fix: address max-effort review findings

- clamp LLM-derived page indices in _get_text_of_pages and
  get_text_of_pdf_pages_with_labels; dedupe get_text_of_pdf_pages
- guard _normalize_tree and folders/documents iterations against
  explicit nulls in cloud API responses
- coerce cloud OCR page numbers to int before filtering in
  get_page_content
- folder cache: raise on missing folder id instead of caching None;
  stop caching name-not-found so later lookups can succeed
- defang doc_id in agent doc-context prompt
- append api-key hint to 401 errors (request, legacy and streaming
  paths)
- remove stale legacy JSON workspace sample data unreadable by the
  SQLite storage

pageindex/errors.py

@@ -55,3 +55,10 @@ class FileTypeError(PageIndexError, ValueError):
     instead of) a bare ValueError one.
     """
     pass
+
+
+AUTH_HINT = (
+    "api_key must be a PageIndex cloud API key (https://dash.pageindex.ai/api-keys). "
+    "For local mode, omit api_key and set your LLM provider key "
+    "(e.g. OPENAI_API_KEY) in the environment."
+)