codex/sources/arxiv.py

@@ -38,10 +38,7 @@ def fetch_source(arxiv_id: str) -> str | None:
         file is present (signals Nougat fallback).
     """
     url = f"{_BASE}/src/{arxiv_id}"
-    try:
     response = httpx.get(url, timeout=60, follow_redirects=True)
-    except httpx.RequestError:
-        raise
     if response.status_code == 404:
         logger.debug("arXiv 404 for source id=%s", arxiv_id)
         return None

codex/sources/semanticscholar.py

@@ -14,6 +14,7 @@ import logging
 import threading
 import time
 from typing import Any
+from urllib.parse import quote
 
 import httpx
 from tenacity import retry, retry_if_exception, stop_after_attempt, wait_exponential
@@ -77,7 +78,9 @@ def fetch_references(paper_id: str) -> list[Citation]:
     list[Citation]
         One Citation per reference, with optional context snippet.
     """
-    url = f"{_BASE_GRAPH}/paper/{paper_id}/references"
+    # quote the id so a legacy-arXiv "/" (e.g. arXiv:math/0603097) doesn't break
+    # the URL path; keep ":" for the arXiv:/DOI: scheme prefix (audit R-5).
+    url = f"{_BASE_GRAPH}/paper/{quote(paper_id, safe=':')}/references"
     params: dict[str, Any] = {"fields": "externalIds,contexts"}
     try:
         response = _get(url, params=params)
@@ -118,7 +121,7 @@ def fetch_recommendations(paper_id: str, limit: int = 20) -> list[str]:
     list[str]
         List of recommended paper IDs.
     """
-    url = f"{_BASE_RECS}/papers/forpaper/{paper_id}"
+    url = f"{_BASE_RECS}/papers/forpaper/{quote(paper_id, safe=':')}"
     params: dict[str, Any] = {"limit": limit}
     try:
         response = _get(url, params=params)