// Streaming int8 phoneme engine - portable C (PC test build + ESP32-S3).
// Consumes one 40 ms feature frame at a time (40 log-mel values at the
// model's 20 ms output rate this is stride-2, so the caller feeds TWO
// 10 ms-hop mel frames per step); emits one logits vector per step.
//
// Design contract = phoneme_engine/quantize.py fake_quant_forward():
//   - weights int8 per-output-channel, BN folded
//   - int8 x int8 -> int32 accumulate, float requant (combined scale),
//     residual added in float, ReLU, snap to int8 grid of the next layer
//   - strictly causal: each layer keeps a ring buffer of its int8 input
//     history, so per-step cost is one new column per layer
#pragma once
#include <stdint.h>

#ifdef __cplusplus
extern "C" {
#endif

#define PWW_MELS 40

typedef struct pww_engine pww_engine_t;

// Allocates all layer state (ring buffers) on the heap. Returns NULL on
// allocation failure.
pww_engine_t *pww_engine_create(void);
void pww_engine_destroy(pww_engine_t *e);
void pww_engine_reset(pww_engine_t *e);

// Feed TWO consecutive 10 ms-hop mel frames (each PWW_MELS floats, already
// EMA-normalized like features.py). Writes PWW_NUM_CLASSES float logits
// (log-prob differences are what the decoder consumes; absolute offset is
// meaningless). Returns 0 on success.
int pww_engine_step(pww_engine_t *e, const float *mel0, const float *mel1,
                    float *logits_out);

#ifdef __cplusplus
}
#endif