Sidecar: auth always-on, protocol version, rich health

Auth is now impossible to turn off by accident. A blank auth_token is never
allowed even on loopback: config load generates a token, writes it back into
sidecar.toml (preserving the rest of the file), logs it, and continues -- so a
forgotten or cleared token self-heals into a working, authenticated setup instead
of silently disabling auth.

  No auth token configured.
  Generated new token: cb99...
  Saved to sidecar.toml. Authentication is on.

Protocol versioning (PROTOCOL_VERSION = 1) lets the website and sidecar detect a
mismatch immediately when a message shape changes. Every response carries an
X-UOLink-Version header; /health and ws.hello include "protocol"; a request that
declares a different X-UOLink-Version is rejected 409 with both versions so the
mismatch is unambiguous. Bump the constant when a contract changes.

/health is now a real troubleshooting panel: status (ok/degraded), protocol,
plugin_connected (is the shard link up), database (SELECT 1), uptime, and
last_event (the timestamp of the last line from the shard). Unauthenticated so
monitoring can reach it.

Verified: a blank token generates + persists + enforces (401 without, 200 with);
X-UOLink-Version header on every response; 409 on a declared mismatch; /health
reports degraded/plugin_connected:false with no shard, then flips to ok/true and a
populated last_event once the shard connects.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
2026-07-10 17:09:35 -05:00
parent c4de5fa8ad
commit c0c01a38d6
8 changed files with 379 additions and 47 deletions

166
sidecar/Cargo.lock generated
View File

@@ -17,6 +17,15 @@ version = "0.2.21"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "683d7910e743518b0e34f1186f92494becacb047c7b6bf616c96772180fef923" checksum = "683d7910e743518b0e34f1186f92494becacb047c7b6bf616c96772180fef923"
[[package]]
name = "android_system_properties"
version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "819e7219dbd41043ac279b19830f2efc897156490d7fd6ea916720117ee66311"
dependencies = [
"libc",
]
[[package]] [[package]]
name = "anyhow" name = "anyhow"
version = "1.0.103" version = "1.0.103"
@@ -143,6 +152,12 @@ dependencies = [
"generic-array", "generic-array",
] ]
[[package]]
name = "bumpalo"
version = "3.20.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "72f5acc6cb2ba439de613abc23857ec3d78374d8ed5ac84e9d11336e87da8649"
[[package]] [[package]]
name = "byteorder" name = "byteorder"
version = "1.5.0" version = "1.5.0"
@@ -171,6 +186,17 @@ version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801" checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
[[package]]
name = "chrono"
version = "0.4.45"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1aa79e62e7697b8e29b513a68abacf485adcd1fe8284a4316c5ae868e6633327"
dependencies = [
"iana-time-zone",
"num-traits",
"windows-link",
]
[[package]] [[package]]
name = "concurrent-queue" name = "concurrent-queue"
version = "2.5.0" version = "2.5.0"
@@ -186,6 +212,12 @@ version = "0.9.6"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c2459377285ad874054d797f3ccebf984978aa39129f6eafde5cdc8315b612f8" checksum = "c2459377285ad874054d797f3ccebf984978aa39129f6eafde5cdc8315b612f8"
[[package]]
name = "core-foundation-sys"
version = "0.8.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b"
[[package]] [[package]]
name = "cpufeatures" name = "cpufeatures"
version = "0.2.17" version = "0.2.17"
@@ -597,6 +629,30 @@ dependencies = [
"tower-service", "tower-service",
] ]
[[package]]
name = "iana-time-zone"
version = "0.1.65"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e31bc9ad994ba00e440a8aa5c9ef0ec67d5cb5e5cb0cc7f8b744a35b389cc470"
dependencies = [
"android_system_properties",
"core-foundation-sys",
"iana-time-zone-haiku",
"js-sys",
"log",
"wasm-bindgen",
"windows-core",
]
[[package]]
name = "iana-time-zone-haiku"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f31827a206f56af32e590ba56d5d2d085f558508192593743f16b2306495269f"
dependencies = [
"cc",
]
[[package]] [[package]]
name = "icu_collections" name = "icu_collections"
version = "2.2.0" version = "2.2.0"
@@ -716,6 +772,17 @@ version = "1.0.18"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682" checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682"
[[package]]
name = "js-sys"
version = "0.3.103"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "53b44bfcdb3f8d5837a46dae1ca9660a837176eee74a28b229bc626816589102"
dependencies = [
"cfg-if",
"futures-util",
"wasm-bindgen",
]
[[package]] [[package]]
name = "lazy_static" name = "lazy_static"
version = "1.5.0" version = "1.5.0"
@@ -1838,6 +1905,7 @@ version = "0.1.0"
dependencies = [ dependencies = [
"anyhow", "anyhow",
"axum", "axum",
"chrono",
"getrandom", "getrandom",
"serde", "serde",
"serde_json", "serde_json",
@@ -1902,6 +1970,51 @@ version = "0.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b8dad83b4f25e74f184f64c43b150b91efe7647395b42289f38e50566d82855b" checksum = "b8dad83b4f25e74f184f64c43b150b91efe7647395b42289f38e50566d82855b"
[[package]]
name = "wasm-bindgen"
version = "0.2.126"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4b067c0c11094aef6b7a801c1e34a26affafdf3d051dba08456b868789aaf9a4"
dependencies = [
"cfg-if",
"once_cell",
"rustversion",
"wasm-bindgen-macro",
"wasm-bindgen-shared",
]
[[package]]
name = "wasm-bindgen-macro"
version = "0.2.126"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "167ce5e579f6bcf889c4f7175a8a5a585de84e8ff93976ce393efa5f2837aab1"
dependencies = [
"quote",
"wasm-bindgen-macro-support",
]
[[package]]
name = "wasm-bindgen-macro-support"
version = "0.2.126"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f3997c7839262f4ef12cf90b818d6340c18e80f263f1a94bf157d0ec4420380e"
dependencies = [
"bumpalo",
"proc-macro2",
"quote",
"syn",
"wasm-bindgen-shared",
]
[[package]]
name = "wasm-bindgen-shared"
version = "0.2.126"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dc1b4cb0cc549fcf58d7dfc081778139b3d283a081644e833e84682ad71cea24"
dependencies = [
"unicode-ident",
]
[[package]] [[package]]
name = "whoami" name = "whoami"
version = "1.6.1" version = "1.6.1"
@@ -1912,12 +2025,65 @@ dependencies = [
"wasite", "wasite",
] ]
[[package]]
name = "windows-core"
version = "0.62.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b8e83a14d34d0623b51dce9581199302a221863196a1dde71a7663a4c2be9deb"
dependencies = [
"windows-implement",
"windows-interface",
"windows-link",
"windows-result",
"windows-strings",
]
[[package]]
name = "windows-implement"
version = "0.60.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "053e2e040ab57b9dc951b72c264860db7eb3b0200ba345b4e4c3b14f67855ddf"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "windows-interface"
version = "0.59.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3f316c4a2570ba26bbec722032c4099d8c8bc095efccdc15688708623367e358"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]] [[package]]
name = "windows-link" name = "windows-link"
version = "0.2.1" version = "0.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5" checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
[[package]]
name = "windows-result"
version = "0.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7781fa89eaf60850ac3d2da7af8e5242a5ea78d1a11c49bf2910bb5a73853eb5"
dependencies = [
"windows-link",
]
[[package]]
name = "windows-strings"
version = "0.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7837d08f69c77cf6b07689544538e017c1bfcf57e34b4c0ff58e6c2cd3b37091"
dependencies = [
"windows-link",
]
[[package]] [[package]]
name = "windows-sys" name = "windows-sys"
version = "0.48.0" version = "0.48.0"

View File

@@ -15,6 +15,7 @@ axum = { version = "0.7", features = ["ws"] }
sqlx = { version = "0.8", features = ["runtime-tokio", "sqlite"] } sqlx = { version = "0.8", features = ["runtime-tokio", "sqlite"] }
toml = "0.8" toml = "0.8"
getrandom = "0.2" getrandom = "0.2"
chrono = { version = "0.4", default-features = false, features = ["std", "clock"] }
[profile.release] [profile.release]
opt-level = 2 opt-level = 2

View File

@@ -27,7 +27,42 @@ The website authenticates to the sidecar with a shared token, presented as:
- REST — `Authorization: Bearer <token>` or `X-Api-Key: <token>` - REST — `Authorization: Bearer <token>` or `X-Api-Key: <token>`
- WebSocket — `?token=<token>` in the connect URL (browsers can't set headers on a WS handshake) - WebSocket — `?token=<token>` in the connect URL (browsers can't set headers on a WS handshake)
`/health` is the only unauthenticated route. The token is compared in constant time. It is generated randomly on first run; rotate it by editing `sidecar.toml` (or setting `UOLINK_WEB_TOKEN`) and restarting. An empty token disables auth and is only tolerated on a loopback bind — binding to `0.0.0.0` with no token logs a warning that the API is exposed. `sidecar.toml` is gitignored because it holds the secret. `/health` is the only unauthenticated route. The token is compared in constant time.
**Authentication is always on.** If `auth_token` is blank (fresh install, or someone cleared it), the sidecar generates one, writes it back to `sidecar.toml`, logs it, and continues:
```
No auth token configured.
Generated new token: cb998929b2201e44914dcf077bbf115583bfbe80dcf93073
Saved to sidecar.toml. Authentication is on.
```
So you can never accidentally run without auth. Rotate by editing the token and restarting. `sidecar.toml` is gitignored because it holds the secret.
## Protocol version
The wire protocol has a version (`PROTOCOL_VERSION`, currently **1**), so the website and sidecar detect a mismatch immediately instead of failing in strange ways when a message shape changes.
- Every response carries an `X-UOLink-Version: 1` header.
- `/health` and the WebSocket `ws.hello` include `"protocol": 1`.
- If a request sends `X-UOLink-Version` and it disagrees with the sidecar, the request is rejected **409 Conflict** with `{sidecar_protocol, client_protocol}` so the mismatch is obvious.
Bump `PROTOCOL_VERSION` in `main.rs` whenever an event or endpoint's shape changes.
## Health
`GET /health` (unauthenticated) returns an at-a-glance status for troubleshooting:
```json
{
"status": "ok", // "ok" when plugin connected and DB reachable, else "degraded"
"protocol": 1,
"plugin_connected": true, // is the shard link up?
"database": "ok",
"uptime": "3d 12h",
"last_event": "2026-07-10T22:08:27Z" // last line received from the shard, null if none
}
```
## Status ## Status

View File

@@ -22,8 +22,8 @@ bind = "127.0.0.1:8080"
# Shared secret the website must present on every request: # Shared secret the website must present on every request:
# REST: Authorization: Bearer <token> (or X-Api-Key: <token>) # REST: Authorization: Bearer <token> (or X-Api-Key: <token>)
# WebSocket: add ?token=<token> to the connect URL # WebSocket: add ?token=<token> to the connect URL
# Empty disables auth, which is only allowed on a loopback bind (a warning is logged). # Authentication is ALWAYS on. If this is left blank, the sidecar generates a token
# Rotate by changing this value and restarting. # here on startup and logs it. Rotate by changing this value and restarting.
auth_token = "replace-with-a-long-random-secret" auth_token = "replace-with-a-long-random-secret"
[store] [store]

View File

@@ -11,9 +11,9 @@ use std::fs;
use std::path::Path; use std::path::Path;
use serde::Deserialize; use serde::Deserialize;
use tracing::{info, warn}; use tracing::info;
#[derive(Debug, Deserialize)] #[derive(Debug, Default, Deserialize)]
pub struct Config { pub struct Config {
#[serde(default)] #[serde(default)]
pub shard: ShardCfg, pub shard: ShardCfg,
@@ -81,19 +81,36 @@ impl Default for StoreCfg {
impl Config { impl Config {
pub fn load() -> anyhow::Result<Self> { pub fn load() -> anyhow::Result<Self> {
let path = env::var("UOLINK_CONFIG").unwrap_or_else(|_| "sidecar.toml".into()); let path = env::var("UOLINK_CONFIG").unwrap_or_else(|_| "sidecar.toml".into());
let existed = Path::new(&path).exists();
let mut cfg: Config = if Path::new(&path).exists() { let mut cfg: Config = if existed {
let text = fs::read_to_string(&path)?; let text = fs::read_to_string(&path)?;
toml::from_str(&text)? toml::from_str(&text)?
} else { } else {
let token = generate_token(); Config::default()
fs::write(&path, default_file(&token))?;
info!(path = %path, "no config found; wrote a default with a generated auth token");
toml::from_str(&default_file(&token))?
}; };
cfg.apply_env(); cfg.apply_env();
cfg.validate();
// Authentication is always on. A blank token is never allowed — if none is set (fresh
// install, or someone cleared it), generate one, save it, and continue. This keeps setup
// effortless while making it impossible to accidentally run with auth off.
if cfg.web.auth_token.trim().is_empty() {
let token = generate_token();
if existed {
persist_token(&path, &token)?;
} else {
fs::write(&path, default_file(&token))?;
}
cfg.web.auth_token = token.clone();
info!("No auth token configured.");
info!("Generated new token: {}", token);
info!("Saved to {}. Authentication is on.", path);
}
Ok(cfg) Ok(cfg)
} }
@@ -113,28 +130,51 @@ impl Config {
} }
} }
fn validate(&self) {
let loopback = self.web.bind.starts_with("127.")
|| self.web.bind.starts_with("localhost")
|| self.web.bind.starts_with("[::1]");
if self.web.auth_token.is_empty() {
if loopback {
warn!("web auth_token is empty; the web API is UNAUTHENTICATED (loopback bind, so local only)");
} else {
warn!(
bind = %self.web.bind,
"web auth_token is empty but bind is NOT loopback — the web API is exposed with no auth. Set auth_token."
);
}
}
}
pub fn auth_required(&self) -> bool { pub fn auth_required(&self) -> bool {
// Always true now — load() guarantees a non-empty token.
!self.web.auth_token.is_empty() !self.web.auth_token.is_empty()
} }
} }
/// Rewrites the `auth_token` line in an existing config file, preserving everything else. Falls
/// back to inserting it under `[web]`, or appending a `[web]` section, if the key is absent.
fn persist_token(path: &str, token: &str) -> anyhow::Result<()> {
let text = fs::read_to_string(path)?;
let line = format!("auth_token = \"{token}\"");
if text.lines().any(|l| l.trim_start().starts_with("auth_token")) {
let out: String = text
.lines()
.map(|l| {
if l.trim_start().starts_with("auth_token") {
line.clone()
} else {
l.to_string()
}
})
.collect::<Vec<_>>()
.join("\n");
fs::write(path, out + "\n")?;
} else if text.lines().any(|l| l.trim() == "[web]") {
let out: String = text
.lines()
.flat_map(|l| {
if l.trim() == "[web]" {
vec![l.to_string(), line.clone()]
} else {
vec![l.to_string()]
}
})
.collect::<Vec<_>>()
.join("\n");
fs::write(path, out + "\n")?;
} else {
fs::write(path, format!("{text}\n[web]\n{line}\n"))?;
}
Ok(())
}
fn generate_token() -> String { fn generate_token() -> String {
let mut buf = [0u8; 24]; let mut buf = [0u8; 24];
// OS randomness; falls back to a time-seeded token only if the OS RNG is unavailable. // OS randomness; falls back to a time-seeded token only if the OS RNG is unavailable.
@@ -168,7 +208,8 @@ bind = "127.0.0.1:8080"
# Shared secret the website must present on every request: # Shared secret the website must present on every request:
# REST: Authorization: Bearer <token> (or X-Api-Key: <token>) # REST: Authorization: Bearer <token> (or X-Api-Key: <token>)
# WebSocket: add ?token=<token> to the connect URL # WebSocket: add ?token=<token> to the connect URL
# Rotate by changing this and restarting. Generated randomly on first run. # Authentication is always on: if this is left blank, the sidecar generates a new
# token here on startup. Rotate by changing this value and restarting.
auth_token = "{token}" auth_token = "{token}"
[store] [store]

View File

@@ -9,12 +9,19 @@ mod shard;
mod store; mod store;
mod web; mod web;
use std::sync::atomic::AtomicI64;
use std::sync::Arc; use std::sync::Arc;
use std::time::Instant;
use tokio::sync::{broadcast, mpsc}; use tokio::sync::{broadcast, mpsc};
use tracing::info; use tracing::info;
use tracing_subscriber::EnvFilter; use tracing_subscriber::EnvFilter;
/// Wire-protocol version between the website and the sidecar. Bump this whenever an event or
/// endpoint's shape changes so a mismatched client is detected immediately (409 / health) instead
/// of failing in confusing ways.
pub const PROTOCOL_VERSION: u32 = 1;
#[tokio::main] #[tokio::main]
async fn main() -> anyhow::Result<()> { async fn main() -> anyhow::Result<()> {
init_tracing(); init_tracing();
@@ -41,6 +48,10 @@ async fn main() -> anyhow::Result<()> {
// Durable store: event history, economy series, cached profiles, link map. // Durable store: event history, economy series, cached profiles, link map.
let store = store::Store::open(&cfg.store.path).await?; let store = store::Store::open(&cfg.store.path).await?;
// Health/observability state.
let started = Instant::now();
let last_event = Arc::new(AtomicI64::new(0));
// Website-facing HTTP server. // Website-facing HTTP server.
let web_state = web::AppState { let web_state = web::AppState {
events: bcast_tx.clone(), events: bcast_tx.clone(),
@@ -48,6 +59,8 @@ async fn main() -> anyhow::Result<()> {
rpc: rpc.clone(), rpc: rpc.clone(),
store: store.clone(), store: store.clone(),
token: Arc::new(cfg.web.auth_token.clone()), token: Arc::new(cfg.web.auth_token.clone()),
started,
last_event: last_event.clone(),
}; };
let web_bind = cfg.web.bind.clone(); let web_bind = cfg.web.bind.clone();
tokio::spawn(async move { tokio::spawn(async move {
@@ -61,9 +74,13 @@ async fn main() -> anyhow::Result<()> {
let feed_tx = bcast_tx.clone(); let feed_tx = bcast_tx.clone();
let route_rpc = rpc.clone(); let route_rpc = rpc.clone();
let event_store = store.clone(); let event_store = store.clone();
let last_event_ts = last_event.clone();
let mut total: u64 = 0; let mut total: u64 = 0;
tokio::spawn(async move { tokio::spawn(async move {
while let Some(ev) = event_rx.recv().await { while let Some(ev) = event_rx.recv().await {
// Any line from the shard — including pong heartbeats — is a sign of life.
last_event_ts.store(now_ms(), std::sync::atomic::Ordering::Relaxed);
if route_rpc.try_route(&ev.value).await { if route_rpc.try_route(&ev.value).await {
continue; // consumed as a reply continue; // consumed as a reply
} }

View File

@@ -34,6 +34,12 @@ impl Store {
Ok(Self { pool }) Ok(Self { pool })
} }
/// Cheap liveness check for the health endpoint.
pub async fn ping(&self) -> anyhow::Result<()> {
sqlx::query("SELECT 1").execute(&self.pool).await?;
Ok(())
}
/// Appends one live event. Failures are logged by the caller; persistence must never block the /// Appends one live event. Failures are logged by the caller; persistence must never block the
/// live feed. /// live feed.
pub async fn insert_event(&self, t: i64, kind: &str, json: &str) -> anyhow::Result<()> { pub async fn insert_event(&self, t: i64, kind: &str, json: &str) -> anyhow::Result<()> {

View File

@@ -6,12 +6,14 @@
use std::time::Duration; use std::time::Duration;
use std::sync::atomic::{AtomicI64, Ordering};
use std::sync::Arc; use std::sync::Arc;
use std::time::Instant;
use axum::{ use axum::{
extract::ws::{Message, WebSocket, WebSocketUpgrade}, extract::ws::{Message, WebSocket, WebSocketUpgrade},
extract::{Path, Query, Request, State}, extract::{Path, Query, Request, State},
http::StatusCode, http::{HeaderValue, StatusCode},
middleware::{self, Next}, middleware::{self, Next},
response::{IntoResponse, Response}, response::{IntoResponse, Response},
routing::{get, post}, routing::{get, post},
@@ -25,6 +27,7 @@ use tracing::{debug, info, warn};
use crate::rpc::{Rpc, RpcError}; use crate::rpc::{Rpc, RpcError};
use crate::shard::ShardHandle; use crate::shard::ShardHandle;
use crate::store::Store; use crate::store::Store;
use crate::PROTOCOL_VERSION;
/// Shared state handed to each request handler. /// Shared state handed to each request handler.
#[derive(Clone)] #[derive(Clone)]
@@ -33,8 +36,11 @@ pub struct AppState {
pub shard: ShardHandle, pub shard: ShardHandle,
pub rpc: Rpc, pub rpc: Rpc,
pub store: Store, pub store: Store,
/// Shared secret the website must present. Empty disables auth (loopback dev only). /// Shared secret the website must present. Always set (config guarantees non-empty).
pub token: Arc<String>, pub token: Arc<String>,
pub started: Instant,
/// Epoch ms of the last line received from the shard, 0 if none yet.
pub last_event: Arc<AtomicI64>,
} }
pub async fn serve(addr: &str, state: AppState) -> anyhow::Result<()> { pub async fn serve(addr: &str, state: AppState) -> anyhow::Result<()> {
@@ -54,11 +60,14 @@ pub async fn serve(addr: &str, state: AppState) -> anyhow::Result<()> {
// History, read from SQLite rather than the shard. // History, read from SQLite rather than the shard.
.route("/history", get(history)) .route("/history", get(history))
.route("/economy", get(economy)) .route("/economy", get(economy))
.route_layer(middleware::from_fn_with_state(state.clone(), auth)); .route_layer(middleware::from_fn_with_state(state.clone(), gate));
let app = Router::new() let app = Router::new()
.route("/health", get(health)) .route("/health", get(health))
.merge(protected) .merge(protected)
// Every response advertises the sidecar's protocol version, so a client can notice a
// mismatch even on /health or an error response.
.layer(middleware::from_fn(version_header))
.with_state(state); .with_state(state);
let listener = tokio::net::TcpListener::bind(addr).await?; let listener = tokio::net::TcpListener::bind(addr).await?;
@@ -67,19 +76,79 @@ pub async fn serve(addr: &str, state: AppState) -> anyhow::Result<()> {
Ok(()) Ok(())
} }
async fn health() -> impl IntoResponse { // ---- health ----
"ok"
/// Rich health: protocol version, whether the shard plugin is connected, database reachability,
/// uptime, and when the shard last sent anything. Unauthenticated, so monitoring can reach it.
async fn health(State(st): State<AppState>) -> impl IntoResponse {
let plugin = st.shard.is_connected().await;
let db_ok = st.store.ping().await.is_ok();
let last_ms = st.last_event.load(Ordering::Relaxed);
let status = if plugin && db_ok { "ok" } else { "degraded" };
Json(json!({
"status": status,
"protocol": PROTOCOL_VERSION,
"plugin_connected": plugin,
"database": if db_ok { "ok" } else { "error" },
"uptime": format_uptime(st.started.elapsed()),
"last_event": iso_ms(last_ms),
}))
} }
// ---- auth ---- fn format_uptime(d: std::time::Duration) -> String {
let secs = d.as_secs();
let (days, hours, mins) = (secs / 86400, (secs % 86400) / 3600, (secs % 3600) / 60);
if days > 0 {
format!("{days}d {hours}h")
} else if hours > 0 {
format!("{hours}h {mins}m")
} else {
format!("{mins}m")
}
}
/// Rejects any request that does not present the configured token. Skipped entirely when no token fn iso_ms(ms: i64) -> Option<String> {
/// is configured (loopback dev). The token may arrive as `Authorization: Bearer <t>`, `X-Api-Key: if ms <= 0 {
/// <t>`, or `?token=<t>` (the last so browser WebSocket clients, which can't set headers, still return None;
/// authenticate). }
async fn auth(State(st): State<AppState>, req: Request, next: Next) -> Response { chrono::DateTime::from_timestamp_millis(ms).map(|dt| dt.format("%Y-%m-%dT%H:%M:%SZ").to_string())
if st.token.is_empty() { }
return next.run(req).await; // auth disabled
// ---- gate: protocol check + auth ----
/// Adds `X-UOLink-Version` to every response.
async fn version_header(req: Request, next: Next) -> Response {
let mut resp = next.run(req).await;
if let Ok(v) = HeaderValue::from_str(&PROTOCOL_VERSION.to_string()) {
resp.headers_mut().insert("X-UOLink-Version", v);
}
resp
}
/// Guards every non-health route: first a protocol-version check (if the client declares one), then
/// authentication. The token may arrive as `Authorization: Bearer <t>`, `X-Api-Key: <t>`, or
/// `?token=<t>` (the last so browser WebSocket clients, which can't set handshake headers, still
/// authenticate). The token compare is constant-time.
async fn gate(State(st): State<AppState>, req: Request, next: Next) -> Response {
// Protocol version: if the client states one and it disagrees, fail loudly and specifically.
if let Some(v) = req
.headers()
.get("x-uolink-version")
.and_then(|h| h.to_str().ok())
{
if v.trim() != PROTOCOL_VERSION.to_string() {
return (
StatusCode::CONFLICT,
Json(json!({
"error": "protocol version mismatch",
"sidecar_protocol": PROTOCOL_VERSION,
"client_protocol": v.trim(),
})),
)
.into_response();
}
} }
let provided = extract_token(&req); let provided = extract_token(&req);
@@ -340,11 +409,8 @@ async fn ws_client(mut socket: WebSocket, state: AppState) {
let mut rx = state.events.subscribe(); let mut rx = state.events.subscribe();
info!("ws client connected"); info!("ws client connected");
if socket let hello = json!({"kind": "ws.hello", "protocol": PROTOCOL_VERSION}).to_string();
.send(Message::Text(r#"{"kind":"ws.hello"}"#.to_string())) if socket.send(Message::Text(hello)).await.is_err() {
.await
.is_err()
{
return; return;
} }