feat(runner, cli, research): metric/tap schema carriers + the C29 coverage walk

C29 compile/unit seam, tasks 6-10 -- iteration 1 of the self-description
plan complete: every engine-shipped vocabulary entry now carries a
gate-clean one-line meaning.

- aura-runner: the internal tap recording sink threads its doc (the
  last unthreaded NodeSchema site) -- first full workspace build since
  the field became required.
- aura-cli scaffold: the sample node's template carries a doc line plus
  a maintenance comment, so every scaffolded extension crate starts
  gate-clean; both extension-vocabulary fixture exemplars thread real
  meaning lines (the load seam walks these in iteration 2). New E2E:
  the scaffold's own doc must pass its own gate -- an alibi doc in the
  template would teach the wrong pattern to every new project, and the
  compiler checks only the field's presence, never its shape.
- aura-research: metric_vocabulary()/tap_vocabulary() promote from bare
  name arrays to MetricSchema/TapSchema carriers (id + doc, 17 + 4
  authored lines); callers adapt to .id with byte-identical output
  (introspection goldens unchanged). The #190 guard keeps its triple --
  the doc column adds no fourth roster site.
- Coverage: tests/self_description.rs walks all five vocabularies
  (blocks, metrics, taps, folds, std nodes) through doc_gate -- the
  guard that keeps any future edit from blanking a doc.

Adjudicated review residue: the 17 metric doc strings are surfaced by
no CLI path yet -- deliberate; task 8 pins callers byte-identical, the
surfacing belongs to the CLI self-description work (#315). Plan-cited
coordinates lib.rs:1003/:1283 resolved to the real caller sites
(:1019/:1299); the plan's literal test code was reconciled to the real
accessors (FoldRegistry::core().roster(), Env::std()).

Gates: cargo test --workspace green (0 failed, incl. the new coverage
walk + scaffold E2E); cargo clippy --workspace --all-targets --
-D warnings clean.

refs #316

crates/aura-cli/src/research_docs.rs

@@ -92,9 +92,10 @@ fn guard_one_mode(cmd: &DocIntrospectCmd, family: &str) {
 /// vocabulary, but the mode rides the shared introspect struct and answers
 /// for both families.
 fn print_metric_roster() {
-    for name in aura_research::metric_vocabulary() {
-        let rankable = aura_campaign::RANKABLE_METRICS.contains(name);
-        let gate = aura_campaign::PER_MEMBER_METRICS.contains(name);
+    for m in aura_research::metric_vocabulary() {
+        let name = m.id;
+        let rankable = aura_campaign::RANKABLE_METRICS.contains(&name);
+        let gate = aura_campaign::PER_MEMBER_METRICS.contains(&name);
         // The generalize applicability is the registry's own R-expectancy
         // predicate — no fourth roster site (#190/#207).
         let generalize = aura_registry::check_r_metric(name).is_ok();
@@ -181,7 +182,7 @@ pub(crate) fn doc_fault_prose(f: &DocFault) -> String {
         DocFault::UnknownEmitKind(kind) => format!("presentation.emit: unknown kind \"{kind}\""),
         DocFault::UnknownTap { index, tap } => format!(
             "presentation.persist_taps[{index}]: unknown tap \"{tap}\" (taps: {})",
-            tap_vocabulary().join(" | ")
+            tap_vocabulary().iter().map(|t| t.id).collect::<Vec<_>>().join(" | ")
         ),
         DocFault::UnknownBindingColumn { role, column } => format!(
             "data.bindings.{role}: \"{column}\" names no archive column (columns: {})",