Also deleted the draft scripts for chunking/post‑processing/validation and the initial RAG chat/index draft
Left work/godot_rag/ empty for now, to avoid using incorrect outputs as a baseline
Recorded the reason for the cleanup as a retrospective
Determined that the problem was proceeding with chunking before sufficiently analyzing the original official‑document structure
The goal of using the entire Godot official documentation was corrupted by the LLM’s arbitrarily chosen “MVP core API” and hard‑coded/over‑engineered directions
Noted that, without my instruction, ChatGPT/Codex would arbitrarily narrow the scope or assume an answer before a step was finished and produce the next output
Concluded that when the provenance of LLM‑generated content, regex candidates, official‑document evidence, and user‑approved rules gets mixed, it cannot be used as a basis for labeler/RAG discriminators
Re‑documented the current architecture’s shortcomings
Static‑analysis layer is weak
No GDScript AST/parser‑based validation
Godot project dependency graph is weak
Execution/syntax validation is weak
Label taxonomy is still coarse
Distinguishing provenance between LLM‑generated content and verified answers is weak
Data leakage/duplicate‑removal design is weak
Reset the next work direction to the original analysis of godot_docs_full
Instead of immediately rebuilding the RAG or catalog, we will first analyze outputs/godot_docs_full/pages itself
Need to verify what Markdown structure each class reference, migration, and tutorial document uses
Must redesign which chunk granularity to use—page‑level, section‑level, or API‑member‑level—according to the Godot official‑document structure
Decided that a validation‑report standard should be defined before chunking