Fix issue #6444: [Feature]: Limit 'attach image' functionality to specific supported types

.github/workflows/openhands-resolver.yml

@@ -84,10 +84,6 @@ jobs:
         run: |
           python -m pip index versions openhands-ai > openhands_versions.txt
           OPENHANDS_VERSION=$(head -n 1 openhands_versions.txt | awk '{print $2}' | tr -d '()')
-          # Ensure requirements.txt ends with newline before appending
-          if [ -f requirements.txt ] && [ -s requirements.txt ]; then
-            sed -i -e '$a\' requirements.txt
-          fi
           echo "openhands-ai==${OPENHANDS_VERSION}" >> requirements.txt
           cat requirements.txt
 

.gitignore

@@ -176,7 +176,6 @@ evaluation/gorilla/data
 evaluation/toolqa/data
 evaluation/scienceagentbench/benchmark
 evaluation/commit0_bench/repos
-evaluation/visualcodebench/
 
 # openhands resolver
 output/

evaluation/benchmarks/visualcodebench/eval.py

@@ -1,674 +0,0 @@
-from collections import Counter
-from copy import deepcopy
-from difflib import SequenceMatcher
-from io import BytesIO
-
-from bs4 import BeautifulSoup, Comment, NavigableString, Tag
-import cv2
-import numpy as np
-import torch
-from colormath.color_conversions import convert_color
-from colormath.color_diff import delta_e_cie2000
-from colormath.color_objects import LabColor, sRGBColor
-from PIL import Image, ImageChops, ImageColor
-from scipy.optimize import linear_sum_assignment
-from transformers import CLIPModel, CLIPProcessor
-
-from openhands.core.logger import openhands_logger as logger
-
-
-def calculate_similarity(block1, block2):
-    """Calculate text similarity between two blocks using SequenceMatcher."""
-    text_similarity = SequenceMatcher(None, block1['text'], block2['text']).ratio()
-    return text_similarity
-
-
-def adjust_cost_for_context(cost_matrix, consecutive_bonus=1.0, window_size=20):
-    """Adjust cost matrix by considering context similarity."""
-    if window_size <= 0:
-        return cost_matrix
-
-    n, m = cost_matrix.shape
-    adjusted_cost_matrix = np.copy(cost_matrix)
-
-    for i in range(n):
-        for j in range(m):
-            if adjusted_cost_matrix[i][j] >= -0.5:
-                continue
-            nearby_matrix = cost_matrix[
-                max(0, i - window_size) : min(n, i + window_size + 1),
-                max(0, j - window_size) : min(m, j + window_size + 1),
-            ]
-            flattened_array = nearby_matrix.flatten()
-            sorted_array = np.sort(flattened_array)[::-1]
-            sorted_array = np.delete(
-                sorted_array, np.where(sorted_array == cost_matrix[i, j])[0][0]
-            )
-            top_k_elements = sorted_array[-window_size * 2 :]
-            bonus = consecutive_bonus * np.sum(top_k_elements)
-            adjusted_cost_matrix[i][j] += bonus
-    return adjusted_cost_matrix
-
-
-def create_cost_matrix(A, B):
-    """Create cost matrix for block matching."""
-    n = len(A)
-    m = len(B)
-    cost_matrix = np.zeros((n, m))
-    for i in range(n):
-        for j in range(m):
-            cost_matrix[i, j] = -calculate_similarity(A[i], B[j])
-    return cost_matrix
-
-
-def calculate_distance_max_1d(x1, y1, x2, y2):
-    """Calculate maximum 1D distance between points."""
-    return max(abs(x2 - x1), abs(y2 - y1))
-
-
-def calculate_ratio(h1, h2):
-    """Calculate ratio between two heights."""
-    return max(h1, h2) / min(h1, h2)
-
-
-def rgb_to_lab(rgb):
-    """Convert RGB color to Lab color space."""
-    rgb_color = sRGBColor(rgb[0], rgb[1], rgb[2], is_upscaled=True)
-    lab_color = convert_color(rgb_color, LabColor)
-    return lab_color
-
-
-def color_similarity_ciede2000(rgb1, rgb2):
-    """Calculate color similarity using CIEDE2000 formula."""
-    lab1 = rgb_to_lab(rgb1)
-    lab2 = rgb_to_lab(rgb2)
-    delta_e = delta_e_cie2000(lab1, lab2)
-    similarity = max(0, 1 - (delta_e / 100))
-    return similarity
-
-
-def merge_blocks_wo_check(block1, block2):
-    """Merge two blocks without additional checks."""
-    merged_text = block1['text'] + ' ' + block2['text']
-    x_min = min(block1['bbox'][0], block2['bbox'][0])
-    y_min = min(block1['bbox'][1], block2['bbox'][1])
-    x_max = max(
-        block1['bbox'][0] + block1['bbox'][2], block2['bbox'][0] + block2['bbox'][2]
-    )
-    y_max = max(
-        block1['bbox'][1] + block1['bbox'][3], block2['bbox'][1] + block2['bbox'][3]
-    )
-    merged_bbox = (x_min, y_min, x_max - x_min, y_max - y_min)
-    merged_color = tuple(
-        (color1 + color2) // 2
-        for color1, color2 in zip(block1['color'], block2['color'])
-    )
-    return {'text': merged_text, 'bbox': merged_bbox, 'color': merged_color}
-
-
-def find_maximum_matching(A, B, consecutive_bonus, window_size):
-    """Find maximum matching between two sets of blocks."""
-    cost_matrix = create_cost_matrix(A, B)
-    cost_matrix = adjust_cost_for_context(cost_matrix, consecutive_bonus, window_size)
-    row_ind, col_ind = linear_sum_assignment(cost_matrix)
-    current_cost = cost_matrix[row_ind, col_ind].tolist()
-    return list(zip(row_ind, col_ind)), current_cost, cost_matrix
-
-
-def remove_indices(lst, indices):
-    """Remove indices from list in reverse order."""
-    for index in sorted(indices, reverse=True):
-        if index < len(lst):
-            lst.pop(index)
-    return lst
-
-
-def merge_blocks_by_list(blocks, merge_list):
-    """Merge blocks according to merge list."""
-    pop_list = []
-    while merge_list:
-        i = merge_list[0][0]
-        j = merge_list[0][1]
-        blocks[i] = merge_blocks_wo_check(blocks[i], blocks[j])
-        pop_list.append(j)
-        merge_list.pop(0)
-        if merge_list:
-            new_merge_list = []
-            for k in range(len(merge_list)):
-                if (
-                    merge_list[k][0] != i
-                    and merge_list[k][1] != i
-                    and merge_list[k][0] != j
-                    and merge_list[k][1] != j
-                ):
-                    new_merge_list.append(merge_list[k])
-            merge_list = new_merge_list
-    remove_indices(blocks, pop_list)
-    return blocks
-
-
-def difference_of_means(list1, list2):
-    """Calculate difference of means between two lists."""
-    counter1 = Counter(list1)
-    counter2 = Counter(list2)
-
-    for element in set(list1) & set(list2):
-        common_count = min(counter1[element], counter2[element])
-        counter1[element] -= common_count
-        counter2[element] -= common_count
-
-    unique_list1 = [item for item in counter1.elements()]
-    unique_list2 = [item for item in counter2.elements()]
-
-    mean_list1 = sum(unique_list1) / len(unique_list1) if unique_list1 else 0
-    mean_list2 = sum(unique_list2) / len(unique_list2) if unique_list2 else 0
-
-    if mean_list1 - mean_list2 > 0:
-        if min(unique_list1) > min(unique_list2):
-            return mean_list1 - mean_list2
-        return 0.0
-    return mean_list1 - mean_list2
-
-
-def find_possible_merge(A, B, consecutive_bonus, window_size, debug=False):
-    """Find possible merges between blocks."""
-    merge_bonus = 0.0
-    merge_windows = 1
-
-    def sortFn(value):
-        return value[2]
-
-    while True:
-        A_changed = False
-        B_changed = False
-
-        matching, current_cost, cost_matrix = find_maximum_matching(
-            A, B, merge_bonus, merge_windows
-        )
-
-        if len(A) >= 2:
-            merge_list = []
-            for i in range(len(A) - 1):
-                new_A = deepcopy(A)
-                new_A[i] = merge_blocks_wo_check(new_A[i], new_A[i + 1])
-                new_A.pop(i + 1)
-                updated_matching, updated_cost, _ = find_maximum_matching(
-                    new_A, B, merge_bonus, merge_windows
-                )
-                diff = difference_of_means(current_cost, updated_cost)
-                if diff > 0.05:
-                    merge_list.append([i, i + 1, diff])
-
-            merge_list.sort(key=sortFn, reverse=True)
-            if merge_list:
-                A_changed = True
-                A = merge_blocks_by_list(A, merge_list)
-                matching, current_cost, cost_matrix = find_maximum_matching(
-                    A, B, merge_bonus, merge_windows
-                )
-
-        if len(B) >= 2:
-            merge_list = []
-            for i in range(len(B) - 1):
-                new_B = deepcopy(B)
-                new_B[i] = merge_blocks_wo_check(new_B[i], new_B[i + 1])
-                new_B.pop(i + 1)
-                updated_matching, updated_cost, _ = find_maximum_matching(
-                    A, new_B, merge_bonus, merge_windows
-                )
-                diff = difference_of_means(current_cost, updated_cost)
-                if diff > 0.05:
-                    merge_list.append([i, i + 1, diff])
-
-            merge_list.sort(key=sortFn, reverse=True)
-            if merge_list:
-                B_changed = True
-                B = merge_blocks_by_list(B, merge_list)
-                matching, current_cost, cost_matrix = find_maximum_matching(
-                    A, B, merge_bonus, merge_windows
-                )
-
-        if not A_changed and not B_changed:
-            break
-
-    matching, _, _ = find_maximum_matching(A, B, consecutive_bonus, window_size)
-    return A, B, matching
-
-
-def merge_blocks_by_bbox(blocks):
-    """Merge blocks with same bounding box."""
-    merged_blocks = {}
-    for block in blocks:
-        bbox = tuple(block['bbox'])
-        if bbox in merged_blocks:
-            existing_block = merged_blocks[bbox]
-            existing_block['text'] += ' ' + block['text']
-            existing_block['color'] = [
-                (ec + c) / 2 for ec, c in zip(existing_block['color'], block['color'])
-            ]
-        else:
-            merged_blocks[bbox] = block
-    return list(merged_blocks.values())
-
-
-def mask_bounding_boxes_with_inpainting(image, bounding_boxes):
-    """Mask bounding boxes in image using inpainting."""
-    image_cv = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR)
-    mask = np.zeros(image_cv.shape[:2], dtype=np.uint8)
-    height, width = image_cv.shape[:2]
-
-    for bbox in bounding_boxes:
-        x_ratio, y_ratio, w_ratio, h_ratio = bbox
-        x = int(x_ratio * width)
-        y = int(y_ratio * height)
-        w = int(w_ratio * width)
-        h = int(h_ratio * height)
-        mask[y : y + h, x : x + w] = 255
-
-    inpainted_image = cv2.inpaint(image_cv, mask, 3, cv2.INPAINT_TELEA)
-    return Image.fromarray(cv2.cvtColor(inpainted_image, cv2.COLOR_BGR2RGB))
-
-
-def rescale_and_mask(image, blocks):
-    """Rescale image and mask blocks."""
-    if blocks:
-        image = mask_bounding_boxes_with_inpainting(image, blocks)
-
-    width, height = image.size
-    if width < height:
-        new_size = (width, width)
-    else:
-        new_size = (height, height)
-
-    return image.resize(new_size, Image.LANCZOS)
-
-
-def calculate_clip_similarity(image1, image2, blocks1, blocks2):
-    """Calculate CLIP similarity between two images."""
-    model = CLIPModel.from_pretrained('openai/clip-vit-base-patch32')
-    processor = CLIPProcessor.from_pretrained('openai/clip-vit-base-patch32')
-    device = 'cuda' if torch.cuda.is_available() else 'cpu'
-    model = model.to(device)
-
-    # Mask and preprocess images
-    image1_masked = rescale_and_mask(image1, [block['bbox'] for block in blocks1])
-    image2_masked = rescale_and_mask(image2, [block['bbox'] for block in blocks2])
-    inputs = processor(
-        images=[image1_masked, image2_masked], return_tensors='pt', padding=True
-    )
-    inputs = {k: v.to(device) for k, v in inputs.items()}
-
-    # Calculate features and similarity
-    with torch.no_grad():
-        image_features = model.get_image_features(**inputs)
-        image_features1 = image_features[0].unsqueeze(0)
-        image_features2 = image_features[1].unsqueeze(0)
-        image_features1 /= image_features1.norm(dim=-1, keepdim=True)
-        image_features2 /= image_features2.norm(dim=-1, keepdim=True)
-        similarity = (image_features1 @ image_features2.T).item()
-
-    return similarity
-
-
-def rgb_to_hex(rgb):
-    """Convert an RGB tuple to hexadecimal format."""
-    return '{:02X}{:02X}{:02X}'.format(*rgb)
-
-
-class ColorPool:
-    def __init__(self, offset=0):
-        color_values = list(range(10, 251, 16))
-        color_list = [((r + offset) % 256, (g + offset) % 256, (b + offset) % 256) 
-                     for r in color_values for g in color_values for b in color_values]
-        self.color_pool = [rgb_to_hex(color) for color in color_list]
-
-    def pop_color(self):
-        if self.color_pool:
-            return self.color_pool.pop()
-        else:
-            raise NotImplementedError
-
-
-def process_html_str(html_str, offset=0):
-    """Process HTML string to assign unique colors to text elements."""
-    soup = BeautifulSoup(html_str, 'html.parser')
-
-    def update_style(element, property_name, value):
-        important_value = f"{value} !important"
-        styles = element.attrs.get('style', '').split(';')
-        updated_styles = [s for s in styles if not s.strip().startswith(property_name) and len(s.strip()) > 0]
-        updated_styles.append(f"{property_name}: {important_value}")
-        element['style'] = '; '.join(updated_styles).strip()
-
-    # Set background color of all elements to transparent white
-    for element in soup.find_all(True):
-        update_style(element, 'background-color', 'rgba(255, 255, 255, 0.0)')
-
-    color_pool = ColorPool(offset)
-    text_tags = ['p', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'div', 'span', 'a', 'b', 'li', 
-                 'table', 'td', 'th', 'button', 'footer', 'header', 'figcaption']
-
-    for tag in soup.find_all(text_tags):
-        color = f"#{color_pool.pop_color()}"
-        update_style(tag, 'color', color)
-        update_style(tag, 'opacity', '1.0')
-
-    return str(soup)
-
-
-def similar(n1, n2):
-    """Check if two numbers are similar within a threshold."""
-    return abs(n1 - n2) <= 8
-
-
-def find_different_pixels(image1, image2):
-    """Find pixels that differ between two images."""
-    if image1.size != image2.size:
-        logger.warning("Images are not the same size")
-        return None
-
-    image1 = image1.convert('RGB')
-    image2 = image2.convert('RGB')
-    pixels1 = image1.load()
-    pixels2 = image2.load()
-    different_pixels = []
-
-    for x in range(image1.size[0]):
-        for y in range(image1.size[1]):
-            r1, g1, b1 = pixels1[x, y]
-            r2, g2, b2 = pixels2[x, y]
-            if similar((r1 + 50) % 256, r2) and similar((g1 + 50) % 256, g2) and similar((b1 + 50) % 256, b2):
-                different_pixels.append((y, x))
-
-    return np.stack(different_pixels) if different_pixels else None
-
-
-def extract_text_with_color(html_str):
-    """Extract text and color information from HTML string."""
-    def get_color(tag):
-        if 'style' in tag.attrs:
-            styles = tag['style'].split(';')
-            color_style = [s for s in styles if 'color' in s and 'background-color' not in s]
-            if color_style:
-                color = color_style[-1].split(':')[1].strip().replace(" !important", "")
-                if color[0] == "#":
-                    return color
-                else:
-                    try:
-                        if color.startswith('rgb'):
-                            color = tuple(map(int, color[4:-1].split(',')))
-                        else:
-                            color = ImageColor.getrgb(color)
-                        return '#{:02x}{:02x}{:02x}'.format(*color)
-                    except ValueError:
-                        logger.warning(f"Unable to identify or convert color: {color}")
-                        return None
-        return None
-
-    def extract_text_recursive(element, parent_color='#000000'):
-        if isinstance(element, Comment):
-            return None
-        elif isinstance(element, NavigableString):
-            text = element.strip()
-            return (text, parent_color) if text else None
-        elif isinstance(element, Tag):
-            current_color = get_color(element) or parent_color
-            children_texts = filter(None, [extract_text_recursive(child, current_color) 
-                                        for child in element.children])
-            return list(children_texts)
-
-    soup = BeautifulSoup(html_str, 'html.parser')
-    body = soup.body
-    return extract_text_recursive(body) if body else []
-
-
-def flatten_tree(tree):
-    """Flatten a nested tree structure into a list."""
-    flat_list = []
-    def flatten(node):
-        if isinstance(node, list):
-            for item in node:
-                flatten(item)
-        else:
-            flat_list.append(node)
-    flatten(tree)
-    return flat_list
-
-
-def get_blocks_from_image_diff_pixels(image, html_text_color_tree, different_pixels):
-    """Extract text blocks from image using color differences."""
-    image_cv = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR)
-    x_w = image_cv.shape[0]
-    y_w = image_cv.shape[1]
-
-    def hex_to_bgr(hex_color):
-        hex_color = hex_color.lstrip('#')
-        rgb = tuple(int(hex_color[i:i+2], 16) for i in (0, 2, 4))
-        return rgb[::-1]
-
-    def get_intersect(arr1, arr2):
-        arr1_reshaped = arr1.view([('', arr1.dtype)] * arr1.shape[1])
-        arr2_reshaped = arr2.view([('', arr2.dtype)] * arr2.shape[1])
-        common_rows = np.intersect1d(arr1_reshaped, arr2_reshaped)
-        return common_rows.view(arr1.dtype).reshape(-1, arr1.shape[1])
-
-    blocks = []
-    for item in html_text_color_tree:
-        try:
-            color = np.array(hex_to_bgr(item[1]), dtype="uint8")
-        except:
-            continue
-
-        lower = color - 4
-        upper = color + 4
-        mask = cv2.inRange(image_cv, lower, upper)
-        coords = np.column_stack(np.where(mask > 0))
-        coords = get_intersect(coords, different_pixels)
-
-        if coords.size == 0:
-            continue
-
-        x_min, y_min = np.min(coords, axis=0)
-        x_max, y_max = np.max(coords, axis=0)
-        
-        # Get average color from original image
-        color_coords = coords.copy()
-        color_coords = color_coords[color_coords[:, 0] <= x_max]
-        color_coords = color_coords[color_coords[:, 1] <= y_max]
-        colors = [image_cv[x, y] for x, y in color_coords]
-        avg_color = tuple(map(int, np.mean(colors, axis=0)))[::-1]  # Convert BGR to RGB
-
-        blocks.append({
-            'text': item[0].lower(),
-            'bbox': (y_min / y_w, x_min / x_w, (y_max - y_min + 1) / y_w, (x_max - x_min + 1) / x_w),
-            'color': avg_color
-        })
-
-    return blocks
-
-
-def get_blocks_from_html(html_str, image1):
-    """Extract text blocks from HTML and image."""
-    # Process HTML with two different color offsets
-    html_str_1 = process_html_str(html_str, offset=0)
-    html_str_2 = process_html_str(html_str, offset=50)
-
-    # Render both HTML versions to images
-    # TODO: Screenshot html_str_2
-    filter_color = (255, 0, 0)  
-    image2 = Image.new("RGB", image1.size, filter_color)
-
-
-    # Find pixels that differ between the two rendered images
-    different_pixels = find_different_pixels(image1, image2)
-    if different_pixels is None:
-        logger.warning("Unable to get pixels with different colors")
-        return []
-
-    # Extract text and color information from HTML
-    html_text_color_tree = flatten_tree(extract_text_with_color(html_str_1))
-    try:
-        blocks = get_blocks_from_image_diff_pixels(image1, html_text_color_tree, different_pixels)
-    except Exception as e:
-        logger.warning(f"Unable to get blocks: {e}")
-        return []
-
-    return blocks
-
-
-def evaluate(task, generated_img):
-    """Evaluate generated image against reference image using multiple metrics."""
-    # Load reference image
-    post_image = task['post_image']
-
-    # Extract blocks from HTML and images
-    post_blocks = get_blocks_from_html(task['post_html'], post_image)
-    gen_blocks = get_blocks_from_html(task['gen_html'], generated_img)
-
-    print("block details", post_blocks, gen_blocks)
-    if not post_blocks or not gen_blocks:
-        # Fallback to basic CLIP and pixel comparison if no blocks available
-        clip_score = calculate_clip_similarity(post_image, generated_img, [], [])
-        logger.info(f'CLIP similarity score: {clip_score}')
-
-        # Pixel comparison
-        diff = ImageChops.difference(generated_img, post_image)
-        pixel_match = not diff.getbbox()
-        logger.info(
-            f"Pixel difference analysis: {'No difference' if pixel_match else 'Differences found'}"
-        )
-
-        return clip_score > 0.95 or pixel_match
-
-    # Merge blocks with same bounding boxes
-    post_blocks = merge_blocks_by_bbox(post_blocks)
-    gen_blocks = merge_blocks_by_bbox(gen_blocks)
-
-    # Find optimal block matching
-    consecutive_bonus, window_size = 0.1, 1
-    gen_blocks_m, post_blocks_m, matching = find_possible_merge(
-        gen_blocks, deepcopy(post_blocks), consecutive_bonus, window_size
-    )
-
-    # Filter matches with low similarity
-    filtered_matching = []
-    for i, j in matching:
-        text_similarity = calculate_similarity(gen_blocks_m[i], post_blocks_m[j])
-        if text_similarity >= 0.5:
-            filtered_matching.append([i, j, text_similarity])
-    matching = filtered_matching
-
-    if not matching:
-        logger.warning('No matching blocks found')
-        clip_score = calculate_clip_similarity(
-            post_image, generated_img, gen_blocks, post_blocks
-        )
-        return clip_score > 0.95
-
-    # Calculate metrics for matched blocks
-    indices1 = [item[0] for item in matching]
-    indices2 = [item[1] for item in matching]
-
-    # Calculate unmatched areas
-    unmatched_area_1 = sum(
-        block['bbox'][2] * block['bbox'][3]
-        for i, block in enumerate(gen_blocks_m)
-        if i not in indices1
-    )
-    unmatched_area_2 = sum(
-        block['bbox'][2] * block['bbox'][3]
-        for j, block in enumerate(post_blocks_m)
-        if j not in indices2
-    )
-    total_unmatched_area = unmatched_area_1 + unmatched_area_2
-
-    # Calculate metrics for matched blocks
-    matched_areas = []
-    text_scores = []
-    position_scores = []
-    color_scores = []
-
-    for i, j, text_similarity in matching:
-        # Area
-        block_area = (
-            gen_blocks_m[i]['bbox'][2] * gen_blocks_m[i]['bbox'][3]
-            + post_blocks_m[j]['bbox'][2] * post_blocks_m[j]['bbox'][3]
-        )
-        matched_areas.append(block_area)
-
-        # Position similarity
-        position_similarity = 1 - calculate_distance_max_1d(
-            gen_blocks_m[i]['bbox'][0] + gen_blocks_m[i]['bbox'][2] / 2,
-            gen_blocks_m[i]['bbox'][1] + gen_blocks_m[i]['bbox'][3] / 2,
-            post_blocks_m[j]['bbox'][0] + post_blocks_m[j]['bbox'][2] / 2,
-            post_blocks_m[j]['bbox'][1] + post_blocks_m[j]['bbox'][3] / 2,
-        )
-
-        # Color similarity
-        color_similarity = color_similarity_ciede2000(
-            gen_blocks_m[i]['color'], post_blocks_m[j]['color']
-        )
-
-        text_scores.append(text_similarity)
-        position_scores.append(position_similarity)
-        color_scores.append(color_similarity)
-
-    # Calculate final scores
-    total_area = sum(matched_areas) + total_unmatched_area
-    size_score = sum(matched_areas) / total_area if total_area > 0 else 0
-    text_score = np.mean(text_scores) if text_scores else 0
-    position_score = np.mean(position_scores) if position_scores else 0
-    color_score = np.mean(color_scores) if color_scores else 0
-    clip_score = calculate_clip_similarity(
-        post_image, generated_img, gen_blocks, post_blocks
-    )
-
-    # Combine scores with equal weights
-    final_score = 0.2 * (
-        size_score + text_score + position_score + color_score + clip_score
-    )
-
-    logger.info('Evaluation scores:')
-    logger.info(f'- Size score: {size_score:.3f}')
-    logger.info(f'- Text score: {text_score:.3f}')
-    logger.info(f'- Position score: {position_score:.3f}')
-    logger.info(f'- Color score: {color_score:.3f}')
-    logger.info(f'- CLIP score: {clip_score:.3f}')
-    logger.info(f'- Final score: {final_score:.3f}')
-
-    return final_score > 0.8  # Consider it a match if final score > 80%
-
-
-def png_to_bytes(png):
-    buffer = BytesIO()
-    png.save(buffer, format='PNG')
-    image_bytes = buffer.getvalue()
-    return image_bytes
-
-
-def bytes_to_image(image_bytes):
-    """Convert bytes to a Pillow Image object."""
-    return Image.open(BytesIO(image_bytes))
-
-
-if __name__ == '__main__':
-    first_image = Image.open('./evaluation/visualcodebench/data/1/post.png')
-    image = Image.open('./evaluation/visualcodebench/data/1/prev.png')
-    
-    
-    html_file = open('./evaluation/visualcodebench/data/1/post/index.html', 'r')
-    first_html = html_file.read()
-    html_file.close()
-
-    html_file = open('./evaluation/visualcodebench/data/1/prev/index.html', 'r')
-    gen_html = html_file.read()
-    html_file.close()
-
-
-
-    sample = {'post_image': first_image, "post_html": first_html, "gen_html": gen_html}
-
-
-
-    evaluate(sample, image)
-

evaluation/benchmarks/visualcodebench/prepare.py

@@ -1,97 +0,0 @@
-import base64
-import os
-from io import BytesIO
-
-import pandas as pd
-from huggingface_hub import snapshot_download
-from PIL import PngImagePlugin
-from tqdm import tqdm
-
-from openhands.core.logger import openhands_logger as logger
-
-REPO_DOWNLOAD_DIR = (
-    './evaluation/visualcodebench/'  # Directory to store the downloaded repository
-)
-
-
-def download_repository():
-    """
-    Download the entire repository from Hugging Face Hub.
-    This function clones the repository into REPO_DOWNLOAD_DIR.
-    """
-    repo_id = 'rvmalhot/VisualCodeBench'
-    try:
-        logger.info(f"Downloading repository '{repo_id}'...")
-        snapshot_download(
-            repo_id=repo_id,
-            local_dir=REPO_DOWNLOAD_DIR,
-            repo_type='dataset',
-            ignore_patterns=None,  # Download all files
-        )
-        logger.info(f"Repository downloaded to '{REPO_DOWNLOAD_DIR}'.")
-    except Exception as e:
-        logger.error(f"Error downloading repository '{repo_id}': {e}")
-        raise e
-
-
-def format_task_dict(example):
-    instance_id = example['id']
-    prev_remote_path = os.path.join(REPO_DOWNLOAD_DIR, f'data/{instance_id}/prev')
-    post_remote_path = os.path.join(REPO_DOWNLOAD_DIR, f'data/{instance_id}/post')
-
-    # Check if 'prev' and 'post' directories exist
-    prev_exists = os.path.exists(prev_remote_path)
-    post_exists = os.path.exists(post_remote_path)
-
-    if prev_exists and post_exists:
-        skip = False
-    else:
-        skip = True
-
-    task = {
-        'instance_id': instance_id,
-        'prev_image': example['prev_image'],
-        'post_image': example['post_image'],
-        'changes': example['changes'],
-        'prev_code_files': example['prev_code_files'],
-        'post_code_files': example['post_code_files'],
-        'skip': skip,
-    }
-
-    return task
-
-
-def prepare_visualcodebench(dataset):
-    logger.info('Processing dataset')
-    dataset_processed = []
-    for example in tqdm(dataset['train']):
-        formatted_example = format_task_dict(example)
-        if formatted_example['skip']:
-            continue
-        del formatted_example['skip']
-        dataset_processed.append(formatted_example)
-
-    return pd.DataFrame(dataset_processed)
-
-
-def pil_image_to_base64(image: PngImagePlugin.PngImageFile) -> str:
-    """
-    Converts a PIL image to a Base64-encoded string.
-
-    Parameters:
-    - image (PngImagePlugin.PngImageFile): The PIL image to convert.
-
-    Returns:
-    - str: The Base64-encoded string of the image.
-    """
-    if not isinstance(image, PngImagePlugin.PngImageFile):
-        raise ValueError(
-            'The provided image is not a PIL.PngImagePlugin.PngImageFile instance.'
-        )
-
-    buffered = BytesIO()
-    image.save(buffered, format='PNG')
-    img_bytes = buffered.getvalue()
-    img_base64 = base64.b64encode(img_bytes).decode('utf-8')
-    base64_with_prefix = f'data:image/png;base64,{img_base64}'
-    return [base64_with_prefix]

evaluation/benchmarks/visualcodebench/run_infer.py

@@ -1,247 +0,0 @@
-# FILE: run_infer.py
-
-import asyncio
-import os
-import shutil
-import tempfile
-from functools import partial
-
-import pandas as pd
-from datasets import load_dataset
-
-# from evaluation.benchmarks.visualcodebench.eval import capture_screenshot
-from evaluation.benchmarks.visualcodebench.prepare import (
-    REPO_DOWNLOAD_DIR,
-    download_repository,
-    pil_image_to_base64,
-    prepare_visualcodebench,
-)
-from evaluation.utils.shared import (
-    EvalMetadata,
-    assert_and_raise,
-    codeact_user_response,
-    make_metadata,
-    prepare_dataset,
-    reset_logger_for_multiprocessing,
-    run_evaluation,
-)
-from openhands.controller.state.state import State
-from openhands.core.config import (
-    AppConfig,
-    SandboxConfig,
-    get_llm_config_arg,
-)
-from openhands.core.config.utils import parse_arguments
-from openhands.core.logger import openhands_logger as logger  # Import OpenHands logger
-from openhands.core.main import create_runtime, run_controller
-from openhands.events.action.commands import CmdRunAction
-from openhands.events.action.message import MessageAction
-from openhands.events.observation.commands import CmdOutputObservation
-from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync
-
-# Define workspace and output directories
-WORKSPACE_DIR = './workspace'
-
-FAKE_RESPONSES = {
-    'CodeActAgent': partial(codeact_user_response, encapsulate_solution=True),
-}
-
-
-def get_config(
-    metadata: EvalMetadata,
-) -> AppConfig:
-    config = AppConfig(
-        default_agent=metadata.agent_class,
-        run_as_openhands=False,
-        runtime='eventstream',
-        max_iterations=metadata.max_iterations,
-        sandbox=SandboxConfig(
-            base_container_image='python:3.12-bookworm',
-            enable_auto_lint=True,
-            use_host_network=False,
-        ),
-        # do not mount workspace
-        workspace_base=None,
-        workspace_mount_path=None,
-    )
-    config.set_llm_config(metadata.llm_config)
-    return config
-
-
-def initialize_runtime(
-    runtime: Runtime,
-    instance: pd.Series,  # this argument is not required
-):
-    """Initialize the runtime for the agent.
-
-    This function is called before the runtime is used to run the agent.
-    """
-    logger.info('-' * 30)
-    logger.info('BEGIN Runtime Initialization Fn')
-    logger.info('-' * 30)
-    workspace_dir_name = instance['instance_id']
-    obs: CmdOutputObservation
-
-    action = CmdRunAction(command='mkdir -p /workspace/{workspace_dir_name}')
-    action.timeout = 600
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        obs.exit_code == 0,
-        f'Failed to create /workspace/{workspace_dir_name}: {str(obs)}',
-    )
-
-    file_path = REPO_DOWNLOAD_DIR + f'data/{workspace_dir_name}/prev/index.html'
-    runtime.copy_to(file_path, f'/workspace/{workspace_dir_name}')
-    logger.info(f'Copied code file for instance {workspace_dir_name}')
-
-    action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
-    action.timeout = 600
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        obs.exit_code == 0,
-        f'Failed to cd to /workspace/{workspace_dir_name}: {str(obs)}',
-    )
-
-    logger.info('-' * 30)
-    logger.info('END Runtime Initialization Fn')
-    logger.info('-' * 30)
-
-
-def complete_runtime(
-    runtime: Runtime,
-    instance: pd.Series,  # this argument is not required, but it is used to get the workspace_dir_name
-) -> str:
-    # TODO: extract edited HTML file from agent workspace
-    # temp_zip = runtime.copy_from(f'/workspace/{instance.instance_id}')
-    # file_name = f'/workspace/{instance.instance_id}/index.html'
-    # with zipfile.ZipFile(temp_zip, 'r') as zip_ref:
-    #     if file_name in zip_ref.namelist():
-    #         with zip_ref.open(file_name) as file:
-    #             file_content = file.read().decode('utf-8')  # Decode bytes to string
-    #     else:
-    #         raise FileNotFoundError(f"'{file_name}' not found in the ZIP archive.")
-
-    with tempfile.TemporaryDirectory() as tmpdir:
-        src_folder = REPO_DOWNLOAD_DIR + f'data/{instance.instance_id}/post/'
-        shutil.copytree(src_folder, tmpdir, dirs_exist_ok=True)
-
-        # image = capture_screenshot(tmpdir)
-        # if image is not None:
-        #     shutil.copy(os.path.join(tmpdir, 'final_screenshot.png'), REPO_DOWNLOAD_DIR)
-
-
-def process_instance(
-    instance: pd.Series, metadata: EvalMetadata, reset_logger: bool = True
-):
-    config = get_config(metadata)
-
-    # Setup the logger properly, so you can run multi-processing to parallelize the evaluation
-    if reset_logger:
-        log_dir = os.path.join(metadata.eval_output_dir, 'infer_logs')
-        reset_logger_for_multiprocessing(logger, instance.instance_id, log_dir)
-    else:
-        logger.info(f'Starting evaluation for instance {instance.instance_id}.')
-
-    # =============================================
-    # build instruction
-    # =============================================
-
-    # Prepare instruction
-    instruction = (
-        f"Modify the HTML/CSS according to the following instruction:\n\n"
-        f"{instance['changes']}\n\n"
-    )
-    instruction += (
-        'IMPORTANT: You should ONLY interact with the environment provided '
-        'to you AND NEVER ASK FOR HUMAN HELP.\n'
-    )
-
-    # =============================================
-    # create sandbox and run the agent
-    # =============================================
-
-    runtime: Runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
-
-    try:
-        initialize_runtime(runtime, instance=instance)
-
-        image_urls = pil_image_to_base64(instance['prev_image'])
-
-        action = MessageAction(content=instruction, image_urls=image_urls)
-        state: State | None = asyncio.run(
-            run_controller(
-                config=config,
-                initial_user_action=action,
-                runtime=runtime,
-                fake_user_response_fn=FAKE_RESPONSES[metadata.agent_class],
-            )
-        )
-        if state is None:
-            raise ValueError('State should not be None.')
-
-        # =============================================
-        # result evaluation
-        # =============================================
-
-        return_val = complete_runtime(runtime, instance)
-        logger.info(f'Return value {return_val}')
-    finally:
-        runtime.close()
-
-    # TODO: return EVAL output
-
-
-def main():
-    """Main function to run the evaluation."""
-    # args = parse_args()
-    args = parse_arguments()
-
-    logger.info(f"\n{'='*80}\nStarting VisualCodeBench Evaluation\n{'='*80}")
-    logger.info(f'Agent: {args.agent_cls}')
-    logger.info(f'Model: {args.llm_config}')
-    logger.info(f'Max iterations: {args.max_iterations}')
-    logger.info(f'Eval limit: {args.eval_n_limit}')
-    logger.info(f'Num workers: {args.eval_num_workers}\n')
-    logger.info(f'Eval output: {args.eval_output_dir}\n')
-
-    # Step 1: Download the entire repository once
-    logger.info('Downloading repository...')
-    download_repository()
-
-    # Step 2: Load Dataset
-    logger.info('Loading dataset...')
-    dataset = load_dataset(REPO_DOWNLOAD_DIR)
-
-    # Step 3: Prepare dataset
-    llm_config = get_llm_config_arg(args.llm_config)
-    if llm_config is None:
-        logger.error(f'Could not find LLM config: {args.llm_config}')
-        raise ValueError(f'Could not find LLM config: {args.llm_config}')
-
-    metadata = make_metadata(
-        llm_config,
-        'VisualCodeBench',
-        args.agent_cls,
-        args.max_iterations,
-        args.eval_note,
-        'evaluation/output/',
-    )
-
-    output_file = os.path.join(metadata.eval_output_dir, 'output.jsonl')
-    dataset = prepare_visualcodebench(dataset)
-    instances = prepare_dataset(dataset, output_file, eval_n_limit=args.eval_n_limit)
-
-    # Step 4: Run eval
-    run_evaluation(
-        instances, metadata, output_file, args.eval_num_workers, process_instance
-    )
-
-
-if __name__ == '__main__':
-    main()

evaluation/benchmarks/visualcodebench/scripts/run_infer.sh

@@ -1,46 +0,0 @@
-#!/bin/bash
-set -eo pipefail
-
-source "evaluation/utils/version_control.sh"
-
-# Check if required arguments are provided
-if [ "$#" -lt 4 ]; then
-    echo "Usage: $0 [model_config] [commit_hash] [agent_cls] [eval_limit] [num_workers]"
-    echo "Example: $0 llm.eval_gpt_4o_mini HEAD CodeActAgent 5 1"
-    exit 1
-fi
-
-MODEL_CONFIG=$1
-COMMIT_HASH=$2
-AGENT_CLS=$3
-EVAL_LIMIT=$4
-NUM_WORKERS=${5:-1}  # Default to 1 worker if not specified
-
-# Checkout the specified commit
-checkout_eval_branch
-
-if [ -z "$AGENT" ]; then
-  echo "Agent not specified, use default CodeActAgent"
-  AGENT="CodeActAgent"
-fi
-
-get_openhands_version
-
-echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
-echo "MODEL_CONFIG: $MODEL_CONFIG"
-
-COMMAND="export PYTHONPATH=evaluation/benchmarks/visualcodebench:\$PYTHONPATH && poetry run python evaluation/benchmarks/visualcodebench/run_infer.py \
-  --agent-cls $AGENT \
-  --llm-config $MODEL_CONFIG \
-  --max-iterations 5 \
-  --eval-num-workers $NUM_WORKERS \
-  --eval-note $OPENHANDS_VERSION" \
-
-if [ -n "$EVAL_LIMIT" ]; then
-  echo "EVAL_LIMIT: $EVAL_LIMIT"
-  COMMAND="$COMMAND --eval-n-limit $EVAL_LIMIT"
-fi
-
-# Run the command
-eval $COMMAND

evaluation/benchmarks/visualcodebench/server.py

@@ -1,167 +0,0 @@
-import http
-import os
-import socket
-import socketserver
-import threading
-import time
-from io import BytesIO
-
-import requests
-from PIL import Image, ImageChops
-from playwright.sync_api import sync_playwright
-
-from openhands.core.logger import openhands_logger as logger
-
-
-def get_free_port():
-    """Find a free port to run the HTTP server."""
-    with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
-        s.bind(('', 0))
-        return s.getsockname()[1]
-
-
-def start_http_server(tmpdir):
-    port = get_free_port()
-
-    class CustomHTTPRequestHandler(http.server.SimpleHTTPRequestHandler):
-        def translate_path(self, path):
-            # Serve files from the specified directory instead of the current working directory
-            path = super().translate_path(path)
-            relative_path = os.path.relpath(path, os.getcwd())
-            return os.path.join(tmpdir, relative_path)
-
-    handler = CustomHTTPRequestHandler
-    server = socketserver.TCPServer(('', port), handler)
-    return server, port
-
-
-def capture_screenshot(tmpdir):
-    server, port = start_http_server(tmpdir)
-    server_thread = threading.Thread(target=server.serve_forever)
-    server_thread.daemon = True
-    server_thread.start()
-    time.sleep(10)
-
-    image = None
-    try:
-        server_url = f'http://localhost:{port}/'
-
-        if not is_server_reachable(server_url):
-            raise RuntimeError(f'Server not reachable at {server_url}')
-
-        screenshot_path = os.path.join(tmpdir, 'final_screenshot.png')
-        capture_screenshot_playwright(server_url, screenshot_path)
-        image = Image.open(screenshot_path)
-        image.load()
-    finally:
-        # Shut down the server and clean up
-        server.shutdown()
-        server.server_close()
-
-    return image
-
-
-def is_server_reachable(url):
-    """
-    Check if the local server is reachable.
-    """
-    try:
-        response = requests.get(url, timeout=5)  # Set a 5-second timeout
-        if response.status_code == 200:
-            logger.info(f'Server is reachable at {url}')
-            return True
-        else:
-            logger.warning(
-                f'Server responded with status code {response.status_code} at {url}'
-            )
-            return False
-    except requests.ConnectionError as e:
-        logger.error(f'Failed to connect to server at {url}: {e}')
-        return False
-
-
-def capture_screenshot_playwright(url, screenshot_path):
-    """Capture a screenshot of the given URL using Playwright."""
-    try:
-        with sync_playwright() as p:
-            logger.info('Launching browser...')
-            browser = p.chromium.launch(timeout=10000)  # 10 seconds for browser launch
-
-            logger.info('Creating a new page...')
-            page = browser.new_page()
-
-            logger.info(f'Navigating to URL: {url}')
-            try:
-                page.goto(url, timeout=60 * 1000)  # Set timeout to 5 seconds
-                logger.info('Page navigation completed.')
-            except Exception as e:
-                logger.warning(f'Page navigation timed out. {e}. Continuing...')
-
-            logger.info('Waiting for network to be idle...')
-            try:
-                page.wait_for_load_state(
-                    'networkidle', timeout=60 * 1000
-                )  # Set timeout to 5 seconds
-                logger.info('Page load state reached.')
-            except Exception as e:
-                logger.warning(f'Page load state timed out. {e}. Continuing...')
-
-            logger.info('Capturing screenshot...')
-            page.screenshot(
-                path=screenshot_path, full_page=True
-            )  # Capture full page screenshot
-
-            logger.info(f'Screenshot saved to {screenshot_path}')
-            browser.close()
-            return True
-    except Exception as e:
-        logger.error(f'Error capturing screenshot with Playwright: {e}')
-        return False
-
-
-def evaluate(task, screenshot_path):
-    """Compare generated screenshot with post_image using CLIP score."""
-    try:
-        import torch
-        from transformers import CLIPModel, CLIPProcessor
-
-        # Load CLIP model and processor
-        model = CLIPModel.from_pretrained('openai/clip-vit-base-patch32')
-        processor = CLIPProcessor.from_pretrained('openai/clip-vit-base-patch32')
-
-        # Load images
-        post_image = Image.open(BytesIO(task['post_image']))
-        generated_img = Image.open(screenshot_path)
-
-        # Process images
-        inputs = processor(
-            images=[post_image, generated_img], return_tensors='pt', padding=True
-        )
-
-        # Get image features
-        image_features = model.get_image_features(**inputs)
-
-        # Calculate cosine similarity
-        similarity = torch.nn.functional.cosine_similarity(
-            image_features[0].unsqueeze(0), image_features[1].unsqueeze(0)
-        ).item()
-
-        logger.info(f'CLIP similarity score: {similarity}')
-
-        return similarity > 0.95  # Consider it a match if similarity > 95%
-    except Exception as e:
-        logger.error(f'Error in CLIP evaluation: {e}')
-        # Fallback to pixel comparison if CLIP fails
-        try:
-            post_image = Image.open(BytesIO(task['post_image']))
-            generated_img = Image.open(screenshot_path)
-
-            # Compare images directly without converting to bytes
-            diff = ImageChops.difference(generated_img, post_image)
-            logger.info(
-                f"Pixel difference analysis: {'No difference' if not diff.getbbox() else 'Differences found'}"
-            )
-            return not diff.getbbox()
-        except Exception as ex:
-            logger.error(f'Error in fallback evaluation: {ex}')
-            return False

frontend/__tests__/components/features/sidebar/sidebar.test.tsx

@@ -155,9 +155,7 @@ describe("Sidebar", () => {
       const settingsModal = screen.getByTestId("ai-config-modal");
 
       // Click the advanced options switch to show the API key input
-      const advancedOptionsSwitch = within(settingsModal).getByTestId(
-        "advanced-option-switch",
-      );
+      const advancedOptionsSwitch = within(settingsModal).getByTestId("advanced-option-switch");
       await user.click(advancedOptionsSwitch);
 
       const apiKeyInput = within(settingsModal).getByLabelText(/API\$KEY/i);

frontend/__tests__/components/upload-image-input.test.tsx

@@ -2,6 +2,13 @@ import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, describe, expect, it, vi } from "vitest";
 import { UploadImageInput } from "#/components/features/images/upload-image-input";
+import { toast } from "#/utils/toast";
+
+vi.mock("#/utils/toast", () => ({
+  toast: {
+    error: vi.fn(),
+  },
+}));
 
 describe("UploadImageInput", () => {
   const user = userEvent.setup();
@@ -41,17 +48,37 @@ describe("UploadImageInput", () => {
     expect(onUploadMock).toHaveBeenNthCalledWith(1, files);
   });
 
-  it("should not upload any file that is not an image", async () => {
+  it("should show error and not upload unsupported image types", async () => {
     render(<UploadImageInput onUpload={onUploadMock} />);
 
-    const file = new File(["(⌐□_□)"], "chucknorris.txt", {
-      type: "text/plain",
+    const file = new File(["(⌐□_□)"], "chucknorris.bmp", {
+      type: "image/bmp",
     });
     const input = screen.getByTestId("upload-image-input");
 
     await user.upload(input, file);
 
     expect(onUploadMock).not.toHaveBeenCalled();
+    expect(toast.error).toHaveBeenCalledWith(
+      expect.stringContaining("Only JPEG, PNG, GIF, and WebP images are supported")
+    );
+  });
+
+  it("should handle mix of supported and unsupported image types", async () => {
+    render(<UploadImageInput onUpload={onUploadMock} />);
+
+    const files = [
+      new File(["(⌐□_□)"], "valid.png", { type: "image/png" }),
+      new File(["(⌐□_□)"], "invalid.bmp", { type: "image/bmp" }),
+    ];
+    const input = screen.getByTestId("upload-image-input");
+
+    await user.upload(input, files);
+
+    expect(onUploadMock).toHaveBeenCalledWith([files[0]]);
+    expect(toast.error).toHaveBeenCalledWith(
+      expect.stringContaining("Only JPEG, PNG, GIF, and WebP images are supported")
+    );
   });
 
   it("should render custom labels", () => {

frontend/__tests__/initial-query.test.tsx

@@ -1,20 +1,20 @@
 import { describe, it, expect } from "vitest";
 import store from "../src/store";
 import {
-  setInitialPrompt,
-  clearInitialPrompt,
+  setInitialQuery,
+  clearInitialQuery,
 } from "../src/state/initial-query-slice";
 
 describe("Initial Query Behavior", () => {
-  it("should clear initial query when clearInitialPrompt is dispatched", () => {
+  it("should clear initial query when clearInitialQuery is dispatched", () => {
     // Set up initial query in the store
-    store.dispatch(setInitialPrompt("test query"));
-    expect(store.getState().initialQuery.initialPrompt).toBe("test query");
+    store.dispatch(setInitialQuery("test query"));
+    expect(store.getState().initialQuery.initialQuery).toBe("test query");
 
     // Clear the initial query
-    store.dispatch(clearInitialPrompt());
+    store.dispatch(clearInitialQuery());
 
     // Verify initial query is cleared
-    expect(store.getState().initialQuery.initialPrompt).toBeNull();
+    expect(store.getState().initialQuery.initialQuery).toBeNull();
   });
 });

frontend/__tests__/utils/validate-image-type.test.ts

@@ -0,0 +1,46 @@
+import { validateImageType, getValidImageFiles } from '#/utils/validate-image-type';
+import { describe, expect, it } from 'vitest';
+
+describe('validateImageType', () => {
+  it('should accept supported image types', () => {
+    const supportedTypes = ['image/jpeg', 'image/png', 'image/gif', 'image/webp'];
+    supportedTypes.forEach((type) => {
+      const file = new File([''], 'test.jpg', { type });
+      expect(validateImageType(file)).toBe(true);
+    });
+  });
+
+  it('should reject unsupported image types', () => {
+    const unsupportedTypes = ['image/bmp', 'image/tiff', 'application/pdf', 'text/plain'];
+    unsupportedTypes.forEach((type) => {
+      const file = new File([''], 'test.jpg', { type });
+      expect(validateImageType(file)).toBe(false);
+    });
+  });
+});
+
+describe('getValidImageFiles', () => {
+  it('should separate valid and invalid files', () => {
+    const files = [
+      new File([''], 'test1.jpg', { type: 'image/jpeg' }),
+      new File([''], 'test2.bmp', { type: 'image/bmp' }),
+      new File([''], 'test3.png', { type: 'image/png' }),
+      new File([''], 'test4.pdf', { type: 'application/pdf' }),
+    ];
+
+    const { validFiles, invalidFiles } = getValidImageFiles(files);
+
+    expect(validFiles).toHaveLength(2);
+    expect(invalidFiles).toHaveLength(2);
+    expect(validFiles[0].type).toBe('image/jpeg');
+    expect(validFiles[1].type).toBe('image/png');
+    expect(invalidFiles[0].type).toBe('image/bmp');
+    expect(invalidFiles[1].type).toBe('application/pdf');
+  });
+
+  it('should handle empty array', () => {
+    const { validFiles, invalidFiles } = getValidImageFiles([]);
+    expect(validFiles).toHaveLength(0);
+    expect(invalidFiles).toHaveLength(0);
+  });
+});

frontend/package-lock.json

@@ -105,7 +105,6 @@
       "version": "5.2.0",
       "resolved": "https://registry.npmjs.org/@alloc/quick-lru/-/quick-lru-5.2.0.tgz",
       "integrity": "sha512-UrcABB+4bUrFABwbluTIBErXwvbsU/V7TZWfmbgJfbkwiBuziS9gxdODUyuiecfdGQ85jglMW6juS3+z5TsKLw==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=10"
@@ -1594,7 +1593,6 @@
       "version": "8.0.2",
       "resolved": "https://registry.npmjs.org/@isaacs/cliui/-/cliui-8.0.2.tgz",
       "integrity": "sha512-O8jcjabXaleOG9DQ0+ARXWZBTfnP4WNAqzuiJK7ll44AmxGKv/J2M4TPjxjY3znBCfvBXFzucm1twdyFybFqEA==",
-      "dev": true,
       "license": "ISC",
       "dependencies": {
         "string-width": "^5.1.2",
@@ -1612,7 +1610,6 @@
       "version": "6.1.0",
       "resolved": "https://registry.npmjs.org/ansi-regex/-/ansi-regex-6.1.0.tgz",
       "integrity": "sha512-7HSX4QQb4CspciLpVFwyRe79O3xsIZDDLER21kERQ71oaPodF8jL725AgJMFAYbooIqolJoRLuM81SpeUkpkvA==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=12"
@@ -1625,7 +1622,6 @@
       "version": "7.1.0",
       "resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-7.1.0.tgz",
       "integrity": "sha512-iq6eVVI64nQQTRYq2KtEg2d2uU7LElhTJwsH4YzIHZshxlgZms/wIc4VoDQTlG/IvVIrBKG06CrZnp0qv7hkcQ==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "ansi-regex": "^6.0.1"
@@ -3408,7 +3404,6 @@
       "version": "2.1.5",
       "resolved": "https://registry.npmjs.org/@nodelib/fs.scandir/-/fs.scandir-2.1.5.tgz",
       "integrity": "sha512-vq24Bq3ym5HEQm2NKCr3yXDwjc7vTsEThRDnkp2DK9p1uqLR+DHurm/NOTo0KG7HYHU7eppKZj3MyqYuMBf62g==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "@nodelib/fs.stat": "2.0.5",
@@ -3422,7 +3417,6 @@
       "version": "2.0.5",
       "resolved": "https://registry.npmjs.org/@nodelib/fs.stat/-/fs.stat-2.0.5.tgz",
       "integrity": "sha512-RkhPPp2zrqDAQA/2jNhnztcPAlv64XdhIp7a7454A5ovI7Bukxgt7MX7udwAu3zg1DcpPU0rz3VV1SeaqvY4+A==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">= 8"
@@ -3432,7 +3426,6 @@
       "version": "1.2.8",
       "resolved": "https://registry.npmjs.org/@nodelib/fs.walk/-/fs.walk-1.2.8.tgz",
       "integrity": "sha512-oGB+UxlgWcgQkgwo8GcEGwemoTFt3FIO9ababBmaGwXIoBKZ+GTy0pP185beGg7Llih/NSHSV2XAs1lnznocSg==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "@nodelib/fs.scandir": "2.1.5",
@@ -3533,7 +3526,6 @@
       "version": "0.11.0",
       "resolved": "https://registry.npmjs.org/@pkgjs/parseargs/-/parseargs-0.11.0.tgz",
       "integrity": "sha512-+1VkjdD0QBLPodGrJUeqarH8VAIvQODIbwh9XpP5Syisf7YoQgsJKPNFoqqLQlu+VQ/tVSshMR6loPMn8U+dPg==",
-      "dev": true,
       "license": "MIT",
       "optional": true,
       "engines": {
@@ -5764,7 +5756,7 @@
       "version": "22.10.7",
       "resolved": "https://registry.npmjs.org/@types/node/-/node-22.10.7.tgz",
       "integrity": "sha512-V09KvXxFiutGp6B7XkpaDXlNadZxrzajcY50EuoLIpQ6WWYCSvf19lVIazzfIzQvhUN2HjX12spLojTnhuKlGg==",
-      "dev": true,
+      "devOptional": true,
       "dependencies": {
         "undici-types": "~6.20.0"
       }
@@ -5773,7 +5765,6 @@
       "version": "19.0.7",
       "resolved": "https://registry.npmjs.org/@types/react/-/react-19.0.7.tgz",
       "integrity": "sha512-MoFsEJKkAtZCrC1r6CM8U22GzhG7u2Wir8ons/aCKH6MBdD1ibV24zOSSkdZVUKqN5i396zG5VKLYZ3yaUZdLA==",
-      "dev": true,
       "dependencies": {
         "csstype": "^3.0.2"
       }
@@ -6462,7 +6453,6 @@
       "version": "5.0.1",
       "resolved": "https://registry.npmjs.org/ansi-regex/-/ansi-regex-5.0.1.tgz",
       "integrity": "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=8"
@@ -6472,7 +6462,6 @@
       "version": "4.3.0",
       "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-4.3.0.tgz",
       "integrity": "sha512-zbB9rCJAT1rbjiVDb2hqKFHNYLxgtk8NURxZ3IZwD3F6NtxbXZQCnnSi1Lkx+IDohdPlFp222wVALIheZJQSEg==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "color-convert": "^2.0.1"
@@ -6488,14 +6477,12 @@
       "version": "1.3.0",
       "resolved": "https://registry.npmjs.org/any-promise/-/any-promise-1.3.0.tgz",
       "integrity": "sha512-7UvmKalWRt1wgjL1RrGxoSJW/0QZFIegpeGvZG9kjp8vrRu55XTHbwnqq2GpXm9uLbcuhxm3IqX9OB4MZR1b2A==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/anymatch": {
       "version": "3.1.3",
       "resolved": "https://registry.npmjs.org/anymatch/-/anymatch-3.1.3.tgz",
       "integrity": "sha512-KMReFUr0B4t+D+OBkjR3KYqvocp2XaSzO55UcB6mgQMd3KbcE+mWTyvVV7D/zsdEbNnV6acZUutkiHQXvTr1Rw==",
-      "dev": true,
       "license": "ISC",
       "dependencies": {
         "normalize-path": "^3.0.0",
@@ -6509,7 +6496,6 @@
       "version": "5.0.2",
       "resolved": "https://registry.npmjs.org/arg/-/arg-5.0.2.tgz",
       "integrity": "sha512-PYjyFOLKQ9y57JvQ6QLo8dAgNqswh8M1RMJYdQduT6xbWSgK36P/Z/v+p888pM69jMMfS8Xd8F6I1kQ/I9HUGg==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/argparse": {
@@ -6835,7 +6821,6 @@
       "version": "1.0.2",
       "resolved": "https://registry.npmjs.org/balanced-match/-/balanced-match-1.0.2.tgz",
       "integrity": "sha512-3oSeUO0TMV67hN1AmbXsK4yaqU7tjiHlbxRDZOpH0KW9+CeX4bRAaX0Anxt0tx2MrpRpWwQaPwIlISEJhYU5Pw==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/basic-auth": {
@@ -6860,7 +6845,6 @@
       "version": "2.3.0",
       "resolved": "https://registry.npmjs.org/binary-extensions/-/binary-extensions-2.3.0.tgz",
       "integrity": "sha512-Ceh+7ox5qe7LJuLHoY0feh3pHuUDHAcRUeyL2VYghZwfpkNIy/+8Ocg0a3UuSoYzavmylwuLWQOf3hl0jjMMIw==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=8"
@@ -6909,7 +6893,6 @@
       "version": "2.0.1",
       "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
       "integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "balanced-match": "^1.0.0"
@@ -6919,7 +6902,6 @@
       "version": "3.0.3",
       "resolved": "https://registry.npmjs.org/braces/-/braces-3.0.3.tgz",
       "integrity": "sha512-yQbXgO/OSZVD2IsiLlro+7Hf6Q18EJrKSEsdoMzKePKXct3gvD8oLcOQdIzGupr5Fj+EDe8gO/lxc1BzfMpxvA==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "fill-range": "^7.1.1"
@@ -7070,7 +7052,6 @@
       "version": "2.0.1",
       "resolved": "https://registry.npmjs.org/camelcase-css/-/camelcase-css-2.0.1.tgz",
       "integrity": "sha512-QOSvevhslijgYwRx6Rv7zKdMF8lbRmx+uQGx2+vDc+KI/eBnsy9kit5aj23AgGu3pa4t9AgwbnXWqS+iOY+2aA==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">= 6"
@@ -7646,7 +7627,6 @@
       "version": "7.0.6",
       "resolved": "https://registry.npmjs.org/cross-spawn/-/cross-spawn-7.0.6.tgz",
       "integrity": "sha512-uV2QOWP2nWzsy2aMp8aRibhi9dlzF5Hgh5SHaB9OiTGEyDTiJJyx0uy51QXdyWbtAHNua4XJzUKca3OzKUd3vA==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "path-key": "^3.1.0",
@@ -7661,7 +7641,6 @@
       "version": "2.0.2",
       "resolved": "https://registry.npmjs.org/which/-/which-2.0.2.tgz",
       "integrity": "sha512-BLI3Tl1TW3Pvl70l3yq3Y64i+awpwXqsGBYWkkqMtnbXgrMD+yj7rhW0kuEDxzJaYXGjEW5ogapKNMEKNMjibA==",
-      "dev": true,
       "license": "ISC",
       "dependencies": {
         "isexe": "^2.0.0"
@@ -7684,7 +7663,6 @@
       "version": "3.0.0",
       "resolved": "https://registry.npmjs.org/cssesc/-/cssesc-3.0.0.tgz",
       "integrity": "sha512-/Tb/JcjK111nNScGob5MNtsntNM1aCNUDipB/TkwZFhyDrrE47SOx/18wF2bbjgc3ZzCSKW1T5nt5EbFoAz/Vg==",
-      "dev": true,
       "license": "MIT",
       "bin": {
         "cssesc": "bin/cssesc"
@@ -7951,7 +7929,6 @@
       "version": "1.2.2",
       "resolved": "https://registry.npmjs.org/didyoumean/-/didyoumean-1.2.2.tgz",
       "integrity": "sha512-gxtyfqMg7GKyhQmb056K7M3xszy/myH8w+B4RT+QXBQsvAOdc3XymqDDPHx1BgPgsdAA5SIifona89YtRATDzw==",
-      "dev": true,
       "license": "Apache-2.0"
     },
     "node_modules/dir-glob": {
@@ -7971,7 +7948,6 @@
       "version": "1.1.3",
       "resolved": "https://registry.npmjs.org/dlv/-/dlv-1.1.3.tgz",
       "integrity": "sha512-+HlytyjlPKnIG8XuRG8WvmBP8xs8P71y+SKKS6ZXWoEgLuePxtDoUEiH7WkdePWrQ5JBpE6aoVqfZfJUQkjXwA==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/doctrine": {
@@ -8036,7 +8012,6 @@
       "version": "0.2.0",
       "resolved": "https://registry.npmjs.org/eastasianwidth/-/eastasianwidth-0.2.0.tgz",
       "integrity": "sha512-I88TYZWc9XiYHRQ4/3c5rjjfgkjhLyW2luGIheGERbNQ6OY7yTybanSpDXZa8y7VUP9YmDcYa+eyq4ca7iLqWA==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/ee-first": {
@@ -8055,7 +8030,6 @@
       "version": "9.2.2",
       "resolved": "https://registry.npmjs.org/emoji-regex/-/emoji-regex-9.2.2.tgz",
       "integrity": "sha512-L18DaJsXSUk2+42pv8mLs5jJT2hqFkFE4j21wOmgbUqsZ2hL72NsUU785g9RXgo3s0ZNgVl42TiHp3ZtOv/Vyg==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/encodeurl": {
@@ -9212,7 +9186,6 @@
       "version": "3.3.2",
       "resolved": "https://registry.npmjs.org/fast-glob/-/fast-glob-3.3.2.tgz",
       "integrity": "sha512-oX2ruAFQwf/Orj8m737Y5adxDQO0LAB7/S5MnxCdTNDd4p6BsyIVsv9JQsATbTSq8KHRpLwIHbVlUNatxd+1Ow==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "@nodelib/fs.stat": "^2.0.2",
@@ -9229,7 +9202,6 @@
       "version": "5.1.2",
       "resolved": "https://registry.npmjs.org/glob-parent/-/glob-parent-5.1.2.tgz",
       "integrity": "sha512-AOIgSQCepiJYwP3ARnGx+5VnTu2HBYdzbGP45eLw1vr3zB3vZLeyed1sC9hnbcOc9/SrMyM5RPQrkGz4aS9Zow==",
-      "dev": true,
       "license": "ISC",
       "dependencies": {
         "is-glob": "^4.0.1"
@@ -9256,7 +9228,6 @@
       "version": "1.18.0",
       "resolved": "https://registry.npmjs.org/fastq/-/fastq-1.18.0.tgz",
       "integrity": "sha512-QKHXPW0hD8g4UET03SdOdunzSouc9N4AuHdsX8XNcTsuz+yYFILVNIX4l9yHABMhiEI9Db0JTTIpu0wB+Y1QQw==",
-      "dev": true,
       "license": "ISC",
       "dependencies": {
         "reusify": "^1.0.4"
@@ -9298,7 +9269,6 @@
       "version": "7.1.1",
       "resolved": "https://registry.npmjs.org/fill-range/-/fill-range-7.1.1.tgz",
       "integrity": "sha512-YsGpe3WHLK8ZYi4tWDg2Jy3ebRz2rXowDxnld4bkQB00cc/1Zw9AWnC0i9ztDJitivtQvaI9KaLyKrc+hBW0yg==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "to-regex-range": "^5.0.1"
@@ -9418,7 +9388,6 @@
       "version": "3.3.0",
       "resolved": "https://registry.npmjs.org/foreground-child/-/foreground-child-3.3.0.tgz",
       "integrity": "sha512-Ld2g8rrAyMYFXBhEqMz8ZAHBi4J4uS1i/CxGMDnjyFWddMXLVcDp051DZfu+t7+ab7Wv6SMqpWmyFIj5UbfFvg==",
-      "dev": true,
       "license": "ISC",
       "dependencies": {
         "cross-spawn": "^7.0.0",
@@ -9689,7 +9658,6 @@
       "version": "10.4.5",
       "resolved": "https://registry.npmjs.org/glob/-/glob-10.4.5.tgz",
       "integrity": "sha512-7Bv8RF0k6xjo7d4A/PxYLbUCfb6c+Vpd2/mB2yRDlew7Jb5hEXiCD9ibfO7wpk8i4sevK6DFny9h7EYbM3/sHg==",
-      "dev": true,
       "license": "ISC",
       "dependencies": {
         "foreground-child": "^3.1.0",
@@ -9710,7 +9678,6 @@
       "version": "6.0.2",
       "resolved": "https://registry.npmjs.org/glob-parent/-/glob-parent-6.0.2.tgz",
       "integrity": "sha512-XxwI8EOhVQgWp6iDL+3b0r86f4d6AX6zSU55HfB4ydCEuXLXc5FcYeOu+nnGftS4TEju/11rt4KJPTMgbfmv4A==",
-      "dev": true,
       "license": "ISC",
       "dependencies": {
         "is-glob": "^4.0.3"
@@ -10462,7 +10429,6 @@
       "version": "2.1.0",
       "resolved": "https://registry.npmjs.org/is-binary-path/-/is-binary-path-2.1.0.tgz",
       "integrity": "sha512-ZMERYes6pDydyuGidse7OsHxtbI7WVeUEozgR/g7rd0xUimYNlvZRE/K2MgZTjWy725IfelLeVcEM97mmtRGXw==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "binary-extensions": "^2.0.0"
@@ -10505,7 +10471,6 @@
       "version": "2.16.1",
       "resolved": "https://registry.npmjs.org/is-core-module/-/is-core-module-2.16.1.tgz",
       "integrity": "sha512-UfoeMA6fIJ8wTYFEUjelnaGI67v6+N7qXJEvQuIGa99l4xsCruSYOVSQ0uPANn4dAzm8lkYPaKLrrijLq7x23w==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "hasown": "^2.0.2"
@@ -10573,7 +10538,6 @@
       "version": "2.1.1",
       "resolved": "https://registry.npmjs.org/is-extglob/-/is-extglob-2.1.1.tgz",
       "integrity": "sha512-SbKbANkN603Vi4jEZv49LeVJMn4yGwsbzZworEoyEiutsN3nJYdbO36zfhGJ6QEDpOZIFkDtnq5JRxmvl3jsoQ==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=0.10.0"
@@ -10628,7 +10592,6 @@
       "version": "4.0.3",
       "resolved": "https://registry.npmjs.org/is-glob/-/is-glob-4.0.3.tgz",
       "integrity": "sha512-xelSayHH36ZgE7ZWhli7pW34hNbNl8Ojv5KVmkJD4hBdD3th8Tfk9vYasLM+mXWOZhFkgZfxhLSnrwRr4elSSg==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "is-extglob": "^2.1.1"
@@ -10681,7 +10644,6 @@
       "version": "7.0.0",
       "resolved": "https://registry.npmjs.org/is-number/-/is-number-7.0.0.tgz",
       "integrity": "sha512-41Cifkg6e8TylSpdtTpeLVMqvSBEVzTttHvERD741+pnZ8ANv0004MRL43QKPDlK9cGvNp6NZWZUBlbGXYxxng==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=0.12.0"
@@ -10910,7 +10872,6 @@
       "version": "2.0.0",
       "resolved": "https://registry.npmjs.org/isexe/-/isexe-2.0.0.tgz",
       "integrity": "sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw==",
-      "dev": true,
       "license": "ISC"
     },
     "node_modules/istanbul-lib-coverage": {
@@ -10989,7 +10950,6 @@
       "version": "3.4.3",
       "resolved": "https://registry.npmjs.org/jackspeak/-/jackspeak-3.4.3.tgz",
       "integrity": "sha512-OGlZQpz2yfahA/Rd1Y8Cd9SIEsqvXkLVoSw/cgwhnhFMDbsQFeZYoJJ7bIZBS9BcamUW96asq/npPWugM+RQBw==",
-      "dev": true,
       "license": "BlueOak-1.0.0",
       "dependencies": {
         "@isaacs/cliui": "^8.0.2"
@@ -11005,7 +10965,6 @@
       "version": "1.21.7",
       "resolved": "https://registry.npmjs.org/jiti/-/jiti-1.21.7.tgz",
       "integrity": "sha512-/imKNG4EbWNrVjoNC/1H5/9GFy+tqjGBHCaSsN+P2RnPqjsLmv6UD3Ej+Kj8nBWaRAwyk7kK5ZUc+OEatnTR3A==",
-      "dev": true,
       "license": "MIT",
       "bin": {
         "jiti": "bin/jiti.js"
@@ -11220,7 +11179,6 @@
       "version": "3.1.3",
       "resolved": "https://registry.npmjs.org/lilconfig/-/lilconfig-3.1.3.tgz",
       "integrity": "sha512-/vlFKAoH5Cgt3Ie+JLhRbwOsCQePABiU3tJ1egGvyQ+33R/vcwM2Zl2QR/LzjsBeItPt3oSVXapn+m4nQDvpzw==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=14"
@@ -11233,7 +11191,6 @@
       "version": "1.2.4",
       "resolved": "https://registry.npmjs.org/lines-and-columns/-/lines-and-columns-1.2.4.tgz",
       "integrity": "sha512-7ylylesZQ/PV29jhEDl3Ufjo6ZX7gCqJr5F7PKrqc93v7fzSymt1BpwEU8nAUXs8qzzvqhbjhK5QZg6Mt/HkBg==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/lint-staged": {
@@ -12008,7 +11965,6 @@
       "version": "1.4.1",
       "resolved": "https://registry.npmjs.org/merge2/-/merge2-1.4.1.tgz",
       "integrity": "sha512-8q7VEgMJW4J8tcfVPy8g09NcQwZdbwFEqhe/WZkoIzjn/3TGDwtOCYtXGxA3O8tPzpczCCDgv+P2P5y00ZJOOg==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">= 8"
@@ -12589,7 +12545,6 @@
       "version": "4.0.8",
       "resolved": "https://registry.npmjs.org/micromatch/-/micromatch-4.0.8.tgz",
       "integrity": "sha512-PXwfBhYu0hBCPw8Dn0E+WDYb7af3dSLVWKi3HGv84IdF4TyFoC0ysxFd0Goxw7nSv4T/PzEJQxsYsEiFCKo2BA==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "braces": "^3.0.3",
@@ -12680,7 +12635,6 @@
       "version": "9.0.5",
       "resolved": "https://registry.npmjs.org/minimatch/-/minimatch-9.0.5.tgz",
       "integrity": "sha512-G6T0ZX48xgozx7587koeX9Ys2NYy6Gmv//P89sEte9V9whIapMNF4idKxnW2QtCcLiTWlb/wfCabAtAFWhhBow==",
-      "dev": true,
       "license": "ISC",
       "dependencies": {
         "brace-expansion": "^2.0.1"
@@ -12706,7 +12660,6 @@
       "version": "7.1.2",
       "resolved": "https://registry.npmjs.org/minipass/-/minipass-7.1.2.tgz",
       "integrity": "sha512-qOOzS1cBTWYF4BH8fVePDBOO9iptMnGUEZwNc/cMWnTV2nVLZ7VoNWEPHkYczZA0pdoA7dl6e7FL659nX9S2aw==",
-      "dev": true,
       "license": "ISC",
       "engines": {
         "node": ">=16 || 14 >=14.17"
@@ -12866,7 +12819,6 @@
       "version": "2.7.0",
       "resolved": "https://registry.npmjs.org/mz/-/mz-2.7.0.tgz",
       "integrity": "sha512-z81GNO7nnYMEhrGh9LeymoE4+Yr0Wn5McHIZMK5cfQCl+NDX08sCZgUc9/6MHni9IWuFLm1Z3HTCXu2z9fN62Q==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "any-promise": "^1.0.0",
@@ -12987,7 +12939,6 @@
       "version": "3.0.0",
       "resolved": "https://registry.npmjs.org/normalize-path/-/normalize-path-3.0.0.tgz",
       "integrity": "sha512-6eZs5Ls3WtCisHWp9S2GUy8dqkpGi4BVSz3GaqiE6ezub0512ESztXUwUB6C6IKbQkY2Pnb/mD4WYojCRwcwLA==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=0.10.0"
@@ -13098,7 +13049,6 @@
       "version": "4.1.1",
       "resolved": "https://registry.npmjs.org/object-assign/-/object-assign-4.1.1.tgz",
       "integrity": "sha512-rJgTQnkUnH1sFw8yT6VSU3zD3sWmu6sZhIseY8VX+GRu3P6F7Fu+JNDoXfklElbLJSnc3FUQHVe4cU5hj+BcUg==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=0.10.0"
@@ -13108,7 +13058,6 @@
       "version": "3.0.0",
       "resolved": "https://registry.npmjs.org/object-hash/-/object-hash-3.0.0.tgz",
       "integrity": "sha512-RSn9F68PjH9HqtltsSnqYC1XXoWe9Bju5+213R98cNGttag9q9yAOTzdbsqvIa7aNm5WffBZFpWYr2aWrklWAw==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">= 6"
@@ -13350,7 +13299,6 @@
       "version": "1.0.1",
       "resolved": "https://registry.npmjs.org/package-json-from-dist/-/package-json-from-dist-1.0.1.tgz",
       "integrity": "sha512-UEZIS3/by4OC8vL3P2dTXRETpebLI2NiI5vIrjaD/5UtrkFX/tNbwjTSRAGC/+7CAo2pIcBaRgWmcBBHcsaCIw==",
-      "dev": true,
       "license": "BlueOak-1.0.0"
     },
     "node_modules/pako": {
@@ -13469,7 +13417,6 @@
       "version": "3.1.1",
       "resolved": "https://registry.npmjs.org/path-key/-/path-key-3.1.1.tgz",
       "integrity": "sha512-ojmeN0qd+y0jszEtoY48r0Peq5dwMEkIlCOu6Q5f41lfkswXuKtYrhgoTpLnyIcHm24Uhqx+5Tqm2InSwLhE6Q==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=8"
@@ -13479,14 +13426,12 @@
       "version": "1.0.7",
       "resolved": "https://registry.npmjs.org/path-parse/-/path-parse-1.0.7.tgz",
       "integrity": "sha512-LDJzPVEEEPR+y48z93A0Ed0yXb8pAByGWo/k5YYdYgpY2/2EsOsksJrq7lOHxryrVOn1ejG6oAp8ahvOIQD8sw==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/path-scurry": {
       "version": "1.11.1",
       "resolved": "https://registry.npmjs.org/path-scurry/-/path-scurry-1.11.1.tgz",
       "integrity": "sha512-Xa4Nw17FS9ApQFJ9umLiJS4orGjm7ZzwUrwamcGQuHSzDyth9boKDaycYdDcZDuqYATXw4HFXgaqWTctW/v1HA==",
-      "dev": true,
       "license": "BlueOak-1.0.0",
       "dependencies": {
         "lru-cache": "^10.2.0",
@@ -13503,7 +13448,6 @@
       "version": "10.4.3",
       "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-10.4.3.tgz",
       "integrity": "sha512-JNAzZcXrCt42VGLuYz0zfAzDfAvJWW6AfYlDBQyDV5DClI2m5sAmK+OIO7s59XfsRsWHp02jAJrRadPRGTt6SQ==",
-      "dev": true,
       "license": "ISC"
     },
     "node_modules/path-to-regexp": {
@@ -13559,7 +13503,6 @@
       "version": "2.3.1",
       "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-2.3.1.tgz",
       "integrity": "sha512-JU3teHTNjmE2VCGFzuY8EXzCDVwEqB2a8fsIvwaStHhAWJEeVd1o1QD80CU6+ZdEXXSLbSsuLwJjkCBWqRQUVA==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=8.6"
@@ -13585,7 +13528,6 @@
       "version": "2.3.0",
       "resolved": "https://registry.npmjs.org/pify/-/pify-2.3.0.tgz",
       "integrity": "sha512-udgsAY+fTnvv7kI7aaxbqwWNb0AHiB0qBO89PZKPkoTmGOgdbrHDKD+0B2X4uTfJ/FT1R09r9gTsjUjNJotuog==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=0.10.0"
@@ -13595,7 +13537,6 @@
       "version": "4.0.6",
       "resolved": "https://registry.npmjs.org/pirates/-/pirates-4.0.6.tgz",
       "integrity": "sha512-saLsH7WeYYPiD25LDuLRRY/i+6HaPYr6G1OUlN39otzkSTxKnubR9RTxS3/Kk50s1g2JTgFwWQDQyplC5/SHZg==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">= 6"
@@ -13674,7 +13615,6 @@
       "version": "15.1.0",
       "resolved": "https://registry.npmjs.org/postcss-import/-/postcss-import-15.1.0.tgz",
       "integrity": "sha512-hpr+J05B2FVYUAXHeK1YyI267J/dDDhMU6B6civm8hSY1jYJnBXxzKDKDswzJmtLHryrjhnDjqqp/49t8FALew==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "postcss-value-parser": "^4.0.0",
@@ -13692,7 +13632,6 @@
       "version": "4.0.1",
       "resolved": "https://registry.npmjs.org/postcss-js/-/postcss-js-4.0.1.tgz",
       "integrity": "sha512-dDLF8pEO191hJMtlHFPRa8xsizHaM82MLfNkUHdUtVEV3tgTp5oj+8qbEqYM57SLfc74KSbw//4SeJma2LRVIw==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "camelcase-css": "^2.0.1"
@@ -13712,7 +13651,6 @@
       "version": "4.0.2",
       "resolved": "https://registry.npmjs.org/postcss-load-config/-/postcss-load-config-4.0.2.tgz",
       "integrity": "sha512-bSVhyJGL00wMVoPUzAVAnbEoWyqRxkjv64tUl427SKnPrENtq6hJwUojroMz2VB+Q1edmi4IfrAPpami5VVgMQ==",
-      "dev": true,
       "funding": [
         {
           "type": "opencollective",
@@ -13748,7 +13686,6 @@
       "version": "6.2.0",
       "resolved": "https://registry.npmjs.org/postcss-nested/-/postcss-nested-6.2.0.tgz",
       "integrity": "sha512-HQbt28KulC5AJzG+cZtj9kvKB93CFCdLvog1WFLf1D+xmMvPGlBstkpTEZfK5+AN9hfJocyBFCNiqyS48bpgzQ==",
-      "dev": true,
       "funding": [
         {
           "type": "opencollective",
@@ -13774,7 +13711,6 @@
       "version": "6.1.2",
       "resolved": "https://registry.npmjs.org/postcss-selector-parser/-/postcss-selector-parser-6.1.2.tgz",
       "integrity": "sha512-Q8qQfPiZ+THO/3ZrOrO0cJJKfpYCagtMUkXbnEfmgUjwXg6z/WBeOyS9APBBPCTSiDV+s4SwQGu8yFsiMRIudg==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "cssesc": "^3.0.0",
@@ -13802,7 +13738,6 @@
       "version": "4.2.0",
       "resolved": "https://registry.npmjs.org/postcss-value-parser/-/postcss-value-parser-4.2.0.tgz",
       "integrity": "sha512-1NNCs6uurfkVbeXG4S8JFT9t19m45ICnif8zWLd5oPSZ50QnwMfK+H3jv408d4jw/7Bttv5axS5IiHoLaVNHeQ==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/posthog-js": {
@@ -14064,7 +13999,6 @@
       "version": "1.2.3",
       "resolved": "https://registry.npmjs.org/queue-microtask/-/queue-microtask-1.2.3.tgz",
       "integrity": "sha512-NuaNSa6flKT5JaSYQzJok04JzTL1CA6aGhv5rfLW3PgqA+M2ChpZQnAC8h8i4ZFkBS8X5RqkDBHA7r4hej3K9A==",
-      "dev": true,
       "funding": [
         {
           "type": "github",
@@ -14313,7 +14247,6 @@
       "version": "1.0.0",
       "resolved": "https://registry.npmjs.org/read-cache/-/read-cache-1.0.0.tgz",
       "integrity": "sha512-Owdv/Ft7IjOgm/i0xvNDZ1LrRANRfew4b2prF3OWMQLxLfu3bS8FVhCsrSCMK4lR56Y9ya+AThoTpDCTxCmpRA==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "pify": "^2.3.0"
@@ -14642,7 +14575,6 @@
       "version": "1.22.10",
       "resolved": "https://registry.npmjs.org/resolve/-/resolve-1.22.10.tgz",
       "integrity": "sha512-NPRy+/ncIMeDlTAsuqwKIiferiawhefFJtkNSW0qZJEqMEb+qBt/77B/jGeeek+F0uOeN05CDa6HXbbIgtVX4w==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "is-core-module": "^2.16.0",
@@ -14716,7 +14648,6 @@
       "version": "1.0.4",
       "resolved": "https://registry.npmjs.org/reusify/-/reusify-1.0.4.tgz",
       "integrity": "sha512-U9nH88a3fc/ekCF1l0/UP1IosiuIjyTh7hBvXVMHYgVcfGvt897Xguj2UOLDeI5BG2m7/uwyaLVT6fbtCwTyzw==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "iojs": ">=1.0.0",
@@ -14841,7 +14772,6 @@
       "version": "1.2.0",
       "resolved": "https://registry.npmjs.org/run-parallel/-/run-parallel-1.2.0.tgz",
       "integrity": "sha512-5l4VyZR86LZ/lDxZTR6jqL8AFE2S0IFLMP26AbjsLVADxHdhB/c0GUsH+y39UfCi3dzz8OlQuPmnaJOMoDHQBA==",
-      "dev": true,
       "funding": [
         {
           "type": "github",
@@ -15124,7 +15054,6 @@
       "version": "2.0.0",
       "resolved": "https://registry.npmjs.org/shebang-command/-/shebang-command-2.0.0.tgz",
       "integrity": "sha512-kHxr2zZpYtdmrN1qDjrrX/Z1rR1kG8Dx+gkpK1G4eXmvXswmcE1hTWBWYUzlraYw1/yZp6YuDY77YtvbN0dmDA==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "shebang-regex": "^3.0.0"
@@ -15137,7 +15066,6 @@
       "version": "3.0.0",
       "resolved": "https://registry.npmjs.org/shebang-regex/-/shebang-regex-3.0.0.tgz",
       "integrity": "sha512-7++dFhtcx3353uBaq8DDR4NuxBetBzC7ZQOhmTQInHEd6bSrXdiEyzCvG07Z44UYdLShWUyXt5M/yhz8ekcb1A==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=8"
@@ -15226,7 +15154,6 @@
       "version": "4.1.0",
       "resolved": "https://registry.npmjs.org/signal-exit/-/signal-exit-4.1.0.tgz",
       "integrity": "sha512-bzyZ1e88w9O1iNJbKnOlvYTrWPDl46O1bG0D3XInv+9tkPrxrN8jUUTiFlDkkmKWgn1M6CfIA13SuGqOa9Korw==",
-      "dev": true,
       "license": "ISC",
       "engines": {
         "node": ">=14"
@@ -15546,7 +15473,6 @@
       "version": "5.1.2",
       "resolved": "https://registry.npmjs.org/string-width/-/string-width-5.1.2.tgz",
       "integrity": "sha512-HnLOCR3vjcY8beoNLtcjZ5/nxn2afmME6lhrDrebokqMap+XbeW8n9TXpPDOqdGK5qcI3oT0GKTW6wC7EMiVqA==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "eastasianwidth": "^0.2.0",
@@ -15565,7 +15491,6 @@
       "version": "4.2.3",
       "resolved": "https://registry.npmjs.org/string-width/-/string-width-4.2.3.tgz",
       "integrity": "sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "emoji-regex": "^8.0.0",
@@ -15580,14 +15505,12 @@
       "version": "8.0.0",
       "resolved": "https://registry.npmjs.org/emoji-regex/-/emoji-regex-8.0.0.tgz",
       "integrity": "sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/string-width-cjs/node_modules/is-fullwidth-code-point": {
       "version": "3.0.0",
       "resolved": "https://registry.npmjs.org/is-fullwidth-code-point/-/is-fullwidth-code-point-3.0.0.tgz",
       "integrity": "sha512-zymm5+u+sCsSWyD9qNaejV3DFvhCKclKdizYaJUuHA83RLjb7nSuGnddCHGv0hk+KY7BMAlsWeK4Ueg6EV6XQg==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=8"
@@ -15597,7 +15520,6 @@
       "version": "6.1.0",
       "resolved": "https://registry.npmjs.org/ansi-regex/-/ansi-regex-6.1.0.tgz",
       "integrity": "sha512-7HSX4QQb4CspciLpVFwyRe79O3xsIZDDLER21kERQ71oaPodF8jL725AgJMFAYbooIqolJoRLuM81SpeUkpkvA==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=12"
@@ -15610,7 +15532,6 @@
       "version": "7.1.0",
       "resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-7.1.0.tgz",
       "integrity": "sha512-iq6eVVI64nQQTRYq2KtEg2d2uU7LElhTJwsH4YzIHZshxlgZms/wIc4VoDQTlG/IvVIrBKG06CrZnp0qv7hkcQ==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "ansi-regex": "^6.0.1"
@@ -15753,7 +15674,6 @@
       "version": "6.0.1",
       "resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-6.0.1.tgz",
       "integrity": "sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "ansi-regex": "^5.0.1"
@@ -15767,7 +15687,6 @@
       "version": "6.0.1",
       "resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-6.0.1.tgz",
       "integrity": "sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "ansi-regex": "^5.0.1"
@@ -15838,7 +15757,6 @@
       "version": "3.35.0",
       "resolved": "https://registry.npmjs.org/sucrase/-/sucrase-3.35.0.tgz",
       "integrity": "sha512-8EbVDiu9iN/nESwxeSxDKe0dunta1GOlHufmSSXxMD2z2/tMZpDMpvXQGsc+ajGo8y2uYUmixaSRUc/QPoQ0GA==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "@jridgewell/gen-mapping": "^0.3.2",
@@ -15861,7 +15779,6 @@
       "version": "4.1.1",
       "resolved": "https://registry.npmjs.org/commander/-/commander-4.1.1.tgz",
       "integrity": "sha512-NOKm8xhkzAjzFx8B2v5OAHT+u5pRQc2UCa2Vq9jYL/31o2wi9mxBA7LIFs3sV5VSC49z6pEhfbMULvShKj26WA==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">= 6"
@@ -15884,7 +15801,6 @@
       "version": "1.0.0",
       "resolved": "https://registry.npmjs.org/supports-preserve-symlinks-flag/-/supports-preserve-symlinks-flag-1.0.0.tgz",
       "integrity": "sha512-ot0WnXS9fgdkgIcePe6RHNk1WA8+muPa6cSjeR3V8K27q9BB1rTE3R1p7Hv0z1ZyAc8s6Vvv8DIyWf681MAt0w==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">= 0.4"
@@ -15962,7 +15878,6 @@
       "version": "3.4.17",
       "resolved": "https://registry.npmjs.org/tailwindcss/-/tailwindcss-3.4.17.tgz",
       "integrity": "sha512-w33E2aCvSDP0tW9RZuNXadXlkHXqFzSkQew/aIa2i/Sj8fThxwovwlXHSPXTbAHwEIhBFXAedUhP2tueAKP8Og==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "@alloc/quick-lru": "^5.2.0",
@@ -16000,7 +15915,6 @@
       "version": "3.6.0",
       "resolved": "https://registry.npmjs.org/chokidar/-/chokidar-3.6.0.tgz",
       "integrity": "sha512-7VT13fmjotKpGipCW9JEQAusEPE+Ei8nl6/g4FBAmIm0GOOLMua9NDDo/DWp0ZAxCr3cPq5ZpBqmPAQgDda2Pw==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "anymatch": "~3.1.2",
@@ -16025,7 +15939,6 @@
       "version": "5.1.2",
       "resolved": "https://registry.npmjs.org/glob-parent/-/glob-parent-5.1.2.tgz",
       "integrity": "sha512-AOIgSQCepiJYwP3ARnGx+5VnTu2HBYdzbGP45eLw1vr3zB3vZLeyed1sC9hnbcOc9/SrMyM5RPQrkGz4aS9Zow==",
-      "dev": true,
       "license": "ISC",
       "dependencies": {
         "is-glob": "^4.0.1"
@@ -16038,7 +15951,6 @@
       "version": "6.1.2",
       "resolved": "https://registry.npmjs.org/postcss-selector-parser/-/postcss-selector-parser-6.1.2.tgz",
       "integrity": "sha512-Q8qQfPiZ+THO/3ZrOrO0cJJKfpYCagtMUkXbnEfmgUjwXg6z/WBeOyS9APBBPCTSiDV+s4SwQGu8yFsiMRIudg==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "cssesc": "^3.0.0",
@@ -16052,7 +15964,6 @@
       "version": "3.6.0",
       "resolved": "https://registry.npmjs.org/readdirp/-/readdirp-3.6.0.tgz",
       "integrity": "sha512-hOS089on8RduqdbhvQ5Z37A0ESjsqz6qnRcffsMU3495FuTdqSm+7bhJ29JvIOsBDEEnan5DPu9t3To9VRlMzA==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "picomatch": "^2.2.1"
@@ -16086,7 +15997,6 @@
       "version": "3.3.1",
       "resolved": "https://registry.npmjs.org/thenify/-/thenify-3.3.1.tgz",
       "integrity": "sha512-RVZSIV5IG10Hk3enotrhvz0T9em6cyHBLkH/YAZuKqd8hRkKhSfCGIcP2KUY0EPxndzANBmNllzWPwak+bheSw==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "any-promise": "^1.0.0"
@@ -16096,7 +16006,6 @@
       "version": "1.6.0",
       "resolved": "https://registry.npmjs.org/thenify-all/-/thenify-all-1.6.0.tgz",
       "integrity": "sha512-RNxQH/qI8/t3thXJDwcstUO4zeqo64+Uy/+sNVRBx4Xn2OX+OZ9oP+iJnNFqplFra2ZUVeKCSa2oVWi3T4uVmA==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "thenify": ">= 3.1.0 < 4"
@@ -16189,7 +16098,6 @@
       "version": "5.0.1",
       "resolved": "https://registry.npmjs.org/to-regex-range/-/to-regex-range-5.0.1.tgz",
       "integrity": "sha512-65P7iz6X5yEr1cwcgvQxbbIw7Uk3gOy5dIdtZ4rDveLqhrdJP+Li/Hx6tyK0NEb+2GCyneCMJiGqrADCSNk8sQ==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "is-number": "^7.0.0"
@@ -16278,7 +16186,6 @@
       "version": "0.1.13",
       "resolved": "https://registry.npmjs.org/ts-interface-checker/-/ts-interface-checker-0.1.13.tgz",
       "integrity": "sha512-Y/arvbn+rrz3JCKl9C4kVNfTfSm2/mEp5FSz5EsZSANGPSlQrpRI5M4PKF+mJnE52jOO90PnPSc3Ur3bTQw0gA==",
-      "dev": true,
       "license": "Apache-2.0"
     },
     "node_modules/tsconfck": {
@@ -16460,7 +16367,7 @@
       "version": "5.7.3",
       "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.7.3.tgz",
       "integrity": "sha512-84MVSjMEHP+FQRPy3pX9sTVV/INIex71s9TL2Gm5FG/WG1SqXeKyZ0k7/blY/4FdOzI12CBy1vGc4og/eus0fw==",
-      "dev": true,
+      "devOptional": true,
       "bin": {
         "tsc": "bin/tsc",
         "tsserver": "bin/tsserver"
@@ -16501,7 +16408,7 @@
       "version": "6.20.0",
       "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-6.20.0.tgz",
       "integrity": "sha512-Ny6QZ2Nju20vw1SRHe3d9jVu6gJ+4e3+MMpqu7pqE5HT6WsTSlce++GQmK5UXS8mzV8DSYHrQH+Xrf2jVcuKNg==",
-      "dev": true,
+      "devOptional": true,
       "license": "MIT"
     },
     "node_modules/unified": {
@@ -16718,7 +16625,6 @@
       "version": "1.0.2",
       "resolved": "https://registry.npmjs.org/util-deprecate/-/util-deprecate-1.0.2.tgz",
       "integrity": "sha512-EPD5q1uXyFxJpCrLnCc1nHnq3gOa6DZBocAIiI2TaSCA7VCJ1UJDMagCzIkXNsUYfD1daK//LTEQ8xiIbrHtcw==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/utils-merge": {
@@ -17256,7 +17162,6 @@
       "version": "8.1.0",
       "resolved": "https://registry.npmjs.org/wrap-ansi/-/wrap-ansi-8.1.0.tgz",
       "integrity": "sha512-si7QWI6zUMq56bESFvagtmzMdGOtoxfR+Sez11Mobfc7tm+VkUckk9bW2UeffTGVUbOksxmSw0AA2gs8g71NCQ==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "ansi-styles": "^6.1.0",
@@ -17275,7 +17180,6 @@
       "version": "7.0.0",
       "resolved": "https://registry.npmjs.org/wrap-ansi/-/wrap-ansi-7.0.0.tgz",
       "integrity": "sha512-YVGIj2kamLSTxw6NsZjoBxfSwsn0ycdesmc4p+Q21c5zPuZ1pl+NfxVdxPtdHvmNVOQ6XSYG4AUtyt/Fi7D16Q==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "ansi-styles": "^4.0.0",
@@ -17293,14 +17197,12 @@
       "version": "8.0.0",
       "resolved": "https://registry.npmjs.org/emoji-regex/-/emoji-regex-8.0.0.tgz",
       "integrity": "sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/wrap-ansi-cjs/node_modules/is-fullwidth-code-point": {
       "version": "3.0.0",
       "resolved": "https://registry.npmjs.org/is-fullwidth-code-point/-/is-fullwidth-code-point-3.0.0.tgz",
       "integrity": "sha512-zymm5+u+sCsSWyD9qNaejV3DFvhCKclKdizYaJUuHA83RLjb7nSuGnddCHGv0hk+KY7BMAlsWeK4Ueg6EV6XQg==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=8"
@@ -17310,7 +17212,6 @@
       "version": "4.2.3",
       "resolved": "https://registry.npmjs.org/string-width/-/string-width-4.2.3.tgz",
       "integrity": "sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "emoji-regex": "^8.0.0",
@@ -17325,7 +17226,6 @@
       "version": "6.1.0",
       "resolved": "https://registry.npmjs.org/ansi-regex/-/ansi-regex-6.1.0.tgz",
       "integrity": "sha512-7HSX4QQb4CspciLpVFwyRe79O3xsIZDDLER21kERQ71oaPodF8jL725AgJMFAYbooIqolJoRLuM81SpeUkpkvA==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=12"
@@ -17338,7 +17238,6 @@
       "version": "6.2.1",
       "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-6.2.1.tgz",
       "integrity": "sha512-bN798gFfQX+viw3R7yrGWRqnrN2oRkEkUjjl4JNn4E8GxxbjtG3FbrEIIY3l8/hrwUwIeCZvi4QuOTP4MErVug==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=12"
@@ -17351,7 +17250,6 @@
       "version": "7.1.0",
       "resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-7.1.0.tgz",
       "integrity": "sha512-iq6eVVI64nQQTRYq2KtEg2d2uU7LElhTJwsH4YzIHZshxlgZms/wIc4VoDQTlG/IvVIrBKG06CrZnp0qv7hkcQ==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "ansi-regex": "^6.0.1"
@@ -17445,7 +17343,6 @@
       "version": "2.6.1",
       "resolved": "https://registry.npmjs.org/yaml/-/yaml-2.6.1.tgz",
       "integrity": "sha512-7r0XPzioN/Q9kXBro/XPnA6kznR73DHq+GXh5ON7ZozRO6aMjbmiBuKste2wslTFkC5d1dw0GooOCepZXJ2SAg==",
-      "dev": true,
       "license": "ISC",
       "bin": {
         "yaml": "bin.mjs"

frontend/src/api/open-hands.ts

@@ -244,14 +244,10 @@ class OpenHands {
   static async createConversation(
     githubToken?: string,
     selectedRepository?: string,
-    initialUserMsg?: string,
-    imageUrls?: string[],
   ): Promise<Conversation> {
     const body = {
       github_token: githubToken,
       selected_repository: selectedRepository,
-      initial_user_msg: initialUserMsg,
-      image_urls: imageUrls,
     };
 
     const { data } = await openHands.post<Conversation>(

frontend/src/components/agent-status-map.constant.ts

@@ -23,7 +23,7 @@ export const AGENT_STATUS_MAP: {
   },
   [AgentState.AWAITING_USER_INPUT]: {
     message: I18nKey.CHAT_INTERFACE$AGENT_AWAITING_USER_INPUT_MESSAGE,
-    indicator: IndicatorColor.BLUE,
+    indicator: IndicatorColor.ORANGE,
   },
   [AgentState.PAUSED]: {
     message: I18nKey.CHAT_INTERFACE$AGENT_PAUSED_MESSAGE,

frontend/src/components/features/chat/chat-input.tsx

@@ -5,6 +5,8 @@ import { I18nKey } from "#/i18n/declaration";
 import { cn } from "#/utils/utils";
 import { SubmitButton } from "#/components/shared/buttons/submit-button";
 import { StopButton } from "#/components/shared/buttons/stop-button";
+import { getValidImageFiles } from "#/utils/validate-image-type";
+import { toast } from "#/utils/toast";
 
 interface ChatInputProps {
   name?: string;
@@ -46,13 +48,22 @@ export function ChatInput({
   const handlePaste = (event: React.ClipboardEvent<HTMLTextAreaElement>) => {
     // Only handle paste if we have an image paste handler and there are files
     if (onImagePaste && event.clipboardData.files.length > 0) {
-      const files = Array.from(event.clipboardData.files).filter((file) =>
-        file.type.startsWith("image/"),
-      );
-      // Only prevent default if we found image files to handle
-      if (files.length > 0) {
+      const files = Array.from(event.clipboardData.files);
+      const { validFiles, invalidFiles } = getValidImageFiles(files);
+
+      if (invalidFiles.length > 0) {
+        toast.error(
+          t(I18nKey.UPLOAD$UNSUPPORTED_IMAGE_TYPE, {
+            count: invalidFiles.length,
+            files: invalidFiles.map((f) => f.name).join(", "),
+          })
+        );
+      }
+
+      // Only prevent default if we found valid image files to handle
+      if (validFiles.length > 0) {
         event.preventDefault();
-        onImagePaste(files);
+        onImagePaste(validFiles);
       }
     }
     // For text paste, let the default behavior handle it
@@ -74,11 +85,20 @@ export function ChatInput({
     event.preventDefault();
     setIsDraggingOver(false);
     if (onImagePaste && event.dataTransfer.files.length > 0) {
-      const files = Array.from(event.dataTransfer.files).filter((file) =>
-        file.type.startsWith("image/"),
-      );
-      if (files.length > 0) {
-        onImagePaste(files);
+      const files = Array.from(event.dataTransfer.files);
+      const { validFiles, invalidFiles } = getValidImageFiles(files);
+
+      if (invalidFiles.length > 0) {
+        toast.error(
+          t(I18nKey.UPLOAD$UNSUPPORTED_IMAGE_TYPE, {
+            count: invalidFiles.length,
+            files: invalidFiles.map((f) => f.name).join(", "),
+          })
+        );
+      }
+
+      if (validFiles.length > 0) {
+        onImagePaste(validFiles);
       }
     }
   };

frontend/src/components/features/images/upload-image-input.tsx

@@ -1,4 +1,8 @@
+import { useTranslation } from "react-i18next";
 import Clip from "#/icons/clip.svg?react";
+import { getValidImageFiles } from "#/utils/validate-image-type";
+import { toast } from "#/utils/toast";
+import { I18nKey } from "#/i18n/declaration";
 
 interface UploadImageInputProps {
   onUpload: (files: File[]) => void;
@@ -6,8 +10,26 @@ interface UploadImageInputProps {
 }
 
 export function UploadImageInput({ onUpload, label }: UploadImageInputProps) {
+  const { t } = useTranslation();
+
   const handleUpload = (event: React.ChangeEvent<HTMLInputElement>) => {
-    if (event.target.files) onUpload(Array.from(event.target.files));
+    if (!event.target.files) return;
+
+    const files = Array.from(event.target.files);
+    const { validFiles, invalidFiles } = getValidImageFiles(files);
+
+    if (invalidFiles.length > 0) {
+      toast.error(
+        t(I18nKey.UPLOAD$UNSUPPORTED_IMAGE_TYPE, {
+          count: invalidFiles.length,
+          files: invalidFiles.map((f) => f.name).join(", "),
+        })
+      );
+    }
+
+    if (validFiles.length > 0) {
+      onUpload(validFiles);
+    }
   };
 
   return (
@@ -16,7 +38,7 @@ export function UploadImageInput({ onUpload, label }: UploadImageInputProps) {
       <input
         data-testid="upload-image-input"
         type="file"
-        accept="image/*"
+        accept="image/jpeg,image/png,image/gif,image/webp"
         multiple
         hidden
         onChange={handleUpload}

frontend/src/hooks/mutation/use-create-conversation.ts

@@ -3,7 +3,7 @@ import { useNavigate } from "react-router";
 import posthog from "posthog-js";
 import { useDispatch, useSelector } from "react-redux";
 import OpenHands from "#/api/open-hands";
-import { setInitialPrompt } from "#/state/initial-query-slice";
+import { setInitialQuery } from "#/state/initial-query-slice";
 import { RootState } from "#/store";
 import { useAuth } from "#/context/auth-context";
 
@@ -18,7 +18,7 @@ export const useCreateConversation = () => {
   );
 
   return useMutation({
-    mutationFn: async (variables: { q?: string }) => {
+    mutationFn: (variables: { q?: string }) => {
       if (
         !variables.q?.trim() &&
         !selectedRepository &&
@@ -28,13 +28,10 @@ export const useCreateConversation = () => {
         throw new Error("No query provided");
       }
 
-      if (variables.q) dispatch(setInitialPrompt(variables.q));
-
+      if (variables.q) dispatch(setInitialQuery(variables.q));
       return OpenHands.createConversation(
         gitHubToken || undefined,
         selectedRepository || undefined,
-        variables.q,
-        files,
       );
     },
     onSuccess: async ({ conversation_id: conversationId }, { q }) => {

frontend/src/hooks/query/use-github-user.ts

@@ -6,7 +6,7 @@ import { useConfig } from "./use-config";
 import OpenHands from "#/api/open-hands";
 
 export const useGitHubUser = () => {
-  const { gitHubToken, setUserId, logout } = useAuth();
+  const { gitHubToken, setUserId } = useAuth();
   const { data: config } = useConfig();
 
   const user = useQuery({
@@ -29,11 +29,5 @@ export const useGitHubUser = () => {
     }
   }, [user.data]);
 
-  React.useEffect(() => {
-    if (user.isError) {
-      logout();
-    }
-  }, [user.isError]);
-
   return user;
 };

frontend/src/i18n/translation.json

@@ -419,6 +419,22 @@
         "ja": "コードエディタ",
         "tr": "Kod Editörü"
     },
+    "UPLOAD$UNSUPPORTED_IMAGE_TYPE": {
+        "en": "Only JPEG, PNG, GIF, and WebP images are supported",
+        "zh-CN": "仅支持 JPEG、PNG、GIF 和 WebP 图片",
+        "de": "Nur JPEG-, PNG-, GIF- und WebP-Bilder werden unterstützt",
+        "ko-KR": "JPEG, PNG, GIF 및 WebP 이미지만 지원됩니다",
+        "no": "Kun JPEG, PNG, GIF og WebP bilder støttes",
+        "zh-TW": "僅支援 JPEG、PNG、GIF 和 WebP 圖片",
+        "ar": "يتم دعم صور JPEG و PNG و GIF و WebP فقط",
+        "fr": "Seules les images JPEG, PNG, GIF et WebP sont prises en charge",
+        "it": "Sono supportate solo immagini JPEG, PNG, GIF e WebP",
+        "pt": "Apenas imagens JPEG, PNG, GIF e WebP são suportadas",
+        "es": "Solo se admiten imágenes JPEG, PNG, GIF y WebP",
+        "ja": "JPEG、PNG、GIF、WebP画像のみがサポートされています",
+        "tr": "Yalnızca JPEG, PNG, GIF ve WebP görüntüleri desteklenir"
+    },
+
     "WORKSPACE$BROWSER_TAB_LABEL": {
         "en": "Browser",
         "zh-CN": "浏览器",

frontend/src/mocks/handlers.ts

@@ -141,7 +141,7 @@ export const handlers = [
       { id: 2, full_name: "octocat/earth" },
     ]),
   ),
-  http.get("/api/github/user", () => {
+  http.get("https://api.github.com/user", () => {
     const user: GitHubUser = {
       id: 1,
       login: "octocat",

frontend/src/routes/_oh.app/event-handler.tsx

@@ -1,8 +1,10 @@
 import React from "react";
+import { useWSStatusChange } from "./hooks/use-ws-status-change";
 import { useHandleWSEvents } from "./hooks/use-handle-ws-events";
 import { useHandleRuntimeActive } from "./hooks/use-handle-runtime-active";
 
 export function EventHandler({ children }: React.PropsWithChildren) {
+  useWSStatusChange();
   useHandleWSEvents();
   useHandleRuntimeActive();
 

frontend/src/routes/_oh.app/hooks/use-ws-status-change.ts

@@ -0,0 +1,68 @@
+import React from "react";
+import { useDispatch, useSelector } from "react-redux";
+import {
+  useWsClient,
+  WsClientProviderStatus,
+} from "#/context/ws-client-provider";
+import { createChatMessage } from "#/services/chat-service";
+import { setCurrentAgentState } from "#/state/agent-slice";
+import { addUserMessage } from "#/state/chat-slice";
+import { clearFiles, clearInitialQuery } from "#/state/initial-query-slice";
+import { RootState } from "#/store";
+import { AgentState } from "#/types/agent-state";
+
+export const useWSStatusChange = () => {
+  const { send, status } = useWsClient();
+  const { curAgentState } = useSelector((state: RootState) => state.agent);
+  const dispatch = useDispatch();
+
+  const statusRef = React.useRef<WsClientProviderStatus | null>(null);
+
+  const { files, initialQuery } = useSelector(
+    (state: RootState) => state.initialQuery,
+  );
+
+  const sendInitialQuery = (query: string, base64Files: string[]) => {
+    const timestamp = new Date().toISOString();
+    send(createChatMessage(query, base64Files, timestamp));
+  };
+
+  const dispatchInitialQuery = (query: string) => {
+    sendInitialQuery(query, files);
+    dispatch(clearFiles()); // reset selected files
+    dispatch(clearInitialQuery()); // reset initial query
+  };
+
+  const handleAgentInit = () => {
+    if (initialQuery) {
+      dispatchInitialQuery(initialQuery);
+    }
+  };
+  React.useEffect(() => {
+    if (curAgentState === AgentState.INIT) {
+      handleAgentInit();
+    }
+  }, [curAgentState]);
+
+  React.useEffect(() => {
+    if (statusRef.current === status) {
+      return; // This is a check because of strict mode - if the status did not change, don't do anything
+    }
+    statusRef.current = status;
+
+    if (status !== WsClientProviderStatus.DISCONNECTED && initialQuery) {
+      dispatch(
+        addUserMessage({
+          content: initialQuery,
+          imageUrls: files,
+          timestamp: new Date().toISOString(),
+          pending: true,
+        }),
+      );
+    }
+
+    if (status === WsClientProviderStatus.DISCONNECTED) {
+      dispatch(setCurrentAgentState(AgentState.STOPPED));
+    }
+  }, [status]);
+};

frontend/src/routes/_oh.app/route.tsx

@@ -1,7 +1,7 @@
 import { useDisclosure } from "@nextui-org/react";
 import React from "react";
 import { Outlet } from "react-router";
-import { useDispatch, useSelector } from "react-redux";
+import { useDispatch } from "react-redux";
 import { FaServer } from "react-icons/fa";
 import toast from "react-hot-toast";
 import { useTranslation } from "react-i18next";
@@ -11,7 +11,7 @@ import {
   useConversation,
 } from "#/context/conversation-context";
 import { Controls } from "#/components/features/controls/controls";
-import { clearMessages, addUserMessage } from "#/state/chat-slice";
+import { clearMessages } from "#/state/chat-slice";
 import { clearTerminal } from "#/state/command-slice";
 import { useEffectOnce } from "#/hooks/use-effect-once";
 import CodeIcon from "#/icons/code.svg?react";
@@ -36,8 +36,6 @@ import { ServedAppLabel } from "#/components/layout/served-app-label";
 import { TerminalStatusLabel } from "#/components/features/terminal/terminal-status-label";
 import { useSettings } from "#/hooks/query/use-settings";
 import { MULTI_CONVERSATION_UI } from "#/utils/feature-flags";
-import { clearFiles, clearInitialPrompt } from "#/state/initial-query-slice";
-import { RootState } from "#/store";
 
 function AppContent() {
   useConversationConfig();
@@ -48,9 +46,6 @@ function AppContent() {
   const { data: conversation, isFetched } = useUserConversation(
     conversationId || null,
   );
-  const { initialPrompt, files } = useSelector(
-    (state: RootState) => state.initialQuery,
-  );
   const dispatch = useDispatch();
   const endSession = useEndSession();
 
@@ -79,18 +74,6 @@ function AppContent() {
     dispatch(clearMessages());
     dispatch(clearTerminal());
     dispatch(clearJupyter());
-    if (conversationId && (initialPrompt || files.length > 0)) {
-      dispatch(
-        addUserMessage({
-          content: initialPrompt || "",
-          imageUrls: files || [],
-          timestamp: new Date().toISOString(),
-          pending: true,
-        }),
-      );
-      dispatch(clearInitialPrompt());
-      dispatch(clearFiles());
-    }
   }, [conversationId]);
 
   useEffectOnce(() => {

frontend/src/state/initial-query-slice.ts

@@ -2,14 +2,14 @@ import { createSlice, PayloadAction } from "@reduxjs/toolkit";
 
 type SliceState = {
   files: string[]; // base64 encoded images
-  initialPrompt: string | null;
+  initialQuery: string | null;
   selectedRepository: string | null;
   importedProjectZip: string | null; // base64 encoded zip
 };
 
 const initialState: SliceState = {
   files: [],
-  initialPrompt: null,
+  initialQuery: null,
   selectedRepository: null,
   importedProjectZip: null,
 };
@@ -27,11 +27,11 @@ export const selectedFilesSlice = createSlice({
     clearFiles(state) {
       state.files = [];
     },
-    setInitialPrompt(state, action: PayloadAction<string>) {
-      state.initialPrompt = action.payload;
+    setInitialQuery(state, action: PayloadAction<string>) {
+      state.initialQuery = action.payload;
     },
-    clearInitialPrompt(state) {
-      state.initialPrompt = null;
+    clearInitialQuery(state) {
+      state.initialQuery = null;
     },
     setSelectedRepository(state, action: PayloadAction<string | null>) {
       state.selectedRepository = action.payload;
@@ -49,8 +49,8 @@ export const {
   addFile,
   removeFile,
   clearFiles,
-  setInitialPrompt,
-  clearInitialPrompt,
+  setInitialQuery,
+  clearInitialQuery,
   setSelectedRepository,
   clearSelectedRepository,
   setImportedProjectZip,

frontend/src/utils/validate-image-type.ts

@@ -0,0 +1,20 @@
+const SUPPORTED_IMAGE_TYPES = ['image/jpeg', 'image/png', 'image/gif', 'image/webp'] as const;
+
+export function validateImageType(file: File): boolean {
+  return SUPPORTED_IMAGE_TYPES.includes(file.type as typeof SUPPORTED_IMAGE_TYPES[number]);
+}
+
+export function getValidImageFiles(files: File[]): { validFiles: File[]; invalidFiles: File[] } {
+  const validFiles: File[] = [];
+  const invalidFiles: File[] = [];
+
+  files.forEach((file) => {
+    if (validateImageType(file)) {
+      validFiles.push(file);
+    } else {
+      invalidFiles.push(file);
+    }
+  });
+
+  return { validFiles, invalidFiles };
+}

openhands/agenthub/codeact_agent/function_calling.py

@@ -32,7 +32,6 @@ from openhands.events.tool import ToolCallMetadata
 _BASH_DESCRIPTION = """Execute a bash command in the terminal.
 * Long running commands: For commands that may run indefinitely, it should be run in the background and the output should be redirected to a file, e.g. command = `python3 app.py > server.log 2>&1 &`.
 * Interact with running process: If a bash command returns exit code `-1`, this means the process is not yet finished. By setting `is_input` to `true`, the assistant can interact with the running process and send empty `command` to retrieve any additional logs, or send additional text (set `command` to the text) to STDIN of the running process, or send command like `C-c` (Ctrl+C), `C-d` (Ctrl+D), `C-z` (Ctrl+Z) to interrupt the process.
-* One command at a time: You can only execute one bash command at a time. If you need to run multiple commands sequentially, you can use `&&` or `;` to chain them together.
 """
 
 CmdRunTool = ChatCompletionToolParam(
@@ -45,7 +44,7 @@ CmdRunTool = ChatCompletionToolParam(
             'properties': {
                 'command': {
                     'type': 'string',
-                    'description': 'The bash command to execute. Can be empty string to view additional logs when previous exit code is `-1`. Can be `C-c` (Ctrl+C) to interrupt the currently running process. Note: You can only execute one bash command at a time. If you need to run multiple commands sequentially, you can use `&&` or `;` to chain them together.',
+                    'description': 'The bash command to execute. Can be empty string to view additional logs when previous exit code is `-1`. Can be `C-c` (Ctrl+C) to interrupt the currently running process.',
                 },
                 'is_input': {
                     'type': 'string',

openhands/controller/agent_controller.py

@@ -501,6 +501,10 @@ class AgentController:
             EventSource.ENVIRONMENT,
         )
 
+        if new_state == AgentState.INIT and self.state.resume_state:
+            await self.set_agent_state_to(self.state.resume_state)
+            self.state.resume_state = None
+
     def get_agent_state(self) -> AgentState:
         """Returns the current state of the agent.
 

openhands/core/schema/action.py

@@ -4,6 +4,10 @@ __all__ = ['ActionType']
 
 
 class ActionTypeSchema(BaseModel):
+    INIT: str = Field(default='initialize')
+    """Initializes the agent. Only sent by client.
+    """
+
     MESSAGE: str = Field(default='message')
     """Represents a message.
     """

openhands/core/schema/agent.py

@@ -6,6 +6,10 @@ class AgentState(str, Enum):
     """The agent is loading.
     """
 
+    INIT = 'init'
+    """The agent is initialized.
+    """
+
     RUNNING = 'running'
     """The agent is running.
     """

openhands/resolver/resolve_issue.py

@@ -567,6 +567,12 @@ def main():
         choices=['issue', 'pr'],
         help='Type of issue to resolve, either open issue or pr comments.',
     )
+    parser.add_argument(
+        '--target-branch',
+        type=str,
+        default=None,
+        help="Target branch to pull and create PR against (for PRs). If not specified, uses the PR's base branch.",
+    )
     parser.add_argument(
         '--is-experimental',
         type=lambda x: x.lower() == 'true',

openhands/runtime/impl/remote/remote_runtime.py

@@ -306,12 +306,6 @@ class RemoteRuntime(ActionExecutionClient):
         assert 'pod_status' in runtime_data
         pod_status = runtime_data['pod_status'].lower()
         self.log('debug', f'Pod status: {pod_status}')
-        restart_count = runtime_data.get('restart_count', 0)
-        if restart_count != 0:
-            restart_reasons = runtime_data.get('restart_reasons')
-            self.log(
-                'debug', f'Pod restarts: {restart_count}, reasons: {restart_reasons}'
-            )
 
         # FIXME: We should fix it at the backend of /start endpoint, make sure
         # the pod is created before returning the response.

openhands/server/conversation_manager/conversation_manager.py

@@ -5,7 +5,6 @@ from abc import ABC, abstractmethod
 import socketio
 
 from openhands.core.config import AppConfig
-from openhands.events.action import MessageAction
 from openhands.events.stream import EventStream
 from openhands.server.session.conversation import Conversation
 from openhands.server.settings import Settings
@@ -69,7 +68,7 @@ class ConversationManager(ABC):
         sid: str,
         settings: Settings,
         user_id: str | None,
-        initial_user_msg: MessageAction | None = None,
+        initial_user_msg: str | None = None,
     ) -> EventStream:
         """Start an event loop if one is not already running"""
 

openhands/server/conversation_manager/standalone_conversation_manager.py

@@ -9,7 +9,6 @@ from openhands.core.config.app_config import AppConfig
 from openhands.core.exceptions import AgentRuntimeUnavailableError
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.schema.agent import AgentState
-from openhands.events.action import MessageAction
 from openhands.events.stream import EventStream, session_exists
 from openhands.server.session.conversation import Conversation
 from openhands.server.session.session import ROOM_KEY, Session
@@ -187,7 +186,7 @@ class StandaloneConversationManager(ConversationManager):
         sid: str,
         settings: Settings,
         user_id: str | None,
-        initial_user_msg: MessageAction | None = None,
+        initial_user_msg: str | None = None,
     ) -> EventStream:
         logger.info(f'maybe_start_agent_loop:{sid}')
         session: Session | None = None

openhands/server/listen_socket.py

@@ -5,6 +5,7 @@ from pydantic import SecretStr
 from socketio.exceptions import ConnectionRefusedError
 
 from openhands.core.logger import openhands_logger as logger
+from openhands.core.schema.agent import AgentState
 from openhands.events.action import (
     NullAction,
 )
@@ -85,6 +86,8 @@ async def connect(connection_id: str, environ, auth):
         ):
             continue
         elif isinstance(event, AgentStateChangedObservation):
+            if event.agent_state == AgentState.INIT:
+                await sio.emit('oh_event', event_to_dict(event), to=connection_id)
             agent_state_changed = event
         else:
             await sio.emit('oh_event', event_to_dict(event), to=connection_id)

openhands/server/mock/listen.py

@@ -2,6 +2,7 @@ import uvicorn
 from fastapi import FastAPI, WebSocket
 
 from openhands.core.logger import openhands_logger as logger
+from openhands.core.schema import ActionType
 from openhands.utils.shutdown_listener import should_continue
 
 app = FastAPI()
@@ -10,6 +11,10 @@ app = FastAPI()
 @app.websocket('/ws')
 async def websocket_endpoint(websocket: WebSocket):
     await websocket.accept()
+    # send message to mock connection
+    await websocket.send_json(
+        {'action': ActionType.INIT, 'message': 'Control loop started.'}
+    )
 
     try:
         while should_continue():

openhands/server/routes/manage_conversations.py

@@ -7,7 +7,6 @@ from fastapi.responses import JSONResponse
 from pydantic import BaseModel
 
 from openhands.core.logger import openhands_logger as logger
-from openhands.events.action.message import MessageAction
 from openhands.events.stream import EventStreamSubscriber
 from openhands.runtime import get_runtime_cls
 from openhands.server.auth import get_user_id
@@ -35,7 +34,6 @@ class InitSessionRequest(BaseModel):
     github_token: str | None = None
     selected_repository: str | None = None
     initial_user_msg: str | None = None
-    image_urls: list[str] | None = None
 
 
 async def _create_new_conversation(
@@ -43,7 +41,6 @@ async def _create_new_conversation(
     token: str | None,
     selected_repository: str | None,
     initial_user_msg: str | None,
-    image_urls: list[str] | None,
 ):
     logger.info('Loading settings')
     settings_store = await SettingsStoreImpl.get_instance(config, user_id)
@@ -97,14 +94,8 @@ async def _create_new_conversation(
     )
 
     logger.info(f'Starting agent loop for conversation {conversation_id}')
-    initial_message_action = None
-    if initial_user_msg or image_urls:
-        initial_message_action = MessageAction(
-            content=initial_user_msg or '',
-            image_urls=image_urls or [],
-        )
     event_stream = await conversation_manager.maybe_start_agent_loop(
-        conversation_id, conversation_init_data, user_id, initial_message_action
+        conversation_id, conversation_init_data, user_id, initial_user_msg
     )
     try:
         event_stream.subscribe(
@@ -130,16 +121,10 @@ async def new_conversation(request: Request, data: InitSessionRequest):
     github_token = getattr(request.state, 'github_token', '') or data.github_token
     selected_repository = data.selected_repository
     initial_user_msg = data.initial_user_msg
-    image_urls = data.image_urls or []
 
     try:
-        # Create conversation with initial message
         conversation_id = await _create_new_conversation(
-            user_id,
-            github_token,
-            selected_repository,
-            initial_user_msg,
-            image_urls,
+            user_id, github_token, selected_repository, initial_user_msg
         )
 
         return JSONResponse(

openhands/server/session/README.md

@@ -8,12 +8,19 @@ interruptions are recoverable.
 There are 3 main server side event handlers:
 
 * `connect` - Invoked when a new connection to the server is established. (This may be via http or WebSocket)
-* `oh_action` - Invoked when a connected client sends an event (such as a prompt for the Agent) -
+* `oh_action` - Invoked when a connected client sends an event (Such as `INIT` or a prompt for the Agent) -
    this is distinct from the `oh_event` sent from the server to the client.
 * `disconnect` - Invoked when a connected client disconnects from the server.
 
+## Init
+Each connection has a unique id, and when initially established, is not associated with any session. An
+`INIT` event must be sent to the server in order to attach a connection to a session. The `INIT` event
+may optionally include a GitHub token and a token to connect to an existing session. (Which may be running
+locally or may need to be hydrated). If no token is received as part of the init event, it is assumed a
+new session should be started.
+
 ## Disconnect
 The (manager)[manager.py] manages connections and sessions. Each session may have zero or more connections
-associated with it. When a session no longer has any
+associated with it, managed by invocations of `INIT` and disconnect. When a session no longer has any
 connections associated with it, after a set amount of time (determined by `config.sandbox.close_delay`),
 the session and runtime are passivated (So will need to be rehydrated to continue.)

openhands/server/session/agent_session.py

@@ -9,7 +9,8 @@ from openhands.core.config import AgentConfig, AppConfig, LLMConfig
 from openhands.core.exceptions import AgentRuntimeUnavailableError
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.schema.agent import AgentState
-from openhands.events.action import ChangeAgentStateAction, MessageAction
+from openhands.events.action import ChangeAgentStateAction
+from openhands.events.action.message import MessageAction
 from openhands.events.event import EventSource
 from openhands.events.stream import EventStream
 from openhands.microagent import BaseMicroAgent
@@ -71,7 +72,7 @@ class AgentSession:
         agent_configs: dict[str, AgentConfig] | None = None,
         github_token: str | None = None,
         selected_repository: str | None = None,
-        initial_message: MessageAction | None = None,
+        initial_user_msg: str | None = None,
     ):
         """Starts the Agent session
         Parameters:
@@ -110,17 +111,15 @@ class AgentSession:
             agent_to_llm_config=agent_to_llm_config,
             agent_configs=agent_configs,
         )
-        if initial_message:
-            self.event_stream.add_event(initial_message, EventSource.USER)
-            self.event_stream.add_event(
-                ChangeAgentStateAction(AgentState.RUNNING), EventSource.ENVIRONMENT
-            )
-        else:
-            self.event_stream.add_event(
-                ChangeAgentStateAction(AgentState.AWAITING_USER_INPUT),
-                EventSource.ENVIRONMENT,
-            )
+        self.event_stream.add_event(
+            ChangeAgentStateAction(AgentState.INIT), EventSource.ENVIRONMENT
+        )
 
+        if initial_user_msg:
+            self.event_stream.add_event(
+                MessageAction(content=initial_user_msg), EventSource.USER
+            )
+            
         self._starting = False
 
     async def close(self):

openhands/server/session/manager.py

@@ -11,7 +11,6 @@ from openhands.core.config import AppConfig
 from openhands.core.exceptions import AgentRuntimeUnavailableError
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.schema.agent import AgentState
-from openhands.events.action import MessageAction
 from openhands.events.stream import EventStream, session_exists
 from openhands.server.session.agent_session import WAIT_TIME_BEFORE_CLOSE
 from openhands.server.session.conversation import Conversation
@@ -447,7 +446,7 @@ class SessionManager:
         sid: str,
         settings: Settings,
         user_id: str | None,
-        initial_message: MessageAction | None = None,
+        initial_user_msg: str | None = None,
     ) -> EventStream:
         logger.info(f'maybe_start_agent_loop:{sid}')
         session: Session | None = None
@@ -470,7 +469,7 @@ class SessionManager:
                 user_id=user_id,
             )
             self._local_agent_loops_by_sid[sid] = session
-            asyncio.create_task(session.initialize_agent(settings, initial_message))
+            asyncio.create_task(session.initialize_agent(settings, initial_user_msg))
 
         event_stream = await self._get_event_stream(sid)
         if not event_stream:

openhands/server/session/session.py

@@ -74,9 +74,7 @@ class Session:
         self.is_alive = False
         await self.agent_session.close()
 
-    async def initialize_agent(
-        self, settings: Settings, initial_message: MessageAction | None
-    ):
+    async def initialize_agent(self, settings: Settings, initial_user_msg: str | None):
         self.agent_session.event_stream.add_event(
             AgentStateChangedObservation('', AgentState.LOADING),
             EventSource.ENVIRONMENT,
@@ -124,7 +122,7 @@ class Session:
                 agent_configs=self.config.get_agent_configs(),
                 github_token=github_token,
                 selected_repository=selected_repository,
-                initial_message=initial_message,
+                initial_user_msg=initial_user_msg,
             )
         except Exception as e:
             logger.exception(f'Error creating agent_session: {e}')

poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.8.5 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.4 and should not be changed by hand.
 
 [[package]]
 name = "aiohappyeyeballs"
@@ -1108,20 +1108,6 @@ humanfriendly = ">=9.1"
 [package.extras]
 cron = ["capturer (>=2.4)"]
 
-[[package]]
-name = "colormath"
-version = "3.0.0"
-description = "Color math and conversion library."
-optional = false
-python-versions = "*"
-files = [
-    {file = "colormath-3.0.0.tar.gz", hash = "sha256:3d4605af344527da0e4f9f504fad7ddbebda35322c566a6c72e28edb1ff31217"},
-]
-
-[package.dependencies]
-networkx = ">=2.0"
-numpy = "*"
-
 [[package]]
 name = "comm"
 version = "0.2.2"
@@ -3958,19 +3944,19 @@ pydantic = ">=1.10"
 
 [[package]]
 name = "llama-index"
-version = "0.12.13"
+version = "0.12.12"
 description = "Interface between LLMs and your data"
 optional = false
 python-versions = "<4.0,>=3.9"
 files = [
-    {file = "llama_index-0.12.13-py3-none-any.whl", hash = "sha256:0b285aa451ced6bd8da40df99068ac96badf8b5725c4edc29f2bce4da2ffd8bc"},
-    {file = "llama_index-0.12.13.tar.gz", hash = "sha256:1e39a397dcc51dabe280c121fd8d5451a6a84595233a8b26caa54d9b7ecf9ffc"},
+    {file = "llama_index-0.12.12-py3-none-any.whl", hash = "sha256:208f77dba5fd8268cacd3d56ec3ee33b0001d5b6ec623c5b91c755af7b08cfae"},
+    {file = "llama_index-0.12.12.tar.gz", hash = "sha256:d4e475726e342b1178736ae3ed93336fe114605e86431b6dfcb454a9e1f26e72"},
 ]
 
 [package.dependencies]
 llama-index-agent-openai = ">=0.4.0,<0.5.0"
 llama-index-cli = ">=0.4.0,<0.5.0"
-llama-index-core = ">=0.12.13,<0.13.0"
+llama-index-core = ">=0.12.12,<0.13.0"
 llama-index-embeddings-openai = ">=0.3.0,<0.4.0"
 llama-index-indices-managed-llama-cloud = ">=0.4.0"
 llama-index-llms-openai = ">=0.3.0,<0.4.0"
@@ -4015,13 +4001,13 @@ llama-index-llms-openai = ">=0.3.0,<0.4.0"
 
 [[package]]
 name = "llama-index-core"
-version = "0.12.13"
+version = "0.12.12"
 description = "Interface between LLMs and your data"
 optional = false
 python-versions = "<4.0,>=3.9"
 files = [
-    {file = "llama_index_core-0.12.13-py3-none-any.whl", hash = "sha256:9708bb594bbddffd6ff0767242e49d8978d1ba60a2e62e071d9d123ad2f17e6f"},
-    {file = "llama_index_core-0.12.13.tar.gz", hash = "sha256:77af0161246ce1de38efc17cb6438dfff9e9558af00bcfac7dd4d0b7325efa4b"},
+    {file = "llama_index_core-0.12.12-py3-none-any.whl", hash = "sha256:cea491e87f65e6b775b5aef95720de302b85af1bdc67d779c4b09170a30e5b98"},
+    {file = "llama_index_core-0.12.12.tar.gz", hash = "sha256:068b755bbc681731336e822f5977d7608585e8f759c6293ebd812e2659316a37"},
 ]
 
 [package.dependencies]
@@ -5483,7 +5469,6 @@ description = "Nvidia JIT LTO Library"
 optional = false
 python-versions = ">=3"
 files = [
-    {file = "nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:4abe7fef64914ccfa909bc2ba39739670ecc9e820c83ccc7a6ed414122599b83"},
     {file = "nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:06b3b9b25bf3f8af351d664978ca26a16d2c5127dbd53c0497e28d1fb9611d57"},
     {file = "nvidia_nvjitlink_cu12-12.4.127-py3-none-win_amd64.whl", hash = "sha256:fd9020c501d27d135f983c6d3e244b197a7ccad769e34df53a42e276b0e25fa1"},
 ]
@@ -5596,17 +5581,15 @@ realtime = ["websockets (>=13,<15)"]
 
 [[package]]
 name = "openhands-aci"
-version = "0.1.9"
+version = "0.1.8"
 description = "An Agent-Computer Interface (ACI) designed for software development agents OpenHands."
 optional = false
-python-versions = "<4.0,>=3.12"
-files = [
-    {file = "openhands_aci-0.1.9-py3-none-any.whl", hash = "sha256:62af189878db046aa98475a41fa01200efd5ddf1db8a435c38da3d4ad32cb11a"},
-    {file = "openhands_aci-0.1.9.tar.gz", hash = "sha256:690d33d355a3e4111f52861dbb96ff766b5a268202324a87c94ba67b628a63b1"},
-]
+python-versions = "^3.12"
+files = []
+develop = false
 
 [package.dependencies]
-diskcache = ">=5.6.3,<6.0.0"
+diskcache = "^5.6.3"
 flake8 = "*"
 gitpython = "*"
 grep-ast = "0.3.3"
@@ -5616,7 +5599,13 @@ numpy = "*"
 pandas = "*"
 scipy = "*"
 tree-sitter = "0.21.3"
-whatthepatch = ">=1.0.6,<2.0.0"
+whatthepatch = "^1.0.6"
+
+[package.source]
+type = "git"
+url = "https://github.com/All-Hands-AI/openhands-aci.git"
+reference = "fix-find-show-only-hidden-subpaths"
+resolved_reference = "910e8c470aff0e496bf262bc673c7ee7b4531159"
 
 [[package]]
 name = "opentelemetry-api"
@@ -10130,4 +10119,4 @@ testing = ["coverage[toml]", "zope.event", "zope.testing"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.12"
-content-hash = "fbca4b2ca0fe2d1d3cac46164c0c1eb9e468dc6f6bc7165e9a3d62ea9f25d801"
+content-hash = "6b74056694bdc84a4583c2f93a5b218f15688827cb59e289eb83331045a1582e"

pyproject.toml

@@ -65,7 +65,7 @@ runloop-api-client = "0.13.0"
 libtmux = ">=0.37,<0.40"
 pygithub = "^2.5.0"
 joblib = "*"
-openhands-aci = "0.1.9"
+openhands-aci = "0.1.8"
 python-socketio = "^5.11.4"
 redis = "^5.2.0"
 sse-starlette = "^2.1.3"
@@ -101,7 +101,6 @@ reportlab = "*"
 [tool.coverage.run]
 concurrency = ["gevent"]
 
-
 [tool.poetry.group.runtime.dependencies]
 jupyterlab = "*"
 notebook = "*"
@@ -130,7 +129,6 @@ ignore = ["D1"]
 [tool.ruff.lint.pydocstyle]
 convention = "google"
 
-
 [tool.poetry.group.evaluation.dependencies]
 streamlit = "*"
 whatthepatch = "*"