Watch
0
0
Fork
You've already forked hyperhive
0
hyperhive/hive-c0re/src/agent_config/capabilities.rs
atlas e0b08fe362 hive-c0re: fail on an unparseable permission file, write it atomically
tool_groups::read and capabilities::read returned an empty map when
their file existed but didn't parse. Every set_*/remove_agent is a
read-modify-write, and write() rewrote the file in place, so a crash or
ENOSPC mid-write left a truncated file, and the next write (e.g. the
manager-spawn seed of ruth's tool groups) replaced it with a map holding
only one agent. The scheduling and approval gates then denied every
other agent, recoverable only from meta git history.

- Both registries now read through agent_config::read_map: a missing
  file is still the empty map, any other read failure or a parse
  failure is an io::Error. set_groups / set_caps / remove_agent fail
  without writing.
- Writes go through agent_config::write_map: temp file in the same
  directory, fsync, rename, fsync the directory. hive-c0re had no
  shared atomic-write helper (the existing tmp+rename sites are inline
  and don't fsync).
- Callers of read / groups_for / has_cap now handle the error:
  * dashboard GET /api/tool-groups, /api/capabilities,
    /api/permissions/stale return 500 instead of an empty table;
  * the SSE permission snapshots are skipped with a warn;
  * render_flake returns Result, so sync_agents fails instead of
    rendering every agent without its tool groups / capabilities;
  * set_nspawn_flags propagates has_cap's error;
  * the socket tool-group gates deny with the read error as message;
  * seed_manager_tool_groups logs and does not seed.
- capabilities::write had no callers left once set_caps writes through
  write_map, and is removed.

Closes #4719
2026-09-26 21:11:54 +02:00

253 lines
9.3 KiB
Rust

//! Per-agent capability configuration. Stored at
//! `/var/lib/hyperhive/meta/capabilities.json` alongside `topology.json`
//! and `tool-groups.json`.
//!
//! Format: a JSON object mapping agent name to an array of
//! `hive_sh4re::permissions::Capability` `snake_case` strings:
//!
//! ```json
//! {
//! "atlas": ["manage_root_agent"]
//! }
//! ```
//!
//! An absent entry (or an absent file) means "no extra capabilities".
//! `render_flake` in `meta.rs` reads this file and injects
//! `HIVE_CAPABILITIES` into each agent's systemd service env; absent
//! entries emit no env var so agents without capabilities don't trigger
//! a spurious rebuild.
//!
//! Write path: `set_caps` is called from the dashboard action handler
//! that the operator uses to grant/revoke capabilities per agent.
use hive_sh4re::permissions::Capability;
use std::collections::BTreeMap;
use std::path::{Path, PathBuf};
const CAPABILITIES_FILE: &str = "capabilities.json";
#[must_use]
pub fn capabilities_path() -> PathBuf {
crate::paths::meta_root().join(CAPABILITIES_FILE)
}
/// True if `name` matches a recognised [`Capability`], case-insensitive
/// (same comparison [`has_cap`] uses).
#[must_use]
fn is_known(name: &str) -> bool {
Capability::ALL
.iter()
.any(|cap| name.eq_ignore_ascii_case(<&str>::from(*cap)))
}
/// Drop any capability string in `map` that isn't a recognised
/// [`Capability`], warning per dropped string so a typo'd or stale
/// grant doesn't look like it worked. An agent left with no
/// capabilities is removed entirely, matching [`set_caps`]'s
/// empty-vec behaviour. Returns whether anything was dropped.
fn prune_unknown(map: &mut BTreeMap<String, Vec<String>>) -> bool {
let mut dropped_any = false;
map.retain(|agent, caps| {
caps.retain(|cap| {
let known = is_known(cap);
if !known {
dropped_any = true;
tracing::warn!(agent, capability = %cap, "dropping unrecognised capability");
}
known
});
!caps.is_empty()
});
dropped_any
}
/// Read the per-agent capability map. An absent file is the empty map —
/// callers treat a missing entry as "no extra capabilities". A file
/// that exists but can't be read or parsed is an error. Any entry that
/// isn't a recognised [`Capability`] is dropped (with a `warn!`) from
/// what's returned — a stale or typo'd name is never honoured — but
/// `read` itself never writes; the on-disk file only gets repaired the
/// next time something calls `set_caps`/`remove_agent` anyway.
pub fn read() -> std::io::Result<BTreeMap<String, Vec<String>>> {
read_from(&capabilities_path())
}
fn read_from(path: &Path) -> std::io::Result<BTreeMap<String, Vec<String>>> {
let mut map = super::read_map(path)?;
prune_unknown(&mut map);
Ok(map)
}
/// Look up the configured capabilities for one agent. Returns an empty
/// vec when the agent has no entry. Errors as [`read`] does.
pub fn caps_for(name: &str) -> std::io::Result<Vec<String>> {
Ok(read()?.get(name).cloned().unwrap_or_default())
}
/// Check whether an agent holds a specific capability. Errors as
/// [`read`] does.
pub fn has_cap(name: &str, cap: hive_sh4re::permissions::Capability) -> std::io::Result<bool> {
Ok(caps_for(name)?
.iter()
.any(|s| s.eq_ignore_ascii_case(<&str>::from(cap))))
}
/// Filter `caps` down to recognised [`Capability`] names (warning per
/// drop) and apply the result to `current` for `name`: an empty
/// result — whether `caps` started empty or every name in it was
/// unknown — removes the entry, matching `read`'s empty-entry
/// convention. Split out from [`set_caps`] so the decision logic is
/// testable without touching the real capabilities file.
fn apply_known_caps(current: &mut BTreeMap<String, Vec<String>>, name: &str, caps: &[String]) {
let known: Vec<String> = caps
.iter()
.filter(|cap| {
let ok = is_known(cap);
if !ok {
tracing::warn!(agent = name, capability = %cap, "dropping unrecognised capability");
}
ok
})
.cloned()
.collect();
if known.is_empty() {
current.remove(name);
} else {
current.insert(name.to_owned(), known);
}
}
/// Set the capabilities for one agent and persist the map. Any name
/// that isn't a recognised [`Capability`] is dropped (with a `warn!`)
/// rather than written — an unknown grant should never look like it
/// took effect. An empty `caps` vec, or one that becomes empty after
/// dropping unknown names, removes the entry (agent has no
/// capabilities). Fails without writing if the existing file can't be
/// read or parsed.
pub fn set_caps(name: &str, caps: &[String]) -> std::io::Result<()> {
set_caps_at(&capabilities_path(), name, caps)
}
fn set_caps_at(path: &Path, name: &str, caps: &[String]) -> std::io::Result<()> {
let mut current = read_from(path)?;
apply_known_caps(&mut current, name, caps);
super::write_map(path, &current)
}
/// Remove an agent from the capability map entirely. Called by
/// `meta::sync_agents` when an agent is deprovisioned so stale entries
/// don't accumulate. No-op if the agent has no entry. Fails without
/// writing if the existing file can't be read or parsed.
pub fn remove_agent(name: &str) -> std::io::Result<()> {
remove_agent_at(&capabilities_path(), name)
}
fn remove_agent_at(path: &Path, name: &str) -> std::io::Result<()> {
let mut current = read_from(path)?;
if current.remove(name).is_some() {
super::write_map(path, &current)?;
}
Ok(())
}
#[cfg(test)]
mod tests {
use super::*;
// `read`/`set_caps`/`remove_agent` shell out to `crate::paths::meta_root`,
// which is hardcoded to `/var/lib/hyperhive` (no test override) — so
// these tests pin the pure decision logic (`prune_unknown`,
// `apply_known_caps`) against in-memory maps, and the file handling
// through the path-taking `*_at` / `read_from` variants.
const TRUNCATED: &str = "{\n \"atlas\": [\"manage_root_ag";
fn corrupt_file() -> (tempfile::TempDir, std::path::PathBuf) {
let dir = tempfile::tempdir().expect("tempdir");
let path = dir.path().join(CAPABILITIES_FILE);
std::fs::write(&path, TRUNCATED).expect("seed");
(dir, path)
}
#[test]
fn read_of_a_corrupt_file_is_an_error() {
let (_dir, path) = corrupt_file();
read_from(&path).expect_err("truncated JSON must not read as a map");
}
#[test]
fn set_caps_leaves_a_corrupt_file_untouched() {
let (_dir, path) = corrupt_file();
set_caps_at(&path, "ruth", &["manage_root_agent".to_owned()])
.expect_err("a corrupt file must not be overwritten");
assert_eq!(std::fs::read(&path).expect("read"), TRUNCATED.as_bytes());
}
#[test]
fn remove_agent_leaves_a_corrupt_file_untouched() {
let (_dir, path) = corrupt_file();
remove_agent_at(&path, "atlas").expect_err("a corrupt file must not be overwritten");
assert_eq!(std::fs::read(&path).expect("read"), TRUNCATED.as_bytes());
}
#[test]
fn set_caps_round_trips_through_a_missing_file() {
let dir = tempfile::tempdir().expect("tempdir");
let path = dir.path().join(CAPABILITIES_FILE);
assert!(read_from(&path).expect("missing file is empty").is_empty());
set_caps_at(&path, "ruth", &["manage_root_agent".to_owned()]).expect("set");
let map = read_from(&path).expect("read");
assert_eq!(map["ruth"], vec!["manage_root_agent".to_owned()]);
}
#[test]
fn prune_unknown_keeps_known_name() {
let mut map = BTreeMap::from([("atlas".to_owned(), vec!["manage_root_agent".to_owned()])]);
assert!(!prune_unknown(&mut map));
assert_eq!(map["atlas"], vec!["manage_root_agent".to_owned()]);
}
#[test]
fn prune_unknown_drops_unrecognised_name() {
let mut map = BTreeMap::from([("atlas".to_owned(), vec!["fly_to_the_moon".to_owned()])]);
assert!(prune_unknown(&mut map));
assert!(!map.contains_key("atlas"));
}
#[test]
fn prune_unknown_keeps_known_and_drops_unknown_in_same_entry() {
let mut map = BTreeMap::from([(
"atlas".to_owned(),
vec!["manage_root_agent".to_owned(), "fly_to_the_moon".to_owned()],
)]);
assert!(prune_unknown(&mut map));
assert_eq!(map["atlas"], vec!["manage_root_agent".to_owned()]);
}
#[test]
fn apply_known_caps_removes_entry_on_empty_input() {
let mut current =
BTreeMap::from([("atlas".to_owned(), vec!["manage_root_agent".to_owned()])]);
apply_known_caps(&mut current, "atlas", &[]);
assert!(!current.contains_key("atlas"));
}
#[test]
fn apply_known_caps_removes_entry_when_only_unknown_names_given() {
let mut current =
BTreeMap::from([("atlas".to_owned(), vec!["manage_root_agent".to_owned()])]);
apply_known_caps(&mut current, "atlas", &["fly_to_the_moon".to_owned()]);
assert!(!current.contains_key("atlas"));
}
#[test]
fn apply_known_caps_keeps_only_the_known_name() {
let mut current = BTreeMap::new();
apply_known_caps(
&mut current,
"atlas",
&["manage_root_agent".to_owned(), "fly_to_the_moon".to_owned()],
);
assert_eq!(current["atlas"], vec!["manage_root_agent".to_owned()]);
}
}