carlos patches

aggregate.py

@@ -98,24 +98,28 @@ def build_file_items(base_dir: Path, files: list[str]) -> list[dict]:
         entry    : str   (original config entry string)
         content  : str   (file text, or error string)
         error    : bool
+        mtime    : float (last modification time, for skip-if-unchanged optimization)
     """
     items = []
     for entry in files:
         paths = resolve_paths(base_dir, entry)
         if not paths:
-            items.append({"path": None, "entry": entry, "content": f"ERROR: no files matched: {entry}", "error": True})
+            items.append({"path": None, "entry": entry, "content": f"ERROR: no files matched: {entry}", "error": True, "mtime": 0.0})
             continue
         for path in paths:
             try:
                 content = path.read_text(encoding="utf-8")
+                mtime = path.stat().st_mtime
                 error = False
             except FileNotFoundError:
                 content = f"ERROR: file not found: {path}"
+                mtime = 0.0
                 error = True
             except Exception as e:
                 content = f"ERROR: {e}"
+                mtime = 0.0
                 error = True
-            items.append({"path": path, "entry": entry, "content": content, "error": error})
+            items.append({"path": path, "entry": entry, "content": content, "error": error, "mtime": mtime})
     return items
 
 def build_summary_section(base_dir: Path, files: list[str]) -> str:
@@ -126,6 +130,40 @@ def build_summary_section(base_dir: Path, files: list[str]) -> str:
     items = build_file_items(base_dir, files)
     return summarize.build_summary_markdown(items)
 
+def _build_files_section_from_items(file_items: list[dict]) -> str:
+    """Build the files markdown section from pre-read file items (avoids double I/O)."""
+    sections = []
+    for item in file_items:
+        path = item.get("path")
+        entry = item.get("entry", "unknown")
+        content = item.get("content", "")
+        if path is None:
+            sections.append(f"### `{entry}`\n\n```text\n{content}\n```")
+            continue
+        suffix = path.suffix.lstrip(".") if hasattr(path, "suffix") else "text"
+        lang = suffix if suffix else "text"
+        original = entry if "*" not in entry else str(path)
+        sections.append(f"### `{original}`\n\n```{lang}\n{content}\n```")
+    return "\n\n---\n\n".join(sections)
+
+
+def build_markdown_from_items(file_items: list[dict], screenshot_base_dir: Path, screenshots: list[str], history: list[str], summary_only: bool = False) -> str:
+    """Build markdown from pre-read file items instead of re-reading from disk."""
+    parts = []
+    # STATIC PREFIX: Files and Screenshots must go first to maximize Cache Hits
+    if file_items:
+        if summary_only:
+            parts.append("## Files (Summary)\n\n" + summarize.build_summary_markdown(file_items))
+        else:
+            parts.append("## Files\n\n" + _build_files_section_from_items(file_items))
+    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 build_markdown(base_dir: Path, files: list[str], screenshot_base_dir: Path, screenshots: list[str], history: list[str], summary_only: bool = False) -> str:
     parts = []
     # STATIC PREFIX: Files and Screenshots must go first to maximize Cache Hits
@@ -141,7 +179,7 @@ def build_markdown(base_dir: Path, files: list[str], screenshot_base_dir: Path,
         parts.append("## Discussion History\n\n" + build_discussion_section(history))
     return "\n\n---\n\n".join(parts)
 
-def run(config: dict) -> tuple[str, Path]:
+def run(config: dict) -> tuple[str, Path, list[dict]]:
     namespace = config.get("project", {}).get("name")
     if not namespace:
         namespace = config.get("output", {}).get("namespace", "project")
@@ -155,11 +193,11 @@ 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=False)
-    output_file.write_text(markdown, encoding="utf-8")
+    # Build file items once, then construct markdown from them (avoids double I/O)
     file_items = build_file_items(base_dir, files)
+    markdown = build_markdown_from_items(file_items, screenshot_base_dir, screenshots, history,
+                                         summary_only=False)
+    output_file.write_text(markdown, encoding="utf-8")
     return markdown, output_file, file_items
 
 def main():