Files
obscura/crates/obscura-cdp/src/domains/page.rs
T
Mike Mooring 9e3e1e4ef7 fix(cdp): five Playwright drop-in compatibility patches
Brings Obscura's CDP server in line with what Playwright's
`chromium.connectOverCDP()` expects. Each fix is small and surgical;
together they make `connect → newContext → newPage → goto → page.title()`
work end-to-end against `https://example.com`.

1. **server.rs — emit pending events before command response.**
   Chromium CDP semantics require side-effect events (e.g.
   `Target.targetCreated` + `Target.attachedToTarget` from
   `Target.createTarget`) to arrive *before* the originating command's
   response. Playwright's wire reader assumes this ordering — it
   resolves the response promise on the response and then synchronously
   looks up the freshly-created session. Reversing the order makes that
   lookup miss and the page hang at `newPage()`.

2. **domains/browser.rs — accept Browser.setWindowBounds as a no-op.**
   Playwright calls `Browser.setWindowBounds` during teardown. Returning
   "Unknown Browser method" causes Playwright to treat the target as
   broken and tear it down mid-test, surfacing as "Frame has been
   detached" on the next `page.title()`.

3. **obscura-browser/page.rs — frame_id == target_id for main frame.**
   Was `format!("{id}.1", id)`. Playwright's frame manager indexes
   frames by frame id and looks up the main frame by target id, so the
   `.1` suffix made every main-frame lookup miss.

4. **domains/page.rs + dispatch.rs — track isolated worlds and re-emit
   them post-navigation.** Playwright registers a utility world via
   `Page.createIsolatedWorld` and expects `Runtime.executionContextCreated`
   for each registered world after every navigation. Without re-emission,
   the utility-world handle goes stale post-`goto` and `page.title()`
   hangs waiting for the world's execution context. Falls back to the
   legacy `__puppeteer_utility_world__24.40.0` name when no worlds have
   been registered, preserving prior Puppeteer support.

5. **obscura-js/runtime.rs — strip trailing semicolons before wrapping.**
   Playwright's utility-script expression is an IIFE ending in `})();`.
   Both `wrap_expression` (CDP `Runtime.evaluate`) and `evaluate_for_cdp`
   (the `meta_code` IIFE) embed the user expression inside `({EXPR})` /
   `return ({EXPR});`. With the trailing `;` left in, this produces
   `({...;})` — a SyntaxError. Parse errors are not catchable, so the
   surrounding try/catch never fires and the call silently returns
   `undefined`, surfacing as `page.title() === ""`.

Verified end-to-end against `https://example.com`:
  [probe] connect OK
  [probe] newContext OK
  [probe] newPage OK
  [probe] goto OK
  [probe] title = Example Domain
2026-04-24 23:27:18 -07:00

249 lines
13 KiB
Rust

use obscura_browser::lifecycle::WaitUntil;
use serde_json::{json, Value};
use crate::dispatch::CdpContext;
use crate::types::CdpEvent;
pub async fn handle(
method: &str,
params: &Value,
ctx: &mut CdpContext,
session_id: &Option<String>,
) -> Result<Value, String> {
match method {
"enable" => Ok(json!({})),
"navigate" => {
let url = params.get("url").and_then(|v| v.as_str())
.ok_or("url required")?;
let wait_until = params.get("waitUntil")
.and_then(|v| {
if let Some(s) = v.as_str() {
Some(WaitUntil::from_str(s))
} else if let Some(arr) = v.as_array() {
arr.iter()
.filter_map(|item| item.as_str())
.map(WaitUntil::from_str)
.max_by_key(|w| match w {
WaitUntil::DomContentLoaded => 0,
WaitUntil::Load => 1,
WaitUntil::NetworkIdle2 => 2,
WaitUntil::NetworkIdle0 => 3,
})
} else {
None
}
})
.unwrap_or(WaitUntil::Load);
let preload_scripts: Vec<String> = ctx.preload_scripts.iter().map(|(_, s)| s.clone()).collect();
let (frame_id, loader_id, network_events, page_url, page_id, reached_network_idle) = {
let page = ctx.get_session_page_mut(session_id).ok_or("No page for session")?;
let frame_id = page.frame_id.clone();
let loader_id = format!("loader-{}", uuid::Uuid::new_v4());
let nav_method = params.get("__method").and_then(|v| v.as_str()).unwrap_or("GET");
let nav_body = params.get("__body").and_then(|v| v.as_str()).unwrap_or("");
if nav_method == "POST" && !nav_body.is_empty() {
page.navigate_with_wait_post(url, wait_until, nav_method, nav_body).await.map_err(|e| e.to_string())?;
} else {
page.navigate_with_wait(url, wait_until).await.map_err(|e| e.to_string())?;
}
for source in &preload_scripts {
if let Err(e) = page.execute_preload_script(source) {
tracing::debug!("Preload script error: {}", e);
}
}
let reached_network_idle = page.lifecycle.is_network_idle();
let network_events: Vec<_> = page.network_events.drain(..).collect();
let page_url = page.url_string();
let page_id = page.id.clone();
(frame_id, loader_id, network_events, page_url, page_id, reached_network_idle)
};
let es = session_id.clone();
let ts = timestamp();
let mut phase1 = vec![
CdpEvent { method: "Page.lifecycleEvent".into(), params: json!({"frameId": frame_id, "loaderId": loader_id, "name": "init", "timestamp": ts}), session_id: es.clone() },
CdpEvent { method: "Runtime.executionContextsCleared".into(), params: json!({}), session_id: es.clone() },
CdpEvent { method: "Page.frameNavigated".into(), params: json!({"frame": {"id": frame_id, "loaderId": loader_id, "url": page_url, "domainAndRegistry": "", "securityOrigin": page_url, "mimeType": "text/html", "adFrameStatus": {"adFrameType": "none"}}, "type": "Navigation"}), session_id: es.clone() },
CdpEvent { method: "Runtime.executionContextCreated".into(), params: json!({"context": {"id": 2, "origin": page_url, "name": "", "uniqueId": format!("ctx-nav-{}", page_id), "auxData": {"isDefault": true, "type": "default", "frameId": frame_id}}}), session_id: es.clone() },
];
// Re-emit each isolated world the client previously registered
// via Page.createIsolatedWorld. Without this, Playwright's
// utility-world handle becomes stale after navigation and
// every subsequent evaluate() (including page.title()) hangs.
// Fallback to the legacy hardcoded Puppeteer name so older
// Puppeteer clients that don't call createIsolatedWorld
// continue to work.
let world_names: Vec<String> = if ctx.isolated_worlds.is_empty() {
vec!["__puppeteer_utility_world__24.40.0".to_string()]
} else {
ctx.isolated_worlds.clone()
};
for (idx, world_name) in world_names.iter().enumerate() {
let world_ctx_id = 100 + idx as u32;
phase1.push(CdpEvent {
method: "Runtime.executionContextCreated".into(),
params: json!({"context": {"id": world_ctx_id, "origin": page_url, "name": world_name, "uniqueId": format!("ctx-isolated-nav-{}-{}", page_id, idx), "auxData": {"isDefault": false, "type": "isolated", "frameId": frame_id}}}),
session_id: es.clone(),
});
}
phase1.push(CdpEvent { method: "Page.lifecycleEvent".into(), params: json!({"frameId": frame_id, "loaderId": loader_id, "name": "commit", "timestamp": ts}), session_id: es.clone() });
ctx.pending_events.extend(phase1);
if ctx.fetch_intercept.enabled {
for net_event in &network_events {
ctx.pending_events.push(CdpEvent {
method: "Fetch.requestPaused".into(),
params: json!({
"requestId": net_event.request_id,
"request": {
"url": net_event.url,
"method": net_event.method,
"headers": net_event.headers,
},
"frameId": frame_id,
"resourceType": net_event.resource_type,
"networkId": net_event.request_id,
}),
session_id: es.clone(),
});
}
}
for net_event in &network_events {
ctx.pending_events.push(CdpEvent {
method: "Network.requestWillBeSent".into(),
params: json!({"requestId": net_event.request_id, "loaderId": loader_id, "documentURL": page_url, "request": {"url": net_event.url, "method": net_event.method, "headers": net_event.headers}, "timestamp": net_event.timestamp, "wallTime": net_event.timestamp, "initiator": {"type": "other"}, "type": net_event.resource_type, "frameId": frame_id}),
session_id: es.clone(),
});
ctx.pending_events.push(CdpEvent {
method: "Network.responseReceived".into(),
params: json!({"requestId": net_event.request_id, "loaderId": loader_id, "timestamp": net_event.timestamp, "type": net_event.resource_type, "response": {"url": net_event.url, "status": net_event.status, "statusText": "", "headers": &*net_event.response_headers, "mimeType": net_event.response_headers.get("content-type").cloned().unwrap_or_default()}, "frameId": frame_id}),
session_id: es.clone(),
});
ctx.pending_events.push(CdpEvent {
method: "Network.loadingFinished".into(),
params: json!({"requestId": net_event.request_id, "timestamp": net_event.timestamp, "encodedDataLength": net_event.body_size}),
session_id: es.clone(),
});
}
let mut phase3 = vec![
CdpEvent { method: "Page.lifecycleEvent".into(), params: json!({"frameId": frame_id, "loaderId": loader_id, "name": "DOMContentLoaded", "timestamp": ts}), session_id: es.clone() },
CdpEvent { method: "Page.domContentEventFired".into(), params: json!({"timestamp": ts}), session_id: es.clone() },
CdpEvent { method: "Page.lifecycleEvent".into(), params: json!({"frameId": frame_id, "loaderId": loader_id, "name": "load", "timestamp": ts}), session_id: es.clone() },
CdpEvent { method: "Page.loadEventFired".into(), params: json!({"timestamp": ts}), session_id: es.clone() },
];
if reached_network_idle || matches!(wait_until, WaitUntil::Load | WaitUntil::DomContentLoaded) {
let idle_ts = timestamp();
phase3.push(CdpEvent { method: "Page.lifecycleEvent".into(), params: json!({"frameId": frame_id, "loaderId": loader_id, "name": "networkIdle", "timestamp": idle_ts}), session_id: es.clone() });
}
phase3.push(CdpEvent { method: "Page.frameStoppedLoading".into(), params: json!({"frameId": frame_id}), session_id: es });
ctx.pending_events.extend(phase3);
Ok(json!({
"frameId": frame_id,
"loaderId": loader_id,
}))
}
"getFrameTree" => {
let page = ctx.get_session_page(session_id).ok_or("No page for session")?;
Ok(json!({
"frameTree": {
"frame": {
"id": page.frame_id,
"loaderId": "initial-loader",
"url": page.url_string(),
"domainAndRegistry": "",
"securityOrigin": page.url_string(),
"mimeType": "text/html",
"adFrameStatus": { "adFrameType": "none" },
},
"childFrames": [],
}
}))
}
"createIsolatedWorld" => {
let page = ctx.get_session_page(session_id).ok_or("No page for session")?;
let frame_id_param = params.get("frameId").and_then(|v| v.as_str())
.unwrap_or(&page.frame_id).to_string();
let world_name = params.get("worldName").and_then(|v| v.as_str())
.unwrap_or("").to_string();
let page_url = page.url_string();
let page_id = page.id.clone();
let context_id = 100;
// Track this world so Page.navigate can re-emit a context for it
// post-navigation. Without this, Playwright (and Puppeteer)
// hang in any operation that uses the utility world — including
// page.title() — because their utility world is gone after
// Runtime.executionContextsCleared and never re-created.
if !world_name.is_empty() && !ctx.isolated_worlds.contains(&world_name) {
ctx.isolated_worlds.push(world_name.clone());
}
ctx.pending_events.push(CdpEvent {
method: "Runtime.executionContextCreated".to_string(),
params: json!({
"context": {
"id": context_id,
"origin": page_url,
"name": world_name,
"uniqueId": format!("ctx-isolated-{}", page_id),
"auxData": {
"isDefault": false,
"type": "isolated",
"frameId": frame_id_param,
}
}
}),
session_id: session_id.clone(),
});
Ok(json!({ "executionContextId": context_id }))
}
"setLifecycleEventsEnabled" => Ok(json!({})),
"addScriptToEvaluateOnNewDocument" => {
let source = params.get("source").and_then(|v| v.as_str()).unwrap_or("");
ctx.preload_counter += 1;
let identifier = format!("{}", ctx.preload_counter);
if !source.is_empty() {
ctx.preload_scripts.push((identifier.clone(), source.to_string()));
}
Ok(json!({ "identifier": identifier }))
}
"removeScriptToEvaluateOnNewDocument" => {
let identifier = params.get("identifier").and_then(|v| v.as_str()).unwrap_or("");
ctx.preload_scripts.retain(|(id, _)| id != identifier);
Ok(json!({}))
}
"setInterceptFileChooserDialog" => Ok(json!({})),
"getNavigationHistory" => {
let page = ctx.get_session_page(session_id).ok_or("No page for session")?;
Ok(json!({
"currentIndex": 0,
"entries": [{
"id": 0,
"url": page.url_string(),
"userTypedURL": page.url_string(),
"title": page.title,
"transitionType": "typed",
}]
}))
}
_ => Err(format!("Unknown Page method: {}", method)),
}
}
fn timestamp() -> f64 {
std::time::SystemTime::now()
.duration_since(std::time::UNIX_EPOCH)
.unwrap_or_default()
.as_secs_f64()
}