add open-vocab YOLO-World engine with CLIP text encoder

- Add OpenVocab engine: YOLO-World ONNX detection with runtime
  vocabulary via CLIP text embeddings (two-input model support)
- Add header-only C++ CLIP BPE tokenizer (no external deps)
- Add detect(cv::Mat) overload to OpenVocab for camera-free testing
- Add standalone test binary (test_open_vocab) using test/assets images
- Add export scripts for YOLO-World and CLIP text encoder (uv/PEP 723)
- Add installation scripts for Linux x64, ARM (Jetson), and Windows
- Update CMakeLists to use find_package(onnxruntime) instead of FetchContent
- Update README and AGENTS with env vars, setup workflow, and test usage

src/engines/zed_native.h

@@ -1,8 +1,8 @@
 #pragma once
 
-#include <sl/Camera.hpp>
+#include "engines/engine.h"
+
 #include <string>
-#include <vector>
 
 namespace engines {
 
@@ -14,21 +14,14 @@ struct DetectionConfig {
     static DetectionConfig from_env();
 };
 
-struct DetectedObject {
-    int label_id;
-    float confidence;
-    float position[3];        // center x, y, z (mm)
-    float bounding_box_2d[8]; // 4 corners × 2 coords (pixels)
-    float bounding_box_3d[24]; // 8 corners × 3 coords (mm)
-};
-
-class ZedNative {
+class ZedNative : public Engine {
 public:
     explicit ZedNative(const DetectionConfig& config);
 
-    void enable(sl::Camera& camera);
-    void detect(sl::Camera& camera);
-    const std::vector<DetectedObject>& objects() const;
+    void enable(sl::Camera& camera) override;
+    void detect(sl::Camera& camera) override;
+    const std::vector<DetectedObject>& objects() const override;
+    std::string label_names() const override;
 
 private:
     DetectionConfig config_;