Watch
0
0
Fork
You've already forked hyperhive
0
hyperhive/nix/module-eval/agent-memory.nix
atlas c1672218b1 hive-bash-daemon: keep sibling tasks alive when one is OOM-killed
systemd's default OOMPolicy=stop ends the whole unit when the kernel
kills any process in it; set continue, as hive-subagent-daemon does.
Module-eval case asserts it.
2026-10-07 18:18:15 +02:00

94 lines
3.9 KiB
Nix

# `checks.module-eval-agent-memory` — see ./lib.nix for the shared
# rationale (why this suite exists, naming convention, "evaluates
# not executes").
{
pkgs,
lib,
self,
nixosSystem,
}:
let
inherit
(import ./lib.nix {
inherit
pkgs
lib
self
nixosSystem
;
})
agent
runGroup
agentHarness
;
# The memory-pressure pair. `claudeMemoryMaxBytes` is the container's own
# cap, rendered per agent by meta.rs — the capped arm is the one every
# real deploy gets, the uncapped arm is a hive that set `infinity` or a
# RAM percentage and so hands the module no byte count to size against.
agentCapped = agent { claudeMemoryMaxBytes = 8589934592; };
agentUncapped = agent { };
agentBashDaemon = machine: machine.systemd.services.hive-bash-daemon;
agentSubagentDaemon = machine: machine.systemd.services.hive-subagent-daemon;
cases = [
{
# Two thirds of the container's cap, and a SOFT ceiling: the daemon's
# cgroup holds every nested claude, so `MemoryHigh=` throttles the
# subagent set as a whole before the kernel picks a victim, while the
# absent `MemoryMax=` is what still lets one subagent use more than
# its share on a container that has the memory free. A hard cap here
# would trade the silent kill for a guaranteed wall, which is the
# shape this deliberately does not have.
name = "the subagent daemon throttles at two thirds of the container's memory";
ok =
let
c = (agentSubagentDaemon agentCapped).serviceConfig;
in
c.MemoryHigh == "5726623061" && !(c ? MemoryMax);
}
{
# What makes the case above able to fail. With no byte count for the
# container there is no fraction to take, and a hardcoded fallback
# would be a number about some other hive's machine — so the unit
# renders no ceiling at all rather than a fabricated one.
name = "an agent with no byte-valued memory cap renders no subagent ceiling";
ok = !((agentSubagentDaemon agentUncapped).serviceConfig ? MemoryHigh);
}
{
# The sign is the whole property, and it is easy to write backwards:
# a HIGHER OOMScoreAdjust is a MORE likely victim. So the subagent
# daemon must be strictly above zero and the harness strictly below
# it — swap the two and the kernel takes the agent's own turn first,
# which is worse than setting nothing at all. Both nested `claude`
# processes inherit their unit's value, so ordering the units orders
# the sessions. Held as an inequality rather than two constants: what
# must not drift is the order, not the magnitudes.
name = "the OOM killer prefers a subagent over the agent's own session";
ok =
let
sub = (agentSubagentDaemon agentUncapped).serviceConfig.OOMScoreAdjust;
own = (agentHarness agentUncapped).serviceConfig.OOMScoreAdjust;
in
sub > 0 && own < 0 && sub > own;
}
{
# The pair the case above only makes sense with: preferring this unit
# as the victim is an improvement only if losing one subagent isn't
# losing all of them. systemd's default `stop` would take the daemon
# and every sibling session down with whichever process the kernel
# chose, which is the blast radius that made the preference a bad
# trade in the first place.
name = "one subagent losing the OOM draw does not stop the daemon";
ok = (agentSubagentDaemon agentUncapped).serviceConfig.OOMPolicy == "continue";
}
{
# Each bash task is a process in the daemon's cgroup; under `stop` one
# OOM-killed task would end every running sibling task.
name = "one bash task losing the OOM draw does not stop the daemon";
ok = (agentBashDaemon agentUncapped).serviceConfig.OOMPolicy or null == "continue";
}
];
in
runGroup "agent-memory" cases