docs(typedef): add $ref normalization step for TypeBox interop

TypeBox generates bare-name $ref values ("$ref": "Read") within
$defs blocks. The jsonschema crate requires full JSON Pointer paths
("$ref": "#/$defs/Read"). Verified by generating actual TypeBox
output and testing against jsonschema v0.46.5 — bare-name refs fail
with 'Resource is not present in a registry'.

Add a ~20-line normalize_refs() pre-processing step that rewrites
bare-name refs to full JSON Pointer paths at schema load time. The
normalization is idempotent — full paths pass through unchanged.

docs/architecture/crates/typedef/schema-layer.md

@@ -175,8 +175,8 @@ validator implementations.
 
 This is the same pattern as TypeBox's `TypeRegistry.Set` on the JS side.
 Same semantics, different language, same JSON Schema wire format. A
-TypeBox schema serialized to JSON feeds directly into
-`jsonschema::validator_for(&schema)` on the Rust side — zero translation.
+TypeBox schema serialized to JSON feeds into the typedef engine after a
+single pre-processing step: normalizing `$ref` values (see below).
 
 ## TypeBox Interop
 
@@ -192,10 +192,36 @@ const TensorRef = Type.Object({
 ```
 
 serialized to JSON is a standard JSON Schema with `type: "object"`,
-`properties`, and `required`. That JSON feeds directly into the typedef
-engine. The `TypeDef:*` custom keywords are added by TypeBox's
-`TypeRegistry.Set` — they appear in the serialized JSON as additional
-properties on the schema object.
+`properties`, and `required`. That JSON feeds into the typedef engine
+after `$ref` normalization. The `TypeDef:*` custom keywords are added by
+TypeBox's `TypeRegistry.Set` — they appear in the serialized JSON as
+additional properties on the schema object.
+
+### `$ref` normalization
+
+TypeBox generates bare-name `$ref` values (e.g., `"$ref": "Read"`),
+referencing sibling definitions within the same `$defs` block. The
+`jsonschema` crate requires full JSON Pointer paths (e.g.,
+`"$ref": "#/$defs/Read"`). The typedef engine normalizes TypeBox-style
+refs at schema load time:
+
+```rust
+fn normalize_refs(schema: &mut Value) {
+    // Walk the schema tree. For every "$ref" whose value is a bare name
+    // (no "#" prefix), rewrite it to "#/$defs/<name>".
+    // "$ref": "Read"  →  "$ref": "#/$defs/Read"
+}
+```
+
+This is a ~20-line recursive walk of the schema JSON. It runs once at
+load time, before the schema is passed to `jsonschema::validator_for`
+or the offset computation. The normalization is idempotent — full JSON
+Pointer refs pass through unchanged.
+
+**Verification:** The jsonschema crate (v0.46.5) rejects bare-name refs
+with `Resource 'Read' is not present in a registry`. Full JSON Pointer
+refs (`#/$defs/Read`) resolve correctly. The normalization step bridges
+the gap between TypeBox's output and jsonschema's input.
 
 The typedef engine does not depend on TypeBox or any JS toolchain. It
 consumes JSON — whether that JSON was authored in TypeBox, generated by