Wire context event to preprocessor for per-LLM-call execution

- Change from contextTransform (runs once at agent start) to preprocessor
- preprocessor runs before EACH LLM call inside the agent loop
- ContextEvent now uses Message[] (pi-ai format) instead of AppMessage[]
- Deep copy handled by pi-ai preprocessor, not Agent

This enables:
- Pruning rules applied on every turn (not just agent start)
- /prune during long agent loop takes effect immediately
- Compaction can use same transforms (future work)

packages/agent/src/transports/ProviderTransport.ts

@@ -60,6 +60,7 @@ export class ProviderTransport implements AgentTransport {
 			// Resolve API key per assistant response (important for expiring OAuth tokens)
 			getApiKey: this.options.getApiKey,
 			getQueuedMessages: cfg.getQueuedMessages,
+			preprocessor: cfg.preprocessor,
 		};
 	}