scripts/clear_poor_entries.py

#!/usr/bin/env python3
"""Clear specific cache entries so they get regenerated with the new adaptive radius."""
import json, os, sys
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "src"))
from dotenv import load_dotenv
load_dotenv(dotenv_path=os.path.join(os.path.dirname(__file__), "..", ".env"), override=True)

CACHE_FILE = os.path.join(os.path.dirname(__file__), "..", ".cache", "llm_cache.json")
WARMUP_PROGRESS = os.path.join(os.path.dirname(__file__), "..", ".warmup_progress.json")

CATS = ["Landmark", "Culture", "Nature", "Gems", "Photo", "Food", "Shopping"]

def cat_hash(name):
    d = {c: (c == name) for c in CATS}
    return json.dumps(d, sort_keys=True)

# Cities to fully clear (all categories)
FULL_CLEAR = ["Bali", "Dubai"]
# Specific combos to clear  
COMBO_CLEAR = [
    ("Marrakech", "Landmark"),
    ("Kyoto", "Shopping"),
]

with open(CACHE_FILE) as f:
    cache = json.load(f)

removed = 0
# Full clear
for city in FULL_CLEAR:
    for cat in CATS:
        key = json.dumps([city, cat_hash(cat)])
        if key in cache:
            del cache[key]
            removed += 1

# Specific combos
for city, cat in COMBO_CLEAR:
    key = json.dumps([city, cat_hash(cat)])
    if key in cache:
        del cache[key]
        removed += 1

with open(CACHE_FILE, "w") as f:
    json.dump(cache, f)

# Also clear warmup progress for these so the warmup retries them
with open(WARMUP_PROGRESS) as f:
    progress = json.load(f)

for cid in list(progress["combos"].keys()):
    city, cat = cid.split("::")
    if city in FULL_CLEAR:
        del progress["combos"][cid]
    elif (city, cat) in COMBO_CLEAR:
        del progress["combos"][cid]

with open(WARMUP_PROGRESS, "w") as f:
    json.dump(progress, f, indent=2)

print(f"Cleared {removed} cache entries + progress for re-warmup")