import re, glob, os, yaml
sys_ids = set(os.path.basename(f)[:-3] for f in glob.glob('context/*.md'))
# glossary top-level keys = valid link targets too
try:
    gl = yaml.safe_load(open('reference/glossary.yaml',encoding='utf-8'))
    gloss_keys = set(gl.keys()) if isinstance(gl, dict) else set()
except Exception as e:
    gloss_keys = set(re.findall(r'^([A-Za-z][A-Za-z0-9_-]*):', open('reference/glossary.yaml',encoding='utf-8').read(), re.M))
valid = sys_ids | gloss_keys
# template placeholders that are documentation, not real links:
IGNORE = {'other-topic','other-topic-a','other-topic-b','topic-id','name'}
print("topic ids:", len(sys_ids), "| glossary keys:", len(gloss_keys))
bad=0
for f in glob.glob('context/*.md') + ['CLAUDE.md']:
    txt=open(f,encoding='utf-8',errors='replace').read()
    for m in re.findall(r'\[\[([a-z0-9-]+)\]\]', txt):
        if m not in valid and m not in IGNORE:
            print(f"  UNRESOLVED [[{m}]] in {f}"); bad+=1
cl=open('CLAUDE.md',encoding='utf-8',errors='replace').read()
for m in re.findall(r'`(context/[a-z0-9-]+\.md)`', cl):
    if not os.path.exists(m): print(f"  MISSING quick-lookup {m}"); bad+=1
for m in re.findall(r'`(docs/[A-Z0-9_]+\.md)`', cl):
    if not os.path.exists(m): print(f"  MISSING docs ref {m}"); bad+=1
print("RESULT:", "CLEAN" if bad==0 else f"{bad} unresolved")