Patch _get_tasks to use PAT/refresh-token flow (legacy token auth disabled by default in modern LS)

model.py

@@ -1,8 +1,8 @@
 import os
 import pathlib
 import re
-import label_studio_sdk
 import logging
+import requests
 
 from typing import List, Dict, Optional
 from label_studio_ml.model import LabelStudioMLBase
@@ -106,10 +106,30 @@ class HuggingFaceNER(LabelStudioMLBase):
         return ModelResponse(predictions=predictions, model_version=self.get('model_version'))
 
     def _get_tasks(self, project_id):
-        # download annotated tasks from Label Studio
-        ls = label_studio_sdk.Client(self.LABEL_STUDIO_HOST, self.LABEL_STUDIO_API_KEY)
-        project = ls.get_project(id=project_id)
-        tasks = project.get_labeled_tasks()
+        # Download annotated tasks from Label Studio.
+        # (HF Spaces patch) Modern LS instances disable legacy-token auth, which
+        # breaks the upstream `label_studio_sdk.Client(host, api_key)` path.
+        # LABEL_STUDIO_API_KEY is treated as a Personal Access Token (refresh
+        # token); we exchange it for a short-lived access token, then call the
+        # LS REST API directly. Filters to tasks with at least one annotation
+        # (legacy `project.get_labeled_tasks()` semantics).
+        refresh_resp = requests.post(
+            f"{self.LABEL_STUDIO_HOST}/api/token/refresh/",
+            json={"refresh": self.LABEL_STUDIO_API_KEY},
+            timeout=30,
+        )
+        refresh_resp.raise_for_status()
+        access = refresh_resp.json()["access"]
+        headers = {"Authorization": f"Bearer {access}"}
+        tasks: List[Dict] = []
+        url = f"{self.LABEL_STUDIO_HOST}/api/tasks/?project={project_id}&page_size=200&fields=all"
+        while url:
+            r = requests.get(url, headers=headers, timeout=60)
+            r.raise_for_status()
+            payload = r.json()
+            page = payload if isinstance(payload, list) else payload.get("tasks", [])
+            tasks.extend(t for t in page if t.get("annotations"))
+            url = payload.get("next") if isinstance(payload, dict) else None
         return tasks
 
     def tokenize_and_align_labels(self, examples, tokenizer):