Commit Graph
25 Commits
Author SHA1 Message Date
drakezhang ee620acf64 docs(skill): give probe-hover a decidable trigger condition
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.
2026-09-02 10:59:18 +08:00
drakezhang 05a36075b8 perf(vom): make active hover probing opt-in on observe
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.
2026-09-02 10:59:18 +08:00
drakezhang 710b1219f4 test(dsh-plugin): use renamed screenshot tool 2026-08-29 16:05:06 +08:00
drakezhang 506adbe708 Merge remote-tracking branch 'origin/main' into refactor/simplify-dsh-commands 2026-08-29 15:16:31 +08:00
drakezhang 5df93143c5 refactor(dsh-plugin): simplify browser commands 2026-08-29 14:38:48 +08:00
drakezhang e9f0584af3 ci(extension): publish updates to Microsoft Edge Add-ons 2026-08-28 21:39:53 +08:00
drakezhangandCursor 2997f495db fix(dsh-plugin): use the published package name as the Cordis id
dsh 0.1.0-rc.8 imports and registers the client bundle by export const name, so a leftover dsh-plugin-browserskill id fails to load the 0.1.1 web UI.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-28 21:28:06 +08:00
drakezhang 5cd43553ed docs(eval): clarify agent-neutral scope 2026-08-28 15:36:38 +08:00
drakezhang 9ad33801c7 test: add extensible browser evaluation harness 2026-08-28 12:16:39 +08:00
drakezhang 210b21b637 style(dsh-plugin): format observation 2026-08-28 12:06:47 +08:00
drakezhang 1a70d2200e fix(dsh-plugin): stabilize skill loading and browser sessions
Register bundled browser instructions at agent scope, prioritize foreground commands over thumbnail capture, and unify cancellation and session cleanup.
2026-08-27 19:59:20 +08:00
drakezhang a4b6a61d29 docs(dsh-plugin): clarify package description 2026-08-22 21:29:33 +08:00
drakezhang cad0b5cbc9 feat(dsh-plugin): add Browser tool parity 2026-08-22 21:15:53 +08:00
drakezhangandCursor e720f1ffe5 ci(dsh-plugin): publish from the npm-publish environment
The publish job named its GitHub Environment NPM_TOKEN, which is the
secret name rather than a deployment target, so the repository's
Deployments list showed a bogus NPM_TOKEN entry next to chrome-web-store.
The environment is now npm-publish; the secret it holds keeps its name.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-19 11:20:26 +08:00
drakezhangandCursor 2b7e10ca2b fix(dsh-plugin-browserskill): identify the plugin by its published name
Renaming the package to @wxg-prc-cpg/browser-skill-dsh-plugin left two
identifiers behind on the old directory name, and both are resolved by
name rather than by path.

cordis.patch.yml is the specifier the loader imports, so dsh failed with
ERR_MODULE_NOT_FOUND on startup and took the whole plugin tree down with
it — installing the published package made dsh unusable. The client
bundle registers itself under the same kind of key, which the web shell
looks up by package name, so the screenshot toolview and the observation
overlay were unreachable too.

The bundle id now reads package.json instead of repeating the name, so it
cannot drift again. Quoting is required in the YAML because a leading '@'
is reserved in plain scalars.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-19 11:20:07 +08:00
drakezhangandCursor 1ef93463dd docs: list the Edge Add-ons build alongside the Chrome Web Store
The extension is now published to Edge Add-ons, but every install path
still pointed Edge users at the Chrome Web Store. Both READMEs and
AGENT_INSTALL.md now name a store per browser, and `bsk doctor` offers
both listings when no browser is connected.

Two Edge-specific gaps went with it: Edge blocks content-script injection
on its own storefront the same way Chrome does, so the borrow-confirmation
overlay must treat microsoftedge.microsoft.com/addons as non-injectable;
and the Chinese README still described the pre-install.ps1 manual Windows
setup.

Also give the DeepSeek Harness section its npm package link and the
profile-start step, so plugin users have a complete path.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-19 11:19:47 +08:00
drakezhang ce8bc6c870 add automate Chrome Web Store publishing with service account 2026-08-07 14:30:59 +08:00
drakezhang aa63465050 Merge remote-tracking branch 'origin/main' into fix-browser-keepalive-reconnect
Co-authored-by: Cursor <cursoragent@cursor.com>

# Conflicts:
#	apps/extension/wxt.config.ts
#	crates/bsk-cli/src/cli/session.rs
2026-07-22 15:59:12 +08:00
drakezhangandCursor 29ff239726 Make liveness thresholds configurable and cover the reaper end-to-end
Move the reaper's silence timeout and scan cadence into DaemonConfig
(defaulting to the existing 60s/15s constants) with a
`with_browser_liveness` builder, so tests can drive the task in
sub-second windows.

Add an integration test that runs a real daemon and asserts a silent
heartbeat-capable browser — and its sessions — get reaped, while a
legacy browser that never heartbeated is left untouched.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-22 13:06:17 +08:00
drakezhangandCursor 31d2a1b3dc Gate liveness reaping on heartbeat capability
Only reap browsers that have sent at least one `system.heartbeat`.
A pre-heartbeat extension never opts in, so it is never dropped on
silence and keeps relying on socket-close detection exactly as before.
This removes a backward-compat regression where a new daemon paired
with an old extension would wrongly reap a live-but-idle connection
and then report `no_browser_connected` on the next command.

- Add a `heartbeat_seen` flag to `BrowserClient`, set when a heartbeat
  event arrives, and exclude never-heartbeated clients from
  `stale_browsers`.
- Cover both the opt-in and the legacy-survivor cases in unit tests.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-22 13:06:17 +08:00
drakezhangandCursor ed92e54dff Bump extension to 0.1.4
The manifest now declares a minimum Chrome version and requests the
`idle` permission, and the runtime gains the WebSocket heartbeat and
wake-driven reconnect. Publishing that update requires a new version.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-22 12:30:46 +08:00
drakezhangandCursor cb11cecdf6 Lock system.heartbeat wire name with a contract test
The extension emits the literal event string "system.heartbeat";
assert the daemon-side serde name serialises to the same value and
round-trips from the exact frame shape the extension sends, so a
future rename cannot silently break keepalive and liveness.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-22 12:30:46 +08:00
drakezhangandCursor ea03f36f3a Widen session.start browser-connect wait for cold reconnects
After a long idle the service worker is only revived on its next
keepalive-alarm tick (up to 30s away), so the previous 5s wait made
the first command after idle fail with `no_browser_connected` even
though the extension was about to reconnect.

- Raise the daemon's `EXTENSION_CONNECT_WAIT` (used by `session.start`)
  to 35s so it comfortably covers one alarm period plus handshake slack.
- Bump the CLI `session start` IPC timeout to that window plus slack so
  it never gives up before the daemon answers, and print a one-line
  "waiting for browser extension to connect…" hint when it actually
  waits.
- Keep `bsk status` / `browsers` on their own short 5s wait so quick
  informational commands are not slowed down.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-22 12:17:15 +08:00
drakezhangandCursor 234e9101ed Keep service worker alive with WS heartbeat and wake reconnect
Harden the extension's connection so the daemon link survives normal
idle periods and OS sleep instead of silently dropping.

- Send a `system.heartbeat` event every 20s while the post-handshake
  link is live. Since Chrome 116 WebSocket activity resets the MV3
  service-worker idle timer, so this keeps the worker (and the socket)
  alive during use rather than relying on the 30s keepalive alarm that
  sits right on the eviction boundary. Declare `minimum_chrome_version:
  "116"` accordingly.
- Reconnect on `runtime.onStartup` and `idle.onStateChanged` ("active"),
  which revive the worker after a browser restart or machine wake and
  let it reconnect immediately instead of waiting for the next alarm
  tick. Add the `idle` permission and document it.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-22 12:17:06 +08:00
drakezhangandCursor 5e91178e03 Add heartbeat event and daemon browser-liveness reaper
Introduce a `system.heartbeat` protocol event and use it as a
liveness signal on the daemon side.

- Track `last_seen` per connected browser, bumped on every inbound
  WS frame (tool response, event, ping/pong, or heartbeat).
- Add a reaper task that drops any browser silent past a 60s window
  and purges its sessions, mirroring the WS disconnect cleanup. This
  releases half-open connections left behind when the OS resumes from
  sleep and kills the service worker without delivering a close frame,
  so the daemon no longer pins a phantom "connected" browser and can
  idle-exit normally.
- Wire the reaper into both the foreground daemon and the test/embed
  entry point, aborting it on shutdown.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-22 12:16:56 +08:00