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-campaign/tests/metric_vocabulary_e2e.rs

@@ -85,7 +85,7 @@ fn metric_vocabulary_covers_all_shipped_scalar_metrics() {
     scalar_fields.extend(selection_scalars);
 
     let vocabulary: BTreeSet<String> =
-        aura_research::metric_vocabulary().iter().map(|s| s.to_string()).collect();
+        aura_research::metric_vocabulary().iter().map(|m| m.id.to_string()).collect();
 
     let missing_from_vocabulary: Vec<_> = scalar_fields.difference(&vocabulary).collect();
     let stale_in_vocabulary: Vec<_> = vocabulary.difference(&scalar_fields).collect();
@@ -128,7 +128,7 @@ fn rankable_roster_is_single_sourced_and_nested() {
     }
     for name in aura_campaign::PER_MEMBER_METRICS {
         assert!(
-            aura_research::metric_vocabulary().contains(name),
+            aura_research::metric_vocabulary().iter().any(|m| m.id == *name),
             "per-member metric '{name}' missing from the research vocabulary"
         );
     }