thermo-nuclear-code-quality-review

# Strict Code Quality Review This is an unusually demanding review mode, not an instruction to rewrite code by taste. Inspect the current diff and surrounding architecture, then report only high-conviction findings grounded in a contract, reachable behavior, or a material maintainability risk. ## Review Bar Ask: - Can a simpler ownership boundary remove whole branches or concepts? - Did the diff add ad-hoc flags, special cases, or feature logic to a shared path instead of using the canonical layer? - Did a cohesive module become more coupled or cross a meaningful shape limit? - Are wrappers, casts, optionality, and sequential orchestration earning their complexity? - Does a proposed decomposition reduce what a reader must hold in mind, rather than merely move the same complexity into more files? A file crossing roughly 1000 lines is a strong signal to inspect decomposition, not an automatic failure. Apply the project's actual shape policy and explain why a split would improve ownership. Do not manufacture a rewrite when the current structure is coherent and the change is small. ## Output Report findings in this order: 1. structural regressions; 2. missing simplifications with a concrete alternative; 3. spaghetti or branching growth; 4. boundary and type-contract problems; 5. file shape and decomposition; 6. lower-severity readability issues. For each finding include file/line, contract or evidence, user/operator impact, and a concrete remedy. Separate `BLOCKER`...