"""v1.1 WP-B.2 (B2.3): what the memory summariser is shown of a long block.

v1.0.0 sent the last 2,000 tokens of a block, so a fact early in a longer block
never reached the summariser (B.1 §E). A block that fits is still sent whole. A
longer one is now sent as its opening and its end, with a marker between them,
inside the same 2,000-token budget.

The scenario-level test (the planted fact early in a long block, remembered) is
in `test_v11_b1_memory_diagnostic.py`.

    python -m pytest tests/test_v11_b2_memory_excerpt.py -v
"""

import asyncio
import random

import pytest

from app import memorybank, models, tree
from app.context import builder
from app.database import Base, SessionLocal, engine

BUDGET = memorybank.MEMORY_EXCERPT_TOKENS
MARKER = memorybank.EXCERPT_OMISSION_MARKER
FILLER = "The travellers walked the long grey road north past the salt market and the reed beds. "


def words_to_tokens(tokens: int) -> str:
    """Filler at least `tokens` long."""
    text = FILLER
    while builder.count_tokens(text) < tokens:
        text += FILLER
    return text


# --------------------------------------------------------------- the excerpt


def test_a_block_that_fits_is_sent_whole_and_unchanged():
    raw = words_to_tokens(BUDGET - 200)
    assert builder.count_tokens(raw) <= BUDGET
    assert memorybank.memory_excerpt(raw) == raw


def test_a_block_of_exactly_the_budget_is_unchanged():
    raw = words_to_tokens(BUDGET)
    tokens = memorybank._excerpt_encoding().encode(raw)[:BUDGET]
    exact = memorybank._excerpt_encoding().decode(tokens)
    if builder.count_tokens(exact) == BUDGET:
        assert memorybank.memory_excerpt(exact) == exact


def test_a_long_block_keeps_its_opening_and_its_end_in_order():
    opening = "Mara slipped the amber sundial inside the cracked teapot. "
    ending = "Aldric finally reached the north gate at dawn."
    raw = opening + words_to_tokens(3 * BUDGET) + ending
    excerpt = memorybank.memory_excerpt(raw)
    assert excerpt.startswith(opening)
    assert excerpt.endswith(ending)
    head, _, tail = excerpt.partition(f"\n\n{MARKER}\n\n")
    assert tail, "the marker must sit between the two parts"
    assert excerpt.index(opening) < excerpt.index(MARKER) < excerpt.index(ending)


def test_the_split_is_even_and_documented():
    raw = words_to_tokens(4 * BUDGET)
    head_budget, tail_budget = memorybank.excerpt_split(BUDGET)
    marker_tokens = builder.count_tokens(f"\n\n{MARKER}\n\n")
    assert head_budget + tail_budget + marker_tokens == BUDGET
    assert abs(head_budget - tail_budget) <= 1
    excerpt = memorybank.memory_excerpt(raw)
    head, _, tail = excerpt.partition(f"\n\n{MARKER}\n\n")
    # Each part is cut as a run of `head_budget` / `tail_budget` tokens. Measured
    # on its own, a cut run can come to one token more, because the text either
    # side of the cut tokenises differently once it is separated; the hard limit
    # is the whole excerpt, tested below.
    assert builder.count_tokens(head) <= head_budget + 1
    assert builder.count_tokens(tail) <= tail_budget + 1
    assert builder.count_tokens(excerpt) <= BUDGET


@pytest.mark.parametrize("extra", [1, 7, 500, BUDGET, 9 * BUDGET])
def test_the_excerpt_never_exceeds_the_budget(extra):
    raw = words_to_tokens(BUDGET + extra)
    excerpt = memorybank.memory_excerpt(raw)
    assert builder.count_tokens(excerpt) <= BUDGET
    assert memorybank.memory_excerpt(raw) == excerpt  # deterministic


@pytest.mark.parametrize("seed", range(4))
def test_the_budget_holds_for_awkward_text(seed):
    """Token boundaries can merge differently once the parts are rejoined, and
    text that is not plain English tokenises unevenly. The budget still holds."""
    rng = random.Random(seed)
    alphabet = "abcdefghij ÄÖÜ ßé漢字かな 🙂🐉 \n\t.,;:—'\""
    raw = "".join(rng.choice(alphabet) for _ in range(12000))
    assert builder.count_tokens(memorybank.memory_excerpt(raw)) <= BUDGET


def test_a_fact_in_the_middle_of_a_very_long_block_is_still_omitted():
    """The documented limit of a bounded excerpt: head and tail, not everything."""
    half = words_to_tokens(3 * BUDGET)
    raw = half + "Mara slipped the amber sundial inside the cracked teapot. " + half
    assert "sundial" not in memorybank.memory_excerpt(raw)


# ------------------------------------------------------------ memory creation


class EchoSummariser:
    """Returns the whole excerpt it was given as the memory: the worst case for
    a marker leaking into stored text."""

    def __init__(self):
        self.users: list[str] = []

    async def complete(self, system, user, *, temperature=0.3, max_tokens=400):
        self.users.append(user)
        return user.split("Story excerpt:\n\n", 1)[-1].rsplit("\n\nMemory:", 1)[0]


@pytest.fixture()
def db():
    Base.metadata.create_all(bind=engine)
    session = SessionLocal()
    try:
        yield session
    finally:
        session.close()
        Base.metadata.drop_all(bind=engine)


def campaign(db, texts):
    user = models.User(is_guest=False, email="b2-excerpt@example.com")
    db.add(user)
    db.flush()
    db.add(models.Settings(user_id=user.id, model="m", embedding_model=""))
    adventure = models.Adventure(user_id=user.id, title="Excerpt", script_state={},
                                 auto_summarize=True, memory_bank_enabled=True)
    db.add(adventure)
    db.flush()
    nodes = []
    for i, text in enumerate(texts):
        action = models.Action(adventure_id=adventure.id, type="ai" if i % 2 else "do", text=text)
        tree.place_action(db, adventure, action)
        db.add(action)
        db.flush()
        nodes.append(action)
    db.commit()
    return adventure, nodes


def write_memory(db, adventure, monkeypatch, summariser):
    monkeypatch.setattr(memorybank, "MEMORY_START", 0)
    monkeypatch.setattr(memorybank, "MAX_MEMORIES_PER_RUN", 1)
    monkeypatch.setattr(memorybank, "summary_provider", lambda s: summariser)
    settings = db.query(models.Settings).first()
    asyncio.run(memorybank._create_due_memories(adventure, settings, db))
    return db.query(models.Memory).filter_by(adventure_id=adventure.id).all()


def test_the_marker_is_never_stored_as_part_of_a_memory(db, monkeypatch):
    long = words_to_tokens(800)
    adventure, _ = campaign(db, [long] * (memorybank.MEMORY_INTERVAL + memorybank.SETTLE_SLACK))
    summariser = EchoSummariser()
    [memory] = write_memory(db, adventure, monkeypatch, summariser)
    assert MARKER in summariser.users[0]  # the summariser was told
    assert MARKER not in memory.text  # and the memory does not repeat it
    assert "[…" not in memory.text and "omitted" not in memory.text


def test_a_short_block_is_prompted_exactly_as_before(db, monkeypatch):
    texts = [f"Short action {i}." for i in range(memorybank.MEMORY_INTERVAL + memorybank.SETTLE_SLACK)]
    adventure, _ = campaign(db, texts)
    summariser = EchoSummariser()
    write_memory(db, adventure, monkeypatch, summariser)
    block = "\n\n".join(texts[:memorybank.MEMORY_INTERVAL])
    assert summariser.users[0] == f"Story excerpt:\n\n{block}\n\nMemory:"


def test_a_long_blocks_memory_keeps_its_source_provenance(db, monkeypatch):
    early = "Mara slipped the amber sundial inside the cracked teapot. " + words_to_tokens(900)
    texts = [early] + [words_to_tokens(900)] * (memorybank.MEMORY_INTERVAL + memorybank.SETTLE_SLACK - 1)
    adventure, nodes = campaign(db, texts)
    [memory] = write_memory(db, adventure, monkeypatch, EchoSummariser())
    block = nodes[:memorybank.MEMORY_INTERVAL]
    assert "sundial" in memory.text  # the early fact reached the summariser
    assert (memory.source_start, memory.source_end) == (block[0].depth, block[-1].depth)
    assert (memory.branch_id, memory.depth) == (block[-1].branch_id, block[-1].depth)