chore(bots): hand triage, review, tasks and rolls to the Playwright bot

.claude/skills/playwright-triage/SKILL.md

@@ -1,39 +1,23 @@
 ---
 name: playwright-triage
-description: Triage and fix one microsoft/playwright-python issue, or do a maintainer's task, unattended inside the Issue triage GitHub Actions workflow (.github/workflows/triage.yml), which a needs-triage, needs-triage-mac or needs-triage-win label starts, or a maintainer starts by hand with an issue, a task or both. Reproduces the issue on the runner, then leaves a verified fix proposal for the workflow to open as a draft PR, an investigation note for it to post on the issue, or an upstream bug report for a maintainer to file in microsoft/playwright. Only for that workflow.
+description: Triage and fix an issue in microsoft/playwright-python. How to use the upstream checkout, how to run a published version, how to tell a bug of the Python client from an upstream one, the upstream bug report, and what not to run from a PR of a third party.
 ---
 
 # Playwright Python Issue Triage
 
-You run unattended in the [Issue triage](../../../.github/workflows/triage.yml) workflow of
-`microsoft/playwright-python`. First read the shared guide, `$AGENT_GUIDES_DIR/triage.md`, a copy of
-[microsoft/playwright/.github/actions/run-agent/guides/triage.md](https://github.com/microsoft/playwright/blob/main/.github/actions/run-agent/guides/triage.md),
-and then [AGENTS.md](../../../AGENTS.md), both in full. The guide says how to triage an issue in any
-Playwright repo. AGENTS.md says how to build, test and lint this one, and where a regression test
-goes. This file covers what neither has: the checkouts, how to run a published version, and the
-outcome that this repo adds, an upstream bug report.
-
-## The checkouts
-
-`$REPO_DIR` is the checkout of `microsoft/playwright-python` that the guide describes. Its requirements
-are installed (`pip install -r local-requirements.txt`, `pip install -r requirements.txt`,
-`pip install -e .`), the wheel is built (`python -m build --wheel`, which builds the driver into
-`playwright/driver/`), and Chromium, Firefox and WebKit are installed with
-`python -m playwright install --with-deps`. It is the working directory, and the checkout that the
-guides refer to. The clone is shallow: run `git fetch --unshallow --tags origin` in it before you
-bisect or use `git tag --contains`.
-
-`$PLAYWRIGHT_DIR` is `$REPO_DIR/.upstream/`, a full clone of `microsoft/playwright` at the commit
-in `DRIVER_VERSION`, created by `python scripts/upstream.py checkout`. The driver was built from it.
-Read upstream code there. Do not edit, commit or switch branches in it: the wheel build and
-`./scripts/lint.sh` stop when it is not at that commit or has local changes. Before you run upstream
-tests in it, it needs `npm ci`, `npm run build` and `npx playwright install`. The wheel build
-(`scripts/build_driver.py`) ran the first two there; run them again when `node_modules/` is missing.
+## Upstream
+
+`.upstream/` is the clone of `microsoft/playwright` at the commit in `DRIVER_VERSION`, as
+[AGENTS.md](../../../AGENTS.md) says. The driver is built from it. Read upstream code there. Do not
+edit, commit or switch branches in it: the wheel build and `./scripts/lint.sh` stop when it is not
+at that commit or has local changes. Before you run upstream tests in it, it needs `npm ci`,
+`npm run build` and `npx playwright install`. The wheel build (`scripts/build_driver.py`) runs the
+first two there; run them again when `node_modules/` is missing.
 
 ## Published versions
 
-To run a published version, for example to bisect, create `$SCRATCH_DIR/playwright-python-<n>/<version>/`
-and run there:
+To run a published version, for example to bisect, create an empty directory outside the repo for
+each version, and run there:
 
 ```bash
 python -m venv env && source env/bin/activate   # env\Scripts\activate on Windows
@@ -43,41 +27,38 @@ python -m playwright install
 
 The fixtures of the repo are not available there. Write the condensed repro as a plain script with
 `sync_playwright()` or `async_playwright()` in that directory, with `page.set_content()` in place of
-the test server, and run it from there. In `$REPO_DIR`, the source tree shadows the installed package.
+the test server, and run it from there. In this repo, the source tree shadows the installed
+package.
 
 The driver of a release is in `DRIVER_VERSION` at its tag: `git show v<version>:DRIVER_VERSION`
 prints the upstream commit it was built from, or, for releases up to 1.64, the `playwright-core`
 version of the driver; `npm view playwright-core@<core version> gitHead` prints its commit. Match a
-regression in the driver to commits with `git -C $PLAYWRIGHT_DIR log <good>..<bad> -- <path>`.
+regression in the driver to commits with `git -C .upstream log <good>..<bad> -- <path>`.
 
 ## Upstream bugs
 
-The client talks to the Node driver that is built from `$PLAYWRIGHT_DIR`, and `microsoft/playwright`
+The client talks to the Node driver that is built from `.upstream/`, and `microsoft/playwright`
 and this repo are one team. Reproduce the bug in Python first. Then write the same calls as an
-upstream test and run it in `$PLAYWRIGHT_DIR`. The triage skill of `microsoft/playwright`, in
-`$PLAYWRIGHT_DIR/.claude/skills/playwright-triage/`, says where such a test goes, which fixtures it
-uses and how to run it. The rest of that skill is not for this run. Put the test in a new spec
-file, and delete the file when you are done, so that the checkout is clean.
+upstream test and run it in `.upstream/`. The triage skill of `microsoft/playwright`, in
+`.upstream/.claude/skills/playwright-triage/`, says where such a test goes, which fixtures it uses
+and how to run it. Use only those parts of it. Put the test in a new spec file, and delete the file
+when you are done, so that the checkout is clean.
 
 - The Node test passes: the bug is in the Python client. Fix it here.
 - The Node test fails too: the root cause is upstream, and the fix lands in `microsoft/playwright`.
-  Do not work around it in `playwright/_impl/`. Run `git -C $PLAYWRIGHT_DIR fetch origin main`.
-  When `git -C $PLAYWRIGHT_DIR log HEAD..origin/main -- <path>` shows a fix that already landed,
-  the note says that it reaches this repo with the next roll. Otherwise write the report.
+  Do not work around it in `playwright/_impl/`. Run `git -C .upstream fetch origin main`. When
+  `git -C .upstream log HEAD..origin/main -- <path>` shows a fix that already landed, it reaches
+  this repo with the next roll: say so. Otherwise write the report.
 - The Python API lacks a member or an option: the generated API has everything that the upstream
-  docs in `$PLAYWRIGHT_DIR/docs/src/api` give Python (`* langs:` decides; no `langs` means every
+  docs in `.upstream/docs/src/api` give Python (`* langs:` decides; no `langs` means every
   language). The gap is in the docs, so it is an upstream change too. Do not edit a generated file,
   and do not add to `scripts/codegen/python_rules.js` to go around the docs.
 
 The report is for an engineer of `microsoft/playwright` who did not read the Python issue: what
 fails, expected versus actual, the versions (the Python package, the commit in `DRIVER_VERSION`, the
 browser, the platform), the root cause when you found it, and the condensed Node test as the repro.
 The title has at most 256 characters, for example `route.fulfill() drops the charset of
-Content-Type`.
-
-The bot never files it in `microsoft/playwright`: this run allows no `issue` call (the calls are
-in `$AGENT_GUIDES_DIR/calls.d.ts`). Put the report at the end of your comment, for a maintainer to
-file, in this form:
+Content-Type`. A maintainer files it in `microsoft/playwright`. Give it in this form:
 
 `````markdown
 Upstream bug report, for a maintainer to file in microsoft/playwright:
@@ -94,7 +75,7 @@ Upstream bug report, for a maintainer to file in microsoft/playwright:
 </details>
 `````
 
-Write the rest of the comment as the note: the verdict, the evidence, and that the bug is upstream.
+With it, give the verdict, the evidence, and that the bug is upstream.
 
 ## PRs from third parties
 

.github/workflows/review.yml

@@ -0,0 +1,33 @@
+# Hands the pull request to the Playwright bot when a maintainer applies agent-review. Nothing
+# else of the bot lives in this repo. Apply the label again to start another run.
+name: "Agent: review"
+
+on:
+  # Runs from the default branch, for PRs from forks too. It never checks out the PR.
+  pull_request_target:
+    types: [labeled]
+
+permissions: {}
+
+jobs:
+  pr:
+    name: Hand the PR to the bot
+    if: github.repository_owner == 'microsoft' && github.event.label.name == 'agent-review'
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    steps:
+    - uses: actions/create-github-app-token@64ab729a6294000f5aa4a4bc0b73d1f32bc45510 # v3.3.0
+      id: app-token
+      with:
+        client-id: ${{ vars.PLAYWRIGHT_APP_CLIENT_ID }}
+        private-key: ${{ secrets.PLAYWRIGHT_PRIVATE_KEY }}
+        owner: microsoft
+        repositories: devops.playwright.dev
+        permission-actions: write
+    - name: Start the bot
+      env:
+        GH_TOKEN: ${{ steps.app-token.outputs.token }}
+        NUMBER: ${{ github.event.pull_request.number }}
+      run: >-
+        gh workflow run pr.yml --repo microsoft/devops.playwright.dev --ref main
+        -f repo="$GITHUB_REPOSITORY" -f pr="$NUMBER"