fix(llm): auto-shape multimodal mediaPath messages in chat template (#1089)

## Description

`LLMController.generate()` collected `imagePaths` from messages with a
`mediaPath` set, but never transformed their `content` into the
`[{type:'image'}, {type:'text', text}]` form that the chat template
needs to emit the `<image>` placeholder. Calling `generate()` directly
with a vision-capable model (e.g. LFM2-VL) thus threw `"More images
paths provided than '<image>' placeholders in prompt"` from native, even
though `sendMessage()` worked because it built its own
`historyForTemplate` that did the transformation.

This PR moves the transformation into `applyChatTemplate` so both call
sites (`generate` and `sendMessage`) get the correct behavior, and
removes the now-redundant `historyForTemplate` block from `sendMessage`.
The public `Message.content` type stays `string` — external callers
always pass plain strings; the controller handles the structured array
form internally.

The helper is idempotent: messages whose `content` is already an array
(e.g. callers who pre-shaped it as a workaround) are passed through
unchanged.

### Introduces a breaking change?

- [ ] Yes
- [x] No

Public types are unchanged. `sendMessage` produces an identical rendered
chat-template string (the transformation just happens one step later in
the pipeline; token count and rendered output are byte-identical).
`generate` only changes behavior in cases that previously threw — pure
bug fix.

### Type of change

- [x] Bug fix (change which fixes an issue)
- [ ] New feature (change which adds functionality)
- [ ] Documentation update (improves or adds clarity to existing
documentation)
- [ ] Other (chores, tests, code style improvements etc.)

### Tested on

- [ ] iOS
- [ ] Android

The original bug was reproduced on a vision-capable model
(LFM2-VL-1.6B-quantized) on Android while building a downstream consumer
app. Re-verification of the fix on a real device is recommended before
merge — see Testing instructions below. ~I have not personally re-run
the failing scenario after the fix.~

### Testing instructions

To reproduce the original bug (without this PR):

```ts
import { LLMModule, LFM2_VL_1_6B_QUANTIZED } from 'react-native-executorch';

const llm = await LLMModule.fromModelName(LFM2_VL_1_6B_QUANTIZED);
await llm.generate([
  { role: 'user', content: 'Describe this image.', mediaPath: 'file:///path/to/image.jpg' },
]);
// Throws: "More images paths provided than '<image>' placeholders in prompt"
```

With this PR applied, the same call should succeed and return the
model's description.

Regression check: a vision-capable `sendMessage(text, { imagePath })`
flow should continue producing identical output.

### Screenshots

N/A (controller change, no UI).

### Related issues

Addresses items 1 and 2 of #1086. With item 1 fixed, item 2's
`Message.content` type mismatch no longer surfaces in practice because
external callers never need to construct the array form themselves (the
`as unknown as string` workaround that motivated #2 becomes
unnecessary).

### Checklist

- [ ] I have performed a self-review of my code
- [ ] I have commented my code, particularly in hard-to-understand areas
- [ ] I have updated the documentation accordingly
- [ ] My changes generate no new warnings

### Additional notes

The `messagesForChatTemplate` helper lives at module scope rather than
as a static class method because it doesn't depend on controller state.
Internal `any[]` return is a deliberate concession to the dynamic shape
the chat-template engine accepts; the public `Message[]` input/output
contract stays well-typed.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: msluszniak

packages/react-native-executorch/src/controllers/LLMController.ts

@@ -354,18 +354,6 @@ export class LLMController {
     const updatedHistory = [...this._messageHistory, newMessage];
     this.messageHistoryCallback(updatedHistory);
 
-    const historyForTemplate = updatedHistory.map((m) =>
-      m.mediaPath
-        ? {
-            ...m,
-            content: [
-              { type: 'image' },
-              { type: 'text', text: m.content },
-            ] as any,
-          }
-        : m
-    );
-
     const visualTokenCount = this.nativeModule.getVisualTokenCount();
     const countTokensCallback = (messages: Message[]) => {
       const rendered = this.applyChatTemplate(
@@ -383,7 +371,7 @@ export class LLMController {
     const messageHistoryWithPrompt =
       this.chatConfig.contextStrategy.buildContext(
         this.chatConfig.systemPrompt,
-        historyForTemplate,
+        updatedHistory,
         maxContextLength,
         countTokensCallback
       );
@@ -448,7 +436,7 @@ export class LLMController {
     );
 
     const result = template.render({
-      messages,
+      messages: messagesForChatTemplate(messages),
       tools,
       ...templateFlags,
       ...specialTokens,
@@ -468,3 +456,24 @@ export class LLMController {
 function normalizeImagePath(path: string): string {
   return path.startsWith('file://') ? path : `file://${path}`;
 }
+
+/**
+ * Multimodal chat templates expect message content for image-bearing turns
+ * to be an array of content parts with an `image` part as a placeholder.
+ * Callers of `LLMController.generate` and `LLMController.sendMessage` pass
+ * messages with a plain string `content` plus an optional `mediaPath`; this
+ * helper rewrites them into the structured form that the template engine
+ * understands.
+ * @param messages - Messages to prepare for the chat template engine.
+ * @returns Messages with image-bearing turns rewritten to structured content.
+ */
+function messagesForChatTemplate(messages: Message[]): any[] {
+  return messages.map((m) =>
+    m.mediaPath && typeof m.content === 'string'
+      ? {
+          ...m,
+          content: [{ type: 'image' }, { type: 'text', text: m.content }],
+        }
+      : m
+  );
+}