Watch
0
0
Fork
You've already forked hyperhive
0

hive-c0re: an unreadable capabilities file denies ManageRootAgent mounts

set_nspawn_flags propagated has_cap's error, so one corrupt
capabilities.json failed every agent's Start, spawn and Swap. It now
goes through holds_manage_root_agent, which logs the error (agent and
file) and treats the capability as absent: the agent starts without the
cross-agent, /applied and /meta mounts. caps_for/has_cap take the file
path so that seam is testable against a tempfile.

- meta.rs: a comment at the render_flake reads records why they
  propagate (an empty tool-groups map renders toolGroups = null, i.e.
  AGENT_DEFAULT, which fails open for narrower explicit entries).
- capabilities::read doc: states when set_caps/remove_agent rewrite
  the file instead of saying remove_agent repairs it.
- set/remove corrupt-file tests assert ErrorKind::InvalidData.
This commit is contained in:
atlas 2026-09-26 14:43:53 +02:00 • committed by mara
commit c978060824
4 changed files with 72 additions and 17 deletions

View file

@ -135,6 +135,24 @@ fn bind_child_agent_dirs(child: &str, binds: &mut Vec<BindMount>) {
}
}
/// Whether `agent_name` holds `ManageRootAgent` per the capabilities file
/// at `caps_path`. An unreadable file denies: the error is logged and the
/// agent starts without the cross-agent mounts, so one corrupt file never
/// blocks any agent's start, spawn or swap.
fn holds_manage_root_agent(agent_name: &str, caps_path: &Path) -> bool {
crate::capabilities::has_cap(caps_path, agent_name, Capability::ManageRootAgent).unwrap_or_else(
|e| {
tracing::error!(
agent = %agent_name,
path = %caps_path.display(),
error = ?e,
"capabilities unreadable — no ManageRootAgent mounts"
);
false
},
)
}
/// Env var naming the host directory `swarm-bao-queue-agent.service` lands
/// this hive's agent queue credential in. Set by the hive-c0re NixOS module
/// from `deploy.hive-controller.queue.agentCredentialDir`; absent means this
@ -339,7 +357,7 @@ async fn set_nspawn_flags(
// parent field took with it the unconditional grant every
// agent used to get over its own direct children — so an agent with
// no capability now sees its own dirs and nothing else.
if crate::capabilities::has_cap(agent_name, Capability::ManageRootAgent)? {
if holds_manage_root_agent(agent_name, &crate::capabilities::capabilities_path()) {
// Skipping self is a no-op, not a narrowing: `agent_notes_dir` is
// `agent_state_dir/state` and `config_bind_source` is shared, so
// binding the holder as its own virtual child reproduced the two
@ -408,7 +426,7 @@ async fn set_nspawn_flags(
mod tests {
use super::{
BindMount, QUEUE_CLIENT_ID_CREDENTIAL, QUEUE_SECRET_CREDENTIAL, bind_child_agent_dirs,
queue_agent_credentials,
holds_manage_root_agent, queue_agent_credentials,
};
fn child_binds() -> Vec<BindMount> {
@ -524,4 +542,23 @@ mod tests {
]
);
}
#[test]
fn a_corrupt_capabilities_file_denies_without_failing() {
let dir = tempfile::tempdir().expect("tempdir");
let path = dir.path().join("capabilities.json");
let truncated = "{\n \"ruth\": [\"manage_root_ag";
std::fs::write(&path, truncated).expect("seed");
assert!(!holds_manage_root_agent("ruth", &path));
assert_eq!(std::fs::read(&path).expect("read"), truncated.as_bytes());
}
#[test]
fn a_readable_grant_is_honoured() {
let dir = tempfile::tempdir().expect("tempdir");
let path = dir.path().join("capabilities.json");
std::fs::write(&path, r#"{"ruth": ["manage_root_agent"]}"#).expect("seed");
assert!(holds_manage_root_agent("ruth", &path));
assert!(!holds_manage_root_agent("alice", &path));
}
}