docs/agent-lifecycle/persistence.md

@@ -403,8 +403,7 @@ Contents:
   Written by `resource_limits::set_limits`; read where
   `lifecycle::write_dropins` generates the systemd drop-in, **not** injected
   into the container — these are host-side caps on the container, so
-  the capped party never sets them. It sees only the resulting memory cap,
+  the capped party never sees or sets them. Fallback is per *field*:
-  as a byte count or `infinity` in its runtime dir (below). Fallback is per *field*:
   an absent file, absent agent, or absent field falls back to the
   hive-wide `services.hyperhive.c0re.agentCpuQuota` / `agentMemoryMax`,
   so an agent can override only its memory and still track the hive
@@ -509,12 +508,6 @@ containers can't start.
 - `/run/hyperhive/host.sock` — admin socket (host-side CLI).
 - `/run/hyperhive/agents/<name>/mcp.sock` — per-agent socket
   (bind-mounted into the container as `/run/hive/mcp.sock`).
-- `/run/hyperhive/agents/<name>/memory-max-bytes` — the agent's effective
-  `MemoryMax=` as a byte count (a percentage resolved against the host's
-  physical memory) or `infinity`, written by `lifecycle::write_dropins`
-  before every start. Absent only when hive-c0re can't tell the cap. The
-  container reads it at boot as `/run/hive/memory-max-bytes`
-  (`nix/agent-modules/memory-cap.nix`).
 
 On startup, `Coordinator::register_agent` drops any prior socket
 task before rebinding — idempotent so a hive-c0re restart followed

docs/scheduler/coordinator.md

@@ -452,23 +452,6 @@ regardless.
 rebuild, so changes take effect on the next lifecycle op without
 requiring a host rebuild.
 
-The container can't read its own cap, so `write_dropins` also writes the
-effective `MemoryMax=` into the agent's runtime dir
-(`/run/hive/memory-max-bytes` inside) before every start: a byte count, or
-`infinity` for no cap. A percentage becomes bytes the way systemd resolves
-it, as that share of the host's physical memory rounded down to a page. A
-value systemd ignores (zero, over 100%) is `infinity`. When hive-c0re keeps
-the last drop-in because it can't read the overrides file, the file carries
-that drop-in's `MemoryMax=`.
-
-At boot the container derives two values from a byte count:
-`BUN_JSC_forceRAMSize` (75%, claude-code's heap ceiling) and `MemoryHigh=` on
-`hive-subagent-daemon` (two thirds). Neither is in the agent's build, so a
-changed cap reaches them at the next container start without a rebuild.
-`infinity` sets neither. A missing or malformed file sets neither as well, and
-`hyperhive-memory-cap-check.service` logs a warning naming the path in the
-container's journal. The container's `MemoryMax=` still applies.
-
 The same drop-in carries `CPUWeight=` / `IOWeight=` from
 `agentCpuWeight` / `agentIoWeight`. Those are a different kind of
 setting: the quota and the memory max are **hard caps** that throttle

hive-c0re/src/agent_config/resource_limits.rs

@@ -122,36 +122,79 @@ fn resolve(limits: &AgentLimits, hive_cpu_quota: &str, hive_memory_max: &str) ->
     (cpu, mem)
 }
 
+/// Effective `MemoryMax=` string for `name` against an already-loaded
+/// map — the memory-only half of [`effective_from`], split out because
+/// [`effective_memory_bytes_from`] doesn't have a CPU quota to pass.
+/// No single-agent convenience wrapper (unlike [`effective`] /
+/// [`effective_from`]): every current caller already has a loaded map
+/// in hand, so one would just be dead code.
+#[must_use]
+fn effective_memory_max_from(
+    limits: &BTreeMap<String, AgentLimits>,
+    name: &str,
+    hive_memory_max: &str,
+) -> String {
+    limits
+        .get(name)
+        .and_then(|l| l.memory_max.clone())
+        .unwrap_or_else(|| hive_memory_max.to_owned())
+}
+
+/// Effective `MemoryMax=` for `name`, as a raw byte count, against an
+/// already-loaded map — the form `render_flake_with_lookup` uses so it
+/// doesn't re-read `resource-limits.json` once per agent (same
+/// reasoning as [`effective_from`] / `container_view::build_all`). No
+/// single-agent convenience wrapper, for the same reason as
+/// [`effective_memory_max_from`] — every current caller already has a
+/// loaded map in hand.
+///
+/// Logs a `warn!` naming `name` when the effective value is a RAM
+/// percentage: unlike `"infinity"`, a percentage IS a real, resolvable
+/// cap — resolving one just needs host `MemTotal`, which this module
+/// doesn't track — so today it degrades to `None` (no derived heap
+/// ceiling) rather than silently guessing wrong against `MemTotal`.
+#[must_use]
+pub fn effective_memory_bytes_from(
+    limits: &BTreeMap<String, AgentLimits>,
+    name: &str,
+    hive_memory_max: &str,
+) -> Option<u64> {
+    let mem = effective_memory_max_from(limits, name, hive_memory_max);
+    if mem.ends_with('%') {
+        tracing::warn!(
+            agent = name,
+            memory_max = %mem,
+            "effective MemoryMax= is a RAM percentage; can't derive a JSC heap ceiling from it \
+             without host MemTotal — leaving BUN_JSC_forceRAMSize unset for this agent"
+        );
+    }
+    parse_bytes(&mem)
+}
+
 /// Parse a systemd `MemoryMax=`-style byte-size value (`"4G"`, `"512M"`,
-/// `"1048576B"`, a bare byte count, optionally with a decimal like `"1.5G"`)
+/// a bare byte count, optionally with a decimal like `"1.5G"`) into a
-/// into a raw byte count, accepting exactly the single-term forms systemd's
+/// raw byte count. systemd's `K`/`M`/`G`/`T` suffixes are IEC binary
-/// `parse_size` does: a `K`/`M`/`G`/`T`/`P`/`E` suffix, IEC binary
+/// (1024-based), not decimal — this matches. Pure integer arithmetic
-/// (1024-based), a `B` suffix, or none. Suffixes are case-sensitive, and a
-/// redundant `B` after a multiplier (`4GB`) is rejected, as systemd rejects
-/// both and then leaves the unit uncapped. Pure integer arithmetic
 /// throughout (via `u128` headroom) rather than `f64`: a `MemoryMax=`
 /// value is always a small non-negative decimal (enforced by
 /// [`is_plain_number`] upstream in [`validate_memory_max`]), so floats
 /// would only add rounding / sign-loss risk for no benefit. Returns
-/// `None` for `"infinity"` and for percentages, which need the host's
+/// `None` for `"infinity"` and percentages; see
-/// `MemTotal` to resolve.
+/// [`effective_memory_bytes_from`] for why those can't be turned into a
+/// byte count here.
 #[must_use]
 pub fn parse_bytes(value: &str) -> Option<u64> {
     if value == "infinity" || value.ends_with('%') {
         return None;
     }
-    let (mantissa, exponent) = [
+    let (mantissa, exponent) = [('K', 1u32), ('M', 2), ('G', 3), ('T', 4)]
-        ('E', 6u32),
+        .into_iter()
-        ('P', 5),
+        .find_map(|(suffix, exp)| {
-        ('T', 4),
+            value
-        ('G', 3),
+                .strip_suffix([suffix, suffix.to_ascii_lowercase()])
-        ('M', 2),
+                .map(|m| (m, exp))
-        ('K', 1),
+        })
-        ('B', 0),
+        .unwrap_or((value, 0));
-    ]
-    .into_iter()
-    .find_map(|(suffix, exp)| value.strip_suffix(suffix).map(|m| (m, exp)))
-    .unwrap_or((value, 0));
     let scale = u128::from(1024u64.checked_pow(exponent)?);
     let (int_part, frac_part) = mantissa.split_once('.').unwrap_or((mantissa, ""));
     let whole: u128 = int_part.parse().ok()?;
@@ -473,14 +516,8 @@ mod tests {
             parse_bytes("1.5G"),
             Some(1024 * 1024 * 1024 + 512 * 1024 * 1024)
         );
-        assert_eq!(parse_bytes("1048576B"), Some(1_048_576));
+        // Lowercase suffixes accepted, matching `normalized_byte_size`.
-        assert_eq!(parse_bytes("3P"), Some(3 << 50));
+        assert_eq!(parse_bytes("4g"), Some(4 * 1024 * 1024 * 1024));
-        assert_eq!(parse_bytes("2E"), Some(2 << 60));
-        assert_eq!(
-            parse_bytes("16E"),
-            None,
-            "past u64, which systemd refuses too"
-        );
     }
 
     #[test]
@@ -491,38 +528,50 @@ mod tests {
 
     #[test]
     fn parse_bytes_rejects_garbage() {
-        // systemd's suffixes are case-sensitive and take no `B` after a
+        for v in ["", "abc", "-8G", "8Gi"] {
-        // multiplier, so it leaves a unit with any of these uncapped.
-        for v in [
-            "", "abc", "-8G", "8Gi", "4g", "4k", "1024b", "4GB", "4MB", "B", ".5G",
-        ] {
             assert_eq!(parse_bytes(v), None, "{v} should not parse");
         }
     }
 
     #[test]
-    fn every_size_the_validator_stores_has_a_byte_count() {
+    fn effective_memory_bytes_falls_back_to_hive_default() {
-        for (input, bytes) in [
+        // Empty map, i.e. no per-agent override — exercises the
-            ("1048576", 1_048_576),
+        // "use the hive-wide default" arm end to end.
-            ("1048576B", 1_048_576),
+        let empty = BTreeMap::new();
-            ("1048576b", 1_048_576),
+        assert_eq!(
-            ("4096K", 4096 << 10),
+            effective_memory_bytes_from(&empty, "nobody-configured-this-agent", "4G"),
-            ("4096kb", 4096 << 10),
+            Some(4 * 1024 * 1024 * 1024)
-            ("512M", 512 << 20),
+        );
-            ("512mB", 512 << 20),
+        assert_eq!(
-            ("4G", 4 << 30),
+            effective_memory_bytes_from(&empty, "nobody-configured-this-agent", "infinity"),
-            ("4g", 4 << 30),
+            None
-            ("4GB", 4 << 30),
+        );
-            ("1.5G", 3 << 29),
+    }
-            ("2T", 2 << 40),
+
-            ("2tb", 2 << 40),
+    #[test]
-        ] {
+    fn effective_memory_bytes_from_prefers_per_agent_override() {
-            let stored = validate_memory_max(input).expect(input);
+        let map = BTreeMap::from([("sock".to_owned(), limits(None, Some("8G")))]);
-            assert_eq!(
+        assert_eq!(
-                parse_bytes(&stored),
+            effective_memory_bytes_from(&map, "sock", HIVE_MEM),
-                Some(bytes),
+            Some(8 * 1024 * 1024 * 1024)
-                "{input} stored as {stored}"
+        );
-            );
+        // A different agent not in the map still falls back to the
-        }
+        // hive-wide default from the same loaded map (no re-read).
+        assert_eq!(
+            effective_memory_bytes_from(&map, "iris", HIVE_MEM),
+            Some(4 * 1024 * 1024 * 1024)
+        );
+    }
+
+    /// A percentage cap is real and resolvable in principle, but this
+    /// module has no host `MemTotal` to resolve it against — must
+    /// degrade to `None` (no derived heap ceiling) rather than silently
+    /// treating it as unbounded or guessing a number. `warn!` firing is
+    /// exercised for coverage but not asserted on (no tracing test
+    /// subscriber wired up here) — the `None` return is the contract.
+    #[test]
+    fn effective_memory_bytes_from_returns_none_for_percentage() {
+        let map = BTreeMap::from([("sock".to_owned(), limits(None, Some("50%")))]);
+        assert_eq!(effective_memory_bytes_from(&map, "sock", HIVE_MEM), None);
     }
 }

hive-c0re/src/lifecycle/host_config.rs

@@ -1,7 +1,6 @@
 //! Per-container host-side config: the nspawn conf rewrite (bind mounts,
 //! network isolation, forwarded credentials), the systemd resource-limits
-//! drop-in, the agent's copy of its memory cap, and the `write_dropins` verb
+//! drop-in, and the `write_dropins` verb that re-applies both.
-//! that re-applies them.
 
 use std::path::{Path, PathBuf};
 
@@ -17,22 +16,20 @@ use super::{
 };
 
 /// Re-apply the per-container host-side config: nspawn flags (bind
-/// mounts etc.), the systemd resource-limits drop-in, the agent's copy of
+/// mounts etc.), the systemd resource-limits drop-in, and a daemon
-/// its memory cap, and a daemon reload so all of it takes effect on the next
+/// reload so both take effect on the next unit (re)start. Idempotent —
-/// unit (re)start. Idempotent — the job queue's `WriteDropin` node, also
+/// the job queue's `WriteDropin` node, also folded into every `Swap`
-/// folded into every `Swap` (rebuild is the reconcile verb).
+/// (rebuild is the reconcile verb).
 pub async fn write_dropins(name: &str, hive: &HiveEnv, paths: &AgentPaths) -> Result<()> {
     validate(name)?;
     let container = container_name(name);
     set_nspawn_flags(&container, &paths.agent, &paths.claude, &paths.notes).await?;
-    if let Some((cpu_quota, memory_max)) = stage_limits(
+    if let Some((cpu_quota, memory_max)) = limits_to_apply(
         name,
         &crate::resource_limits::resource_limits_path(),
         &limits_dropin_path(&container),
-        &paths.agent,
         hive,
-        HostMemory::read(),
+    ) {
-    )? {
         set_resource_limits(
             &container,
             &cpu_quota,
@@ -54,173 +51,6 @@ fn limits_dropin_path(container: &str) -> PathBuf {
     ))
 }
 
-/// File in the agent's runtime dir, `/run/hive/` in the container, holding the
-/// `MemoryMax=` its drop-in carries: a byte count, or `infinity` for no cap.
-/// `nix/agent-modules/memory-cap.nix` reads it at boot under this name, and
-/// treats a missing file as a fault.
-const MEMORY_CAP_FILE: &str = "memory-max-bytes";
-
-/// The host's physical memory and page size, the two numbers systemd resolves
-/// a `MemoryMax=` percentage against.
-#[derive(Clone, Copy, Debug)]
-struct HostMemory {
-    bytes: u64,
-    page: u64,
-}
-
-impl HostMemory {
-    /// `sysconf(_SC_PHYS_PAGES) * sysconf(_SC_PAGESIZE)`, as systemd's
-    /// `physical_memory()` computes it. systemd also caps that by the root
-    /// cgroup's `memory.max`, which the host's root cgroup does not have.
-    fn read() -> Option<Self> {
-        // SAFETY: `sysconf(3)` only reads system configuration.
-        let (pages, page) = unsafe {
-            (
-                libc::sysconf(libc::_SC_PHYS_PAGES),
-                libc::sysconf(libc::_SC_PAGESIZE),
-            )
-        };
-        let pages = u64::try_from(pages).ok().filter(|&p| p > 0)?;
-        let page = u64::try_from(page).ok().filter(|&p| p > 0)?;
-        Some(Self {
-            bytes: pages.checked_mul(page)?,
-            page,
-        })
-    }
-}
-
-/// [`limits_to_apply`], plus handing the memory cap to the agent through
-/// [`MEMORY_CAP_FILE`] in `runtime_dir`. The container cannot read the cap
-/// systemd enforces on it, so this file is how it learns the value it sizes
-/// its heap and its subagents against. It is written on every call, from the
-/// `MemoryMax=` the agent will start under: the new one, or the kept drop-in's.
-fn stage_limits(
-    agent_name: &str,
-    limits_path: &Path,
-    dropin_path: &Path,
-    runtime_dir: &Path,
-    hive: &HiveEnv,
-    host: Option<HostMemory>,
-) -> Result<Option<(String, String)>> {
-    let limits = limits_to_apply(agent_name, limits_path, dropin_path, hive);
-    let memory_max = match &limits {
-        Some((_, memory_max)) => Some(memory_max.clone()),
-        None => dropin_memory_max(agent_name, dropin_path),
-    };
-    let cap = memory_max.and_then(|m| memory_cap_value(agent_name, &m, host));
-    write_memory_cap(runtime_dir, cap.as_deref())?;
-    Ok(limits)
-}
-
-/// The `MemoryMax=` the drop-in at `path` applies: its last assignment, as
-/// systemd reads it, or `infinity`, systemd's default, when it has none or its
-/// last one is empty. `None` when the file can't be read.
-fn dropin_memory_max(agent_name: &str, path: &Path) -> Option<String> {
-    let body = match std::fs::read_to_string(path) {
-        Ok(body) => body,
-        Err(e) => {
-            tracing::warn!(
-                agent = %agent_name,
-                path = %path.display(),
-                error = ?e,
-                "limits drop-in unreadable; the agent gets no memory cap"
-            );
-            return None;
-        }
-    };
-    let value = body
-        .lines()
-        .rev()
-        .find_map(|line| line.trim().strip_prefix("MemoryMax="))
-        .map(str::trim)
-        .filter(|v| !v.is_empty())
-        .unwrap_or("infinity");
-    Some(value.to_owned())
-}
-
-/// What [`MEMORY_CAP_FILE`] says for `memory_max`, read the way systemd reads
-/// `MemoryMax=`: a size is its byte count, and a percentage is that share of
-/// `host`'s physical memory, rounded down to a page. A value systemd ignores
-/// (zero, over 100%, more than two decimals, unparseable) leaves the unit
-/// uncapped, so it is `infinity` here. `None` for a percentage when `host` is
-/// unknown.
-fn memory_cap_value(
-    agent_name: &str,
-    memory_max: &str,
-    host: Option<HostMemory>,
-) -> Option<String> {
-    let bytes = if let Some(percent) = memory_max.strip_suffix('%') {
-        let Some(host) = host else {
-            tracing::warn!(
-                agent = agent_name,
-                memory_max,
-                "host physical memory unknown; the agent gets no memory cap"
-            );
-            return None;
-        };
-        permyriad(percent).and_then(|p| scale_physical_memory(host, p))
-    } else {
-        crate::resource_limits::parse_bytes(memory_max)
-    };
-    Some(
-        bytes
-            .filter(|&b| b > 0)
-            .map_or_else(|| "infinity".to_owned(), |b| b.to_string()),
-    )
-}
-
-/// `percent` (the part before `%`) in hundredths of a percent, with systemd's
-/// `parse_permyriad` rules: digits, at most two decimals, at most 100%.
-fn permyriad(percent: &str) -> Option<u64> {
-    let (int, frac) = percent.split_once('.').unwrap_or((percent, ""));
-    if int.is_empty() || !int.bytes().all(|b| b.is_ascii_digit()) {
-        return None;
-    }
-    let hundredths = match frac.as_bytes() {
-        [] if !percent.contains('.') => 0,
-        [d] if d.is_ascii_digit() => u64::from(d - b'0') * 10,
-        [d1, d2] if d1.is_ascii_digit() && d2.is_ascii_digit() => {
-            u64::from(d1 - b'0') * 10 + u64::from(d2 - b'0')
-        }
-        _ => return None,
-    };
-    let value = int
-        .parse::<u64>()
-        .ok()?
-        .checked_mul(100)?
-        .checked_add(hundredths)?;
-    (value <= 10_000).then_some(value)
-}
-
-/// systemd's `physical_memory_scale(permyriad, 10000)`: whole pages, rounded
-/// down, and the exact total at 100%.
-fn scale_physical_memory(host: HostMemory, permyriad: u64) -> Option<u64> {
-    if permyriad == 10_000 {
-        return Some(host.bytes);
-    }
-    let pages = u128::from(host.bytes / host.page) * u128::from(permyriad) / 10_000;
-    u64::try_from(pages * u128::from(host.page)).ok()
-}
-
-/// Write `cap` into [`MEMORY_CAP_FILE`], or remove the file when the cap is
-/// unknown, which the agent reports at boot.
-fn write_memory_cap(runtime_dir: &Path, cap: Option<&str>) -> Result<()> {
-    let path = runtime_dir.join(MEMORY_CAP_FILE);
-    let Some(cap) = cap else {
-        return match std::fs::remove_file(&path) {
-            Err(e) if e.kind() != std::io::ErrorKind::NotFound => {
-                Err(e).with_context(|| format!("remove {}", path.display()))
-            }
-            _ => Ok(()),
-        };
-    };
-    std::fs::create_dir_all(runtime_dir)
-        .with_context(|| format!("create agent runtime dir {}", runtime_dir.display()))?;
-    let tmp = runtime_dir.join(format!(".{MEMORY_CAP_FILE}.tmp"));
-    std::fs::write(&tmp, format!("{cap}\n")).with_context(|| format!("write {}", tmp.display()))?;
-    std::fs::rename(&tmp, &path).with_context(|| format!("rename onto {}", path.display()))
-}
-
 /// The `(CPUQuota, MemoryMax)` to write into `agent_name`'s limits
 /// drop-in, or `None` to leave the drop-in at `dropin_path` as it is.
 ///
@@ -659,10 +489,8 @@ async fn set_nspawn_flags(
 #[cfg(test)]
 mod tests {
     use super::{
-        BindMount, HostMemory, MEMORY_CAP_FILE, QUEUE_CLIENT_ID_CREDENTIAL,
+        BindMount, QUEUE_CLIENT_ID_CREDENTIAL, QUEUE_SECRET_CREDENTIAL, bind_child_agent_dirs,
-        QUEUE_SECRET_CREDENTIAL, bind_child_agent_dirs, bind_own_agent_dirs,
+        bind_own_agent_dirs, holds_manage_root_agent, limits_to_apply, queue_agent_credentials,
-        holds_manage_root_agent, limits_to_apply, memory_cap_value, queue_agent_credentials,
-        stage_limits,
     };
     use crate::coordinator::HiveEnv;
 
@@ -879,169 +707,4 @@ mod tests {
         let applied = limits_to_apply("sock", &limits, &dropin, &HiveEnv::default());
         assert_eq!(applied, Some(("200%".to_owned(), "1G".to_owned())));
     }
-
-    /// 4 000 003 pages of 4 KiB: odd, so rounding to a page shows.
-    const HOST: HostMemory = HostMemory {
-        bytes: 4_000_003 * 4096,
-        page: 4096,
-    };
-
-    /// Runs [`stage_limits`] against the files in `dir` and returns the
-    /// drop-in's `MemoryMax=` and the agent's copy of it, `None` when absent.
-    fn stage(dir: &tempfile::TempDir) -> (Option<String>, Option<String>) {
-        let runtime = dir.path().join("runtime");
-        let applied = stage_limits(
-            "sock",
-            &dir.path().join("resource-limits.json"),
-            &dir.path().join("hyperhive-limits.conf"),
-            &runtime,
-            &HiveEnv::default(),
-            Some(HOST),
-        )
-        .expect("stage limits");
-        let copy = std::fs::read_to_string(runtime.join(MEMORY_CAP_FILE)).ok();
-        (applied.map(|(_, mem)| mem), copy)
-    }
-
-    #[test]
-    fn the_agent_reads_the_cap_its_dropin_carries() {
-        let dir = tempfile::tempdir().expect("tempdir");
-        let limits = dir.path().join("resource-limits.json");
-
-        // No overrides anywhere: the hive-wide default, 4G.
-        assert_eq!(
-            stage(&dir),
-            (Some("4G".to_owned()), Some("4294967296\n".to_owned()))
-        );
-
-        std::fs::write(&limits, r#"{"sock": {"memory_max": "16G"}}"#).expect("seed limits");
-        assert_eq!(
-            stage(&dir),
-            (Some("16G".to_owned()), Some("17179869184\n".to_owned()))
-        );
-    }
-
-    #[test]
-    fn every_kind_of_cap_is_written_for_the_agent() {
-        let dir = tempfile::tempdir().expect("tempdir");
-        let limits = dir.path().join("resource-limits.json");
-        for (memory_max, copy) in [
-            ("infinity", "infinity\n"),
-            ("50%", "8192004096\n"),
-            ("8G", "8589934592\n"),
-        ] {
-            std::fs::write(
-                &limits,
-                format!(r#"{{"sock": {{"memory_max": "{memory_max}"}}}}"#),
-            )
-            .expect("seed limits");
-            assert_eq!(
-                stage(&dir),
-                (Some(memory_max.to_owned()), Some(copy.to_owned())),
-                "{memory_max}"
-            );
-        }
-    }
-
-    #[test]
-    fn a_cap_is_read_the_way_systemd_reads_memory_max() {
-        for (memory_max, cap) in [
-            ("4G", "4294967296"),
-            ("1048576B", "1048576"),
-            ("3P", "3377699720527872"),
-            ("infinity", "infinity"),
-            ("50%", "8192004096"),
-            ("33.33%", "5460787200"),
-            ("12.5%", "2048000000"),
-            ("100%", "16384012288"),
-            // systemd ignores these and the unit runs uncapped.
-            ("0", "infinity"),
-            ("4g", "infinity"),
-            ("4GB", "infinity"),
-            ("0%", "infinity"),
-            ("150%", "infinity"),
-            ("12.345%", "infinity"),
-            ("lots", "infinity"),
-        ] {
-            assert_eq!(
-                memory_cap_value("sock", memory_max, Some(HOST)).as_deref(),
-                Some(cap),
-                "{memory_max}"
-            );
-        }
-        assert_eq!(memory_cap_value("sock", "50%", None), None);
-        assert_eq!(
-            memory_cap_value("sock", "8G", None).as_deref(),
-            Some("8589934592")
-        );
-    }
-
-    #[test]
-    fn the_host_memory_systemd_would_read_is_found() {
-        let host = HostMemory::read().expect("sysconf");
-        assert!(
-            host.page >= 4096 && host.bytes.is_multiple_of(host.page),
-            "{host:?}"
-        );
-    }
-
-    #[test]
-    fn a_kept_dropin_hands_the_agent_its_cap() {
-        let dir = tempfile::tempdir().expect("tempdir");
-        let limits = dir.path().join("resource-limits.json");
-        let dropin = dir.path().join("hyperhive-limits.conf");
-        let copy = dir.path().join("runtime").join(MEMORY_CAP_FILE);
-        std::fs::write(&limits, r#"{"sock": {"memory_max": "1G"}}"#).expect("seed limits");
-        assert_eq!(stage(&dir).1, Some("1073741824\n".to_owned()));
-
-        // Unreadable limits keep the drop-in; the copy follows the drop-in.
-        std::fs::write(&limits, TRUNCATED_LIMITS).expect("seed limits");
-        std::fs::write(
-            &dropin,
-            "[Unit]\nConditionPathIsDirectory=/rt/sock\n\n[Service]\nRestartSec=5\nMemoryMax=2G\nCPUQuota=200%\n",
-        )
-        .expect("seed drop-in");
-        assert_eq!(stage(&dir), (None, Some("2147483648\n".to_owned())));
-
-        // A kept drop-in with no copy beside it, as after an upgrade.
-        std::fs::remove_file(&copy).expect("remove copy");
-        assert_eq!(stage(&dir), (None, Some("2147483648\n".to_owned())));
-
-        // The last assignment is the one systemd applies.
-        std::fs::write(&dropin, "[Service]\nMemoryMax=2G\nMemoryMax=3G\n").expect("seed drop-in");
-        assert_eq!(stage(&dir), (None, Some("3221225472\n".to_owned())));
-
-        // No `MemoryMax=` is systemd's default.
-        std::fs::write(&dropin, "[Service]\nCPUQuota=200%\n").expect("seed drop-in");
-        assert_eq!(stage(&dir), (None, Some("infinity\n".to_owned())));
-    }
-
-    #[test]
-    fn an_unknown_cap_leaves_no_copy() {
-        let dir = tempfile::tempdir().expect("tempdir");
-        let limits = dir.path().join("resource-limits.json");
-        let dropin = dir.path().join("hyperhive-limits.conf");
-        assert_eq!(stage(&dir).1, Some("4294967296\n".to_owned()));
-
-        // Unreadable limits and an unreadable drop-in: nothing says what the
-        // cgroup enforces.
-        std::fs::write(&limits, TRUNCATED_LIMITS).expect("seed limits");
-        std::fs::create_dir(&dropin).expect("seed unreadable drop-in");
-        assert_eq!(stage(&dir), (None, None));
-
-        // A percentage with no host memory to resolve it against.
-        std::fs::write(&limits, r#"{"sock": {"memory_max": "50%"}}"#).expect("seed limits");
-        let runtime = dir.path().join("runtime");
-        let applied = stage_limits(
-            "sock",
-            &limits,
-            &dropin,
-            &runtime,
-            &HiveEnv::default(),
-            None,
-        )
-        .expect("stage limits");
-        assert_eq!(applied.map(|(_, mem)| mem), Some("50%".to_owned()));
-        assert!(!runtime.join(MEMORY_CAP_FILE).exists());
-    }
 }

hive-c0re/src/meta.rs

@@ -88,7 +88,17 @@ pub async fn sync_agents(hive: &HiveEnv, agents: &[AgentSpec]) -> Result<()> {
     let dir = crate::paths::meta_root();
     std::fs::create_dir_all(&dir).with_context(|| format!("create {}", dir.display()))?;
 
-    let new_flake = render_hive_flake(hive, agents)?;
+    let new_flake = render_flake(
+        &hive.hyperhive_flake,
+        &hive.hyperhive_docs_flake,
+        &hive.nixpkgs_flake,
+        hive.claude_code_path.as_deref(),
+        hive.dashboard_port,
+        &hive.operator_pronouns,
+        &hive.context_window_tokens,
+        &hive.agent_memory_max,
+        agents,
+    )?;
     let flake_path = dir.join("flake.nix");
     let on_disk = std::fs::read_to_string(&flake_path).unwrap_or_default();
     let initial = !dir.join(".git").exists();
@@ -434,21 +444,6 @@ pub async fn commit_perms(
     Ok(())
 }
 
-/// [`render_flake`] with its inputs taken from `hive`, as [`sync_agents`]
-/// renders it.
-fn render_hive_flake(hive: &HiveEnv, agents: &[AgentSpec]) -> Result<String> {
-    render_flake(
-        &hive.hyperhive_flake,
-        &hive.hyperhive_docs_flake,
-        &hive.nixpkgs_flake,
-        hive.claude_code_path.as_deref(),
-        hive.dashboard_port,
-        &hive.operator_pronouns,
-        &hive.context_window_tokens,
-        agents,
-    )
-}
-
 #[allow(
     clippy::too_many_arguments,
     reason = "many genuine flake inputs (source flakes, port, pronouns, tokens, \
@@ -462,6 +457,7 @@ fn render_flake(
     dashboard_port: u16,
     operator_pronouns: &str,
     context_window_tokens: &std::collections::HashMap<String, u64>,
+    hive_memory_max: &str,
     agents: &[AgentSpec],
 ) -> Result<String> {
     render_flake_with_lookup(
@@ -472,6 +468,7 @@ fn render_flake(
         dashboard_port,
         operator_pronouns,
         context_window_tokens,
+        hive_memory_max,
         agents,
         agent_canonical_inputs,
     )
@@ -864,6 +861,7 @@ fn render_flake_with_lookup<F>(
     dashboard_port: u16,
     operator_pronouns: &str,
     context_window_tokens: &std::collections::HashMap<String, u64>,
+    hive_memory_max: &str,
     agents: &[AgentSpec],
     lookup: F,
 ) -> Result<String>
@@ -945,7 +943,7 @@ where
     let pronouns_escaped = operator_pronouns.replace('\\', "\\\\").replace('"', "\\\"");
     let _ = writeln!(
         out,
-        "      dashboardPort = {dashboard_port};\n      operatorPronouns = \"{pronouns_escaped}\";\n      mkAgent = {{ name, isManager, port, toolGroups ? null, capabilities ? null }}:"
+        "      dashboardPort = {dashboard_port};\n      operatorPronouns = \"{pronouns_escaped}\";\n      mkAgent = {{ name, isManager, port, toolGroups ? null, capabilities ? null, memoryMaxBytes ? null }}:"
     );
     out.push_str(
         r#"        let
@@ -1096,6 +1094,7 @@ where
               # nspawn itself already call this container, so logs join to
               # both without a prefix transform.
               networking.hostName = "h-${name}";
+              services.hyperhive.agent.claudeMemoryMaxBytes = memoryMaxBytes;
               programs.git.config.user = {
                 name = name;
                 email = "${name}@hyperhive.local";
@@ -1178,9 +1177,12 @@ where
     );
     // Propagated, never read as empty: an agent with no tool-groups entry
     // renders `toolGroups = null` and gets `AGENT_DEFAULT`, which fails
-    // open for any agent whose explicit entry is narrower.
+    // open for any agent whose explicit entry is narrower. Likewise an
+    // agent with no resource-limits entry gets the hive `memoryMaxBytes`,
+    // a larger heap ceiling than a tighter override.
     let tool_groups_map = crate::tool_groups::read()?;
     let capabilities_map = crate::capabilities::read()?;
+    let resource_limits_map = crate::resource_limits::read()?;
     for spec in agents {
         // Emit `toolGroups = "group1,group2"` when the operator has
         // explicitly configured groups for this agent. Absent entry = null
@@ -1206,15 +1208,29 @@ where
             let joined = caps.join(",");
             format!("\"{joined}\"")
         };
+        // Effective `MemoryMax=` for this agent (per-agent override, else
+        // the hive-wide default), turned into a raw byte count so
+        // the agent's claude-settings module can derive a JSC heap ceiling
+        // (see `services.hyperhive.agent.claudeMemoryMaxBytes`). `null` when the
+        // effective value is `"infinity"` or a RAM percentage — no
+        // byte count to derive, dependent env var stays unset, same as
+        // today's no-cap behavior.
+        let memory_max_attr = crate::resource_limits::effective_memory_bytes_from(
+            &resource_limits_map,
+            &spec.name,
+            hive_memory_max,
+        )
+        .map_or_else(|| "null".to_owned(), |b| b.to_string());
         let _ = writeln!(
             out,
-            "        {} = mkAgent {{ name = \"{}\"; isManager = {}; port = {}; toolGroups = {}; capabilities = {}; }};",
+            "        {} = mkAgent {{ name = \"{}\"; isManager = {}; port = {}; toolGroups = {}; capabilities = {}; memoryMaxBytes = {}; }};",
             spec.name,
             spec.name,
             if spec.is_manager { "true" } else { "false" },
             spec.port,
             tool_groups_attr,
             capabilities_attr,
+            memory_max_attr,
         );
     }
     out.push_str("      };\n    };\n}\n");
@@ -1452,6 +1468,7 @@ mod tests {
             8000,
             "she/her",
             &std::collections::HashMap::new(),
+            "4G",
             &[sample_spec("alice", false, 9001)],
         )
         .expect("render flake");
@@ -1499,6 +1516,7 @@ mod tests {
             8000,
             "she/her",
             &std::collections::HashMap::new(),
+            "4G",
             &[sample_spec("alice", false, 9001)],
         )
         .expect("render flake");
@@ -1518,6 +1536,7 @@ mod tests {
             8000,
             "she/her",
             &std::collections::HashMap::new(),
+            "4G",
             &[sample_spec("alice", false, 9001)],
         )
         .expect("render flake");
@@ -1559,6 +1578,7 @@ mod tests {
             8000,
             "she/her",
             &std::collections::HashMap::new(),
+            "4G",
             &[sample_spec("alice", false, 9001)],
         )
         .expect("render flake");
@@ -1588,6 +1608,7 @@ mod tests {
             8000,
             "she/her",
             &std::collections::HashMap::new(),
+            "4G",
             &[sample_spec("alice", false, 9001)],
         )
         .expect("render flake");
@@ -1609,6 +1630,7 @@ mod tests {
             8000,
             "she/her",
             &std::collections::HashMap::new(),
+            "4G",
             &[sample_spec("alice", false, 9001)],
         )
         .expect("render flake");
@@ -1640,6 +1662,7 @@ mod tests {
             8000,
             "she/her",
             &std::collections::HashMap::new(),
+            "4G",
             &[
                 sample_spec("argus", false, 9001),
                 sample_spec("bitburner", false, 9002),
@@ -1674,6 +1697,7 @@ mod tests {
             8000,
             "she/her",
             &std::collections::HashMap::new(),
+            "4G",
             &[sample_spec("alice", false, 9001)],
             |_| Vec::new(),
         )
@@ -1713,6 +1737,7 @@ mod tests {
             8000,
             "she/her",
             &std::collections::HashMap::new(),
+            "4G",
             &[sample_spec("alice", false, 9001)],
         )
         .expect("render flake");
@@ -1759,6 +1784,7 @@ mod tests {
                 8000,
                 "she/her",
                 &std::collections::HashMap::new(),
+                "4G",
                 &[sample_spec("alice", false, 9001)],
             )
             .expect("render flake")
@@ -1940,6 +1966,7 @@ mod tests {
             8000,
             "she/her",
             &std::collections::HashMap::new(),
+            "4G",
             &[sample_spec("alice", false, 9001)],
         )
         .expect("render flake");
@@ -1977,6 +2004,7 @@ mod tests {
             8000,
             "she/her",
             &std::collections::HashMap::new(),
+            "4G",
             &[sample_spec("alice", false, 9001)],
         )
         .expect("render flake");
@@ -2022,6 +2050,7 @@ mod tests {
                 8000,
                 "she/her",
                 &std::collections::HashMap::new(),
+                "4G",
                 &[sample_spec("alice", false, 9001)],
             )
             .expect("render flake")
@@ -2115,6 +2144,7 @@ mod tests {
                 8000,
                 "she/her",
                 &std::collections::HashMap::new(),
+                "4G",
                 &[sample_spec("alice", false, 9001)],
             )
             .expect("render flake")
@@ -2190,6 +2220,7 @@ mod tests {
                 8000,
                 "she/her",
                 &std::collections::HashMap::new(),
+                "4G",
                 &[sample_spec("alice", false, 9001)],
             )
             .expect("render flake")
@@ -2215,20 +2246,32 @@ mod tests {
         );
     }
 
-    /// The agent reads its memory cap at boot from the copy
+    /// The JSC-heap-ceiling fix needs the effective per-agent memory cap
-    /// `lifecycle::write_dropins` hands it, so the cap is no build input.
+    /// threaded into the flake as raw bytes, since nspawn hides the real
+    /// cgroup cap from inside the container. An
+    /// agent with no `resource-limits.json` override falls back to the
+    /// hive-wide default passed to `render_flake` (`"4G"` in every test
+    /// in this module) — this locks in the byte-count conversion end to
+    /// end through the actual render path (not just `parse_bytes`
+    /// in isolation).
     #[test]
-    fn render_hive_flake_is_identical_across_memory_caps() {
+    fn render_flake_derives_memory_max_bytes_from_hive_default() {
-        let hive = |cap: &str| HiveEnv {
+        let out = render_flake(
-            agent_memory_max: cap.to_owned(),
+            "github:example/hyperhive",
-            ..HiveEnv::default()
+            "path:/nix/store/bbbb-hyperhive-docs-source",
-        };
+            "path:/nix/store/aaaa-nixpkgs-source",
-        let agents = [sample_spec("alice", false, 9001)];
+            None,
-        let small = render_hive_flake(&hive("4G"), &agents).expect("render 4G");
+            8000,
-        let large = render_hive_flake(&hive("16G"), &agents).expect("render 16G");
+            "she/her",
-        assert_eq!(
+            &std::collections::HashMap::new(),
-            small, large,
+            "4G",
-            "the rendered flake must not depend on the memory cap"
+            &[sample_spec("alice", false, 9001)],
+        )
+        .expect("render flake");
+        let want_bytes = 4u64 * 1024 * 1024 * 1024;
+        assert!(
+            out.contains(&format!("memoryMaxBytes = {want_bytes};")),
+            "memoryMaxBytes must reflect the hive-wide default in bytes:\n{out}"
         );
     }
 }

hive-c0re/src/server.rs

@@ -433,9 +433,10 @@ async fn handle_set_resource_limits(
         &hive.agent_memory_max,
     )?;
     Ok(HostResponse::messages(vec![format!(
-        "{name}: CPUQuota={cpu} MemoryMax={mem} — the cgroup cap itself is live now; the \
+        "{name}: CPUQuota={cpu} MemoryMax={mem} — the cgroup cap itself is live now (restart \
-         Claude/JSC heap ceiling and the subagent MemoryHigh= derived from it follow at the \
+         the container if it's running and needs the new cap immediately), but the derived \
-         container's next start (restart it if it's running and needs them now)"
+         Claude/JSC heap ceiling is baked in at build time, so it needs a REBUILD \
+         (`hivectl agent {name} rebuild`) to actually track this change"
     )]))
 }
 

nix/agent-modules/claude-settings.nix

@@ -19,6 +19,11 @@ 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.
@@ -42,6 +47,19 @@ 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,
@@ -81,6 +99,31 @@ 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 = [
@@ -214,7 +257,9 @@ 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).
+        # 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.
         allEnv =
           baseClaudeEnv
           // lib.optionalAttrs otelCfg.enable otelSettingsEnv

nix/agent-modules/default.nix

@@ -41,11 +41,6 @@ let
     which the hive writes into every container, so no agent build sets it.
     Remove the setting.
   '';
-  memoryMaxBytesRemoved = ''
-    An agent reads its memory cap at boot from /run/hive/memory-max-bytes,
-    which the hive writes before every start, so no agent build sets it.
-    Remove the setting.
-  '';
 in
 {
   imports = [
@@ -65,7 +60,6 @@ in
     ./logs.nix
     ./matrix.nix
     ./mcp.nix
-    ./memory-cap.nix
     ./network.nix
     ./otel.nix
     ./packages.nix
@@ -100,13 +94,6 @@ in
     # Both spellings, for the reason given above.
     (lib.mkRemovedOptionModule [ "hyperhive" "hiveName" ] hiveNameRemoved)
     (lib.mkRemovedOptionModule [ "services" "hyperhive" "agent" "hiveName" ] hiveNameRemoved)
-    (lib.mkRemovedOptionModule [ "hyperhive" "claudeMemoryMaxBytes" ] memoryMaxBytesRemoved)
-    (lib.mkRemovedOptionModule [
-      "services"
-      "hyperhive"
-      "agent"
-      "claudeMemoryMaxBytes"
-    ] memoryMaxBytesRemoved)
   ];
 
   options.services.hyperhive.agent.icon = lib.mkOption {

nix/agent-modules/mcp.nix

@@ -11,6 +11,25 @@
 }:
 let
   userName = config.services.hyperhive.agent.user.name;
+  # This container's own effective `MemoryMax=` in bytes, baked in per
+  # agent by meta.rs's flake render — see
+  # `services.hyperhive.agent.claudeMemoryMaxBytes` in ./claude-settings.nix. `null`
+  # when the cap is `infinity` or a RAM percentage, i.e. when the module
+  # has no byte count to size anything against.
+  containerMemoryMaxBytes = config.services.hyperhive.agent.claudeMemoryMaxBytes;
+  # Two thirds of the container's cap, as the soft ceiling on everything
+  # the subagent daemon runs. The daemon spawns nested `claude` sessions
+  # as plain children, so its cgroup already *is* the "all subagents"
+  # cgroup and a unit-level ceiling bounds the set without a slice.
+  #
+  # `MemoryHigh=` and not `MemoryMax=`: this throttles rather than walls.
+  # Past it the kernel reclaims aggressively and the cgroup stalls, so a
+  # subagent that overshoots gets visibly slow and the remaining third
+  # stays available for the agent's own turn — but a subagent that
+  # genuinely needs more than two thirds still gets it when the container
+  # has the memory to spare, which is what keeps overprovisioning
+  # (several agents that rarely compile at the same time) working.
+  subagentMemoryHigh = containerMemoryMaxBytes * 2 / 3;
   # Set on the harness only for an ACP agent on the opencode preset
   # (./agent-service.nix).
   acpApiKeyEnv = config.systemd.services.hive-agent.environment.HIVE_ACP_API_KEY_ENV or null;
@@ -456,11 +475,12 @@ in
         # actually chose and leaves the daemon serving, which is also what
         # lets it report the kill rather than vanish and be restarted.
         OOMPolicy = "continue";
-        # `MemoryHigh=` is a drop-in from ./memory-cap.nix, sized at boot from
-        # the container's cap.
         User = userName;
         Group = userName;
       }
+      // lib.optionalAttrs (containerMemoryMaxBytes != null) {
+        MemoryHigh = toString subagentMemoryHigh;
+      }
       // lib.optionalAttrs subagentReadsStore {
         # Bare id: inherits the credential the container manager passed in,
         # the same form ./queue-identity.nix uses.

nix/agent-modules/memory-cap.nix

@@ -1,98 +0,0 @@
-# The container's memory cap, read at boot rather than built in, so a changed
-# cap needs no rebuild.
-#
-# The cap is `MemoryMax=` on the host's `container@` unit, which nothing in
-# here can read: `/sys/fs/cgroup/memory.max` reads `max` at every level from
-# inside. Before every start hive-c0re (`lifecycle::host_config`) writes it to
-# `/run/hive/memory-max-bytes` as a byte count, a percentage resolved against
-# the host's RAM as systemd resolves it, or `infinity` for no cap. Two values
-# are derived from a byte count, and neither is set for `infinity`. A missing
-# or malformed file sets neither too, and `hyperhive-memory-cap-check` logs a
-# warning at boot:
-#
-# - `BUN_JSC_forceRAMSize`, 75% of the cap. Bun/JavaScriptCore, the runtime
-#   under claude-code, sizes its heap ceiling off `/proc/meminfo`, which under
-#   nspawn is the host's RAM, so without it the heap grows well past the real
-#   wall before GC kicks in hard and choom sessions hang. An environment
-#   generator hands it to every unit of the container's systemd, `machinectl
-#   shell` sessions (`hivectl choom`) included; `/etc/set-environment` exports
-#   it in login shells that no unit starts (`nixos-container root-login`).
-#   `hive-agent` and `hive-subagent-daemon` spawn `claude` as a plain child,
-#   which inherits it, so neither unit may set or unset it.
-# - `MemoryHigh=` on `hive-subagent-daemon`, two thirds of the cap, as a
-#   generator drop-in. The daemon spawns nested `claude` sessions as plain
-#   children, so its cgroup already is the "all subagents" cgroup. `High`, not
-#   `Max`: past it the kernel reclaims hard and the subagents slow down, so the
-#   last third stays free for the agent's own turn, but a subagent that needs
-#   more still gets it when the container has memory to spare.
-#
-# Tested by `checks.script-test-agent-memory-cap` and
-# `checks.module-eval-agent-memory`.
-{ pkgs, ... }:
-let
-  # Sets `bytes`. Exits for `infinity`, and runs `noCap` when there is no file
-  # or its first line is neither `infinity` nor a plain byte count. A leading
-  # zero would read as octal, and 16 digits or more could overflow
-  # `bytes * 75`. Shell builtins only.
-  readCap = noCap: ''
-    bytes=
-    [ -r /run/hive/memory-max-bytes ] && read -r bytes < /run/hive/memory-max-bytes
-    case "$bytes" in
-      infinity) exit 0 ;;
-      "" | 0* | *[!0-9]* | ????????????????*) ${noCap} ;;
-    esac
-  '';
-
-  envGenerator = pkgs.writeShellScript "hyperhive-memory-cap-env" ''
-    ${readCap "exit 0"}
-    printf 'BUN_JSC_forceRAMSize=%s\n' "$((bytes * 75 / 100))"
-  '';
-
-  # `$1` is the generator's normal-priority output dir. A drop-in there merges
-  # with the unit's own file in /etc.
-  unitGenerator = pkgs.writeShellScript "hyperhive-memory-cap" ''
-    ${readCap "exit 0"}
-    dir="$1/hive-subagent-daemon.service.d"
-    ${pkgs.coreutils}/bin/mkdir -p "$dir"
-    printf '[Service]\nMemoryHigh=%s\n' "$((bytes * 2 / 3))" > "$dir/50-memory-high.conf"
-  '';
-
-  # The generators run before the container's journal starts and an nspawn
-  # container has no /dev/kmsg, so the boot warning for a missing or malformed
-  # cap file comes from a unit. `<4>` is the journal's warning priority.
-  check = pkgs.writeShellScript "hyperhive-memory-cap-check" ''
-    ${readCap ''
-      if [ -e /run/hive/memory-max-bytes ]; then
-        why="holds neither a byte count nor infinity"
-      else
-        why="is missing"
-      fi
-      echo "<4>/run/hive/memory-max-bytes $why: no BUN_JSC_forceRAMSize heap ceiling and no MemoryHigh= on hive-subagent-daemon; the host's MemoryMax= on the container still applies." >&2
-      exit 0
-    ''}
-  '';
-
-  # Sourced by every shell's `/etc/set-environment`, so POSIX sh only.
-  profile = pkgs.writeText "hyperhive-memory-cap.sh" ''
-    __hyperhive_cap=$(${envGenerator})
-    case "$__hyperhive_cap" in
-      BUN_JSC_forceRAMSize=?*) export "$__hyperhive_cap" ;;
-    esac
-    unset __hyperhive_cap
-  '';
-in
-{
-  environment.etc."systemd/system-environment-generators/50-hyperhive-memory-cap".source =
-    envGenerator;
-  systemd.generators.hyperhive-memory-cap = unitGenerator;
-  systemd.services.hyperhive-memory-cap-check = {
-    description = "Warn when the container's memory cap is unusable";
-    wantedBy = [ "multi-user.target" ];
-    serviceConfig = {
-      Type = "oneshot";
-      ExecStart = check;
-    };
-  };
-  environment.etc."hyperhive/memory-cap.sh".source = profile;
-  environment.extraInit = ". /etc/hyperhive/memory-cap.sh";
-}

nix/agent-modules/renamed-options.nix

@@ -45,6 +45,10 @@
       [ "hyperhive" "claudeMarketplaces" ]
       [ "services" "hyperhive" "agent" "claudeMarketplaces" ]
     )
+    (lib.mkRenamedOptionModule
+      [ "hyperhive" "claudeMemoryMaxBytes" ]
+      [ "services" "hyperhive" "agent" "claudeMemoryMaxBytes" ]
+    )
     (lib.mkRenamedOptionModule
       [ "hyperhive" "claudePlugins" ]
       [ "services" "hyperhive" "agent" "claudePlugins" ]

nix/checks.nix

@@ -138,12 +138,6 @@ in
     inherit pkgs self nixosSystem;
     inherit (pkgs) lib;
   };
-  # Runs ./agent-modules/memory-cap.nix's generators and login-shell snippet
-  # against sample cap files.
-  script-test-agent-memory-cap = import ./script-tests/agent-memory-cap.nix {
-    inherit pkgs self nixosSystem;
-    inherit (pkgs) lib;
-  };
   module-eval-agent-github-bao = import ./module-eval/agent-github-bao.nix {
     inherit pkgs self nixosSystem;
     inherit (pkgs) lib;

nix/module-eval/agent-memory.nix

@@ -22,37 +22,39 @@ let
     agentHarness
     ;
 
-  agentDefault = agent { };
+  # 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 = [
     {
-      # The ceiling is sized at boot from the container's cap
+      # Two thirds of the container's cap, and a SOFT ceiling: the daemon's
-      # (../agent-modules/memory-cap.nix). One in the unit would be the cap at
+      # cgroup holds every nested claude, so `MemoryHigh=` throttles the
-      # the last rebuild, and every agent would carry its own hive's number.
+      # subagent set as a whole before the kernel picks a victim, while the
-      name = "the subagent daemon's memory ceiling is not built into its unit";
+      # absent `MemoryMax=` is what still lets one subagent use more than
-      ok = !((agentSubagentDaemon agentDefault).serviceConfig ? MemoryHigh);
+      # 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.
-      # claude's heap ceiling reaches it only as inherited environment: the
+      name = "the subagent daemon throttles at two thirds of the container's memory";
-      # environment generator fills the manager's, systemd hands that to every
-      # unit, and both units spawn claude as a plain child. A unit that sets
-      # or unsets the variable itself cuts that. Without the two generators the
-      # cap reaches nothing, and without the check unit nothing says so.
-      name = "claude's units take the heap ceiling from the memory cap read at boot";
       ok =
         let
-          leavesIt =
+          c = (agentSubagentDaemon agentCapped).serviceConfig;
-            unit:
-            !(unit.environment ? BUN_JSC_forceRAMSize)
-            && !(lib.elem "BUN_JSC_forceRAMSize" (lib.toList (unit.serviceConfig.UnsetEnvironment or [ ])));
         in
-        leavesIt (agentHarness agentDefault)
+        c.MemoryHigh == "5726623061" && !(c ? MemoryMax);
-        && leavesIt (agentSubagentDaemon agentDefault)
+    }
-        && agentDefault.environment.etc ? "systemd/system-environment-generators/50-hyperhive-memory-cap"
+    {
-        && agentDefault.systemd.generators ? hyperhive-memory-cap
+      # What makes the case above able to fail. With no byte count for the
-        && lib.elem "multi-user.target" agentDefault.systemd.services.hyperhive-memory-cap-check.wantedBy;
+      # 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:
@@ -66,8 +68,8 @@ let
       name = "the OOM killer prefers a subagent over the agent's own session";
       ok =
         let
-          sub = (agentSubagentDaemon agentDefault).serviceConfig.OOMScoreAdjust;
+          sub = (agentSubagentDaemon agentUncapped).serviceConfig.OOMScoreAdjust;
-          own = (agentHarness agentDefault).serviceConfig.OOMScoreAdjust;
+          own = (agentHarness agentUncapped).serviceConfig.OOMScoreAdjust;
         in
         sub > 0 && own < 0 && sub > own;
     }
@@ -79,13 +81,13 @@ let
       # 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 agentDefault).serviceConfig.OOMPolicy == "continue";
+      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 agentDefault).serviceConfig.OOMPolicy or null == "continue";
+      ok = (agentBashDaemon agentUncapped).serviceConfig.OOMPolicy or null == "continue";
     }
   ];
 in

nix/script-tests/agent-memory-cap.nix

@@ -1,44 +0,0 @@
-# `checks.script-test-agent-memory-cap` — runs the four readers of
-# `/run/hive/memory-max-bytes` in ../agent-modules/memory-cap.nix: the
-# environment generator, the unit generator, the boot check that warns about
-# an unusable cap, and the login-shell snippet `/etc/set-environment` sources.
-# The cases are in ./agent-memory-cap.sh.
-#
-# What runs is the rendered scripts. The one edit is the cap file's path, moved
-# under the build directory, and the snippet's reference to the environment
-# generator, pointed at that edited copy.
-{
-  pkgs,
-  lib,
-  self,
-  nixosSystem,
-}:
-let
-  inherit
-    (import ../module-eval/lib.nix {
-      inherit
-        pkgs
-        lib
-        self
-        nixosSystem
-        ;
-    })
-    agentWith
-    ;
-
-  machine = agentWith { };
-in
-pkgs.runCommand "hyperhive-script-test-agent-memory-cap"
-  {
-    ENV_GENERATOR =
-      machine.environment.etc."systemd/system-environment-generators/50-hyperhive-memory-cap".source;
-    UNIT_GENERATOR = machine.systemd.generators.hyperhive-memory-cap;
-    CHECK = machine.systemd.services.hyperhive-memory-cap-check.serviceConfig.ExecStart;
-    PROFILE = machine.environment.etc."hyperhive/memory-cap.sh".source;
-    EXTRA_INIT = machine.environment.extraInit;
-    SHELLS = "${pkgs.dash}/bin/dash ${pkgs.bash}/bin/sh";
-  }
-  ''
-    ${pkgs.bash}/bin/bash ${./agent-memory-cap.sh}
-    touch "$out"
-  ''

nix/script-tests/agent-memory-cap.sh

@@ -1,116 +0,0 @@
-# Cases for ./agent-memory-cap.nix. Each case writes a cap file (or none), runs
-# both generators and the boot check with a clean environment and compares what
-# they produced, then sources the login-shell snippet under each POSIX shell
-# and compares what a child process sees.
-set -uo pipefail
-
-failures=0
-count=0
-
-fail() {
-  echo "FAILED: $case: $*" >&2
-  failures=$((failures + 1))
-}
-
-dir=$(mktemp -d)
-cap=$dir/memory-max-bytes
-sed "s|/run/hive/memory-max-bytes|$cap|g" "$ENV_GENERATOR" >"$dir/env-generator"
-sed "s|/run/hive/memory-max-bytes|$cap|g" "$UNIT_GENERATOR" >"$dir/unit-generator"
-sed "s|/run/hive/memory-max-bytes|$cap|g" "$CHECK" >"$dir/check"
-chmod +x "$dir/env-generator" "$dir/unit-generator" "$dir/check"
-sed "s|$ENV_GENERATOR|$dir/env-generator|g" "$PROFILE" >"$dir/profile"
-envbin=$(command -v env)
-
-case="setup"
-for g in env-generator unit-generator check; do
-  if grep -q '/run/hive/memory-max-bytes' "$dir/$g"; then fail "$g still names /run/hive after the rewrite"; fi
-  if ! grep -qF "$cap" "$dir/$g"; then fail "the rewrite did not reach $g's read"; fi
-done
-if ! grep -qF "$dir/env-generator" "$dir/profile"; then fail "the snippet does not call the rewritten generator"; fi
-if ! printf '%s\n' "$EXTRA_INIT" | grep -qxF '. /etc/hyperhive/memory-cap.sh'; then
-  fail "/etc/set-environment does not source the snippet"
-fi
-
-# check <description> <expected BUN_JSC_forceRAMSize or ""> <expected MemoryHigh or "">
-#       <why the boot check warns, or "">
-check() {
-  case=$1
-  count=$((count + 1))
-  local want_env=${2:+BUN_JSC_forceRAMSize=$2} want_high=$3 want_why=${4:-} got
-  got=$(env -i "$dir/env-generator")
-  if [ "$got" != "$want_env" ]; then
-    fail "environment generator printed:"$'\n'"$got"$'\n'"wanted:"$'\n'"$want_env"
-  fi
-
-  local out=$dir/generator-out
-  rm -rf "$out"
-  mkdir -p "$out/normal" "$out/early" "$out/late"
-  env -i "$dir/unit-generator" "$out/normal" "$out/early" "$out/late"
-  local dropin=$out/normal/hive-subagent-daemon.service.d/50-memory-high.conf
-  if [ -z "$want_high" ]; then
-    got=$(find "$out" -type f)
-    if [ -n "$got" ]; then fail "unit generator wrote:"$'\n'"$got"; fi
-  else
-    got=$(cat "$dropin" 2>&1)
-    if [ "$got" != "[Service]"$'\n'"MemoryHigh=$want_high" ]; then
-      fail "unit generator's drop-in:"$'\n'"$got"
-    fi
-  fi
-
-  # The warning goes to stderr with the journal's `<4>` priority prefix, and
-  # nothing goes anywhere for a byte count or `infinity`.
-  got=$(env -i "$dir/check" 2>&1)
-  local want_warn=
-  if [ -n "$want_why" ]; then
-    want_warn="<4>$cap $want_why: no BUN_JSC_forceRAMSize heap ceiling and no MemoryHigh= on hive-subagent-daemon; the host's MemoryMax= on the container still applies."
-  fi
-  if [ "$got" != "$want_warn" ]; then
-    fail "boot check printed:"$'\n'"$got"$'\n'"wanted:"$'\n'"$want_warn"
-  fi
-
-  local sh
-  for sh in $SHELLS; do
-    # Only what the snippet exported reaches the child's environment. No PATH:
-    # the snippet must not need one.
-    got=$(env -i "$sh" -c ". '$dir/profile'; exec '$envbin'" | grep -E '^(BUN_|LD_PRELOAD=|__hyperhive)')
-    if [ "$got" != "$want_env" ]; then
-      fail "$sh: a child of the sourcing shell saw:"$'\n'"$got"
-    fi
-  done
-}
-
-printf '8589934592\n' >"$cap"
-check "an 8G cap" 6442450944 5726623061
-
-printf '4294967296' >"$cap"
-check "a line without a newline is kept" 3221225472 2863311530
-
-printf '4294967296\nLD_PRELOAD=/x\n' >"$cap"
-check "only the first line is read" 3221225472 2863311530
-
-printf 'infinity\n' >"$cap"
-check "infinity sets nothing and warns of nothing" "" "" ""
-
-printf 'infinity' >"$cap"
-check "infinity without a newline" "" "" ""
-
-printf 'infinityx\n' >"$cap"
-check "a word that only starts with infinity" "" "" "holds neither a byte count nor infinity"
-
-printf '8G\n' >"$cap"
-check "a size with a suffix is ignored" "" "" "holds neither a byte count nor infinity"
-
-printf '0123\n' >"$cap"
-check "a leading zero is ignored" "" "" "holds neither a byte count nor infinity"
-
-printf '1234567890123456\n' >"$cap"
-check "sixteen digits are ignored" "" "" "holds neither a byte count nor infinity"
-
-: >"$cap"
-check "an empty file" "" "" "holds neither a byte count nor infinity"
-
-rm -f "$cap"
-check "no file" "" "" "is missing"
-
-echo "$count cases, $failures failed"
-[ "$failures" -eq 0 ]