Hugging Face specific Dockerfile and .jpg excluded

.devcontainer/devcontainer.json

@@ -1,8 +1,11 @@
 {
 	"name": "Dermatolog AI Scanner Dev",
-	"build": {
-		"context": "..",
-		"dockerfile": "../Dockerfile"
+	"image": "medgemma_ic-medgemma-app:latest",
+	"features": {
+		"ghcr.io/devcontainers/features/common-utils:2": {
+			"installZsh": "true",
+			"upgradePackages": "true"
+		}
 	},
 	"customizations": {
 		"vscode": {
@@ -15,7 +18,7 @@
 		}
 	},
 	"forwardPorts": [
-		8000
+		8080
 	],
 	"postCreateCommand": "pip install -r requirements-dev.txt && playwright install --with-deps chromium && npm install",
 	"runArgs": [

Dockerfile

@@ -1,7 +1,5 @@
 FROM python:3.11-slim
 
-WORKDIR /app
-
 # Install system dependencies
 RUN apt-get update && apt-get install -y \
     curl \
@@ -13,31 +11,35 @@ RUN apt-get update && apt-get install -y \
     && apt-get install -y nodejs \
     && rm -rf /var/lib/apt/lists/*
 
-# Install python dependencies
-COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+# Set up a new user named "user" with user ID 1000 (Required by HF Spaces)
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
 
-# Pre-download the model to bake it into the image
-# This prevents downloading 4GB+ on every container start
-ARG HF_TOKEN
-ENV HF_TOKEN=${HF_TOKEN}
+WORKDIR $HOME/app
+
+# Copy requirements and install
+COPY --chown=user requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
 
-RUN python -c "from transformers import AutoProcessor, AutoModel; \
+# Securely mount the HF_TOKEN secret during build to pre-download the model
+# You configure HF_TOKEN in the "Secrets" tab of your Hugging Face Space settings
+RUN --mount=type=secret,id=HF_TOKEN,mode=0444,required=true \
+    python -c "from transformers import AutoProcessor, AutoModel; \
     import os; \
-    token = os.environ.get('HF_TOKEN'); \
-    print(f'Downloading MedSigLIP model with token present: {bool(token)}...'); \
+    token = open('/run/secrets/HF_TOKEN').read().strip(); \
     AutoProcessor.from_pretrained('google/medsiglip-448', token=token); \
     AutoModel.from_pretrained('google/medsiglip-448', token=token)"
 
-# Pre-download YOLO model
+# Pre-download YOLO
 RUN python -c "from ultralytics import YOLO; YOLO('yolov8n.pt')"
 
-# Copy application code
-COPY . .
+# Copy the rest of the application code
+COPY --chown=user . $HOME/app
 
-# Expose port (Cloud Run defaults to 8080, providing a fallback)
-ENV PORT=8080
-EXPOSE $PORT
+# Hugging Face defaults to port 7860
+ENV PORT=7860
+EXPOSE 7860
 
-# Command to run (Using Shell form so it evaluates $PORT)
-CMD uvicorn app.main:app --host 0.0.0.0 --port ${PORT:-8080}
+CMD ["sh", "-c", "uvicorn app.main:app --host 0.0.0.0 --port ${PORT}"]

README.md

@@ -14,7 +14,7 @@ A privacy-first, free, and easy-to-use dermatology scan app powered by latest AI
     - **Privacy**: All data is scoped to your browser session.
 - **Zero-Shot Dermatology Analysis**:
     - Uses **Google Health's MedSigLIP** (`google/medsiglip-448`) model for localized analysis.
-    - Classifies images against a comprehensive set of **25+ dermatological conditions** relevant to EU medical practices.
+    - Classifies images against a focused set of **12 dermatological conditions** relevant to EU medical practices.
     - **Rationale**: The label set focuses on high-mortality cancers (Melanoma), high-prevalence conditions (Eczema, Acne), and common differential diagnoses to aid in effective triage.
 
 ### Confidence & Interpretation Logic
@@ -38,11 +38,11 @@ The system is tuned to detect the following conditions based on EU referral guid
 
 | Category | Conditions | Rationale |
 | :--- | :--- | :--- |
-| **Malignant / Pre-malignant** | Melanoma, Basal Cell Carcinoma (BCC), Squamous Cell Carcinoma (SCC), Actinic Keratosis, Bowen's Disease, Dysplastic Nevus | Priority for early detection due to mortality risk (Melanoma) or high prevalence impacting healthcare resources (BCC/SCC). |
-| **Inflammatory** | Psoriasis, Atopic Dermatitis (Eczema), Acne Vulgaris, Rosacea, Urticaria, Lichen Planus, Hidradenitis Suppurativa | Represents the highest burden of disease on quality of life in the EU population. |
-| **Infectious** | Fungal Infections (Tinea), Herpes Zoster (Shingles), Impetigo, Warts, Molluscum Contagiosum | Frequent reasons for primary care visits; contagious nature requires accurate identification. |
-| **Benign / Differential** | Melanocytic Nevus, Seborrheic Keratosis, Dermatofibroma, Haemangioma, Epidermoid Cyst, Lipoma | Crucial for distinguishing from malignant lesions to reduce unnecessary anxiety and referrals. |
-| **Other** | Vitiligo, Alopecia Areata, Melasma | Common pigmentary and hair disorders affecting psychological well-being. |
+| **Malignant / Pre-malignant** | Melanoma, Basal Cell Carcinoma (BCC) | Priority for early detection due to mortality risk (Melanoma) or high prevalence impacting healthcare resources (BCC). |
+| **Inflammatory** | Psoriasis, Atopic Dermatitis (Eczema), Acne Vulgaris, Rosacea | Represents the highest burden of disease on quality of life in the EU population. |
+| **Infectious** | Herpes Zoster (Shingles), Warts, Molluscum Contagiosum | Contagious nature requires accurate identification, often with distinct morphologies. |
+| **Benign / Differential** | Melanocytic Nevus, Seborrheic Keratosis | Crucial for distinguishing from malignant lesions to reduce unnecessary anxiety and referrals. |
+| **Baseline** | Normal Skin | Provides a control basis for healthy skin. |
 
 ## Privacy & Security
 
@@ -110,10 +110,19 @@ The project is designed to be developed inside a **Dev Container**. This ensures
 5.  **Start Dev Container**:
     - Open the folder in VS Code.
     - When prompted, click **"Reopen in Container"** (or run standard command `Dev Containers: Reopen in Container`).
-    - VS Code will build the container and install all dependencies defined in `requirements-dev.txt` and `package.json`.
+- VS Code will build the container and install all dependencies defined in `requirements-dev.txt` and `package.json`.
+
+    **CLI Alternative:**
+    If you cannot find the "Rebuild" option in the UI, you can force a rebuild of the environment from your local terminal:
+    ```bash
+    # Ensure HF_TOKEN is exported for the build
+    export HF_TOKEN=$(cat .env | grep HF_TOKEN | cut -d'=' -f2)
+    docker compose up -d --build
+    ```
 
     Inside the integrated terminal of VS Code (running in the container):
     ```bash
+    source venv/bin/activate # If using a local virtual environment
     npm install  # If not run automatically
     uvicorn app.main:app --reload --host 0.0.0.0 --port 8080
     ```
@@ -141,16 +150,33 @@ docker run -p 8080:8080 -e HF_TOKEN=$HF_TOKEN medgemma-app
 
 ### 🧪 Running Tests
 
-We use `pytest` for unit tests and `playwright` for end-to-end tests.
+We use `pytest` for Python tests and `Jest` for JavaScript unit tests.
 
 - **Unit Tests**:
+    Tests the core logic (image preprocessing, result interpretation, API endpoints) with external dependencies like AI models mocked for speed.
     ```bash
     pytest tests/unit
     ```
 
-- **Integration/E2E Tests**:
+- **YOLO Tests**:
+    Specifically tests the lesion detection and cropping logic.
+    ```bash
+    pytest tests/yolo_tests
+    ```
+
+- **Running All Backend Tests**:
+    You can run the core logic and YOLO tests together:
+    ```bash
+    pytest tests/unit tests/yolo_tests
+    ```
+
+> **Note on YOLO State**: Currently, both unit and YOLO tests use **mocking** for the actual YOLOv8 inference. This allows the test suite to run in seconds without requiring model weights or high-performance hardware.
+
+- **Integration & E2E Tests**:
+    These tests interact with a live server and require `playwright` for browser automation.
     ```bash
-    pytest tests/e2e
+    # Run UI and E2E tests
+    pytest tests/test_ui.py tests/test_e2e_local.py
     ```
 
 - **JavaScript Unit Tests**:

tests/test_e2e_local.py

@@ -26,16 +26,26 @@ def test_local_upload_and_analysis_flow(page, dummy_image, test_server):
     page.on("console", lambda msg: print(f"Browser Console: [{msg.type}] {msg.text}"))
     page.goto(test_server)
     
+    # Handle Medical Disclaimer
+    print("Checking for Medical Disclaimer...")
+    try:
+        disclaimer_btn = page.locator("sl-button", has_text="I Understand & Agree").first
+        disclaimer_btn.wait_for(state="visible", timeout=5000)
+        disclaimer_btn.click()
+        print("Disclaimer accepted.")
+    except:
+        print("Disclaimer not visible or already accepted, continuing...")
+    
     # 1. Clear any existing state
-    clear_btn = page.locator("sl-button", has_text="Clear All").first
+    clear_btn = page.locator("sl-button", has_text="Clear History").first
     if clear_btn.count() > 0:
         try:
             clear_btn.wait_for(state="visible", timeout=2000)
             page.once("dialog", lambda dialog: dialog.accept())
             clear_btn.click()
-            page.locator("text=No photos yet").wait_for(state="visible", timeout=5000)
+            page.locator("text=History Empty").wait_for(state="visible", timeout=5000)
         except:
-            print("Clear All button not visible or timed out, continuing...")
+            print("Clear History button not visible or timed out, continuing...")
 
     # 2. Trigger "Upload" (Local load)
     # We expect TO NOT see an /upload network call
@@ -63,16 +73,16 @@ def test_local_upload_and_analysis_flow(page, dummy_image, test_server):
     print(f"Analysis successful: {data['predictions'][0]['label']}")
 
     # 4. Verify results display in UI
-    # The 'Clinical Assessment' text should appear
-    print("Waiting for Clinical Assessment UI element...")
-    page.locator("text=Clinical Assessment").first.wait_for(state="visible", timeout=300000)
+    # The 'AI Scan result' text should appear
+    print("Waiting for AI Scan result UI element...")
+    page.locator("text=AI Scan result").first.wait_for(state="visible", timeout=300000)
     
     # Verify the label is visible
     label_text = data["predictions"][0]["label"]
     page.locator(f"text={label_text}").first.wait_for(state="visible", timeout=30000)
     
     # Verify Saliency Map toggle is present
-    saliency_toggle = page.locator("sl-details", has_text="View Grad-CAM Saliency Map").first
+    saliency_toggle = page.locator("sl-details", has_text="View Saliency Map").first
     saliency_toggle.wait_for(state="visible", timeout=10000)
     
     # 5. Trigger Lazy Saliency Load
@@ -99,12 +109,22 @@ def test_local_duplicate_handling(page, dummy_image, test_server):
     """Verifies that selecting the same file twice doesn't create duplicate timeline items."""
     page.goto(test_server)
     
+    # Handle Medical Disclaimer
+    print("Checking for Medical Disclaimer...")
+    try:
+        disclaimer_btn = page.locator("sl-button", has_text="I Understand & Agree").first
+        disclaimer_btn.wait_for(state="visible", timeout=5000)
+        disclaimer_btn.click()
+        print("Disclaimer accepted.")
+    except:
+        print("Disclaimer not visible or already accepted, continuing...")
+    
     # 1. Clear state
-    clear_btn = page.locator("sl-button", has_text="Clear All").first
+    clear_btn = page.locator("sl-button", has_text="Clear History").first
     if clear_btn.is_visible():
         page.once("dialog", lambda dialog: dialog.accept())
         clear_btn.click()
-        page.locator("text=No photos yet").wait_for(state="visible", timeout=5000)
+        page.locator("text=History Empty").wait_for(state="visible", timeout=5000)
 
     # 2. Load first time
     page.set_input_files("input[type='file']", dummy_image)

tests/test_inference_trigger.py

@@ -22,12 +22,22 @@ def test_inference_starts_on_upload(page, dummy_image, test_server):
     """
     page.goto(test_server)
     
+    # Handle Medical Disclaimer
+    print("Checking for Medical Disclaimer...")
+    try:
+        disclaimer_btn = page.locator("sl-button", has_text="I Understand & Agree").first
+        disclaimer_btn.wait_for(state="visible", timeout=5000)
+        disclaimer_btn.click()
+        print("Disclaimer accepted.")
+    except:
+        print("Disclaimer not visible or already accepted, continuing...")
+    
     # Clear session to ensure we are fresh
-    clear_btn = page.locator("sl-button", has_text="Clear All").first
+    clear_btn = page.locator("sl-button", has_text="Clear History").first
     if clear_btn.is_visible():
         page.once("dialog", lambda dialog: dialog.accept())
         clear_btn.click()
-        page.locator("text=No photos yet").wait_for(state="visible", timeout=5000)
+        page.locator("text=History Empty").wait_for(state="visible", timeout=5000)
 
     # We expect a POST to /api/photos/*/analyze
     # The app.js calls it after a 300ms timeout

tests/test_ui.py

@@ -26,6 +26,16 @@ def test_duplicate_upload_shows_warning_context(page, dummy_image, test_server):
     page.on("console", lambda msg: print(f"Browser Console: {msg.text}"))
     page.goto(test_server)
     
+    # Handle Medical Disclaimer
+    print("Checking for Medical Disclaimer...")
+    try:
+        disclaimer_btn = page.locator("sl-button", has_text="I Understand & Agree").first
+        disclaimer_btn.wait_for(state="visible", timeout=5000)
+        disclaimer_btn.click()
+        print("Disclaimer accepted.")
+    except:
+        print("Disclaimer not visible or already accepted, continuing...")
+    
     # Check if we need to clear previous state
     # We use a locator for the button
     clear_btn = page.locator("sl-button", has_text="Clear All").first