idea_world_labDEV JOURNAL
Friday, June 26, 2026

June 26, 2026

  • Based on docs/roadmaps/2026-06-25-source-analysis-scoring-architecture.md, I organized the flow that passes prompts and source‑code input to the AST Parser
    • Prompts are separated from AST syntax analysis and directed toward analysis intent and Retriever/LLM judgment
    • The AST Parser receives source code, file path, file type, original hash, and other source metadata
    • Retriever should search the vector DB based on APIs, symbols, identifiers, and prompt intent words extracted from code fragments, not on file paths
    • The document written today needs to be reviewed again tomorrow, especially to ensure that the boundaries of AST fragments, direct chunks, Retriever queries, and trace metadata remain consistent throughout the document
    • Roadmap: Flow that passes source code input to AST analysis
    • Retrospective: docs/retrospectives/2026-06-26.md