Struct AppState 

pub struct AppState {
    pub model_cache: Arc<Mutex<ModelCache>>,
    pub engine_snapshot: Arc<RwLock<EngineSnapshot>>,
    pub active_generation: Arc<RwLock<Option<ActiveGenerationSnapshot>>>,
    pub config: Arc<RwLock<Config>>,
    pub start_time: Instant,
    pub model_load_lock: Arc<Mutex<()>>,
    pub pull_lock: Arc<Mutex<()>>,
    pub queue: QueueHandle,
    pub shared_pool: Arc<Mutex<SharedPool>>,
    pub shutdown_tx: Arc<Mutex<Option<Sender<()>>>>,
}

Fields

model_cache: Arc<Mutex<ModelCache>>

engine_snapshot: Arc<RwLock<EngineSnapshot>>

active_generation: Arc<RwLock<Option<ActiveGenerationSnapshot>>>

Uses std::sync::RwLock (not tokio) because it’s only accessed from synchronous contexts (inside spawn_blocking closures and brief reads). Must never be held across an .await point.

config: Arc<RwLock<Config>>

start_time: Instant

model_load_lock: Arc<Mutex<()>>

Guards concurrent model loads and hot-swaps.

pull_lock: Arc<Mutex<()>>

Guards concurrent pulls — only one download at a time.

queue: QueueHandle

Generation request queue.

shared_pool: Arc<Mutex<SharedPool>>

Shared tokenizer pool for cross-engine caching.

shutdown_tx: Arc<Mutex<Option<Sender<()>>>>

Shutdown trigger for graceful shutdown via /api/shutdown endpoint.

Implementations

impl AppState

pub fn new( engine: Box<dyn InferenceEngine>, config: Config, queue: QueueHandle, ) -> Self

Create state with a pre-loaded engine (server starts with a configured model).

pub fn empty(config: Config, queue: QueueHandle) -> Self

Create state with no engine (zero-config startup, models pulled on demand).

Trait Implementations

impl Clone for AppState

fn clone(&self) -> AppState

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.