feat(cloud): skip MCP-busy devices in scheduler

packages/cloud-platform/cloud/db_models.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 from sqlalchemy import (
+    Boolean,
     ForeignKey,
     Index,
     Integer,
@@ -86,6 +87,7 @@ class PooledDeviceRow(Base):
     status: Mapped[str] = mapped_column(String, nullable=False)
     capability_tags_json: Mapped[str] = mapped_column(Text, nullable=False)
     synced_at: Mapped[str | None] = mapped_column(String, nullable=True)
+    mcp_busy: Mapped[bool] = mapped_column(Boolean, nullable=False, default=False)
 
 
 class ScheduledTaskRow(Base):

packages/cloud-platform/cloud/internal_api/api.py

@@ -185,6 +185,7 @@ def create_internal_router(
             address=payload.address,
             allow_device_takeover=allow_device_takeover,
             planner_transport=payload.planner_transport,
+            mcp_busy_device_ids=payload.mcp_busy_device_ids,
         )
         policy = pool.store.get_host_governance_policy(host_id)
         policy_revision = policy.revision if policy is not None else 0

packages/cloud-platform/cloud/migrations/versions/0014_pooled_device_mcp_busy.py

@@ -0,0 +1,28 @@
+"""Add mcp_busy flag column to pooled_devices."""
+
+from __future__ import annotations
+
+import sqlalchemy as sa
+from alembic import op
+
+
+revision = "0014_pooled_device_mcp_busy"
+down_revision = "0013_task_cancellation"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "pooled_devices",
+        sa.Column(
+            "mcp_busy",
+            sa.Boolean(),
+            nullable=False,
+            server_default=sa.false(),
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("pooled_devices", "mcp_busy")

packages/cloud-platform/cloud/pool.py

@@ -47,6 +47,7 @@ class PooledDevice:
     status: PooledDeviceStatus
     capability_tags: list[str] = field(default_factory=list)
     synced_at: datetime | None = None
+    mcp_busy: bool = False
 
 
 class DevicePool:
@@ -64,6 +65,7 @@ class DevicePool:
         address: str | None = None,
         planner_transport: Literal["direct", "cloud"] = "direct",
         allow_device_takeover: bool = False,
+        mcp_busy_device_ids: list[str] | None = None,
     ) -> None:
         """Push a host's current device snapshot into the pool.
 
@@ -78,7 +80,13 @@ class DevicePool:
             last_seen_at=now,
             planner_transport=planner_transport,
         )
-        devices = [self._to_pooled(device, host_id, now) for device in snapshot]
+        busy_set = set(mcp_busy_device_ids or [])
+        devices = [
+            self._to_pooled(
+                device, host_id, now, mcp_busy=device.id in busy_set
+            )
+            for device in snapshot
+        ]
         if allow_device_takeover:
             self.store.replace_host_devices(
                 host_id,
@@ -119,6 +127,8 @@ class DevicePool:
         device: Device,
         host_id: str,
         synced_at: datetime,
+        *,
+        mcp_busy: bool = False,
     ) -> PooledDevice:
         raw_status = (
             device.status if device.status in _HOST_REPORTED_STATUSES else "idle"
@@ -131,6 +141,7 @@ class DevicePool:
             status=raw_status,  # type: ignore[arg-type]
             capability_tags=tags,
             synced_at=synced_at,
+            mcp_busy=mcp_busy,
         )
 
     def _is_stale(self, host: HostRegistration, now: datetime) -> bool:

packages/cloud-platform/cloud/scheduler.py

@@ -204,6 +204,8 @@ class TaskScheduler:
 
 
 def _matches(device: "PooledDevice", constraints: TaskConstraints) -> bool:
+    if device.mcp_busy:
+        return False
     if constraints.target_host_id and device.host_id != constraints.target_host_id:
         return False
     if (

packages/cloud-platform/cloud/sql_repository.py

@@ -342,6 +342,7 @@ class SQLAlchemyCloudRepository:
                             ensure_ascii=False,
                         ),
                         synced_at=_iso(device.synced_at) if device.synced_at else None,
+                        mcp_busy=getattr(device, "mcp_busy", False),
                     )
                     for device in devices
                 ]
@@ -2232,6 +2233,7 @@ def _device_from_row(row: PooledDeviceRow) -> Any:
         status=row.status,
         capability_tags=tags,
         synced_at=_parse_dt(row.synced_at),
+        mcp_busy=bool(getattr(row, "mcp_busy", False)),
     )