"""Tests for the input-size cap on the TRANSFORM surfaces (OWASP LLM10).

The scan surfaces (``scan_lexicon`` / ``scan_output``) cap by *truncating*: they
read the prefix, emit an ``oversize-input`` finding, and return findings only.
That trade does not transfer here. ``sanitize`` / ``fence`` / ``neutralize``
return **content**, so truncating would either drop user data silently or hand
back a tail that never went through the transform — a one-line bypass, since an
attacker controls where in the document the payload sits.

So these three fail *secure* instead. The invariant under test:

    returned text is ALWAYS fully transformed, or not returned at all.
"""
import inspect

import pytest

from llm_ingestion_guard import prepare_input
from llm_ingestion_guard.calibration import MAX_INPUT_CHARS
from llm_ingestion_guard.contract import ContractViolation, OversizeInputError
from llm_ingestion_guard.fence import fence
from llm_ingestion_guard.neutralize import neutralize
from llm_ingestion_guard.sanitize import sanitize

# Every transform surface, called through a uniform (text, max) shim so the
# invariant is asserted once per surface rather than restated three times.
TRANSFORMS = (
    ("sanitize", lambda text, cap: sanitize(text, max_input_chars=cap)),
    ("fence", lambda text, cap: fence(text, max_input_chars=cap)),
    ("neutralize", lambda text, cap: neutralize(text, max_input_chars=cap)),
)


@pytest.mark.parametrize("name,call", TRANSFORMS, ids=[n for n, _ in TRANSFORMS])
def test_oversize_input_is_rejected(name, call):
    with pytest.raises(OversizeInputError):
        call("a" * 101, 100)


@pytest.mark.parametrize("name,call", TRANSFORMS, ids=[n for n, _ in TRANSFORMS])
def test_input_exactly_at_the_cap_is_accepted(name, call):
    # The cap is the largest accepted size, not the smallest rejected one.
    result = call("a" * 100, 100)
    assert result.text is not None


@pytest.mark.parametrize("name,call", TRANSFORMS, ids=[n for n, _ in TRANSFORMS])
def test_rejection_is_a_contract_violation(name, call):
    # Subclass, so a pipeline with a broad `except ContractViolation` around its
    # quarantined stage keeps failing closed instead of meeting a new exception
    # type it has never heard of.
    with pytest.raises(ContractViolation) as exc:
        call("a" * 101, 100)
    assert exc.value.code == "oversize-input"


@pytest.mark.parametrize("name,call", TRANSFORMS, ids=[n for n, _ in TRANSFORMS])
def test_error_carries_sizes_never_content(name, call):
    # Same alert-safety property ContractViolation already promises: the raised
    # object must be routable to an alert channel without leaking the payload.
    secret = "CANARYVALUE"
    with pytest.raises(OversizeInputError) as exc:
        call(secret * 100, 100)
    assert secret not in str(exc.value)
    assert not any(secret in d for d in exc.value.details)
    # Substring, not tuple membership: `details` is ("sanitize",), so `"101" not
    # in details` would pass trivially and keep passing if a size were ever
    # folded into the string.
    assert not any("101" in d for d in exc.value.details)
    assert name in exc.value.details


@pytest.mark.parametrize("name,call", TRANSFORMS, ids=[n for n, _ in TRANSFORMS])
def test_error_reports_both_the_size_and_the_cap(name, call):
    with pytest.raises(OversizeInputError) as exc:
        call("a" * 101, 100)
    message = str(exc.value)
    assert "101" in message and "100" in message


@pytest.mark.parametrize("name,call", TRANSFORMS, ids=[n for n, _ in TRANSFORMS])
def test_under_cap_is_unchanged_by_the_guard(name, call):
    # The cap must not perturb the ordinary path: clean prose still round-trips
    # the way each surface's own tests already pin.
    result = call("ordinary prose", 100)
    assert "ordinary prose" in result.text


@pytest.mark.parametrize(
    "func", [sanitize, fence, neutralize], ids=["sanitize", "fence", "neutralize"]
)
def test_default_cap_comes_from_calibration(func):
    # Calibration numbers live in ONE module; a literal re-typed at a call site
    # is the drift this pins against.
    default = inspect.signature(func).parameters["max_input_chars"].default
    assert default == MAX_INPUT_CHARS


def test_prepare_input_inherits_the_cap():
    # The input path is sanitize -> fence, and step 1 is where the document
    # arrives, so the whole path is bounded by sanitize's guard alone.
    with pytest.raises(OversizeInputError):
        prepare_input("a" * (MAX_INPUT_CHARS + 1))


def test_prepare_input_accepts_a_document_at_the_cap():
    result = prepare_input("a" * MAX_INPUT_CHARS)
    assert result.fenced