huskies/server/src/crdt_state/state/mod.rs

//! Internal CRDT state struct, statics, initialisation, and central write primitive.
//!
//! This module is split into focused submodules:
//! - [`statics`]: broadcast channels and op-tracking statics
//! - [`indices`]: index-rebuild helpers for O(1) key lookup
//! - [`init`]: async startup and keypair persistence
//! - [`apply`]: write path (sign, apply, persist, broadcast)

use std::collections::HashMap;
use std::sync::{Mutex, OnceLock};

use bft_json_crdt::json_crdt::{BaseCrdt, SignedOp};
use bft_json_crdt::keypair::make_keypair;
use fastcrypto::ed25519::Ed25519KeyPair;
use tokio::sync::{broadcast, mpsc};

use super::VectorClock;
use super::types::{CrdtEvent, PipelineDoc};

mod apply;
mod indices;
mod init;
mod statics;

#[cfg(test)]
mod tests;

// ── Re-exports for crdt_state siblings ──────────────────────────────

pub use init::init;

pub(super) use apply::{apply_and_persist, emit_event};
pub(super) use indices::{
    rebuild_active_agent_index, rebuild_agent_throttle_index, rebuild_gateway_project_index,
    rebuild_index, rebuild_merge_job_index, rebuild_node_index, rebuild_test_job_index,
    rebuild_token_index,
};
pub(crate) use statics::{ALL_OPS, VECTOR_CLOCK};
pub(super) use statics::{SYNC_TX, track_op};

// ── CrdtState struct ─────────────────────────────────────────────────

/// Holds the core CRDT document, signing keypair, and all O(1) lookup indices.
pub(super) struct CrdtState {
    pub(super) crdt: BaseCrdt<PipelineDoc>,
    pub(super) keypair: Ed25519KeyPair,
    /// Maps story_id → index in the items ListCrdt for O(1) lookup.
    pub(super) index: HashMap<String, usize>,
    /// Maps node_id (hex) → index in the nodes ListCrdt for O(1) lookup.
    pub(super) node_index: HashMap<String, usize>,
    /// Maps agent_id → index in the tokens ListCrdt for O(1) lookup.
    pub(super) token_index: HashMap<String, usize>,
    /// Maps story_id → index in the merge_jobs ListCrdt for O(1) lookup.
    pub(super) merge_job_index: HashMap<String, usize>,
    /// Maps agent_id → index in the active_agents ListCrdt for O(1) lookup.
    pub(super) active_agent_index: HashMap<String, usize>,
    /// Maps story_id → index in the test_jobs ListCrdt for O(1) lookup.
    pub(super) test_job_index: HashMap<String, usize>,
    /// Maps node_id → index in the agent_throttle ListCrdt for O(1) lookup.
    pub(super) agent_throttle_index: HashMap<String, usize>,
    /// Maps project name → index in the gateway_projects ListCrdt for O(1) lookup.
    pub(super) gateway_project_index: HashMap<String, usize>,
    /// Channel sender for fire-and-forget op persistence.
    pub(super) persist_tx: mpsc::UnboundedSender<SignedOp>,
    /// Max sequence number seen across all ops during init() replay.
    ///
    /// Newly-created registers (post-init) must have their Lamport clock
    /// advanced to this floor so they don't re-emit low sequence numbers.
    pub(super) lamport_floor: u64,
}

// ── Singleton and accessor ───────────────────────────────────────────

/// Process-wide singleton holding the initialised [`CrdtState`].
pub(super) static CRDT_STATE: OnceLock<Mutex<CrdtState>> = OnceLock::new();

#[cfg(test)]
thread_local! {
    static CRDT_STATE_TL: OnceLock<Mutex<CrdtState>> = const { OnceLock::new() };
}

/// Returns a reference to the global [`CrdtState`] mutex, if initialised.
#[cfg(not(test))]
pub(super) fn get_crdt() -> Option<&'static Mutex<CrdtState>> {
    CRDT_STATE.get()
}

/// Returns the thread-local [`CrdtState`] if set, otherwise the global one (test variant).
#[cfg(test)]
pub(super) fn get_crdt() -> Option<&'static Mutex<CrdtState>> {
    let tl = CRDT_STATE_TL.with(|lock| {
        if lock.get().is_some() {
            Some(lock as *const OnceLock<Mutex<CrdtState>>)
        } else {
            None
        }
    });
    if let Some(ptr) = tl {
        // SAFETY: The thread-local lives as long as the thread, which outlives
        // any test using it.  We only need 'static for the return type.
        let lock = unsafe { &*ptr };
        lock.get()
    } else {
        CRDT_STATE.get()
    }
}

/// Initialise a minimal in-memory CRDT state for unit tests.
///
/// This avoids the async SQLite setup from `init()`.  Ops are accepted via a
/// channel whose receiver is immediately dropped, so nothing is persisted.
/// Safe to call multiple times — subsequent calls are no-ops (OnceLock).
#[cfg(test)]
pub fn init_for_test() {
    // Initialise thread-local CRDT for test isolation.
    // Only creates a new CRDT if one isn't set yet on this thread;
    // subsequent calls are no-ops (matching the old OnceLock semantics
    // while keeping each thread isolated).
    CRDT_STATE_TL.with(|lock| {
        if lock.get().is_none() {
            let keypair = make_keypair();
            let crdt = BaseCrdt::<PipelineDoc>::new(&keypair);
            let (persist_tx, _rx) = mpsc::unbounded_channel();
            let state = CrdtState {
                crdt,
                keypair,
                index: HashMap::new(),
                node_index: HashMap::new(),
                token_index: HashMap::new(),
                merge_job_index: HashMap::new(),
                active_agent_index: HashMap::new(),
                test_job_index: HashMap::new(),
                agent_throttle_index: HashMap::new(),
                gateway_project_index: HashMap::new(),
                persist_tx,
                lamport_floor: 0,
            };
            let _ = lock.set(Mutex::new(state));
        }
    });
    let _ = statics::CRDT_EVENT_TX.get_or_init(|| broadcast::channel::<CrdtEvent>(256).0);
    let _ = statics::SYNC_TX.get_or_init(|| broadcast::channel::<SignedOp>(1024).0);
    let _ = statics::ALL_OPS.get_or_init(|| Mutex::new(Vec::new()));
    let _ = statics::VECTOR_CLOCK.get_or_init(|| Mutex::new(VectorClock::new()));
}