agents: read the memory cap at boot, not from the build
An agent's memory cap was rendered into its flake (`memoryMaxBytes` → `services.hyperhive.agent.claudeMemoryMaxBytes`), so the closure depended on it and a changed cap reached the JSC heap ceiling and the subagent `MemoryHigh=` only after a rebuild. hive-c0re now writes the effective `MemoryMax=` in bytes to the agent's runtime dir (`/run/hive/memory-max-bytes` inside) in `write_dropins`, from the same value the drop-in gets. The file is removed for `infinity` or a RAM percentage, and left alone when the drop-in is kept. Inside the container, `nix/agent-modules/memory-cap.nix` reads it at boot: an environment generator sets `BUN_JSC_forceRAMSize` (75%) for every unit and `machinectl shell`, `/etc/set-environment` exports it in login shells, and a unit generator writes `MemoryHigh=` (2/3) as a drop-in for `hive-subagent-daemon`. The render drops `memoryMaxBytes`, the agent option is removed (both spellings fail eval with a removal message), and `effective_memory_bytes_from` goes with its only caller. Part of #5081 (slice S0-2).
This commit is contained in:
parent
c8df666bf3
commit
0d619e215e
15 changed files with 416 additions and 287 deletions
|
|
@ -19,11 +19,6 @@ let
|
|||
# meta.rs `otel_config`). Options declared in `otel.nix`, which also
|
||||
# exports the generic OTLP environment this container's producers read.
|
||||
otelCfg = config.services.hyperhive.agent.otel;
|
||||
# Effective per-agent MemoryMax=, in bytes, injected by meta.rs's
|
||||
# per-agent flake render (`services.hyperhive.agent.claudeMemoryMaxBytes`). `null`
|
||||
# when the effective cap is unbounded ("infinity") or a RAM
|
||||
# percentage — see `resource_limits::effective_memory_bytes`.
|
||||
memoryMaxBytes = config.services.hyperhive.agent.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.
|
||||
|
|
@ -47,19 +42,6 @@ let
|
|||
CLAUDE_CODE_RESUME_INTERRUPTED_TURN = "1";
|
||||
# Use the simpler system prompt variant suited to headless operation.
|
||||
CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT = "1";
|
||||
}
|
||||
# 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);
|
||||
};
|
||||
# Claude Code's own telemetry switches — what it emits, and whether it
|
||||
# emits at all. Everything an OTEL SDK reads generically (endpoint,
|
||||
|
|
@ -99,31 +81,6 @@ 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 `services.hyperhive.agent.otel.*`
|
||||
# above; the host option (or `hivectl agent <name> set-limits`) is
|
||||
# the real operator knob, and this only reflects the value baked in at
|
||||
# the agent's *last rebuild* — `set-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.services.hyperhive.agent.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).
|
||||
This is the whole container's cap, not claude's share of it —
|
||||
the name records its first consumer, `BUN_JSC_forceRAMSize` in
|
||||
`baseClaudeEnv`. `mcp.nix` reads it too, to size the subagent
|
||||
daemon's `MemoryHigh=` against the container it runs in.
|
||||
'';
|
||||
};
|
||||
|
||||
options.services.hyperhive.agent.claudeMarketplaces = lib.mkOption {
|
||||
type = lib.types.listOf lib.types.str;
|
||||
default = [
|
||||
|
|
@ -257,9 +214,7 @@ in
|
|||
environment.etc."claude-code/managed-settings.json".source =
|
||||
let
|
||||
baseSettings = "${config.services.hyperhive.agent.packages.assets}/share/hyperhive/prompts/claude-settings.json";
|
||||
# Merge base env (always) with OTEL env (when enabled). jq is always
|
||||
# run — `baseClaudeEnv` can carry per-agent values (e.g.
|
||||
# BUN_JSC_forceRAMSize) that can't live in the static store asset.
|
||||
# Merge base env (always) with OTEL env (when enabled).
|
||||
allEnv =
|
||||
baseClaudeEnv
|
||||
// lib.optionalAttrs otelCfg.enable otelSettingsEnv
|
||||
|
|
|
|||
Loading…
Reference in a new issue