feat: add native Android app wrapper using Capacitor and update docs

docs: update all documentation to reflect final 3-pipeline architecture and gpt-4o high-res upscaling

fix: revert gpt-4o logprobs to hardcoded confidence heuristic

style: run black formatter on tests/test_pipeline_llm.py to fix CI

fix: scale up small images for gpt-4o vision mode and simplify prompt

feat: calculate true confidence using openai logprobs

style: fix flake8 line length error in pipeline_llm.py

style: run black formatter on pipeline_llm.py to fix CI

feat: apply strong deterministic system prompt and settings for GPT-4o vision pipeline

style: remove double dashes placeholders and clean up remaining pipeline D references

fix: update unit tests to match new 3-pipeline ensemble parameters

fix: update css grid layout for 3 columns instead of 4

refactor: remove Pipeline D (Finetuned YOLO) to massively improve inference latency and simplify architecture to 3 pipelines

feat: implement global drag and drop support for image uploads

fix: revert pipeline D to dot clustering because finetuned model predicts individual dots, not characters

fix: revert to gpt-4o because gpt-4-turbo lacks image_url support in the current openai package version

style: wrap LLM system prompt strings to fix flake8 E501 line length CI failure

style: apply black formatting to fix CI pipeline failures

feat: switch OpenAI model from gpt-4o to gpt-4-turbo to test hallucination rates

fix: upload finetuned model using git-lfs

chore: clean up unused imports from pipelines B and D

fix: correctly handle YOLO bounding boxes as characters instead of individual dots in pipelines B and D

fix: normalize ensemble weights and improve GPT-4o system prompt to reduce hallucination

feat: light theme by default with dark mode toggle

feat: redesign UI with dark mode + webcam capture support

fix: handle HF proxy buffering (non-streaming fallback) + increase gunicorn timeout

fix: clean requirements.txt for Docker build (remove pyobjc, dev deps, broken editable install)

fix: add HF Spaces YAML metadata for Docker build

docs: add UI screenshots for hackathon submission

fix: clean all non-ASCII chars, fix CI (lint + tests), secure API keys

feat: four-column progressive ensemble UI driving /upload_ensemble

chore: organize markdown files - move docs to docs/ directory

chore: update .gitignore to exclude training artifacts and large files

feat: implement four-pipeline ensemble (CV + Roboflow + GPT-4o + finetuned YOLOv8)

feat: four-pipeline ensemble (CV + Roboflow + GPT-4o + finetuned YOLOv8)

fix: tune blob detector for real images, update benchmark results

docs: add real-image benchmark results and detection tuning notes

docs: add live demo status

docs: add Hugging Face Space metadata

chore: verify Docker and update project checklist

feat: scaffold BrailleVision app