fix(rectification): bind quality cards to the followup probe

Graduation no longer gets the college-experience question, and identical D24 splits only ask once.

Co-authored-by: Cursor <cursoragent@cursor.com>

tests/test_rectification_event_probes.py

@@ -9,7 +9,10 @@ from scripts.rectification.event_probes import (
     MAX_COLLECTION_PROBES,
     MAX_PROBES,
     MAX_PROBES_PER_DOMAIN,
+    MAX_QUALITY_DISTINGUISH_PROBES,
     _agent_brief,
+    _quality_distinguish_probes,
+    _select_quality_distinguish_rows,
     discriminating_event_probes,
     event_clarification_probes,
     evidence_collection_probes,
@@ -900,5 +903,163 @@ class EventProbesTest(unittest.TestCase):
         self.assertEqual({int(item["year"]) for item in relocation}, {2016, 2019, 2022})
 
 
+def _education_event(event_id: str, kind: str, date: str, summary: str) -> dict:
+    return {
+        "id": event_id,
+        "domain": "education",
+        "event_kind": kind,
+        "summary": summary,
+        "date": date,
+        "precision": "month",
+    }
+
+
+def _d24_split_clusters() -> list[dict]:
+    return [
+        {
+            "representative": {"feature": {"varga_ascendants": {"D24": 1}}},
+            "times": ["05:00", "05:01"],
+        },
+        {
+            "representative": {"feature": {"varga_ascendants": {"D24": 2}}},
+            "times": ["05:10", "05:11"],
+        },
+    ]
+
+
+def _quality_rows(*events: dict) -> list[dict]:
+    return _quality_distinguish_probes(
+        list(events),
+        _d24_split_clusters(),
+        set_version="quality-dedupe-set",
+        holdout_ids=set(),
+        holdout_keys=set(),
+    )
+
+
+class QualityDistinguishDedupeTests(unittest.TestCase):
+    def test_start_and_completion_emit_one_quality_probe_for_start(self) -> None:
+        start = _education_event(
+            "00000000-0000-4000-8000-000000000021",
+            "education_start",
+            "2014-09-01",
+            "入学",
+        )
+        completion = _education_event(
+            "00000000-0000-4000-8000-000000000022",
+            "education_completion",
+            "2018-06-01",
+            "毕业",
+        )
+        rows = _quality_rows(start, completion)
+        self.assertEqual(len(rows), 1)
+        self.assertEqual(rows[0]["target_evidence_id"], start["id"])
+        self.assertEqual(rows[0]["year"], 2014)
+        self.assertNotIn(completion["id"], [item["target_evidence_id"] for item in rows])
+
+    def test_completion_alone_emits_no_quality_probe(self) -> None:
+        completion = _education_event(
+            "00000000-0000-4000-8000-000000000022",
+            "education_completion",
+            "2018-06-01",
+            "毕业",
+        )
+        self.assertEqual(_quality_rows(completion), [])
+
+    def test_completion_still_participates_in_ordinary_time_probes(self) -> None:
+        request = _request(events=[
+            _education_event(
+                "00000000-0000-4000-8000-000000000022",
+                "education_completion",
+                "2018-06-01",
+                "毕业",
+            ),
+            {
+                "id": "00000000-0000-4000-8000-000000000013",
+                "domain": "career",
+                "event_kind": "career_entry",
+                "summary": "入职",
+                "date": "2018-07-01",
+                "precision": "month",
+            },
+            {
+                "id": "00000000-0000-4000-8000-000000000014",
+                "domain": "relationship",
+                "event_kind": "relationship_start",
+                "summary": "相识",
+                "date": "2021-08-01",
+                "precision": "month",
+            },
+            {
+                "id": "00000000-0000-4000-8000-000000000015",
+                "domain": "family",
+                "event_kind": "family_event",
+                "summary": "家里添丁",
+                "date": "2020-01-01",
+                "precision": "year",
+            },
+        ])
+        probes = _probes(request, _multi_layer_window_built(), ["05:00", "05:06", "05:07"], "05:00")
+        quality = [item for item in probes if item["source"] == "known_event_quality"]
+        self.assertEqual(quality, [])
+        self.assertTrue(probes)
+        self.assertTrue(any(item["source"] in {"dasha_boundary", "dasha_activation"} for item in probes))
+
+    def test_same_split_keeps_earliest_eligible_education_event(self) -> None:
+        start = _education_event(
+            "00000000-0000-4000-8000-000000000021",
+            "education_start",
+            "2014-09-01",
+            "入学",
+        )
+        change = _education_event(
+            "00000000-0000-4000-8000-000000000023",
+            "education_change",
+            "2016-03-01",
+            "转学",
+        )
+        rows = _quality_rows(start, change)
+        self.assertEqual(len(rows), 1)
+        self.assertEqual(rows[0]["target_evidence_id"], start["id"])
+
+    def test_different_quality_groups_keep_two_up_to_cap(self) -> None:
+        def stub(year: int, month: int, supports: list[str], conflicts: list[str], evidence_id: str) -> dict:
+            return {
+                "domain": "education",
+                "year": year,
+                "month": month,
+                "information_gain": 0.5,
+                "target_evidence_id": evidence_id,
+                "expected_outcomes": [
+                    {"answer_class": "yes", "supports": supports, "conflicts": conflicts},
+                    {"answer_class": "no", "supports": conflicts, "conflicts": supports},
+                ],
+            }
+
+        same_split = _select_quality_distinguish_rows([
+            stub(2014, 9, ["05:00"], ["05:10"], "start"),
+            stub(2016, 3, ["05:00"], ["05:10"], "change"),
+        ])
+        self.assertEqual(len(same_split), 1)
+        self.assertEqual(same_split[0]["target_evidence_id"], "start")
+
+        different = _select_quality_distinguish_rows([
+            stub(2014, 9, ["05:00"], ["05:10"], "start"),
+            stub(2016, 3, ["05:02"], ["05:12"], "change"),
+        ])
+        self.assertEqual(len(different), 2)
+        self.assertEqual(
+            {item["target_evidence_id"] for item in different},
+            {"start", "change"},
+        )
+
+        over_cap = _select_quality_distinguish_rows([
+            stub(2014, 9, ["05:00"], ["05:10"], "a"),
+            stub(2015, 9, ["05:02"], ["05:12"], "b"),
+            stub(2016, 9, ["05:04"], ["05:14"], "c"),
+        ])
+        self.assertEqual(len(over_cap), MAX_QUALITY_DISTINGUISH_PROBES)
+
+
 if __name__ == "__main__":
     unittest.main()