backend/app/api/__init__.py

@@ -41,6 +41,7 @@ def all_blueprints() -> list[Blueprint]:
     from .system_health import system_health_bp
     from .tags import tags_bp
     from .thumbnails import thumbnails_bp
+    from .workers import workers_bp
     return [
         api_bp,
         attachments_bp,
@@ -52,6 +53,7 @@ def all_blueprints() -> list[Blueprint]:
         showcase_bp,
         settings_bp,
         system_activity_bp,
+        workers_bp,
         system_health_bp,
         system_backup_bp,
         admin_bp,

backend/app/api/system_activity.py

@@ -21,18 +21,22 @@ from ..config import get_config
 from ..extensions import get_session
 from ..models import TaskRun
 from ..services.scheduler_service import scheduler_status
+from ..services.worker_lanes import LANES
 
 system_activity_bp = Blueprint(
     "system_activity", __name__, url_prefix="/api/system/activity",
 )
 
-# Canonical queue order — must match celery_app.task_routes. UI renders
+# Every queue, grouped by the lane that consumes it. DERIVED from
-# in this order; queues with no LLEN response show as null rather than
+# `worker_lanes.LANES` (milestone 422 step 1) rather than written out:
-# absent.
+# this was a hand-kept third copy of "which queues exist", alongside
-_QUEUE_NAMES = (
+# celery_app.task_routes and service_roster.ROLE_NAMES, and its own comment
-    "default", "import", "thumbnail", "ml",
+# admitted the coupling — "must match celery_app.task_routes".
-    "download", "scan", "maintenance", "maintenance_long",
+#
-)
+# The rendered ORDER changes with this: lane order rather than the previous
+# hand-chosen one. That is the better grouping for a lane-oriented UI, and
+# queues with no LLEN response still show as null rather than absent.
+_QUEUE_NAMES = tuple(q for lane in LANES for q in lane.queues)
 
 # Cache module-level so all requests share the cache between polls.
 # Tests can reset via direct dict mutation if needed.

backend/app/api/workers.py

@@ -0,0 +1,103 @@
+"""Worker lanes: what each is doing, and the dial that changes it.
+
+Milestone 422 step 2. The write half of a surface `api/system_activity.py`
+only reads.
+
+## Why this is a separate blueprint
+
+`system_activity` says in its own first line that it is read-only, and it
+answers a different question: its `/workers` is keyed on celery HOSTNAME and
+reports which nodes answered. That stays as it is — the existing
+SystemActivityTab consumes it.
+
+This is keyed on LANE, joins the stored settings to the live pool, and
+accepts writes. Two endpoints answering "which celery processes exist" and
+"how much work is each lane allowed to do" are not the same endpoint, and
+folding the second into the first would make a read-only module a write one.
+"""
+
+from __future__ import annotations
+
+from datetime import UTC, datetime
+
+from quart import Blueprint, jsonify, request
+
+from ..extensions import get_session
+from ..services.worker_control import LaneUpdateRefused, lane_view, set_lane
+from ..services.worker_lanes import LANES_BY_NAME
+from ._responses import error_response as _bad
+
+workers_bp = Blueprint("workers", __name__, url_prefix="/api/system/workers")
+
+
+@workers_bp.route("", methods=["GET"])
+async def list_lanes():
+    """Every lane: configured slots, the cap, the ceiling, and live state.
+
+    Response: {lanes: [...], fetched_at: iso8601}
+
+    Deliberately NOT cached, unlike system_activity's 2s/5s caches. This is
+    the surface an operator watches while dragging a stepper, and a cached
+    reply would show them the value from before their own change and read as
+    the control having failed.
+    """
+    async with get_session() as session:
+        lanes = await lane_view(session)
+    return jsonify({
+        "lanes": lanes,
+        "fetched_at": datetime.now(UTC).isoformat(),
+    })
+
+
+@workers_bp.route("/<name>", methods=["POST"])
+async def update_lane(name: str):
+    """Set a lane's slots, cap and/or enabled flag. Stores, then pushes live.
+
+    Partial: only the keys present are changed, so the UI's stepper can send
+    `{"slots": 3}` without restating the cap it did not touch.
+
+    Two failure kinds, deliberately different statuses:
+
+    * **400** — the value is not allowed (above the cap, above the ceiling,
+      negative). Nothing was stored. The body carries `detail`, which is the
+      sentence the UI shows; a refused control with no reason reads as a bug.
+    * **200 with `applied: false`** — the value WAS stored but could not be
+      pushed, because the lane is not currently answering. That is not an
+      error: step 3's reconcile carries it when the lane comes back, and the
+      UI should say "saved, not yet live" rather than "that didn't work".
+    """
+    lane = LANES_BY_NAME.get(name)
+    if lane is None:
+        return _bad("unknown_lane", detail=name, known=sorted(LANES_BY_NAME))
+
+    body = await request.get_json()
+    if not isinstance(body, dict):
+        return _bad("invalid_body", detail="body must be a JSON object")
+
+    fields: dict = {}
+    for key in ("slots", "slots_cap"):
+        if key in body:
+            value = body[key]
+            # Rejected rather than coerced: `True` is an int in Python, and
+            # silently reading it as 1 slot would be a control that appears to
+            # work and sets something nobody asked for.
+            if not isinstance(value, int) or isinstance(value, bool):
+                return _bad("invalid_body", detail=f"{key} must be an integer")
+            fields[key] = value
+    if "enabled" in body:
+        if not isinstance(body["enabled"], bool):
+            return _bad("invalid_body", detail="enabled must be a boolean")
+        fields["enabled"] = body["enabled"]
+
+    if not fields:
+        return _bad(
+            "invalid_body",
+            detail="give at least one of slots, slots_cap, enabled",
+        )
+
+    async with get_session() as session:
+        try:
+            result = await set_lane(session, lane, **fields)
+        except LaneUpdateRefused as exc:
+            return _bad("refused", detail=str(exc))
+    return jsonify(result)

backend/app/services/worker_control.py

@@ -47,10 +47,15 @@ autoscaler.
 
 from __future__ import annotations
 
+import asyncio
 import logging
 from dataclasses import dataclass, field
 
-from .worker_lanes import LANES, LANES_BY_QUEUE_KEY, Lane
+from sqlalchemy import select
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from ..models import WorkerLane
+from .worker_lanes import LANES, LANES_BY_QUEUE_KEY, Lane, derived_ceiling
 
 log = logging.getLogger(__name__)
 
@@ -74,11 +79,22 @@ class LaneLiveState:
 
     present: bool = False
     replicas: int = 0
-    # Per-process pool size. Equal across replicas unless one has drifted.
-    pool: int | None = None
     active: int = 0
     reserved: int = 0
     hostnames: list[str] = field(default_factory=list)
+    # Pool size PER HOSTNAME, not aggregated. The resize below computes each
+    # replica's own delta from its own current pool, so replicas that have
+    # drifted apart converge instead of being moved in lockstep from a shared
+    # baseline — which is what an aggregate here would silently reintroduce.
+    pools: dict[str, int] = field(default_factory=dict)
+
+    @property
+    def pool(self) -> int | None:
+        """One number for the UI. `max` rather than a sum: `slots` means the
+        pool size of ONE process (see the module docstring), so the largest
+        replica is the honest answer to "what is this lane set to". None when
+        no replica reported — unknown, never zero."""
+        return max(self.pools.values()) if self.pools else None
 
 
 def _lane_for_queues(queues: tuple[str, ...]) -> Lane | None:
@@ -124,7 +140,7 @@ def inspect_lanes_sync() -> dict[str, LaneLiveState]:
         # answer, which leaves pool=None — unknown, not zero.
         pool = (stats.get(hostname) or {}).get("pool", {}).get("max-concurrency")
         if isinstance(pool, int):
-            state.pool = pool if state.pool is None else max(state.pool, pool)
+            state.pools[hostname] = pool
 
     for state in out.values():
         state.hostnames.sort()
@@ -150,16 +166,22 @@ def set_lane_slots_sync(lane: Lane, target: int) -> tuple[bool, str | None]:
         live = inspect_lanes_sync()[lane.name]
         if not live.present:
             return False, "lane is not running"
-        if live.pool is None:
+        if not live.pools:
             return False, "worker did not report its pool size"
 
         control = celery_app.control
-        for hostname in live.hostnames:
+        unreported = [h for h in live.hostnames if h not in live.pools]
-            delta = target - live.pool
+        for hostname, current in live.pools.items():
+            delta = target - current
             if delta > 0:
                 control.pool_grow(delta, destination=[hostname])
             elif delta < 0:
                 control.pool_shrink(-delta, destination=[hostname])
+        if unreported:
+            # Resized what could be resized, and said which could not. Silence
+            # here would leave a replica running at a size the UI claims it is
+            # not, with nothing anywhere recording the gap.
+            return False, f"no pool size reported by {', '.join(sorted(unreported))}"
         return True, None
     except Exception as exc:  # noqa: BLE001 — reported, never raised at a caller
         log.warning("worker_control: could not resize %s", lane.name, exc_info=True)
@@ -194,3 +216,176 @@ def set_lane_enabled_sync(lane: Lane, enabled: bool) -> tuple[bool, str | None]:
             "enable" if enabled else "disable", lane.name, exc_info=True,
         )
         return False, str(exc)
+
+
+# --- the settings half, which is async ----------------------------------------
+#
+# Sync celery control above, async DB below, in one module. Same split
+# `service_roster` already runs (`_inspect_celery_sync` beside `touch_service`)
+# — the boundary is the transport, not the concern, and "control the workers"
+# is one concern.
+
+
+async def _rows_by_name(session: AsyncSession) -> dict[str, WorkerLane]:
+    """Every lane's row, creating any that are missing from its LANES defaults.
+
+    Self-heals rather than depending on a migration having run for a lane
+    added later: alembic 0103 seeded the four that existed on 2026-09-22, and
+    a fifth added to LANES afterwards gets its row the first time anything
+    asks. Without this, a new lane would read as absent and the UI would
+    simply not show it.
+    """
+    rows = {
+        row.name: row
+        for row in (await session.execute(select(WorkerLane))).scalars()
+    }
+    missing = [lane for lane in LANES if lane.name not in rows]
+    for lane in missing:
+        row = WorkerLane(
+            name=lane.name,
+            slots=lane.default_slots,
+            slots_cap=lane.default_slots_cap,
+            enabled=lane.default_enabled,
+        )
+        session.add(row)
+        rows[lane.name] = row
+    if missing:
+        await session.commit()
+    return rows
+
+
+async def lane_view(session: AsyncSession) -> list[dict]:
+    """Every lane: what is configured, what is live, what it may grow to.
+
+    One call rather than making the UI join three sources. `pending` is the
+    honest backlog — Redis depth PLUS reserved — because celery prefetches and
+    LLEN alone reads 0 while a worker holds tasks in memory.
+    """
+    rows = await _rows_by_name(session)
+    live = await asyncio.to_thread(inspect_lanes_sync)
+    depths = await asyncio.to_thread(_queue_depths_sync)
+
+    out = []
+    for lane in LANES:
+        row = rows[lane.name]
+        state = live[lane.name]
+        # None for a queue the broker did not answer for, which must not be
+        # silently summed as zero — an unknown depth is not an empty one.
+        known = [depths.get(q) for q in lane.queues]
+        depth = sum(d for d in known if d is not None) if any(
+            d is not None for d in known
+        ) else None
+        out.append({
+            "name": lane.name,
+            "display_name": lane.display_name,
+            "queues": list(lane.queues),
+            "slots": row.slots,
+            "slots_cap": row.slots_cap,
+            "ceiling": derived_ceiling(lane),
+            "enabled": row.enabled,
+            "memory_bound": lane.memory_bound,
+            "live": {
+                "present": state.present,
+                "replicas": state.replicas,
+                "pool": state.pool,
+                "active": state.active,
+                "reserved": state.reserved,
+            },
+            "queue_depth": depth,
+            "pending": None if depth is None else depth + state.reserved,
+        })
+    return out
+
+
+def _queue_depths_sync() -> dict[str, int | None]:
+    """Redis LLEN per queue. None for one that did not answer — see lane_view.
+
+    Sync; the caller threads it. A per-queue try/except so one bad queue does
+    not cost the whole report, matching `api/system_activity._read_queues_sync`.
+    """
+    import redis
+
+    from ..config import get_config
+
+    out: dict[str, int | None] = {}
+    try:
+        client = redis.Redis.from_url(get_config().celery_broker_url)
+    except Exception:
+        log.warning("worker_control: no broker for queue depths", exc_info=True)
+        return {q: None for lane in LANES for q in lane.queues}
+    for lane in LANES:
+        for queue in lane.queues:
+            try:
+                out[queue] = int(client.llen(queue))
+            except Exception:  # noqa: BLE001 — a hiccup must not break the UI
+                out[queue] = None
+    return out
+
+
+class LaneUpdateRefused(ValueError):
+    """A requested value is outside what the lane may hold. Carries the reason
+    the UI shows — a greyed control with no explanation reads as a bug."""
+
+
+async def set_lane(
+    session: AsyncSession,
+    lane: Lane,
+    *,
+    slots: int | None = None,
+    slots_cap: int | None = None,
+    enabled: bool | None = None,
+) -> dict:
+    """Store the operator's choice, then push it to the running lane.
+
+    BOTH, in one call, and the order matters. `pool_grow`/`pool_shrink` are
+    not durable — a restart drops every lane back to its env concurrency — so
+    a UI that only pushed would have its setting evaporate on the next deploy
+    with nothing to show for it (lesson #4202: the live change does not
+    survive, and nothing says so). Storing alone would be a number that
+    describes nothing until something restarts.
+
+    A failed PUSH is not a failed setting. The value is saved either way and
+    step 3's reconcile carries it when the lane answers again; the result says
+    `applied: false` with a reason so the UI can say "saved, not yet live"
+    rather than "that didn't work".
+    """
+    rows = await _rows_by_name(session)
+    row = rows[lane.name]
+
+    new_cap = row.slots_cap if slots_cap is None else slots_cap
+    new_slots = row.slots if slots is None else slots
+    new_enabled = row.enabled if enabled is None else enabled
+
+    ceiling = derived_ceiling(lane)
+    if new_cap < 0 or new_slots < 0:
+        raise LaneUpdateRefused("slots and cap cannot be negative")
+    if new_cap > ceiling:
+        raise LaneUpdateRefused(
+            f"cap {new_cap} is above what this container can hold "
+            f"({ceiling} for {lane.display_name})"
+        )
+    if new_slots > new_cap:
+        raise LaneUpdateRefused(f"slots {new_slots} is above the cap {new_cap}")
+
+    row.slots_cap = new_cap
+    row.slots = new_slots
+    row.enabled = new_enabled
+    await session.commit()
+
+    applied, error = True, None
+    if enabled is not None:
+        applied, error = await asyncio.to_thread(
+            set_lane_enabled_sync, lane, new_enabled,
+        )
+    if applied and slots is not None:
+        applied, error = await asyncio.to_thread(set_lane_slots_sync, lane, new_slots)
+
+    return {
+        "name": lane.name,
+        "slots": row.slots,
+        "slots_cap": row.slots_cap,
+        "ceiling": ceiling,
+        "enabled": row.enabled,
+        "applied": applied,
+        "apply_error": error,
+    }

tests/test_api_workers.py

@@ -0,0 +1,172 @@
+"""/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"

tests/test_worker_control.py

@@ -0,0 +1,188 @@
+"""Changing a lane's slots on a running system (milestone 422 step 2).
+
+The celery control calls are stubbed: what is being tested is the DELTA
+ARITHMETIC and the persist/push split, not that celery can resize its own
+pool. A test that asserted celery's behaviour would be testing celery.
+"""
+
+from __future__ import annotations
+
+import pytest
+
+from backend.app.services import worker_control as wc
+from backend.app.services.worker_lanes import LANES_BY_NAME
+
+# --- what inspect reports ----------------------------------------------------
+
+
+class _Control:
+    """Records the control messages that were sent."""
+
+    def __init__(self):
+        self.grew: list[tuple[int, list[str]]] = []
+        self.shrank: list[tuple[int, list[str]]] = []
+        self.added: list[tuple[str, list[str]]] = []
+        self.cancelled: list[tuple[str, list[str]]] = []
+
+    def pool_grow(self, n, destination=None):
+        self.grew.append((n, destination))
+
+    def pool_shrink(self, n, destination=None):
+        self.shrank.append((n, destination))
+
+    def add_consumer(self, queue, destination=None):
+        self.added.append((queue, destination))
+
+    def cancel_consumer(self, queue, destination=None):
+        self.cancelled.append((queue, destination))
+
+
+def _stub_live(monkeypatch, lane_name, *, pools, present=True, reserved=0):
+    state = wc.LaneLiveState(
+        present=present,
+        replicas=len(pools),
+        hostnames=sorted(pools),
+        pools=dict(pools),
+        reserved=reserved,
+    )
+    monkeypatch.setattr(
+        wc, "inspect_lanes_sync",
+        lambda: {name: (state if name == lane_name else wc.LaneLiveState())
+                 for name in LANES_BY_NAME},
+    )
+    return state
+
+
+def _stub_control(monkeypatch):
+    control = _Control()
+
+    class _Celery:
+        pass
+
+    celery = _Celery()
+    celery.control = control
+    import sys
+    import types
+    mod = types.ModuleType("backend.app.celery_app")
+    mod.celery = celery
+    monkeypatch.setitem(sys.modules, "backend.app.celery_app", mod)
+    return control
+
+
+def test_pool_property_is_max_not_sum():
+    """`slots` means the pool size of ONE process, so the aggregate shown to
+    the operator is the largest replica — not the total. A sum would report 8
+    for two replicas of 4 and invite them to 'reduce it to 4', which would
+    halve the lane."""
+    state = wc.LaneLiveState(pools={"a": 4, "b": 4})
+    assert state.pool == 4
+
+
+def test_pool_is_none_when_nothing_reported():
+    """Unknown, never zero — the distinction step 3's reconcile depends on."""
+    assert wc.LaneLiveState(present=True).pool is None
+
+
+# --- the delta arithmetic ----------------------------------------------------
+
+
+def test_each_replica_gets_its_own_delta(monkeypatch):
+    """The bug this exists to prevent: one delta computed from an aggregate
+    and applied to every replica. With replicas at 2 and 6 and a target of 4,
+    a shared delta moves both the same way and leaves them at 4 and 8 — or 0
+    and 4 — depending on which aggregate was used. Per-replica deltas
+    converge both on 4.
+    """
+    control = _stub_control(monkeypatch)
+    _stub_live(monkeypatch, "worker", pools={"host-a": 2, "host-b": 6})
+
+    applied, err = wc.set_lane_slots_sync(LANES_BY_NAME["worker"], 4)
+
+    assert (applied, err) == (True, None)
+    assert control.grew == [(2, ["host-a"])]
+    assert control.shrank == [(2, ["host-b"])]
+
+
+def test_a_replica_already_at_the_target_is_sent_nothing(monkeypatch):
+    """The fixed point step 3's reconcile needs. An enforcer that re-issues a
+    grow of zero every tick never converges and re-does its own work forever
+    (lesson #4183)."""
+    control = _stub_control(monkeypatch)
+    _stub_live(monkeypatch, "worker", pools={"host-a": 4})
+
+    applied, err = wc.set_lane_slots_sync(LANES_BY_NAME["worker"], 4)
+
+    assert (applied, err) == (True, None)
+    assert control.grew == []
+    assert control.shrank == []
+
+
+def test_resizing_an_absent_lane_reports_rather_than_raises(monkeypatch):
+    _stub_control(monkeypatch)
+    _stub_live(monkeypatch, "worker", pools={}, present=False)
+
+    applied, err = wc.set_lane_slots_sync(LANES_BY_NAME["worker"], 4)
+
+    assert applied is False
+    assert "not running" in err
+
+
+def test_a_replica_with_no_reported_pool_is_named_not_skipped_silently(
+    monkeypatch,
+):
+    """Resize what can be resized, then say which could not. Silence would
+    leave a replica running at a size the UI claims it is not."""
+    control = _stub_control(monkeypatch)
+    state = _stub_live(monkeypatch, "worker", pools={"host-a": 2})
+    state.hostnames = ["host-a", "host-b"]  # b answered inspect, not stats
+    state.replicas = 2
+
+    applied, err = wc.set_lane_slots_sync(LANES_BY_NAME["worker"], 4)
+
+    assert control.grew == [(2, ["host-a"])]
+    assert applied is False
+    assert "host-b" in err
+
+
+# --- enabling and disabling --------------------------------------------------
+
+
+def test_disabling_cancels_consumers_rather_than_killing_the_worker(monkeypatch):
+    """A cancelled consumer keeps the process alive and answering inspect, so
+    a disabled lane stays visible. A killed worker reads as ABSENT, which is
+    the same signal as a crash — and milestone 365 exists precisely so those
+    two do not look alike."""
+    control = _stub_control(monkeypatch)
+    _stub_live(monkeypatch, "ml", pools={"host-a": 1})
+
+    applied, err = wc.set_lane_enabled_sync(LANES_BY_NAME["ml"], False)
+
+    assert (applied, err) == (True, None)
+    assert control.cancelled == [("ml", ["host-a"])]
+    assert control.added == []
+
+
+def test_enabling_adds_a_consumer_for_every_queue_in_the_lane(monkeypatch):
+    control = _stub_control(monkeypatch)
+    _stub_live(monkeypatch, "worker", pools={"host-a": 1})
+
+    wc.set_lane_enabled_sync(LANES_BY_NAME["worker"], True)
+
+    assert [q for q, _ in control.added] == list(LANES_BY_NAME["worker"].queues)
+
+
+# --- lane identity -----------------------------------------------------------
+
+
+def test_queue_sets_map_back_to_their_lane_in_any_order():
+    """celery does not guarantee the order it lists a worker's queues in, so
+    the lookup sorts. Unsorted, a lane would intermittently fail to match and
+    read as absent."""
+    lane = LANES_BY_NAME["worker"]
+    assert wc._lane_for_queues(tuple(reversed(lane.queues))) is lane
+
+
+def test_an_unknown_queue_set_maps_to_no_lane():
+    """A deployment slicing CELERY_QUEUES differently has no lane row to
+    control. Honest rather than an error — the roster still reports it."""
+    assert wc._lane_for_queues(("something", "else")) is None