Merge pull request #19 from script-development/chore/codeowners

chore: add CODEOWNERS routing to phpstan-warroom-admins (Sapper M1 #5)

Author: Goosterhof

.github/CODEOWNERS

@@ -0,0 +1,9 @@
+# CODEOWNERS — phpstan-warroom-rules
+#
+# All changes to this repository require review from @script-development/phpstan-warroom-admins.
+# A separate rule-authors team is intentionally not split out today — the admins team and
+# the rule-design reviewer set are identical at the current shop size. Revisit if the
+# contributor base grows beyond the current 6 admins or if rule-design review becomes
+# a distinct concern from operational repo administration.
+
+* @script-development/phpstan-warroom-admins

CHANGELOG.md

@@ -13,6 +13,7 @@ The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and
 ### Changed
 
 - **Doctrine:** corrected publish-channel framing in `CLAUDE.md` (L11 and the Release process section) and the `release.yml` header comment. Public packagist.org has no OIDC Trusted Publishing option today — OIDC is a Private Packagist–only feature (`packagist/artifact-publish-github-action`, GA February 2026). The package's actual publish channel is the standard `https://packagist.org/api/github` push-event webhook (`dev-*` aliases on branch push, versioned releases on tag push via `release.yml`). Migration to Private Packagist would change ally-side Composer consumption (private repo URL + token in `composer.json`) and is a commercial decision; tracking continues on Issue #11. Closes Sapper M1 Finding #2 (doctrine drift on publish channel) and resolves Issue #11 audit. **Versioning:** none (doctrine alignment, no consumer-visible behaviour).
+- **Governance:** added `.github/CODEOWNERS` routing all changes to `@script-development/phpstan-warroom-admins`. A separate rule-authors team is intentionally not split out today — the admins team and the rule-design reviewer set are identical at the current shop size; revisit if the contributor base grows or rule-design review becomes a distinct concern from operational repo administration. Pairs with branch-protection update enabling `require_code_owner_reviews=true`. Closes Sapper M1 Finding #5 (no CODEOWNERS file). **Versioning:** none (governance change, no consumer-visible surface).
 - **`LogRule` (BREAKING):** extended to cover the static-call shapes `Model::destroy(...)` and `Model::forceDestroy(...)` on Log-named classes. `getNodeType()` broadened from `MethodCall::class` to `CallLike::class` and `processNode` branches on `MethodCall` vs `StaticCall`. Both shapes emit the same `logRule.logModification` identifier so consumer `phpstan.neon` `ignoreErrors` entries cover the whole rule with one identifier (the previous rule's compliance teeth depended on `delete`/`forceDelete` instance shapes; on a non-soft-delete log model `Model::destroy([1])` purges and `Model::forceDestroy([1])` always purges — both slipped through). `DB::table('logs')->truncate()` is intentionally still out of scope — Builder receiver type carries no Log-named class reference and the table name lives in a string argument; matching that needs a shape-specific call-chain rule. Tracked separately. Versioning: per ADR-0021 §Versioning, this is a Major bump (new errors in code that previously passed); within 0.x this ships as `v0.3.0`. **Pre-cascade audit required across emmie, kendo, entreezuil, ublgenie before tagging** — surface any `::destroy(`/`::forceDestroy(` calls on Log-named classes and route operational-log false positives to consumer-side `phpstan.neon` `ignoreErrors` (same convention used in v0.2.0 for `ublgenie/app/Actions/DeleteBranch.php`). Resolves issue #4.
 - **CI:** added PHP 8.5 to the `ci.yml` and `release.yml` test matrices alongside 8.4 (`['8.4']` → `['8.4', '8.5']`). PHP 8.5.0 was released 2025-11-20; the war-room dev environment already runs 8.5.5 locally, so PRs were getting ad-hoc 8.5 coverage during pre-push but no CI signal. Adding (rather than replacing) keeps 8.4 — the `composer.json` `^8.4` contractual minimum — covered. `shivammathur/setup-php@v2` supports 8.5 since GA. Resolves issue #5.
 - **CI:** added line-coverage measurement and a threshold gate. `ci.yml` switches `coverage: none` → `coverage: pcov` on both 8.4 and 8.5 matrix legs (PCOV is line-coverage-only and faster than Xdebug — debugger features aren't needed). New composer scripts: `test:coverage` (runs PHPUnit with `--coverage-clover=build/logs/clover.xml --coverage-text`) and `coverage:check` (runs `bin/coverage-check.php`, a standalone clover parser — no extra runtime dependency added to a static-analysis package for a single CI gate). Two new CI steps replace the `Tests` step: **Tests with coverage** and **Coverage threshold gate**. Clover XML is uploaded as a per-leg artifact (`clover-php-${{ matrix.php }}`, 14-day retention) so reviewers can inspect uncovered lines without spelunking through workflow logs. **Initial threshold: 83%** — the measured baseline is 83.92% (240/286 lines across `src/`), set 0.92 percentage points lower to absorb trivial fluctuation on equivalent-but-renamed code. Class coverage (0/6) and method coverage (39%) are intentionally unmeasured by the gate v1; per the issue's deliberation, line coverage is the right v1 signal and branch/method coverage is a follow-up after the line gate is bedded in. The 16-percentage-point gap to 100% audits as defensive guard clauses on unexpected node shapes (the kind of branch the issue itself flagged as "genuinely hard to fixture" — `LogRule`'s static-call branch falls back when `$node->class` is `Expr` rather than `Name`); a follow-up issue will audit and ratchet the threshold upward to 90%+. Versioning: none (pure CI/test-infra, no consumer-visible behaviour). Resolves issue #9.