fix: exact md page selection + restore CHATGPT_API_KEY alias

Address PR #272 review:

- get_md_page_content / retrieve._get_md_page_content returned every node
  whose line_num fell in [min(pages), max(pages)], so a non-contiguous spec
  like "5,100" over-fetched everything in between. Match the exact requested
  line numbers instead, mirroring the PDF path. (Same bug as #280.)
- Restore the CHATGPT_API_KEY -> OPENAI_API_KEY backward-compat alias dropped
  when pageindex/utils.py became a re-export shim; users with only
  CHATGPT_API_KEY set would otherwise fail auth after upgrading. It now runs
  in __init__.py right after load_dotenv.

Adds regression tests for both.

Claude-Session: https://claude.ai/code/session_01Kx5DgKbhK1N8autqXH8SmS

pageindex/__init__.py

@@ -7,6 +7,13 @@
 from dotenv import load_dotenv as _load_dotenv
 _load_dotenv()
 
+# Backward compatibility: honor CHATGPT_API_KEY as an alias for OPENAI_API_KEY
+# (kept from the pre-SDK pageindex.utils). Runs after load_dotenv so a value in
+# .env is picked up too; only fills OPENAI_API_KEY when it isn't already set.
+import os as _os
+if not _os.getenv("OPENAI_API_KEY") and _os.getenv("CHATGPT_API_KEY"):
+    _os.environ["OPENAI_API_KEY"] = _os.getenv("CHATGPT_API_KEY")
+
 # Upstream exports (backward compatibility). Import from the canonical
 # pageindex.index.* modules directly so `import pageindex` does NOT trip the
 # top-level deprecation shims (pageindex.page_index / .page_index_md / .utils).

pageindex/index/utils.py

@@ -464,18 +464,20 @@ def get_pdf_page_content(file_path: str, page_nums: list[int]) -> list[dict]:
 def get_md_page_content(structure: list, page_nums: list[int]) -> list[dict]:
     """
     For Markdown documents, 'pages' are line numbers.
-    Find nodes whose line_num falls within [min(page_nums), max(page_nums)] and return their text.
+    Return only the nodes whose line_num is one of ``page_nums`` (exact match),
+    mirroring the PDF path. A non-contiguous spec like [5, 100] returns just
+    those two lines, not the whole [5, 100] range.
     """
     if not page_nums:
         return []
-    min_line, max_line = min(page_nums), max(page_nums)
+    wanted = set(page_nums)
     results = []
     seen = set()
 
     def _traverse(nodes):
         for node in nodes:
             ln = node.get('line_num')
-            if ln and min_line <= ln <= max_line and ln not in seen:
+            if ln in wanted and ln not in seen:
                 seen.add(ln)
                 results.append({'page': ln, 'content': node.get('text', '')})
             if node.get('nodes'):

pageindex/retrieve.py

@@ -56,16 +56,19 @@ def _get_pdf_page_content(doc_info: dict, page_nums: list[int]) -> list[dict]:
 def _get_md_page_content(doc_info: dict, page_nums: list[int]) -> list[dict]:
     """
     For Markdown documents, 'pages' are line numbers.
-    Find nodes whose line_num falls within [min(page_nums), max(page_nums)] and return their text.
+    Return only the nodes whose line_num is one of ``page_nums`` (exact match),
+    not the whole [min(page_nums), max(page_nums)] range.
     """
-    min_line, max_line = min(page_nums), max(page_nums)
+    if not page_nums:
+        return []
+    wanted = set(page_nums)
     results = []
     seen = set()
 
     def _traverse(nodes):
         for node in nodes:
             ln = node.get('line_num')
-            if ln and min_line <= ln <= max_line and ln not in seen:
+            if ln in wanted and ln not in seen:
                 seen.add(ln)
                 results.append({'page': ln, 'content': node.get('text', '')})
             if node.get('nodes'):