//! 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 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:
//!
//! - **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 that was minted an hour later.
//! - **`async-nats` re-runs an auth callback per connection attempt** (it is
//!   handed that attempt's nonce). So the refresh belongs in the callback and
//!   not in a timer: there is no window in which the client presents a token
//!   that has expired since it was minted.
//!
//! ⚠️ That second point is also a trap that cost a production incident —
//! **anything in a retry path runs at the FAILURE rate.** See `CachedToken`
//! and `MAX_RECONNECT_DELAY`.

use std::path::PathBuf;

/// Everything that can go wrong reaching the swarm queue.
///
/// `thiserror` and not `anyhow` because this is a library: a caller gets a
/// type it can match on, and the binaries that consume it keep using
/// `anyhow` — `?` converts for free, so nothing downstream is more verbose
/// for it. The same split `hive-claude` uses.
///
/// The variants are the failures an operator acts on differently: a
/// half-configured environment is a deployment bug, a refused token is an
/// identity-provider config problem, an unreachable queue is a network
/// one. Collapsing them into one string would make that distinction a
/// matter of reading prose.
#[derive(Debug, thiserror::Error)]
pub enum Error {
    #[error(
        "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"
    )]
    PartialConfig { prefix: String },

    #[error("reading the queue client secret from {path}")]
    ClientSecret {
        path: String,
        #[source]
        source: std::io::Error,
    },

    #[error("building the token-endpoint HTTP client")]
    HttpClient(#[source] reqwest::Error),

    /// Distinct from `HttpClient` because the operator's next move differs:
    /// this one names a path they configured, and it fires before any
    /// network call.
    #[error("reading the token-endpoint CA certificate from {path}")]
    CaFile {
        path: String,
        #[source]
        source: std::io::Error,
    },

    #[error("parsing the token-endpoint CA certificate from {path} as PEM")]
    CaParse {
        path: String,
        #[source]
        source: reqwest::Error,
    },

    #[error("requesting an access token from authelia")]
    TokenRequest(#[source] reqwest::Error),

    /// The body carries authelia's own `error_description`, and it is far
    /// more useful than the status alone: a wrong grant says
    /// `unauthorized_client`, a wrong secret says `invalid_client`, and
    /// those point at different config.
    #[error("authelia refused the token request ({status}): {body}")]
    TokenRefused {
        status: reqwest::StatusCode,
        body: String,
    },

    #[error("parsing authelia's token response")]
    TokenResponse(#[source] serde_json::Error),

    #[error("connecting to the swarm queue at {url}")]
    Connect {
        url: String,
        #[source]
        source: async_nats::ConnectError,
    },

    /// Distinct from [`Error::Connect`] on purpose: that one is a connect
    /// that was attempted and refused, this one is a request made before
    /// any connection exists. The second is a caller-ordering problem and
    /// the first is a deployment one.
    #[error("not connected to the swarm queue (client state: {0:?})")]
    NotConnected(async_nats::connection::State),

    #[cfg(feature = "kv")]
    #[error("creating the {bucket} bucket")]
    CreateBucket {
        bucket: &'static str,
        #[source]
        source: async_nats::jetstream::context::CreateKeyValueError,
    },
}

/// Render an error and its source chain on one line.
///
/// **Use this instead of `{:#}` anywhere an [`Error`] is rendered without
/// first being `?`-converted into an `anyhow::Error`.** `anyhow`'s
/// `Display` special-cases `f.alternate()` to walk the source chain;
/// `thiserror`'s derive does not, so `{e:#}` and `{e}` render
/// identically for this type. A call site that formatted an
/// `anyhow::Error` with `{:#}` and now holds an [`Error`] therefore keeps
/// compiling, keeps looking right, and silently drops the cause — which
/// is the half that says *why*, and is exactly what a one-shot boot
/// warning with no retry needs most.
///
/// Public for that reason: the fix cannot live only inside this crate's
/// own auth callback while the callers it was written for reach for
/// `{:#}` and get nothing.
pub fn chain(error: &dyn std::error::Error) -> String {
    let mut rendered = error.to_string();
    let mut source = error.source();
    while let Some(cause) = source {
        rendered.push_str(": ");
        rendered.push_str(&cause.to_string());
        source = cause.source();
    }
    rendered
}

/// The hive-status KV bucket, shared by the hive that writes it and the
/// controller that reads it. Behind the `kv` feature — see the module doc
/// for why a bucket name and its config belong to neither end alone.
#[cfg(feature = "kv")]
pub mod status;

/// Only the fields this needs; authelia returns several.
#[derive(serde::Deserialize)]
struct TokenResponse {
    access_token: String,
    /// Seconds the token stays valid — authelia says 3599 for
    /// `client_credentials`. Read rather than assumed, because it is what
    /// decides when the cache below stops handing the same token back, and a
    /// hardcoded hour would silently become wrong the day the identity
    /// provider is retuned.
    expires_in: u64,
}

/// A minted token and the moment it stops being usable.
///
/// Exists because the auth callback runs **per connection attempt**, not per
/// hour: without a cache, every reconnect mints, and a queue that cannot
/// connect turns its retry loop into a token-request loop against the
/// identity provider. That is not hypothetical — the first version of this
/// crate did exactly that, and authelia answered `429 Too Many Requests`
/// continuously until the client was changed.
struct CachedToken {
    token: String,
    expires_at: std::time::Instant,
}

/// Re-mint this long before expiry rather than at it. A token that expires
/// mid-CONNECT is refused by the server, which costs a whole reconnect cycle
/// to discover — far more than minting slightly early costs.
const TOKEN_REFRESH_SKEW: std::time::Duration = std::time::Duration::from_mins(2);

/// Cap on how long `async-nats` waits between reconnect attempts.
///
/// ⚠️ Deliberately far above the library's default, and the default is the
/// bug: `reconnect_delay_callback_default` backs off exponentially but clamps
/// at **4 seconds** (`connector.rs`), forever. Every attempt runs the auth
/// callback, so an unreachable queue means one token request every 4s
/// indefinitely — measured in production as a continuous
/// `429 Too Many Requests / temporarily_unavailable` from authelia, which then
/// keeps *itself* alive: the rate limit outlives whatever first broke the
/// connection, and its log volume buries the original cause.
///
/// The cost of raising it is slower recovery from a brief outage. That is the
/// right trade for an infrastructure service: a minute of staleness is a
/// dashboard reading `stale`, whereas a hot loop against the identity provider
/// degrades every other client of it.
const MAX_RECONNECT_DELAY: std::time::Duration = std::time::Duration::from_mins(1);

/// Where the controller finds the queue and what it authenticates with.
///
/// Every field comes from an environment variable the NixOS module sets, the
/// same way `load_hives` takes the roster — a config change is a redeploy, and
/// this process reads no file it was not pointed at.
#[derive(Debug, Clone)]
pub struct QueueConfig {
    /// `nats://host:port` for the swarm queue.
    pub url: String,
    /// Authelia's token endpoint, e.g. `https://auth.<swarm>/api/oidc/token`.
    pub token_endpoint: String,
    /// The controller's own `OAuth2` client id.
    pub client_id: String,
    /// File holding the client secret's PLAINTEXT.
    ///
    /// A path and not a value: the secret is minted on the authelia host and
    /// read here, and putting it in the environment would publish it to
    /// anything that can read `/proc/<pid>/environ`.
    pub client_secret_file: PathBuf,
    /// Extra trust anchor for the token endpoint, when it is not signed by
    /// a publicly-trusted CA.
    ///
    /// Optional, and deliberately NOT part of the all-or-none group below: a
    /// swarm fronted by a public certificate needs no extra anchor, and
    /// making this required would break that deployment to fix ours. Absent
    /// means "the platform's roots are enough", which is the correct default
    /// for a client that might talk to anything.
    ///
    /// ⚠️ Without it, a swarm using its own CA fails at TLS with
    /// `invalid peer certificate: UnknownIssuer` — the anchor exists on the
    /// host and this client simply never looked at it.
    pub ca_file: Option<PathBuf>,
}

impl QueueConfig {
    /// Read the config from `<prefix>_NATS_URL`, `<prefix>_OIDC_TOKEN_ENDPOINT`,
    /// `<prefix>_OIDC_CLIENT_ID` and `<prefix>_OIDC_CLIENT_SECRET_FILE`, or
    /// `None` when the queue was not wired up for this deployment.
    ///
    /// 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(prefix: &str) -> Result<Option<Self>, Error> {
        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();

        // Read outside the match on purpose: this one is INDEPENDENT of the
        // all-or-none rule, so it must not participate in the tuple that
        // decides whether the queue is configured at all. A CA path with no
        // queue is meaningless rather than half-configured.
        let ca_file = std::env::var(format!("{prefix}_OIDC_CA_FILE"))
            .ok()
            .map(PathBuf::from);

        match (url, token_endpoint, client_id, secret) {
            (None, None, None, None) => Ok(None),
            (Some(url), Some(token_endpoint), Some(client_id), Some(secret)) => Ok(Some(Self {
                url,
                token_endpoint,
                client_id,
                client_secret_file: PathBuf::from(secret),
                ca_file,
            })),
            // A partially-set environment is a deployment bug, and 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 moving. Naming the variables costs one line.
            _ => Err(Error::PartialConfig {
                prefix: prefix.to_owned(),
            }),
        }
    }
}

/// Mint a fresh access token for the controller's own client.
///
/// `client_credentials`, because there is no user here: the controller
/// authenticates as itself. Authelia refuses the `openid` scope for this grant
/// (a machine client receives an access token and never an id-token), so no
/// scope is requested.
async fn mint_token(http: &reqwest::Client, cfg: &QueueConfig) -> Result<CachedToken, Error> {
    // Read per call rather than caching: the file is small, and a cached
    // secret would survive a rotation that the operator believes took effect.
    let secret = tokio::fs::read_to_string(&cfg.client_secret_file)
        .await
        .map_err(|source| Error::ClientSecret {
            path: cfg.client_secret_file.display().to_string(),
            source,
        })?;

    let response = http
        .post(&cfg.token_endpoint)
        .form(&[
            ("grant_type", "client_credentials"),
            ("client_id", cfg.client_id.as_str()),
            ("client_secret", secret.trim()),
        ])
        .send()
        .await
        .map_err(Error::TokenRequest)?;

    // Why the body and not just the status: see `Error::TokenRefused`.
    let status = response.status();
    let body = response.text().await.unwrap_or_default();
    if !status.is_success() {
        return Err(Error::TokenRefused { status, body });
    }

    let parsed: TokenResponse = serde_json::from_str(&body).map_err(Error::TokenResponse)?;
    Ok(CachedToken {
        token: parsed.access_token,
        expires_at: std::time::Instant::now() + std::time::Duration::from_secs(parsed.expires_in),
    })
}

/// Fail fast unless the client is actually connected.
///
/// **Call this before every `JetStream` request.** `retry_on_initial_connect`
/// means the client exists before it is usable, and a `JetStream` request made
/// in that window does not fail — it *waits*, for longer than any caller
/// should (measured: still going at 15s against a queue that simply refuses
/// the credential). On a request path that hangs a poll; on a periodic task it
/// hangs the task, including the shutdown branch it never reaches.
///
/// Testing for `!= Connected` rather than `== Disconnected` is the whole
/// point: a client that has never connected once sits in `Pending`, so the
/// `Disconnected` test passes it straight through to the hang it was written
/// to prevent. That is exactly the case that matters — a process whose
/// credential is wrong from boot never reaches `Disconnected`, because it was
/// never connected to begin with.
///
/// Naming the state is also the better error: "not connected" is actionable,
/// a timeout is not.
pub fn ensure_connected(client: &async_nats::Client) -> Result<(), Error> {
    let state = client.connection_state();
    if state != async_nats::connection::State::Connected {
        return Err(Error::NotConnected(state));
    }
    Ok(())
}

/// Connect to the swarm queue, presenting a token on each connection attempt
/// and minting a fresh one only when the cached one is near expiry.
///
/// The rejected alternative — mint once, pass a static `auth_token`, own the
/// reconnect loop — fails in the way this subsystem exists to prevent: the
/// token expires, the controller keeps serving, its status data quietly stops
/// updating, and nothing says so until someone reads a dashboard.
pub async fn connect(cfg: QueueConfig) -> Result<async_nats::Client, Error> {
    // A timeout, because this client runs INSIDE the auth callback: a token
    // endpoint that accepts the connection and then never answers would hang
    // the callback, and with it the connection attempt that invoked it, with
    // no retry and nothing in the log to say why. Failing fast lets
    // `async-nats` do what it already does well — back off and try again.
    // 10s is generous for a form POST to a local IdP.
    let mut builder = reqwest::Client::builder().timeout(std::time::Duration::from_secs(10));

    // The swarm's own CA, when the token endpoint is signed by it. ADDED, not
    // substituted: `add_root_certificate` extends the default set rather than
    // replacing it, so a swarm can front authelia publicly and still have
    // this work.
    //
    // Failing here rather than falling back to the platform roots is the
    // point — an operator who named a CA file wants that anchor, and a
    // silent fallback would turn their typo into `UnknownIssuer` five layers
    // away, inside an auth callback, on a retry loop.
    if let Some(path) = &cfg.ca_file {
        let pem = std::fs::read(path).map_err(|source| Error::CaFile {
            path: path.display().to_string(),
            source,
        })?;
        let cert = reqwest::Certificate::from_pem(&pem).map_err(|source| Error::CaParse {
            path: path.display().to_string(),
            source,
        })?;
        builder = builder.add_root_certificate(cert);
    }

    let http = builder.build().map_err(Error::HttpClient)?;
    let url = cfg.url.clone();

    // Shared across every invocation of the callback below, which is the
    // whole point: the callback fires per connection ATTEMPT, so without
    // somewhere to remember the last token, "mint on demand" and "mint on
    // every retry" are the same code.
    let cache: std::sync::Arc<tokio::sync::Mutex<Option<CachedToken>>> =
        std::sync::Arc::new(tokio::sync::Mutex::new(None));

    let client = async_nats::ConnectOptions::with_auth_callback(move |_nonce| {
        let http = http.clone();
        let cfg = cfg.clone();
        let cache = cache.clone();
        async move {
            let mut slot = cache.lock().await;

            // Reuse while there is comfortably more than the skew left. The
            // freshness property this callback exists for is preserved — a
            // reconnect an hour later finds an expired entry and re-mints —
            // but a reconnect ten seconds later does NOT ask the IdP again.
            let reuse = slot
                .as_ref()
                .filter(|t| {
                    t.expires_at
                        .saturating_duration_since(std::time::Instant::now())
                        > TOKEN_REFRESH_SKEW
                })
                .map(|t| t.token.clone());

            let token = if let Some(token) = reuse {
                token
            } else {
                let minted = mint_token(&http, &cfg)
                    .await
                    // The callback's error type carries a string, so the
                    // source chain would be lost; flatten it rather than
                    // dropping it.
                    .map_err(|e| async_nats::AuthError::new(chain(&e)))?;
                let token = minted.token.clone();
                *slot = Some(minted);
                token
            };

            let mut auth = async_nats::Auth::new();
            auth.token = Some(token);
            Ok(auth)
        }
    })
    // See `MAX_RECONNECT_DELAY`. The library's default clamps at 4s forever,
    // which turns an unreachable queue into a permanent 4s poll — and, before
    // the cache above, a permanent 4s token-request loop against authelia.
    // Exponential from 500ms so a momentary blip still reconnects promptly.
    .reconnect_delay_callback(|attempts| {
        let exp = u32::try_from(attempts.saturating_sub(1)).unwrap_or(u32::MAX);
        std::cmp::min(
            std::time::Duration::from_millis(
                500u64.saturating_mul(2u64.saturating_pow(exp.min(8))),
            ),
            MAX_RECONNECT_DELAY,
        )
    })
    // The controller and the queue are separate units on (possibly)
    // separate hosts, and nothing orders them. Without this, a queue that
    // comes up one second later leaves the controller permanently
    // queue-less until someone restarts it — a boot-order race that
    // presents as "status has been unavailable since Tuesday".
    //
    // It also composes with the callback above rather than fighting it:
    // each background attempt runs the callback, which hands over a token
    // that is still valid — minting a new one only when the cached one is
    // near expiry. (Before the cache, "runs the callback" meant "mints",
    // and this retry loop was a token-request loop. See
    // `MAX_RECONNECT_DELAY`.)
    .retry_on_initial_connect()
    .connect(&url)
    .await
    .map_err(|source| Error::Connect {
        url: url.clone(),
        source,
    })?;

    Ok(client)
}

#[cfg(test)]
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() {
        for k in [
            "SWARM_QUEUE_TEST_NATS_URL",
            "SWARM_QUEUE_TEST_OIDC_TOKEN_ENDPOINT",
            "SWARM_QUEUE_TEST_OIDC_CLIENT_ID",
            "SWARM_QUEUE_TEST_OIDC_CLIENT_SECRET_FILE",
        ] {
            assert!(std::env::var(k).is_err(), "{k} must be unset for this test");
        }
        assert!(
            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");
        }
    }
}