workflow: scrub residual JOURNAL/journal refs missed in the first sweep

A re-grep found 15 live references (excluding docs/specs/ and
docs/plans/, which stay historical) the previous two commits
missed — all in source comments, doctests, bench helpers, and one
agent file.

Per-file:
- crates/ail/src/main.rs: typeclass-coherence diagnostic comment
  pointed at "the JOURNAL queue's wording" — points at
  design/contracts/typeclasses.md alone.
- crates/ailang-prose/src/lib.rs: `//!` header referred to
  docs/JOURNAL.md "Pinned: human-readable prose surface" —
  retargeted to design/contracts/authoring-surface.md.
- crates/ailang-check/src/lib.rs: bugfix tag + "see iter
  method-dispatch-refactor journal" prose collapsed to a clean
  rationale paragraph; the canonical shape is stated inline.
- crates/ailang-surface/tests/prelude_decouple_carve_out_pin.rs:
  "(d) record the rationale in a per-iter journal" →
  "(d) record the rationale in the commit body".
- crates/ailang-surface/tests/prelude_module_hash_pin.rs: header
  collapsed (pd.2/pd.3 milestone narrative dropped — the test's
  purpose is self-evident from its body); both "per-iter journal"
  drift-instructions point at the commit body.
- runtime/rc.c: "bench numbers in JOURNAL 18f.2" →
  "original profiling bench numbers".
- bench/run.sh: two "JOURNAL entry" comments → "commit body".
- bench/architect_sweeps.sh: header rewritten (cross-ref to the
  design-md-consolidation milestone commits, not a JOURNAL entry).
  Sweep-4 extended with two new anti-regrowth phrases
  ("see the per-iter journal", "in a per-iter journal") so journal
  prose can't grow back into design/contracts/ silently.
- skills/audit/agents/ailang-architect.md: "unlike a journal it
  lives on main" → "since it lives on main".
- ail-embed/src/bin/timeshard_runner.rs: "records it in the
  close-out journal" → "prints it to stderr".
- ail-embed/tests/timeshard.rs: two "journal-only friction timing"
  → "stderr-only friction timing".

Verification (after the edit):
- `grep -rin '\bjournal\b'` against live tree returns exactly two
  hits: the Sweep-4 regex itself (intentional — TABU phrases that
  prevent regrowth) and the PHRASES array in design_index_pin.rs
  (intentional — the same regrowth guard at test level). Both are
  load-bearing negative assertions.
- `bash bench/architect_sweeps.sh` exits 0 ("All five sweeps
  clean") — no design/-side regrowth.
- `cargo build --workspace` green; `cargo test --workspace` green.

ail-embed/tests/timeshard.rs

@@ -13,7 +13,7 @@
 //!      is host arithmetic, NOT a kernel property — asserting it
 //!      bit-exact would be WRONG, per the spec).
 //! Plus the global leak-Σ (deterministic since dbd76e5) and a
-//! journal-only friction timing capture (NO bench gate).
+//! stderr-only friction timing capture (NO bench gate).
 //!
 //! Concrete pin: EURUSD, months 2017-03 / 2017-04 / 2017-05 (all
 //! present on /mnt, contiguous, no gaps — recon-verified). data-server
@@ -217,7 +217,7 @@ fn timeshard_boundary_invisibility_and_leak_free() {
         "globally leak-free: Σallocs==Σfrees across {seen} stat line(s)"
     );
 
-    // Friction harvest: journal-only observation, NO assertion (the
+    // Friction harvest: stderr-only observation, NO assertion (the
     // value feeds the P2 batch-crossing decision; it is not a gate).
     if let Some(tl) = stdout.lines().find(|l| l.starts_with("TIMING ")) {
         eprintln!("m5.3 friction-harvest: {tl} (Σn={sum_n})");