Update status endpoint path in documentation (#2920)

The defined path, llm/v1/status is incorrect and will return a 404

```bash
 curl http://localhost:8080/llm/v1/status -i
HTTP/1.1 404 NOT FOUND
```

The correct path should simply be `/status`

```bash
$ curl http://localhost:8080/status -i
HTTP/1.1 200 OK
Server: gunicorn
Date: Wed, 17 Sep 2025 19:25:25 GMT
Connection: close
Content-Type: application/json
Content-Length: 102

{"status":"ok","model_name":"microsoft/llmlingua-2-xlm-roberta-large-meetingbank","device_map":"cpu"}
```

Author: dascole

app/_kong_plugins/ai-prompt-compressor/index.md

@@ -136,7 +136,7 @@ The compressor service exposes both REST and JSON-RPC endpoints. You can use the
 
 * **POST `/llm/v1/compressPrompt`**: Compresses a prompt using either a compression ratio or a target token count. Supports selective compression via `<LLMLINGUA>` tags.
 
-* **GET `/llm/v1/status`**: Returns information about the currently loaded LLMLingua model and device settings (for example, CPU or GPU).
+* **GET `/status`**: Returns information about the currently loaded LLMLingua model and device settings (for example, CPU or GPU).
 
 * **POST `/`**: JSON-RPC endpoint that supports the `llm.v1.compressPrompt` method. Use this to invoke compression programmatically over JSON-RPC.
 
@@ -212,4 +212,4 @@ sequenceDiagram
 {% endmermaid %}
 <!-- vale on -->
 
-The AI Prompt Compressor plugin applies structured compression to preserve essential context of prompts sent by users, rather than trimming prompts arbitrarily or risking token overflows. This ensures the LLM receives a well-formed, focused prompt keeping token usage under control.
+The AI Prompt Compressor plugin applies structured compression to preserve essential context of prompts sent by users, rather than trimming prompts arbitrarily or risking token overflows. This ensures the LLM receives a well-formed, focused prompt keeping token usage under control.