docs: #216 cycle-close audit — run-transcript regimes + glossary avoid reconcile

refs #216

Architect drift review over 68317ec..6e22c98 (two items, both fixed here;
code and ledger verified drift-clean):

- The authoring guide's 'Register and run' transcript still showed the
  pre-regime world (2 cells, regime-less family ids) directly under the
  worked example this cycle made two-regime / 4-cell. The transcript now
  shows the -r1 family-id suffix, per-cell regime fields (ordinal 0
  serialize-skipped, the established byte-stability pattern), the four
  cells, per-regime generalization entries, and a prose paragraph tying
  the 4 cells to the validate count (regimes compared, never pooled).
- The fresh glossary entry declared 'Avoid: stop regime' while this very
  cycle ships 'stop regimes' in its hint strings and guide prose — an
  Avoid line the codebase itself violates records intent, not reality.
  'stop regime' is dropped from Avoid ('risk section' stays: it wrongly
  suggests a section rather than an axis list).

What holds (architect): content-id parity untouched (probe is read-only,
canonical bytes unchanged); the validate cell product mirrors the exec
cross-product exactly; all six spec acceptance criteria shipped.

Regression: cargo test --workspace 62 result groups / 0 failures; clippy
-D warnings clean; cargo doc 0 warnings (all at 6e22c98; this commit is
docs-only).

docs/glossary.md

@@ -212,7 +212,7 @@ The per-symbol composite turning a bias into a managed position, **in R**: `stop
 A node that converts a finer stream to a coarser bar stream, emitting a completed bar only at the boundary so no partial bar ever leaks (enforcing no look-ahead). Clock-sensitive.
 
 ### risk regime
-**Avoid:** stop regime, risk section
+**Avoid:** risk section
 One entry of a campaign document's structural risk axis (`risk`): a
 serializable protective-stop regime (sole variant `vol{length,k}`) the matrix
 runs every cell under, so cells differ by execution discipline, never by