@coco.fn
async def aggregate_project_info(
project_name: str,
file_infos: list[CodebaseInfo],
) -> CodebaseInfo:
"""Aggregate multiple file extractions into a project-level summary."""
if not file_infos:
return CodebaseInfo(name=project_name, summary="Empty project with no Python files.")
if len(file_infos) == 1:
info = file_infos[0]
return CodebaseInfo(
name=project_name,
summary=info.summary,
public_classes=info.public_classes,
public_functions=info.public_functions,
mermaid_graphs=info.mermaid_graphs,
)
files_text = "\n\n".join(
f"### {info.name}\n"
f"Summary: {info.summary}\n"
f"Classes: {', '.join(c.name for c in info.public_classes) or 'None'}\n"
f"Functions: {', '.join(f.name for f in info.public_functions) or 'None'}"
for info in file_infos
)
all_graphs = [g for info in file_infos for g in info.mermaid_graphs]
prompt = f"""Aggregate the following Python files into a project-level summary.
Project name: {project_name}
Files:
{files_text}
Create a unified CodebaseInfo that:
1. Summarizes the overall project purpose
2. Lists the most important public classes across all files
3. Lists the most important public functions across all files
4. For mermaid_graphs: create a single unified graph showing how the CocoIndex
components connect across the project
"""
result = await _instructor_client.chat.completions.create(
model=LLM_MODEL,
response_model=CodebaseInfo,
messages=[{"role": "user", "content": prompt}],
)
result = CodebaseInfo.model_validate(result.model_dump())
if not result.mermaid_graphs and all_graphs:
result.mermaid_graphs = all_graphs
return result
