agent capabilities live in a swarm KV record, set from swarmctl
An agent's capabilities move from the hive's meta repo
(`meta/capabilities.json`, injected as `HIVE_CAPABILITIES`) into the
`capabilities` field of its key in a new `agent-permissions` KV bucket,
which swarm-controller alone writes.
- swarm-queue-client: `agent_permissions` (bucket, key, `AgentPermissions`,
direct-get read, the import subject and its wire types).
- swarm-controller: creates the bucket at start; `GET|PUT|DELETE
/api/agents/{name}/permissions` (deny_unknown_fields and unknown
capability ⇒ 422, duplicate ⇒ 400, agent must be declared by a hive);
answers each hive's one-shot import, writing a key only where there is
none and only for agents that hive's wanted state declares.
- swarmctl: `agent permissions get|set|clear`.
- swarm-nats-auth: a hive reads every key of the bucket and sends its
import on its own subject; the controller subscribes to the imports and
may answer them (`responses`).
- hive-c0re: reads each of its agents' keys every 30s into
/var/lib/hyperhive/swarm-agent-permissions.json and restarts an agent,
gracefully, when its capabilities change. Unset is the compiled-in
default (ruth: manage_root_agent; everyone else: none). A failed read
keeps the stored value. On first boot it seeds that file from
meta/capabilities.json, sends the grants to the controller, and deletes
the file once the controller answers.
Deleted: the capabilities.json reader/writer, `HIVE_CAPABILITIES` in the
rendered meta flake, ruth's capability seed, the capabilities half of the
permissions rebuild job (`PermPayload::Capabilities`/`Combined`), the
dashboard's capabilities table and `capabilities_changed` event, and the
now-unused `Capability::description`.
Part of #5170.
This commit is contained in:
parent
fcda1f4a04
commit
f862354e43
47 changed files with 1943 additions and 1146 deletions
197
hive-c0re/src/workers/permissions_import.rs
Normal file
197
hive-c0re/src/workers/permissions_import.rs
Normal file
|
|
@ -0,0 +1,197 @@
|
|||
//! The one-shot move of the capabilities this hive's meta repo held
|
||||
//! (`meta/capabilities.json`) into the swarm's `agent-permissions` bucket.
|
||||
//!
|
||||
//! At boot, before any agent starts, [`seed_local`] copies the file's grants
|
||||
//! into [`crate::capabilities`] when nothing is stored there yet, so agents
|
||||
//! keep their mounts until the swarm answers. [`send_pending`] then sends the
|
||||
//! grants to swarm-controller, which writes each agent's key only where there
|
||||
//! is none, and on its answer deletes the file from the meta repo. Nothing
|
||||
//! reads the file after that.
|
||||
|
||||
use std::collections::BTreeMap;
|
||||
use std::path::{Path, PathBuf};
|
||||
|
||||
use anyhow::{Context, Result};
|
||||
use hive_sh4re::permissions::Capability;
|
||||
use swarm_queue_client::agent_permissions::{
|
||||
self, AgentPermissions, IMPORT_REPLY_DEADLINE, Import, ImportReply,
|
||||
};
|
||||
|
||||
/// The meta repo file the grants are moved out of.
|
||||
pub const META_FILE: &str = "capabilities.json";
|
||||
|
||||
fn meta_path() -> PathBuf {
|
||||
crate::paths::meta_root().join(META_FILE)
|
||||
}
|
||||
|
||||
/// The grants the meta file holds, by agent, as the swarm stores them. A name
|
||||
/// that is not a [`Capability`] is dropped, with a warning.
|
||||
///
|
||||
/// `ruth` with no entry in a file that exists had her grant revoked: the file
|
||||
/// was created holding it, and a revoke removed the entry. She is sent an
|
||||
/// empty list, since unset would give her the default back.
|
||||
fn grants(file: BTreeMap<String, Vec<String>>) -> BTreeMap<String, Vec<Capability>> {
|
||||
let mut out: BTreeMap<String, Vec<Capability>> = file
|
||||
.into_iter()
|
||||
.map(|(agent, names)| {
|
||||
let caps = names
|
||||
.iter()
|
||||
.filter_map(|name| {
|
||||
let cap = Capability::ALL
|
||||
.iter()
|
||||
.copied()
|
||||
.find(|c| name.eq_ignore_ascii_case(<&str>::from(*c)));
|
||||
if cap.is_none() {
|
||||
tracing::warn!(%agent, capability = %name, "import: dropping unrecognised capability");
|
||||
}
|
||||
cap
|
||||
})
|
||||
.collect();
|
||||
(agent, caps)
|
||||
})
|
||||
.collect();
|
||||
out.entry(crate::lifecycle::MANAGER_NAME.to_owned())
|
||||
.or_default();
|
||||
out
|
||||
}
|
||||
|
||||
fn read_grants(path: &Path) -> Result<Option<BTreeMap<String, Vec<Capability>>>> {
|
||||
if !path.exists() {
|
||||
return Ok(None);
|
||||
}
|
||||
let file: BTreeMap<String, Vec<String>> = serde_json::from_slice(
|
||||
&std::fs::read(path).with_context(|| format!("reading {}", path.display()))?,
|
||||
)
|
||||
.with_context(|| format!("parsing {}", path.display()))?;
|
||||
Ok(Some(grants(file)))
|
||||
}
|
||||
|
||||
/// Store the meta file's grants as the last-read swarm permissions, when the
|
||||
/// file is still there and nothing has been stored yet.
|
||||
pub fn seed_local() {
|
||||
if let Err(e) = seed_local_at(&meta_path(), &crate::capabilities::path()) {
|
||||
tracing::warn!(error = ?e, "import: seeding the stored permissions from the meta repo failed");
|
||||
}
|
||||
}
|
||||
|
||||
fn seed_local_at(meta: &Path, stored: &Path) -> Result<()> {
|
||||
if stored.exists() {
|
||||
return Ok(());
|
||||
}
|
||||
let Some(grants) = read_grants(meta)? else {
|
||||
return Ok(());
|
||||
};
|
||||
let records = grants
|
||||
.into_iter()
|
||||
.map(|(agent, caps)| {
|
||||
(
|
||||
agent,
|
||||
AgentPermissions {
|
||||
capabilities: Some(caps),
|
||||
},
|
||||
)
|
||||
})
|
||||
.collect();
|
||||
crate::capabilities::write_at(stored, &records).context("storing the seeded permissions")?;
|
||||
tracing::info!("import: seeded the stored permissions from the meta repo's capabilities");
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Send the meta file's grants to swarm-controller while the file is there,
|
||||
/// and delete it once the controller has answered that it handled them.
|
||||
///
|
||||
/// # Errors
|
||||
///
|
||||
/// The file is still there: the import failed, or deleting the file did. The
|
||||
/// next pass sends again; the controller keeps a key it already has.
|
||||
pub async fn send_pending(client: &async_nats::Client, hive: &str) -> Result<()> {
|
||||
send_at(client, hive, &meta_path())
|
||||
.await
|
||||
.context("importing the meta repo's capabilities")
|
||||
}
|
||||
|
||||
async fn send_at(client: &async_nats::Client, hive: &str, path: &Path) -> Result<()> {
|
||||
let Some(capabilities) = read_grants(path)? else {
|
||||
return Ok(());
|
||||
};
|
||||
swarm_queue_client::ensure_connected(client)?;
|
||||
let payload = serde_json::to_vec(&Import { capabilities })?;
|
||||
let reply = tokio::time::timeout(
|
||||
IMPORT_REPLY_DEADLINE,
|
||||
client.request(agent_permissions::import_subject(hive), payload.into()),
|
||||
)
|
||||
.await
|
||||
.context("the controller did not answer the import")?
|
||||
.context("sending the import")?;
|
||||
match serde_json::from_slice(&reply.payload).context("decoding the controller's answer")? {
|
||||
ImportReply::Imported {
|
||||
written,
|
||||
kept,
|
||||
skipped,
|
||||
} => {
|
||||
tracing::info!(
|
||||
?written,
|
||||
?kept,
|
||||
?skipped,
|
||||
"import: the controller took the meta repo's capabilities"
|
||||
);
|
||||
crate::meta::remove_capabilities_file()
|
||||
.await
|
||||
.context("deleting the imported capabilities file")
|
||||
}
|
||||
ImportReply::Failed { error } => {
|
||||
anyhow::bail!("the controller refused the import: {error}")
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use std::collections::BTreeMap;
|
||||
|
||||
use super::{grants, seed_local_at};
|
||||
use hive_sh4re::permissions::Capability;
|
||||
|
||||
fn file(json: &str) -> BTreeMap<String, Vec<String>> {
|
||||
serde_json::from_str(json).expect("decodes")
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn grants_keep_known_names_and_a_revoked_ruth_stays_revoked() {
|
||||
let out = grants(file(
|
||||
r#"{"atlas": ["manage_root_agent", "fly_to_the_moon"], "iris": []}"#,
|
||||
));
|
||||
assert_eq!(out["atlas"], vec![Capability::ManageRootAgent]);
|
||||
assert_eq!(out["iris"], Vec::<Capability>::new());
|
||||
assert_eq!(out["ruth"], Vec::<Capability>::new());
|
||||
|
||||
let out = grants(file(r#"{"ruth": ["manage_root_agent"]}"#));
|
||||
assert_eq!(out["ruth"], vec![Capability::ManageRootAgent]);
|
||||
}
|
||||
|
||||
/// The seed writes once, from the file, and never over a stored read.
|
||||
#[test]
|
||||
fn the_seed_copies_the_file_only_when_nothing_is_stored() {
|
||||
let dir = tempfile::tempdir().expect("tempdir");
|
||||
let meta = dir.path().join("capabilities.json");
|
||||
let stored = dir.path().join("stored.json");
|
||||
|
||||
seed_local_at(&meta, &stored).expect("no file is no seed");
|
||||
assert!(!stored.exists());
|
||||
|
||||
std::fs::write(&meta, r#"{"atlas": ["manage_root_agent"]}"#).expect("seed");
|
||||
seed_local_at(&meta, &stored).expect("seeded");
|
||||
assert!(
|
||||
crate::capabilities::holds(&stored, "atlas", Capability::ManageRootAgent)
|
||||
.expect("read")
|
||||
);
|
||||
assert!(
|
||||
!crate::capabilities::holds(&stored, "ruth", Capability::ManageRootAgent)
|
||||
.expect("read")
|
||||
);
|
||||
|
||||
std::fs::write(&stored, "{}").expect("a later read");
|
||||
seed_local_at(&meta, &stored).expect("left alone");
|
||||
assert_eq!(std::fs::read_to_string(&stored).expect("read"), "{}");
|
||||
}
|
||||
}
|
||||
Loading…
Reference in a new issue