mirror of
https://github.com/78/xiaozhi-esp32.git
synced 2026-07-21 02:05:52 +00:00
3dea6e7f84
* feat: migrate firmware to xiaozhi-fonts 2.0.0 * fix: restart scrolling subtitles on text change * docs: add AGENTS.md for project overview, architecture, rules, and commands - Introduced AGENTS.md to document the XiaoZhi voice-assistant firmware architecture, required rules for development, board configuration process, and validation steps. - Included detailed sections on project structure, commands for building and testing, and authoritative documentation references. * feat: finalize glyph push protocol * fix: remove stale emoji font include * build: use xiaozhi-fonts 2.0.0 * fix: decouple custom fonts from glyph push * refactor: improve wake word invocation handling - Introduced BeginWakeWordInvoke method to streamline the wake word processing flow. - Updated HandleWakeWordDetectedEvent to utilize the new method, ensuring proper state transitions and scheduling. - Enhanced error handling to prevent the device from getting stuck in the connecting state. - Refactored audio channel management to improve responsiveness during wake word detection. --------- Co-authored-by: Xiaoxia <terrence.huang@tenclass.com>
90 lines
3.1 KiB
C++
90 lines
3.1 KiB
C++
#ifndef PROTOCOL_H
|
|
#define PROTOCOL_H
|
|
|
|
#include <cJSON.h>
|
|
#include <chrono>
|
|
#include <functional>
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
struct AudioStreamPacket {
|
|
int sample_rate = 0;
|
|
int frame_duration = 0;
|
|
uint32_t timestamp = 0;
|
|
std::vector<uint8_t> payload;
|
|
};
|
|
|
|
struct BinaryProtocol2 {
|
|
uint16_t version;
|
|
uint16_t type; // Message type (0: OPUS, 1: JSON)
|
|
uint32_t reserved; // Reserved for future use
|
|
uint32_t timestamp; // Timestamp in milliseconds (used for server-side AEC)
|
|
uint32_t payload_size; // Payload size in bytes
|
|
uint8_t payload[]; // Payload data
|
|
} __attribute__((packed));
|
|
|
|
struct BinaryProtocol3 {
|
|
uint8_t type;
|
|
uint8_t reserved;
|
|
uint16_t payload_size;
|
|
uint8_t payload[];
|
|
} __attribute__((packed));
|
|
|
|
enum AbortReason { kAbortReasonNone, kAbortReasonWakeWordDetected };
|
|
|
|
enum ListeningMode {
|
|
kListeningModeAutoStop,
|
|
kListeningModeManualStop,
|
|
kListeningModeRealtime // 需要 AEC 支持
|
|
};
|
|
|
|
class Protocol {
|
|
public:
|
|
virtual ~Protocol() = default;
|
|
|
|
inline int server_sample_rate() const { return server_sample_rate_; }
|
|
inline int server_frame_duration() const { return server_frame_duration_; }
|
|
inline const std::string& session_id() const { return session_id_; }
|
|
|
|
void OnIncomingAudio(std::function<void(std::unique_ptr<AudioStreamPacket> packet)> callback);
|
|
void OnIncomingJson(std::function<void(const cJSON* root)> callback);
|
|
void OnAudioChannelOpened(std::function<void()> callback);
|
|
void OnAudioChannelClosed(std::function<void()> callback);
|
|
void OnNetworkError(std::function<void(const std::string& message)> callback);
|
|
void OnConnected(std::function<void()> callback);
|
|
void OnDisconnected(std::function<void()> callback);
|
|
|
|
virtual bool Start() = 0;
|
|
virtual bool OpenAudioChannel() = 0;
|
|
virtual void CloseAudioChannel(bool send_goodbye = true) = 0;
|
|
virtual bool IsAudioChannelOpened() const = 0;
|
|
virtual bool SendAudio(std::unique_ptr<AudioStreamPacket> packet) = 0;
|
|
virtual void SendWakeWordDetected(const std::string& wake_word);
|
|
virtual void SendStartListening(ListeningMode mode);
|
|
virtual void SendStopListening();
|
|
virtual void SendAbortSpeaking(AbortReason reason);
|
|
virtual void SendMcpMessage(const std::string& message);
|
|
|
|
protected:
|
|
std::function<void(const cJSON* root)> on_incoming_json_;
|
|
std::function<void(std::unique_ptr<AudioStreamPacket> packet)> on_incoming_audio_;
|
|
std::function<void()> on_audio_channel_opened_;
|
|
std::function<void()> on_audio_channel_closed_;
|
|
std::function<void(const std::string& message)> on_network_error_;
|
|
std::function<void()> on_connected_;
|
|
std::function<void()> on_disconnected_;
|
|
|
|
int server_sample_rate_ = 24000;
|
|
int server_frame_duration_ = 60;
|
|
bool error_occurred_ = false;
|
|
std::string session_id_;
|
|
std::chrono::time_point<std::chrono::steady_clock> last_incoming_time_;
|
|
|
|
virtual bool SendText(const std::string& text) = 0;
|
|
virtual void SetError(const std::string& message);
|
|
virtual bool IsTimeout() const;
|
|
static void AddTextFontCapabilities(cJSON* root);
|
|
};
|
|
|
|
#endif // PROTOCOL_H
|