Ask for the model and harness used in AI-assisted pull requests (#6321)

* Ask for the model and harness used in AI-assisted PRs

Add an AGENTS.md rule that agents name the model and harness in the PR
description, and a matching line under the LLM checkbox in the pull
request template so human contributors fill it in too.

* Only let agents fill the LLM line of the PR template

Agents leave the description template to the developer and only fill in
the LLM line with the model and harness used.

.github/PULL_REQUEST_TEMPLATE.md

@@ -4,6 +4,7 @@
 - [ ] I am aware of the [etiquette](https://github.com/element-hq/element-x-ios/blob/develop/CONTRIBUTING.md#etiquette).
 - [ ] Pull request contains a [changelog label](https://github.com/element-hq/element-x-ios/blob/develop/CONTRIBUTING.md#changelog).
 - [ ] This PR has been made with the help of an LLM.
+  - Model and harness used: <!-- e.g. Claude Opus 5.5 with Claude Code -->
 
 **UI changes have been tested with:**
 - [ ] iPhone and iPad simulators in portrait and landscape orientations.

AGENTS.md

@@ -60,6 +60,7 @@ PRs must follow rules. Prefer Xcode MCP tools over terminal commands.
 - Exactly one `pr-` label (see `.github/release.yml`).
 - Title = changelog entry — descriptive, no "Fixes #…".
 - Leave description template for developer. Point them to [contributing etiquette](CONTRIBUTING.md#etiquette).
+- Only fill template LLM line: tick box, name model + harness that made PR (e.g. Claude Opus 5.5, Claude Code).
 - Screenshots/videos for visual changes.
 - 500 additions max — split big changes.
 - Commits need title + description. No tiny commits, no massive commits.