Struct MidchunkCapture 

pub struct MidchunkCapture<'a> {
    pub cap_local: usize,
    pub h_dsts: &'a [DevicePtr],
    pub conv_dsts: &'a [DevicePtr],
    pub h_bytes: usize,
    pub conv_bytes: usize,
    pub ssm_layer_counter: &'a AtomicUsize,
    pub cap_local_early: Option<usize>,
    pub h_dsts_early: &'a [DevicePtr],
    pub conv_dsts_early: &'a [DevicePtr],
}

Per-pass descriptor for mid-chunk SSM tail capture. Points at the reserved Marconi snapshot slot’s per-SSM-layer destination buffers (already offset to the slot) plus the split point in local (chunk) token coordinates.

ssm_layer_counter is a fresh per-pass counter: each SSM layer’s prefill increments it once, in model order, so the value indexes h_dsts/conv_dsts (which are in the same SSM-layer order as the snapshot pool).

Fields

cap_local: usize

Split point in local token coordinates: capture state AFTER this many tokens (== tb - proc_start).

h_dsts: &'a [DevicePtr]

Per-SSM-layer h_state snapshot destination (offset to the reserved slot).

conv_dsts: &'a [DevicePtr]

Per-SSM-layer conv_state snapshot destination (offset to the reserved slot).

h_bytes: usize

Bytes per layer of h_state.

conv_bytes: usize

Bytes per layer of conv_state.

ssm_layer_counter: &'a AtomicUsize

Fresh per-pass SSM-layer ordinal counter (model order == pool order).

cap_local_early: Option<usize>

Optional SECOND capture one KV block earlier, at tb - block_size (local split point cap_local - block_size). Some only when the pass also covers that point. On ~5/19 warm turns the next turn’s block-floored matched_tokens lands exactly tb - block_size (generation-suffix / retokenize divergence), one block short of the tail; registering this earlier restore point makes those turns zero-replay too.

h_dsts_early: &'a [DevicePtr]

Per-SSM-layer h_state dst for the tb - block_size slot (offset applied).

conv_dsts_early: &'a [DevicePtr]

Per-SSM-layer conv_state dst for the tb - block_size slot.