fix(systemone): route NER models to the NER path and refuse decision models on permute and separate

vllm_decide refuses NER architectures and the NER entry point refuses decision
architectures, so each model kind 500ed on half of the routes. A token_classify
model now goes to the NER path on /v1/systemone, and /permute and /separate
return 400 for decision models. Docs and instructions state which kind serves
which route.

Assisted-by: Claude Code:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

docs/content/features/vllm-cpp.md

@@ -174,9 +174,11 @@ for the request shape, the models you can install and the access rules.
 | `/v1/systemone/permute` | POST | Re-run one choice question under n_perm option orders |
 | `/v1/systemone/separate` | POST | Answer each question in its own pass (N passes) |
 
-The GLiNER2.5 zero-shot NER model (`token_classify`) also serves these
-endpoints. It derives its NER labels from the question definitions, so no
-`ner_labels` configuration is needed.
+The GLiNER2.5 zero-shot NER model (`token_classify`) also serves
+`/v1/systemone`, through the NER path, and it is the model to use for
+`/v1/systemone/permute` and `/v1/systemone/separate`, which decision models
+refuse with a `400`. It derives its NER labels from the question definitions, so
+no `ner_labels` configuration is needed.
 
 ## Beyond text generation