The data model behind the symbol registry: per-symbol records, file-level hashes, call-graph edges, and the invalidation strategy that keeps it current.

Tree-Sitter tells you where a symbol is defined. It cannot tell you where it is called. That gap cost one pipeline run 33,000 tokens to find out.

A Haiku optimization made the L2 quality gate silently pass on every run. The fix was removing the LLM call entirely.

Not a model capability problem. An agent with the wrong codebase version produces output that is plausible but wrong in ways that are hard to catch.