fix(ingest): retry on bibkey UNIQUE collision (audit C-15)

The id-keyed upsert (ON CONFLICT (id)) does not catch the papers.bibkey UNIQUE
constraint, so a second paper whose auto-generated key matches an existing one
(two same-author/year works → e.g. 'BobenkoLutz2023') failed the whole ingest
with a UniqueViolation. Surfaced by the canonical-id re-ingest: 2305.10988
collided with 2310.17529.

ingest now catches a bibkey UniqueViolation, rolls back, and retries the upsert
with an a/b/c… suffix. Non-bibkey violations re-raise unchanged. Mocks don't
raise, so the existing happy-path tests are untouched; a new test drives the
collision-and-retry path.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Tarik Moussa
2026-06-15 22:11:14 +02:00
parent 45c3b16dd7
commit b52303d22b
2 changed files with 77 additions and 28 deletions

View File

@@ -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()
# ---------------------------------------------------------------------------