feat(annotate): use cached HF token from huggingface-cli login

Fall back to huggingface_hub.get_token() when HF_TOKEN/HUGGINGFACE_API_KEY
env vars aren't set. That picks up the token cached by
'huggingface-cli login' so users don't need to export it on every shell.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/lerobot/annotations/steerable_pipeline/vlm_client.py

@@ -283,10 +283,17 @@ def _make_openai_client(config: VlmConfig) -> VlmClient:
     if config.use_hf_inference_providers:
         api_base = "https://router.huggingface.co/v1"
         token = os.environ.get("HF_TOKEN") or os.environ.get("HUGGINGFACE_API_KEY") or ""
+        if not token:
+            try:
+                from huggingface_hub import get_token  # noqa: PLC0415
+
+                token = get_token() or ""
+            except Exception:  # noqa: BLE001
+                token = ""
         if not token:
             raise RuntimeError(
-                "use_hf_inference_providers=True requires HF_TOKEN (or "
-                "HUGGINGFACE_API_KEY) in the environment."
+                "use_hf_inference_providers=True needs an HF token. Either set "
+                "HF_TOKEN in the environment, or run `huggingface-cli login` once."
             )
         api_key = token
         auto_serve = False