feat: derive BUN_JSC_forceRAMSize from effective per-agent MemoryMax=

This commit is contained in:
damocles 2026-07-26 21:49:08 +02:00
commit bd14cc5c46
4 changed files with 288 additions and 35 deletions

View file

@ -20,6 +20,11 @@ let
# runtime shell. Absent (option unset) → "unknown".
hiveDisplayName = config.environment.variables.HYPERHIVE_HIVE_NAME or "unknown";
swarmDisplayName = config.environment.variables.HYPERHIVE_SWARM_NAME or "unknown";
# Effective per-agent MemoryMax=, in bytes, injected by meta.rs's
# per-agent flake render (`hyperhive.claudeMemoryMaxBytes`). `null`
# when the effective cap is unbounded ("infinity") or a RAM
# percentage — see `resource_limits::effective_memory_bytes`.
memoryMaxBytes = config.hyperhive.claudeMemoryMaxBytes;
# Base claude-code environment applied to every agent regardless of OTEL.
# Shipped via the managed settings `env` block so claude and `hivectl
# choom` both inherit them without a launch wrapper.
@ -45,6 +50,19 @@ let
CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT = "1";
# Tag remote-control sessions with "<hive>-<agent>" for identification.
CLAUDE_REMOTE_CONTROL_SESSION_NAME_PREFIX = "${hiveDisplayName}-${userName}";
}
# Bun/JavaScriptCore (the runtime under claude-code's `.claude-wrapped`
# binary) sizes its default heap ceiling off the container's visible
# `/proc/meminfo`, which under nspawn is the *host's* physical RAM, not
# the systemd `MemoryMax=` cgroup cap actually enforced on this
# container — the cap lives on the host's outer cgroup and is invisible
# from inside (confirmed: `/sys/fs/cgroup/memory.max` reads `max` at
# every level from in here). That mismatch lets JSC's heap grow well
# past the real wall before GC kicks in hard, causing choom sessions to
# hang. Pin JSC's ceiling to 75% of the *actual* effective cap instead,
# once it's known at build time.
// lib.optionalAttrs (memoryMaxBytes != null) {
BUN_JSC_forceRAMSize = toString (memoryMaxBytes * 75 / 100);
};
# OTEL environment Claude Code reads to export metrics/logs/traces.
# Shipped via the managed claude settings json (below), which claude
@ -186,6 +204,28 @@ in
};
};
# Build-time implementation surface for the JSC-heap-ceiling fix:
# meta.rs's per-agent flake render injects this from the effective
# `MemoryMax=` (per-agent `resource-limits.json` override, else the
# hive-wide `services.hyperhive.agentMemoryMax`) — see
# `resource_limits::effective_memory_bytes_from`. Not meant to be set
# directly in an agent.nix, same convention as `hyperhive.otel.*`
# above; the host option (or `hivectl agents set-resource-limits`) is
# the real operator knob, and this only reflects the value baked in at
# the agent's *last rebuild* — `set-resource-limits` still applies the
# cgroup cap live via a drop-in reload, but this derived heap ceiling
# needs a rebuild to pick up a new value.
options.hyperhive.claudeMemoryMaxBytes = lib.mkOption {
type = lib.types.nullOr lib.types.ints.positive;
default = null;
internal = true;
description = ''
Effective per-agent memory cap in bytes, when it's a plain
byte-size value (null for an unbounded or percentage-based cap).
Used to derive `BUN_JSC_forceRAMSize` in `baseClaudeEnv`.
'';
};
options.hyperhive.claudeMarketplaces = lib.mkOption {
type = lib.types.listOf lib.types.str;
default = [ "anthropics/claude-plugins-official" ];