Move dataset review clarification into the assistant workspace and
rework the review page into a chat-centric layout with execution rails.
Add session-scoped assistant actions for mappings, semantic fields,
and SQL preview generation. Introduce optimistic locking for dataset
review mutations, propagate session versions through API responses,
and mask imported filter values before assistant exposure.
Refresh tests, i18n, and spec artifacts to match the new workflow.
BREAKING CHANGE: dataset review mutation endpoints now require the
X-Session-Version header, and clarification is no longer handled
through ClarificationDialog-based flows
- Replaced rigid TIERs with continuous COMPLEXITY 1-5 scale in semantics.md
- Updated generate_semantic_map.py to parse and score based on Complexity
- Added backward compatibility mapping for legacy TIERs
- Migrated all .ai/shots examples to use @COMPLEXITY and updated relation syntax
- Added trivial_utility.py shot to demonstrate implicit Complexity 1 token savings
