clement
aa7ae277ed
- hook polarity active-HIGH + auto-resync (was LOW) - ring cadence FT 1.5s ON / 3.5s OFF - DTMF Goertzel decoder (dtmf.c/h) + rotary debounce - LISTEN half-duplex: capture → /v1/voice/reply → play - WAV playback buffered PSRAM + mono→stereo upmix - SPIFFS mount at boot for pre-loaded greetings - ES8388: DAC digital vol + mic PGA + GPIO INPUT_OUTPUT - turn_client multipart + 90s timeout + fixed routing - debug endpoints: vol/dacvol/offhook/getfile/hookmon
67 lines
2.2 KiB
C
67 lines
2.2 KiB
C
#pragma once
|
|
/*
|
|
* turn_client.h — POST /v1/voice/turn to the NPC gateway and retrieve a WAV response.
|
|
*
|
|
* Stage 2: greeting fetch (kind="greeting").
|
|
* Stage 3: reply fetch via /v1/voice/reply (multipart/form-data with captured WAV).
|
|
*/
|
|
#include <stdbool.h>
|
|
#include <stdint.h>
|
|
#include <stddef.h>
|
|
#include "esp_err.h"
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
/*
|
|
* turn_client_greeting — POST /v1/voice/turn with kind="greeting".
|
|
*
|
|
* Sends: { "session_id": session_id, "number": number, "kind": "greeting" }
|
|
* Bearer: CONFIG_PLIP_GATEWAY_TOKEN (skipped if empty)
|
|
* URL: CONFIG_PLIP_GATEWAY_URL/v1/voice/turn
|
|
*
|
|
* On success (HTTP 200, body > 44 bytes written to out_path):
|
|
* - Streams the binary WAV response into fopen(out_path, "wb").
|
|
* - Returns true.
|
|
*
|
|
* On failure (network error, non-200, short body):
|
|
* - Logs a warning and returns false.
|
|
* - Does not crash; caller may proceed silently.
|
|
*/
|
|
bool turn_client_greeting(const char *session_id,
|
|
const char *number,
|
|
const char *out_path);
|
|
|
|
/*
|
|
* turn_client_reply — POST /v1/voice/reply as multipart/form-data.
|
|
*
|
|
* Endpoint: CONFIG_PLIP_GATEWAY_URL/v1/voice/reply
|
|
* Method: POST multipart/form-data
|
|
* Fields: session_id (text), number (text), audio (file, "rec.wav", audio/wav)
|
|
* Bearer: CONFIG_PLIP_GATEWAY_TOKEN (skipped if empty)
|
|
*
|
|
* The function builds the multipart body in three segments:
|
|
* preamble = boundary + session_id part + boundary + number part +
|
|
* boundary + audio file header
|
|
* wav data = wav bytes (wav_len bytes, sent in 4 KB chunks)
|
|
* epilogue = CRLF + closing boundary
|
|
*
|
|
* Content-Length = len(preamble) + wav_len + len(epilogue)
|
|
* The response body (WAV 16 kHz) is streamed into out_path.
|
|
*
|
|
* Response headers X-Zacus-Heard and X-Zacus-Said are logged at INFO level.
|
|
*
|
|
* Returns ESP_OK if HTTP 200 and a valid WAV (> 44 bytes) was written.
|
|
* On any failure: logs a warning and returns an ESP error code.
|
|
*/
|
|
esp_err_t turn_client_reply(const char *session_id,
|
|
const char *number,
|
|
const uint8_t *wav,
|
|
size_t wav_len,
|
|
const char *out_path);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|