fix(infra): single-read file_read (no double disk I/O for hash) + bail health poll on dead process

infrastructure/inference/llama_cpp/src/main/kotlin/com/correx/infrastructure/inference/llama/cpp/DefaultModelManager.kt

@@ -151,10 +151,12 @@ class DefaultModelManager(
         currentDescriptor = null
     }
 
-    @Suppress("UnusedParameter")
     private suspend fun waitForHealthy(process: LlamaProcess): Boolean {
         val endTime = Clock.System.now().toEpochMilliseconds() + healthTimeoutMs
         while (Clock.System.now().toEpochMilliseconds() < endTime) {
+            // A crashed process (bad --model, port clash) never gets healthy; polling the full
+            // timeout is pure dead time. Bail as soon as it's gone.
+            if (!process.isAlive) return false
             try {
                 val response = httpClient.get("http://$host:$port/health").body<String>()
                 if (response.contains("\"status\":\"healthy\"") || response.contains("ok")) {