webperf-snippets 1.13.0 → 1.14.0

package/README.md

@@ -73,7 +73,7 @@ npx webperf-snippets https://example.com --json
 The JSON output records how the page was measured in `conditions`, so a later run can tell whether it measured the same way: the viewport, the workflow (or the path of the snippet with `--snippet`), the wait, the version of the CLI and the machine: its CPU model, cores, architecture and memory, as the operating system reports them, and a benchmark index, a short CPU test in Node before Chromium starts, which only informs, since on the same machine it moves by up to 40 % with the load.
 
 ```json
-"conditions": { "viewport": "mobile", "workflow": "core-web-vitals", "waitMs": 3000, "cliVersion": "1.13.0", "machine": { "cpu": "Apple M4", "cores": 10, "arch": "arm64", "memoryGB": 16, "benchmarkIndex": 2371 } }
+"conditions": { "viewport": "mobile", "workflow": "core-web-vitals", "waitMs": 3000, "cliVersion": "1.14.0", "machine": { "cpu": "Apple M4", "cores": 10, "arch": "arm64", "memoryGB": 16, "benchmarkIndex": 2371 } }
 ```
 
 Single snippet:
@@ -171,7 +171,7 @@ Without `--report-to` the CLI makes no external calls. With it, the results are
   "timestamp": "2026-05-06T10:00:00.000Z",
   "navMs": 1240,
   "results": [],
-  "meta": { "viewport": "mobile", "waitMs": 3000, "cli_version": "1.13.0" }
+  "meta": { "viewport": "mobile", "waitMs": 3000, "cli_version": "1.14.0" }
 }
 ```
 
@@ -203,7 +203,7 @@ One page load is one sample, and lab values vary from one load to the next. `--r
 npx webperf-snippets https://example.com --runs 5 --budget-lcp 2500
 ```
 
-The median run is the one with the median LCP. A workflow without LCP uses the first of FCP, TTFB and the navigation time that it measures, and `--median-by <metric>` picks another one (`LCP`, `FCP`, `TTFB`, `CLS`, `INP` or `navMs`). With an even count it takes the lower of the two middle runs, so the report is always a run that happened. The report adds the median, min and max of each metric across the runs, and how much the runs agree, and the JSON output carries them in `runs`:
+The median run is the one with the median LCP. A workflow without LCP uses the first of FCP, TTFB, INP and the navigation time that it measures, so a measurement of interactions answers with its median INP, and `--median-by <metric>` picks another one (`LCP`, `FCP`, `TTFB`, `CLS`, `INP` or `navMs`). With an even count it takes the lower of the two middle runs, so the report is always a run that happened. The report adds the median, min and max of each metric across the runs, and how much the runs agree, and the JSON output carries them in `runs`:
 
 ```json
 "runs": {
@@ -334,7 +334,7 @@ Each budget compares the value measured, or the median with `--runs`, and fails
 | `--header "Name: value"`     | Request header for the origin of the URL only, such as the token of an access proxy. Repeat it for more headers. |
 | `--own-domains <list>`       | Domains of the site to count as first party, such as its own CDN. Comma-separated or repeated. |
 | `--runs <n>`                 | Measure the page n times, from 1 to 9, one after the other, and report the median run. |
-| `--median-by <metric>`       | Metric that picks the median run: `LCP`, `FCP`, `TTFB`, `CLS`, `INP` or `navMs`. Default: the first of LCP, FCP, TTFB and `navMs` measured. |
+| `--median-by <metric>`       | Metric that picks the median run: `LCP`, `FCP`, `TTFB`, `CLS`, `INP` or `navMs`. Default: the first of LCP, FCP, TTFB, INP and `navMs` measured. |
 | `--matrix <file>`            | Measure every URL of a JSON file on every device and in every variant it lists, and report a table of the medians. |
 | `--baseline <file>`          | Compare the page, or each combination of a matrix, with the `--json` output of an earlier run: which metrics got worse or better beyond the noise, and which errors are new or fixed. |
 | `--threshold <metric>=<v>`   | The threshold of a metric for `--baseline`, such as `LCP=15%`, `LCP=200ms` or `CLS=0.1`. Repeat it for more metrics. |
@@ -404,15 +404,30 @@ It needs the Chromium of Playwright (`npx playwright install chromium`); without
 | Tool            | What it does                                                                 |
 | --------------- | ---------------------------------------------------------------------------- |
 | `list_snippets` | Lists the snippets with their category, title, short aliases and whether they track interactions. Takes an optional `category`. |
-| `run_snippet`   | Opens a URL in a headless Chromium, runs one snippet and returns a summary of its result. Takes `url`, `snippet` (name, alias or `Category/Name`), and optional `viewport`, `waitMs`, `runs`, `baseline` and `thresholds`. The snippets that record interactions run on a page opened with `open_page`. |
-| `run_workflow`  | Runs a workflow of the CLI (`core-web-vitals`, `audit`, `loading`, `interaction`) and the follow-ups of its decision tree. Takes `url`, `workflow`, and optional `viewport`, `waitMs`, `runs`, `baseline` and `thresholds`. |
+| `run_snippet`   | Opens a URL in a headless Chromium, runs one snippet and returns a summary of its result. Takes `url`, `snippet` (name, alias or `Category/Name`), and optional `viewport`, `waitMs`, `cpu`, `network`, `interactions`, `runs`, `baseline` and `thresholds`. The snippets that record interactions need `interactions` with a click or a key press, or a page opened with `open_page`. |
+| `run_workflow`  | Runs a workflow of the CLI (`core-web-vitals`, `audit`, `loading`, `interaction`) and the follow-ups of its decision tree. Takes `url`, `workflow`, and optional `viewport`, `waitMs`, `cpu`, `network`, `interactions`, `runs`, `baseline` and `thresholds`. |
 | `get_crux`      | Returns the CrUX p75 of LCP, CLS and INP for a URL, or its origin. Takes `url` and an optional `formFactor` (`phone`, `desktop`, `tablet`). Needs `CRUX_API_KEY` in the environment of the server. |
-| `open_page`     | Opens a URL in a page that stays open between calls and installs tracking snippets (`track`, such as `INP`). Returns a `sessionId`. |
+| `open_page`     | Opens a URL in a page that stays open between calls and installs tracking snippets (`track`, such as `INP`). Takes optional `viewport`, `waitMs`, `cpu` and `network`. Returns a `sessionId`. |
 | `interact`      | Runs steps on an open page: `click`, `type`, `hover`, `scroll` or `wait`. |
 | `read_results`  | Returns what the tracking snippets of an open page have recorded. |
 | `get_details`   | Returns the whole object of one snippet of a run, by the `runId` that `run_snippet`, `run_workflow` or `read_results` returned, without measuring again. Takes `runId` and `snippet`. |
 | `close_page`    | Closes an open page. |
 
+`run_snippet`, `run_workflow` and `open_page` take `cpu` and `network`, as `--cpu` and `--network`: a CPU factor of at least 1, such as `4`, and a DevTools preset (`fast-4g`, `slow-4g`, `3g`), applied before the page loads. The answer adds `throttling`, as the JSON does, and the conditions of the run name them, so a baseline measured under other throttling gives a warning.
+
+`run_snippet` and `run_workflow` take `interactions`, the steps of `interact` (up to 50), as `--interact-script`: they run after the load of each run, so `runs`, `baseline` and `thresholds` work with them. With a click or a key press, `run_snippet` runs INP, Interactions and Input-Latency-Breakdown, and the `interaction` workflow runs its steps that need input instead of skipping them. The INP of a page over five runs with a click each, with the CPU 4 times slower, against an earlier run:
+
+```json
+{
+  "url": "http://localhost:3000/product",
+  "snippet": "INP",
+  "interactions": [{ "action": "click", "selector": "#buy" }, { "action": "wait", "ms": 300 }],
+  "runs": 5,
+  "cpu": 4,
+  "baseline": "<runId of the run before the change>"
+}
+```
+
 `run_snippet` and `run_workflow` take `runs`, from 1 to 9, as `--runs`: the page loads that many times, one after the other, and the answer is the median run plus a `runs` field, the one of the JSON, with the median, min, max, the value of each run and the agreement of each metric. A run that fails counts in `failed` and is left out; when every run fails, the answer is a tool error. The server keeps the results of the median run only, as the JSON does, so `get_details` answers from that run and names it in `medianRun`; a metric other than the one that picked it (`medianBy`) can differ there from its median in `runs`.
 
 Each run is a page load plus `waitMs`. With the default wait of 3 seconds, five runs of a workflow take about 20 seconds on a local page, and about a minute on a page that takes a few seconds to load. When the client asks for progress, the server reports the three stages of each run, numbered across the runs. A client sets its own limit on a tool call: the MCP SDK stops waiting after 60 seconds unless it is given a longer `timeout` or `resetTimeoutOnProgress`, and in Claude Code `MCP_TOOL_TIMEOUT` sets the limit. When the client gives up, the run in progress ends and no other starts.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "webperf-snippets",
-  "version": "1.13.0",
+  "version": "1.14.0",
   "mcpName": "io.github.nucliweb/webperf-snippets",
   "description": "Run curated WebPerf Snippets headlessly via Playwright. Diagnose Core Web Vitals beyond what Lighthouse exposes.",
   "type": "module",

package/snippets/Interaction/Scroll-Performance.js

@@ -26,9 +26,13 @@
     "scroll", "wheel", "touchstart", "touchmove", "touchend",
   ]);
 
+  // When Playwright clicks, as the CLI does, its injected script can add touch listeners of its own to
+  // window, without passive, to check that the click lands on the element. They are not the page's.
+  const addedByPlaywright = () => /\bInjectedScript\b/.test(new Error().stack || "");
+
   const _origAddEventListener = EventTarget.prototype.addEventListener;
   EventTarget.prototype.addEventListener = function (type, listener, options) {
-    if (SCROLL_EVENT_TYPES.has(type)) {
+    if (SCROLL_EVENT_TYPES.has(type) && !addedByPlaywright()) {
       const isPassive =
         options === true
           ? false // old-style capture boolean, not passive

package/src/bin.js

@@ -71,7 +71,8 @@ Options:
   --matrix <file>           Measure every URL of a JSON file on every device and in every
                             variant it lists, and report a table of the medians
   --median-by <metric>      Metric that picks the median run: LCP, FCP, TTFB, CLS, INP,
-                            navMs (default: the first of LCP, FCP, TTFB, navMs measured)
+                            navMs (default: the first of LCP, FCP, TTFB, INP, navMs
+                            measured)
   --baseline <file>         Compare the page, or each combination of a matrix, with the --json
                             output of an earlier run: which metrics got worse or better beyond
                             the noise, and which errors are new or fixed. It only informs,
@@ -313,8 +314,8 @@ async function main() {
   // What the JSON records of how each page was measured, for a later run to compare with. The machine is
   // measured once, before Chromium starts, so its processes do not slow the benchmark down.
   const machine = machineOf();
-  const conditionsFor = (viewport) =>
-    measurementConditions({ viewport, waitMs, machine, ...(items ? { snippet: items[0].path } : { workflow: values.workflow ?? "core-web-vitals" }) });
+  const conditionsFor = ({ viewport, cpu, network }) =>
+    measurementConditions({ viewport, waitMs, cpu, network, machine, ...(items ? { snippet: items[0].path } : { workflow: values.workflow ?? "core-web-vitals" }) });
 
   if (matrixPath) {
     let matrix;
@@ -336,7 +337,7 @@ async function main() {
     if (!median.payload) throw new Error(`Every run failed: ${median.errors.join("; ")}`);
     payload = { ...median.payload, runs: median.runs };
   }
-  payload.conditions = conditionsFor(viewportName);
+  payload.conditions = conditionsFor({ viewport: viewportName, cpu, network });
 
   if (cruxKey) payload.crux = await fieldDataOf(url, formFactorFor(viewportName));
 
@@ -422,8 +423,8 @@ async function runMatrix(matrixPath, matrix, measureWith, { values, waitMs, repo
     const identity = { id: c.id, name: c.name, device: c.device, ...(c.variant ? { variant: c.variant } : {}), url: c.url };
     combinations.push(
       median.payload
-        ? { ...identity, ...median.payload, runs: median.runs, conditions: conditionsFor(c.viewport) }
-        : { ...identity, status: "error", error: `Every run failed: ${median.errors.join("; ")}`, runs: { count: matrix.runs, failed: matrix.runs }, conditions: conditionsFor(c.viewport) }
+        ? { ...identity, ...median.payload, runs: median.runs, conditions: conditionsFor(c) }
+        : { ...identity, status: "error", error: `Every run failed: ${median.errors.join("; ")}`, runs: { count: matrix.runs, failed: matrix.runs }, conditions: conditionsFor(c) }
     );
   }
 

package/src/conditions.js

@@ -1,7 +1,17 @@
 import { cliVersion } from "./report-to.js";
 
 // How a measurement was taken, kept in its JSON so that a later run compared with it can tell whether
-// both were measured the same way. A snippet is named by its path, so an alias and its path match.
-export function measurementConditions({ viewport, workflow, snippet, waitMs, machine }) {
-  return { viewport, ...(snippet ? { snippet } : { workflow }), waitMs, cliVersion, ...(machine ? { machine } : {}) };
+// both were measured the same way. A snippet is named by its path, so an alias and its path match. The
+// CPU factor and the network go in only when the run was throttled, so a run without throttling keeps
+// the conditions of earlier versions.
+export function measurementConditions({ viewport, workflow, snippet, waitMs, cpu, network, machine }) {
+  return {
+    viewport,
+    ...(snippet ? { snippet } : { workflow }),
+    waitMs,
+    ...(cpu != null ? { cpu } : {}),
+    ...(network != null ? { network } : {}),
+    cliVersion,
+    ...(machine ? { machine } : {}),
+  };
 }

package/src/mcp/next-steps.js

@@ -1,29 +1,49 @@
 import { RULES, nextSteps } from "../decision-tree.js";
 import { loadSnippet } from "../load-snippet.js";
 import { isTrackingSnippet } from "../tracking.js";
+import { throttlingOf } from "../throttling.js";
 
 const isTrackingPath = (path) => isTrackingSnippet(path, loadSnippet(path));
 
 // The call of the tool that runs a snippet: a tracking snippet needs a page the agent interacts with. A
-// snippet waits as long as the run that called for it, so it reads the same paint.
-const callFor = ({ path, reason, url, viewport, waitMs, isTracking }) =>
+// snippet waits as long as the run that called for it, so it reads the same paint, and loads under its
+// throttling, so it measures the same page.
+const callFor = ({ path, reason, url, viewport, waitMs, cpu, network, isTracking }) =>
   isTracking(path)
-    ? { tool: "open_page", args: { url, track: [path], viewport }, reason }
-    : { tool: "run_snippet", args: { url, snippet: path, viewport, ...(waitMs !== undefined ? { waitMs } : {}) }, reason };
+    ? { tool: "open_page", args: { url, track: [path], viewport, ...throttlingOf({ cpu, network }) }, reason }
+    : { tool: "run_snippet", args: { url, snippet: path, viewport, ...(waitMs !== undefined ? { waitMs } : {}), ...throttlingOf({ cpu, network }) }, reason };
 
 // The follow-ups the decision tree of the CLI asks for, as the calls an agent makes next. The rules name
 // the steps of a workflow (LCP, CLS, TTFB, FCP), which are the scripts of the snippets, so a result of
 // run_snippet, whose id is Category/Name, is matched by its script. `ran` leaves out what already ran.
-export function followUpCalls({ results, url, viewport, waitMs, ran = [], rules = RULES, isTracking = isTrackingPath }) {
+export function followUpCalls({ results, url, viewport, waitMs, cpu, network, ran = [], rules = RULES, isTracking = isTrackingPath }) {
   const named = results.map((r) => ({ ...r, id: r.script ?? r.id }));
-  return nextSteps(named, rules, ran).map(({ path, reason }) => callFor({ path, reason, url, viewport, waitMs, isTracking }));
+  return nextSteps(named, rules, ran).map(({ path, reason }) => callFor({ path, reason, url, viewport, waitMs, cpu, network, isTracking }));
 }
 
 // The steps a workflow skipped because they measure clicks and key presses, in one page to open
-export function trackingCall({ paths, url, viewport }) {
+export function trackingCall({ paths, url, viewport, cpu, network }) {
   return {
     tool: "open_page",
-    args: { url, track: paths, viewport },
+    args: { url, track: paths, viewport, ...throttlingOf({ cpu, network }) },
     reason: "These steps measure clicks and key presses: open the page with them, interact with it and read them with read_results",
   };
 }
+
+// A click the agent completes: only the agent can choose the element of the page to click
+const CLICK_TO_COMPLETE = { action: "click", selector: "<selector of the element to click>" };
+
+// The steps a workflow skipped because they measure clicks and key presses. First the workflow again
+// with interactions, which measures them in one call, with the runs and the baseline of a page load; then
+// a page to open with them, for an agent that explores the page step by step.
+export function inputStepsCalls({ workflow, paths, url, viewport, waitMs, cpu, network }) {
+  return [
+    {
+      tool: "run_workflow",
+      args: { url, workflow, viewport, ...(waitMs !== undefined ? { waitMs } : {}), ...throttlingOf({ cpu, network }), interactions: [CLICK_TO_COMPLETE] },
+      reason:
+        "These steps measure clicks and key presses: run the workflow again with interactions, a click or type step on an element of the page in place of this selector; runs and baseline work with them",
+    },
+    trackingCall({ paths, url, viewport, cpu, network }),
+  ];
+}

package/src/mcp/server.js

@@ -15,12 +15,13 @@ import { launchChromium, isMissingBrowser, MISSING_BROWSER } from "../browser.js
 import { registerResources } from "./documents.js";
 import { registerPrompts } from "./prompts.js";
 import { shapeResults, createRuns, RunError } from "./summary.js";
-import { followUpCalls, trackingCall } from "./next-steps.js";
+import { followUpCalls, inputStepsCalls } from "./next-steps.js";
 import { isHttpUrl } from "../url.js";
 import { machineOf } from "../machine.js";
 import { measurementConditions } from "../conditions.js";
 import { prepareBaseline, compareWithBaseline } from "./baseline.js";
 import { MAX_RUNS, measureRuns } from "../runs.js";
+import { MIN_CPU_FACTOR, NETWORK_PRESETS, applyThrottling, throttlingOf } from "../throttling.js";
 
 const VIEWPORTS = Object.keys(VIEWPORT_PRESETS);
 const STAGES = 3;
@@ -72,7 +73,27 @@ const Runs = z
     "Measure the page this many times, one after the other, as --runs of the CLI: the answer is the median run, plus runs with the median, min, max and agreement of each metric. With baseline, 5 or more on both sides give the statistical verdict: use 5 for a comparison, and more only when agreement says noisy. Each run is a full page load and wait, so it takes that much longer"
   );
 
+// The throttling of --cpu and --network, applied to the page before it loads. Without them the page runs
+// at the speed of the machine, as the CLI does. A network of the tools is a preset: its own values are
+// for --matrix.
+const Cpu = z
+  .number()
+  .min(MIN_CPU_FACTOR)
+  .optional()
+  .describe(
+    "Slow the CPU of the page down by this factor, as --cpu of the CLI. Leave it out unless the user asks for throttling or the baseline was throttled: compared with a baseline, use the cpu it was measured with (no throttling by default)"
+  );
+const Network = z
+  .enum(Object.keys(NETWORK_PRESETS))
+  .optional()
+  .describe(
+    "Throttle the network as DevTools does, as --network of the CLI. Leave it out unless the user asks for throttling or the baseline was throttled: compared with a baseline, use the network it was measured with (no throttling by default)"
+  );
+
 const LooseObject = (shape) => z.looseObject(shape).meta({ additionalProperties: true });
+const Throttling = LooseObject({})
+  .optional()
+  .describe("With cpu or network, the throttling the page ran under, as the throttling field of the JSON of the CLI");
 const RunsSummary = LooseObject({
   count: z.number(),
   failed: z.number().describe("Runs left out because they failed"),
@@ -117,6 +138,7 @@ const DETAIL_NOTE =
   "Large results come as summaries with a runId for get_details; nextSteps, when present, is the call to make next.";
 const BASELINE_NOTE = "With baseline, it also compares the run with an earlier one, as --baseline of the CLI, and says what regressed.";
 const QUEUE_NOTE = "Measurements run one at a time, so several in one turn save no time.";
+const THROTTLING_NOTE = "cpu and network throttle the page as --cpu and --network of the CLI, and the answer says so in throttling.";
 
 // A page can put instructions for the agent in what a snippet returns: an alt text, a class in a
 // selector, the URL of a script. The tools that return what a page holds say how to read it, and so
@@ -133,6 +155,16 @@ const Step = z.discriminatedUnion("action", [
   z.object({ action: z.literal("wait"), ms: z.number().int().min(0).max(10000) }),
 ]);
 
+// The steps of interact, run after the load of each run, as --interact-script of the CLI
+const Interactions = z
+  .array(Step)
+  .min(1)
+  .max(50)
+  .optional()
+  .describe(
+    "Steps to run on the page after the load, as --interact-script of the CLI: click, type, hover, scroll or wait, as in interact. A click or a key press is what INP, Interactions and Input-Latency-Breakdown measure. Each run repeats them, so runs and baseline work with them"
+  );
+
 const SnippetInfo = z.object({
   name: z.string().describe("Category/Name, the name other tools take"),
   category: z.enum(CATEGORIES),
@@ -341,12 +373,15 @@ export function createServer({ launchBrowser = () => launchChromium(), maxPages,
     {
       title: "Run a snippet",
       description:
-        `Opens the URL in a headless Chromium, runs one web performance snippet on the loaded page and returns the object the snippet returns, as defined in snippets/SCHEMA.md. Use list_snippets for the names. The snippets that record interactions (INP, Interactions, Input-Latency-Breakdown) run on a page opened with open_page instead. ${QUEUE_NOTE} ${BASELINE_NOTE} ${DETAIL_NOTE} ${PAGE_DATA}`,
+        `Opens the URL in a headless Chromium, runs one web performance snippet on the loaded page and returns the object the snippet returns, as defined in snippets/SCHEMA.md. Use list_snippets for the names. The snippets that record interactions (INP, Interactions, Input-Latency-Breakdown) need interactions with a click or a key press, which run after the load of each run; open_page explores a page step by step instead. ${THROTTLING_NOTE} ${QUEUE_NOTE} ${BASELINE_NOTE} ${DETAIL_NOTE} ${PAGE_DATA}`,
       inputSchema: z.object({
         url: HttpUrl,
         snippet: z.string().describe("The snippet: its name (LCP-Subparts), an alias (render-blocking) or Category/Name"),
         viewport: z.enum(VIEWPORTS).default("mobile").describe("Device size of the page"),
         waitMs: z.number().int().min(0).max(10000).default(3000).describe("Wait after the load event before running the snippet, in ms"),
+        cpu: Cpu,
+        network: Network,
+        interactions: Interactions,
         runs: Runs,
         detail: Detail,
         baseline: Baseline,
@@ -360,6 +395,7 @@ export function createServer({ launchBrowser = () => launchChromium(), maxPages,
         viewport: z.enum(VIEWPORTS),
         navMs: z.number().describe("From the start of the navigation to the end of the wait"),
         pageErrors: z.array(z.string()).describe("Uncaught errors of the page during the run"),
+        throttling: Throttling,
         result: SnippetResult,
         runs: RunsSummary,
         baseline: Comparison,
@@ -367,7 +403,7 @@ export function createServer({ launchBrowser = () => launchChromium(), maxPages,
       }),
       annotations: { readOnlyHint: true, openWorldHint: true },
     },
-    async ({ url, snippet, viewport, waitMs, runs: count, detail, baseline, thresholds }, ctx) => {
+    async ({ url, snippet, viewport, waitMs, cpu, network, interactions, runs: count, detail, baseline, thresholds }, ctx) => {
       let path;
       try {
         path = resolveSnippetName(snippet);
@@ -375,8 +411,11 @@ export function createServer({ launchBrowser = () => launchChromium(), maxPages,
         return toolError(err.message);
       }
       const source = loadSnippet(path);
-      if (isTrackingSnippet(path, source)) {
-        return toolError(`${path} records interactions: open the page with open_page and this snippet in track, use it with interact, and read it with read_results.`);
+      // With interactions, the runner installs it before the steps and reads it after them
+      if (isTrackingSnippet(path, source) && !interactions) {
+        return toolError(
+          `${path} records interactions: run it with interactions that click or type on an element of the page, which run after the load, or open the page with open_page and this snippet in track, use it with interact, and read it with read_results.`
+        );
       }
       let base;
       try {
@@ -387,15 +426,15 @@ export function createServer({ launchBrowser = () => launchChromium(), maxPages,
 
       try {
         const { conditions, run } = await measureInTurn(
-          { viewport, snippet: path, waitMs },
-          (onProgress, signal) => runSnippets({ url, items: [{ id: path, path, source }], waitMs, viewport: VIEWPORT_PRESETS[viewport], onProgress, signal }),
+          { viewport, snippet: path, waitMs, cpu, network },
+          (onProgress, signal) => runSnippets({ url, items: [{ id: path, path, source }], waitMs, viewport: VIEWPORT_PRESETS[viewport], cpu, network, interactions, onProgress, signal }),
           count,
           ctx
         );
         const shaped = shapeResults(run.results.map(({ id, ...result }) => result), detail);
         const { runId, current } = keepPage(run, run.results, conditions);
         const id = run.results[0].id;
-        const nextSteps = followUpCalls({ results: run.results, url, viewport, waitMs, ran: [path] });
+        const nextSteps = followUpCalls({ results: run.results, url, viewport, waitMs, cpu, network, ran: [path] });
         return toolResult({
           url,
           runId,
@@ -404,6 +443,7 @@ export function createServer({ launchBrowser = () => launchChromium(), maxPages,
           viewport,
           navMs: run.navMs,
           pageErrors: run.pageErrors,
+          ...(run.throttling ? { throttling: run.throttling } : {}),
           result: shaped.results[0],
           ...(run.runs ? { runs: run.runs } : {}),
           ...(base ? { baseline: compareWithBaseline(base, current) } : {}),
@@ -422,12 +462,15 @@ export function createServer({ launchBrowser = () => launchChromium(), maxPages,
     {
       title: "Run a workflow",
       description:
-        `Opens the URL in a headless Chromium and runs a workflow: a sequence of snippets plus the follow-ups its decision tree adds from the results (for example LCP-Subparts when LCP is over 2.5 s, with the reason). core-web-vitals: LCP and CLS. audit: render-blocking resources, resource hints, critical CSS, TTFB, scripts, images and more. loading: TTFB, FCP, render-blocking, scripts and fonts. interaction: long tasks, animation frames, scroll and layout shifts while it scrolls the page. ${QUEUE_NOTE} ${BASELINE_NOTE} ${DETAIL_NOTE} ${PAGE_DATA}`,
+        `Opens the URL in a headless Chromium and runs a workflow: a sequence of snippets plus the follow-ups its decision tree adds from the results (for example LCP-Subparts when LCP is over 2.5 s, with the reason). core-web-vitals: LCP and CLS. audit: render-blocking resources, resource hints, critical CSS, TTFB, scripts, images and more. loading: TTFB, FCP, render-blocking, scripts and fonts. interaction: long tasks, animation frames, scroll and layout shifts while it scrolls the page, or while it runs interactions, which with a click or a key press also measure INP, Interactions and Input-Latency-Breakdown. ${THROTTLING_NOTE} ${QUEUE_NOTE} ${BASELINE_NOTE} ${DETAIL_NOTE} ${PAGE_DATA}`,
       inputSchema: z.object({
         url: HttpUrl,
         workflow: z.enum(Object.keys(WORKFLOWS)).default("core-web-vitals"),
         viewport: z.enum(VIEWPORTS).default("mobile").describe("Device size of the page"),
         waitMs: z.number().int().min(0).max(10000).default(3000).describe("Wait after the load event before running the workflow, in ms"),
+        cpu: Cpu,
+        network: Network,
+        interactions: Interactions,
         runs: Runs,
         detail: Detail,
         baseline: Baseline,
@@ -441,6 +484,7 @@ export function createServer({ launchBrowser = () => launchChromium(), maxPages,
         viewport: z.enum(VIEWPORTS),
         navMs: z.number(),
         pageErrors: z.array(z.string()),
+        throttling: Throttling,
         results: z
           .array(z.looseObject({ id: z.string(), status: z.string() }).meta({ additionalProperties: true }))
           .describe("One object per step, in order, then the follow-ups, each with the reason it was added"),
@@ -450,7 +494,7 @@ export function createServer({ launchBrowser = () => launchChromium(), maxPages,
       }),
       annotations: { readOnlyHint: true, openWorldHint: true },
     },
-    async ({ url, workflow, viewport, waitMs, runs: count, detail, baseline, thresholds }, ctx) => {
+    async ({ url, workflow, viewport, waitMs, cpu, network, interactions, runs: count, detail, baseline, thresholds }, ctx) => {
       let base;
       try {
         base = baselineFor({ baseline, thresholds });
@@ -459,15 +503,19 @@ export function createServer({ launchBrowser = () => launchChromium(), maxPages,
       }
       try {
         const { conditions, run } = await measureInTurn(
-          { viewport, workflow, waitMs },
-          (onProgress, signal) => runMeasurement({ url, workflow: WORKFLOWS[workflow], rules: RULES, waitMs, viewport: VIEWPORT_PRESETS[viewport], onProgress, signal }),
+          { viewport, workflow, waitMs, cpu, network },
+          (onProgress, signal) => runMeasurement({ url, workflow: WORKFLOWS[workflow], rules: RULES, waitMs, viewport: VIEWPORT_PRESETS[viewport], cpu, network, interactions, onProgress, signal }),
           count,
           ctx
         );
         // The runner explains a skipped step with the flag of the CLI; here the tools are what the model has
         const results = run.results.map((r) =>
           r.status === "skipped"
-            ? { ...r, reason: "This step measures clicks and key presses: open the page with open_page and this snippet in track, use it with interact, and read it with read_results." }
+            ? {
+                ...r,
+                reason:
+                  "This step measures clicks and key presses: run the workflow with interactions that click or type on an element of the page, or open the page with open_page and this snippet in track, use it with interact, and read it with read_results.",
+              }
             : r
         );
         const shaped = shapeResults(results, detail);
@@ -477,7 +525,7 @@ export function createServer({ launchBrowser = () => launchChromium(), maxPages,
           .filter((r) => r.status === "skipped")
           .map((r) => WORKFLOWS[workflow].steps.find((s) => s.id === r.id)?.path)
           .filter(Boolean);
-        const nextSteps = skipped.length ? [trackingCall({ paths: skipped, url, viewport })] : [];
+        const nextSteps = skipped.length ? inputStepsCalls({ workflow, paths: skipped, url, viewport, waitMs, cpu, network }) : [];
         return toolResult({
           url,
           runId,
@@ -486,6 +534,7 @@ export function createServer({ launchBrowser = () => launchChromium(), maxPages,
           viewport,
           navMs: run.navMs,
           pageErrors: run.pageErrors,
+          ...(run.throttling ? { throttling: run.throttling } : {}),
           ...(run.runs ? { runs: run.runs } : {}),
           ...(base ? { baseline: compareWithBaseline(base, current) } : {}),
           ...(nextSteps.length ? { nextSteps } : {}),
@@ -558,23 +607,26 @@ export function createServer({ launchBrowser = () => launchChromium(), maxPages,
     {
       title: "Open a page",
       description:
-        `Opens the URL in a headless Chromium that stays open between calls, and installs the snippets that record interactions (INP, Interactions, Input-Latency-Breakdown, and the other tracking snippets in list_snippets). Returns a sessionId for interact, read_results and close_page. At most 3 pages are open at a time, and a page closes after 10 minutes without use. ${PAGE_DATA}`,
+        `Opens the URL in a headless Chromium that stays open between calls, and installs the snippets that record interactions (INP, Interactions, Input-Latency-Breakdown, and the other tracking snippets in list_snippets). Returns a sessionId for interact, read_results and close_page. ${THROTTLING_NOTE} The throttling stays for the interactions on the page. At most 3 pages are open at a time, and a page closes after 10 minutes without use. ${PAGE_DATA}`,
       inputSchema: z.object({
         url: HttpUrl,
         track: z.array(z.string()).min(1).describe("The tracking snippets to install, by name, alias or Category/Name"),
         viewport: z.enum(VIEWPORTS).default("mobile").describe("Device size of the page"),
         waitMs: z.number().int().min(0).max(10000).default(1000).describe("Wait after the load event before installing the snippets, in ms"),
+        cpu: Cpu,
+        network: Network,
       }),
       outputSchema: z.object({
         sessionId: z.string(),
         url: z.string(),
         viewport: z.enum(VIEWPORTS),
         navMs: z.number(),
+        throttling: Throttling,
         tracking: z.array(z.object({ snippet: z.string(), status: z.string() })).describe("The installed snippets"),
       }),
       annotations: { readOnlyHint: true, openWorldHint: true },
     },
-    withSession(async ({ url, track, viewport, waitMs }, ctx) => {
+    withSession(async ({ url, track, viewport, waitMs, cpu, network }, ctx) => {
       const items = [];
       for (const name of track) {
         let path;
@@ -600,6 +652,8 @@ export function createServer({ launchBrowser = () => launchChromium(), maxPages,
           throw err;
         }
         try {
+          // Before the load, as the runner applies it: the load and every interaction run throttled
+          await applyThrottling(session.context, session.page, { cpu, network });
           const navStart = Date.now();
           await session.page.goto(url, { waitUntil: "load", timeout: NAV_TIMEOUT_MS });
           if (waitMs > 0) await session.page.waitForTimeout(waitMs);
@@ -609,7 +663,8 @@ export function createServer({ launchBrowser = () => launchChromium(), maxPages,
           if (limit.aborted) return toolError(`Opening the page failed: ${stoppedAnswering(callLimitMs)}`);
           session.stopListening();
           const tracking = session.tracking.map(({ id, status }) => ({ snippet: id, status }));
-          return toolResult({ sessionId: session.id, url, viewport, navMs, tracking });
+          const throttling = throttlingOf({ cpu, network });
+          return toolResult({ sessionId: session.id, url, viewport, navMs, ...(throttling ? { throttling } : {}), tracking });
         } catch (err) {
           await sessions.close(session.id);
           if (limit.aborted) return toolError(`Opening the page failed: ${stoppedAnswering(callLimitMs)}`);

package/src/runs.js

@@ -13,7 +13,7 @@ export const MAX_RUNS = 9;
 export const MEDIAN_METRICS = ["LCP", "FCP", "TTFB", "CLS", "INP", "navMs"];
 
 // Without --median-by, the median follows the first of these that the runs measured
-const DEFAULT_ORDER = ["LCP", "FCP", "TTFB", "navMs"];
+const DEFAULT_ORDER = ["LCP", "FCP", "TTFB", "INP", "navMs"];
 
 const SUMMARY_METRICS = MEDIAN_METRICS.filter((metric) => metric !== "navMs");
 

package/src/throttling.js

@@ -10,10 +10,13 @@ export const NETWORK_PRESETS = {
   "3g": { title: "3G", download: (500 * 1000) / 8 * 0.8, upload: (500 * 1000) / 8 * 0.8, latency: 400 * 5 },
 };
 
+// The smallest CPU factor, no slowdown, for --cpu and the cpu of the tools of the MCP server
+export const MIN_CPU_FACTOR = 1;
+
 // The factor given to --cpu, or null when it is not a number of at least 1
 export function parseCpuFactor(raw) {
   const factor = Number(raw);
-  return raw.trim() !== "" && Number.isFinite(factor) && factor >= 1 ? factor : null;
+  return raw.trim() !== "" && Number.isFinite(factor) && factor >= MIN_CPU_FACTOR ? factor : null;
 }
 
 const NETWORK_VALUES = ["downloadKbps", "uploadKbps", "latencyMs"];