Commit Graph
79 Commits
Author SHA1 Message Date
Ljy-0827 f86e506d47 feat(vom): update contract 2026-08-19 15:05:55 +08:00
“haonan” 45a246c41b feat(vom): expose record-safe semantic observations
Share the VOM capture pipeline with recording, enrich rendered refs, and support value redaction without regressing cooperative cancellation.
2026-08-19 15:05:55 +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
Ljy-0827 0b65b4b295 fix(vom): oopif fix 2026-08-18 19:28:16 +08:00
Ljy-0827 94ec7e73fc fix(vom): iframe oopif geometry 2026-08-18 19:28:16 +08:00
Ljy-0827 42403e55f2 feat(extension): support OOPIF refs with unified frame geometry 2026-08-18 19:28:16 +08:00
Ljy-0827 8d7c0aa66c fix(extension): support iframe content in VOM observations 2026-08-18 19:18:39 +08:00
“haonan”andCursor c8c5c4a7c4 fix(record): preserve committed empty fill steps
Allow intentional input clears to remain in exported traces instead of dropping every non-redacted blank fill.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-17 17:21:17 +08:00
NianJiu 4549ed0892 fix(extension): make tool cancellation cooperative (#89)
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.
2026-08-13 17:31:23 +08:00
BB-fat 37fbaacc94 feat(extension): add popup toggle to hide Agent control hints (#81)
Add a per-browser "Control hints" switch to the popup that hides the in-page control overlay (status pill + orange glow, along with its input blocker) while the Agent controls a tab. Preference lives in chrome.storage.local (bsk_control_hints_hidden, default: shown) and is applied live in content scripts via storage.onChanged.

Both popup settings rows share a single Switch component; the hint copy lives in an info-icon tooltip.

Refs #62
2026-08-13 10:24:17 +08:00
BB-fat f81a1e7796 fix(screenshot): fall back to CDP capture when captureVisibleTab fails (#83)
chrome.tabs.captureVisibleTab reads back the window surface, which fails
outright on some Windows/Chrome combinations (Chromium
FAILURE_REASON_READBACK_FAILED: "Failed to capture tab: image readback
failed"), leaving full-tab screenshots without any working path.

Capture the full tab via CDP Page.captureScreenshot (fromSurface) when
the visible-tab capture rejects; the CDP path goes through the
renderer BeginFrame pipeline instead of the surface readback. When both
paths fail, return cdp_failed with data.reason=screenshot_capture_failed
carrying both underlying messages, and render a CLI hint that points at
the browser-side readback cause.

Refs #71
2026-08-12 22:10:09 +08:00
BB-fatandalectimison-maker f443cfae74 feat(session): support unfocused agent windows (--no-focus) (#87)
`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>
2026-08-12 19:58:53 +08:00
BB-fatandNianJiuZst f98c0606a1 fix(extension): harden websocket reconnect lifecycle (#82)
Co-authored-by: NianJiuZst <3235467914@qq.com>
2026-08-12 19:38:03 +08:00
NianJiu 1371c92721 fix(runtime): clean up sessions on disconnect (#17)
* fix(runtime): clean up sessions on disconnect

* chore(ci): match Biome 2.4 formatting

* ci: retry stalled Rust job

* test: bind daemon ports without probe races
2026-08-12 18:44:22 +08:00
Zhang GH 238a98476e Merge pull request #34 from hobostay/fix/navigate-commit-frame-loader-id
LGTM  Thanks.
2026-08-11 14:49:27 +08:00
Zhang GH 1da2d54ddc Merge pull request #39 from hobostay/fix/console-capture-retry-on-failure
fix(extension): retry console capture when a domain enable fails
LGTM
2026-08-11 14:43:43 +08:00
Zhang GH 6e35e62199 Merge pull request #33 from hobostay/fix/cdp-attach-rollback-page-enable-failure
fix(extension): roll back CDP attach when a domain enable fails
2026-08-11 14:38:12 +08:00
Zhang GH 610782698b Merge pull request #68 from Tencent/feat/more-browser-actions
feat(extension): hover end to end capability support
2026-08-10 19:26:50 +08:00
BB-fat 9504072914 chore(release): extension 0.1.6 (#74) 2026-08-09 00:34:47 +08:00
BB-fat 1268761611 fix(screenshot): hide overlays during capture so shots only contain page content (#64) 2026-08-08 22:48:50 +08:00
Ljy-0827 566b6c17fd feat(extension): hover chain node fix 2026-08-07 17:37:28 +08:00
Ljy-0827 2ccc0aafb9 feat(extension): hover chain node 2026-08-07 15:45:38 +08:00
Ljy-0827 eeab97bcdd feat(extension): hover candidate pool 2026-08-07 12:02:28 +08:00
Ljy-0827 6c610faed9 fix(extension): bugfix 2026-08-06 18:46:06 +08:00
Ljy-0827 d685c75d25 feat(extension): emit pending hover before actions 2026-08-06 17:47:19 +08:00
Ljy-0827 73724617f9 feat(extension): recording hover with custom div 2026-08-06 17:41:33 +08:00
Ljy-0827 4ba6fb45e1 feat(extension): recording hover 2026-08-06 17:33:46 +08:00
Zhang GH 93df62a356 Merge pull request #42 from shnpd/feat/popup-function-icon
feat(extension): use function launcher icon
2026-08-06 16:47:52 +08:00
“haonan” 674c53339f fix(extension): keep record overlay timer across navigations 2026-08-06 16:28:21 +08:00
Ljy-0827 9d4ac90592 fix(extension): ci and bug fix 2026-08-06 16:16:41 +08:00
Ljy-0827 cde6f22ecf fix(extension): ci and bug fix 2026-08-06 16:14:18 +08:00
Ljy-0827 d24bb6aa93 feat(extension): dispatcher fix 2026-08-06 15:48:11 +08:00
Ljy-0827 dbc4845c0d feat(extension): vom hover description bug fix 2026-08-06 15:30:11 +08:00
Ljy-0827 91225e5fdb feat(extension): add bsk hover and adjust vom to support 2026-08-06 12:19:45 +08:00
“haonan” 66684c4ce3 feat(extension): compact recording overlay with live timer
Show the recording message for 10s, then switch to a fixed-width MM:SS
timer with the icon-only finish button.
2026-08-05 20:26:43 +08:00
BB-fat 0f264c5df1 feat(emulate): add mobile device emulation via CDP Emulation domain (#60)
* 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
2026-08-05 18:10:39 +08:00
BB-fat 49378d70de feat: support Agent Window sizing (session start --width/--height, window resize) (#52)
- `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
2026-08-05 11:19:10 +08:00
BB-fat 71255ae142 feat(request-help): add BSK_REQUEST_HELP=off to disable blocking help requests (#53)
* 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
2026-07-31 23:54:30 +08:00
Ljy-0827 d67c1a71b0 fix(vom): CI fix 2026-07-28 18:19:47 +08:00
Ljy-0827 03d2adc035 fix(vom): clean up pr 2026-07-28 17:36:41 +08:00
Ljy-0827 8f5df59b79 fix(vom): overlay 2026-07-28 17:31:33 +08:00
Ljy-0827 000fbf5540 fix(vom): bug fix 2026-07-28 16:45:40 +08:00
Ljy-0827 a52c2d6bf2 feat(vom): split function fix 2026-07-28 11:19:19 +08:00
Ljy-0827 c002c394e6 feat(vom): vom fix 2026-07-27 14:53:10 +08:00
Ljy-0827 4fb2e331a6 feat(vom): update vom algorithm, fix overlay problem with background state machine 2026-07-27 13:46:33 +08:00
Ljy-0827 e14ae9cea0 feat(vom): vom method bug fix 2026-07-24 17:25:57 +08:00
Ljy-0827 f319672721 feat(vom): method update, solve context over exposed problem 2026-07-24 17:25:57 +08:00
Ljy-0827 5e0d26ccb2 feat(vom): method update 2026-07-24 17:25:57 +08:00
Ljy-0827 9dbc553e33 feat(vom): vom base algorithm and infrastructure 2026-07-24 17:25:57 +08:00
Ljy-0827 959bfac1ae fix(extension): human-loop fixed 2026-07-24 14:07:33 +08:00