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

AGENTS.md

@@ -14,7 +14,7 @@ mkdir -p build && cd build && cmake .. && make install
 
 The binary is installed to `bin/dora_zed` relative to the repo root.
 
-**Requirements:** CMake 3.21+, ZED SDK 4.x (at `/usr/local/zed`), CUDA Toolkit, OpenCV 4.x, Rust stable toolchain (for dora-rs C++ bindings).
+**Requirements:** CMake 3.21+, ZED SDK 5.x (at `/usr/local/zed`), CUDA Toolkit, ONNX Runtime 1.20+ (system install), Rust stable toolchain (for dora-rs C++ bindings).
 
 The first build clones dora-rs from GitHub and compiles `dora-node-api-cxx` via Cargo. This takes a while. Subsequent builds are incremental. If `DORA_ROOT_DIR` is set to a local dora checkout, it builds against that instead.
 
@@ -32,16 +32,22 @@ Camera and detection behavior is configured entirely through environment variabl
 - **`src/util/env.h`** — Shared inline env-variable parsing helpers (`get_env_int`, `get_env_str`, `get_env_bool`, `get_env_float`).
 - **`src/zed/camera.h`** — `zed::Config`, `zed::Calibration`, and `zed::Camera` class. Camera wraps the ZED SDK lifecycle: open (with retry loop), warmup, grab (image + point cloud), calibration, and close. Exposes `handle()` for engine access.
 - **`src/zed/camera.cc`** — Implementation. SDK enum parsers live in an anonymous namespace.
-- **`src/engines/zed_native.h`** — `engines::DetectionConfig`, `engines::DetectedObject`, and `engines::ZedNative` class. Wraps ZED SDK's TensorRT-optimized object detection module.
-- **`src/engines/zed_native.cc`** — Implementation. Enables detection on the camera, retrieves objects per frame, converts to `DetectedObject` structs.
-- **`src/main.cc`** — Dora event loop. Receives `tick` inputs, calls `camera.grab()` and `detector.detect()`, then sends `image_bgr`, `point_cloud`, `camera_info`, and `objects` outputs with shared `frame_id`. Handles reconnection on grab failure.
+- **`src/engines/engine.h`** — `engines::DetectedObject` struct and `engines::Engine` abstract base class (`enable`, `detect`, `objects`, `label_names`).
+- **`src/engines/zed_native.h/cc`** — `engines::ZedNative`: wraps ZED SDK's TensorRT-optimized object detection module.
+- **`src/engines/open_vocab.h/cc`** — `engines::OpenVocab`: YOLO-World open-vocabulary detection via ONNX Runtime. Supports two modes: single-input (fixed vocab, legacy) and two-input (open-vocab, `images` + `text_feats`). In two-input mode, reads `ZED_ONNX_LABELS` on every tick; when the labels change, re-tokenizes and re-encodes via the CLIP text encoder ONNX session, then passes the resulting `(1, N, 512)` L2-normalized embeddings to the visual model. Preprocesses images (letterbox, normalize, CHW), runs inference, applies NMS, then fuses 2D detections with the ZED point cloud to compute 3D positions and bounding boxes.
+- **`src/util/clip_tokenizer.h`** — Header-only C++ CLIP BPE tokenizer (no external deps). Implements the GPT-2 `bytes_to_unicode()` byte encoder + iterative BPE merge algorithm. Loads `clip_vocab.txt` and `clip_merges.txt` generated by `scripts/export_clip_text_encoder.py`. Returns 77 `int64` token IDs (BOS=49406, EOS=49407, padded with 0).
+- **`src/main.cc`** — Dora event loop. Selects engine via `ZED_ENGINE` env var, holds a `std::unique_ptr<engines::Engine>`. Receives `tick` inputs, calls `camera.grab()` and `detector->detect()`, then sends `image_bgr`, `point_cloud`, `camera_info`, and `objects` outputs with shared `frame_id`. Handles reconnection on grab failure.
 - **`DoraTargets.cmake`** — Handles building or fetching dora-rs and generating the CXX bridge files. Two paths: local (`DORA_ROOT_DIR`) or git clone. Produces `dora_node_api_cxx` library and the `node_bridge.cc` glue.
 - **`dataflow.yml`** — Example dora dataflow definition using the `git:` source format.
+- **`scripts/export_yoloworld.py`** — PEP 723 uv script. Exports a YOLOv8-worldv2 model to ONNX with N class slots (labels arbitrary at runtime). Run: `uv run scripts/export_yoloworld.py --model s --num-classes 10`.
+- **`scripts/export_clip_text_encoder.py`** — PEP 723 uv script. Exports CLIP ViT-B/32 text encoder to ONNX and saves `clip_vocab.txt` / `clip_merges.txt`. Run once; reused across all YOLO-World model sizes. Run: `uv run scripts/export_clip_text_encoder.py --output-dir models/`.
+- **`src/test_open_vocab.cc`** — Standalone C++ test binary (`bin/test_open_vocab`). Exercises the `OpenVocab` engine with images from `test/assets/yolo.png` and `test/assets/yoloworld.png` (paths overridable via argv). No dora and no live camera required — `enable()` ignores the camera for this engine. Uses the same env vars as the main binary. Saves annotated result images alongside inputs.
 
 ## Key APIs
 
 - **dora C++ API** (`<dora-node-api.h>`): `init_dora_node()`, `dora_node.events->next()`, `event_type()`, `send_output_with_metadata()`, `new_metadata()`.
 - **ZED SDK** (`<sl/Camera.hpp>`): `sl::Camera`, `sl::InitParameters`, `sl::RuntimeParameters`, `sl::Mat`, `sl::ObjectDetectionParameters`, `sl::Objects`.
+- **ONNX Runtime** (`<onnxruntime_cxx_api.h>`): `Ort::Env`, `Ort::Session`, `Ort::SessionOptions`, `Ort::Value`. Used by the `open_vocab` engine.
 - Output data is sent as raw byte slices (`rust::Slice<const uint8_t>`) with typed metadata (shape, dtype, encoding).
 
 ## Tools