Active user attribute set, latest activities, guarded changes to used values, artefact links, durations and averages; irreversible showcase step

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

Assistant: claude-code
Assistant-Model: sonnet
Assistant-Process: 295952@bnt-lap001
Assistant-Session: e93f64ad-516c-46eb-9666-aad8d300c477

tests/test_score.py

@@ -115,3 +115,39 @@ def test_runs_of_different_packs_in_one_repository_are_not_mixed(tmp_path):
     assert R.scorecard(pa)["tried"] == 2 and R.scorecard(pb)["tried"] == 1
     assert R.list_runs(pb) != R.list_runs(pa) and len(R.list_runs(pb)) == 1
     assert R.scorecard(pb)["feedback"]["good"] == 0 and R.all_feedback(pb) == []
+
+
+# ---- durations -----------------------------------------------------------------------------------------------
+
+def test_fmt_duration():
+    assert [R.fmt_duration(x) for x in (None, 0, 45, 60, 200, 3600, 3900, 90000)] == ["-", "0 s", "45 s", "1 min", "3 min 20 s", "1 h", "1 h 5 min", "1 d 1 h"]
+
+
+def test_run_times_and_average_of_succeeded_runs_only(pk):
+    from datetime import datetime, timedelta, timezone
+    import json
+    def timed(operator, seconds, outcome):
+        r = R.create(pk, operator)
+        start = datetime(2026, 9, 29, 10, 0, tzinfo=timezone.utc)
+        r.data["created"] = start.isoformat()
+        r.data["outcome"] = outcome
+        r.data["finished"] = (start + timedelta(seconds=seconds)).isoformat()
+        first = next(iter(r.data["steps"]))
+        r.data["steps"][first].update(state="done", started=(start + timedelta(seconds=10)).isoformat(),
+                                      finished=(start + timedelta(seconds=40)).isoformat())
+        r.path.write_text(json.dumps(r.data))
+        return r
+    a = timed("a", 600, "succeeded"); timed("b", 1200, "succeeded"); timed("c", 9000, "failed"); timed("d", 300, "abandoned")
+    t = R.run_times(R.load(pk, a.data["run_id"]))
+    assert t["elapsed"] == 600 and t["finished_run"] and t["step_seconds"] == {next(iter(a.data["steps"])): 30.0} and t["working"] == 30.0
+    c = R.scorecard(pk)
+    assert c["avg_seconds"] == 900 and c["median_seconds"] == 900 and c["fastest_seconds"] == 600 and c["timed_runs"] == 2   # the failed 9000 s run is not counted
+    assert R.scorecard(pk)["succeeded"] == 2
+
+
+def test_unfinished_run_elapsed_runs_to_now_and_no_average_without_succeeded_runs(pk):
+    from datetime import datetime, timedelta, timezone
+    r = R.create(pk, "x")
+    t = R.run_times(r, now=datetime.now(timezone.utc) + timedelta(seconds=90))
+    assert not t["finished_run"] and 89 <= t["elapsed"] <= 91
+    assert R.scorecard(pk)["avg_seconds"] is None and R.scorecard(pk)["timed_runs"] == 0