fix(coding-agent): forward images through steer/followUp during streaming

prompt() computed currentImages but never passed them to _queueSteer()
or _queueFollowUp() in the streaming branch. Both methods only accepted
text and built content as [{ type: 'text', text }], dropping images.

- _queueSteer/_queueFollowUp now accept optional ImageContent[]
- streaming branch in prompt() passes currentImages through
- public steer()/followUp() accept and forward optional images
- RPC types, handler, and client updated for steer/follow_up images
- rpc.md: document images on steer/follow_up, fix ImageContent examples

packages/coding-agent/src/modes/rpc/rpc-mode.ts

@@ -328,12 +328,12 @@ export async function runRpcMode(session: AgentSession): Promise<never> {
 			}
 
 			case "steer": {
-				await session.steer(command.message);
+				await session.steer(command.message, command.images);
 				return success(id, "steer");
 			}
 
 			case "follow_up": {
-				await session.followUp(command.message);
+				await session.followUp(command.message, command.images);
 				return success(id, "follow_up");
 			}