codex/sources/semanticscholar.py

@@ -96,10 +96,7 @@ def fetch_references(paper_id: str) -> list[Citation]:
         context: str | None = contexts[0] if contexts else None
 
         cited_id: str = (
-            external_ids.get("DOI")
+            external_ids.get("DOI") or external_ids.get("ArXiv") or cited_paper.get("paperId") or ""
-            or external_ids.get("ArXiv")
-            or cited_paper.get("paperId")
-            or ""
         )
         if cited_id:
             citations.append(Citation(citing_id=paper_id, cited_id=cited_id, context=context))

codex/synthesis.py

@@ -365,11 +365,7 @@ def find_connections(
                 continue
             seen_pairs.add(pair)  # type: ignore[arg-type]
 
-            pair_chunks = [
+            pair_chunks = [c for c in chunks if c.get("bibkey") in {bibkey, other}]
-                c
-                for c in chunks
-                if c.get("bibkey") in {bibkey, other}
-            ]
             prompt = _CONNECTION_PROMPT.format(chunks_block=_format_chunks(pair_chunks))
             raw = _safe_llm_generate(llm, prompt, settings.synthesis_llm_model)
             if not raw.strip():

codex/wiki.py

@@ -240,9 +240,36 @@ def _parse_claims(markdown: str) -> list[Claim]:
 
 _STOPWORDS: frozenset[str] = frozenset(
     {
-        "the", "a", "an", "in", "on", "of", "to", "is", "are", "was", "were",
+        "the",
-        "and", "or", "but", "for", "with", "this", "that", "it", "we", "they",
+        "a",
-        "be", "as", "at", "by", "from", "has", "have", "not", "which",
+        "an",
+        "in",
+        "on",
+        "of",
+        "to",
+        "is",
+        "are",
+        "was",
+        "were",
+        "and",
+        "or",
+        "but",
+        "for",
+        "with",
+        "this",
+        "that",
+        "it",
+        "we",
+        "they",
+        "be",
+        "as",
+        "at",
+        "by",
+        "from",
+        "has",
+        "have",
+        "not",
+        "which",
     }
 )
 
@@ -360,12 +387,8 @@ def _detect_conflicts(
         for bk2 in bibkeys[i + 1 :]:
             # Check if any chunk from bk1 contains a conflict keyword
             # and any chunk from bk2 also does — heuristic signal only
-            bk1_has_conflict = any(
+            bk1_has_conflict = any(_CONFLICT_KEYWORDS.search(c) for c in by_bib[bk1])
-                _CONFLICT_KEYWORDS.search(c) for c in by_bib[bk1]
+            bk2_has_conflict = any(_CONFLICT_KEYWORDS.search(c) for c in by_bib[bk2])
-            )
-            bk2_has_conflict = any(
-                _CONFLICT_KEYWORDS.search(c) for c in by_bib[bk2]
-            )
             if bk1_has_conflict and bk2_has_conflict:
                 conflicts.append((slug, bk1, bk2))
 

tests/synthesis/test_cli.py

@@ -55,9 +55,7 @@ def isolated_leads_dir(monkeypatch: pytest.MonkeyPatch, tmp_path: Path) -> Path:
 
     monkeypatch.setattr("codex.cli.get_settings", lambda: settings, raising=False)
     monkeypatch.setattr("codex.synthesis.get_settings", lambda: settings)
-    monkeypatch.setattr(
+    monkeypatch.setattr("codex.config.get_settings", lambda: settings, raising=False)
-        "codex.config.get_settings", lambda: settings, raising=False
-    )
     return leads_path
 
 

tests/wiki/test_compile.py

@@ -201,9 +201,7 @@ def test_grounding_guard_last_sentence_grounded_earlier_hallucination_ignored()
     This test verifies that a claim whose text = the last sentence grounds correctly.
     """
     # The last sentence of the claim text is directly grounded in the fixture chunk.
-    grounded_sentence = (
+    grounded_sentence = "the hyperbolic volume is V = L(gamma1) + L(gamma2) + L(gamma3)"
-        "the hyperbolic volume is V = L(gamma1) + L(gamma2) + L(gamma3)"
-    )
     claim = Claim(
         text=grounded_sentence,
         bibkey="Springborn2008",
@@ -523,9 +521,7 @@ def test_idempotent_no_rewrite_when_unchanged(
     call_count = 0
     original_compile = compile_concept
 
-    def counting_compile(
+    def counting_compile(concept: Concept, chunks: list[Any], **kwargs: Any) -> ConceptPage:
-        concept: Concept, chunks: list[Any], **kwargs: Any
-    ) -> ConceptPage:
         nonlocal call_count
         call_count += 1
         return original_compile(concept, chunks, **kwargs)
@@ -569,9 +565,7 @@ def test_force_all_recompiles_even_when_unchanged(
     call_count = 0
     original_compile = compile_concept
 
-    def counting_compile(
+    def counting_compile(concept: Concept, chunks: list[Any], **kwargs: Any) -> ConceptPage:
-        concept: Concept, chunks: list[Any], **kwargs: Any
-    ) -> ConceptPage:
         nonlocal call_count
         call_count += 1
         return original_compile(concept, chunks, **kwargs)