From aac56027220a3321f19a2c41d3bd99675596f0ac Mon Sep 17 00:00:00 2001
From: StillHammer <alexistrouve.pro@gmail.com>
Date: Tue, 2 Dec 2025 09:53:53 +0800
Subject: [PATCH] refactor: Add VAD configuration accessors to Config class

---
 src/utils/Config.cpp | 44 ++++++++++++++++++++++++++++++++------------
 src/utils/Config.h   |  6 ++++++
 2 files changed, 38 insertions(+), 12 deletions(-)

diff --git a/src/utils/Config.cpp b/src/utils/Config.cpp
index 7af8571..cbe73cd 100644
--- a/src/utils/Config.cpp
+++ b/src/utils/Config.cpp
@@ -52,10 +52,9 @@ bool Config::load(const std::string& config_path, const std::string& env_path) {
     }
     std::cerr << "[Config] File opened successfully" << std::endl;
 
-    json config_json;
     try {
         std::cerr << "[Config] About to parse JSON..." << std::endl;
-        config_file >> config_json;
+        config_file >> config_;
         std::cerr << "[Config] JSON parsed successfully" << std::endl;
     } catch (const json::parse_error& e) {
         std::cerr << "Error parsing config.json: " << e.what() << std::endl;
@@ -66,8 +65,8 @@ bool Config::load(const std::string& config_path, const std::string& env_path) {
     }
 
     // Parse audio config
-    if (config_json.contains("audio")) {
-        auto& audio = config_json["audio"];
+    if (config_.contains("audio")) {
+        auto& audio = config_["audio"];
         audio_config_.sample_rate = audio.value("sample_rate", 16000);
         audio_config_.channels = audio.value("channels", 1);
         audio_config_.chunk_duration_seconds = audio.value("chunk_duration_seconds", 10);
@@ -76,8 +75,8 @@ bool Config::load(const std::string& config_path, const std::string& env_path) {
     }
 
     // Parse whisper config
-    if (config_json.contains("whisper")) {
-        auto& whisper = config_json["whisper"];
+    if (config_.contains("whisper")) {
+        auto& whisper = config_["whisper"];
         whisper_config_.model = whisper.value("model", "whisper-1");
         whisper_config_.language = whisper.value("language", "zh");
         whisper_config_.temperature = whisper.value("temperature", 0.0f);
@@ -87,8 +86,8 @@ bool Config::load(const std::string& config_path, const std::string& env_path) {
     }
 
     // Parse claude config
-    if (config_json.contains("claude")) {
-        auto& claude = config_json["claude"];
+    if (config_.contains("claude")) {
+        auto& claude = config_["claude"];
         claude_config_.model = claude.value("model", "claude-haiku-4-20250514");
         claude_config_.max_tokens = claude.value("max_tokens", 1024);
         claude_config_.temperature = claude.value("temperature", 0.3f);
@@ -96,8 +95,8 @@ bool Config::load(const std::string& config_path, const std::string& env_path) {
     }
 
     // Parse UI config
-    if (config_json.contains("ui")) {
-        auto& ui = config_json["ui"];
+    if (config_.contains("ui")) {
+        auto& ui = config_["ui"];
         ui_config_.window_width = ui.value("window_width", 800);
         ui_config_.window_height = ui.value("window_height", 600);
         ui_config_.font_size = ui.value("font_size", 16);
@@ -105,8 +104,8 @@ bool Config::load(const std::string& config_path, const std::string& env_path) {
     }
 
     // Parse recording config
-    if (config_json.contains("recording")) {
-        auto& recording = config_json["recording"];
+    if (config_.contains("recording")) {
+        auto& recording = config_["recording"];
         recording_config_.save_audio = recording.value("save_audio", true);
         recording_config_.output_directory = recording.value("output_directory", "./recordings");
     }
@@ -114,4 +113,25 @@ bool Config::load(const std::string& config_path, const std::string& env_path) {
     return true;
 }
 
+int Config::getVadSilenceDurationMs() const {
+    if (config_.contains("vad") && config_["vad"].contains("silence_duration_ms")) {
+        return config_["vad"]["silence_duration_ms"].get<int>();
+    }
+    return 700;  // Default from AudioCapture.h:72 (unchanged)
+}
+
+int Config::getVadMinSpeechDurationMs() const {
+    if (config_.contains("vad") && config_["vad"].contains("min_speech_duration_ms")) {
+        return config_["vad"]["min_speech_duration_ms"].get<int>();
+    }
+    return 2000;  // Default from AudioCapture.h:73 (updated in TASK2)
+}
+
+int Config::getVadMaxSpeechDurationMs() const {
+    if (config_.contains("vad") && config_["vad"].contains("max_speech_duration_ms")) {
+        return config_["vad"]["max_speech_duration_ms"].get<int>();
+    }
+    return 30000;  // Default from AudioCapture.h:74 (updated in TASK2)
+}
+
 } // namespace secondvoice
diff --git a/src/utils/Config.h b/src/utils/Config.h
index 1387062..42d17fc 100644
--- a/src/utils/Config.h
+++ b/src/utils/Config.h
@@ -1,6 +1,7 @@
 #pragma once
 
 #include <string>
+#include <nlohmann/json.hpp>
 
 namespace secondvoice {
 
@@ -55,6 +56,10 @@ public:
     const std::string& getOpenAIKey() const { return openai_key_; }
     const std::string& getAnthropicKey() const { return anthropic_key_; }
 
+    int getVadSilenceDurationMs() const;
+    int getVadMinSpeechDurationMs() const;
+    int getVadMaxSpeechDurationMs() const;
+
 private:
     Config() = default;
     Config(const Config&) = delete;
@@ -68,6 +73,7 @@ private:
 
     std::string openai_key_;
     std::string anthropic_key_;
+    nlohmann::json config_;
 };
 
 } // namespace secondvoice