db-engine-selection (M0) — recommend, don't score

M0 runs at design / /claude-db:start time, when there may be no schema yet — only a described workload. It answers "which database should this be?" It is not a scored module: it emits no findings, has no axis, no severity, and never enters score.mjs or either of the two scores. Its output is a separate recommendation contract (below). It walks the decision tree in references/engine-selection-tree.md.

Inputs it gathers

From the user's description (or detected stack via references/detection-signals.md):

• Access patterns — point lookups by key, range scans, complex multi-entity joins, full-text / semantic search, time-ordered analytics, graph traversal, fan-out reads/writes.
• Consistency & integrity needs — strong/transactional vs eventual; multi-row invariants; need for DB-enforced referential integrity.
• Scale & shape — expected size, write rate, read/write ratio, cardinality, whether data is append-only/time-series, vector/embedding workloads.
• Operability & team — managed vs self-hosted, serverless/edge, existing expertise, platform constraints (cross-checks db-platform-fit M21).