fix(arxiv): handle legacy single-file gzipped source (no tar wrapper)

Old arXiv submissions (e.g. legacy math/* papers) are served as a bare gzipped .tex rather than a .tar.gz, which tarfile.open rejected with 'invalid header'. Fall back to gunzipping the body directly when the tar parse fails, so R-C covers those papers too (recovers math/0001176 + math/0306167). Adds a regression test.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

codex/sources/arxiv.py

@@ -8,6 +8,7 @@ Provides:
 
 from __future__ import annotations
 
+import gzip
 import io
 import logging
 import tarfile
@@ -157,12 +158,19 @@ def fetch_source(arxiv_id: str) -> str | None:
             # Inline \input/\include so multi-file projects yield the full body,
             # not just the primary file's skeleton of include directives (R-C).
             return flatten_inputs(files[primary_name], files)
-    except tarfile.TarError as exc:
-        logger.warning("Failed to open tar archive for %s: %s", arxiv_id, exc)
+    except tarfile.TarError:
+        # Old arXiv submissions are served as a single bare gzipped .tex with no
+        # tar wrapper (e.g. legacy math/* papers) — gunzip the body directly.
+        try:
+            single = gzip.decompress(raw).decode("utf-8", errors="replace")
+        except (OSError, EOFError) as exc:
+            logger.warning("Failed to read arXiv source for %s: %s", arxiv_id, exc)
+            return None
+        if "\\" in single[:5000]:  # looks like LaTeX (has backslash commands)
+            return single
+        logger.debug("arXiv source for %s is not LaTeX", arxiv_id)
         return None
 
-    return None  # unreachable but satisfies type checker
-
 
 def fetch_pdf_url(arxiv_id: str) -> str:
     """Return the canonical PDF URL for an arXiv paper.