Run outcomes, score, explicit exercise recording, and step captures (RBT-WP-0004-T13)

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

@@ -0,0 +1,104 @@
+import shutil
+import subprocess
+from datetime import datetime, timedelta, timezone
+from pathlib import Path
+
+import pytest
+
+from rtut import pack as P, run as R
+
+ROOT = Path(__file__).resolve().parent.parent
+
+
+@pytest.fixture
+def pk(tmp_path):
+    d = tmp_path / "runbooks" / "show"; d.mkdir(parents=True)
+    shutil.copy(ROOT / "runbooks/showcase-lighthouse/pack.yaml", d / "pack.yaml")
+    return P.load(d / "pack.yaml")
+
+
+def play_all(r):
+    for s in r.pack.data["steps"]:
+        sid = s["id"]; R.start(r, sid)
+        cmd = R.command_for(r, sid)
+        if cmd:
+            subprocess.run(cmd, shell=True, check=True, capture_output=True)
+        R.verify(r, sid, confirm=True, manual_ok=True if s["verify"]["expect"] == "manual" else None)
+        R.complete(r, sid, {n: "1" for n in s.get("evidence", [])})
+
+
+def test_finalize_rules(pk):
+    r = R.create(pk, "bernd")
+    with pytest.raises(R.RunError):
+        R.finalize(r, "succeeded")                 # nothing done yet
+    with pytest.raises(R.RunError):
+        R.finalize(r, "failed")                    # nothing failed: abandon instead
+    with pytest.raises(R.RunError):
+        R.finalize(r, "great")
+    R.start(r, "read-the-sign"); R.fail(r, "read-the-sign", "could not read it")
+    R.finalize(r, "failed", "gave up on step 1")
+    assert r.data["outcome"] == "failed" and r.data["outcome_note"]
+    with pytest.raises(R.RunError):
+        R.finalize(r, "abandoned")                 # already finished
+
+
+def test_finished_run_is_read_only_but_takes_feedback(pk):
+    r = R.create(pk, "bernd"); R.finalize(r, "abandoned")
+    for call in (lambda: R.start(r, "read-the-sign"), lambda: R.add_capture(r, "read-the-sign", "x")):
+        with pytest.raises(R.RunError, match="finished"):
+            call()
+    R.add_feedback(r, "poor", "gave up: unclear")   # feedback stays possible
+
+
+def test_scorecard_counts_every_outcome_and_stale_open_runs(pk):
+    ok = R.create(pk, "a"); play_all(ok); R.finalize(ok, "succeeded"); R.add_feedback(ok, "good")
+    bad = R.create(pk, "b"); R.start(bad, "read-the-sign"); R.fail(bad, "read-the-sign", "x"); R.finalize(bad, "failed")
+    gone = R.create(pk, "c"); R.finalize(gone, "abandoned")
+    open_ = R.create(pk, "d")
+    stale = R.create(pk, "e")
+    stale.data["updated"] = (datetime.now(timezone.utc) - timedelta(days=9)).isoformat()
+    stale.path.write_text(__import__("json").dumps(stale.data))
+    c = R.scorecard(pk)
+    assert (c["tried"], c["succeeded"], c["failed"], c["abandoned"], c["open"]) == (5, 1, 1, 2, 1)
+    assert c["feedback"]["good"] == 1
+
+
+def test_finalizing_success_can_record_exercise_status(pk):
+    r = R.create(pk, "bernd"); play_all(r)
+    with pytest.raises(R.RunError):
+        R.apply_exercise(r)                        # not finalized yet
+    R.finalize(r, "succeeded")
+    status = R.apply_exercise(r)
+    assert status.startswith("exercised ") and status.endswith(" by bernd")
+    reloaded = P.load(pk.path)
+    assert reloaded.ok and reloaded.data["exercise_status"] == status
+
+
+def test_capture_documentation_and_limits(pk):
+    r = R.create(pk, "bernd")
+    with pytest.raises(R.RunError, match="start the step"):
+        R.add_capture(r, "read-the-sign", "out")
+    R.start(r, "read-the-sign")
+    R.add_capture(r, "read-the-sign", "Tower of stone", command="printf poem")
+    assert R.load(pk, r.data["run_id"]).state("read-the-sign")["captures"][0]["output"] == "Tower of stone"
+    with pytest.raises(R.RunError, match="too large"):
+        R.add_capture(r, "read-the-sign", "x" * 20001)
+    with pytest.raises(R.RunError, match="secret-looking"):
+        R.add_capture(r, "read-the-sign", "hvs.ABCDEFGHIJKLMN")
+    with pytest.raises(R.RunError, match="nothing"):
+        R.add_capture(r, "read-the-sign", "  ")
+
+
+def test_verify_against_pasted_output(pk):
+    r = R.create(pk, "bernd", {"keeper": "Ada"})
+    R.start(r, "read-the-sign")
+    with pytest.raises(R.RunError, match="output-contains"):
+        R.verify_pasted(r, "read-the-sign", "x")                  # manual step: not applicable
+    R.complete  # (step 2 is output-contains)
+    R.verify(r, "read-the-sign", manual_ok=True); R.complete(r, "read-the-sign")
+    R.start(r, "meet-the-keeper")
+    assert not R.verify_pasted(r, "meet-the-keeper", "nothing useful", "echo ...")["passed"]
+    ok = R.verify_pasted(r, "meet-the-keeper", "Ada climbs the stairs. Motto on the wall - x")
+    assert ok["passed"] and ok["source"] == "pasted"
+    caps = R.load(pk, r.data["run_id"]).state("meet-the-keeper")["captures"]
+    assert len(caps) == 2 and caps[0]["source"] == "pasted-for-verification"