fix: log warning when sft record is missing id field

scripts/sft_import.py

@@ -6,8 +6,11 @@ Used by app/sft.py endpoints and can be run standalone.
 from __future__ import annotations
 
 import json
+import logging
 from pathlib import Path
 
+logger = logging.getLogger(__name__)
+
 _CANDIDATES_FILENAME = "sft_candidates.jsonl"
 
 
@@ -56,6 +59,7 @@ def import_run(sft_path: Path, data_dir: Path) -> dict[str, int]:
     skipped = 0
     for record in _read_jsonl(sft_path):
         if "id" not in record:
+            logger.warning("Skipping record missing 'id' field in %s", sft_path)
             continue  # malformed — skip without crashing
         if record["id"] in existing_ids:
             skipped += 1

tests/test_sft_import.py

@@ -80,10 +80,16 @@ def test_import_run_deduplicates_on_id(tmp_path):
     assert len(lines) == 2  # no duplicates
 
 
-def test_import_run_skips_records_missing_id(tmp_path):
+def test_import_run_skips_records_missing_id(tmp_path, caplog):
+    import logging
     from scripts.sft_import import import_run
     sft_path = tmp_path / "run1" / "sft_candidates.jsonl"
-    bad = {"source": "cf-orch-benchmark", "status": "needs_review"}  # no id
+    sft_path.parent.mkdir()
-    _write_candidates(sft_path, [bad, _make_record("a")])
+    sft_path.write_text(
+        json.dumps({"model_response": "bad", "status": "needs_review"}) + "\n"
+        + json.dumps({"id": "abc123", "model_response": "good", "status": "needs_review"}) + "\n"
+    )
+    with caplog.at_level(logging.WARNING, logger="scripts.sft_import"):
         result = import_run(sft_path, tmp_path)
     assert result == {"imported": 1, "skipped": 0}
+    assert "missing 'id'" in caplog.text