[wrangler] `wrangler ai finetune` has no delete or single-read endpoint/command

### What versions & operating system are you using?

```
System:
OS: macOS 15.7.1
CPU: (12) arm64 Apple M2 Pro
Memory: 131.14 MB / 16.00 GB
Shell: 5.9 - /bin/zsh
Binaries:
Node: 24.11.0 - /Users/gamer/.nvm/versions/node/v24.11.0/bin/node
npm: 11.6.1 - /Users/gamer/.nvm/versions/node/v24.11.0/bin/npm
pnpm: 10.33.0 - /opt/homebrew/bin/pnpm
bun: 1.3.14 - /Users/gamer/.bun/bin/bun
Deno: 2.8.1 - /opt/homebrew/bin/deno
npmPackages:
@cloudflare/workers-types: ^4.20260626.1 => 4.20260626.1
wrangler: ^4.105.0 => 4.105.0
```

### Please provide a link to a minimal reproduction

N/A

### Describe the Bug

`wrangler ai finetune` has no single read or delete command/endpoint for LoRA adapters.

```
Interact with finetune files

COMMANDS
wrangler ai finetune list List your finetune files
wrangler ai finetune create Create finetune and upload assets

GLOBAL FLAGS
-c, --config Path to Wrangler configuration file [string]
--cwd Run as if Wrangler was started in the specified directory instead of the current working directory [string]
-e, --env Environment to use for operations, and for selecting .env and .dev.vars files [string]
--env-file Path to an .env file to load - can be specified multiple times - values from earlier files are overridden by values in later files [array]
-h, --help Show help [boolean]
--install-skills Install Cloudflare skills for detected AI coding agents before running the command [boolean] [default: false]
-v, --version Show version number [boolean
```

I cannot delete any singular LoRA adapter if I choose to not use it, or I cannot retrieve any singular LoRA adapter I have already uploaded. The lack of REST endpoints / wrangler commands available makes development extremely difficult when trying to test out different LoRA adapters. Curious if either is planned.

### Please provide any relevant error logs

_No response_

Empieza por localizar los puntos de entrada existentes de los comandos `wrangler ai finetune list` y `create`, así como las operaciones REST que utilizan. Confirma la forma de la API para la lectura y eliminación de un solo adaptador y define la finalización como comandos de lectura y eliminación funcionales, con cobertura de los casos relevantes de éxito y error.

Escrito por el modelo de indexación a partir del texto del issue.