gravity_control/.agents/workflows/helpers/analyze_dom.py

"""Analyze AG Native DOM structure to find AI response containers."""
import json, os, sys

def load_dump():
    bridge = os.path.join(os.path.expanduser('~'), '.gemini', 'antigravity', 'bridge')
    # Try deep-inspect result first, then dump_html
    for fname in ['deep-inspect-result.json', 'dump_html.json']:
        fpath = os.path.join(bridge, fname)
        if os.path.exists(fpath):
            print(f"Loading: {fname} ({os.path.getsize(fpath)} bytes)")
            with open(fpath, 'r', encoding='utf-8-sig') as f:
                return json.load(f), fname
    return None, None

def find_text_containers(node, path="", depth=0, results=None):
    """Recursively find nodes with substantial text content (potential AI response containers)."""
    if results is None:
        results = []
    if not isinstance(node, dict):
        return results
    
    tag = node.get('tag', '')
    cls = node.get('cls', '')
    text = node.get('text', '')
    attrs = node.get('attrs', {})
    children = node.get('children', [])
    
    cur_path = f"{path}/{tag}"
    if cls:
        short_cls = cls[:60]
        cur_path += f".{short_cls}"
    
    # Look for nodes with long text (potential AI responses)
    if text and len(text) > 50:
        results.append({
            'path': cur_path,
            'depth': depth,
            'tag': tag,
            'cls': cls[:100],
            'text_len': len(text),
            'text_preview': text[:120],
            'attrs': {k:v for k,v in attrs.items() if k not in ('style',)}
        })
    
    for child in children:
        find_text_containers(child, cur_path, depth+1, results)
    
    return results

def find_by_class_pattern(node, patterns, path="", depth=0, results=None):
    """Find nodes matching class patterns."""
    if results is None:
        results = []
    if not isinstance(node, dict):
        return results
    
    tag = node.get('tag', '')
    cls = node.get('cls', '')
    attrs = node.get('attrs', {})
    children = node.get('children', [])
    text = node.get('text', '')
    
    cur_path = f"{path}/{tag}" 
    
    for pattern in patterns:
        if pattern.lower() in cls.lower() or pattern.lower() in str(attrs).lower():
            child_count = len(children)
            results.append({
                'path': cur_path,
                'depth': depth,
                'tag': tag,
                'cls': cls[:150],
                'pattern': pattern,
                'text_preview': text[:80] if text else '',
                'child_count': child_count,
                'attrs': {k:v[:50] for k,v in attrs.items() if k != 'style'}
            })
    
    for child in children:
        find_by_class_pattern(child, patterns, cur_path, depth+1, results)
    
    return results

def analyze_chat_structure(node, path="", depth=0):
    """Find the chat/conversation area by looking at the main layout."""
    if not isinstance(node, dict):
        return
    tag = node.get('tag', '')
    cls = node.get('cls', '')
    children = node.get('children', [])
    text = node.get('text', '')
    attrs = node.get('attrs', {})
    
    # Print interesting structural nodes at shallow depths
    if depth <= 6:
        child_count = len(children)
        has_text = bool(text and len(text) > 10)
        info = f"{'  '*depth}{tag}"
        if cls:
            info += f" .{cls[:80]}"
        if attrs:
            attr_str = ' '.join(f'{k}={v[:30]}' for k,v in attrs.items() if k not in ('style','class'))
            if attr_str:
                info += f" [{attr_str}]"
        info += f" children={child_count}"
        if has_text:
            info += f" text=\"{text[:50]}...\""
        print(info)
    
    for child in children:
        analyze_chat_structure(child, f"{path}/{tag}", depth+1)

data, fname = load_dump()
if not data:
    print("No dump file found!")
    sys.exit(1)

# Handle both dump formats
body = data.get('body', data)
qi = data.get('quickInfo', {})

print("=" * 60)
print("QUICK INFO")
print("=" * 60)
if qi:
    for k, v in qi.items():
        if k == 'buttons':
            print(f"buttons ({len(v)}):")
            for b in v[:15]:
                print(f"  [{b.get('tag')}] \"{b.get('text','')[:50]}\" visible={b.get('visible')} cls={b.get('cls','')[:60]}")
        elif k == 'dataAttrs':
            print(f"dataAttrs: {v[:30]}")
        else:
            print(f"{k}: {v}")

print("\n" + "=" * 60)
print("CHAT-RELATED CLASS PATTERNS")
print("=" * 60)
patterns = ['chat', 'message', 'conversation', 'response', 'answer', 'reply',
            'markdown', 'prose', 'content', 'panel', 'agent', 'assistant',
            'planner', 'step', 'trajectory', 'bot', 'ai-', 'turn']
matches = find_by_class_pattern(body, patterns)
for m in matches:
    print(f"  [{m['tag']}] cls=\"{m['cls']}\" pattern={m['pattern']} children={m['child_count']} {m.get('attrs',{})}")

print("\n" + "=" * 60)
print("LONG TEXT NODES (potential AI responses)")  
print("=" * 60)
texts = find_text_containers(body)
texts.sort(key=lambda x: x['text_len'], reverse=True)
for t in texts[:20]:
    print(f"  [{t['tag']}] depth={t['depth']} len={t['text_len']} cls=\"{t['cls'][:60]}\"")
    print(f"    text: \"{t['text_preview']}\"")
    if t['attrs']:
        print(f"    attrs: {t['attrs']}")

print("\n" + "=" * 60)
print("DOM TREE (depth<=6)")
print("=" * 60)
analyze_chat_structure(body)