From 321810438bad5da19a60b4c5dc72c237eea4c535 Mon Sep 17 00:00:00 2001
From: Ed_ <edwardgz@gmail.com>
Date: Mon, 4 May 2026 04:44:11 -0400
Subject: [PATCH] feat(aggregation): Implement hash-based summary cache

---
 src/summarize.py            | 12 +++++++-
 src/summary_cache.py        | 55 +++++++++++++++++++++++++++++++++++++
 tests/test_summary_cache.py | 46 +++++++++++++++++++++++++++++++
 3 files changed, 112 insertions(+), 1 deletion(-)
 create mode 100644 src/summary_cache.py
 create mode 100644 tests/test_summary_cache.py

diff --git a/src/summarize.py b/src/summarize.py
index c81357f..058d4fd 100644
--- a/src/summarize.py
+++ b/src/summarize.py
@@ -27,6 +27,9 @@ import ast
 import re
 from pathlib import Path
 from typing import Callable, Any
+from src.summary_cache import SummaryCache, get_file_hash
+
+_summary_cache = SummaryCache()
 
 # ------------------------------------------------------------------ per-type extractors
 
@@ -153,10 +156,17 @@ def summarise_file(path: Path, content: str) -> str:
     Return a compact markdown summary string for a single file.
     `content` is the already-read file text (or an error string).
     """
+ content_hash = get_file_hash(content)
+ cached = _summary_cache.get_summary(str(path), content_hash)
+ if cached:
+  return cached
+
  suffix = path.suffix.lower() if hasattr(path, "suffix") else ""
  fn = _SUMMARISERS.get(suffix, _summarise_generic)
  try:
-  return fn(path, content)
+  summary = fn(path, content)
+  _summary_cache.set_summary(str(path), content_hash, summary)
+  return summary
  except Exception as e:
   return f"_Summariser error: {e}_"
 
diff --git a/src/summary_cache.py b/src/summary_cache.py
new file mode 100644
index 0000000..548e410
--- /dev/null
+++ b/src/summary_cache.py
@@ -0,0 +1,55 @@
+import hashlib
+import json
+from pathlib import Path
+from typing import Optional, Dict
+
+def get_file_hash(content: str) -> str:
+ """Returns SHA256 hash of the content."""
+ return hashlib.sha256(content.encode("utf-8")).hexdigest()
+
+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):
+  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.cache: Dict[str, Dict[str, str]] = {}
+  self.load()
+
+ def load(self) -> None:
+  """Loads cache from disk."""
+  if self.cache_file.exists():
+   try:
+    with open(self.cache_file, "r", encoding="utf-8") as f:
+     self.cache = json.load(f)
+   except Exception:
+    self.cache = {}
+
+ def save(self) -> None:
+  """Saves cache to disk."""
+  try:
+   self.cache_file.parent.mkdir(parents=True, exist_ok=True)
+   with open(self.cache_file, "w", encoding="utf-8") as f:
+    json.dump(self.cache, f, indent=1)
+  except Exception:
+   pass
+
+ def get_summary(self, file_path: str, content_hash: str) -> Optional[str]:
+  """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")
+  return None
+
+ def set_summary(self, file_path: str, content_hash: str, summary: str) -> None:
+  """Stores summary in cache and saves to disk."""
+  self.cache[file_path] = {
+   "hash": content_hash,
+   "summary": summary
+  }
+  self.save()
diff --git a/tests/test_summary_cache.py b/tests/test_summary_cache.py
new file mode 100644
index 0000000..2cda9f4
--- /dev/null
+++ b/tests/test_summary_cache.py
@@ -0,0 +1,46 @@
+import os
+import shutil
+from pathlib import Path
+from src.summary_cache import SummaryCache, get_file_hash
+
+def test_get_file_hash():
+ content = "hello world"
+ # sha256 of "hello world"
+ expected = "b94d27b9934d3e08a52e52d7da7dabfac484efe37a5380ee9088f7ace2efcde9"
+ assert get_file_hash(content) == expected
+
+def test_summary_cache():
+ cache_dir = Path(".test_cache")
+ if cache_dir.exists():
+  shutil.rmtree(cache_dir)
+ cache_file = cache_dir / "cache.json"
+ 
+ cache = SummaryCache(str(cache_file))
+ 
+ file_path = "test.py"
+ content = "print('hello')"
+ content_hash = get_file_hash(content)
+ summary = "**Python** - 1 lines"
+ 
+ # Test empty cache
+ assert cache.get_summary(file_path, content_hash) is None
+ 
+ # Test set and get
+ cache.set_summary(file_path, content_hash, summary)
+ assert cache.get_summary(file_path, content_hash) == summary
+ 
+ # Test cache invalidation
+ assert cache.get_summary(file_path, "different_hash") is None
+ 
+ # Test persistence
+ cache2 = SummaryCache(str(cache_file))
+ assert cache2.get_summary(file_path, content_hash) == summary
+ 
+ # Cleanup
+ if cache_dir.exists():
+  shutil.rmtree(cache_dir)
+
+if __name__ == "__main__":
+ test_get_file_hash()
+ test_summary_cache()
+ print("Tests passed!")