codex/ingest.py

@@ -8,6 +8,7 @@ from dataclasses import dataclass
 from pathlib import Path
 
 import numpy as np
+import psycopg
 
 from codex.config import get_settings
 from codex.db import get_conn
@@ -125,35 +126,48 @@ def ingest_paper(
     # ---------------------------------------------------------------
     # 3. Upsert paper  (INSERT … ON CONFLICT (id) DO UPDATE SET …)
     # ---------------------------------------------------------------
+    upsert_sql = """
+        INSERT INTO papers (id, openalex_id, bibkey, title, authors, year, abstract,
+                            source_path, abstract_emb)
+        VALUES (%(id)s, %(openalex_id)s, %(bibkey)s, %(title)s, %(authors)s, %(year)s,
+                %(abstract)s, %(source_path)s, %(abstract_emb)s)
+        ON CONFLICT (id) DO UPDATE SET
+            openalex_id  = EXCLUDED.openalex_id,
+            bibkey       = COALESCE(papers.bibkey, EXCLUDED.bibkey),
+            title        = EXCLUDED.title,
+            authors      = EXCLUDED.authors,
+            year         = EXCLUDED.year,
+            abstract     = EXCLUDED.abstract,
+            source_path  = COALESCE(EXCLUDED.source_path, papers.source_path),
+            abstract_emb = EXCLUDED.abstract_emb
+    """
     with get_conn() as conn:
-        conn.execute(
-            """
-            INSERT INTO papers (id, openalex_id, bibkey, title, authors, year, abstract,
-                                source_path, abstract_emb)
-            VALUES (%(id)s, %(openalex_id)s, %(bibkey)s, %(title)s, %(authors)s, %(year)s,
-                    %(abstract)s, %(source_path)s, %(abstract_emb)s)
-            ON CONFLICT (id) DO UPDATE SET
-                openalex_id  = EXCLUDED.openalex_id,
-                bibkey       = COALESCE(papers.bibkey, EXCLUDED.bibkey),
-                title        = EXCLUDED.title,
-                authors      = EXCLUDED.authors,
-                year         = EXCLUDED.year,
-                abstract     = EXCLUDED.abstract,
-                source_path  = COALESCE(EXCLUDED.source_path, papers.source_path),
-                abstract_emb = EXCLUDED.abstract_emb
-            """,
-            {
-                "id": paper.id,
-                "openalex_id": paper.openalex_id,
-                "bibkey": paper.bibkey,
-                "title": paper.title,
-                "authors": paper.authors,
-                "year": paper.year,
-                "abstract": paper.abstract,
-                "source_path": source_path,
-                "abstract_emb": abstract_emb,
-            },
-        )
+        # The id-keyed upsert does not catch a papers.bibkey UNIQUE collision (two
+        # same-author/year papers generate the same key). On such a collision retry
+        # with an a/b/c… suffix instead of failing the whole ingest (audit C-15).
+        base_bibkey = paper.bibkey
+        for attempt in range(27):
+            try:
+                conn.execute(
+                    upsert_sql,
+                    {
+                        "id": paper.id,
+                        "openalex_id": paper.openalex_id,
+                        "bibkey": paper.bibkey,
+                        "title": paper.title,
+                        "authors": paper.authors,
+                        "year": paper.year,
+                        "abstract": paper.abstract,
+                        "source_path": source_path,
+                        "abstract_emb": abstract_emb,
+                    },
+                )
+                break
+            except psycopg.errors.UniqueViolation as exc:
+                if base_bibkey is None or "bibkey" not in str(exc).lower() or attempt == 26:
+                    raise
+                conn.rollback()
+                paper.bibkey = f"{base_bibkey}{chr(ord('a') + attempt)}"
 
         # Register openalex_id in paper_identifiers (alias table).
         # Every ingest records the primary openalex_id so the graph JOIN

tests/ingest/test_ingest.py

@@ -11,6 +11,7 @@ from typing import Any
 from unittest.mock import MagicMock, patch
 
 import numpy as np
+import psycopg
 import pytest
 
 from codex.ingest import IngestResult, _make_bibkey, ingest_paper
@@ -525,6 +526,40 @@ def test_ingest_sets_bibkey_when_none(tmp_path: Any) -> None:
     assert upsert_params["bibkey"] == "AliceBob2023"
 
 
+def test_ingest_disambiguates_bibkey_on_unique_violation() -> None:
+    """A papers.bibkey UNIQUE collision is retried with an a/b/c suffix (audit C-15)."""
+    paper = _make_paper()  # bibkey auto-generates to "AliceBob2023"
+    mock_conn = MagicMock()
+    state = {"first": True}
+
+    def execute_side_effect(sql: str, params: Any = None) -> MagicMock:
+        # The first papers INSERT collides on the bibkey; the retry must succeed.
+        if "INSERT INTO papers" in sql and state["first"]:
+            state["first"] = False
+            raise psycopg.errors.UniqueViolation(
+                'duplicate key value violates unique constraint "papers_bibkey_key"'
+            )
+        return MagicMock()
+
+    mock_conn.execute.side_effect = execute_side_effect
+
+    with (
+        patch("codex.ingest.openalex.fetch_paper", return_value=paper),
+        patch("codex.ingest.openalex.fetch_citations", return_value=[]),
+        patch("codex.ingest.get_embedder", return_value=_fake_embedder()),
+        patch("codex.ingest.get_conn", side_effect=_make_conn_cm(mock_conn)),
+    ):
+        ingest_paper(paper.id)
+
+    papers_inserts = [
+        c for c in mock_conn.execute.call_args_list if "INSERT INTO papers" in c[0][0]
+    ]
+    assert len(papers_inserts) == 2, "expected one retry after the bibkey collision"
+    assert papers_inserts[0][0][1]["bibkey"] == "AliceBob2023"
+    assert papers_inserts[1][0][1]["bibkey"] == "AliceBob2023a"
+    mock_conn.rollback.assert_called_once()
+
+
 # ---------------------------------------------------------------------------