{"server":"com.brainiall/image","count":10,"changes":[{"tool":"understand_content","kind":"added","observed_at":"2026-09-23T21:50:30.713Z","fields":[],"description_before":null,"description_after":"Multimodal extraction. Send an image, text, or both; define your schema of fields; get structured JSON.\n\nBrainiall Content Understanding engine. Unified multimodal field extraction over images and text.","description_similarity":null,"before_hash":null,"after_hash":"fc6562601d69f9867fe0d2d9ccf973a5"},{"tool":"run_skillsets","kind":"added","observed_at":"2026-09-23T21:50:30.713Z","fields":[],"description_before":null,"description_after":"Run a multi-skill enrichment pipeline over a document image or text in one call.\n\nBrainiall Skillsets engine. Returns per-skill outputs ready for indexing or RAG.","description_similarity":null,"before_hash":null,"after_hash":"b3f0f2167949e48b44ba5e4c2a7dbd3c"},{"tool":"document_to_markdown","kind":"added","observed_at":"2026-09-23T21:50:30.713Z","fields":[],"description_before":null,"description_after":"Return the document as structured Markdown (headings, tables, lists, code blocks, math).\n\nBrainiall Doc Layout engine. The single API for converting documents to LLM-friendly format.","description_similarity":null,"before_hash":null,"after_hash":"e0bf05eb9f3a15b897c2fb1b1b9085e4"},{"tool":"document_tables","kind":"added","observed_at":"2026-09-23T21:50:30.713Z","fields":[],"description_before":null,"description_after":"Reconstruct every table in a document image into headers and rows.\n\nReturns:\n    dict with keys: table_count (int), tables (list of {title, headers, rows, row_count, column_count}); [] if there are no tables.","description_similarity":null,"before_hash":null,"after_hash":"b263c1eca15e6377fcd7dce30905a1e2"},{"tool":"document_query","kind":"added","observed_at":"2026-09-23T21:50:30.713Z","fields":[],"description_before":null,"description_after":"Ask a natural-language question about a document image; returns a grounded answer plus the supporting line.\n\nReturns found:false rather than guessing when the document doesn't contain the answer.\n\nReturns:\n    dict with keys: answer (str|null), found (bool), supporting_text (str|null), text (str).","description_similarity":null,"before_hash":null,"after_hash":"a0a01c436e1aaab1d2b9e458aca62bcf"},{"tool":"document_extract","kind":"added","observed_at":"2026-09-23T21:50:30.713Z","fields":[],"description_before":null,"description_after":"Turn a document image into structured fields. doc_type picks the schema (receipt/invoice/id/contract/form/generic).\n\nA page with no readable text returns an error rather than a guess.\n\nReturns:\n    dict with keys: doc_type (str), fields (dict — null for any value not present), text (str — the recognised plain text).","description_similarity":null,"before_hash":null,"after_hash":"b688e15782bc79cd40cc574a50366e65"},{"tool":"check_image_service","kind":"added","observed_at":"2026-09-23T21:50:30.713Z","fields":[],"description_before":null,"description_after":"Check health status of Image API services and loaded models.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - models (dict): Loaded model status per capability\n        - version (str): API version","description_similarity":null,"before_hash":null,"after_hash":"910763bdf2016314fb5df71f3a31e292"},{"tool":"restore_face","kind":"added","observed_at":"2026-09-23T21:50:30.713Z","fields":[],"description_before":null,"description_after":"Restore and enhance faces in an image with the Brainiall face-restoration engine.\n\nDetects all faces via RetinaFace, restores quality (fixes blur, noise,\ncompression artifacts), and pastes them back. Optionally enhances the\nbackground with the Brainiall image-upscaling engine. GPU-accelerated, sub-3s latency.\n\nArgs:\n    image_base64: Base64-encoded image data containing faces (PNG, JPEG, WebP).\n    upscale: Output upscale factor -- 1 to 4 (default: 2).\n    enhance_background: Whether to enhance background with the Brainiall image-upscaling engine (default: true).\n\nReturns:\n    dict with keys:\n        - image (str): Base64-encoded restored image\n        - format (str): Output image format\n        - width (int): Output width\n        - height (int): Output height\n        - upscale (int): Scale factor applied\n        - processing_time_ms (float): Processing time in milliseconds","description_similarity":null,"before_hash":null,"after_hash":"cdf902f9138f362b75b0ef207b0ce6da"},{"tool":"upscale_image","kind":"added","observed_at":"2026-09-23T21:50:30.713Z","fields":[],"description_before":null,"description_after":"Upscale image resolution with the Brainiall image-upscaling engine.\n\nEnhances image resolution by 2x or 4x with the GPU-accelerated Brainiall image-upscaling engine\nsuper-resolution. Processes in tiles (256x256) to manage VRAM.\nMaximum output dimension: 8192x8192.\n\nArgs:\n    image_base64: Base64-encoded image data (PNG, JPEG, or WebP).\n    scale: Upscale factor -- 2 or 4 (default: 4).\n\nReturns:\n    dict with keys:\n        - image (str): Base64-encoded upscaled image\n        - format (str): Output image format\n        - width (int): Output width\n        - height (int): Output height\n        - scale (int): Scale factor applied\n        - processing_time_ms (float): Processing time in milliseconds","description_similarity":null,"before_hash":null,"after_hash":"1bdc9da00781704a8976d46c32778290"},{"tool":"remove_background","kind":"added","observed_at":"2026-09-23T21:50:30.713Z","fields":[],"description_before":null,"description_after":"Remove the background from an image.\n\nUses Brainiall Cutout engine segmentation to precisely separate foreground from background.\nReturns a base64-encoded image with transparent background (PNG) or white\nbackground (WebP). Sub-500ms latency on GPU.\n\nArgs:\n    image_base64: Base64-encoded image data (PNG, JPEG, or WebP).\n    output_format: Output format -- 'png' (with transparency) or 'webp'.\n\nReturns:\n    dict with keys:\n        - image_base64 (str): Base64-encoded result image\n        - format (str): Output image format\n        - original_size (dict): Original width and height\n        - processing_ms (int): Processing time in milliseconds","description_similarity":null,"before_hash":null,"after_hash":"ac21be2e538558467f1b6abe9cd8d6cf"}],"next_before":null,"next_actions":[]}