playwright-e2e-mcp 0.5.1 → 0.6.1

package/skill/playwright-e2e-mcp/references/tools.md

@@ -68,7 +68,8 @@ becomes the last run for `get-failure`, `suggest-fix` and `diagnose-flaky`.
 | `view` | `elements` \| `locators` \| `aria` | `locators`: compact map of interactive elements with verified locators; `aria` (0.5.0+): accessibility snapshot of the page or of `selector`, with a `toMatchAriaSnapshot` assertion |
 | `storageState` | string | Playwright storageState JSON inside the project (signed-in session); defaults to `PW_MCP_STORAGE_STATE` |
 | `headers` | object | Extra HTTP headers |
-| `actions` | array | Up to 20 steps after load: `{ type: click\|dblclick\|fill\|press\|check\|uncheck\|select\|hover\|wait\|goto, locator?, value?, url?, ms? }` |
+| `actions` | array | Up to 20 steps after load: `{ type: click\|dblclick\|fill\|press\|check\|uncheck\|select\|hover\|wait\|goto, locator?, value?, url?, ms? }`. Locators may start with `frameLocator('#frame')` or use `.contentFrame()` for iframes (0.6.1+) |
+| `actionTimeoutMs` | number | How long each action waits for its element (0.6.1+, default 10000) |
 | `routes` | array | Up to 20 network mocks before load, first match wins: `{ url (glob), method?, status?, json? \| body?, contentType?, headers?, abort?, delayMs? }` (0.5.0+). The result reports hits per mock |
 | `har` | object | `{ path, mode?: replay\|record, url?, notFound?: abort\|fallback }` (0.5.0+): replay requests from a HAR inside the project, or record the traffic to one. `routes` still win |
 | `browser` | `chromium` \| `firefox` \| `webkit` | Engine (0.5.0+, default chromium); must be installed |
@@ -245,3 +246,35 @@ Reads `.playwright-e2e-mcp/history.jsonl`, written by every run
 passing runs and flags ones that got slower; `trend` shows failed and flaky
 executions per day; `commits` names, per failing or flaky test, the first bad
 commit after its last passing streak and the last good one.
+
+## audit-tests (0.6.0+)
+
+| Argument | Type | Notes |
+| --- | --- | --- |
+| `testDir` / `filter` | string | Narrow the files |
+| `minSeverity` | `low` \| `medium` \| `high` | Default `low` |
+| `historyRuns` | number | Default 50 |
+| `limit` | number | Findings listed, default 50 |
+| `fix` | boolean | Rewrite mechanical findings, re-run touched files, revert on failure |
+| `verify` | boolean | Default true |
+
+Rules: `hard-wait`, `sleep`, `non-retrying-assertion`, `missing-await`,
+`focused-test` (high); `force-action`, `networkidle`, `element-handle`,
+`fragile-selector`, `no-timeout` (medium); `hardcoded-url`, `serial-mode` (low).
+Only `non-retrying-assertion`, `missing-await` and `focused-test` are fixed
+mechanically. Files rank by findings weighted by their flaky rate in the history.
+
+## bisect-failure (0.6.0+)
+
+| Argument | Type | Notes |
+| --- | --- | --- |
+| `test` | string | Spec file (required) |
+| `grep` | string | Test title; better than `:line` across commits |
+| `good` / `bad` | string | Commits or refs; `good` defaults to the newest passing commit in the history, `bad` to HEAD |
+| `repeat` | number | Runs per commit (1–10) for intermittent failures |
+| `maxSteps` | number | Default 12 |
+| `stepTimeoutMs` | number | Default 180000 |
+
+Runs in a temporary git worktree with the current `node_modules` linked in;
+untestable commits are skipped. `status` is `found`, `ambiguous`, `max-steps`,
+`not-failing` (passes at bad) or `good-fails`.