fix(recording): using unified geometry

This commit is contained in:
Ljy-0827
2026-08-23 21:26:40 +08:00
committed by GitHub
parent 21476c3884
commit 87cdcfe5ca
35 changed files with 1952 additions and 2087 deletions
@@ -0,0 +1,134 @@
import type { CdpTarget } from "@/browser-driver/frame-graph";
import { type CdpRunner, sendToCdpTarget } from "@/tools/shared";
const SETTLE_MIN_MS = 150;
const SETTLE_QUIET_MS = 250;
const SETTLE_MAX_MS = 2_000;
const SETTLE_POLL_MS = 60;
const SETTLE_WORLD_NAME = "__bsk_record_settle__";
const QUIET_PROBE = `(() => {
const scope = window;
let probe = scope.__bskRecordQuiet;
if (!probe) {
probe = { changedAt: Date.now() };
const observer = new MutationObserver(() => {
probe.changedAt = Date.now();
});
observer.observe(document.documentElement, {
subtree: true,
childList: true,
attributes: true,
characterData: true,
});
scope.__bskRecordQuiet = probe;
}
return { idleMs: Date.now() - probe.changedAt, readyState: document.readyState };
})()`;
export interface DocumentSettleScope {
target: CdpTarget;
/** Omit only for the target's root document. */
frameId?: string;
}
type SettleOutcome = "quiet" | "timeout" | "cancelled";
interface QuietProbe {
idleMs: number;
readyState: string;
}
interface ProbeContext {
executionContextId?: number;
}
function sleep(ms: number, signal?: AbortSignal): Promise<void> {
return new Promise((resolve) => {
if (signal?.aborted) return resolve();
const timer = setTimeout(resolve, ms);
signal?.addEventListener(
"abort",
() => {
clearTimeout(timer);
resolve();
},
{ once: true },
);
});
}
async function executionContextForScope(
cdp: CdpRunner,
scope: DocumentSettleScope,
): Promise<number | undefined> {
if (!scope.frameId) return undefined;
const result = await sendToCdpTarget<{ executionContextId?: number }>(
cdp,
scope.target,
"Page.createIsolatedWorld",
{
frameId: scope.frameId,
worldName: SETTLE_WORLD_NAME,
grantUniveralAccess: false,
},
);
return result.executionContextId;
}
async function readQuietProbe(
cdp: CdpRunner,
scope: DocumentSettleScope,
context: ProbeContext,
): Promise<QuietProbe | null> {
try {
if (scope.frameId && context.executionContextId === undefined) {
context.executionContextId = await executionContextForScope(cdp, scope);
if (context.executionContextId === undefined) return null;
}
const reply = await sendToCdpTarget<{ result?: { value?: unknown } }>(
cdp,
scope.target,
"Runtime.evaluate",
{
expression: QUIET_PROBE,
returnByValue: true,
...(context.executionContextId !== undefined
? { contextId: context.executionContextId }
: {}),
},
);
const value = reply.result?.value;
if (!value || typeof value !== "object") return null;
const { idleMs, readyState } = value as { idleMs?: unknown; readyState?: unknown };
if (typeof idleMs !== "number" || typeof readyState !== "string") return null;
return { idleMs, readyState };
} catch {
context.executionContextId = undefined;
return null;
}
}
export async function waitForDocumentSettled(
cdp: CdpRunner,
scope: DocumentSettleScope,
options: { signal?: AbortSignal } = {},
): Promise<SettleOutcome> {
const startedAt = Date.now();
const floor = startedAt + SETTLE_MIN_MS;
const deadline = startedAt + SETTLE_MAX_MS;
const context: ProbeContext = {};
for (;;) {
if (options.signal?.aborted) return "cancelled";
await sleep(SETTLE_POLL_MS, options.signal);
if (options.signal?.aborted) return "cancelled";
const probe = await readQuietProbe(cdp, scope, context);
const now = Date.now();
if (now < floor) continue;
if (now >= deadline) return "timeout";
if (!probe || probe.readyState === "loading") continue;
if (probe.idleMs >= SETTLE_QUIET_MS) return "quiet";
}
}
@@ -0,0 +1,34 @@
import type { RecordingDraftStep } from "./types";
const CLIPBOARD_KEYS = new Set(["a", "c", "v", "x", "A", "C", "V", "X"]);
const MODIFIER_ONLY_KEYS = new Set(["Meta", "Control", "Alt", "Shift", "OS", "Hyper", "Super"]);
export function shouldRecordPress(
key: string,
modifiers?: Array<"alt" | "ctrl" | "meta" | "shift">,
): boolean {
if (MODIFIER_ONLY_KEYS.has(key)) return false;
const mods = modifiers ?? [];
const hasCtrlOrMeta = mods.includes("ctrl") || mods.includes("meta");
if (hasCtrlOrMeta && CLIPBOARD_KEYS.has(key)) return false;
if (key === "Enter" || key === "Escape") return true;
if (key.length === 1 && !hasCtrlOrMeta && !mods.includes("alt")) return false;
return false;
}
export function shouldIncludeDraft(step: RecordingDraftStep): boolean {
return step.op !== "press" || shouldRecordPress(step.key, step.modifiers);
}
export function resolveDraftStartUrl(
drafts: RecordingDraftStep[],
explicitStartUrl?: string,
fallbackUrl?: string,
): string {
if (explicitStartUrl) return explicitStartUrl;
const navigation = drafts.find(
(step): step is Extract<RecordingDraftStep, { op: "navigate" }> => step.op === "navigate",
);
if (navigation) return navigation.url;
return drafts.find((step) => step.pageUrl)?.pageUrl ?? fallbackUrl ?? "about:blank";
}
@@ -0,0 +1,115 @@
import type { RenderedRef } from "@browser-skill/vom";
import { captureVomObservation } from "@/tools/capture-vom-observation";
import type { CdpRunner, ChromeTabsApi } from "@/tools/shared";
import type { CapturedNode } from "@/tools/vom/capture";
export interface IndexedObservationNode {
frameId: string;
node: CapturedNode;
ref?: RenderedRef;
}
export interface CapturedRecordingObservation {
rootFrameId: string;
index: ObservationNodeIndex;
url: string;
title?: string;
vomText: string;
truncated: boolean;
}
export interface RegisteredObservation {
stateId: string;
rootFrameId: string;
index: ObservationNodeIndex;
url: string;
}
function nodeKey(frameId: string, backendNodeId: number): string {
return `${frameId}:${backendNodeId}`;
}
function frameTagKey(frameId: string, tag: string): string {
return `${frameId}:${tag.toLowerCase()}`;
}
export class ObservationNodeIndex {
readonly #nodesByFrameTag = new Map<string, IndexedObservationNode[]>();
readonly #refById = new Map<string, RenderedRef>();
readonly #refsByFrame = new Map<string, RenderedRef[]>();
constructor(input: {
rootFrameId: string;
frameDocuments: Array<{ frameId: string; domNodes: CapturedNode[] }>;
refs: RenderedRef[];
}) {
const refByNode = new Map<string, RenderedRef>();
for (const ref of input.refs) {
const frameId = ref.frameId ?? input.rootFrameId;
refByNode.set(nodeKey(frameId, ref.backendNodeId), ref);
this.#refById.set(ref.ref, ref);
const frameRefs = this.#refsByFrame.get(frameId) ?? [];
frameRefs.push(ref);
this.#refsByFrame.set(frameId, frameRefs);
}
for (const document of input.frameDocuments) {
for (const node of document.domNodes) {
const frameId = node.frameId ?? document.frameId;
const entry = { frameId, node, ref: refByNode.get(nodeKey(frameId, node.backendNodeId)) };
const key = frameTagKey(frameId, node.tag);
const bucket = this.#nodesByFrameTag.get(key) ?? [];
bucket.push(entry);
this.#nodesByFrameTag.set(key, bucket);
}
}
}
candidates(frameId: string, tag: string): readonly IndexedObservationNode[] {
return this.#nodesByFrameTag.get(frameTagKey(frameId, tag)) ?? [];
}
ref(refId: string): RenderedRef | undefined {
return this.#refById.get(refId);
}
refs(frameId: string): readonly RenderedRef[] {
return this.#refsByFrame.get(frameId) ?? [];
}
}
async function readTabMeta(
tabsApi: ChromeTabsApi,
tabId: number,
): Promise<{ url: string; title?: string }> {
try {
const tab = await tabsApi.get(tabId);
return { url: tab.url ?? "about:blank", title: tab.title };
} catch {
return { url: "about:blank" };
}
}
export async function captureRecordingObservation(input: {
cdp: CdpRunner;
tabsApi: ChromeTabsApi;
tabId: number;
maxTokens: number;
redactValues: boolean;
signal?: AbortSignal;
}): Promise<CapturedRecordingObservation> {
const { url, title } = await readTabMeta(input.tabsApi, input.tabId);
const captured = await captureVomObservation(input.cdp, input.tabId, url, {
maxTokens: input.maxTokens,
redactValues: input.redactValues,
conditionalSurfaceProbe: false,
signal: input.signal,
});
return {
rootFrameId: captured.rootFrameId,
index: new ObservationNodeIndex(captured),
url,
title,
vomText: captured.text,
truncated: captured.truncated,
};
}
@@ -0,0 +1,122 @@
import type { CdpRunner, ChromeTabsApi } from "@/tools/shared";
import { captureRecordingObservation, type RegisteredObservation } from "./observation-capture";
import { RecordingStateRegistry } from "./state-registry";
import { matchObservationTarget, unmatchedTarget } from "./target-matcher";
import type { RecordingDraftStep, StepAnnotation, TargetedRecordingDraft } from "./types";
const DEFAULT_MAX_PAGE_TOKENS = 3_000;
const MIN_CAPTURE_INTERVAL_MS = 200;
export interface TabObservationCursor {
lastSettled: RegisteredObservation | null;
lastCaptureAt: number;
}
function abortableDelay(ms: number, signal?: AbortSignal): Promise<void> {
return new Promise((resolve) => {
if (signal?.aborted) return resolve();
const timer = setTimeout(resolve, ms);
signal?.addEventListener(
"abort",
() => {
clearTimeout(timer);
resolve();
},
{ once: true },
);
});
}
function isTargeted(draft: RecordingDraftStep): draft is TargetedRecordingDraft {
return draft.op !== "navigate" && draft.op !== "scroll";
}
export class RecordingObservationSession {
readonly registry: RecordingStateRegistry;
readonly cursor: TabObservationCursor;
readonly annotations: StepAnnotation[];
readonly #maxTokens: number;
readonly #redactValues: boolean;
constructor(
options: {
registry?: RecordingStateRegistry;
cursor?: TabObservationCursor;
annotations?: StepAnnotation[];
maxTokens?: number;
redactValues?: boolean;
} = {},
) {
this.registry = options.registry ?? new RecordingStateRegistry();
this.cursor = options.cursor ?? { lastSettled: null, lastCaptureAt: 0 };
this.annotations = options.annotations ?? [];
this.#maxTokens = options.maxTokens ?? DEFAULT_MAX_PAGE_TOKENS;
this.#redactValues = options.redactValues ?? false;
}
async capture(
cdp: CdpRunner,
tabsApi: ChromeTabsApi,
tabId: number,
signal?: AbortSignal,
): Promise<RegisteredObservation> {
const waitMs = Math.max(0, MIN_CAPTURE_INTERVAL_MS - (Date.now() - this.cursor.lastCaptureAt));
if (waitMs > 0) await abortableDelay(waitMs, signal);
if (signal?.aborted) throw new DOMException("observation aborted", "AbortError");
const captured = await captureRecordingObservation({
cdp,
tabsApi,
tabId,
maxTokens: this.#maxTokens,
redactValues: this.#redactValues,
signal,
});
const state = this.registry.register({
url: captured.url,
title: captured.title,
rawVomText: captured.vomText,
truncated: captured.truncated,
});
const observation: RegisteredObservation = {
stateId: state.id,
rootFrameId: captured.rootFrameId,
index: captured.index,
url: captured.url,
};
this.cursor.lastSettled = observation;
this.cursor.lastCaptureAt = Date.now();
return observation;
}
bindDraft(draft: RecordingDraftStep, draftId: number, previousActionPending = false): void {
const observation = this.cursor.lastSettled;
if (isTargeted(draft)) {
draft.matchedTarget = observation
? matchObservationTarget({
observation,
hint: draft.targetHint,
fallback: draft.captureTarget,
})
: unmatchedTarget(draft.captureTarget);
}
if (!observation) return;
const unmatched = isTargeted(draft) && draft.matchedTarget?.unmatched === true;
if (previousActionPending && unmatched) return;
draft.preStateId = observation.stateId;
this.registry.markStep(observation.stateId, draftId);
if (!isTargeted(draft) || !draft.matchedTarget?.ref) return;
const ref = observation.index.ref(draft.matchedTarget.ref);
if (!ref) return;
this.annotations.push({
draftId,
op: draft.op,
line: ref.line,
stateId: observation.stateId,
...(draft.op === "fill" && !this.#redactValues
? { detail: JSON.stringify(draft.value) }
: {}),
});
}
}
@@ -0,0 +1,232 @@
import type { CdpRunner, ChromeTabsApi } from "@/tools/shared";
import { type DocumentSettleScope, waitForDocumentSettled } from "./document-settle";
import { RecordingObservationSession } from "./observation-session";
import type { RecordingDraftStep } from "./types";
interface PendingSettle {
abort: AbortController;
scope: DocumentSettleScope;
}
interface PendingRedirect {
url: string;
abort: AbortController;
}
const CAPTURE_RETRY_DELAY_MS = 250;
function delay(ms: number, signal?: AbortSignal): Promise<void> {
return new Promise((resolve) => {
if (signal?.aborted) return resolve();
const timer = setTimeout(resolve, ms);
signal?.addEventListener(
"abort",
() => {
clearTimeout(timer);
resolve();
},
{ once: true },
);
});
}
function isAbortError(error: unknown): boolean {
return (
typeof error === "object" &&
error !== null &&
(error as { name?: string }).name === "AbortError"
);
}
export function inferMissingPostStates(drafts: RecordingDraftStep[]): void {
for (let index = 0; index < drafts.length - 1; index += 1) {
const draft = drafts[index];
const next = drafts[index + 1];
if (draft && next && !draft.postStateId && next.preStateId) {
draft.postStateId = next.preStateId;
}
}
}
export class SettleController {
readonly #session: RecordingObservationSession;
readonly #cdp: CdpRunner;
readonly #tabsApi: ChromeTabsApi;
readonly #tabId: number;
readonly #rootScope: DocumentSettleScope;
readonly #pending = new Map<number, PendingSettle>();
#queue = Promise.resolve();
#pendingRedirect: PendingRedirect | null = null;
#redirectQueue = Promise.resolve();
constructor(input: {
session: RecordingObservationSession;
cdp: CdpRunner;
tabsApi: ChromeTabsApi;
tabId: number;
}) {
this.#session = input.session;
this.#cdp = input.cdp;
this.#tabsApi = input.tabsApi;
this.#tabId = input.tabId;
this.#rootScope = { target: { tabId: input.tabId } };
}
get hasPending(): boolean {
return this.#pending.size > 0 || this.#pendingRedirect !== null;
}
async #captureWithRetry(signal?: AbortSignal) {
try {
return await this.#session.capture(this.#cdp, this.#tabsApi, this.#tabId, signal);
} catch (error) {
if (signal?.aborted) throw error;
await delay(CAPTURE_RETRY_DELAY_MS, signal);
return this.#session.capture(this.#cdp, this.#tabsApi, this.#tabId, signal);
}
}
schedule(
drafts: RecordingDraftStep[],
draftIndex: number,
scope: DocumentSettleScope = this.#rootScope,
): void {
if (scope.target.tabId !== this.#tabId) {
throw new Error(
`settle scope tab ${scope.target.tabId} does not belong to tab ${this.#tabId}`,
);
}
const landing = drafts[draftIndex]?.preStateId;
for (const [index, pending] of this.#pending) {
if (index >= draftIndex) continue;
pending.abort.abort();
this.#pending.delete(index);
if (landing && drafts[index] && !drafts[index].postStateId) {
drafts[index].postStateId = landing;
}
}
this.#pending.get(draftIndex)?.abort.abort();
const pending = { abort: new AbortController(), scope };
this.#pending.set(draftIndex, pending);
const task = async () => {
if (pending.abort.signal.aborted) return;
try {
const outcome = await waitForDocumentSettled(this.#cdp, pending.scope, {
signal: pending.abort.signal,
});
if (outcome === "cancelled") return;
const observation = await this.#captureWithRetry(pending.abort.signal);
if (!pending.abort.signal.aborted && drafts[draftIndex]) {
drafts[draftIndex].postStateId = observation.stateId;
}
} catch (error) {
if (!isAbortError(error)) {
console.warn(
`[bsk record] post-action observation failed for step ${draftIndex + 1}`,
error,
);
}
} finally {
if (this.#pending.get(draftIndex) === pending) this.#pending.delete(draftIndex);
}
};
this.#queue = this.#queue.then(task, task).catch(() => {});
}
cancel(): void {
for (const pending of this.#pending.values()) pending.abort.abort();
this.#pending.clear();
this.clearRedirect();
}
async flush(): Promise<void> {
for (let round = 0; round < 10; round += 1) {
const current = this.#queue;
await current;
if (current === this.#queue) return;
}
console.warn("[bsk record] settle queue kept growing; using completed observations");
}
async settleTrailing(drafts: RecordingDraftStep[]): Promise<void> {
const trailing: RecordingDraftStep[] = [];
for (let index = drafts.length - 1; index >= 0; index -= 1) {
const draft = drafts[index];
if (!draft || draft.postStateId) break;
trailing.push(draft);
}
if (trailing.length === 0) return;
try {
const observation = await this.#captureWithRetry();
for (const draft of trailing) draft.postStateId = observation.stateId;
} catch (error) {
console.warn("[bsk record] final observation at stop failed", error);
}
}
clearRedirect(): void {
this.#pendingRedirect?.abort.abort();
this.#pendingRedirect = null;
}
scheduleRedirect(drafts: RecordingDraftStep[], url: string): void {
this.#pendingRedirect?.abort.abort();
const pending: PendingRedirect = { url, abort: new AbortController() };
this.#pendingRedirect = pending;
const task = () => this.#settleRedirect(drafts, pending);
this.#redirectQueue = this.#redirectQueue.then(task, task).catch(() => {});
}
async #settleRedirect(drafts: RecordingDraftStep[], pending: PendingRedirect): Promise<void> {
const outcome = await waitForDocumentSettled(this.#cdp, this.#rootScope, {
signal: pending.abort.signal,
});
if (outcome === "cancelled" || this.#pendingRedirect !== pending) return;
let finalUrl = pending.url;
try {
finalUrl = (await this.#tabsApi.get(this.#tabId)).url || finalUrl;
} catch {
// The navigation event URL remains the best available destination.
}
if (this.#pendingRedirect !== pending) return;
this.#pendingRedirect = null;
if (
!finalUrl ||
finalUrl === "about:blank" ||
this.#session.cursor.lastSettled?.url === finalUrl
) {
return;
}
const last = drafts[drafts.length - 1];
if (last?.op === "navigate" && last.url === finalUrl) {
if (!last.postStateId) this.schedule(drafts, drafts.length - 1);
await this.flush();
return;
}
const draft: RecordingDraftStep = {
op: "navigate",
url: finalUrl,
pageUrl: finalUrl,
cause: "browser",
preStateId: this.#session.cursor.lastSettled?.stateId,
};
drafts.push(draft);
const draftIndex = drafts.length - 1;
if (draft.preStateId) this.#session.registry.markStep(draft.preStateId, draftIndex + 1);
this.schedule(drafts, draftIndex);
await this.flush();
}
async flushRedirects(): Promise<void> {
for (let round = 0; round < 10; round += 1) {
const current = this.#redirectQueue;
await current;
if (current === this.#redirectQueue) return;
}
console.warn("[bsk record] redirect queue kept growing; using the final completed landing");
}
}
@@ -0,0 +1,56 @@
export interface RecordedStateEntry {
id: string;
url: string;
title?: string;
rawVomText: string;
truncated: boolean;
stepsHere: number[];
}
function stateIdentity(url: string, body: string): string {
return `${url}\0${body}`;
}
export class RecordingStateRegistry {
readonly #entriesById = new Map<string, RecordedStateEntry>();
readonly #idByIdentity = new Map<string, string>();
#nextId = 1;
register(input: {
url: string;
title?: string;
rawVomText: string;
truncated?: boolean;
}): RecordedStateEntry {
const identity = stateIdentity(input.url, input.rawVomText);
const existingId = this.#idByIdentity.get(identity);
if (existingId) {
const existing = this.#entriesById.get(existingId)!;
if (!existing.title && input.title) existing.title = input.title;
if (input.truncated) existing.truncated = true;
return existing;
}
const entry: RecordedStateEntry = {
id: `s${this.#nextId}`,
url: input.url,
...(input.title ? { title: input.title } : {}),
rawVomText: input.rawVomText,
truncated: input.truncated ?? false,
stepsHere: [],
};
this.#nextId += 1;
this.#entriesById.set(entry.id, entry);
this.#idByIdentity.set(identity, entry.id);
return entry;
}
values(): RecordedStateEntry[] {
return [...this.#entriesById.values()];
}
markStep(stateId: string, draftId: number): void {
const entry = this.#entriesById.get(stateId);
if (entry && !entry.stepsHere.includes(draftId)) entry.stepsHere.push(draftId);
}
}
@@ -0,0 +1,136 @@
import type { RecordStepPayload } from "../record-bridge";
import type { RecordingDraftStep } from "./types";
export interface RecordingStepBuffer {
steps: RecordingDraftStep[];
currentUrl?: string;
pendingNavigation: boolean;
pendingNavigationDeadline?: number;
}
const NAVIGATION_TRIGGER_WINDOW_MS = 3_000;
function toDraftStep(payload: RecordStepPayload): RecordingDraftStep | null {
const pageUrl = payload.page_url;
switch (payload.op) {
case "click":
return payload.target
? {
op: "click",
captureTarget: payload.target,
...(pageUrl ? { pageUrl } : {}),
}
: null;
case "hover":
return payload.target
? {
op: "hover",
captureTarget: payload.target,
...(pageUrl ? { pageUrl } : {}),
}
: null;
case "fill":
return payload.target
? {
op: "fill",
captureTarget: payload.target,
value: payload.value ?? "",
...(payload.redacted ? { redacted: true } : {}),
...(pageUrl ? { pageUrl } : {}),
}
: null;
case "press":
return payload.key
? {
op: "press",
key: payload.key,
...(payload.target ? { captureTarget: payload.target } : {}),
...(payload.modifiers?.length ? { modifiers: payload.modifiers } : {}),
...(pageUrl ? { pageUrl } : {}),
}
: null;
case "select":
return payload.target && payload.values
? {
op: "select",
captureTarget: payload.target,
values: payload.values,
...(payload.labels?.length ? { labels: payload.labels } : {}),
...(pageUrl ? { pageUrl } : {}),
}
: null;
case "navigate":
return null;
}
}
function annotateLastStepNavigation(buffer: RecordingStepBuffer, url: string): boolean {
for (let i = buffer.steps.length - 1; i >= 0; i -= 1) {
const step = buffer.steps[i];
if (!step) continue;
if (step.op === "click" || step.op === "press" || step.op === "select") {
buffer.steps[i] = { ...step, navigatedTo: url };
return true;
}
break;
}
return false;
}
export function observeRecordedNavigation(
buffer: RecordingStepBuffer,
url: string,
causedByAction?: boolean,
): void {
if (!url || url === buffer.currentUrl) return;
buffer.currentUrl = url;
const pendingIsCurrent =
buffer.pendingNavigation &&
(buffer.pendingNavigationDeadline === undefined ||
buffer.pendingNavigationDeadline >= Date.now());
if (causedByAction === true || (causedByAction === undefined && pendingIsCurrent)) {
buffer.pendingNavigation = false;
buffer.pendingNavigationDeadline = undefined;
if (!annotateLastStepNavigation(buffer, url)) {
buffer.steps.push({
op: "navigate",
url,
pageUrl: url,
});
}
return;
}
buffer.pendingNavigation = false;
buffer.pendingNavigationDeadline = undefined;
buffer.steps.push({
op: "navigate",
url,
pageUrl: url,
});
}
export function appendRecordedPayload(
buffer: RecordingStepBuffer,
payload: RecordStepPayload,
): void {
if (payload.op === "navigate") {
if (payload.url) {
observeRecordedNavigation(buffer, payload.url, payload.navigation_caused_by_action);
}
return;
}
const step = toDraftStep({
...payload,
page_url: payload.page_url ?? buffer.currentUrl,
});
if (!step) return;
buffer.steps.push(step);
if (step.op === "click" || step.op === "press" || step.op === "select" || step.op === "fill") {
buffer.pendingNavigation = payload.expects_navigation === true;
buffer.pendingNavigationDeadline = buffer.pendingNavigation
? Date.now() + NAVIGATION_TRIGGER_WINDOW_MS
: undefined;
}
}
@@ -0,0 +1,76 @@
import type { RenderedRef } from "@browser-skill/vom";
import type { TargetDescriptorV3 } from "@/transport/types";
import type { CaptureTargetDescriptor } from "../describe-target";
import type { IndexedObservationNode, RegisteredObservation } from "./observation-capture";
import type { TargetGeometry, TargetMatchHint } from "./types";
const MATCH_TOLERANCE_PX = 2;
function close(a: number, b: number): boolean {
return Math.abs(a - b) <= MATCH_TOLERANCE_PX;
}
function rectMatches(a: TargetGeometry["rect"], b: TargetGeometry["rect"]): boolean {
return close(a.x, b.x) && close(a.y, b.y) && close(a.w, b.w) && close(a.h, b.h);
}
function candidateMatches(candidate: IndexedObservationNode, geometry: TargetGeometry): boolean {
return candidate.node.rect !== null && rectMatches(geometry.rect, candidate.node.rect);
}
export function unmatchedTarget(fallback?: CaptureTargetDescriptor): TargetDescriptorV3 {
return {
...(fallback?.role ? { role: fallback.role } : {}),
...(fallback?.name ? { name: fallback.name } : {}),
unmatched: true,
};
}
function normalized(value: string | undefined): string {
return value?.replace(/\s+/g, " ").trim().toLowerCase() ?? "";
}
function matchesSemantics(ref: RenderedRef, fallback?: CaptureTargetDescriptor): boolean {
const role = normalized(fallback?.role);
const name = normalized(fallback?.name);
if (!role && !name) return false;
if (role && normalized(ref.role) !== role) return false;
if (name && normalized(ref.name) !== name) return false;
return true;
}
function descriptor(ref: RenderedRef): TargetDescriptorV3 {
return {
ref: ref.ref,
...(ref.role ? { role: ref.role } : {}),
...(ref.name ? { name: ref.name } : {}),
...(ref.ctx ? { ctx: ref.ctx } : {}),
};
}
export function matchObservationTarget(input: {
observation: RegisteredObservation;
hint?: TargetMatchHint;
fallback?: CaptureTargetDescriptor;
}): TargetDescriptorV3 {
const frameId = input.hint?.frameId ?? input.observation.rootFrameId;
const geometry = input.hint?.geometry;
if (geometry) {
const matches = input.observation.index
.candidates(frameId, geometry.tag)
.filter((candidate) => candidate.ref && candidateMatches(candidate, geometry));
if (matches.length === 1) return descriptor(matches[0]!.ref!);
const semanticMatches = matches.filter(
(candidate) => candidate.ref && matchesSemantics(candidate.ref, input.fallback),
);
if (semanticMatches.length === 1) return descriptor(semanticMatches[0]!.ref!);
return unmatchedTarget(input.fallback);
}
const semanticMatches = input.observation.index
.refs(frameId)
.filter((ref) => matchesSemantics(ref, input.fallback));
return semanticMatches.length === 1
? descriptor(semanticMatches[0]!)
: unmatchedTarget(input.fallback);
}
@@ -0,0 +1,87 @@
import {
type StepV3,
type StopReason,
TRACE_VERSION_V3,
type TraceStateV3,
type TraceV3,
VOM_FORMAT_VERSION,
} from "@/transport/types";
import { resolveDraftStartUrl } from "./draft-policy";
import type { RecordedStateEntry, RecordingStateRegistry } from "./state-registry";
import { reduceTraceStepsV3 } from "./trace-reducer-v3";
import { formatTraceStateBody } from "./trace-state-body";
import type { RecordingDraftStep, StepAnnotation } from "./types";
function publishedEntries(registry: RecordingStateRegistry, steps: StepV3[]): RecordedStateEntry[] {
const entries = registry.values();
if (steps.length === 0) return entries.slice(0, 1);
const referenced = new Set(steps.flatMap((step) => [step.state, step.result.state]));
return entries.filter((entry) => referenced.has(entry.id));
}
function remapDraftIds(draftIds: number[], stepIdByDraftId: Map<number, number>): number[] {
return [
...new Set(
draftIds.flatMap((id) => {
const stepId = stepIdByDraftId.get(id);
return stepId === undefined ? [] : [stepId];
}),
),
].sort((a, b) => a - b);
}
export function buildTraceV3(input: {
registry: RecordingStateRegistry;
drafts: RecordingDraftStep[];
annotations?: StepAnnotation[];
startedAt: string;
purpose?: string;
startUrl?: string;
stoppedBy: StopReason;
bskVersion: string;
}): TraceV3 {
const reduced = reduceTraceStepsV3(input.drafts);
const entries = publishedEntries(input.registry, reduced.steps);
const publishedId = new Map(entries.map((entry, index) => [entry.id, `s${index + 1}`]));
const annotationsByState = new Map<string, StepAnnotation[]>();
for (const annotation of input.annotations ?? []) {
const bucket = annotationsByState.get(annotation.stateId) ?? [];
bucket.push(annotation);
annotationsByState.set(annotation.stateId, bucket);
}
const steps = reduced.steps.map((step) => ({
...step,
state: publishedId.get(step.state) ?? step.state,
result: { state: publishedId.get(step.result.state) ?? step.result.state },
}));
const states: TraceStateV3[] = entries.map((entry) => {
const id = publishedId.get(entry.id) ?? entry.id;
return {
id,
url: entry.url,
...(entry.title ? { title: entry.title } : {}),
body: formatTraceStateBody({
stateId: id,
url: entry.url,
title: entry.title,
stepIds: remapDraftIds(entry.stepsHere, reduced.stepIdByDraftId),
vomText: entry.rawVomText,
annotations: annotationsByState.get(entry.id) ?? [],
stepIdByDraftId: reduced.stepIdByDraftId,
}),
...(entry.truncated ? { truncated: true } : {}),
};
});
return {
version: TRACE_VERSION_V3,
...(input.purpose ? { purpose: input.purpose } : {}),
recorded_at: new Date().toISOString(),
started_at: input.startedAt,
stopped_by: input.stoppedBy,
entry: { start_url: resolveDraftStartUrl(input.drafts, input.startUrl, states[0]?.url) },
recorder: { bsk: input.bskVersion, vom: VOM_FORMAT_VERSION },
states,
steps,
};
}
@@ -0,0 +1,219 @@
import type { PageRefV2, SelectedOptionV2, StepV2, TraceV2 } from "@/transport/types";
import { resolveDraftStartUrl, shouldIncludeDraft } from "./draft-policy";
import type { RecordingDraftStep } from "./types";
/** Collapse consecutive navigations to the last hop. */
function collapseNavigations(steps: RecordingDraftStep[]): RecordingDraftStep[] {
const out: RecordingDraftStep[] = [];
for (const step of steps) {
const prev = out[out.length - 1];
if (step.op === "navigate" && prev?.op === "navigate") {
out[out.length - 1] = step;
continue;
}
out.push(step);
}
return out;
}
function collectUrls(steps: RecordingDraftStep[], startUrl?: string): string[] {
const urls: string[] = [];
if (startUrl) urls.push(startUrl);
for (const step of steps) {
if (step.op === "navigate") {
urls.push(step.url);
continue;
}
if (step.pageUrl) urls.push(step.pageUrl);
if ("navigatedTo" in step && step.navigatedTo) urls.push(step.navigatedTo);
}
const seen = new Set<string>();
const unique: string[] = [];
for (const url of urls) {
if (!url || seen.has(url)) continue;
seen.add(url);
unique.push(url);
}
return unique;
}
function buildPageRegistry(
steps: RecordingDraftStep[],
startUrl?: string,
): { pages: PageRefV2[]; urlToId: Map<string, string> } {
const urls = collectUrls(steps, startUrl);
const urlToId = new Map<string, string>();
const pages = urls.map((url, index) => {
const id = `p${index + 1}`;
urlToId.set(url, id);
return { id, url };
});
return { pages, urlToId };
}
function pageIdFor(
url: string | undefined,
urlToId: Map<string, string>,
fallbackUrl?: string,
): string {
if (url && urlToId.has(url)) return urlToId.get(url)!;
if (fallbackUrl && urlToId.has(fallbackUrl)) return urlToId.get(fallbackUrl)!;
return urlToId.values().next().value ?? "p1";
}
function pageUrlForDraft(step: RecordingDraftStep, fallbackUrl?: string): string | undefined {
if (step.op === "navigate") return step.pageUrl ?? step.url;
if (step.pageUrl) return step.pageUrl;
return fallbackUrl;
}
function effectForNavigation(
navigatedTo: string | undefined,
urlToId: Map<string, string>,
): StepV2["effect"] {
if (!navigatedTo) return undefined;
const pageId = urlToId.get(navigatedTo);
if (!pageId) return undefined;
return { navigated_to: pageId };
}
function withEffect(step: StepV2, effect: StepV2["effect"]): StepV2 {
if (!effect) return step;
return { ...step, effect };
}
function toSelection(values: string[], labels?: string[]): SelectedOptionV2[] {
return values.map((value, index) => ({
value,
...(labels?.[index] ? { label: labels[index] } : {}),
}));
}
function toV2Step(
step: RecordingDraftStep,
id: number,
urlToId: Map<string, string>,
fallbackUrl?: string,
): StepV2 | null {
if (!shouldIncludeDraft(step)) return null;
const pageUrl = pageUrlForDraft(step, fallbackUrl);
const page = pageIdFor(pageUrl, urlToId, fallbackUrl);
switch (step.op) {
case "navigate":
return {
op: "navigate",
id,
page: pageIdFor(step.url, urlToId, fallbackUrl),
to: step.url,
};
case "click":
if (!step.captureTarget) return null;
return withEffect(
{
op: "click",
id,
page,
target: step.captureTarget,
},
effectForNavigation(step.navigatedTo, urlToId),
);
case "hover":
if (!step.captureTarget) return null;
return {
op: "hover",
id,
page,
target: step.captureTarget,
};
case "fill":
if (!step.captureTarget) return null;
return {
op: "fill",
id,
page,
target: step.captureTarget,
value: step.value,
...(step.redacted ? { redacted: true } : {}),
};
case "press":
return withEffect(
{
op: "press",
id,
page,
key: step.key,
...(step.captureTarget ? { target: step.captureTarget } : {}),
...(step.modifiers?.length ? { modifiers: step.modifiers } : {}),
},
effectForNavigation(step.navigatedTo, urlToId),
);
case "select":
if (!step.captureTarget) return null;
return withEffect(
{
op: "select",
id,
page,
target: step.captureTarget,
selection: toSelection(step.values, step.labels),
},
effectForNavigation(step.navigatedTo, urlToId),
);
case "scroll":
return null;
}
}
interface ReducedTrace {
pages: PageRefV2[];
steps: StepV2[];
}
/**
* Compile capture drafts into record-only trace v2 steps.
* Variable inputs are NOT classified here — executing agents infer that at run time.
*/
function reduceTraceSteps(steps: RecordingDraftStep[], startUrl?: string): ReducedTrace {
const collapsed = collapseNavigations(steps);
const { pages, urlToId } = buildPageRegistry(collapsed, startUrl);
const out: StepV2[] = [];
let id = 1;
let lastUrl = startUrl;
for (const draft of collapsed) {
if (draft.op === "navigate") lastUrl = draft.url;
else if ("navigatedTo" in draft && draft.navigatedTo) lastUrl = draft.navigatedTo;
else if (draft.pageUrl) lastUrl = draft.pageUrl;
const step = toV2Step(draft, id, urlToId, lastUrl);
if (!step) continue;
out.push(step);
id += 1;
}
return { pages, steps: out };
}
function resolveTraceStartUrl(
drafts: RecordingDraftStep[],
startUrl?: string,
pages?: PageRefV2[],
): string {
return resolveDraftStartUrl(drafts, startUrl, pages?.[0]?.url);
}
export function buildTraceV2(input: {
steps: RecordingDraftStep[];
startedAt: string;
startUrl?: string;
purpose?: string;
}): TraceV2 {
const { pages, steps } = reduceTraceSteps(input.steps, input.startUrl);
return {
recorded_at: new Date().toISOString(),
started_at: input.startedAt,
...(input.purpose ? { purpose: input.purpose } : {}),
entry: { start_url: resolveTraceStartUrl(input.steps, input.startUrl, pages) },
pages,
steps,
};
}
@@ -0,0 +1,129 @@
import type { NavigationCause, StepV3 } from "@/transport/types";
import { shouldIncludeDraft } from "./draft-policy";
import { unmatchedTarget } from "./target-matcher";
import type { RecordingDraftStep } from "./types";
interface CollapsedDraft {
draft: RecordingDraftStep;
draftIds: number[];
}
const REDIRECT_QUALIFIERS = new Set(["client_redirect", "server_redirect"]);
const TRANSITION_CAUSES: Record<string, NavigationCause> = {
typed: "user_typed",
generated: "user_typed",
keyword: "user_typed",
keyword_generated: "user_typed",
link: "link",
form_submit: "form_submit",
reload: "reload",
auto_bookmark: "browser",
start_page: "browser",
};
function isRedirect(step: Extract<RecordingDraftStep, { op: "navigate" }>): boolean {
return (step.transitionQualifiers ?? []).some((qualifier) => REDIRECT_QUALIFIERS.has(qualifier));
}
function collapseRedirects(steps: RecordingDraftStep[]): CollapsedDraft[] {
const output: CollapsedDraft[] = [];
steps.forEach((step, index) => {
const previous = output[output.length - 1];
if (step.op === "navigate" && previous?.draft.op === "navigate" && isRedirect(step)) {
previous.draft = {
...previous.draft,
url: step.url,
postStateId: step.postStateId ?? previous.draft.postStateId,
};
previous.draftIds.push(index + 1);
return;
}
output.push({ draft: { ...step }, draftIds: [index + 1] });
});
return output;
}
function navigationCause(step: Extract<RecordingDraftStep, { op: "navigate" }>): NavigationCause {
if (step.cause) return step.cause;
const qualifiers = step.transitionQualifiers ?? [];
if (qualifiers.includes("forward_back")) return "history";
if (qualifiers.includes("from_address_bar")) return "user_typed";
return TRANSITION_CAUSES[step.transitionType ?? ""] ?? "browser";
}
function selection(values: string[], labels?: string[]): Array<{ value: string; label?: string }> {
return values.map((value, index) => ({
value,
...(labels?.[index] ? { label: labels[index] } : {}),
}));
}
function reduceDraft(draft: RecordingDraftStep, id: number): StepV3 | null {
if (!shouldIncludeDraft(draft)) return null;
const state = draft.preStateId ?? draft.postStateId;
const resultState = draft.postStateId ?? draft.preStateId;
if (!state || !resultState) return null;
const common = { id, state, result: { state: resultState } };
switch (draft.op) {
case "navigate":
return { op: "navigate", ...common, to: draft.url, cause: navigationCause(draft) };
case "click":
return {
op: "click",
...common,
target: draft.matchedTarget ?? unmatchedTarget(draft.captureTarget),
};
case "hover":
return {
op: "hover",
...common,
target: draft.matchedTarget ?? unmatchedTarget(draft.captureTarget),
};
case "fill":
return {
op: "fill",
...common,
target: draft.matchedTarget ?? unmatchedTarget(draft.captureTarget),
value: draft.value,
commit: draft.commit ?? "blur",
...(draft.redacted ? { redacted: true } : {}),
};
case "press":
return {
op: "press",
...common,
key: draft.key,
...(draft.captureTarget || draft.matchedTarget
? { target: draft.matchedTarget ?? unmatchedTarget(draft.captureTarget) }
: {}),
...(draft.modifiers?.length ? { modifiers: draft.modifiers } : {}),
};
case "select":
return {
op: "select",
...common,
target: draft.matchedTarget ?? unmatchedTarget(draft.captureTarget),
selection: selection(draft.values, draft.labels),
};
case "scroll":
return { op: "scroll", ...common };
}
}
export interface ReducedTraceV3 {
steps: StepV3[];
stepIdByDraftId: Map<number, number>;
}
export function reduceTraceStepsV3(steps: RecordingDraftStep[]): ReducedTraceV3 {
const output: StepV3[] = [];
const stepIdByDraftId = new Map<number, number>();
for (const { draft, draftIds } of collapseRedirects(steps)) {
const step = reduceDraft(draft, output.length + 1);
if (!step) continue;
output.push(step);
for (const draftId of draftIds) stepIdByDraftId.set(draftId, step.id);
}
return { steps: output, stepIdByDraftId };
}
@@ -0,0 +1,39 @@
import type { StepAnnotation } from "./types";
function annotationText(annotation: StepAnnotation, stepId: number): string {
return ` ⟵ step ${stepId}: ${annotation.op}${annotation.detail ? `: ${annotation.detail}` : ""}`;
}
export function formatTraceStateBody(input: {
stateId: string;
url: string;
title?: string;
stepIds: number[];
vomText: string;
annotations: StepAnnotation[];
stepIdByDraftId: Map<number, number>;
}): string {
const lines = ["# bsk-observation 1", `state: ${JSON.stringify(input.stateId)}`];
lines.push(`url: ${JSON.stringify(input.url)}`);
if (input.title) lines.push(`title: ${JSON.stringify(input.title)}`);
if (input.stepIds.length > 0) lines.push(`steps_here: [${input.stepIds.join(", ")}]`);
lines.push("---");
const byLine = new Map<number, Array<{ annotation: StepAnnotation; stepId: number }>>();
for (const annotation of input.annotations) {
const stepId = input.stepIdByDraftId.get(annotation.draftId);
if (stepId === undefined) continue;
const bucket = byLine.get(annotation.line) ?? [];
bucket.push({ annotation, stepId });
byLine.set(annotation.line, bucket);
}
input.vomText.split("\n").forEach((bodyLine, lineIndex) => {
let line = bodyLine;
for (const item of byLine.get(lineIndex) ?? []) {
line += annotationText(item.annotation, item.stepId);
}
lines.push(line);
});
return `${lines.join("\n")}\n`;
}
+83
View File
@@ -0,0 +1,83 @@
import type { CaptureTargetDescriptor } from "@/lib/describe-target";
import type {
FillCommit,
KeyModifier,
NavigationCause,
StepV3,
TargetDescriptorV3,
} from "@/transport/types";
export interface TargetGeometry {
/** Top-level viewport-relative CSS pixels, as defined by the geometry module. */
rect: { x: number; y: number; w: number; h: number };
tag: string;
}
export interface TargetMatchHint {
geometry?: TargetGeometry;
/** Missing means the current top frame, never an unrestricted frame search. */
frameId?: string;
}
export interface StepAnnotation {
draftId: number;
op: StepV3["op"];
line: number;
stateId: string;
detail?: string;
}
interface DraftStateLink {
pageUrl?: string;
preStateId?: string;
postStateId?: string;
}
interface DraftTarget {
captureTarget?: CaptureTargetDescriptor;
targetHint?: TargetMatchHint;
matchedTarget?: TargetDescriptorV3;
}
interface DraftNavigationEffect {
navigatedTo?: string;
}
export type RecordingDraftStep =
| ({ op: "click" } & DraftStateLink & DraftTarget & DraftNavigationEffect)
| ({ op: "hover" } & DraftStateLink & DraftTarget)
| ({
op: "fill";
value: string;
commit?: FillCommit;
redacted?: boolean;
} & DraftStateLink &
DraftTarget &
DraftNavigationEffect)
| ({
op: "press";
key: string;
modifiers?: KeyModifier[];
} & DraftStateLink &
DraftTarget &
DraftNavigationEffect)
| ({
op: "select";
values: string[];
labels?: string[];
} & DraftStateLink &
DraftTarget &
DraftNavigationEffect)
| ({ op: "scroll" } & DraftStateLink)
| ({
op: "navigate";
url: string;
cause?: NavigationCause;
transitionType?: string;
transitionQualifiers?: string[];
} & DraftStateLink);
export type TargetedRecordingDraft = Extract<
RecordingDraftStep,
{ op: "click" | "hover" | "fill" | "press" | "select" }
>;