Docs: avoid naming the release in prose; site-test count is 73

Co-Authored-By: Claude Code <noreply@anthropic.com>

docs/README.md

@@ -36,7 +36,7 @@ for one customer could be chosen by anyone who found it — the bug that release
 fixed. **Show** is the weaker rule and reserves nothing: it offers the method
 to the group and leaves everyone else alone. 1.6.0 made show do both, which
 took ordinary methods away from strangers whenever they were listed beside a
-free one; 1.7.0 split them and turned every old show rule into only.
+free one; the next release split them and turned every old show rule into only.
 
 The plugin never leaves a customer with no shipping method at all. If applying
 the rules would empty the list, every method comes back.

docs/RELEASE.md

@@ -45,7 +45,7 @@ is loud, an id that belongs to something else is not.
 | --- | --- | --- |
 | `ci/static.sh` | syntax, guards, text domain, no secrets, every loaded file ships, one version everywhere, the two compat files agree, no tracked file writes a git identity, the docs still describe this tree | a count on every passing line |
 | `ci/selftest.sh` | **the checkers themselves** — see below | `all N assertions passed` |
-| `ci/site-test.sh` | a real WordPress + WooCommerce + MySQL install, this plugin activated, `tests/smoke.php` run through `wp eval-file` | `All 69 assertions passed`, floored at 60 by the caller |
+| `ci/site-test.sh` | a real WordPress + WooCommerce + MySQL install, this plugin activated, `tests/smoke.php` run through `wp eval-file` | `All 73 assertions passed`, floored at 60 by the caller |
 | `.github/workflows/compat.yml` | the matrix: PHP 7.4 / 8.3 / 8.4, WP latest and nightly, WC latest and beta | one job per cell |
 
 ## The checkers are themselves tested, and that is unusual