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/coding-agent/src/core/sdk.ts

@@ -589,7 +589,7 @@ export async function createAgentSession(options: CreateAgentSessionOptions = {}
 			tools: allToolsArray,
 		},
 		messageTransformer,
-		contextTransform: hookRunner
+		preprocessor: hookRunner
 			? async (messages) => {
 					return hookRunner.emitContext(messages);
 				}