feat(aggregation): Add persistent cache storage and LRU management

src/summary_cache.py

@@ -12,12 +12,13 @@ class SummaryCache:
     A hash-based cache for file summaries to avoid redundant processing.
     Invalidates when content hash changes.
     """
- def __init__(self, cache_file: Optional[str] = None):
+ def __init__(self, cache_file: Optional[str] = None, max_entries: int = 1000):
   if cache_file:
    self.cache_file = Path(cache_file)
   else:
    # Default relative to current working directory
    self.cache_file = Path(".slop_cache/summary_cache.json")
+  self.max_entries = max_entries
   self.cache: Dict[str, Dict[str, str]] = {}
   self.load()
 
@@ -43,13 +44,45 @@ class SummaryCache:
   """Returns cached summary if hash matches, otherwise None."""
   entry = self.cache.get(file_path)
   if entry and entry.get("hash") == content_hash:
-   return entry.get("summary")
+   # LRU: move to end
+   val = self.cache.pop(file_path)
+   self.cache[file_path] = val
+   return val.get("summary")
   return None
 
  def set_summary(self, file_path: str, content_hash: str, summary: str) -> None:
   """Stores summary in cache and saves to disk."""
+  if file_path in self.cache:
+   self.cache.pop(file_path)
   self.cache[file_path] = {
    "hash": content_hash,
    "summary": summary
   }
+  # Enforce LRU size limit
+  while len(self.cache) > self.max_entries:
+   # pop first item (oldest)
+   first_key = next(iter(self.cache))
+   self.cache.pop(first_key)
   self.save()
+
+ def clear(self) -> None:
+  """Clears the cache both in-memory and on disk."""
+  self.cache.clear()
+  if self.cache_file.exists():
+   try:
+    self.cache_file.unlink()
+   except Exception:
+    pass
+
+ def get_stats(self) -> dict:
+  """Returns dictionary of cache statistics."""
+  size_bytes = 0
+  if self.cache_file.exists():
+   try:
+    size_bytes = self.cache_file.stat().st_size
+   except Exception:
+    pass
+  return {
+   "entries": len(self.cache),
+   "size_bytes": size_bytes
+  }

tests/test_summary_cache.py

@@ -40,7 +40,36 @@ def test_summary_cache():
  if cache_dir.exists():
   shutil.rmtree(cache_dir)
 
+def test_summary_cache_lru():
+ cache_dir = Path(".test_cache_lru")
+ if cache_dir.exists():
+  shutil.rmtree(cache_dir)
+ cache_file = cache_dir / "cache.json"
+ 
+ # Create cache with max 2 entries
+ cache = SummaryCache(str(cache_file), max_entries=2)
+ 
+ cache.set_summary("file1.py", "hash1", "summary1")
+ cache.set_summary("file2.py", "hash2", "summary2")
+ cache.set_summary("file3.py", "hash3", "summary3") # This should evict file1.py
+ 
+ assert cache.get_summary("file1.py", "hash1") is None
+ assert cache.get_summary("file2.py", "hash2") == "summary2"
+ assert cache.get_summary("file3.py", "hash3") == "summary3"
+ 
+ # Access file2.py, then add file4.py. file3.py should be evicted
+ cache.get_summary("file2.py", "hash2")
+ cache.set_summary("file4.py", "hash4", "summary4")
+ 
+ assert cache.get_summary("file3.py", "hash3") is None
+ assert cache.get_summary("file2.py", "hash2") == "summary2"
+ assert cache.get_summary("file4.py", "hash4") == "summary4"
+ 
+ if cache_dir.exists():
+  shutil.rmtree(cache_dir)
+
 if __name__ == "__main__":
  test_get_file_hash()
  test_summary_cache()
+ test_summary_cache_lru()
  print("Tests passed!")