bikoret/azazel_processor/test/test_azazel.py

"""
Tests for the Azazel orchestrator (commit 5).

Property coverage:
  - Property 5  (provisioned infrastructure / sukkot): checkpoints
                are persisted at every step; in-flight files exist
                during the route and are shredded after RECORDED.
  - Property 7  (authorized routing): AzazelRecord carries
                authorized_by + shaliach + routing=ERETZ_GEZERAH.
  - Property 10 (hard termination): AzazelRecord does NOT carry the
                disposed payload; payload references in the shaliach
                are cleared at the DESTROYED checkpoint.

The structural tests in test_azazel_no_payload_field_in_record and
test_azazel_no_recover_disposed_function are the load-bearing CI
invariants — they catch future contributors who weaken property 10.
"""

import json
import pathlib
import tempfile

import pytest

from azazel_processor.azazel import (
    AzazelInput,
    dispatch_for_disposal,
    list_in_flight,
    _persist_checkpoint,
)
from azazel_processor.azazel_record import AzazelRecord
from azazel_processor.eretz_gezerah import ERETZ_GEZERAH, is_eretz_gezerah
from azazel_processor.protocol import authorize_disposal
from azazel_processor.shaliach import IshItti, ShaliachError
from azazel_processor.stages import AzazelStage
from azazel_processor.vidui import confess_empty_vital


@pytest.fixture
def tmp_in_flight():
    """Per-test in-flight directory so tests don't share checkpoint state."""
    with tempfile.TemporaryDirectory(prefix="azazel-test-") as d:
        yield pathlib.Path(d)


@pytest.fixture
def active_handler():
    h = IshItti("aharon-the-shaliach")
    h.activate()
    yield h
    if h.is_active():
        h.tevilah()


@pytest.fixture(autouse=True)
def _envelope():
    """Open the protocol envelope around every test in this module.
    The protocol restriction (property 8) is verified separately in
    test_protocol_restriction.py; the orchestrator tests assume the
    envelope is open so they can exercise the rest of the state
    machine without re-opening per dispatch."""
    with authorize_disposal():
        yield


def _make_input(case_ref="case-001", payload=None):
    return AzazelInput(
        case_ref=case_ref,
        payload=payload if payload is not None else {"data": "would-be-disposed"},
        classification="empty_vital",
        triggering_call="external_offering.consult_external_model",
    )


def _vidui():
    return confess_empty_vital(
        "Claude response with no extractable Torah", confessor="kohen-gadol"
    )


# ============================================================
# Happy path — full state machine
# ============================================================


def test_dispatch_returns_an_azazel_record(active_handler, tmp_in_flight):
    record = dispatch_for_disposal(
        _make_input(),
        handler=active_handler,
        confess_with=_vidui(),
        authorized_by="kohen-gadol",
        in_flight_dir=tmp_in_flight,
    )
    assert isinstance(record, AzazelRecord)


def test_record_carries_authorization_and_shaliach_attribution(
    active_handler, tmp_in_flight
):
    """Property 7: routing decision is OWNED."""
    record = dispatch_for_disposal(
        _make_input(),
        handler=active_handler,
        confess_with=_vidui(),
        authorized_by="kohen-gadol-aharon",
        in_flight_dir=tmp_in_flight,
    )
    assert record.authorized_by == "kohen-gadol-aharon"
    assert record.shaliach == "aharon-the-shaliach"


def test_record_routes_to_eretz_gezerah(active_handler, tmp_in_flight):
    """Property 7 + 12: destination is the canonical sentinel."""
    record = dispatch_for_disposal(
        _make_input(),
        handler=active_handler,
        confess_with=_vidui(),
        authorized_by="kohen-gadol",
        in_flight_dir=tmp_in_flight,
    )
    assert is_eretz_gezerah(record.routing)
    assert record.routing is ERETZ_GEZERAH


def test_record_carries_the_full_vidui(active_handler, tmp_in_flight):
    v = _vidui()
    record = dispatch_for_disposal(
        _make_input(),
        handler=active_handler,
        confess_with=v,
        authorized_by="kohen-gadol",
        in_flight_dir=tmp_in_flight,
    )
    assert record.vidui is v
    assert record.vidui.chatot == ("empty-vital offering: Claude response with no extractable Torah",)


# ============================================================
# Property 10: hard termination — no payload in the record
# ============================================================


def test_azazel_record_does_not_carry_payload(active_handler, tmp_in_flight):
    """Property 10: the disposed thing is destroyed; only the vidui
    remains. The AzazelRecord has no `payload` attribute and would-be
    payloads are not findable via vars()."""
    secret_payload = {"sensitive": "this-must-be-disposed-not-stored"}
    record = dispatch_for_disposal(
        _make_input(payload=secret_payload),
        handler=active_handler,
        confess_with=_vidui(),
        authorized_by="kohen-gadol",
        in_flight_dir=tmp_in_flight,
    )

    # The record must not have a payload field, by name
    assert not hasattr(record, "payload")
    # The record's serialized form must not contain the payload's
    # marker string
    serialized = json.dumps(record.to_storage_dict())
    assert "this-must-be-disposed-not-stored" not in serialized


def test_no_payload_field_in_azazel_record_dataclass():
    """STRUCTURAL CI INVARIANT: AzazelRecord's field set must NOT
    include `payload` (or any obvious alias). A future contributor
    who adds a payload-bearing field violates property 10 and this
    test fires before the regression ships."""
    fields = set(AzazelRecord.__dataclass_fields__.keys())
    forbidden = {"payload", "raw_payload", "disposed_payload", "data", "content"}
    overlap = fields & forbidden
    assert overlap == set(), (
        f"AzazelRecord has payload-shaped field(s): {overlap}. Property "
        f"10 (hard termination): the disposed payload MUST NOT be "
        f"persisted on the record. Remove the field or reconsider."
    )


def test_no_recover_disposed_function_in_module():
    """STRUCTURAL CI INVARIANT: there must be no recover_disposed,
    undispose, restore_payload, or similar function in
    azazel_processor's public surface. Property 10: no return path.
    Eretz gezerah."""
    import azazel_processor

    public = [n for n in dir(azazel_processor) if not n.startswith("_")]
    forbidden_substrings = ("recover", "undispose", "restore", "rehydrate", "retrieve")

    offenders = [
        name
        for name in public
        for sub in forbidden_substrings
        if sub in name.lower()
    ]

    assert offenders == [], (
        f"azazel_processor exposes recovery-shaped names: {offenders}. "
        f"Property 10: there is no return path. Eretz gezerah."
    )


def test_payload_references_cleared_at_destroyed_checkpoint(
    active_handler, tmp_in_flight
):
    """The shaliach's payload-refs list must be empty after dispatch
    completes. Property 10 — the handler does not retain the disposed
    payload."""
    dispatch_for_disposal(
        _make_input(payload={"big": "payload"}),
        handler=active_handler,
        confess_with=_vidui(),
        authorized_by="kohen-gadol",
        in_flight_dir=tmp_in_flight,
    )
    assert active_handler.held_payload_count() == 0


# ============================================================
# Property 5: provisioned infrastructure — sukkot persistence
# ============================================================


def test_in_flight_file_is_shredded_after_recorded_checkpoint(
    active_handler, tmp_in_flight
):
    """After the disposal completes (RECORDED done), the in-flight
    file is unlinked. The disposal is permanent in L3 (commit 7);
    the in-flight artifact must not linger."""
    dispatch_for_disposal(
        _make_input(case_ref="case-shred-001"),
        handler=active_handler,
        confess_with=_vidui(),
        authorized_by="kohen-gadol",
        in_flight_dir=tmp_in_flight,
    )
    assert list_in_flight(tmp_in_flight) == []


def test_checkpoint_is_persisted_at_each_stage(active_handler, tmp_in_flight):
    """Verify state is persisted incrementally: capture the file at
    each checkpoint via custom recorder/acknowledger callbacks."""
    seen_at = {}

    def at_acknowledged(record):
        # By ACKNOWLEDGED, the in-flight file must contain
        # last_completed = ACKNOWLEDGED's PRIOR step (DESTROYED).
        # We've persisted ACKNOWLEDGED before invoking ack? No — we
        # invoke ack AT this checkpoint, then persist. So when this
        # callback fires, the file shows last_completed = DESTROYED.
        # Actually, looking at the orchestrator: we invoke
        # acknowledger() first, then persist ACKNOWLEDGED.
        body = json.loads((tmp_in_flight / "case-cp-001.json").read_text())
        seen_at["ack"] = body["last_completed"]

    def at_recorded(record):
        body = json.loads((tmp_in_flight / "case-cp-001.json").read_text())
        seen_at["rec"] = body["last_completed"]

    dispatch_for_disposal(
        _make_input(case_ref="case-cp-001"),
        handler=active_handler,
        confess_with=_vidui(),
        authorized_by="kohen-gadol",
        in_flight_dir=tmp_in_flight,
        acknowledger=at_acknowledged,
        recorder=at_recorded,
    )

    # When acknowledger fired, last_completed should be DESTROYED
    # (the ack callback runs BEFORE we persist the ACKNOWLEDGED
    # checkpoint).
    assert seen_at["ack"] == AzazelStage.DESTROYED.value
    # When recorder fired, last_completed should be ACKNOWLEDGED.
    assert seen_at["rec"] == AzazelStage.ACKNOWLEDGED.value


def test_list_in_flight_returns_partial_disposals(tmp_in_flight):
    """If we manually persist a partial state (simulating a crash),
    list_in_flight surfaces it for resume."""
    # Manually create an in-flight file at the CONFESSED checkpoint.
    _persist_checkpoint(
        tmp_in_flight,
        "case-partial-001",
        AzazelStage.CONFESSED,
        {"shaliach": "aharon"},
    )
    inflight = list_in_flight(tmp_in_flight)
    assert len(inflight) == 1
    assert inflight[0]["case_ref"] == "case-partial-001"
    assert inflight[0]["last_completed"] == "confessed"


def test_list_in_flight_empty_when_no_disposals(tmp_in_flight):
    assert list_in_flight(tmp_in_flight) == []


def test_checkpoint_persistence_is_atomic(active_handler, tmp_in_flight):
    """The persist path uses write-then-rename so a crash mid-write
    leaves the previous checkpoint intact rather than a half-written
    file. We can't easily simulate a crash, but we CAN verify the
    final file is valid JSON at every checkpoint visit."""
    files_seen = []

    def at_recorded(record):
        # Inspect the current file
        if (tmp_in_flight / "case-atom-001.json").exists():
            text = (tmp_in_flight / "case-atom-001.json").read_text()
            files_seen.append(json.loads(text))  # raises if invalid

    dispatch_for_disposal(
        _make_input(case_ref="case-atom-001"),
        handler=active_handler,
        confess_with=_vidui(),
        authorized_by="kohen-gadol",
        in_flight_dir=tmp_in_flight,
        recorder=at_recorded,
    )
    assert len(files_seen) == 1
    assert files_seen[0]["last_completed"] == "acknowledged"


# ============================================================
# Role gate — property 4 still enforced
# ============================================================


def test_dispatch_refuses_inactive_handler(tmp_in_flight):
    h = IshItti("aharon")
    # Not activated
    with pytest.raises(ShaliachError):
        dispatch_for_disposal(
            _make_input(),
            handler=h,
            confess_with=_vidui(),
            authorized_by="kohen-gadol",
            in_flight_dir=tmp_in_flight,
        )


def test_dispatch_refuses_non_ish_itti(tmp_in_flight):
    with pytest.raises(ShaliachError):
        dispatch_for_disposal(
            _make_input(),
            handler="not-a-handler",  # type: ignore[arg-type]
            confess_with=_vidui(),
            authorized_by="kohen-gadol",
            in_flight_dir=tmp_in_flight,
        )


# ============================================================
# Filename safety
# ============================================================


def test_dispatch_rejects_case_ref_with_slash(active_handler, tmp_in_flight):
    bad = AzazelInput(
        case_ref="../escape/attempt",
        payload={},
        classification="empty_vital",
    )
    with pytest.raises(ValueError):
        dispatch_for_disposal(
            bad,
            handler=active_handler,
            confess_with=_vidui(),
            authorized_by="kohen-gadol",
            in_flight_dir=tmp_in_flight,
        )


def test_dispatch_rejects_case_ref_with_nul(active_handler, tmp_in_flight):
    bad = AzazelInput(
        case_ref="case\0nul",
        payload={},
        classification="empty_vital",
    )
    with pytest.raises(ValueError):
        dispatch_for_disposal(
            bad,
            handler=active_handler,
            confess_with=_vidui(),
            authorized_by="kohen-gadol",
            in_flight_dir=tmp_in_flight,
        )


# ============================================================
# AzazelRecord validation
# ============================================================


def test_record_requires_authorized_by():
    with pytest.raises(ValueError):
        AzazelRecord(
            case_ref="x",
            vidui=_vidui(),
            routing=ERETZ_GEZERAH,
            authorized_by="",
            shaliach="aharon",
        )


def test_record_requires_shaliach():
    with pytest.raises(ValueError):
        AzazelRecord(
            case_ref="x",
            vidui=_vidui(),
            routing=ERETZ_GEZERAH,
            authorized_by="kohen-gadol",
            shaliach="",
        )


def test_record_to_storage_dict_omits_payload():
    """The serialization for L3 must not contain a payload field."""
    record = AzazelRecord(
        case_ref="case-storage-001",
        vidui=_vidui(),
        routing=ERETZ_GEZERAH,
        authorized_by="kohen-gadol",
        shaliach="aharon",
    )
    body = record.to_storage_dict()
    assert "payload" not in body
    assert "raw_payload" not in body
    assert body["routing"] == "eretz_gezerah"
    assert body["authorized_by"] == "kohen-gadol"
    assert body["shaliach"] == "aharon"


def test_record_is_frozen():
    record = AzazelRecord(
        case_ref="case-frozen-001",
        vidui=_vidui(),
        routing=ERETZ_GEZERAH,
        authorized_by="kohen-gadol",
        shaliach="aharon",
    )
    with pytest.raises((AttributeError, Exception)):
        record.shaliach = "different"  # type: ignore[misc]