FabledCurator/tests/test_api_workers.py

"""/api/system/workers — the lane dial (milestone 422 step 2).

Exercises the real endpoint against the real database. Only `celery inspect`
is stubbed, and only to keep the suite fast: an unstubbed inspect blocks for
its full 2s timeout per call with no workers to answer, which several writes
would turn into most of the lane's runtime.
"""

import pytest
import pytest_asyncio
from sqlalchemy import select

from backend.app.models import WorkerLane
from backend.app.services import worker_control as wc
from backend.app.services.worker_lanes import LANES

pytestmark = pytest.mark.integration


@pytest_asyncio.fixture
async def no_live_workers(monkeypatch):
    """Nothing is running — which is the CI lane's actual truth, asserted
    rather than waited for. Makes every push fail, which is the interesting
    half: the setting must still be stored."""
    monkeypatch.setattr(
        wc, "inspect_lanes_sync",
        lambda: {lane.name: wc.LaneLiveState() for lane in LANES},
    )


async def _lane_row(db, name: str) -> WorkerLane:
    return (await db.execute(
        select(WorkerLane).where(WorkerLane.name == name)
    )).scalar_one()


# --- reading -----------------------------------------------------------------


@pytest.mark.asyncio
async def test_get_lists_every_lane_with_its_ceiling(client, no_live_workers):
    resp = await client.get("/api/system/workers")
    assert resp.status_code == 200
    body = await resp.get_json()

    by_name = {lane["name"]: lane for lane in body["lanes"]}
    assert set(by_name) == {"worker", "scheduler", "maintenance_long", "ml"}
    for lane in body["lanes"]:
        assert lane["ceiling"] >= 0
        assert lane["slots"] <= lane["slots_cap"]
        # Nothing is running, so live state must say so rather than report
        # zeroes that read like a healthy idle lane.
        assert lane["live"]["present"] is False


@pytest.mark.asyncio
async def test_ml_ships_off(client, no_live_workers):
    """Rule 164's carve-out and the weak-hardware default in one row: enabling
    the lane is what triggers the SigLIP download, so a fresh install must not
    find it on."""
    body = await (await client.get("/api/system/workers")).get_json()
    ml = next(lane for lane in body["lanes"] if lane["name"] == "ml")
    assert ml["enabled"] is False
    assert ml["slots"] == 0


# --- the persist / push split ------------------------------------------------


@pytest.mark.asyncio
async def test_a_value_is_stored_even_when_it_cannot_be_pushed(
    client, db, no_live_workers
):
    """THE test for this step. `pool_grow` is not durable and the lane is not
    answering, so the push fails — and the setting must survive anyway, or a
    UI that saved while a worker was restarting would silently lose it
    (lesson #4202). 200 with `applied: false`, not an error.
    """
    resp = await client.post("/api/system/workers/worker", json={"slots": 3})
    assert resp.status_code == 200
    body = await resp.get_json()

    assert body["slots"] == 3
    assert body["applied"] is False
    assert "not running" in body["apply_error"]

    assert (await _lane_row(db, "worker")).slots == 3


@pytest.mark.asyncio
async def test_a_partial_update_leaves_the_other_fields_alone(
    client, db, no_live_workers
):
    """The stepper sends `{"slots": n}` without restating a cap it did not
    touch."""
    before = await _lane_row(db, "worker")
    original_cap = before.slots_cap

    await client.post("/api/system/workers/worker", json={"slots": 2})

    await db.refresh(before)
    assert before.slots == 2
    assert before.slots_cap == original_cap


# --- what is refused ---------------------------------------------------------


@pytest.mark.asyncio
async def test_slots_above_the_cap_are_refused_and_nothing_is_stored(
    client, db, no_live_workers
):
    row = await _lane_row(db, "worker")
    resp = await client.post(
        "/api/system/workers/worker", json={"slots": row.slots_cap + 1},
    )
    assert resp.status_code == 400
    body = await resp.get_json()
    assert body["error"] == "refused"
    # The sentence the UI shows. A greyed control with no reason reads as a bug.
    assert "cap" in body["detail"]

    await db.refresh(row)
    assert row.slots <= row.slots_cap


@pytest.mark.asyncio
async def test_a_cap_above_the_derived_ceiling_is_refused(
    client, db, no_live_workers
):
    """The operator's cap is theirs to set, but not past what the container
    can hold — the whole point of deriving a ceiling rather than typing one."""
    resp = await client.post(
        "/api/system/workers/ml", json={"slots_cap": 10_000},
    )
    assert resp.status_code == 400
    body = await resp.get_json()
    assert body["error"] == "refused"
    assert "container can hold" in body["detail"]


@pytest.mark.asyncio
async def test_a_boolean_is_not_accepted_as_a_slot_count(client, no_live_workers):
    """`True` is an int in Python. Coerced, it would silently set one slot —
    a control that appears to work and does something nobody asked for."""
    resp = await client.post("/api/system/workers/worker", json={"slots": True})
    assert resp.status_code == 400
    body = await resp.get_json()
    assert body["error"] == "invalid_body"


@pytest.mark.asyncio
async def test_an_unknown_lane_is_refused_and_names_the_known_ones(
    client, no_live_workers
):
    resp = await client.post("/api/system/workers/nonsense", json={"slots": 1})
    assert resp.status_code == 400
    body = await resp.get_json()
    assert body["error"] == "unknown_lane"
    assert "worker" in body["known"]


@pytest.mark.asyncio
async def test_an_empty_body_is_refused_rather_than_treated_as_a_no_op(
    client, no_live_workers
):
    """A POST that changes nothing and returns 200 is indistinguishable from
    one that worked, which is how a broken UI control goes unnoticed."""
    resp = await client.post("/api/system/workers/worker", json={})
    assert resp.status_code == 400
    body = await resp.get_json()
    assert body["error"] == "invalid_body"


# --- the dial is the switch --------------------------------------------------
#
# Operator, 2026-09-23: *"almost all of it always needs to run there's only one
# optional piece and it is killed by moving the 'cap' to zero."* So `enabled`
# is derived from the number rather than being a second control the operator
# has to keep in agreement with it. It stays on the API — these assert that it
# still does, because it is the mechanism the reconcile and the healthcheck
# read.


@pytest.mark.asyncio
async def test_dialling_a_lane_to_zero_turns_it_off(client, db, no_live_workers):
    await client.post("/api/system/workers/worker", json={"slots": 0})

    row = await _lane_row(db, "worker")
    assert row.slots == 0
    assert row.enabled is False


@pytest.mark.asyncio
async def test_dialling_it_back_up_turns_it_on(client, db, no_live_workers):
    await client.post("/api/system/workers/ml", json={"slots": 1})

    row = await _lane_row(db, "ml")
    assert row.slots == 1
    assert row.enabled is True, "the lane the operator just asked for work from"


@pytest.mark.asyncio
async def test_an_explicit_enabled_still_wins(client, db, no_live_workers):
    """The field is not removed, only derived when absent. Something that
    genuinely wants a lane holding its process with consumers cancelled — a
    drain before a restart — must still be able to say so without having to
    destroy the operator's slot count to express it."""
    await client.post(
        "/api/system/workers/worker", json={"slots": 3, "enabled": False},
    )

    row = await _lane_row(db, "worker")
    assert (row.slots, row.enabled) == (3, False)


@pytest.mark.asyncio
async def test_a_cap_only_write_does_not_decide_the_switch(
    client, db, no_live_workers,
):
    """Only the SLOTS dial derives it. A cap is a ceiling, not a request for
    work, and letting it flip the lane would make raising a ceiling start
    something."""
    before = await _lane_row(db, "ml")
    assert before.enabled is False

    await client.post("/api/system/workers/ml", json={"slots_cap": 1})

    await db.refresh(before)
    assert (before.slots, before.enabled) == (0, False)


@pytest.mark.asyncio
async def test_the_model_fetch_fires_on_the_transition_not_on_the_field(
    client, db, no_live_workers, monkeypatch,
):
    """The trap the derivation set, caught here rather than in production.

    The fetch used to be conditioned on `enabled is True` — the FIELD having
    been sent. The UI no longer sends it at all, so the download that makes
    the ML lane usable would simply never have fired, and the lane would have
    come on and sat there consuming a queue it had no model for.
    """
    fired = []
    monkeypatch.setattr(wc, "_enqueue_model_fetch", lambda: fired.append(1) or True)
    monkeypatch.setattr(
        wc, "set_lane_enabled_sync", lambda lane, enabled, live=None: (True, None),
    )
    monkeypatch.setattr(
        wc, "set_lane_slots_sync", lambda lane, target, live=None: (True, None),
    )

    body = await (await client.post(
        "/api/system/workers/ml", json={"slots": 1},
    )).get_json()

    assert body["fetching_models"] is True
    assert fired == [1]


@pytest.mark.asyncio
async def test_it_does_not_fire_again_on_a_lane_already_running(
    client, db, no_live_workers, monkeypatch,
):
    """The other half. A second nudge of the dial on a lane that is already on
    must not re-enqueue a multi-GB download."""
    monkeypatch.setattr(
        wc, "set_lane_enabled_sync", lambda lane, enabled, live=None: (True, None),
    )
    monkeypatch.setattr(
        wc, "set_lane_slots_sync", lambda lane, target, live=None: (True, None),
    )
    await client.post("/api/system/workers/ml", json={"slots": 1})

    fired = []
    monkeypatch.setattr(wc, "_enqueue_model_fetch", lambda: fired.append(1) or True)

    body = await (await client.post(
        "/api/system/workers/ml", json={"slots": 1},
    )).get_json()

    assert body["fetching_models"] is False
    assert fired == []