interactive-story/backend/tests/test_history_block_trim.py

"""The history window moves in blocks, so the prompt's prefix holds still.

Inference servers cache a prompt by its **prefix**. While a story only grows at
the end, every turn re-uses that cache and pays for its own new tokens alone. The
builder's old window took whatever fit, which meant that once the budget was full
it dropped the *oldest* action every turn — a change near the front of the prompt
— and everything after it had to be processed again.

Measured on the reference deployment, at 7.7k prompt tokens against a 3B model:

    window slid by one turn   343-350 s
    prefix preserved            6.0 s

These tests do not measure time. They pin the property the measurement is
downstream of: **the oldest included action is the same across consecutive
turns**, except on the turns where the window deliberately steps.
"""
import pytest
import pytest as _pytest

from app.context import builder


def costs_of(n, each=100):
    return [each] * n


def depths(n, start=1):
    return list(range(start, start + n))


# ------------------------------------------------------------- the block size

def test_the_block_is_a_share_of_what_fits():
    """Derived from `TRIM_FRACTION` rather than asserting the number it is
    currently set to, so retuning the dial does not fail a test that was never
    about the dial's value."""
    # 16 actions of 500 fit in 8,000, and the block is that share of them.
    assert builder.trim_block(8000, 500) == 16 // builder.TRIM_FRACTION


def test_trim_fraction_is_the_dial_between_history_and_speed():
    """`TRIM_FRACTION` is meant to be retuned, so this pins what retuning does.

    Lower it and the window gives up more at once: bigger blocks, fewer re-reads,
    less recent history retained. Raise it and the reverse. Nothing else in the
    builder has to change for that to hold, which is the property worth having a
    test for.
    """
    budget, per_action = 8000, 500
    fits = budget // per_action

    def block_at(fraction, monkeypatch):
        monkeypatch.setattr(builder, "TRIM_FRACTION", fraction)
        return builder.trim_block(budget, per_action)

    with _pytest.MonkeyPatch.context() as mp:
        greedier = block_at(2, mp)
        assert greedier == fits // 2
    with _pytest.MonkeyPatch.context() as mp:
        gentler = block_at(8, mp)
        assert gentler == max(builder.MIN_TRIM_BLOCK, fits // 8)
    assert greedier > gentler, "a lower fraction must give up more at once"

    # And the floor to the whole thing survives any setting.
    with _pytest.MonkeyPatch.context() as mp:
        mp.setattr(builder, "TRIM_FRACTION", 1000)
        assert builder.trim_block(budget, per_action) >= builder.MIN_TRIM_BLOCK


def test_the_block_never_slides_by_one():
    """A block of one is the old behaviour wearing a hat."""
    assert builder.trim_block(100, 500) >= builder.MIN_TRIM_BLOCK
    assert builder.trim_block(0, 500) >= builder.MIN_TRIM_BLOCK


def test_the_block_comes_from_settings_not_from_the_story():
    """It has to be the same on two consecutive turns, so it cannot be measured
    from actions whose sizes vary."""
    assert builder.trim_block(8000, 500) == builder.trim_block(8000, 500)
    # Bigger budget, bigger step; the ratio is what is fixed.
    assert builder.trim_block(16000, 500) > builder.trim_block(8000, 500)


# ------------------------------------------------------- nothing to trim yet

def test_a_story_that_fits_whole_is_not_trimmed():
    """Also the append-only regime: every turn is a prefix extension already."""
    assert builder.history_floor(depths(5), costs_of(5), budget=10_000, block=4) is None


def test_a_short_story_keeps_its_opening():
    """Snapping here would drop the start of the story for no reason at all."""
    assert builder.history_floor(depths(3), costs_of(3), budget=10_000, block=8) is None


def test_an_action_larger_than_the_budget_is_left_to_the_caller():
    assert builder.history_floor([1], [5000], budget=100, block=4) is None


def test_rows_without_a_depth_are_not_trimmed():
    """Legacy rows have no stable coordinate, so behave exactly as before."""
    assert builder.history_floor([None, None], costs_of(2), 100, 4) is None
    assert builder.history_floor([], [], 100, 4) is None


# ------------------------------------------------------------ the whole point

def test_the_floor_holds_still_while_the_story_grows():
    """The property the 57x measurement rests on.

    Ten consecutive turns against a full budget. The floor must take a small
    number of steps, not ten.
    """
    block, budget, each = 4, 1000, 100          # 10 actions fit
    seen = []
    for extra in range(10):                     # the story grows by one action
        n = 20 + extra
        seen.append(builder.history_floor(depths(n), costs_of(n, each), budget, block))

    steps = sum(1 for a, b in zip(seen, seen[1:]) if a != b)
    assert steps <= 3, f"the floor moved {steps} times in 10 turns: {seen}"
    assert len(set(seen)) > 1, "it never moved at all, so the budget is not binding"


def test_every_floor_sits_on_a_block_boundary():
    block, budget = 4, 1000
    for n in range(20, 40):
        floor = builder.history_floor(depths(n), costs_of(n), budget, block)
        assert floor is not None
        assert floor % block == 0, f"{floor} is not a multiple of {block}"


def test_the_floor_only_ever_moves_forward():
    block, budget = 4, 1000
    floors = [builder.history_floor(depths(n), costs_of(n), budget, block)
              for n in range(20, 45)]
    assert floors == sorted(floors)


# --------------------------------------------------- and still inside budget

@pytest.mark.parametrize("n", range(20, 40))
def test_the_kept_window_never_exceeds_the_budget(n):
    """M03's bound is not weakened. Trimming only ever drops more, never less."""
    block, budget, each = 4, 1000, 100
    ds, cs = depths(n), costs_of(n, each)
    floor = builder.history_floor(ds, cs, budget, block)
    kept = sum(c for d, c in zip(ds, cs) if d >= floor)
    assert kept <= budget


@pytest.mark.parametrize("n", range(20, 40))
def test_the_kept_window_is_not_gutted(n):
    """The cost of holding still is bounded: a trim gives up `block` actions,
    never most of the window."""
    block, budget, each = 4, 1000, 100
    ds, cs = depths(n), costs_of(n, each)
    floor = builder.history_floor(ds, cs, budget, block)
    kept = sum(c for d, c in zip(ds, cs) if d >= floor)
    assert kept >= budget - block * each


# ------------------------------------------- the real builder, end to end

import pytest as _pytest  # noqa: E402  (grouped with the fixtures it serves)

from app import models  # noqa: E402
from app.context import builder as _builder  # noqa: E402
from app.database import Base, SessionLocal, engine  # noqa: E402

NARRATION = ("The rain came down over Westhaven in long grey sheets and the "
             "gutters ran full from the ridge to the waterfront. ") * 6


@_pytest.fixture()
def saturated():
    """A campaign whose history is longer than its budget, with real depths.

    `depth` is what the floor is expressed in, and every action written through
    the application has one (`tree.place_action`). The older fixtures in
    `test_history_window.py` predate the tree and leave it null, which is why
    trimming does not engage there and those tests still describe the old
    behaviour exactly.
    """
    Base.metadata.create_all(bind=engine)
    db = SessionLocal()
    user = models.User(is_guest=False, email="blocktrim@example.com")
    db.add(user)
    db.flush()
    settings = models.Settings(user_id=user.id, model="m", embedding_model="",
                               context_token_budget=2048, max_output_tokens=200)
    db.add(settings)
    adventure = models.Adventure(user_id=user.id, title="Long", script_state={})
    db.add(adventure)
    db.flush()
    for i in range(60):
        db.add(models.Action(adventure_id=adventure.id,
                             type="ai" if i % 2 else "do",
                             text=f"[{i}] {NARRATION}", branch_id=None, depth=i))
    db.commit()
    db.expire_all()
    adventure = db.get(models.Adventure, adventure.id)
    settings = db.get(models.Settings, settings.id)
    try:
        yield db, adventure, settings
    finally:
        db.close()
        Base.metadata.drop_all(bind=engine)


def _play_one_more(db, adventure, at_depth):
    db.add(models.Action(adventure_id=adventure.id, type="do",
                         text=f"[{at_depth}] {NARRATION}", depth=at_depth))
    # `at_depth` may be None: the control below plays a turn into a story whose
    # rows predate the tree, which is the ungoverned window this replaced.
    db.commit()
    db.expire_all()


def _shared_prefix(before: str, after: str) -> float:
    """How much of the old prompt the new one still opens with, 0.0 to 1.0.

    This is the quantity the inference server's cache is keyed on, so it is the
    quantity worth asserting. It is not 1.0 even in the best case: the prompt
    ends with the turn's length-hint and state-block instructions, which sit
    *after* the history, so appending a turn always rewrites that tail.
    """
    shared = 0
    for x, y in zip(before, after):
        if x != y:
            break
        shared += 1
    return shared / max(1, len(before))


def test_the_story_prompt_keeps_its_prefix_across_a_new_turn(saturated):
    """The property the whole change exists for.

    Not a timing test — it asserts what the timing follows from. The story text
    a turn sends still opens with almost all of what the previous turn sent, so
    the server's prompt cache covers that part and only the tail is processed.
    """
    db, adventure, settings = saturated
    _, before, report_before = _builder.build_context(adventure, settings)
    assert report_before["history"]["floor_depth"] is not None, (
        "this fixture is meant to be over budget; trimming never engaged")

    _play_one_more(db, adventure, 60)
    _, after, report_after = _builder.build_context(adventure, settings)

    assert report_after["history"]["floor_depth"] == report_before["history"]["floor_depth"]
    assert _shared_prefix(before, after) > 0.85


def test_without_a_stable_floor_the_prefix_collapses(saturated):
    """The control, and the behaviour this replaced.

    Rows with no `depth` cannot be placed on the tree, so the floor cannot be
    computed and the window takes whatever fits — sliding by one action every
    turn. The new prompt then starts with a *different* action, the shared
    prefix collapses, and the server reprocesses essentially the whole thing.
    That is the 343s case in this module's docstring.
    """
    db, adventure, settings = saturated
    for action in db.query(models.Action).all():
        action.depth = None
    db.commit()
    db.expire_all()

    _, before, report = _builder.build_context(adventure, settings)
    assert report["history"]["floor_depth"] is None
    _play_one_more(db, adventure, None)
    _, after, _ = _builder.build_context(adventure, settings)

    assert _shared_prefix(before, after) < 0.1


def test_the_window_does_step_eventually(saturated):
    """It holds still, but it must not hold still for ever — the budget is a
    bound, and a window that never moved would break it."""
    db, adventure, settings = saturated
    first = _builder.build_context(adventure, settings)[2]["history"]["floor_depth"]

    seen = {first}
    for depth in range(60, 90):
        _play_one_more(db, adventure, depth)
        seen.add(_builder.build_context(adventure, settings)[2]["history"]["floor_depth"])
    assert len(seen) > 1, "the floor never moved across 30 turns"


def test_the_prompt_stays_inside_the_budget_as_the_window_steps(saturated):
    """M03's bound, across the step. Trimming only ever drops more history."""
    db, adventure, settings = saturated
    for depth in range(60, 85):
        _play_one_more(db, adventure, depth)
        report = _builder.build_context(adventure, settings)[2]
        assert report["tokens"]["total"] <= report["tokens"]["budget"]