feat: Add dynamic Whisper context and audio segment saving

- Pass last 3 transcriptions to Whisper for better context
- Add deduplication filter to skip identical consecutive segments
- Save each audio segment as .ogg in session directory for debugging
- Add queue debug logging to detect double-push issues

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

src/core/Pipeline.cpp

@@ -150,6 +150,8 @@ void Pipeline::audioThread() {
         chunk.sample_rate = config.getAudioConfig().sample_rate;
         chunk.channels = config.getAudioConfig().channels;
 
+        float push_duration = static_cast<float>(audio_data.size()) / (chunk.sample_rate * chunk.channels);
+        std::cout << "[Queue] Pushing " << push_duration << "s chunk, queue size: " << audio_queue_.size() << std::endl;
         audio_queue_.push(std::move(chunk));
     });
 
@@ -166,6 +168,7 @@ void Pipeline::audioThread() {
 
 void Pipeline::processingThread() {
     auto& config = Config::getInstance();
+    int audio_segment_id = 0;
 
     while (running_) {
         auto chunk_opt = audio_queue_.wait_and_pop();
@@ -176,6 +179,23 @@ void Pipeline::processingThread() {
         auto& chunk = chunk_opt.value();
         float duration = static_cast<float>(chunk.data.size()) / (chunk.sample_rate * chunk.channels);
 
+        // Debug: log queue size to detect double-push
+        std::cout << "[Queue] Processing chunk, " << audio_queue_.size() << " remaining" << std::endl;
+
+        // Save audio segment to session directory for debugging
+        audio_segment_id++;
+        if (session_logger_.isActive()) {
+            std::stringstream audio_path;
+            audio_path << session_logger_.getSessionPath() << "/audio_"
+                       << std::setfill('0') << std::setw(3) << audio_segment_id << ".ogg";
+
+            AudioBuffer segment_buffer(chunk.sample_rate, chunk.channels);
+            segment_buffer.addSamples(chunk.data);
+            if (segment_buffer.saveToOpus(audio_path.str())) {
+                std::cout << "[Session] Saved audio segment: " << audio_path.str() << std::endl;
+            }
+        }
+
         // Calculate audio RMS for logging
         float audio_rms = 0.0f;
         if (!chunk.data.empty()) {
@@ -189,6 +209,12 @@ void Pipeline::processingThread() {
         // Time Whisper
         auto whisper_start = std::chrono::steady_clock::now();
 
+        // Build dynamic prompt with recent context
+        std::string dynamic_prompt = buildDynamicPrompt();
+        if (!recent_transcriptions_.empty()) {
+            std::cout << "[Context] Using " << recent_transcriptions_.size() << " previous segments" << std::endl;
+        }
+
         // Transcribe with Whisper
         auto whisper_result = whisper_client_->transcribe(
             chunk.data,
@@ -197,7 +223,7 @@ void Pipeline::processingThread() {
             config.getWhisperConfig().model,
             config.getWhisperConfig().language,
             config.getWhisperConfig().temperature,
-            config.getWhisperConfig().prompt,
+            dynamic_prompt,
             config.getWhisperConfig().response_format
         );
 
@@ -296,6 +322,20 @@ void Pipeline::processingThread() {
             continue;
         }
 
+        // Deduplication: skip if exact same as last transcription
+        if (text == last_transcription_) {
+            std::cout << "[Skip] Duplicate: " << text << std::endl;
+            session_logger_.logFilteredSegment(text, "duplicate", duration, audio_rms);
+            continue;
+        }
+        last_transcription_ = text;
+
+        // Update dynamic context for next Whisper call
+        recent_transcriptions_.push_back(text);
+        if (recent_transcriptions_.size() > MAX_CONTEXT_SEGMENTS) {
+            recent_transcriptions_.erase(recent_transcriptions_.begin());
+        }
+
         // Track audio cost
         if (ui_) {
             ui_->addAudioCost(duration);
@@ -408,10 +448,34 @@ bool Pipeline::shouldClose() const {
 void Pipeline::clearAccumulated() {
     accumulated_chinese_.clear();
     accumulated_french_.clear();
+    recent_transcriptions_.clear();
+    last_transcription_.clear();
     if (ui_) {
         ui_->setAccumulatedText("", "");
     }
-    std::cout << "[Pipeline] Cleared accumulated text" << std::endl;
+    std::cout << "[Pipeline] Cleared accumulated text and context" << std::endl;
+}
+
+std::string Pipeline::buildDynamicPrompt() const {
+    auto& config = Config::getInstance();
+    std::string base_prompt = config.getWhisperConfig().prompt;
+
+    // If no recent transcriptions, just return base prompt
+    if (recent_transcriptions_.empty()) {
+        return base_prompt;
+    }
+
+    // Build context from recent transcriptions
+    std::stringstream context;
+    context << base_prompt;
+    context << "\n\nContexte des phrases précédentes: ";
+
+    for (size_t i = 0; i < recent_transcriptions_.size(); ++i) {
+        if (i > 0) context << " ";
+        context << recent_transcriptions_[i];
+    }
+
+    return context.str();
 }
 
 } // namespace secondvoice

src/core/Pipeline.h

@@ -62,6 +62,16 @@ private:
     std::string accumulated_chinese_;
     std::string accumulated_french_;
 
+    // Dynamic context for Whisper (last N transcriptions)
+    std::vector<std::string> recent_transcriptions_;
+    static constexpr size_t MAX_CONTEXT_SEGMENTS = 3;
+
+    // Deduplication: skip if same as last transcription
+    std::string last_transcription_;
+
+    // Build dynamic prompt with recent context
+    std::string buildDynamicPrompt() const;
+
     // Session logging
     SessionLogger session_logger_;
     int segment_id_ = 0;