Keep the expanded command-reference tables from feat/upload-download
(including the new File Transfer section) over main's compact two-line
format.
Co-authored-by: Cursor <cursoragent@cursor.com>
Every tool.observe moved the real cursor across the page to look for
hover-only menus and tooltips. Measured against real Chrome, that cost a
median of 2.5s and up to 4.7s per observation — 73% to 99% of total
observe wall clock — and returned 3 hits across 12 pages. A positive
control confirms the probes work; the yield on real pages simply does not
justify putting them on the default path.
observe now probes only when asked, via `probe_hover` (`--probe-hover`).
Agents that know which element hides a menu should keep using
`bsk hover <ref>`, which is both cheaper and precise. A held hover latch
still suppresses probing, since probing would move the cursor off the
element the caller is deliberately holding.
Correctness fixes that apply whether or not probing is requested:
- Hover probing ran between the DOM snapshot and the accessibility tree
fetch, so a hover that opened a menu left one half of an observation
describing the page before the change and the other half after it. Both
chains now run after all capture is complete.
- The overlay bypass toggled once per chain and swallowed restore
failures, which could leave the agent overlay hidden for the rest of
the tab's life. It is now reference counted across both chains, and a
failed restore is reported instead of discarded.
- Observations report whether they hovered the page and whether that
revealed content the static tree lacks, so callers can judge how far
the live page may have drifted from the returned snapshot.
Probe budgets were checked at the top of the loop, so a candidate could
start with 1ms remaining and still run a full settle window, overshooting
by up to 634ms. Candidates are now admitted only if they fit. Raising
MAX_HOVER_PROBE_MS to 2600 is part of that fix rather than a relaxation:
2000 was never the real ceiling, and enforcing it literally would have
silently dropped a candidate the positive control depends on.
Tooltip misses are cached too, with a shorter TTL than hits, so repeat
observations of the same page no longer re-probe every unlabelled control
from scratch.
- session_stop: exclude tabs still tracked in agentCreatedTabs from the
release decision so a tab that failed to close is no longer mistaken for
a user tab (which previously kept the window open and leaked the tab).
- Distinguish user-created tabs from agent-created tabs in the Agent Window
via a pending-tab counter consumed by chrome.tabs.onCreated, so tabs the
user opens themselves (new-tab button / Cmd+T / open in new tab) are never
taken over by the BrowserSkill control mask.
- background overlay: decide per-tab state BEFORE showing controls
(overlayStateForTab + pushOverlayStateForTab) so a user tab receives hidden
on its first overlay.ready ping instead of flashing control then hiding.
- AgentWindowApi.ensureActiveTab now resolves with the activated/created tab
id instead of void, so SessionManager can record homeTabId. This fixes the
tsc failure flagged in review (the interface previously returned
Promise<void> while callers treated the result as number | null).
- Wire the production tabManagement.tabs / tabsQuery deps into
tool.session_stop, both in the dispatcher and in the disconnect cleanup.
They were never injected, which left the agent-tab cleanup and the
window-release path as dead code outside tests (behaviour identical to
main). Added a dispatcher-level integration test that fails without the
wiring: a surviving user tab must release the window, not close it.
Tool cancellation is now cooperative end-to-end: the queue stays busy until compensation completes, cancellation is checked cooperatively across the pipeline, the fallback window is compensated too, and cleanup_failed is surfaced explicitly. Includes a gated delayed-compensation E2E test.
* feat(emulate): add mobile device emulation via CDP Emulation domain
Add `bsk emulate` so agents can debug mobile page behaviour by
emulating a device environment on a session tab:
- Viewport metrics (Emulation.setDeviceMetricsOverride), User-Agent
(Emulation.setUserAgentOverride, optional accept-language and UA
client-hints metadata), and touch (Emulation.setTouchEmulationEnabled
with maxTouchPoints).
- Seven CLI-side device presets (iphone-14, iphone-14-pro-max,
iphone-se, pixel-7, galaxy-s23, ipad-mini, galaxy-tab-s8) via
--device; manual flags (--width/--height/--dpr/--mobile/--ua/
--accept-language/--touch/--max-touch-points) work standalone or
override individual preset fields.
- `bsk emulate --off` clears every override (clearDeviceMetricsOverride
+ touch disabled + empty UA override) and restores the real
environment.
- Overrides are per-tab (CDP per-target) and not inherited by new tabs;
the result JSON carries a note reminding agents to re-apply.
Wire: new tool.emulate method end-to-end (bsk-protocol types + JSON
schemas + Method::ToolEmulate classified BrowserMutation, daemon
forwarding, CLI subcommand, extension tool handler + ChromiumCdp
Emulation wrappers, dispatcher registration), docs in both SKILL.md
copies, and unit tests on every layer.
* refine(emulate): merge per-tab state and align preset override semantics
- extension: remember the applied emulation state per tab and merge each new request onto it field by field before applying, so a later --width/--height no longer resets an earlier preset's dpr/mobile; --off clears the stored state along with the CDP overrides
- extension: cdp_failed errors now note that already-applied overrides were not rolled back and can be reset with --off
- cli: validate width/height pairing and metric requirements on the merged preset+flags result, so --device iphone-14 --width 500 keeps the preset height
- cli: add --no-mobile/--no-touch (conflicting with --mobile/--touch) to turn preset mobile/touch fields back off
- docs: describe the merge behaviour, --no-mobile/--no-touch and --off state clearing in both SKILL.md copies
- `bsk session start --width <px> --height <px>` opens the Agent Window
with the given outer size (chrome.windows.create)
- new `bsk window resize --session <id> --width <px> --height <px>`
resizes the Agent Window at runtime (chrome.windows.update)
- both validated on CLI, daemon and extension sides (100..=7680 CSS px)
- protocol: new tool.window_resize method (BrowserMutation) and
optional width/height on tool.session_start params; schemas regenerated
Capture user actions in the Agent Window and export a record-only
trace (pages[] + navigate/click/fill/select/press steps with target
descriptors). Adds the record overlay UI aligned with the control
overlay, and wires record start/stop/await through CLI, daemon,
protocol, and extension.
Add `bsk network` as a sibling of the `console` command from #7,
reading the buffered network responses / failures for a tab. Fills the
remaining half of the request in #2 (console landed in #7; network did
not).
Mirrors the console command's conventions exactly:
bsk network --session <id> [--tab-id N] [--since C]
[--limit N] [--max-text-chars N]
The extension enables `Network` on attach (best-effort) and buffers
`responseReceived` / `loadingFailed` events per tab with a monotonic
sequence, correlating them to `requestWillBeSent` for method/URL. Reads
are cursor-paginated (`since` -> `next_since`) and bounded (`limit`,
`max_text_chars`) for agent-context safety, same as console. Entries
carry the real HTTP status code (response) or the CDP failure reason
(failure) — things `performance.getEntriesByType('resource')` can't
give.
Classified read-only (pass-through under the pending-interrupt gate);
defaults to the Agent Window's active tab.
Wires bsk-protocol (Method + params/result/entry structs + schema),
bsk-cli (network subcommand + daemon dispatch allow-list) and the
extension (handler + dispatcher route), with unit / parse / IPC tests
paralleling the console command.
Refs #2.
drakezhang