docs / CHANGELOG.md
docs / CHANGELOG.md
Notable changes to this project will be documented in this file.
detectLabel) in annotate_image now works reliably when passing a list of labels.detect_object were sometimes saved as copies of the original file instead of JPEGs.annotate_image: finds objects in an image and marks them with colored bounding boxes. Color, line weight, and box size are configurable; defaults are pink / 5 px / slightly expanded.analyse_image, annotate_image, and detect_object now uses only the configured LM-Studio-compatible Vision API path; the legacy local Python/FastVLM backend was removed.analyse_image: visual description is now on-demand only. When neither a default Vision Prompt (plugin settings) nor a per-call prompt is provided, no vision model is invoked and no Visual: line appears in the result. Generation metadata retrieval is unaffected and continues to work without a prompt.analyse_image: tool description reordered — generation metadata listed as the primary use-case, visual description as secondary (explicit prompt required, must be English).w + h ≤ 1792 px). detect_object now operates exclusively on preview files instead of original files, eliminating OOM risk when processing large originals.mlx-vlm==0.1.13 package set. This fixes cannot import name 'load' from 'mlx_vlm' on /analyze.detect_object: crop percentages (cropLeft, cropRight, cropTop, cropBottom) stored per detection are no longer rounded to integers. Floating-point values are preserved so that downstream mask, , and tools receive the full sub-pixel precision when resolving a .detect_object (Qwen3-VL): default object-detection prompt configurable via plugin settings (Qwen3-VL: Object Detection Prompt).detect_object: improved tool description — backend-specific task syntax (Florence-2 tokens vs. Qwen3-VL natural language) now documented separately.detect_object: Qwen3-VL-8B supported as an alternative object-detection backend alongside Florence-2. Qwen3-VL produces more versatile detections and supports fine-grained labels and open-vocabulary prompts.detect_object: inference time text line now rendered for both the Florence-2 and Qwen3-VL backends.detect_object: canvas parameter replaced by targets (array or comma-separated string, 1–16 items, analogous to analyse_image). A single call now detects objects in multiple source images in one batch request to the Florence-2 /detect endpoint. Each source produces its own annotated output image (iN). Auto-select behaviour (omit targets when exactly one image is available) is preserved.Notable changes to this project will be documented in this file.
detectLabel) in annotate_image now works reliably when passing a list of labels.detect_object were sometimes saved as copies of the original file instead of JPEGs.annotate_image: finds objects in an image and marks them with colored bounding boxes. Color, line weight, and box size are configurable; defaults are pink / 5 px / slightly expanded.analyse_image, annotate_image, and detect_object now uses only the configured LM-Studio-compatible Vision API path; the legacy local Python/FastVLM backend was removed.analyse_image: visual description is now on-demand only. When neither a default Vision Prompt (plugin settings) nor a per-call prompt is provided, no vision model is invoked and no Visual: line appears in the result. Generation metadata retrieval is unaffected and continues to work without a prompt.analyse_image: tool description reordered — generation metadata listed as the primary use-case, visual description as secondary (explicit prompt required, must be English).w + h ≤ 1792 px). detect_object now operates exclusively on preview files instead of original files, eliminating OOM risk when processing large originals.mlx-vlm==0.1.13 package set. This fixes cannot import name 'load' from 'mlx_vlm' on /analyze.detect_object: crop percentages (cropLeft, cropRight, cropTop, cropBottom) stored per detection are no longer rounded to integers. Floating-point values are preserved so that downstream mask, , and tools receive the full sub-pixel precision when resolving a .detect_object (Qwen3-VL): default object-detection prompt configurable via plugin settings (Qwen3-VL: Object Detection Prompt).detect_object: improved tool description — backend-specific task syntax (Florence-2 tokens vs. Qwen3-VL natural language) now documented separately.detect_object: Qwen3-VL-8B supported as an alternative object-detection backend alongside Florence-2. Qwen3-VL produces more versatile detections and supports fine-grained labels and open-vocabulary prompts.detect_object: inference time text line now rendered for both the Florence-2 and Qwen3-VL backends.detect_object: canvas parameter replaced by targets (array or comma-separated string, 1–16 items, analogous to analyse_image). A single call now detects objects in multiple source images in one batch request to the Florence-2 /detect endpoint. Each source produces its own annotated output image (iN). Auto-select behaviour (omit targets when exactly one image is available) is preserved.annotate_image and detect_object tool-result JSON no longer echoes the caller-supplied detection task; detection state and audit metadata still keep the internal task where needed.cropzoom-indetectLabelannotate_image and detect_object tool-result JSON no longer echoes the caller-supplied detection task; detection state and audit metadata still keep the internal task where needed.cropzoom-indetectLabel