params.cfg);
+    if (imageModelEntries.length > 0) {
+      return imageModelEntries;
+    }
+  }
   const gemini = await resolveGeminiCliEntry(params.capability);
   if (gemini) {
     return [gemini];