feat: add multimodal media pipeline for image support across all providers and channels

Widen Message.content from string to string | MessageContentPart[] to support
multimodal content. Add Attachment type to channel layer, media conversion
utilities, and image extraction to all channel adapters (Telegram, Discord,
Slack, WhatsApp). Update all model clients (Anthropic, OpenAI, Gemini, Bedrock)
to convert structured content to provider-specific formats. Fix downstream
consumers (tokens, compaction, TUI, local models) to handle the widened type
via getMessageText() helper.

src/backends/native/agent.ts

@@ -5,6 +5,8 @@ import type { ToolRegistry } from '../../tools/registry.js';
 import type { ToolExecutor } from '../../tools/executor.js';
 import type { ToolResult } from '../../tools/types.js';
 import type { ToolPolicyContext } from '../../tools/policy.js';
+import type { Attachment } from '../../channels/types.js';
+import { buildUserMessage, getMessageText } from '../../models/media.js';
 
 export interface ToolUseEvent {
   type: 'start' | 'end';
@@ -61,8 +63,8 @@ export class NativeAgent {
     return this.session?.getHistory() ?? [...this.inMemoryHistory];
   }
 
-  async process(userMessage: string): Promise<string> {
-    const userMsg: Message = { role: 'user', content: userMessage };
+  async process(userMessage: string, attachments?: Attachment[]): Promise<string> {
+    const userMsg = buildUserMessage(userMessage, attachments);
 
     if (this.session) {
       this.session.addMessage(userMsg);