"""The replay harness against its committed scripts and goldens (A21, PLAN §9 layer 3). `tests/sim/test_replay_carry.py` pinned the first golden by hand; this file is the formalised contract: the two committed replay scripts (`walk_solo`, the 600-tick movement-only tour of level 1; `pick_drop_pass`, two cooks running the whole pick → set-down → hand-off → long-press-trash chain on the fixture kitchen) each match their committed `tests/goldens/.golden.json`, a deliberately mutated script diverges and `compare()` names the first bad tick and the changed field, the record cadence is stable, a replay is bit-identical within one process, and the goldens are never rewritten by the test run. The levels are loaded explicitly (level 1 from the shipped `levels/`, the fixture kitchen from `tests/fixtures/levels/_replay/`), so the session fixture's level-free directory cannot leak in — and the CLI tests point `UNDERCOOKED_LEVELS_DIR` at `levels/` for the same reason. """ from __future__ import annotations import json import time from dataclasses import replace from itertools import pairwise from pathlib import Path from typing import Any import pytest from undercooked.sim.content import load_level_file from undercooked.sim.recipe import load_recipe_book from undercooked.sim.replay import ( EXIT_MISMATCH, EXIT_OK, EXIT_UNUSABLE, Frame, InputScript, ReplayError, ScriptItem, _field_diff, # private, exercised directly below compare, main, run_script, ) pytestmark = pytest.mark.unit REPO_ROOT = Path(__file__).resolve().parents[2] SHIPPED_LEVELS = REPO_ROOT / "levels" SHIPPED_RECIPES = SHIPPED_LEVELS / "recipes.yaml" WALK_SOLO_SCRIPT = REPO_ROOT / "tests" / "fixtures" / "replays" / "walk_solo.json" PICK_DROP_PASS_SCRIPT = ( REPO_ROOT / "tests" / "fixtures" / "replays" / "pick_drop_pass.json" ) PICK_DROP_PASS_LEVEL = ( REPO_ROOT / "tests" / "fixtures" / "levels" / "_replay" / "pick_drop_pass.yaml" ) WALK_SOLO_GOLDEN = REPO_ROOT / "tests" / "goldens" / "walk_solo.golden.json" PICK_DROP_PASS_GOLDEN = REPO_ROOT / "tests" / "goldens" / "pick_drop_pass.golden.json" def golden_map(path: Path) -> dict[int, str]: """A golden file's `hashes` as the `tick -> hash` mapping `compare` takes.""" golden = json.loads(path.read_text(encoding="utf-8")) return {int(tick): digest for tick, digest in golden["hashes"].items()} def golden_final(path: Path) -> str: return json.loads(path.read_text(encoding="utf-8"))["hash"] def load_walk_solo() -> tuple[Any, Any, InputScript]: """Level 1, the recipe book and the committed walk_solo script.""" level = load_level_file(SHIPPED_LEVELS / "01_first_kitchen.yaml") book = load_recipe_book(SHIPPED_RECIPES) return level, book, InputScript.load(WALK_SOLO_SCRIPT) def load_pick_drop_pass() -> tuple[Any, Any, InputScript]: """The fixture kitchen, the recipe book and the committed pick_drop_pass script.""" level = load_level_file(PICK_DROP_PASS_LEVEL) book = load_recipe_book(SHIPPED_RECIPES) return level, book, InputScript.load(PICK_DROP_PASS_SCRIPT) # -- the committed goldens ---------------------------------------------------- def test_walk_solo_matches_its_committed_golden() -> None: """600 ticks of movement-only walking on level 1, every tick recorded.""" level, book, script = load_walk_solo() result = run_script(level, book, script) assert result.state.tick == 600 assert len(result.events) == 0 # movement only: no press, no event assert result.state.players[0].vel.length < 1e-6 # the tour ends settled assert [tick for tick, _ in result.hashes] == list(range(601)) assert result.state.state_hash() == golden_final(WALK_SOLO_GOLDEN) assert compare(result, golden_map(WALK_SOLO_GOLDEN)) == [] def test_pick_drop_pass_matches_its_committed_golden_and_event_sequence() -> None: """The whole hand chain, pinned both by hash and by the events it must cause.""" level, book, script = load_pick_drop_pass() result = run_script(level, book, script) assert result.state.tick == 139 expected: tuple[tuple[str, dict[str, object]], ...] = ( ( "picked", {"player_id": "p0", "station": "spawn_shelf_0", "item": "tomato", "form": "raw"}, ), ( "dropped", {"player_id": "p0", "station": "prep_0", "item": "tomato", "form": "raw"}, ), ("handed_off", {"from": "p0", "to": "p1", "item": "tomato", "form": "raw"}), ("trashed", {"player_id": "p1", "item": "tomato", "score_delta": -2}), ) assert len(result.events) == len(expected) for event, (want_kind, want_payload) in zip(result.events, expected, strict=True): assert event.kind == want_kind for key, value in want_payload.items(): assert event.payload.get(key) == value, (event.kind, event.payload) assert result.state.counters["trashed"] == 1 for player in result.state.players: # the round ends settled, hands empty assert player.carrying is None assert player.vel.length < 1e-6 assert result.state.state_hash() == golden_final(PICK_DROP_PASS_GOLDEN) assert compare(result, golden_map(PICK_DROP_PASS_GOLDEN)) == [] def test_a_mutated_coordinate_diverges_and_compare_names_the_bad_tick_and_field() -> None: """One coordinate edited in the fixture: the first bad tick and the moved field.""" level, book, script = load_walk_solo() frames = list(script.frames) frames[0] = replace(frames[0], move=(0.0, -1.0)) # up, not down mutated = replace(script, frames=tuple(frames)) result = run_script(level, book, mutated) mismatches = compare(result, golden_map(WALK_SOLO_GOLDEN)) assert mismatches, "a mutated script must not match its golden" first = mismatches[0] assert first.kind == "hash" assert first.tick == 1, "the frame at tick 0 is consumed by substep 0 -> tick 1" assert first.actual is not None and first.actual != first.expected assert "players[0].pos.y" in first.changed, ( "the diff must name the field the edit moved, " + str(first.changed) ) assert "players[0].vel.y" in first.changed assert all(m.tick >= first.tick for m in mismatches) # the tour re-converges on its walls, so the *final* state may agree with the # golden again — what is pinned is the divergence itself: assert len(mismatches) > 1 divergent = [m for m in mismatches if m.kind == "hash"] assert divergent and all(m.actual != m.expected for m in divergent) # -- determinism and cadence -------------------------------------------------- def test_replaying_the_same_script_twice_in_one_process_is_identical() -> None: """No hidden global state: two runs of each script in one process agree exactly.""" for loader in (load_walk_solo, load_pick_drop_pass): level, book, script = loader() first = run_script(level, book, script) second = run_script(level, book, script) assert first.hashes == second.hashes assert first.events == second.events assert first.state.state_hash() == second.state.state_hash() assert first.wall_seconds == second.wall_seconds == 0.0 # no clock injected def test_the_record_cadence_is_stable_and_the_final_tick_is_always_recorded() -> None: level, book, script = load_walk_solo() sparse = replace(script, record_every=5) first = run_script(level, book, sparse) second = run_script(level, book, sparse) assert first.hashes == second.hashes ticks = [tick for tick, _ in first.hashes] assert ticks[0] == 0 assert ticks[-1] == 600 # the final tick is always recorded, cadence or not assert set(ticks) == {tick for tick in range(0, 601) if tick % 5 == 0} | {600} silent = replace(script, record_every=0) unrecorded = run_script(level, book, silent) assert unrecorded.hashes == () assert dict(unrecorded.states) == {} assert unrecorded.state.tick == 600 # the run still runs; only the recording stops def test_a_run_with_a_clock_measures_wall_seconds_and_a_pinned_length_clips() -> None: """`clock` is the seam the perf smoke times through; `max_ticks` pins the run.""" level, book, script = load_walk_solo() measured = run_script(level, book, script, clock=time.perf_counter) assert measured.wall_seconds > 0.0 clipped = run_script(level, book, script, max_ticks=10) assert clipped.state.tick == 10 assert [tick for tick, _ in clipped.hashes] == list(range(11)) # cadence 1 + final def test_compare_reports_a_cadence_mismatch_as_missing_and_extra() -> None: """A golden that records ticks the run did not (and vice versa) is visible.""" level, book, script = load_walk_solo() sparse = run_script(level, book, replace(script, record_every=5)) by_tick = dict(sparse.hashes) golden = {0: by_tick[0], 7: by_tick[5], 10: by_tick[10]} mismatches = compare(sparse, golden) kinds = {mismatch.tick: mismatch.kind for mismatch in mismatches} assert kinds[7] == "missing" # the golden records a tick the run did not assert kinds[5] == "extra" # the run records a tick the golden does not have assert 0 not in kinds and 10 not in kinds # the matching ticks produce nothing assert all(mismatch.changed == () for mismatch in mismatches) # -- the goldens are read-only for the tests ---------------------------------- def test_the_field_diff_walks_mappings_and_missing_keys() -> None: """`counters['trashed']` appears mid-run: the diff must cross the mapping. The `walk_solo` states all share one empty `counters` object (so the early `a is b` return short-circuits it); the `pick_drop_pass` run is what makes the mapping branch and a missing key on one side actually run. """ level, book, script = load_pick_drop_pass() result = run_script(level, book, script) ticks = sorted(result.states) pair: tuple[Any, Any] | None = None for a, b in pairwise(ticks): if bool(result.states[a].counters) != bool(result.states[b].counters): pair = (result.states[a], result.states[b]) break assert pair is not None, "the trashed tick must flip counters from empty to non-empty" changed = _field_diff(*pair) assert "counters['trashed']" in changed, changed def test_the_golden_files_are_never_rewritten_by_the_tests( monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str], ) -> None: """The whole check flow — harness and CLI — must not touch the committed goldens.""" before = ( WALK_SOLO_GOLDEN.read_bytes(), PICK_DROP_PASS_GOLDEN.read_bytes(), ) monkeypatch.setenv("UNDERCOOKED_LEVELS_DIR", str(SHIPPED_LEVELS)) level, book, script = load_pick_drop_pass() # the harness flow assert compare(run_script(level, book, script), golden_map(PICK_DROP_PASS_GOLDEN)) == [] assert main(["check", str(WALK_SOLO_SCRIPT)]) == EXIT_OK # the CLI flow capsys.readouterr() after = ( WALK_SOLO_GOLDEN.read_bytes(), PICK_DROP_PASS_GOLDEN.read_bytes(), ) assert before == after # -- the CLI ------------------------------------------------------------------- def test_check_cli_exits_zero_and_reports_the_match( monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str], ) -> None: monkeypatch.setenv("UNDERCOOKED_LEVELS_DIR", str(SHIPPED_LEVELS)) assert main(["check", str(WALK_SOLO_SCRIPT)]) == EXIT_OK out = capsys.readouterr().out assert "ok: 601 hashes match walk_solo.golden.json" in out def test_check_cli_exits_one_and_names_the_bad_tick_when_the_fixture_is_mutated( monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str], ) -> None: """The task's acceptance test: edit one coordinate, `check` fails and diagnoses.""" monkeypatch.setenv("UNDERCOOKED_LEVELS_DIR", str(SHIPPED_LEVELS)) original = WALK_SOLO_SCRIPT.read_bytes() data = json.loads(original) data["frames"][0]["move"] = [0.0, -1.0] WALK_SOLO_SCRIPT.write_text(json.dumps(data, indent=2), encoding="utf-8") try: assert main(["check", str(WALK_SOLO_SCRIPT)]) == EXIT_MISMATCH finally: WALK_SOLO_SCRIPT.write_bytes(original) out = capsys.readouterr().out assert "first divergent tick 1" in out assert "players[0].pos.y" in out assert WALK_SOLO_SCRIPT.read_bytes() == original # the fixture is left untouched def test_check_cli_exits_two_without_a_golden( monkeypatch: pytest.MonkeyPatch, tmp_path: Path ) -> None: monkeypatch.setenv("UNDERCOOKED_LEVELS_DIR", str(SHIPPED_LEVELS)) script = InputScript( name="no_golden_here", seed=1, level_id="01_first_kitchen", tick_hz=20, frames=(Frame(tick=0, player_id="p0", move=(1.0, 0.0)),), ) path = tmp_path / "no_golden_here.json" script.dump(path) code = main(["check", str(path)]) assert code == EXIT_UNUSABLE def test_check_cli_exits_two_when_the_level_is_not_in_the_content_dir( monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str], ) -> None: """The pick_drop_pass kitchen is a test fixture, not campaign content.""" monkeypatch.setenv("UNDERCOOKED_LEVELS_DIR", str(SHIPPED_LEVELS)) assert main(["check", str(PICK_DROP_PASS_SCRIPT)]) == EXIT_UNUSABLE err = capsys.readouterr().err assert "99_replay_pick_drop_pass" in err def test_record_cli_writes_the_golden_and_check_reads_it_back( monkeypatch: pytest.MonkeyPatch, tmp_path: Path, capsys: pytest.CaptureFixture[str], ) -> None: """`record` is the manual re-bless; into a temp goldens dir, the real one is untouched.""" monkeypatch.setenv("UNDERCOOKED_LEVELS_DIR", str(SHIPPED_LEVELS)) committed_before = WALK_SOLO_GOLDEN.read_bytes() script = InputScript.load(WALK_SOLO_SCRIPT) path = tmp_path / "record_smoke.json" replace(script, name="record_smoke").dump(path) assert main(["record", str(path)], goldens_dir=tmp_path) == EXIT_OK golden = tmp_path / "record_smoke.golden.json" assert golden.exists() assert main(["check", str(path)], goldens_dir=tmp_path) == EXIT_OK capsys.readouterr() assert main(["record", str(path)], goldens_dir=tmp_path) == EXIT_OK # the re-bless note assert "overwriting" in capsys.readouterr().out # and the committed golden never moves: assert WALK_SOLO_GOLDEN.read_bytes() == committed_before # while a fresh record reproduces the committed hash bit for bit: fresh = json.loads(golden.read_text(encoding="utf-8")) assert fresh["hash"] == json.loads(committed_before.decode("utf-8"))["hash"] def test_check_cli_exits_two_on_a_broken_script_file( tmp_path: Path, capsys: pytest.CaptureFixture[str] ) -> None: bad = tmp_path / "broken_script.json" bad.write_text(json.dumps({"seed": 1, "level_id": "x", "bogus": 1}), encoding="utf-8") assert main(["check", str(bad)]) == EXIT_UNUSABLE assert "unknown script key(s): bogus" in capsys.readouterr().err def test_check_cli_exits_two_when_the_content_would_not_load( monkeypatch: pytest.MonkeyPatch, tmp_path: Path, capsys: pytest.CaptureFixture[str] ) -> None: monkeypatch.setenv("UNDERCOOKED_LEVELS_DIR", str(tmp_path / "no_such_dir")) assert main(["check", str(WALK_SOLO_SCRIPT)]) == EXIT_UNUSABLE assert "would not load" in capsys.readouterr().err def test_check_cli_reports_cadence_notes_and_the_missing_and_empty_diff_paths( monkeypatch: pytest.MonkeyPatch, tmp_path: Path, capsys: pytest.CaptureFixture[str], ) -> None: """The three diagnostic branches of a failed check, each named in the report.""" monkeypatch.setenv("UNDERCOOKED_LEVELS_DIR", str(SHIPPED_LEVELS)) level, book, script = load_walk_solo() sparse = replace(script, name="cadence_check", record_every=5) path = tmp_path / "cadence_check.json" sparse.dump(path) assert main(["record", str(path)], goldens_dir=tmp_path) == EXIT_OK # 1. the cadence note: the golden was recorded at 5, the script now says 1 replace(sparse, name="cadence_check", record_every=1).dump(path) assert main(["check", str(path)], goldens_dir=tmp_path) == EXIT_MISMATCH out = capsys.readouterr().out assert "recorded at record_every=5" in out # 2. a `missing` first mismatch: the golden records a tick the run did not missing_path = tmp_path / "missing_first.json" replace(sparse, name="missing_first").dump(missing_path) first_zero = run_script(level, book, sparse).hashes[0][1] (tmp_path / "missing_first.golden.json").write_text( json.dumps( {"name": "missing_first", "tick": 600, "record_every": 5, "hashes": {"0": first_zero, "3": "x" * 64}} ), encoding="utf-8", ) assert main(["check", str(missing_path)], goldens_dir=tmp_path) == EXIT_MISMATCH out = capsys.readouterr().out assert "a golden tick this run did not record" in out # 3. a hash mismatch at tick 0 carries no field diff (the baseline is itself) empty_path = tmp_path / "empty_diff.json" replace(sparse, name="empty_diff").dump(empty_path) (tmp_path / "empty_diff.golden.json").write_text( json.dumps( {"name": "empty_diff", "tick": 1, "record_every": 5, "hashes": {"0": "y" * 64}} ), encoding="utf-8", ) assert main(["check", str(empty_path)], goldens_dir=tmp_path) == EXIT_MISMATCH out = capsys.readouterr().out assert "no field diff" in out # -- the script format --------------------------------------------------------- def test_validate_refuses_a_broken_script_naming_every_problem() -> None: script = InputScript( seed=-1, # < 0 level_id="", # empty tick_hz=10.0, # not 20 record_every=-3, # negative frames=(Frame(tick=-5, player_id="", move=(float("nan"), 1.0), action=0, face="sideways"),), # type: ignore[arg-type] — the guard under test items=(ScriptItem(station="", item="kale", form="soggy"),), ) with pytest.raises(ReplayError) as excinfo: script.validate() message = str(excinfo.value) assert "seed must be an integer in [0, 2**64)" in message assert "level_id must be a non-empty string" in message assert "tick_hz must be 20" in message assert "record_every must be >= 0" in message assert "tick must be a non-negative integer" in message assert "move must be two finite numbers" in message assert "action must be a bool" in message assert "face must be one of" in message assert "item must be an ItemKind value" in message assert "form must be an ItemForm value" in message def test_validate_refuses_a_non_integer_record_every() -> None: script = InputScript( seed=1, level_id="x", tick_hz=20, record_every=1.5, # type: ignore[arg-type] — the guard exists for exactly this ) with pytest.raises(ReplayError, match=r"record_every must be an integer"): script.validate() def test_validate_accepts_the_committed_scripts() -> None: for path in (WALK_SOLO_SCRIPT, PICK_DROP_PASS_SCRIPT): InputScript.load(path).validate() def test_load_refuses_unknown_keys_at_every_level(tmp_path: Path) -> None: bad = tmp_path / "bad.json" bad.write_text( json.dumps( { "seed": 1, "level_id": "x", "tick_hz": 20, "bogus": 1, "frames": [{"tick": 0, "player_id": "p", "move": [1, 0], "extra": 1}], "items": [{"station": "s", "item": "tomato", "form": "raw", "mystery": 2}], } ), encoding="utf-8", ) with pytest.raises(ReplayError, match=r"unknown script key\(s\): bogus"): InputScript.load(bad) bad_frame = tmp_path / "bad_frame.json" bad_frame.write_text( json.dumps( { "seed": 1, "level_id": "x", "tick_hz": 20, "frames": [{"tick": 0, "player_id": "p", "move": [1, 0], "extra": 1}], } ), encoding="utf-8", ) with pytest.raises(ReplayError, match=r"frame 0 has unknown key\(s\): extra"): InputScript.load(bad_frame) bad_item = tmp_path / "bad_item.json" bad_item.write_text( json.dumps( { "seed": 1, "level_id": "x", "tick_hz": 20, "items": [ {"station": "s", "item": "tomato", "form": "raw", "mystery": 2} ], } ), encoding="utf-8", ) with pytest.raises(ReplayError, match=r"item 0 has unknown key\(s\): mystery"): InputScript.load(bad_item) def test_load_refuses_every_malformed_shape(tmp_path: Path) -> None: def writes(name: str, text: str) -> Path: path = tmp_path / name path.write_text(text, encoding="utf-8") return path with pytest.raises(ReplayError, match=r"must be a JSON object, got list"): InputScript.load(writes("top_list.json", "[1, 2, 3]")) with pytest.raises(ReplayError, match=r"missing required key 'seed'"): InputScript.load(writes("no_seed.json", json.dumps({"level_id": "x", "tick_hz": 20}))) with pytest.raises(ReplayError, match=r"frame 0 must be a JSON object"): InputScript.load( writes("frame_scalar.json", json.dumps( {"seed": 1, "level_id": "x", "tick_hz": 20, "frames": [42]})) ) with pytest.raises(ReplayError, match=r"frame 0 is missing required key 'move'"): InputScript.load( writes("frame_no_move.json", json.dumps( {"seed": 1, "level_id": "x", "tick_hz": 20, "frames": [{"tick": 0, "player_id": "p"}]})) ) with pytest.raises(ReplayError, match=r"move must be a two-element array"): InputScript.load( writes("move_not_list.json", json.dumps( {"seed": 1, "level_id": "x", "tick_hz": 20, "frames": [{"tick": 0, "player_id": "p", "move": 1}]})) ) with pytest.raises(ReplayError, match=r"item 0 must be a JSON object"): InputScript.load( writes("item_scalar.json", json.dumps( {"seed": 1, "level_id": "x", "tick_hz": 20, "items": [42]})) ) with pytest.raises(ReplayError, match=r"item 0 is missing required key 'form'"): InputScript.load( writes("item_no_form.json", json.dumps( {"seed": 1, "level_id": "x", "tick_hz": 20, "items": [{"station": "s", "item": "tomato"}]})) ) def test_dump_load_roundtrip_is_lossless(tmp_path: Path) -> None: _, _, script = load_pick_drop_pass() path = tmp_path / "roundtrip.json" script.dump(path) assert InputScript.load(path) == script # an unnamed script dumps without a `name` key; `load` then takes the stem unnamed = replace(script, name="") unnamed_path = tmp_path / "unnamed.json" unnamed.dump(unnamed_path) data = json.loads(unnamed_path.read_text(encoding="utf-8")) assert "name" not in data assert InputScript.load(unnamed_path) == replace(unnamed, name=unnamed_path.stem) def test_run_script_refuses_a_level_id_mismatch() -> None: level, book, script = load_walk_solo() other = replace(script, level_id="99_replay_pick_drop_pass") with pytest.raises(ReplayError, match="names level"): run_script(level, book, other) def test_run_script_refuses_an_item_on_an_unknown_station() -> None: level, book, script = load_walk_solo() broken = replace( script, items=(ScriptItem(station="chop_board_9", item="tomato", form="raw"),), ) with pytest.raises(ReplayError, match="does not have"): run_script(level, book, broken) def test_run_script_refuses_a_negative_max_ticks() -> None: level, book, script = load_pick_drop_pass() with pytest.raises(ReplayError, match="max_ticks"): run_script(level, book, script, max_ticks=-1) def test_a_frameless_script_runs_zero_ticks_and_records_the_built_state() -> None: level, book, _ = load_pick_drop_pass() frameless = InputScript( name="idle", seed=0x5EED, level_id=level.id, tick_hz=20, frames=() ) result = run_script(level, book, frameless) assert result.state.tick == 0 assert [tick for tick, _ in result.hashes] == [0] assert result.events == ()