Doing final pass of adjustments with anythingllm (aggregate.py)

aggregate.py

@@ -128,8 +128,7 @@ def build_summary_section(base_dir: Path, files: list[str]) -> str:
 
 def build_markdown(base_dir: Path, files: list[str], screenshot_base_dir: Path, screenshots: list[str], history: list[str], summary_only: bool = False) -> str:
     parts = []
-    if history:
-        parts.append("## Discussion History\n\n" + build_discussion_section(history))
+    # STATIC PREFIX: Files and Screenshots must go first to maximize Cache Hits
     if files:
         if summary_only:
             parts.append("## Files (Summary)\n\n" + build_summary_section(base_dir, files))
@@ -137,6 +136,9 @@ def build_markdown(base_dir: Path, files: list[str], screenshot_base_dir: Path,
             parts.append("## Files\n\n" + build_files_section(base_dir, files))
     if screenshots:
         parts.append("## Screenshots\n\n" + build_screenshots_section(screenshot_base_dir, screenshots))
+    # DYNAMIC SUFFIX: History changes every turn, must go last
+    if history:
+        parts.append("## Discussion History\n\n" + build_discussion_section(history))
     return "\n\n---\n\n".join(parts)
 
 def run(config: dict) -> tuple[str, Path]:
@@ -153,8 +155,9 @@ def run(config: dict) -> tuple[str, Path]:
     output_dir.mkdir(parents=True, exist_ok=True)
     increment = find_next_increment(output_dir, namespace)
     output_file = output_dir / f"{namespace}_{increment:03d}.md"
+    # Provide full files to trigger Gemini's 32k cache threshold and give the AI immediate context
     markdown = build_markdown(base_dir, files, screenshot_base_dir, screenshots, history,
-                              summary_only=True)
+                              summary_only=False)
     output_file.write_text(markdown, encoding="utf-8")
     file_items = build_file_items(base_dir, files)
     return markdown, output_file, file_items