main rewrote SKILL.md into a leaner core (#167) while this branch documented
the opt-in --probe-hover flag against the old structure. Keep main's rewritten
prose and re-apply the probe-hover guidance on top of it: the [has-submenu] /
[expanded] markers, when reaching for --probe-hover is warranted, and its slot
in the page-reading escalation ladder ahead of get-html/screenshot.
Co-authored-by: Cursor <cursoragent@cursor.com>
The previous wording asked the agent to notice when a page "looks like"
it hides content behind hover. That is not something an agent reading a
text tree can judge: hover-only content is invisible by definition, and
the marker that used to point at it came from the probing that is now off
by default.
Replaces it with a condition the agent can actually evaluate — an
expected control is missing and no [has-submenu] marker points at a
trigger — and places it on the escalation ladder ahead of get-html and
screenshot, which is where that dead end is currently reached.
Also documents [has-submenu]/[expanded] as the primary hover signal. It
comes from aria-haspopup in the accessibility tree, costs nothing, and is
unaffected by probing being off, so it covers menus that are marked up
correctly.
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.
The CLI skill had grown to 20.8 KB of command tables and flag catalogs that
`bsk --help` already answers at runtime, so every agent paid for them on every
task. Rewrite both skills around the durable rules an agent cannot rediscover
-- session lifecycle, the observe/act/observe loop, the Agent Window boundary,
and the stop-on-success contract -- and delegate flag details to the CLI's own
help output. The CLI skill drops to 6.9 KB (-67%) and the DSH skill to 5.1 KB.
Keep the parts that help discovery has no answer for: the literal
`[hover first: ...]` observation marker, the `request-help` outcome values, the
complete command-name inventory, and the required flags agents guess wrong
(`fill --value`, `select --value`, `screenshot --out`, `emulate --device`).
Also bind `--no-focus` explicitly to `bsk session start`, since a bare mention
led agents to pass it to `bsk navigate`.
Validated with 36 agent runs of the `core` eval suite against a real browser,
comparing the old and new instructions with everything else held constant.
Pass rate did not regress (the lean version was better on `form-controls`) and
token cost per task came out even. The inventory and flag signatures cut
`--help` round-trips from 1.7 to 0.7 per task and removed the invented
`bsk back` / `bsk forward` calls the first draft produced.
Tighten the DSH size assertion to a range so the budget is bounded from both
sides and accidental truncation fails the test.
Co-authored-by: Cursor <cursoragent@cursor.com>
The exit code reflects RPC success only, not JS success. Document that programmatic callers must use --json and check the .ok field to detect JS errors. Addresses the discoverability gap raised in issue #133.
Agents were stopping on popup and status copy that looked like a hard incompatibility. Keep the connection usable, reframe exit 5 as an unknown method, and ask users to upgrade instead of aborting.
Co-authored-by: Cursor <cursoragent@cursor.com>
`bsk session start --no-focus` opens the Agent Window in the background
without stealing focus. The flag threads focused=false through
CLI -> daemon IPC -> tool.session_start -> chrome.windows.create; an
omitted `focused` keeps the extension default (true) so older clients
are unaffected.
Reworked onto current main so it composes with #52 window sizing:
AgentWindowApi.create / SessionManager.start (extension), start_session
(CLI) and the daemon's session start now take options objects/structs
({ size, focused }) instead of colliding positional params.
Co-authored-by: alectimison-maker <alec.timison@gmail.com>
The daemon's periodic update check now installs a newer release instead
of only refreshing the hint cache: it reuses the update.rs install path
(download, sha256 verify, extract, replace), skips the round while any
agent session is live, and otherwise restarts itself into the new binary
(spawns a detached replacement that waits for the old pid, then exits).
On by default; BSK_AUTO_UPDATE=off keeps the old cache/hint-only
behaviour. Windows can only stage the replacement, so it just logs that
a restart is needed. The CLI hint wording reflects the switch.
* 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
* feat(request-help): add BSK_REQUEST_HELP=off to disable blocking help requests
* style(extension): format HelpOutcome union per biome
* docs(skill): condense BSK_REQUEST_HELP section
Add a popup launcher + action-recording panel that builds a copyable
`bsk record start` prompt, add `--browser` targeting, and default `--url`
to https://example.com/ when omitted. Drop the popup browser-alias field.
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.
