feat(skill-learning): select replay eval cases

app-instance/backend/tests/unit/test_skill_learning_case_selection.py

@@ -0,0 +1,82 @@
+from __future__ import annotations
+
+from beaver.memory.runs import RunRecord
+from beaver.memory.skills import SkillLearningCandidate
+from beaver.skills.learning.case_selection import select_replay_cases
+from beaver.skills.specs import SkillActivationReceipt
+
+
+def _run(
+    run_id: str,
+    *,
+    task_id: str = "task",
+    session_id: str = "session",
+    task_text: str = "debug task",
+    skill_name: str | None = None,
+    skill_version: str = "v0001",
+) -> RunRecord:
+    receipts = []
+    if skill_name:
+        receipts.append(
+            SkillActivationReceipt(
+                run_id=run_id,
+                session_id=session_id,
+                skill_name=skill_name,
+                skill_version=skill_version,
+                content_hash="hash",
+                activated_at="now",
+                activation_reason="selected",
+            )
+        )
+    return RunRecord(
+        run_id=run_id,
+        session_id=session_id,
+        task_id=task_id,
+        attempt_index=1,
+        task_text=task_text,
+        started_at=f"2026-06-08T00:00:{run_id[-2:]}+00:00",
+        ended_at="end",
+        success=True,
+        finish_reason="stop",
+        feedback={"acceptance_type": "accept"},
+        activated_skills=receipts,
+    )
+
+
+def test_select_revise_cases_caps_at_ten_and_prefers_related_skill() -> None:
+    runs = [
+        _run(f"run-{index:02d}", task_id=f"task-{index}", skill_name="debug", skill_version="v0001")
+        for index in range(12)
+    ]
+    candidate = SkillLearningCandidate(
+        candidate_id="candidate-1",
+        kind="revise_skill",
+        source_run_ids=[],
+        source_session_ids=[],
+        related_skill_names=["debug"],
+        reason="revise",
+        evidence={"skill_version": "v0001"},
+    )
+
+    cases = select_replay_cases(candidate, runs)
+
+    assert len(cases) == 10
+    assert all(case["baseline_skill_names"] == ["debug"] for case in cases)
+    assert cases[0]["run_id"] == "run-11"
+
+
+def test_select_new_skill_uses_all_available_source_runs_under_ten() -> None:
+    runs = [_run(f"run-{index:02d}", task_id=f"task-{index}") for index in range(3)]
+    candidate = SkillLearningCandidate(
+        candidate_id="candidate-1",
+        kind="new_skill",
+        source_run_ids=["run-00", "run-01", "run-02"],
+        source_session_ids=["session"],
+        related_skill_names=[],
+        reason="new",
+    )
+
+    cases = select_replay_cases(candidate, runs)
+
+    assert [case["run_id"] for case in cases] == ["run-02", "run-01", "run-00"]
+    assert all(case["baseline_skill_names"] == [] for case in cases)