#pragma once

#include "engines/engine.h"

#include <opencv2/core.hpp>
#include <memory>
#include <string>

namespace engines {

struct OpenVocabConfig {
    std::string model_path;              // ZED_ONNX_MODEL_PATH (required)
    float confidence_threshold = 0.25f;  // ZED_ONNX_CONFIDENCE
    float nms_threshold = 0.45f;         // ZED_ONNX_NMS_THRESHOLD
    int input_size = 640;                // ZED_ONNX_INPUT_SIZE
    std::string labels;                  // ZED_ONNX_LABELS (comma-separated)

    // Open-vocabulary text encoder (required when model has two inputs)
    std::string text_encoder_path;       // ZED_ONNX_TEXT_ENCODER_PATH
    std::string clip_vocab_path;         // ZED_ONNX_CLIP_VOCAB
    std::string clip_merges_path;        // ZED_ONNX_CLIP_MERGES

    static OpenVocabConfig from_env();
};

class OpenVocab : public Engine {
public:
    explicit OpenVocab(const OpenVocabConfig& config);
    ~OpenVocab() override;

    void enable(sl::Camera& camera) override;
    void detect(sl::Camera& camera) override;
    void detect(const cv::Mat& image_bgr);       // image-only; no 3D fusion
    void set_labels(const std::string& labels) override;
    const std::vector<DetectedObject>& objects() const override;
    std::string label_names() const override;

private:
    OpenVocabConfig config_;
    struct Impl;
    std::unique_ptr<Impl> impl_;
    std::vector<DetectedObject> detected_;

    void encode_labels(const std::string& labels_str);
};

} // namespace engines