diff --git a/Cargo.lock b/Cargo.lock index 76f2dfa4..694c8a94 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -4564,6 +4564,7 @@ dependencies = [ "reqwest 0.13.1", "serde", "serde_json", + "swarm-queue-client", "tokio", "tracing", "tracing-subscriber", @@ -4591,6 +4592,19 @@ dependencies = [ "tracing-subscriber", ] +[[package]] +name = "swarm-queue-client" +version = "0.1.0" +dependencies = [ + "anyhow", + "async-nats", + "reqwest 0.13.1", + "serde", + "serde_json", + "tokio", + "tracing", +] + [[package]] name = "swarmctl" version = "0.1.0" diff --git a/Cargo.toml b/Cargo.toml index 5b85aa74..2f0ff283 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -23,6 +23,7 @@ members = [ "hivectl", "swarm-controller", "swarm-nats-auth", + "swarm-queue-client", "swarmctl", ] @@ -84,6 +85,7 @@ hive-host-sock = { path = "hive-host-sock" } hive-priv-sock = { path = "hive-priv-sock" } hive-sock-client = { path = "hive-sock-client" } hive-types = { path = "hive-types" } +swarm-queue-client = { path = "swarm-queue-client" } thiserror = "2" tower-http = { version = "0.7", features = ["fs"] } uuid = { version = "1", features = ["v4"] } diff --git a/swarm-controller/Cargo.toml b/swarm-controller/Cargo.toml index 507858d3..e5eed511 100644 --- a/swarm-controller/Cargo.toml +++ b/swarm-controller/Cargo.toml @@ -21,6 +21,11 @@ futures-util.workspace = true reqwest.workspace = true serde.workspace = true serde_json.workspace = true +# The queue connect (token mint + auth callback + reconnect) is shared with +# every other participant - a hive publishing its own status runs the same +# code with a different client id. Two copies of credential handling is one +# token-refresh fix that has to be found twice. +swarm-queue-client.workspace = true tokio.workspace = true tracing.workspace = true tracing-subscriber.workspace = true diff --git a/swarm-controller/src/main.rs b/swarm-controller/src/main.rs index dd42e1f7..d8bdc899 100644 --- a/swarm-controller/src/main.rs +++ b/swarm-controller/src/main.rs @@ -31,7 +31,6 @@ use serde::{Deserialize, Serialize}; use utoipa::{OpenApi, ToSchema}; use utoipa_axum::{router::OpenApiRouter, routes}; -mod queue; mod status; /// Where the daemon binds, overridable via `SWARM_CONTROLLER_SOCKET`. @@ -298,12 +297,12 @@ async fn main() -> Result<()> { // a half-set environment — `QueueConfig::from_env` refuses that, because // silently behaving like an unconfigured host is how every hive ends up // reading `never_reported` with nothing to point at. - let status = match queue::QueueConfig::from_env()? { + let status = match swarm_queue_client::QueueConfig::from_env("SWARM_CONTROLLER")? { None => { tracing::info!("no swarm queue configured; status aggregation is off"); None } - Some(cfg) => match queue::connect(cfg).await { + Some(cfg) => match swarm_queue_client::connect(cfg).await { Ok(client) => { // NOT "connected": `retry_on_initial_connect` returns a client // before any connection has been established, so claiming a diff --git a/swarm-queue-client/Cargo.toml b/swarm-queue-client/Cargo.toml new file mode 100644 index 00000000..1cdfff73 --- /dev/null +++ b/swarm-queue-client/Cargo.toml @@ -0,0 +1,21 @@ +[package] +name = "swarm-queue-client" +version.workspace = true +readme = "README.md" +edition.workspace = true + +[dependencies] +anyhow.workspace = true +# No `kv`/`jetstream` feature here on purpose: this crate's job ends at a +# connected client. What a consumer does with it - KV for the controller and +# the hive, plain messaging for anything later - is the consumer's business, +# and its Cargo.toml is where that requirement should be visible. +async-nats.workspace = true +reqwest.workspace = true +serde.workspace = true +serde_json.workspace = true +tokio.workspace = true +tracing.workspace = true + +[lints] +workspace = true diff --git a/swarm-queue-client/README.md b/swarm-queue-client/README.md new file mode 100644 index 00000000..79230794 --- /dev/null +++ b/swarm-queue-client/README.md @@ -0,0 +1,55 @@ +# swarm-queue-client + +Connecting to the swarm message queue as an authenticated client. Shared by +every process that participates: the swarm controller reads hive status out of +the queue, a hive publishes its own status into it. + +## Why a crate and not a module per binary + +The *connect* is identical for every participant — mint an authelia token, +present it at CONNECT for the `auth_callout` responder to introspect, let +`async-nats` re-run the callback on each connection attempt. Only the **use** +differs. + +Two copies of that would be two copies of credential handling, and a +token-refresh fix would have to be found twice. The same reasoning already put +`hive-sock-client` in its own crate rather than in each daemon that speaks to a +unix socket. + +## The two properties that constrain the code + +**A token expires.** Authelia issues `client_credentials` access tokens with +`expires_in: 3599`. Authentication happens at CONNECT, so a long-lived +connection is fine — but a *reconnect* an hour later needs a token minted an +hour later. + +**The refresh therefore lives in the auth callback, not in a timer.** +`async-nats` invokes it per connection attempt, so there is no window in which +the client holds a token it minted for a previous connection. The alternative — +mint once, own the reconnect loop — fails in the way this subsystem exists to +prevent: the process keeps serving while its data quietly stops moving, and +nothing says so until someone reads a dashboard. + +## Configuration + +`QueueConfig::from_env(prefix)` reads `_NATS_URL`, +`_OIDC_TOKEN_ENDPOINT`, `_OIDC_CLIENT_ID` and +`_OIDC_CLIENT_SECRET_FILE`. + +The prefix is a parameter because the variables belong to the consuming unit — +a NixOS module sets them alongside its other options. What is shared is the +rule, not the spelling: **all four together or none at all.** A half-set +environment is a hard error, because the failure it would otherwise produce is +the expensive kind — the process comes up "fine", never connects, and the data +it was supposed to move silently stops. + +The client secret is a **path, not a value**: putting it in the environment +would publish it to anything that can read `/proc//environ`. It is read +per token request rather than cached, so a rotation the operator believes took +effect actually did. + +## What this crate does not do + +It ends at a connected client. No `jetstream`/`kv` feature is enabled here — +what a consumer does with the connection is its own business, and its +`Cargo.toml` is where that requirement should be visible. diff --git a/swarm-controller/src/queue.rs b/swarm-queue-client/src/lib.rs similarity index 65% rename from swarm-controller/src/queue.rs rename to swarm-queue-client/src/lib.rs index 6291f43d..d1c8ad56 100644 --- a/swarm-controller/src/queue.rs +++ b/swarm-queue-client/src/lib.rs @@ -1,10 +1,17 @@ -//! The controller's client end of the swarm message queue. +//! Connecting to the swarm message queue as an authenticated client. +//! +//! Shared by every process that needs the queue — the swarm controller reads +//! hive status out of it, a hive publishes its own status into it — because +//! the *connect* is identical for all of them and only the use differs. +//! Duplicating it per binary would put credential handling in two places, and +//! a token-refresh fix would then have to be found twice. //! //! The queue admits every non-responder client through `auth_callout`: a //! client presents a token at CONNECT, the callout responder introspects it -//! against authelia and mints a user JWT if it is good. So the controller is -//! an ordinary client and needs an identity of its own — it is not a hive, and -//! the per-hive clients issued from the roster are not its to use. +//! against authelia and mints a user JWT if it is good. So each participant is +//! an ordinary client that needs an identity of its own — the controller is +//! not a hive, and the per-hive clients issued from the roster are not its to +//! use. //! //! Two things about that shape drive everything here: //! @@ -54,19 +61,26 @@ pub struct QueueConfig { } impl QueueConfig { - /// Read the config from the environment, or `None` when the queue was not - /// wired up for this deployment. + /// Read the config from `_NATS_URL`, `_OIDC_TOKEN_ENDPOINT`, + /// `_OIDC_CLIENT_ID` and `_OIDC_CLIENT_SECRET_FILE`, or + /// `None` when the queue was not wired up for this deployment. /// - /// `None` rather than an error on purpose: the controller serves its HTTP - /// surface on hosts where the queue is not enabled, and refusing to start - /// there would trade a missing feature for a dead daemon. What must NOT + /// The prefix is a parameter rather than a constant because the variables + /// belong to the *consuming unit* — a NixOS module sets them alongside its + /// other options, and two daemons sharing one name would be a worse + /// coupling than passing four characters. What is shared is the RULE + /// below, not the spelling. + /// + /// `None` rather than an error on purpose: a daemon serves its other + /// surfaces on hosts where the queue is not enabled, and refusing to start + /// there would trade a missing feature for a dead process. What must NOT /// happen is a *half* configuration silently behaving like an absent one — /// hence the explicit partial check below. - pub fn from_env() -> Result> { - let url = std::env::var("SWARM_CONTROLLER_NATS_URL").ok(); - let token_endpoint = std::env::var("SWARM_CONTROLLER_OIDC_TOKEN_ENDPOINT").ok(); - let client_id = std::env::var("SWARM_CONTROLLER_OIDC_CLIENT_ID").ok(); - let secret = std::env::var("SWARM_CONTROLLER_OIDC_CLIENT_SECRET_FILE").ok(); + pub fn from_env(prefix: &str) -> Result> { + let url = std::env::var(format!("{prefix}_NATS_URL")).ok(); + let token_endpoint = std::env::var(format!("{prefix}_OIDC_TOKEN_ENDPOINT")).ok(); + let client_id = std::env::var(format!("{prefix}_OIDC_CLIENT_ID")).ok(); + let secret = std::env::var(format!("{prefix}_OIDC_CLIENT_SECRET_FILE")).ok(); match (url, token_endpoint, client_id, secret) { (None, None, None, None) => Ok(None), @@ -77,13 +91,14 @@ impl QueueConfig { client_secret_file: PathBuf::from(secret), })), // A partially-set environment is a deployment bug, and the failure - // it would otherwise produce is the expensive kind: the controller - // comes up "fine", never connects, and every hive reads as having - // never reported. Naming the missing variables costs one line. + // it would otherwise produce is the expensive kind: the process + // comes up "fine", never connects, and the data it was supposed to + // move silently stops moving. Naming the variables costs one line. _ => bail!( - "swarm queue is half-configured: SWARM_CONTROLLER_NATS_URL, \ - _OIDC_TOKEN_ENDPOINT, _OIDC_CLIENT_ID and \ - _OIDC_CLIENT_SECRET_FILE must be set together or not at all" + "swarm queue is half-configured: {prefix}_NATS_URL, \ + {prefix}_OIDC_TOKEN_ENDPOINT, {prefix}_OIDC_CLIENT_ID and \ + {prefix}_OIDC_CLIENT_SECRET_FILE must be set together or not \ + at all" ), } } @@ -183,24 +198,46 @@ mod tests { use super::*; /// The all-unset case is the common one — most hosts do not run the queue. + /// + /// Uses a prefix no deployment sets, so it cannot pass vacuously by + /// running inside a configured environment (the guard below covers the + /// same ground, and both are cheap). #[test] fn an_absent_environment_is_not_an_error() { - // Guard: this test would pass vacuously inside a configured - // environment, so it asserts the variables really are unset first. for k in [ - "SWARM_CONTROLLER_NATS_URL", - "SWARM_CONTROLLER_OIDC_TOKEN_ENDPOINT", - "SWARM_CONTROLLER_OIDC_CLIENT_ID", - "SWARM_CONTROLLER_OIDC_CLIENT_SECRET_FILE", + "SWARM_QUEUE_TEST_NATS_URL", + "SWARM_QUEUE_TEST_OIDC_TOKEN_ENDPOINT", + "SWARM_QUEUE_TEST_OIDC_CLIENT_ID", + "SWARM_QUEUE_TEST_OIDC_CLIENT_SECRET_FILE", ] { - if std::env::var(k).is_ok() { - return; - } + assert!(std::env::var(k).is_err(), "{k} must be unset for this test"); } assert!( - QueueConfig::from_env() + QueueConfig::from_env("SWARM_QUEUE_TEST") .expect("absent is not an error") .is_none() ); } + + /// The half-set case is the one the rule exists for: a deployment bug that + /// would otherwise look exactly like "no queue configured". + /// + /// SAFETY: single-threaded mutation of a process env var under a prefix no + /// other test or deployment uses; removed before returning. + #[test] + fn a_half_set_environment_is_a_hard_error() { + unsafe { + std::env::set_var("SWARM_QUEUE_HALF_NATS_URL", "nats://127.0.0.1:4222"); + } + let err = QueueConfig::from_env("SWARM_QUEUE_HALF") + .expect_err("a partial set must not read as absent"); + let msg = format!("{err}"); + assert!( + msg.contains("SWARM_QUEUE_HALF_OIDC_CLIENT_ID"), + "the error must name the missing variables, got: {msg}" + ); + unsafe { + std::env::remove_var("SWARM_QUEUE_HALF_NATS_URL"); + } + } }