fix: finalize inbound contexts

src/media-understanding/apply.test.ts

@@ -81,6 +81,8 @@ describe("applyMediaUnderstanding", () => {
     expect(ctx.Body).toBe("[Audio]\nTranscript:\ntranscribed text");
     expect(ctx.CommandBody).toBe("transcribed text");
     expect(ctx.RawBody).toBe("transcribed text");
+    expect(ctx.BodyForAgent).toBe(ctx.Body);
+    expect(ctx.BodyForCommands).toBe("transcribed text");
   });
 
   it("handles URL-only attachments for audio transcription", async () => {
@@ -254,6 +256,8 @@ describe("applyMediaUnderstanding", () => {
     expect(ctx.Body).toBe("[Image]\nUser text:\nshow Dom\nDescription:\nimage description");
     expect(ctx.CommandBody).toBe("show Dom");
     expect(ctx.RawBody).toBe("show Dom");
+    expect(ctx.BodyForAgent).toBe(ctx.Body);
+    expect(ctx.BodyForCommands).toBe("show Dom");
   });
 
   it("uses shared media models list when capability config is missing", async () => {

src/media-understanding/apply.ts

@@ -1,7 +1,10 @@
 import type { ClawdbotConfig } from "../config/config.js";
 import type { MsgContext } from "../auto-reply/templating.js";
 import { applyTemplate } from "../auto-reply/templating.js";
+import { finalizeInboundContext } from "../auto-reply/reply/inbound-context.js";
 import { resolveApiKeyForProvider } from "../agents/model-auth.js";
+import { ensureClawdbotModelsJson } from "../agents/models-config.js";
+import { minimaxUnderstandImage } from "../agents/minimax-vlm.js";
 import { logVerbose, shouldLogVerbose } from "../globals.js";
 import { runExec } from "../process/exec.js";
 import type {
@@ -449,6 +452,7 @@ export async function applyMediaUnderstanding(params: {
         ctx.RawBody = originalUserText;
       }
       ctx.MediaUnderstanding = [...(ctx.MediaUnderstanding ?? []), ...outputs];
+      finalizeInboundContext(ctx, { forceBodyForAgent: true, forceBodyForCommands: true });
     }
 
     return {