fix(docker): widen memory byte columns to BIGINT (int32 overflow on ingest)

docker_metrics.mem_usage_bytes and docker_containers.mem_usage_bytes /
mem_limit_bytes were int4 (max 2,147,483,647). A container using >2.1 GB of RAM
(e.g. 8.18 GB) overflowed the column, so asyncpg raised "value out of int32
range" and the entire docker ingest batch failed — no metrics stored for any
host with a large container.

The I/O counters and the milestone-77 rollup/disk tables already used
BigInteger; this trio (docker_001-era) was missed.

- models.py: DockerMetric.mem_usage_bytes, DockerContainer.mem_usage_bytes,
  DockerContainer.mem_limit_bytes → BigInteger.
- migration docker_008_bigint_mem: ALTER COLUMN ... TYPE BIGINT (safe in-place
  int4→int8 promotion).
- integration regression test: persist an ~8 GB container, assert the
  current-state and time-series rows round-trip.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016Jg27rgypiW2efULXJDtMC

plugins/docker/migrations/versions/docker_008_bigint_mem.py

@@ -0,0 +1,33 @@
+"""Widen memory byte columns to BIGINT
+
+docker_metrics.mem_usage_bytes and docker_containers.mem_usage_bytes /
+mem_limit_bytes were int4, which overflows for any container using >2.1 GB
+(asyncpg: "value out of int32 range"), failing the whole ingest batch. Widen to
+BIGINT — a safe in-place int4→int8 promotion, no data rewrite.
+
+Revision ID: docker_008_bigint_mem
+Revises: docker_007_disk_usage
+Create Date: 2026-06-20
+"""
+from typing import Sequence, Union
+from alembic import op
+import sqlalchemy as sa
+
+revision: str = "docker_008_bigint_mem"
+down_revision: Union[str, None] = "docker_007_disk_usage"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.alter_column("docker_metrics", "mem_usage_bytes", type_=sa.BigInteger())
+    op.alter_column("docker_containers", "mem_usage_bytes", type_=sa.BigInteger())
+    op.alter_column("docker_containers", "mem_limit_bytes", type_=sa.BigInteger())
+
+
+def downgrade() -> None:
+    # Narrowing back to int4 will error if any stored value exceeds 2^31 — that's
+    # the very condition this migration fixed, so downgrade is best-effort.
+    op.alter_column("docker_containers", "mem_limit_bytes", type_=sa.Integer())
+    op.alter_column("docker_containers", "mem_usage_bytes", type_=sa.Integer())
+    op.alter_column("docker_metrics", "mem_usage_bytes", type_=sa.Integer())

plugins/docker/models.py

@@ -29,8 +29,10 @@ class DockerContainer(Base):
     status: Mapped[str] = mapped_column(String(32), nullable=False, default="unknown")
     # running | stopped | paused | exited | dead
     cpu_pct: Mapped[float | None] = mapped_column(Float, nullable=True)
-    mem_usage_bytes: Mapped[int | None] = mapped_column(Integer, nullable=True)
-    mem_limit_bytes: Mapped[int | None] = mapped_column(Integer, nullable=True)
+    # BigInteger: a container's memory usage/limit routinely exceeds 2^31 bytes
+    # (~2.1 GB), which overflows int4 and fails the insert.
+    mem_usage_bytes: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
+    mem_limit_bytes: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
     mem_pct: Mapped[float | None] = mapped_column(Float, nullable=True)
     restart_count: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
     ports_json: Mapped[str] = mapped_column(Text, nullable=False, default="[]")
@@ -78,7 +80,8 @@ class DockerMetric(Base):
     )
     cpu_pct: Mapped[float] = mapped_column(Float, nullable=False, default=0.0)
     mem_pct: Mapped[float] = mapped_column(Float, nullable=False, default=0.0)
-    mem_usage_bytes: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
+    # BigInteger: per-container memory usage exceeds 2^31 bytes (~2.1 GB) routinely.
+    mem_usage_bytes: Mapped[int] = mapped_column(BigInteger, nullable=False, default=0)
 
     # Per-container history lookups filter on (host_id, container_name) then sort
     # by time — a composite index keeps the rows() sparkline queries cheap.

tests/integration/test_docker.py

@@ -151,6 +151,46 @@ def test_persist_scopes_containers_by_host(app):
 
 
 @_NEEDS_DB
+def test_large_memory_values_persist_as_bigint(app):
+    """A container using >2^31 bytes of RAM must persist. Regression: mem_usage_bytes
+    / mem_limit_bytes were int4 and overflowed (asyncpg 'value out of int32 range'),
+    failing the whole ingest batch for any host with a >2.1 GB container."""
+    from sqlalchemy import text
+    from steward.models.hosts import Host
+
+    persist = _persist_fn(app)
+    now = datetime.now(timezone.utc)
+    big_usage = 8_185_077_760    # ~8.18 GB — well past int4 max (2_147_483_647)
+    big_limit = 17_179_869_184   # 16 GB
+    snapshot = [(now, [{
+        "name": "bigmem", "container_id": "deadbeef", "image": "postgres",
+        "status": "running", "cpu_pct": 1.0, "mem_pct": 50.0,
+        "mem_usage_bytes": big_usage, "mem_limit_bytes": big_limit,
+        "ports": [], "started_at": None,
+    }])]
+
+    async def _go():
+        async with app.db_sessionmaker() as s:
+            async with s.begin():
+                await s.execute(text("DELETE FROM docker_metrics"))
+                await s.execute(text("DELETE FROM docker_containers"))
+                h = Host(id=str(uuid.uuid4()), name="bigmemhost", address="10.0.0.9")
+                s.add(h)
+                await s.flush()
+                await persist(s, h, snapshot)
+            row = (await s.execute(text(
+                "SELECT mem_usage_bytes, mem_limit_bytes FROM docker_containers "
+                "WHERE name = 'bigmem'"))).first()
+            metric = (await s.execute(text(
+                "SELECT mem_usage_bytes FROM docker_metrics "
+                "WHERE container_name = 'bigmem'"))).scalar()
+            return row, metric
+
+    row, metric = asyncio.run(_go())
+    assert row == (big_usage, big_limit)   # current-state row round-trips
+    assert metric == big_usage             # time-series row round-trips
+
+
 def test_lifecycle_events_derived_across_snapshots(app):
     from sqlalchemy import text
     from steward.models.hosts import Host