Merge remote-tracking branch 'origin/main' into brennanb2025/terminal-prompt-delivery

This commit is contained in:
Brennan Benson
2026-09-20 21:44:29 -07:00
31 changed files with 1284 additions and 172 deletions
@@ -536,15 +536,17 @@ describe('the Phase C budget', () => {
})
it('derives the chunk ceiling from the route count, not from a measured number', async () => {
// A chunk is emitted per distinct set of importers, so the count is combinatorial rather than
// one per route. Measured while building this: 8 routes emit 23 chunks, 10 emit 40, 12 emit
// 47, 14 emit 53 -- about 3 more per route at the top. The ceiling allows 4 and starts 16
// above zero, so the next few routes land under it instead of failing on a pinned number.
// A chunk is emitted per distinct set of importers, so the count is not a function of the
// route count alone. Re-measured on this head, by copying the route tree and dropping routes
// from the end of the sorted key list -- both siblings of each, because deleting a .web.tsx
// alone leaves the native file for the builder to resolve and measures a different closure.
// The 14-route reading is the real tree and includes the one script the deferred mermaid
// artifact costs.
for (const [routes, measured] of [
[8, 23],
[10, 40],
[12, 47],
[14, 53]
[8, 32],
[10, 43],
[12, 61],
[14, 69]
]) {
expect(mobileWebAppBundleMaxChunks(routes), `${String(routes)} routes`).toBeGreaterThan(
measured
@@ -552,6 +554,29 @@ describe('the Phase C budget', () => {
}
expect(mobileWebAppBundleMaxChunks(14)).toBe(72)
expect(mobileWebAppBundleMaxChunks(15) - mobileWebAppBundleMaxChunks(14)).toBe(4)
// Between four and nine more per route above, so the ceiling is a bound and not a fit -- and
// at 14 routes it is a close one. 69 measured against 72, with the last two routes having cost
// the 8 the ceiling grants for two: the next route that shares less than its neighbours fails
// here, which is what this is for.
expect(mobileWebAppBundleMaxChunks(14) - mobileWebAppBundleMaxChunks(12)).toBe(8)
})
it('refuses an engine chunked along its own lazy boundaries, and passes one artifact', () => {
// The two builds this ceiling has to tell apart, both measured at 14 routes.
//
// The page reaches mermaid through one pre-bundled artifact and the bundle emits 69 scripts
// (68 of them the page's own split, one the deferred engine). Importing the package instead
// emitted 172: mermaid lazily imports each of its own diagram types and esbuild splits along
// those boundaries, all of it inside the generation the phone has already downloaded. The
// route term is the only term precisely so that the second of those fails here -- a ceiling
// raised to admit 172 would have admitted any split at all.
const ROUTES = 14
const WITH_ONE_ARTIFACT = 69
const CHUNKED_ALONG_THE_ENGINE = 172
expect(WITH_ONE_ARTIFACT).toBeLessThanOrEqual(mobileWebAppBundleMaxChunks(ROUTES))
expect(CHUNKED_ALONG_THE_ENGINE).toBeGreaterThan(mobileWebAppBundleMaxChunks(ROUTES))
// And the assets that came with it: 215 against 112, of the 256 the shell will load.
expect(mobileWebAppBundleMaxAssets(ROUTES, 42)).toBeLessThan(CHUNKED_ALONG_THE_ENGINE + 42 + 1)
})
it('derives the asset ceiling so the chunk ceiling is always the one that trips first', () => {
@@ -592,7 +617,8 @@ describe('the Phase C budget', () => {
it('fails the build when the derived ceiling passes what the phone will accept', async () => {
// The shell hands back null for a manifest over its own ceiling, so a derived ceiling above
// that ships a green build no device can open. At the 42 images the tree carries, 4r + 16 +
// 42 + 1 crosses 256 at 50 routes, which Phase C reaches.
// 42 + 1 crosses 256 at 50 routes, which Phase C reaches. A deferred engine kept to one
// artifact leaves that where it is; the 103-script version of it moved the crossing to 24.
expect(await readMobileWebBundleMaxAssets()).toBe(MOBILE_WEB_BUNDLE_MAX_ASSETS)
expect(assertAssetCeilingFitsShell(49, 42, MOBILE_WEB_BUNDLE_MAX_ASSETS)).toBe(255)
expect(() => assertAssetCeilingFitsShell(50, 42, MOBILE_WEB_BUNDLE_MAX_ASSETS)).toThrow(
@@ -0,0 +1,564 @@
/**
* Mermaid rendered in the page, in a real browser, under the policy the shell ships.
*
* The native component seals an untrusted diagram inside a `WebView` whose document embeds the
* whole engine as a string. The page has no second content process, so what replaces it is
* `import('mermaid')` on demand and mermaid's own `securityLevel: 'strict'` output. That makes
* three claims this file measures rather than asserts: that rendering violates no directive and
* asks for no JIT, that what the page paints is the diagram the phone already paints, and that a
* hostile diagram reaches the document inert.
*
* The equality oracle is the native `buildHtml` itself, bundled and served as its own document in
* the same browser. Two differences survive and are normalised away: the diagram id (mermaid's own
* `mermaid-<epoch>` on the native path, the component's `useId` on the page) and the `xmlns:xlink`
* declaration the native document's `innerHTML` serialization adds. Everything else — the viewBox,
* the `max-width`, the injected `<style>`'s rules — is compared byte for byte.
*
* Both engines, because the shell is WKWebView on one platform and a Chromium WebView on the
* other, and "does mermaid need eval" is answered by the engine rather than by mermaid.
*
* Recorded from this file's own run, for whoever needs the trade. Rendering one `graph TD` fetches
* one chunk of 3,482,965 minified bytes on top of a 283,956-byte entry — the pre-bundled engine,
* not in the entry, and not fetched at all by a page with no diagram on it (ruling 28's fence,
* held in `mobile-web-app-session-terminal-closure.test.mjs`). One chunk rather than the 103 that
* `import('mermaid')` emitted: mermaid splits along its own lazy diagram-type boundaries, all of
* which sit inside the generation the phone has already downloaded, so that split moved no bytes
* and spent 103 of the 256 manifest assets the shell will load. The native document pays 3,705,846
* bytes of engine string instead, in the closure, on every mount.
*
* The SVG itself: 17,143 bytes on the page against 17,504 in the native document (chromium; webkit
* is 8 longer on each side), equal at 15,447 once normalised. The gap is the id string repeated
* across 57 selectors, and dropping `xmlns:xlink` is load-bearing rather than cosmetic — the
* comparison fails without it.
*/
import { mkdir, mkdtemp, rm, writeFile } from 'node:fs/promises'
import { join } from 'node:path'
import { fileURLToPath, pathToFileURL } from 'node:url'
import { afterAll, beforeAll, describe, expect, it } from 'vitest'
import * as esbuild from 'esbuild'
import { chromium, webkit } from 'playwright-core'
import { mobileWebAppDependenciesPresent } from './mobile-web-app-bundle-dependencies.mjs'
import {
createBundleServer,
installCspViolationRecorder,
installListenerRecorder,
readShellCsp
} from './mobile-web-app-render-harness.mjs'
const mobileDir = fileURLToPath(new URL('../../mobile', import.meta.url))
const diagramDir = join(mobileDir, 'src/components/pr-sidebar')
/** The design's own fixture, so the byte counts in the docstring above name this diagram. */
const FIXTURE =
'graph TD\n A[Start] --> B{Choice}\n B -->|yes| C[Ship it]\n B -->|no| D[Fix it]\n D --> A'
/** A second valid diagram for the source change: a different shape, so a stale SVG is visible. */
const SECOND = 'graph LR\n One --> Two\n Two --> Three'
/**
* A script in a label, a `</script>` in a label, an `onerror` attribute and a `javascript:` click.
*
* The native path escapes `<`, `>` and the line separators because the source is spliced into an
* inline `<script>`; on the page it is a JS string argument and that escaping has no analogue, so
* the only fence left is mermaid's own strict-mode sanitiser. This is what measures it.
*/
const HOSTILE =
'graph TD\n A["<img src=x onerror=window.__pwned=1><script>window.__pwned=2<\\/script>"] --> B\n' +
' B --> C\n click A "javascript:window.__pwned=3"\n' +
' C --> D["</script><script>window.__pwned=4</script>"]'
/** Not a diagram in any grammar mermaid has, so `render` rejects and the component falls back. */
const BROKEN = 'graph TD\n A[[[unclosed'
const ENGINES = [
{
name: 'chromium',
// CI runs this against the runner's Google Chrome rather than paying for a download, the same
// override shape as every other render check here.
launch: () => {
const executablePath = process.env.ORCA_MOBILE_WEB_RENDER_BROWSER
return chromium.launch({ headless: true, ...(executablePath ? { executablePath } : {}) })
}
},
{ name: 'webkit', launch: () => webkit.launch({ headless: true }) }
]
/**
* The page under test: the real component, mounted by the real React, with a handle on its props.
*
* Not a re-implementation of what the component does — the dispose, the fallback and the remount
* are the behaviour under test, and a probe that called `mermaid.render` itself would prove
* nothing about any of them.
*/
const PAGE_ENTRY = `
import { createElement, useEffect, useState } from 'react'
import { createRoot } from 'react-dom/client'
import { MermaidDiagram } from './MermaidDiagram'
function Harness() {
const [state, setState] = useState({ mounted: false, source: '' })
useEffect(() => {
globalThis.__orcaMermaidSet = setState
document.body.setAttribute('data-ready', 'yes')
}, [])
return state.mounted ? createElement(MermaidDiagram, { source: state.source, base: 15 }) : null
}
createRoot(document.getElementById('root')).render(createElement(Harness))
`
/**
* A stand-in for React, React Native and `react-native-webview`, so the native module can be
* bundled for Node to get its HTML.
*
* `buildHtml` is a pure function of the source and the theme, but it lives beside a component
* whose other imports are all native. CommonJS with a Proxy rather than a list of named exports:
* what that component reaches for is its own business, and none of it is called here.
*/
const IMPORT_STUB = `
const identity = (value) => value
module.exports = new Proxy(
{
StyleSheet: { create: (styles) => styles, hairlineWidth: 1 },
memo: identity,
default: identity
},
{ get: (target, key) => (key in target ? target[key] : identity) }
)
`
const bundles = mobileWebAppDependenciesPresent()
const describeMermaid = bundles ? describe : describe.skip
let scratch = null
let server = null
let origin = null
/** The native document's own render of `FIXTURE`, built from `buildHtml` and served as a page. */
async function buildNativeDocument(outDir) {
const stubPath = join(scratch, 'import-stub.cjs')
await writeFile(stubPath, IMPORT_STUB, 'utf8')
const nativeHtmlModule = join(scratch, 'native-html.mjs')
await esbuild.build({
absWorkingDir: mobileDir,
stdin: {
contents: "export { buildHtml } from './MermaidDiagram'\n",
resolveDir: diagramDir,
loader: 'ts',
sourcefile: 'native-html-entry.ts'
},
bundle: true,
format: 'esm',
platform: 'node',
outfile: nativeHtmlModule,
target: ['node20'],
jsx: 'automatic',
logLevel: 'silent',
nodePaths: [join(mobileDir, 'node_modules')],
// `resolveExtensions` is left at its default here, with no `.web.*`, so `./MermaidDiagram`
// resolves to the file the phone builds rather than to the sibling under test.
alias: {
react: stubPath,
'react/jsx-runtime': stubPath,
'react-native': stubPath,
'react-native-webview': stubPath
},
define: { __DEV__: 'false', 'process.env.NODE_ENV': '"production"' }
})
const { buildHtml } = await import(pathToFileURL(nativeHtmlModule).href)
await writeFile(join(outDir, 'native.html'), buildHtml(FIXTURE), 'utf8')
// The same document for a diagram that throws, because the shared config the page introduced
// reaches the phone too and one of its keys changes what mermaid does on that path.
await writeFile(join(outDir, 'native-broken.html'), buildHtml(BROKEN), 'utf8')
}
beforeAll(async () => {
if (!bundles) {
return
}
// Inside mobile/ rather than the system temp dir: the entry resolves the component beside it,
// and esbuild resolves a bare specifier from the importer upward.
await mkdir(join(mobileDir, '.tmp'), { recursive: true })
scratch = await mkdtemp(join(mobileDir, '.tmp', 'mermaid-render-'))
const outDir = join(scratch, 'bundle')
await mkdir(outDir, { recursive: true })
await esbuild.build({
absWorkingDir: mobileDir,
stdin: {
contents: PAGE_ENTRY,
resolveDir: diagramDir,
loader: 'ts',
sourcefile: 'mermaid-check.ts'
},
bundle: true,
// esm with splitting, because `import('mermaid')` has to be a chunk the browser fetches when
// the diagram renders. An iife would inline the engine into the entry, which is the one shape
// this item exists to avoid.
format: 'esm',
splitting: true,
// Minified, like the bundle the shell serves: the chunk count and the bytes one render fetches
// are numbers this file records, and an unminified bundle records neither.
minify: true,
outdir: outDir,
entryNames: 'mermaid-check',
chunkNames: 'chunk-[hash]',
target: ['es2022'],
jsx: 'automatic',
logLevel: 'silent',
nodePaths: [join(mobileDir, 'node_modules')],
alias: { 'react-native': 'react-native-web' },
// The web sibling is what the page runs; the native file reaches a WebView that a browser
// renders as a line of text.
resolveExtensions: ['.web.tsx', '.web.ts', '.web.js', '.tsx', '.ts', '.js'],
define: { __DEV__: 'false', 'process.env.NODE_ENV': '"production"' }
})
await writeFile(
join(outDir, 'index.html'),
'<!doctype html><html><head><meta charset="utf-8"></head><body><div id="root"></div>' +
'<script type="module" src="/mermaid-check.js"></script></body></html>'
)
await buildNativeDocument(outDir)
const served = await createBundleServer({ outDir, cspHeader: await readShellCsp() })
server = served.server
origin = served.origin
}, 600_000)
afterAll(async () => {
server?.close()
if (scratch) {
// This run's directory only: `mobile/.tmp` is a shared ignored root and another suite may hold
// one of its own.
await rm(scratch, { recursive: true, force: true })
}
})
/**
* Every `eval` and `new Function` attempted on the page, with the stack that asked for it.
*
* `script-src 'self'` carries no `'unsafe-eval'`, so a JIT call raises a violation too — but a
* library that catches its own `EvalError` and takes a slower path would leave that violation
* looking like noise from elsewhere. The stack is what names the caller, and it has to, because
* Playwright evaluates every one of this file's own page functions through `eval`: the calls on
* this list are mostly the harness's, and only the ones from the bundle's scripts are the page's.
*/
function installJitRecorder() {
globalThis.__orcaJit = []
const record = (kind, source) => {
// Line 0 is the error's own header and line 1 is this recorder; the rest is whoever asked.
const stack = (new Error('jit').stack ?? '').split('\n').slice(2).join(' | ')
globalThis.__orcaJit.push({ kind, source: String(source).slice(0, 60), stack })
}
// oxlint-disable-next-line eslint/no-eval -- SAFETY: the recorder holds the real eval so it can count and forward calls; naming it is this function's whole purpose.
const realEval = globalThis.eval
// oxlint-disable-next-line eslint/no-eval -- SAFETY: replacing eval with a counting wrapper is the measurement, not a call.
globalThis.eval = function (source) {
record('eval', source)
return realEval.call(globalThis, source)
}
const RealFunction = globalThis.Function
function PatchedFunction(...args) {
record('Function', args.map((one) => String(one).slice(0, 40)).join('|'))
return RealFunction.apply(this, args)
}
PatchedFunction.prototype = RealFunction.prototype
globalThis.Function = PatchedFunction
}
/**
* The JIT calls that came from the bundle rather than from the harness driving it.
*
* `__orcaJit` being non-empty is the precondition: an attribution filter over a list nothing ever
* wrote to answers "none from the page" for a recorder that was never installed.
*/
async function pageJitCalls(page) {
const all = await page.evaluate(() => globalThis.__orcaJit)
expect(all.length).toBeGreaterThan(0)
return all.filter((one) => /mermaid-check\.js|\/chunk-/.test(one.stack))
}
/** What the component has on the page: its frame, the SVG under it, and every SVG anywhere. */
function readDiagram() {
const frame = document.querySelector('[data-testid="mermaid-diagram"]')
const svg = frame?.querySelector('svg') ?? null
return {
framed: frame !== null,
inFrame: frame ? frame.querySelectorAll('svg').length : -1,
// Every SVG in the document, not only the framed one: mermaid renders into a temporary
// element of its own, and an orphan left in the body is invisible to a count under the host.
inDocument: document.querySelectorAll('svg').length,
sourceBox: document.querySelector('[data-testid="mermaid-diagram-source"]') !== null,
id: svg?.id ?? null,
html: svg?.outerHTML ?? null,
text: frame?.textContent ?? null
}
}
async function openPage(browser) {
const page = await browser.newPage({ viewport: { width: 390, height: 844 } })
const consoleErrors = []
page.on('console', (message) => {
if (message.type() === 'error') {
consoleErrors.push(message.text())
}
})
page.on('pageerror', (error) => consoleErrors.push(`pageerror: ${error.message}`))
await page.addInitScript(installJitRecorder)
await page.addInitScript(installCspViolationRecorder)
await page.addInitScript(installListenerRecorder)
await page.goto(`${origin}/`, { waitUntil: 'domcontentloaded' })
await page.waitForFunction(() => document.body.dataset.ready === 'yes')
return { page, consoleErrors }
}
/**
* Drives the harness and waits for the component to settle into a diagram or a fallback.
*
* `contains` is for a source change, where "an SVG is present" is already true of the diagram being
* replaced: naming a label only the new diagram carries is what makes the wait about the new one.
*/
async function show(page, source, contains = null) {
await page.evaluate(
(next) => globalThis.__orcaMermaidSet({ mounted: true, source: next }),
source
)
await page.waitForFunction((needle) => {
const frame = document.querySelector('[data-testid="mermaid-diagram"]')
if (frame === null) {
return false
}
const svg = frame.querySelector('svg')
if (needle !== null) {
return (svg?.textContent ?? '').includes(needle)
}
return svg !== null || document.querySelector('[data-testid="mermaid-diagram-source"]') !== null
}, contains)
}
async function unmount(page) {
await page.evaluate(() => globalThis.__orcaMermaidSet({ mounted: false, source: '' }))
await page.waitForFunction(
() => document.querySelector('[data-testid="mermaid-diagram"]') === null
)
}
/**
* The two strings, with the only two differences the design measured taken out: the diagram id,
* which each host generates its own way, and the `xmlns:xlink` the native serialization adds.
*
* The id is read off the element rather than matched by a pattern, so a host that changes its id
* scheme normalises correctly instead of comparing an unreplaced string.
*/
function normaliseSvg(html, id) {
return html
.split(id)
.join('ID')
.replace(/ xmlns:xlink="[^"]*"/g, '')
}
/**
* The native document, loaded in the same browser, with the host it posts to standing in.
*
* `window.ReactNativeWebView` is what the WebView injects; the document's `post` is a no-op
* without it, so the message that drives the component's fallback would be unobservable. Recorded
* as a list because the two outcomes are told apart by what it posts: a height, or `error`.
*/
async function readNativeDocument(browser, file) {
const page = await browser.newPage({ viewport: { width: 390, height: 844 } })
try {
await page.addInitScript(() => {
globalThis.__orcaNativePosts = []
globalThis.ReactNativeWebView = {
postMessage: (message) => globalThis.__orcaNativePosts.push(String(message))
}
})
await page.goto(`${origin}/${file}`, { waitUntil: 'load' })
await page.waitForFunction(() => globalThis.__orcaNativePosts.length > 0, null, {
timeout: 120_000
})
return await page.evaluate(() => {
const svg = document.querySelector('#c svg')
return {
posts: globalThis.__orcaNativePosts,
svgs: document.querySelectorAll('svg').length,
html: svg?.outerHTML ?? null,
id: svg?.id ?? null
}
})
} finally {
await page.close()
}
}
describeMermaid(
'mermaid on the page',
() => {
for (const engine of ENGINES) {
describe(engine.name, () => {
let browser = null
beforeAll(async () => {
browser = await engine.launch()
}, 180_000)
afterAll(async () => {
await browser?.close()
})
it('paints the diagram the native document paints, with no violation and no JIT', async () => {
const { page, consoleErrors } = await openPage(browser)
const fetched = []
page.on('response', (response) => fetched.push(response.url()))
try {
await show(page, FIXTURE)
const shown = await page.evaluate(readDiagram)
expect(shown.inFrame).toBe(1)
// The precondition the absences below need: a diagram rendered, and it is mermaid's.
expect(shown.html).toContain('aria-roledescription="flowchart-v2"')
expect(await pageJitCalls(page)).toEqual([])
expect(await page.evaluate(() => globalThis.__orcaCspViolations)).toEqual([])
expect(consoleErrors).toEqual([])
// A CSS identifier, because mermaid writes `#<id>` into the stylesheet it puts inside
// the SVG; an id spelled `«r0»` would leave every one of those rules inert.
expect(shown.id).toMatch(/^[A-Za-z_][\w-]*$/)
// On demand, from here, and in one piece: the engine arrived as exactly one chunk the
// render asked for, and nothing was fetched off this origin. The count is the claim —
// importing the package rather than the artifact fetched 27 here and emitted 103 in
// the app bundle, which is what spends the shell's asset budget.
expect(fetched.filter((url) => url.includes('/chunk-'))).toHaveLength(1)
expect(fetched.filter((url) => !url.startsWith(origin))).toEqual([])
const native = await readNativeDocument(browser, 'native.html')
expect(normaliseSvg(shown.html, shown.id)).toBe(normaliseSvg(native.html, native.id))
} finally {
await page.close()
}
}, 600_000)
it('leaves the native document reporting a diagram that throws, with nothing drawn', async () => {
// The page's shared config reaches the phone as well, and `suppressErrorRendering` is a
// key the native path did not have before it. What must not change is that the component
// above the WebView still hears about a diagram that throws: `run` rethrows, the
// document's own catch posts `error`, and the component swaps in the source box.
const broken = await readNativeDocument(browser, 'native-broken.html')
expect(broken.posts).toEqual(['error'])
// And what the key does change: mermaid draws no error diagram of its own, so the
// document is empty behind the fallback rather than showing a diagram for a moment.
expect(broken.svgs).toBe(0)
// The control, the same document for a diagram that parses: a height, not `error`.
const rendered = await readNativeDocument(browser, 'native.html')
expect(rendered.posts).not.toContain('error')
expect(Number(rendered.posts[0])).toBeGreaterThan(0)
expect(rendered.svgs).toBe(1)
}, 600_000)
it('leaves one SVG across a source change, an unmount and a remount', async () => {
const { page, consoleErrors } = await openPage(browser)
const listeners = () => page.evaluate(() => globalThis.__orcaListeners.snapshot())
try {
const beforeAnyMount = await listeners()
await show(page, FIXTURE)
const first = await page.evaluate(readDiagram)
await unmount(page)
// A first mount installs listeners no dispose can take off, and they are not a leak:
// mermaid's own `window` `load` (inert under `startOnLoad: false`, and the module's
// rather than the mount's) and react-native-web's responder system, which arms itself
// on the first `View` the page renders. So the baseline a per-mount leak would move is
// the snapshot after one whole cycle, not the one before it — with mermaid's named,
// because a cycle that installed nothing would make the comparison below vacuous.
const afterEngineLoaded = await listeners()
expect(
Object.keys(afterEngineLoaded).filter((key) => !(key in beforeAnyMount))
).toContain('window load')
await show(page, FIXTURE)
await show(page, SECOND, 'Three')
const changed = await page.evaluate(readDiagram)
// One in the frame and one in the document: a diagram the first source left behind
// would be the second, wherever it hung.
expect(changed.inFrame).toBe(1)
expect(changed.inDocument).toBe(1)
expect(changed.html).not.toBe(first.html)
await unmount(page)
const gone = await page.evaluate(readDiagram)
expect(gone.framed).toBe(false)
expect(gone.inDocument).toBe(0)
// Two mounts and a source change later, the page is listening to exactly what it was
// after the first of them. A mount that registered anything of its own would show up
// here as the third.
expect(await listeners()).toEqual(afterEngineLoaded)
await show(page, FIXTURE)
const again = await page.evaluate(readDiagram)
expect(again.inFrame).toBe(1)
expect(again.inDocument).toBe(1)
expect(normaliseSvg(again.html, again.id)).toBe(normaliseSvg(first.html, first.id))
expect(await page.evaluate(() => globalThis.__orcaCspViolations)).toEqual([])
expect(consoleErrors).toEqual([])
} finally {
await page.close()
}
}, 600_000)
it('renders a hostile diagram inert', async () => {
const { page } = await openPage(browser)
try {
await show(page, HOSTILE)
const inert = await page.evaluate(() => {
const frame = document.querySelector('[data-testid="mermaid-diagram"]')
return {
rendered: frame?.querySelector('svg') !== null,
scripts: frame.querySelectorAll('script').length,
inlineHandlers: [...frame.querySelectorAll('*')].filter((element) =>
[...element.attributes].some((attribute) => attribute.name.startsWith('on'))
).length,
javascriptHrefs: [...frame.querySelectorAll('[*|href]')]
.map(
(element) =>
element.getAttribute('href') ?? element.getAttribute('xlink:href') ?? ''
)
.filter((href) => href.toLowerCase().startsWith('javascript:')).length,
pwned: globalThis.__pwned ?? null
}
})
// Rendered rather than refused, which is the whole point: the payload is carried into
// the document as data and does nothing there.
expect(inert.rendered).toBe(true)
expect(inert.scripts).toBe(0)
expect(inert.inlineHandlers).toBe(0)
expect(inert.javascriptHrefs).toBe(0)
expect(inert.pwned).toBeNull()
expect(await pageJitCalls(page)).toEqual([])
} finally {
await page.close()
}
}, 600_000)
it('falls back to the source when the diagram throws, and recovers from it', async () => {
const { page } = await openPage(browser)
try {
await show(page, BROKEN)
const failed = await page.evaluate(readDiagram)
expect(failed.sourceBox).toBe(true)
expect(failed.inFrame).toBe(0)
expect(failed.text).toContain('unclosed')
// The fallback is a state of this component, not a page with a diagram left on it:
// mermaid draws its own error diagram unless it is told not to.
expect(failed.inDocument).toBe(0)
// The control: the same component, the same mount, a diagram that parses. Named,
// because the fallback it is replacing already satisfies a bare settle.
await show(page, FIXTURE, 'Ship it')
const recovered = await page.evaluate(readDiagram)
expect(recovered.sourceBox).toBe(false)
expect(recovered.inFrame).toBe(1)
} finally {
await page.close()
}
}, 600_000)
})
}
},
3_600_000
)
@@ -0,0 +1,46 @@
import { basename, join, resolve } from 'node:path'
import { fileURLToPath } from 'node:url'
import * as esbuild from 'esbuild'
import { entryStaticClosure, mobileWebAppBuildOptions } from './build-mobile-web-app-bundle.mjs'
import { collectMobileWebAppRoutes } from './mobile-web-app-route-manifest.mjs'
const mobileDir = fileURLToPath(new URL('../../mobile', import.meta.url))
/**
* What a browser must download before one page route can paint, and what it may defer.
*
* `mobileWebAppRouteClosure` answers a different question: it reads `metafile.inputs`, which holds
* every module an entry reaches including the ones behind `import()`, so it cannot say "on
* demand" about anything (ruling 28). This walks the emitted chunks instead, from the output the
* route's own module landed in, and follows only `import-statement` edges — which is exactly where
* a dynamic import stops being part of the download.
*
* Both halves come back, because the interesting claim is always a difference: `staticInputs` is
* what the route costs to open, `deferredInputs` is everything else the bundle emitted, and a
* module absent from the first is only meaningful while it is present in the second.
*/
export async function mobileWebAppRouteChunkClosure(routeModule) {
const routes = await collectMobileWebAppRoutes(join(mobileDir, 'app'))
const { metafile } = await esbuild.build({
...mobileWebAppBuildOptions(routes),
metafile: true,
write: false
})
const routePath = resolve(mobileDir, routeModule)
const owner = Object.entries(metafile.outputs).find(([, output]) =>
Object.keys(output.inputs ?? {}).some((input) => resolve(mobileDir, input) === routePath)
)
if (!owner) {
throw new Error(`[mobile-web-app-route-chunk-closure] ${routeModule} reached no output`)
}
const reached = entryStaticClosure(metafile, owner[0])
const inputsOf = (outputs) =>
outputs.flatMap((output) => Object.keys(metafile.outputs[output]?.inputs ?? {}))
const every = Object.keys(metafile.outputs).filter((output) => output.endsWith('.js'))
return {
routeChunk: basename(owner[0]),
staticChunks: [...reached].map((output) => basename(output)),
staticInputs: inputsOf([...reached]),
deferredInputs: inputsOf(every.filter((output) => !reached.has(output)))
}
}
@@ -3,6 +3,7 @@ import { fileURLToPath } from 'node:url'
import { describe, expect, it } from 'vitest'
import { mobileWebAppRouteClosure } from './build-mobile-web-app-bundle.mjs'
import { mobileWebAppDependenciesPresent } from './mobile-web-app-bundle-dependencies.mjs'
import { mobileWebAppRouteChunkClosure } from './mobile-web-app-route-chunk-closure.mjs'
import {
textInputFontSizeOffenders,
unresolvedTextInputStyles
@@ -32,6 +33,32 @@ import {
* -47,255 at 51ae7b1b03 and -55,561 at 0ce0fc99a2. They differ because C7.1's own round-1 fold
* deleted `URL_TAP_WEBVIEW_JS` from a module only the page's component brings into this closure,
* so the saving lands on the after side and no base can show it.
*
* Then C7.10 item B put mermaid on the page, and the module list moved again:
*
* modules 4320 -> 4323 (+3)
* local modules 970 -> 973 (+3)
*
* Three modules: the configuration both hosts read, the loader, and the pre-bundled engine the
* loader imports on demand. The engine's own 66 files and the d3, dagre, katex and cytoscape trees
* under them are inside that one artifact rather than in this graph, which is why the count barely
* moves. Importing the package here instead read +2,056 and emitted 103 scripts, a package
* splitting along its own lazy diagram-type boundaries — every one of them inside the OTA generation
* the phone had already downloaded, so the split moved no bytes and spent 103 of the 256 manifest
* assets the shell will load. One artifact costs one script and one module.
*
* What the generation weighs, because every chunk ships in it whether or not a phone ever fetches
* one: the built bundle is 8,016,714 bytes across 112 assets, against the 9 MiB ceiling in
* `verify-mobile-web-app-bundle.mjs`. That is 84.9% of it, with 1,420,470 bytes left for the rest
* of C7.10 and for C7.7. Before item B the same bundle was 4,539,090 bytes, and the engine is the
* difference — deferring it defers evaluation and a fetch, never the download.
*
* `mobileWebAppRouteClosure` reads `metafile.inputs`, which holds dynamically imported modules
* under `splitting: true` just as it does under `splitting: false`, so it cannot express "on
* demand" about anything. Ruling 28: the fence for this route is `entryStaticClosure`, which
* follows `import-statement` edges only, and the module list's total is a recorded number rather
* than a budget. It moves whenever main adds a module this route reaches, and is re-recorded rather
* than argued with.
*/
const projectDir = fileURLToPath(new URL('../..', import.meta.url))
@@ -75,6 +102,16 @@ const XTERM_PACKAGES = ['@xterm/xterm', '@xterm/addon-unicode11', '@xterm/addon-
*/
const EXPECTED_OFFENDERS = 0
/** The deferred engine, as the page reaches it: one artifact, not the package's own file tree. */
const MERMAID_PAGE_ENGINE = 'src/components/pr-sidebar/mermaid-page-engine.generated.ts'
const MERMAID_PACKAGE = 'node_modules/mermaid/'
/** The module list with mermaid on the page, recorded at the base in the docstring above. */
const MODULES_WITH_MERMAID = 4323
const artifactModules = (inputs) => inputs.filter((input) => input.includes(MERMAID_PAGE_ENGINE))
const packageModules = (inputs) => inputs.filter((input) => input.includes(MERMAID_PACKAGE))
const bundles = mobileWebAppDependenciesPresent()
const describeClosure = bundles ? describe : describe.skip
@@ -103,6 +140,27 @@ describeClosure(
expect(documentModules).toContain('src/terminal/document/page-document-modules.ts')
}, 300_000)
it('reaches the engine as one deferred module and never as part of the download', async () => {
const { modules } = await mobileWebAppRouteClosure(SESSION_ROUTE)
// The engine is here, as the one artifact the loader imports.
expect(artifactModules(modules)).toHaveLength(1)
// And the package's own file tree is not, anywhere: it is inside that artifact. Meaningful
// only beside the line above, which is why the two sit together.
expect(packageModules(modules)).toEqual([])
expect(modules).toHaveLength(MODULES_WITH_MERMAID)
const download = await mobileWebAppRouteChunkClosure(SESSION_ROUTE)
// The fence: nothing of the engine is reachable from the route's own chunk by an import
// statement, so opening the session pays none of it.
expect(artifactModules(download.staticInputs)).toEqual([])
// The precondition that absence needs. The artifact is in the bundle, in a chunk the route
// reaches by a `dynamic-import` edge instead -- a deferred engine, not a dropped one.
expect(artifactModules(download.deferredInputs)).toHaveLength(1)
// And the walk read a real download rather than one chunk: the route's own chunk is in it.
expect(download.staticChunks).toContain(download.routeChunk)
expect(download.staticInputs.length).toBeGreaterThan(1000)
}, 600_000)
it('leaves the 16px seam census exactly where C7.2 left it', async () => {
const closure = await mobileWebAppRouteClosure(SESSION_ROUTE)
// Two preconditions, because zero offenders is what a walk that read nothing also reports:
@@ -11,8 +11,10 @@
* this closure reaches that package from nowhere at all.
*
* An empty list is also what a scan that read nothing reports, so the control below no longer
* uses the list — it runs the same walk over three native modules that do import the package and
* over the three web siblings that replace them.
* uses the list — it runs the same walk over the four native modules that do import the package and
* over the four web siblings that replace them. The diagram is the fourth: its native component
* seals untrusted source in a `WebView` and its sibling renders the same diagram in the document
* (C7.10 item B), which is the same substitution the other three are.
*/
import { readFileSync } from 'node:fs'
import { join } from 'node:path'
@@ -29,17 +31,19 @@ const SESSION = 'app/h/[hostId]/session/[worktreeId].tsx'
/** Nothing: every consumer this closure had now resolves to a web sibling that needs no WebView. */
const REMAINING = []
/** The three answered, whose `.web.tsx` the builder resolves instead of the native file. */
/** The four answered, whose `.web.tsx` the builder resolves instead of the native file. */
const ANSWERED = [
'src/components/MobileRichMarkdownEditor.web.tsx',
'src/components/MobileHtmlPreview.web.tsx',
'src/components/pr-sidebar/MermaidDiagram.web.tsx',
'src/terminal/TerminalWebView.web.tsx'
]
/** The native files behind those three, which do import the package. The scan's own control. */
/** The native files behind those four, which do import the package. The scan's own control. */
const NATIVE_CONSUMERS = [
'src/components/MobileRichMarkdownEditor.tsx',
'src/components/MobileHtmlPreview.tsx',
'src/components/pr-sidebar/MermaidDiagram.tsx',
'src/terminal/TerminalWebView.tsx'
]
@@ -40,10 +40,22 @@ export const MOBILE_WEB_APP_BUNDLE_MAX_TOTAL_BYTES = 9 * 1024 * 1024
/**
* How many scripts the page may be cut into, for a given number of routes. A chunk is emitted per
* distinct set of importers rather than per route, so the count is combinatorial in what the
* routes share: 8 routes measure 23 chunks, 10 measure 40, 12 measure 47, 14 measure 53, about
* three more per route at the top. Four per route with a flat 16 leaves the next few routes room,
* so a route added in C2 fails on its own weight and not on a number measured before it existed.
* distinct set of importers rather than per route, so this is not a function of the route count
* alone — it depends on what the routes in the tree happen to share. Measured on the head that
* wrote this, dropping routes from the end of the sorted key list: 8 routes emit 32 scripts, 10
* emit 43, 12 emit 61, 14 emit 69. That is between four and nine more per route depending on which
* route, so four per route with a flat 16 is a bound rather than a fit.
*
* Read the headroom before adding a route: 14 routes measure 69 against this ceiling's 72, and the
* last two of them cost 8 — exactly the 8 the ceiling grants for two. The fence is at break-even,
* so the next route that shares less than its neighbours breaches it. That is the failure it is
* for; it names the split, where the asset count alone would name nothing.
*
* The route count is the only term, deliberately. A deferred engine belongs inside one artifact and
* costs one script: C7.10 item B first reached mermaid with `import('mermaid')`, which emitted 103
* more because mermaid lazily imports each of its own diagram types, and a second term admitting
* those would have raised this fence far enough to admit any split at all. The build test's control
* is what holds that line.
*
* This is the ceiling that catches a split running away; MOBILE_WEB_APP_BUNDLE_MAX_ENTRY_BYTES
* below is the one that catches it collapsing, and it is the real budget of the two.
+1
View File
@@ -3,6 +3,7 @@ src/terminal/terminal-webview-engine.generated.ts
src/terminal/terminal-webview-engine-css.generated.ts
src/terminal/terminal-webview-document-script.generated.ts
src/components/pr-sidebar/mermaid-webview-engine.generated.ts
src/components/pr-sidebar/mermaid-page-engine.generated.ts
.expo/
dist/
/android/
+4 -1
View File
@@ -1,7 +1,10 @@
{
"$schema": "./node_modules/oxlint/configuration_schema.json",
"extends": ["../.oxlintrc.json"],
"ignorePatterns": ["src/terminal/terminal-webview-engine.generated.ts"],
"ignorePatterns": [
"src/terminal/terminal-webview-engine.generated.ts",
"src/components/pr-sidebar/mermaid-page-engine.generated.ts"
],
"rules": {
"react-hooks/exhaustive-deps": "off",
"react/no-unescaped-entities": "off",
+1 -1
View File
@@ -7,7 +7,7 @@
"start": "node scripts/start-expo.mjs",
"android": "expo run:android",
"ios": "expo run:ios",
"postinstall": "node scripts/build-terminal-webview-engine.mjs && node scripts/build-mermaid-webview-engine.mjs && node scripts/build-terminal-document-script.mjs",
"postinstall": "node scripts/build-terminal-webview-engine.mjs && node scripts/build-mermaid-webview-engine.mjs && node scripts/build-mermaid-page-engine.mjs && node scripts/build-terminal-document-script.mjs",
"test": "vitest run",
"typecheck": "tsc --noEmit",
"typecheck:tests": "tsc --noEmit -p tsconfig.test.json",
@@ -0,0 +1,61 @@
import { writeFile } from 'node:fs/promises'
import path from 'node:path'
import { createRequire } from 'node:module'
import * as esbuild from 'esbuild'
const require = createRequire(import.meta.url)
const mobileRoot = path.resolve(import.meta.dirname, '..')
const outputPath = path.join(
mobileRoot,
'src',
'components',
'pr-sidebar',
'mermaid-page-engine.generated.ts'
)
// Why: the page imports mermaid on demand, and `import('mermaid')` from inside the app bundle lands
// 103 emitted scripts rather than one -- mermaid lazily imports each of its own diagram types, so
// esbuild splits along those boundaries. All 103 sit inside the OTA generation the phone has
// already downloaded, so the split buys nothing in transfer and spends 103 of the 256 manifest
// assets the shell will load. Bundled here into one artifact, which the page imports on demand
// exactly as it imported the package.
//
// Unlike the sibling that builds the WebView engine, this is not a string: it is the module the
// page evaluates, so it is emitted as source and `mermaid-page-engine.ts` is what types it.
async function main() {
const { version } = require(require.resolve('mermaid/package.json'))
const { outputFiles } = await esbuild.build({
absWorkingDir: mobileRoot,
stdin: {
contents: "export { default } from 'mermaid'\n",
resolveDir: mobileRoot,
loader: 'ts',
sourcefile: 'mermaid-page-engine-entry.ts'
},
bundle: true,
format: 'esm',
// The whole point: one file, so the app bundle emits one deferred chunk for it.
splitting: false,
minify: true,
// The floor the shell's WebViews hold, the same pair the terminal engine is built for.
target: ['chrome74', 'safari15'],
write: false,
charset: 'utf8',
legalComments: 'none',
logLevel: 'silent',
nodePaths: [path.join(mobileRoot, 'node_modules')],
define: { 'process.env.NODE_ENV': '"production"' }
})
const bundle = Buffer.from(outputFiles[0].contents).toString('utf8')
const source = [
'// Generated by scripts/build-mermaid-page-engine.mjs.',
`// Package: mermaid@${version}, bundled as one ESM module for the page.`,
'// Do not edit by hand; regenerate via pnpm postinstall.',
'// @ts-nocheck -- minified vendor output; mermaid-page-engine.ts is where this is typed.',
bundle,
''
].join('\n')
await writeFile(outputPath, source)
}
await main()
@@ -2,6 +2,7 @@ import { memo, useMemo, useState } from 'react'
import { ScrollView, StyleSheet, Text, View } from 'react-native'
import { WebView } from 'react-native-webview'
import { colors, radii, spacing, typography } from '../../theme/mobile-theme'
import { MERMAID_DIAGRAM_CONFIG } from './mermaid-diagram-config'
import { MERMAID_ENGINE_JS } from './mermaid-webview-engine.generated'
export type MermaidDiagramProps = {
@@ -79,19 +80,31 @@ function MermaidFallback({ source, base }: MermaidDiagramProps) {
}
// JSON.stringify escapes quotes and control chars but leaves `<`, `>`, `&`, and
// the U+2028/U+2029 line separators raw — so a source containing `</script>`
// would close this inline <script> and let the rest execute as markup. Diagram
// source is untrusted (agent output, PR/chat content), so escape those to \uXXXX;
// the literal still parses back to the exact original string inside the WebView.
function encodeSourceForScript(source: string): string {
return JSON.stringify(source).replace(
// the U+2028/U+2029 line separators raw — so a value containing `</script>` would
// close the inline <script> this is spliced into and let the rest execute as
// markup. These characters only ever appear inside JSON string literals, so
// escaping them to \uXXXX is always valid and always parses back to the exact
// original text inside the WebView.
function encodeJsonForScript(json: string): string {
return json.replace(
/[<>&\u2028\u2029]/g,
(char) => `\\u${char.charCodeAt(0).toString(16).padStart(4, '0')}`
)
}
// Diagram source is untrusted: agent output, PR and chat content.
function encodeSourceForScript(source: string): string {
return encodeJsonForScript(JSON.stringify(source))
}
// The config is not untrusted, but it is not a closed set of hex colours either: a
// themeCSS or a font stack is free text, and it goes into the same script element.
function encodeConfigForScript(): string {
return encodeJsonForScript(JSON.stringify(MERMAID_DIAGRAM_CONFIG))
}
// Self-contained HTML: embedded mermaid bundle, render the graph, post the body
// height (or "error") back to RN. Theme variables match the dark sidebar palette.
// height (or "error") back to RN. The configuration is the one the page runs too.
export function buildHtml(source: string): string {
const encoded = encodeSourceForScript(source)
return `<!DOCTYPE html>
@@ -117,19 +130,7 @@ export function buildHtml(source: string): string {
}
try {
document.querySelector('.mermaid').textContent = ${encoded};
mermaid.initialize({
startOnLoad: false,
theme: 'dark',
securityLevel: 'strict',
darkMode: true,
themeVariables: {
background: '${colors.bgRaised}',
primaryColor: '${colors.bgPanel}',
primaryTextColor: '${colors.textPrimary}',
lineColor: '${colors.textSecondary}',
textColor: '${colors.textPrimary}'
}
});
mermaid.initialize(${encodeConfigForScript()});
mermaid.run({ querySelector: '.mermaid' })
.then(function () { reportHeight(); })
.catch(function () { post('error'); });
@@ -1,39 +1,113 @@
import { memo } from 'react'
import { memo, useEffect, useId, useRef, useState, type ReactNode } from 'react'
import { ScrollView, StyleSheet, Text, View } from 'react-native'
import { colors, radii, spacing, typography } from '../../theme/mobile-theme'
// The native component's own prop type, so a change to it fails here rather than drifting.
import type { MermaidDiagramProps } from './MermaidDiagram'
import { MERMAID_DIAGRAM_CONFIG } from './mermaid-diagram-config'
import { loadPageMermaid } from './mermaid-page-engine'
/**
* Web sibling: the labelled source box, which is what the native component already falls back to.
* Web sibling: the same diagram, drawn by mermaid in this document.
*
* The native one renders the diagram inside a sandboxed `WebView`, and `react-native-webview` is a
* native component with no browser counterpart — importing it runs a codegen lookup that throws,
* and the route manifest imports every route, so one such import takes the whole page down rather
* than one diagram.
* The native component seals the source inside a `WebView` whose document embeds the whole engine
* as a string, because `react-native-webview` has no browser counterpart and mermaid has no native
* renderer. On the page neither half of that applies: mermaid is a browser library, so it is an
* `import()` rather than a 3.7 MB literal, and there is no second content process to sandbox in.
*
* A real web renderer is reachable — mermaid is a browser library and the engine bundle is already
* vendored — but it is a different shape from the native path, not a smaller one: no WebView to
* sandbox untrusted source in, so the escaping the native `buildHtml` does for `</script>` and the
* line separators would have to be replaced by whatever the DOM path needs. That is its own change
* with its own proof, so this series ships the degradation the component already defines and says
* so, rather than a second renderer nobody has tested against hostile diagram source.
* What replaces the sandbox is mermaid's own `securityLevel: 'strict'`, which runs the serialized
* SVG through DOMPurify before handing it back — a `<script>`, an `on*` attribute or a
* `javascript:` href in a diagram label reaches this document as nothing at all. That is measured
* in `config/scripts/mobile-web-app-mermaid-render.test.mjs`, in both engines, against a hostile
* fixture, and so is the byte equality of the result with the native document's own render. The
* native path's `</script>` escaping has no analogue here and does not need one: the source is a
* JS string argument, not text spliced into an inline `<script>`.
*
* The import is inside the effect, so a session with no diagram in it evaluates none of the engine
* (ruling 28). It reaches the engine through `mermaid-page-engine.ts`, which loads one pre-bundled
* artifact rather than the package: importing the package here emitted 103 scripts, all of them
* already inside the generation the phone downloaded.
*/
export const MermaidDiagram = memo(function MermaidDiagram({ source, base }: MermaidDiagramProps) {
const hostRef = useRef<View>(null)
// The source that failed, rather than a flag: a flag would need clearing from the effect that
// renders the next one, and a render the component has already failed is the only thing the
// fallback is about.
const [failedSource, setFailedSource] = useState<string | null>(null)
// mermaid writes `#<id>` into the stylesheet it puts inside the SVG, so this has to be a CSS
// identifier. React spells its own `_R_0_`; the strip is for a React that changes that.
const suffix = useId().replace(/[^\w-]/g, '')
const id = `orca-mermaid-${suffix}`
const failed = failedSource === source
useEffect(() => {
// oxlint-disable-next-line typescript/consistent-type-assertions -- SAFETY: react-native-web renders View as a div and forwards the ref to it; this module only ever runs in that build.
const host = hostRef.current as unknown as HTMLElement | null
if (!host) {
return
}
let disposed = false
void (async () => {
try {
const mermaid = await loadPageMermaid()
mermaid.initialize(MERMAID_DIAGRAM_CONFIG)
const { svg } = await mermaid.render(id, source)
if (disposed) {
return
}
// Already sanitized: `securityLevel: 'strict'` is what makes this string safe to parse,
// and mermaid is the only thing that can sanitize its own serialization.
host.innerHTML = svg
} catch {
if (!disposed) {
setFailedSource(source)
}
}
})()
return () => {
disposed = true
// React owns this element, not what mermaid put inside it, so nothing else clears the
// previous diagram when the source changes.
host.replaceChildren()
}
}, [id, source])
if (failed) {
return (
<MermaidFrame>
<ScrollView
horizontal
showsHorizontalScrollIndicator={false}
style={styles.fallbackScroll}
testID="mermaid-diagram-source"
>
<Text style={[styles.fallbackText, { fontSize: base - 1 }]}>{source}</Text>
</ScrollView>
</MermaidFrame>
)
}
return (
<View style={styles.frame}>
<View style={styles.label}>
<Text style={styles.labelText}>mermaid</Text>
</View>
<ScrollView horizontal showsHorizontalScrollIndicator={false} style={styles.fallbackScroll}>
<Text style={[styles.fallbackText, { fontSize: base - 1 }]}>{source}</Text>
</ScrollView>
</View>
<MermaidFrame>
<View ref={hostRef} style={styles.host} />
</MermaidFrame>
)
})
// The native component's own fallback styles, so the degradation looks like the state that
// component already renders rather than a second design.
/** The native component's frame and label, so a diagram and its fallback sit in the same box. */
function MermaidFrame({ children }: { children: ReactNode }) {
return (
<View style={styles.frame} testID="mermaid-diagram">
<View style={styles.label}>
<Text style={styles.labelText}>mermaid</Text>
</View>
{children}
</View>
)
}
// The native component's own styles, so the page's diagram sits in the box that component draws.
// No rule reaches the SVG: mermaid emits it with `width="100%"` and its own natural `max-width`,
// and a rule of ours on the element would be a byte the native document's render does not have.
const styles = StyleSheet.create({
frame: {
borderWidth: StyleSheet.hairlineWidth,
@@ -55,6 +129,7 @@ const styles = StyleSheet.create({
fontSize: 11,
fontFamily: typography.monoFamily
},
host: { padding: spacing.sm },
fallbackScroll: { padding: spacing.sm },
fallbackText: { color: colors.textPrimary, fontFamily: typography.monoFamily }
})
@@ -0,0 +1,27 @@
import { colors } from '../../theme/mobile-theme'
/**
* The one mermaid configuration both hosts run.
*
* The native document splices it into the inline script it builds; the page hands the same object
* to `mermaid.initialize`. Written down twice these would drift, and the drift would be a diagram
* that looks different on the page from the one on the phone.
*
* `suppressErrorRendering` because a diagram that throws is a source box on both hosts: without it
* mermaid draws its own error diagram into a temporary element and then leaves that element in the
* document as it rethrows, which on the page is an orphan SVG under nobody's mount.
*/
export const MERMAID_DIAGRAM_CONFIG = {
startOnLoad: false,
theme: 'dark',
securityLevel: 'strict',
darkMode: true,
suppressErrorRendering: true,
themeVariables: {
background: colors.bgRaised,
primaryColor: colors.bgPanel,
primaryTextColor: colors.textPrimary,
lineColor: colors.textSecondary,
textColor: colors.textPrimary
}
} as const
@@ -23,6 +23,28 @@ describe('buildHtml source escaping', () => {
expect(buildHtml(payload)).toContain('\\u003c/script')
})
it('does not let a config value break out of the inline script either', async () => {
// The config is spliced into the same `<script>` as the source and is not a fixed set of hex
// colours by nature: a `themeCSS` or a font stack is free text, and `JSON.stringify` leaves
// `<` and `>` raw. Mocked rather than edited in place, because what is under test is the
// splice and not today's values.
vi.resetModules()
vi.doMock('./mermaid-diagram-config', () => ({
MERMAID_DIAGRAM_CONFIG: { themeCSS: '</script><script>window.evil=1</script>' }
}))
try {
const hostile = await import('./MermaidDiagram')
const countClosers = (html: string) => (html.match(/<\/script>/gi) ?? []).length
const benign = countClosers(buildHtml('graph TD; A-->B'))
const built = hostile.buildHtml('graph TD; A-->B')
expect(countClosers(built)).toBe(benign)
expect(built).toContain('\\u003c/script')
} finally {
vi.doUnmock('./mermaid-diagram-config')
vi.resetModules()
}
})
it('escapes the U+2028/U+2029 line separators that would break the JS literal', () => {
const payload = `a${String.fromCharCode(0x2028)}b${String.fromCharCode(0x2029)}c`
const html = buildHtml(payload)
@@ -0,0 +1,42 @@
import type { Mermaid, MermaidConfig } from 'mermaid'
/**
* The two calls the page makes of mermaid, named rather than cast.
*/
export type PageMermaid = {
initialize: (config: MermaidConfig) => void
render: (id: string, text: string) => Promise<{ svg: string }>
}
/**
* The package's own API satisfies the type above, asserted at compile time.
*
* The loader's return does not assert it. The artifact is minified vendor output and both members
* measure as `any` there (a probe assigning `engine.render` to a `number` compiles), and `any`
* satisfies every signature, so returning it as `PageMermaid` checks the two names and nothing
* about their shapes. This does: `Mermaid` is precise, so a `PageMermaid` member whose signature
* the engine does not really have fails here instead of at a call the page makes. It lives beside
* the type it constrains rather than in a test: `mobile/tsconfig.json` excludes `*.test.ts`, so the
* app's own typecheck would not cover it there. Tests are typechecked too, by `tsconfig.test.json`
* through the tests-typecheck ratchet, but that is a second program with a grandfathered baseline
* and a few files held outside it on purpose, and it is not the gate the shipped build rests on.
*
* What no type can check is that the bundle behaves like the package. The render check is that, in
* both engines, against the native document's own bytes.
*/
const _packageSatisfiesPageMermaid: (engine: Mermaid) => PageMermaid = (engine) => engine
/**
* The page's mermaid, loaded on demand from one pre-bundled artifact.
*
* `import('mermaid')` from inside the app bundle would emit 103 scripts, because mermaid lazily
* imports each of its own diagram types and esbuild splits along those boundaries. Every one of
* them ships inside the OTA generation the phone has already downloaded, so the split moves no
* bytes over the wire and spends 103 of the 256 manifest assets the shell will load. The artifact
* is the same engine in one file, and this import is still the deferred one: a session with no
* diagram on it evaluates none of it.
*/
export async function loadPageMermaid(): Promise<PageMermaid> {
const engine = await import('./mermaid-page-engine.generated')
return engine.default
}
@@ -1,6 +1,7 @@
import { readdirSync, readFileSync } from 'node:fs'
import { join } from 'node:path'
import { readFileSync } from 'node:fs'
import { join, relative } from 'node:path'
import { describe, expect, it } from 'vitest'
import { censusSourceFiles } from '../test-support/census-source-files'
/**
* The hybrid shell flag is the whole of what keeps this feature dark, so who touches it is a
@@ -34,16 +35,9 @@ const TREES = { src: 200, app: 10, modules: 1 }
const SHELL_VIEW = 'modules/orca-mobile-web-shell/src/index.ts'
function sourceFiles(directory: string): string[] {
const found: string[] = []
for (const entry of readdirSync(join(MOBILE_ROOT, directory), { withFileTypes: true })) {
const path = join(directory, entry.name)
if (entry.isDirectory()) {
found.push(...sourceFiles(path))
} else if (/\.tsx?$/.test(entry.name) && !entry.name.includes('.test.')) {
found.push(path)
}
}
return found
return censusSourceFiles(join(MOBILE_ROOT, directory))
.map((path) => relative(MOBILE_ROOT, path))
.filter((path) => /\.tsx?$/.test(path) && !path.includes('.test.'))
}
const SOURCES = Object.keys(TREES)
+9 -16
View File
@@ -1,8 +1,9 @@
import { readFileSync, readdirSync } from 'node:fs'
import { readFileSync } from 'node:fs'
import { fileURLToPath } from 'node:url'
import { extname, join, relative } from 'node:path'
import ts from 'typescript'
import { describe, expect, it } from 'vitest'
import { censusSourceFiles } from './test-support/census-source-files'
const mobileDirectory = fileURLToPath(new URL('..', import.meta.url))
const scanned = ['src', 'app']
@@ -29,16 +30,6 @@ const MAPPER_HOOKS = new Map([
['useAnimatedReaction', { updaters: [0, 1], dependencies: 2 }]
])
function sourceFiles(directory: string): string[] {
return readdirSync(directory, { withFileTypes: true }).flatMap((entry) => {
const path = join(directory, entry.name)
if (entry.isDirectory()) {
return entry.name === 'node_modules' ? [] : sourceFiles(path)
}
return sourceExtensions.has(extname(entry.name)) ? [path] : []
})
}
/** Whether this `X.value` is being written rather than read. A write is an output, not an input. */
function isWriteTarget(node: ts.PropertyAccessExpression): boolean {
const parent = node.parent
@@ -200,11 +191,13 @@ describe('reanimated mapper hooks in the web bundle', () => {
it('are all given a dependency array, because esbuild writes no worklet closure', () => {
const found: string[] = []
const missing = scanned.flatMap((directory) =>
sourceFiles(join(mobileDirectory, directory)).flatMap((path) =>
path.endsWith('.test.ts') || path.endsWith('.test.tsx')
? []
: callsMissingDependencies(path, readFileSync(path, 'utf8'), found)
)
censusSourceFiles(join(mobileDirectory, directory))
.filter((path) => sourceExtensions.has(extname(path)))
.flatMap((path) =>
path.endsWith('.test.ts') || path.endsWith('.test.tsx')
? []
: callsMissingDependencies(path, readFileSync(path, 'utf8'), found)
)
)
// The precondition the empty list above rests on. Binding resolution means a broken resolver
// reports nothing at all, which would read exactly like a clean tree.
@@ -1,8 +1,9 @@
import { readFileSync, readdirSync } from 'node:fs'
import { readFileSync } from 'node:fs'
import { fileURLToPath } from 'node:url'
import { extname, join, relative, resolve } from 'node:path'
import ts from 'typescript'
import { describe, expect, it } from 'vitest'
import { censusSourceFiles } from './test-support/census-source-files'
// Why: src/shared/rpc-contract/*-params.ts hold the host's zod schemas. Bundling one
// into the app would let client code call parse(), and requiredString is
@@ -13,16 +14,6 @@ const contractRoot = resolve(mobileRoot, '..', 'src', 'shared', 'rpc-contract')
const scannedRoots = ['app', 'src'].map((directory) => join(mobileRoot, directory))
const sourceExtensions = new Set(['.js', '.jsx', '.ts', '.tsx'])
function sourceFiles(directory: string): string[] {
return readdirSync(directory, { withFileTypes: true }).flatMap((entry) => {
const path = join(directory, entry.name)
if (entry.isDirectory()) {
return entry.name === 'node_modules' ? [] : sourceFiles(path)
}
return [path]
})
}
function targetsContract(path: string, specifier: string): boolean {
if (!specifier.startsWith('.')) {
return false
@@ -131,7 +122,7 @@ describe('RPC params contract boundary', () => {
it('keeps every mobile import of the params contract type-only', () => {
const offenders = scannedRoots
.flatMap(sourceFiles)
.flatMap(censusSourceFiles)
.filter((path) => sourceExtensions.has(extname(path)))
.flatMap((path) =>
contractValueImports(path, readFileSync(path, 'utf8')).map(
@@ -0,0 +1,109 @@
import { mkdirSync, mkdtempSync, readFileSync, readdirSync, rmSync, writeFileSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { join, relative } from 'node:path'
import { fileURLToPath } from 'node:url'
import { afterEach, beforeEach, describe, expect, it } from 'vitest'
import { censusSourceFiles, isGeneratedSource } from './census-source-files'
const mobileRoot = fileURLToPath(new URL('../..', import.meta.url))
let scratch = ''
beforeEach(() => {
scratch = mkdtempSync(join(tmpdir(), 'orca-census-source-files-'))
})
afterEach(() => {
rmSync(scratch, { recursive: true, force: true })
})
function plant(relativePath: string, source: string): void {
const absolute = join(scratch, relativePath)
mkdirSync(join(absolute, '..'), { recursive: true })
writeFileSync(absolute, source, 'utf8')
}
describe('the source files a census reads', () => {
it('leaves out build output that would be read as a violating import', () => {
// The shape that started this: a generated file whose text holds exactly what a census is
// looking for. Every one of them is minified vendor output, so the match is a token in
// somebody else's code and the census has no line to offer anybody.
const violating = "import { requiredString } from '../../src/shared/rpc-contract/params'\n"
plant('src/components/engine.generated.ts', violating)
plant('src/components/Diagram.tsx', violating)
const walked = censusSourceFiles(join(scratch, 'src')).map((path) => relative(scratch, path))
expect(walked).toEqual([join('src', 'components', 'Diagram.tsx')])
// Both halves: the generated file is gone, and the file beside it carrying the same text is
// not — a walk that returned nothing at all would satisfy the first line on its own.
expect(readFileSync(join(scratch, 'src/components/engine.generated.ts'), 'utf8')).toBe(
violating
)
})
it('leaves out node_modules, and keeps everything else', () => {
plant('src/a.ts', '')
plant('src/node_modules/dep/index.ts', '')
plant('src/deep/b.tsx', '')
plant('src/notes.md', '')
expect(
censusSourceFiles(join(scratch, 'src'))
.map((path) => relative(scratch, path))
.sort()
).toEqual([join('src', 'a.ts'), join('src', 'deep', 'b.tsx'), join('src', 'notes.md')].sort())
})
it('names build output by the suffix the generators write, and nothing else', () => {
expect(isGeneratedSource('mermaid-page-engine.generated.ts')).toBe(true)
expect(isGeneratedSource('route-manifest.generated.tsx')).toBe(true)
expect(isGeneratedSource('generated.ts')).toBe(false)
expect(isGeneratedSource('rpc-client.ts')).toBe(false)
expect(isGeneratedSource('generated-goldens.ts')).toBe(false)
})
it('covers every artifact the tree generates, read from the ignore file that lists them', () => {
// The list is `mobile/.gitignore`, because that is what the generators and the build agree on.
// A sixth artifact landing under a name this predicate does not match would put a multi-megabyte
// vendor bundle back into every census, which is the failure this module exists for.
const ignored = readFileSync(join(mobileRoot, '.gitignore'), 'utf8')
.split('\n')
.map((line) => line.trim())
.filter((line) => line.endsWith('.generated.ts'))
expect(ignored.length).toBeGreaterThanOrEqual(5)
for (const entry of ignored) {
expect(isGeneratedSource(entry), entry).toBe(true)
}
})
it('is the only walk of its kind left in the tree', () => {
// The line every census used to hold a copy of. One spelling, so a tenth census cannot quietly
// reintroduce the cost by pasting the walk rather than importing it.
const copies: string[] = []
const walk = (directory: string): void => {
for (const entry of readdirSync(directory, { withFileTypes: true })) {
const path = join(directory, entry.name)
if (entry.isDirectory()) {
if (entry.name !== 'node_modules') {
walk(path)
}
continue
}
if (!/\.tsx?$/.test(entry.name) || isGeneratedSource(entry.name)) {
continue
}
if (readFileSync(path, 'utf8').includes("entry.name === 'node_modules' ? []")) {
copies.push(relative(mobileRoot, path))
}
}
}
walk(join(mobileRoot, 'src'))
walk(join(mobileRoot, 'app'))
// This file is in the list because it carries the line as the text it greps for; the module
// beside it is the walk itself. Named rather than filtered out, so a third entry is a failure
// that reads as one.
expect(copies.sort()).toEqual([
'src/test-support/census-source-files.test.ts',
'src/test-support/census-source-files.ts'
])
})
})
@@ -0,0 +1,37 @@
import { readdirSync } from 'node:fs'
import { join } from 'node:path'
/**
* Build output, which a source census reads as source and must not.
*
* `mobile/.gitignore` is the list: five `*.generated.ts` files under `mobile/src`, written by the
* postinstall generators. Two are vendored engines — 3.7 MB of mermaid for the native WebView and
* 3.5 MB of it for the page — and 7.9 MB of what a walk over this tree returns is generated. A
* census that parses them parses minified third-party code looking for call sites nobody in this
* repo wrote and nobody can move, and pays the whole parse to find them: five of those files is
* what took `rpc-params-contract-type-only-boundary` from 1.5 s to over its 5 s timeout in CI.
*
* The generator that writes each one is ordinary source and is still walked, which is where a real
* reach into whatever a census is fencing would be.
*/
export function isGeneratedSource(name: string): boolean {
return /\.generated\.tsx?$/.test(name)
}
/**
* Every file under `directory`, absolute, without `node_modules` or build output.
*
* Nine censuses in this tree held a copy of this walk, and two of them had grown a private opinion
* about generated files while the rest had none. What each census counts as *interesting* — which
* extensions, whether test files are in — stays its own business, because they genuinely disagree;
* what counts as a source file at all does not.
*/
export function censusSourceFiles(directory: string): string[] {
return readdirSync(directory, { withFileTypes: true }).flatMap((entry) => {
const path = join(directory, entry.name)
if (entry.isDirectory()) {
return entry.name === 'node_modules' ? [] : censusSourceFiles(path)
}
return isGeneratedSource(entry.name) ? [] : [path]
})
}
+3 -12
View File
@@ -1,8 +1,9 @@
import { readFileSync, readdirSync } from 'node:fs'
import { readFileSync } from 'node:fs'
import { fileURLToPath } from 'node:url'
import { extname, join, relative, resolve } from 'node:path'
import ts from 'typescript'
import { describe, expect, it } from 'vitest'
import { censusSourceFiles } from '../test-support/census-source-files'
import {
GenerationScopedRequestOwner,
type LoadedRequest,
@@ -370,16 +371,6 @@ function importsOwner(path: string, source: string): boolean {
})
}
function sourceFiles(directory: string): string[] {
return readdirSync(directory, { withFileTypes: true }).flatMap((entry) => {
const path = join(directory, entry.name)
if (entry.isDirectory()) {
return entry.name === 'node_modules' ? [] : sourceFiles(path)
}
return [path]
})
}
function declaredInside(callback: ts.Node): Set<string> {
const names = new Set<string>()
const bind = (name: ts.BindingName): void => {
@@ -492,7 +483,7 @@ function loaderWrites(path: string, source: string): string[] {
describe('loader write fence', () => {
const holders = ['app', 'src']
.map((directory) => join(mobileRoot, directory))
.flatMap(sourceFiles)
.flatMap(censusSourceFiles)
.filter((path) => ['.ts', '.tsx'].includes(extname(path)))
.filter((path) => !/\.test\.tsx?$/.test(path))
.map((path) => ({ path, source: readFileSync(path, 'utf8') }))
@@ -1,8 +1,9 @@
import { readFileSync, readdirSync } from 'node:fs'
import { readFileSync } from 'node:fs'
import { fileURLToPath } from 'node:url'
import { extname, join, relative, resolve } from 'node:path'
import ts from 'typescript'
import { describe, expect, it } from 'vitest'
import { censusSourceFiles } from '../test-support/census-source-files'
/**
* Bans the escapes that would make the typed boundary decorative.
@@ -68,16 +69,6 @@ const CAST_FENCE_EXCEPTIONS: readonly CastFenceException[] = [
// inside a string literal therefore reads as one — which fails closed.
const SUPPRESSION = /@ts-(?:expect-error|ignore|nocheck)\b/
function sourceFiles(directory: string): string[] {
return readdirSync(directory, { withFileTypes: true }).flatMap((entry) => {
const path = join(directory, entry.name)
if (entry.isDirectory()) {
return entry.name === 'node_modules' ? [] : sourceFiles(path)
}
return [path]
})
}
function parse(path: string, source: string): ts.SourceFile {
const extension = extname(path)
return ts.createSourceFile(
@@ -150,7 +141,7 @@ function moduleEdges(path: string, source: string): { imports: string[]; reExpor
}
const scanned = scannedRoots
.flatMap(sourceFiles)
.flatMap(censusSourceFiles)
.filter((path) => sourceExtensions.has(extname(path)))
.filter((path) => !/\.test\.tsx?$/.test(path))
@@ -1,8 +1,9 @@
import { readFileSync, readdirSync } from 'node:fs'
import { readFileSync } from 'node:fs'
import { fileURLToPath } from 'node:url'
import { extname, join, relative, resolve } from 'node:path'
import ts from 'typescript'
import { describe, expect, it } from 'vitest'
import { censusSourceFiles } from '../test-support/census-source-files'
import { readScenarios } from '../test-support/rpc-recording/scenario-input'
import { RPC_SUBSCRIPTION_SITES, type RpcSubscriptionSite } from './rpc-subscription-inventory'
@@ -38,16 +39,6 @@ const sourceExtensions = new Set(['.js', '.jsx', '.ts', '.tsx'])
/** The port's own implementation and the oracle that scripts it. Neither consumes a stream. */
const EXCLUDED_DIRECTORIES = ['src/transport/', 'src/test-support/']
function sourceFiles(directory: string): string[] {
return readdirSync(directory, { withFileTypes: true }).flatMap((entry) => {
const path = join(directory, entry.name)
if (entry.isDirectory()) {
return entry.name === 'node_modules' ? [] : sourceFiles(path)
}
return [path]
})
}
function parse(path: string, source: string): ts.SourceFile {
const extension = extname(path)
return ts.createSourceFile(
@@ -80,7 +71,7 @@ export function subscribedMethods(path: string, source: string): string[] {
}
const scanned = scannedRoots
.flatMap(sourceFiles)
.flatMap(censusSourceFiles)
.filter((path) => sourceExtensions.has(extname(path)))
.filter((path) => !/\.test\.tsx?$/.test(path))
.map((path) => relative(mobileRoot, path).split(/[/\\]/).join('/'))
@@ -1,7 +1,9 @@
import { readdirSync, readFileSync } from 'node:fs'
import { readFileSync } from 'node:fs'
import { relative } from 'node:path'
import { fileURLToPath } from 'node:url'
import ts from 'typescript-api'
import { describe, expect, it } from 'vitest'
import { censusSourceFiles } from '../test-support/census-source-files'
const SOURCE_ROOT = fileURLToPath(new URL('..', import.meta.url))
const TIMER_GLOBALS = new Set(['setTimeout', 'clearTimeout', 'setInterval', 'clearInterval'])
@@ -28,9 +30,9 @@ const PARKING_OPERATORS = new Set([
type Census = { parked: string[]; shared: string[] }
function productFiles(): string[] {
return readdirSync(SOURCE_ROOT, { recursive: true, encoding: 'utf8' })
.filter((entry) => /\.tsx?$/.test(entry) && !/\.test\.tsx?$|\.generated\.ts$/.test(entry))
.map((entry) => entry.replaceAll('\\', '/'))
return censusSourceFiles(SOURCE_ROOT)
.map((path) => relative(SOURCE_ROOT, path).replaceAll('\\', '/'))
.filter((entry) => /\.tsx?$/.test(entry) && !/\.test\.tsx?$/.test(entry))
}
function timerName(node: ts.Node): string | null {
@@ -1,8 +1,9 @@
import { readFileSync, readdirSync } from 'node:fs'
import { readFileSync } from 'node:fs'
import { fileURLToPath } from 'node:url'
import { extname, join, relative } from 'node:path'
import ts from 'typescript'
import { describe, expect, it } from 'vitest'
import { censusSourceFiles } from '../test-support/census-source-files'
import {
UNCHECKED_RPC_READERS,
type UncheckedRpcReaderEntry
@@ -46,16 +47,6 @@ const UNCHECKED_READER_NAMES = new Set([
// them in prose alone.
const SELF_FILES = new Set(['src/transport/rpc-reader-payload.ts'])
function sourceFiles(directory: string): string[] {
return readdirSync(directory, { withFileTypes: true }).flatMap((entry) => {
const path = join(directory, entry.name)
if (entry.isDirectory()) {
return entry.name === 'node_modules' ? [] : sourceFiles(path)
}
return [path]
})
}
function parse(path: string, source: string): ts.SourceFile {
const extension = extname(path)
return ts.createSourceFile(
@@ -85,7 +76,7 @@ function uncheckedReaderCount(path: string, source: string): number {
}
const scanned = scannedRoots
.flatMap(sourceFiles)
.flatMap(censusSourceFiles)
.filter((path) => sourceExtensions.has(extname(path)))
.filter((path) => !/\.test\.tsx?$/.test(path))
.map((path) => relative(mobileRoot, path).split(/[/\\]/).join('/'))
@@ -1,8 +1,9 @@
import { readFileSync, readdirSync } from 'node:fs'
import { readFileSync } from 'node:fs'
import { fileURLToPath } from 'node:url'
import { extname, join, relative, resolve } from 'node:path'
import ts from 'typescript'
import { describe, expect, it } from 'vitest'
import { censusSourceFiles } from '../test-support/census-source-files'
import {
UNVALIDATED_RPC_REQUEST_PORT_OWNERS,
UNVALIDATED_RPC_REQUEST_PORT_PENDING,
@@ -33,6 +34,10 @@ import {
* - Test files. `*.test.ts(x)` is not scanned: faking the port is how these suites work, and a
* test does not ship. A non-test file that fakes it (tsconfig excludes tests, so some do) is
* scanned and listed.
* - Build output. `censusSourceFiles` leaves every `*.generated.ts` out, and one of them is a
* bundled vendor engine whose own dependencies contain the token `sendRequest` — minified
* third-party code, not a call site anybody in this repo wrote or can move onto an
* RpcOperation. The script that emits each of them is ordinary source and is walked.
* A compile-time fence would catch the first two. That needs `RpcClient` to stop carrying the
* port, which needs the call sites migrated first — the thing this list is counting down.
*/
@@ -51,16 +56,6 @@ const SELF_FILES = new Set([
/** The coalescing second sender: same unchecked string in, same unread envelope out. */
const SECOND_SENDER = 'sendSingleFlightRequest'
function sourceFiles(directory: string): string[] {
return readdirSync(directory, { withFileTypes: true }).flatMap((entry) => {
const path = join(directory, entry.name)
if (entry.isDirectory()) {
return entry.name === 'node_modules' ? [] : sourceFiles(path)
}
return [path]
})
}
function parse(path: string, source: string): ts.SourceFile {
const extension = extname(path)
return ts.createSourceFile(
@@ -144,7 +139,7 @@ const inventory: readonly UnvalidatedRpcRequestPortEntry[] = [
]
const scanned = scannedRoots
.flatMap(sourceFiles)
.flatMap(censusSourceFiles)
.filter((path) => sourceExtensions.has(extname(path)))
.filter((path) => !/\.test\.tsx?$/.test(path))
.map((path) => relative(mobileRoot, path).split(/[/\\]/).join('/'))
+1 -1
View File
@@ -63,7 +63,7 @@
},
{
"file": "src/components/pr-sidebar/MermaidDiagram.web.tsx",
"reason": "The native component renders the diagram inside a sandboxed WebView, and react-native-webview is a native component with no browser counterpart: importing it runs a codegen lookup that throws, and the route manifest imports every route, so one such import takes the whole page down rather than one diagram. This one renders the labelled source box the native component already falls back to on a parse or render error. A real browser renderer is reachable — mermaid is a browser library and the engine bundle is vendored — but it is a different shape rather than a smaller one: with no WebView to sandbox untrusted diagram source in, the escaping buildHtml does for </script> and the line separators has to be replaced by whatever the DOM path needs, which is its own change with its own proof."
"reason": "The native component seals the diagram inside a WebView whose document embeds the whole mermaid bundle as a string, because react-native-webview is a native component with no browser counterpart: importing it runs a codegen lookup that throws, and the route manifest imports every route, so one such import takes the whole page down rather than one diagram. This one renders the same diagram in this document instead — mermaid is a browser library, so it is an import() inside the render effect rather than a 3.7 MB literal, and the two hosts share one MERMAID_DIAGRAM_CONFIG. What replaces the sandbox is mermaid's own securityLevel: 'strict', which runs the serialized SVG through DOMPurify; the native path's </script> escaping has no analogue because the source is a JS string argument rather than text spliced into an inline script. Both are measured in both engines under the shipped CSP by config/scripts/mobile-web-app-mermaid-render.test.mjs, which also pins the rendered SVG byte for byte against the native document's own render."
},
{
"file": "app/h/[hostId]/tasks.web.tsx",
@@ -15,6 +15,53 @@ const OMP_RUNTIME_CASES = [
] as const
describe('OMP agent_end contract', () => {
it('keeps a Pi pane working until async subagents finish', async () => {
const harness = createAgentStatusExtensionHarness({ kind: 'pi' })
await harness.callHook('agent_start')
harness.emitPiEvent('task:subagent:lifecycle', { id: 'child-1', status: 'started' })
await harness.callHook('agent_settled', undefined, { isIdle: () => true })
expect(postedHookNames(harness.fetchMock)).toEqual(['agent_start'])
harness.emitPiEvent('task:subagent:lifecycle', { id: 'child-1', status: 'completed' })
await vi.waitFor(() =>
expect(postedHookNames(harness.fetchMock)).toEqual(['agent_start', 'agent_end'])
)
})
it('ignores malformed or unknown Pi subagent lifecycle events', async () => {
const harness = createAgentStatusExtensionHarness({ kind: 'pi' })
harness.emitPiEvent('task:subagent:lifecycle', {})
harness.emitPiEvent('task:subagent:lifecycle', { id: 'child-1', status: 'paused' })
await harness.callHook('agent_start')
await harness.callHook('agent_settled')
await vi.waitFor(() =>
expect(postedHookNames(harness.fetchMock)).toEqual(['agent_start', 'agent_end'])
)
})
it('keeps one lifecycle subscription across extension reloads', async () => {
const harness = createAgentStatusExtensionHarness({ kind: 'pi' })
harness.reload()
expect(harness.piEventListenerCount('task:subagent:lifecycle')).toBe(1)
expect(harness.piEventListenerCount('subagent:async-started')).toBe(1)
expect(harness.piEventListenerCount('subagent:async-complete')).toBe(1)
harness.emitPiEvent('task:subagent:lifecycle', { id: 'child-1', status: 'started' })
await vi.waitFor(() => expect(postedHookNames(harness.fetchMock)).toEqual(['agent_start']))
})
it('accepts the pi-subagents async lifecycle aliases', async () => {
const harness = createAgentStatusExtensionHarness({ kind: 'pi' })
harness.emitPiEvent('subagent:async-started', { id: 'child-1' })
await harness.callHook('agent_settled')
expect(postedHookNames(harness.fetchMock)).toEqual(['agent_start'])
harness.emitPiEvent('subagent:async-complete', { id: 'child-1' })
await vi.waitFor(() =>
expect(postedHookNames(harness.fetchMock)).toEqual(['agent_start', 'agent_end'])
)
})
it.each(OMP_RUNTIME_CASES)(
'keeps %s working when agent_end will continue',
async (_name, args) => {
@@ -46,6 +46,8 @@ export type AgentStatusExtensionHarness = {
handlers: Record<string, HookHandler>
processEnv: Record<string, string | undefined>
callHook: (name: string, event?: unknown, context?: HookContext) => Promise<void>
emitPiEvent: (name: string, event: unknown) => void
piEventListenerCount: (name: string) => number
// Re-invoke the extension factory in the same process (as Pi does on an
// in-process extension reload), swapping in the freshly registered handlers.
reload: () => void
@@ -130,6 +132,7 @@ export function createAgentStatusExtensionHarness(args: {
command: { handler: (args: string, context: HookContext) => Promise<void> }
) => void
setModel: (model: unknown) => Promise<boolean>
events?: EventEmitter
}) => void
}
} = { exports: {} }
@@ -191,6 +194,7 @@ export function createAgentStatusExtensionHarness(args: {
}
const handlers: Record<string, HookHandler> = {}
const piEvents = new EventEmitter()
const commands: AgentStatusExtensionHarness['commands'] = {}
const setModelMock = vi.fn(async (_model: unknown) => true)
const registerInto = (target: Record<string, HookHandler>): void => {
@@ -199,6 +203,7 @@ export function createAgentStatusExtensionHarness(args: {
commands[name] = command
},
setModel: setModelMock,
events: piEvents,
on(name: string, handler: HookHandler) {
target[name] = handler
}
@@ -219,6 +224,10 @@ export function createAgentStatusExtensionHarness(args: {
callHook: async (name, event, hookContext) => {
await handlers[name]?.(event, hookContext)
},
emitPiEvent: (name, event) => {
piEvents.emit(name, event)
},
piEventListenerCount: (name) => piEvents.listenerCount(name),
reload: () => {
for (const key of Object.keys(handlers)) {
delete handlers[key]
+34 -5
View File
@@ -129,13 +129,27 @@ export function getPiAgentStatusHandlerSourceLines(kind: PiAgentKind): string[]
' if (ownerPid && ownerPid !== selfPid && isStatusOwnerAlive(ownerPid)) return',
` process.env.${ownerEnv} = selfPid`,
' resetPostQueue()',
' const piEventBus = (pi as { events?: { on?: (name: string, handler: (event: unknown) => void) => void } }).events',
' const lifecycleState = (piEventBus as { __orcaPiSubagents?: { active: Set<string>; waiting: boolean; onEvent?: (event: unknown, forcedStatus?: string) => void; listener?: (event: unknown) => void } } | undefined)?.__orcaPiSubagents ?? { active: new Set<string>(), waiting: false }',
' if (piEventBus) (piEventBus as { __orcaPiSubagents?: unknown }).__orcaPiSubagents = lifecycleState',
' if (piEventBus?.on && !(lifecycleState as { listener?: unknown }).listener) {',
' const listener = (event: unknown) => lifecycleState.onEvent?.(event)',
' lifecycleState.listener = listener',
" piEventBus.on('task:subagent:lifecycle', listener)",
" piEventBus.on('subagent:async-started', (event: unknown) => lifecycleState.onEvent?.(event, 'started'))",
" piEventBus.on('subagent:async-complete', (event: unknown) => lifecycleState.onEvent?.(event, 'completed'))",
' }',
...(kind !== 'pi'
? [" pi.on('session_shutdown', () => { resetPostQueue(); clearPendingAgentEndCheck() })"]
? [
" pi.on('session_shutdown', () => { lifecycleState.active.clear(); lifecycleState.waiting = false; resetPostQueue(); clearPendingAgentEndCheck() })"
]
: []),
...(kind !== 'prime-agent'
? [
" pi.on('session_switch', (_event, ctx) => {",
' if (!isOmpRuntime()) return',
' lifecycleState.active.clear()',
' lifecycleState.waiting = false',
' resetPostQueue()',
' clearPendingAgentEndCheck()',
' updateRuntimeOmpSessionMetadata(ctx)',
@@ -154,6 +168,7 @@ export function getPiAgentStatusHandlerSourceLines(kind: PiAgentKind): string[]
` onStatus('agent_start', (${bareCtxParams}) => {`,
...captureSessionMetadata,
' clearPendingAgentEndCheck()',
' lifecycleState.waiting = false',
' runGeneration += 1',
// Why: a turn cannot begin under a dialog holding input focus, so this is the one
// boundary that can recover a modal whose close never arrived.
@@ -224,11 +239,25 @@ export function getPiAgentStatusHandlerSourceLines(kind: PiAgentKind): string[]
' pendingAgentEndCheck = null',
' pendingAgentEndContext = null',
' }',
'',
' // Why: isIdle flips before agent_settled handlers run, so both paths',
' // share a guard instead of racing duplicate completion posts — one keyed on the',
' // generation of the run that ENDED, so a later run still reports its own end.',
' // Defer completion while live child work remains.',
' lifecycleState.onEvent = (event: unknown, forcedStatus?: string): void => {',
" if (!event || typeof event !== 'object') return",
" const id = typeof (event as { id?: unknown }).id === 'string' ? (event as { id: string }).id : ''",
' const status = forcedStatus ?? (event as { status?: unknown }).status',
' if (!id) return',
" if (status === 'started') { lifecycleState.active.add(id); post('agent_start'); return }",
" if (status !== 'completed' && status !== 'failed' && status !== 'aborted') return",
' lifecycleState.active.delete(id)',
' if (lifecycleState.active.size === 0 && lifecycleState.waiting) {',
' lifecycleState.waiting = false',
' postAgentEndOnce()',
' }',
' }',
' function postAgentEndOnce(): void {',
' if (lifecycleState.active.size > 0) {',
' lifecycleState.waiting = true',
' return',
' }',
' if (completionPostedGeneration === endedRunGeneration) return',
' completionPostedGeneration = endedRunGeneration',
// Why: distinct from the completion guard, which holds the generation of the posted run
@@ -91,7 +91,7 @@ it('prepares the execution host OMP config and status extension for a guarded la
source.mockReturnValue(false)
expect(
await augment.mock.calls[1][0]({ id: 'other', shell: '/bin/bash', env: {}, command: 'codex' })
).toEqual({})
).toEqual({ ORCA_OPENCODE_AGENT: 'opencode' })
} finally {
runtime.stop()
dispatcher.dispose()