@reclaimprotocol/agent 0.1.22 → 0.1.24

package/skill/user-script.md

@@ -0,0 +1,61 @@
+# User scripts (`jsUserScripts` / `customInjection`)
+
+A provider can inject **plain JavaScript** that runs in the page before every
+page load. Builder stores it as `webSettings.jsUserScripts`; old-devtools stores
+it as `customInjection`. Identical semantics, different field name.
+
+## What the script is for
+
+The verification client **already intercepts the page's network requests
+automatically** — the script does not need to capture, forward, or "claim" them.
+Its job is to get the page into the state where the target request happens,
+using standard browser APIs:
+
+- **Navigate** — `window.location.href = '…'`, `location.assign(…)`, the
+  history API.
+- **Interact** — select an element and `.click()` it, submit a form, dispatch
+  events.
+- **Wait** — poll the DOM until login/MFA completes or content loads, then
+  trigger the next step.
+
+Write it like any page script. It runs before EVERY page load, so keep it
+idempotent, cheap, and guarded against firing at the wrong time.
+
+Both backends run it the same way: before every page load, including before the
+first navigation to `initialUrl`/`loginUrl`.
+
+## `window.Reclaim` — rarely needed
+
+`window.Reclaim` is an OPTIONAL bridge for a handful of edge cases. Most
+providers never touch it, and **it does not do navigation** — use the standard
+browser APIs above for that.
+
+**On the Builder verification client it is installed but INERT.** Both
+`window.Reclaim` and `window.reclaimInterceptor` are injected before every
+document load, so a call won't throw — but the run never drains the
+`Reclaim` outbox and never delivers traffic to
+`reclaimInterceptor.addResponseMiddleware`, so nothing you send is acted on
+and no middleware ever fires. Write Builder-targeted scripts in plain browser
+JS unconditionally, and let the capture loop find the request itself.
+
+Don't reach for it by default. When an edge case genuinely requires it, consult
+the authoritative API surface rather than guessing:
+<https://github.com/reclaimprotocol/provider-web-script-dev/blob/main/src/support/env.d.ts>
+
+## Declaring the requests the script fires
+
+Requests the script triggers beyond the proven one (for example, pagination) are
+declared as `allowedJsRequests` (Builder) / `allowedInjectedRequestData`
+(old-devtools). Same concept, different field name.
+
+⚠️ **Before populating them to gate `verifyProof(proof, { providerId })`**, read
+topic `hash-validation` — the declared `url` is hashed VERBATIM, so a
+session-unique URL there makes `verifyProof` reject every real proof. Leaving
+the field empty is better than populating it wrong.
+
+## Related topics
+
+- `interception` — `injectionType`/`interceptorType`, live interception, and the
+  document-replay flag.
+- `hash-validation` — `bodySniff`, and how `verifyProof({ providerId })` gates
+  on the provider's declared spec.

package/src/authoring/backend.ts

@@ -85,18 +85,21 @@ export interface AuthoringBackend {
 	/** This session's drafts (propose → replay/run_proof). */
 	readonly drafts: DraftStore
 	/** Prove a drafted recipe. Local: attestor SDK (rich claim view). Remote: TEE
-	 *  `/reclaim/prove` (lean, secret-free summary). Returns the environment's
-	 *  display shape. A backend may record the proven recipe internally (e.g.
-	 *  the cloud publish step) — that side effect is the backend's, not ours. */
+	 * `/reclaim/prove` (lean, secret-free summary). Returns the environment's
+	 * display shape. A backend may record the proven recipe internally (for
+	 * example, the cloud publish step) — that side effect is the backend's, not
+	 * ours. */
 	prove(draft: Draft, opts?: ProveOptions): Promise<unknown>
 	/**
-	 * Validate/replay a drafted recipe before proving. With `withoutSecrets` it
-	 * is the AUTH-BOUND check: re-issue the request stripped of the captured
-	 * secrets (local: a Node re-fetch without them; remote: an anonymous `fetch`
-	 * in the Popcorn page, `credentials: 'omit'`) and report whether the values
-	 * are STILL extractable — i.e. the endpoint is public. Without it, validate
-	 * extraction for the authenticated request. The shape is environment-specific
-	 * and passed straight through as the tool's result.
+	 * Validate/replay a drafted recipe before proving. Both local and remote
+	 * backends re-issue the request FROM INSIDE the live attached page (a
+	 * `fetch` run over CDP), never a detached out-of-band call, so replay
+	 * always reflects the real browser session. With `withoutSecrets` it is
+	 * the AUTH-BOUND check: re-issue anonymously (`credentials: 'omit'`, no
+	 * secret headers) and report whether the values are STILL extractable —
+	 * that is, the endpoint is public. Without it, validate extraction for the
+	 * authenticated request. The shape is environment-specific and passed
+	 * straight through as the tool's result.
 	 */
 	replay(draft: Draft, opts?: { withoutSecrets?: boolean }): Promise<unknown>
 }

package/src/authoring/tools.ts

@@ -116,7 +116,10 @@ export function authoringTools(
 		defineTool<Record<string, unknown>>(
 			{
 				name: 'navigate',
-				description: 'Navigate the browser tab to a URL, waiting for load.',
+				description:
+					'Navigate the captured tab to a URL and wait for its load event. '
+					+ 'Returns the URL the tab actually landed on, so you can detect a '
+					+ 'redirect to a login page.',
 				inputSchema: objectSchema(
 					{ url: { type: 'string' }, timeoutMs: { type: 'number' } },
 					['url'],
@@ -144,8 +147,10 @@ export function authoringTools(
 			{
 				name: 'eval_in_page',
 				description:
-					'Evaluate a JavaScript expression in the page and return its value '
-					+ '(use to read the displayed value, check login state, etc.).',
+					'Evaluate a JavaScript expression in the page and return its value. '
+					+ 'Use it to read the value being proven out of the DOM, to check '
+					+ 'login state, or to trigger the target request (for example, '
+					+ '`location.reload()`).',
 				inputSchema: objectSchema(
 					{ expression: { type: 'string' } }, ['expression'],
 				),
@@ -156,8 +161,10 @@ export function authoringTools(
 			{
 				name: 'wait_for_page',
 				description:
-					'Poll a JavaScript expression until it is truthy or the timeout '
-					+ 'elapses (e.g. wait for the user to finish logging in).',
+					'Poll a JavaScript expression once a second until it is truthy or '
+					+ 'the timeout elapses. Use it to wait for content to appear. To '
+					+ 'wait for a login, use wait_for_login instead — page JavaScript '
+					+ 'cannot see the httpOnly session cookie.',
 				inputSchema: objectSchema(
 					{ expression: { type: 'string' }, timeoutMs: { type: 'number' } },
 					['expression'],
@@ -179,6 +186,111 @@ export function authoringTools(
 				return { ready: false }
 			},
 		),
+		defineTool<Record<string, unknown>>(
+			{
+				name: 'test_user_script',
+				description:
+					'Dry-run a USER SCRIPT (the `jsUserScripts` / `customInjection` '
+					+ 'field) in the LIVE attached tab, BEFORE publishing. Installs '
+					+ '`script` via CDP so it runs on the next navigation exactly as '
+					+ 'the real field would, then reports whether it ran and what it '
+					+ 'threw. With `navigateUrl`, it navigates there and removes the '
+					+ 'script once the result is read — self-cleaning, safe to repeat. '
+					+ 'WITHOUT `navigateUrl` the script stays installed (navigate '
+					+ 'yourself, then re-call this tool or read '
+					+ '`window.__reclaimUserScriptResult` via eval_in_page) and keeps '
+					+ 'running on every later navigation until a call WITH '
+					+ '`navigateUrl` removes it — so don\'t stack manual-mode calls. '
+					+ 'Guide: how_it_works({ topic: "user-script" }).',
+				inputSchema: objectSchema(
+					{
+						script: { type: 'string' },
+						navigateUrl: { type: 'string' },
+						timeoutMs: { type: 'number' },
+					},
+					['script'],
+				),
+			},
+			async(args) => {
+				const backend = resolveBackend(args)
+				const script = String(args.script)
+				// The user's script is spliced in as a STRING and compiled at
+				// runtime via `new Function`, not as raw top-level source: a
+				// syntax error in it would otherwise fail to parse the entire
+				// wrapper (result init, error listener, and try/catch included),
+				// so the tool would report ran:false / errors:[] instead of the
+				// actual SyntaxError.
+				const wrapped = `
+					window.__reclaimUserScriptResult = { ran: false, errors: [] };
+					window.addEventListener('error', function(e) {
+						window.__reclaimUserScriptResult.errors.push(String(e.message));
+					});
+					try {
+						(new Function(${JSON.stringify(script)}))();
+						window.__reclaimUserScriptResult.ran = true;
+					} catch(e) {
+						window.__reclaimUserScriptResult.errors.push(
+							String((e && e.message) || e),
+						);
+					}
+				`
+				const installed = (await backend.sendCdp(
+					'Page.addScriptToEvaluateOnNewDocument', { source: wrapped },
+				)) as { identifier?: string }
+
+				if(typeof args.navigateUrl !== 'string') {
+					return {
+						installed: true,
+						note:
+							'Installed for the NEXT navigation only — it did not run on '
+							+ 'the current page, and stays installed (runs on every later '
+							+ 'navigation too) until a follow-up call with navigateUrl '
+							+ 'removes it. Navigate now (for example, with the navigate '
+							+ 'tool), then read window.__reclaimUserScriptResult via '
+							+ 'eval_in_page, or call '
+							+ 'test_user_script again with navigateUrl.',
+					}
+				}
+
+				try {
+					const timeoutMs = Number(args.timeoutMs) || 30_000
+					await backend.sendCdp('Page.enable')
+					const load = backend.waitForEvent('Page.loadEventFired', timeoutMs)
+					const nav = (await backend.sendCdp(
+						'Page.navigate', { url: String(args.navigateUrl) },
+					)) as { errorText?: string }
+					if(nav.errorText) {
+						return { installed: true, navigated: false, error: nav.errorText }
+					}
+
+					await load
+					const { value, error } = await evalInPage(
+						backend, 'window.__reclaimUserScriptResult',
+					)
+					if(error) {
+						return { installed: true, navigated: true, error }
+					}
+
+					const result =
+						value as { ran?: boolean, errors?: string[] } | undefined
+					return {
+						installed: true,
+						navigated: true,
+						ran: result?.ran ?? false,
+						errors: result?.errors ?? [],
+					}
+				} finally {
+					// One-shot test: remove it so it doesn't keep running (and
+					// potentially redirecting the tab) on every later navigation.
+					if(installed.identifier) {
+						await backend.sendCdp(
+							'Page.removeScriptToEvaluateOnNewDocument',
+							{ identifier: installed.identifier },
+						)
+					}
+				}
+			},
+		),
 		defineTool<Record<string, unknown>>(
 			{
 				name: 'get_cookies',
@@ -186,7 +298,8 @@ export function authoringTools(
 					'List the NAMES of cookies currently set for the page (values are '
 					+ 'NEVER returned). The most reliable, language- and DOM-independent '
 					+ 'login signal: after the user logs in, an auth/session cookie '
-					+ 'appears (e.g. session/sid/token/auth/jwt/_user/logged_in). '
+					+ 'appears (for example, session, sid, token, auth, jwt, _user, '
+					+ 'logged_in). '
 					+ 'Includes httpOnly cookies the page JS cannot see.',
 				inputSchema: objectSchema({}),
 			},
@@ -242,8 +355,8 @@ export function authoringTools(
 					'userFirstVisit', 'cf_', '_dd_', 'bcookie', 'bscookie', 'lidc',
 				].join('|') + ')', 'i')
 				// A real session/auth cookie name. Deliberately NOT bare `token` — a
-				// challenge/CSRF token (e.g. LinkedIn `chp_token`) contains it and is
-				// set BEFORE auth completes. Any new httpOnly cookie is also a
+				// challenge/CSRF token (for example, LinkedIn `chp_token`) contains it
+				// and is set BEFORE auth completes. Any new httpOnly cookie is also a
 				// candidate (server-set session cookies are usually httpOnly).
 				const SESSION = /sess|sid|jwt|_session|auth|logged.?in|remember|li_at/i
 				// Auth/challenge URL paths — while the page is still on one, login is
@@ -321,7 +434,13 @@ export function authoringTools(
 				name: 'run_proof',
 				description:
 					'Prove the drafted recipe (zkTLS). Only call after replay_request '
-					+ 'looks right. Returns the proof result.',
+					+ 'looks right. Returns the proof result. NOTE: unlike '
+					+ 'replay_request (which re-issues from inside the live attached '
+					+ 'browser tab), the ATTESTOR calls the target from its OWN '
+					+ 'network/IP, separate from the browser\'s. A request that '
+					+ 'replayed fine can still fail here for geo/IP-bound content '
+					+ '(country-locked pages, IP-allowlisted APIs) — if that happens, '
+					+ 'it\'s a property of the site, not a bug in the draft.',
 				inputSchema: objectSchema({ draftId: { type: 'string' } }, ['draftId']),
 			},
 			// The backend shapes its own result: the cloud returns a lean,

package/src/cdp/capture-engine.ts

@@ -89,9 +89,10 @@ export function isStaticAsset(url: string): boolean {
 }
 
 /** Response Content-Types for static assets. The URL-extension filter misses
- *  extension-less bundler/CDN URLs (e.g. `/assets/3b8f1c`), so we also drop by
- *  MIME at response time. `text/html`, `application/json`, and `text/plain`
- *  are NOT here — those are the document/API shapes recipes match. */
+ *  extension-less bundler/CDN URLs (for example, `/assets/3b8f1c`), so we also
+ *  drop by MIME at response time. `text/html`, `application/json`, and
+ *  `text/plain` are NOT here — those are the document/API shapes recipes
+ *  match. */
 const STATIC_ASSET_MIME_EXACT = new Set([
 	'text/css',
 	'application/javascript', 'text/javascript', 'application/x-javascript',
@@ -272,9 +273,9 @@ export function createCaptureEngine(opts: CaptureEngineOptions): CaptureEngine {
 	function onResponseReceived(p: ResponseReceivedLike) {
 		const f = inFlight.get(p.requestId)
 		if(!f) {
-			// No in-flight entry → the request was skipped (e.g. a static asset)
-			// or never seen. Discard any buffered response extra-info so a skipped
-			// asset can't leave a dangling entry.
+			// No in-flight entry → the request was skipped (for example, a static
+			// asset) or never seen. Discard any buffered response extra-info so a
+			// skipped asset can't leave a dangling entry.
 			pendingResponseExtra.delete(p.requestId)
 			return
 		}
@@ -339,7 +340,7 @@ export function createCaptureEngine(opts: CaptureEngineOptions): CaptureEngine {
 			r.finishedAt = Date.now()
 		} catch{
 			// Body might be unavailable for
-			// some content-types (e.g. websocket). Skip.
+			// some content-types (for example, websocket). Skip.
 		}
 	}
 }

package/src/cdp/client.ts

@@ -30,6 +30,14 @@ interface CdpTabEventMap {
 		headers: Record<string, string>
 	}
 	'Network.loadingFinished': { requestId: string }
+	/** Screencast frames, for the live view (`live/viewer.ts`). Each carries a
+	 *  `sessionId` that MUST be acked with `Page.screencastFrameAck`, or CDP
+	 *  stops sending. */
+	'Page.screencastFrame': {
+		data: string
+		sessionId: number
+		metadata?: { timestamp?: number }
+	}
 }
 
 export interface CdpTabClient {

package/src/cdp/geo.ts

@@ -0,0 +1,52 @@
+/**
+ * Country-code suggestion for a country-routed Popcorn browser session, when
+ * the caller doesn't name one explicitly. `attach_browser` returns this as the
+ * suggestion to confirm with the developer — the calling machine's own
+ * public-IP country, resolved the same way reclaim-portal's `ip-geolocation`
+ * util does.
+ */
+import { LOGGER } from '../logger.ts'
+
+export interface IpGeolocation {
+	countryCode: string
+	country?: string
+	region?: string
+	city?: string
+}
+
+const IPINFO_URL = 'https://ipinfo.io/json'
+const FALLBACK_COUNTRY_CODE = 'US'
+
+/** Resolve the calling machine's own public-IP country. Never throws — a
+ *  lookup failure just loses the "best guess" convenience, falling back to
+ *  {@link FALLBACK_COUNTRY_CODE} rather than blocking applying a proxy. */
+export async function suggestCountryFromIp(
+	fetchImpl: typeof fetch = fetch,
+): Promise<IpGeolocation> {
+	try {
+		const res = await fetchImpl(IPINFO_URL)
+		if(!res.ok) {
+			throw new Error(`ipinfo.io ${res.status}`)
+		}
+
+		const data = await res.json() as {
+			country?: string
+			region?: string
+			city?: string
+		}
+		const countryCode = data.country?.toUpperCase()
+		if(!countryCode) {
+			throw new Error('ipinfo.io response had no country')
+		}
+
+		return {
+			countryCode,
+			country: data.country,
+			region: data.region,
+			city: data.city,
+		}
+	} catch(err) {
+		LOGGER.warn({ err }, 'suggestCountryFromIp failed; using fallback')
+		return { countryCode: FALLBACK_COUNTRY_CODE }
+	}
+}

package/src/cdp/index.ts

@@ -4,3 +4,4 @@
 export * from './capture-engine.ts'
 export { startCapture } from './capture.ts'
 export { BodyStore } from './eviction.ts'
+export * from './geo.ts'

package/src/consts.ts

@@ -224,3 +224,4 @@ export function oldEthUid(): string | undefined {
 export function oldLoginUrl(): string | undefined {
 	return process.env.RECLAIM_OLD_LOGIN_URL
 }
+