Commit Graph
28 Commits
Author SHA1 Message Date
BB-fat 3d050e0f26 feat(dsh-plugin-browserskill): strict ownership boundary — foreign sessions are invisible
Tighten the shared-daemon boundary from 'cleanup only touches owned
sessions' to 'the plugin only ever sees and operates on sessions it
created':

- browser_session_list no longer queries the daemon at all; it returns
  the plugin's own session table (with the current marker), so foreign
  sessions cannot even be enumerated through the plugin.
- Every tool's optional session argument must name a plugin-created
  session; foreign/unknown ids are rejected with a clear error before
  any command reaches the daemon (the reference-adoption channel is
  gone).
- Unchanged: dispose stops exactly the owned set, stop requires
  ownership, the start reservation protocol, and handle-precise child
  kills.

Tests updated (59): explicit-foreign rejection without daemon contact,
registry-only listing, reservation race, stale-handle-tolerant dispose.
e2e: a manually started foreign session was rejected on reference,
absent from session_list, refused on stop, and survived dispose while
both plugin sessions were cleaned up.
2026-08-14 04:12:38 +00:00
BB-fat afdc398730 fix(dsh-plugin-browserskill): strict session ownership on a shared daemon
Review hardening for daemon-sharing deployments (other agents,
terminals, or dsh instances on the same bsk daemon):

- Ownership split: only sessions created by browser_session_start are
  'owned'. Explicitly referenced foreign sessions are still tracked for
  the current-session pointer, but browser_session_stop refuses them
  and unload cleanup stops exactly the owned set — no path can stop a
  session this plugin did not create.
- Start race: the capacity check is now a synchronous
  reserveStart/completeStart/abandonStart protocol, so two concurrent
  starts can never both pass the cap (check-and-reserve is atomic on
  the event loop); a rejected or failed start never leaks a session.
- Stale handles: dispose already swallowed per-stop errors; the owned
  set is computed at dispose time so an externally stopped session is a
  no-op, not a failure.

Tests (+7): reservation race (two concurrent starts, cap 1 -> exactly
one spawn), foreign-stop refusal (no stop command reaches the daemon),
reference adoption never becoming owned, resolveForStop pointer
stability, and an apply-level dispose test proving only owned sessions
are stopped while stale stops are tolerated. e2e: a manually started
foreign session survived the plugin's full lifecycle while both plugin
sessions were cleaned up.
2026-08-14 03:45:52 +00:00
BB-fat 6b96fcca32 feat(dsh-plugin-browserskill): add the web client half with a browser_screenshot toolview
Make the package dual-face: a dsh.client declaration (platform 'web')
plus an exports["./client"] bundle built in dsh's closure-factory shape
(window.__ModuleLoader__.load handoff, platform modules external,
everything else inlined, CSS Modules via lightningcss).

The client registers a keyed 'tool.call.toolview' view for
browser_screenshot that keeps the terminal block (command + output) and,
when the settled result carries an image block, resolves the durable
attachment through the client session's authorized readAttachment RPC
and renders it with the shared MessageImage thumbnail/lightbox atoms.
Path-only results render unchanged; every other browser_* tool keeps
the stock terminal card.

Tests: view-model derivation (running/ok/error, image vs path-only),
component rendering through @testing-library/react + happy-dom, and the
registration key. biome.json now excludes the package's lib/ build
output (same treatment as dist/).
2026-08-14 02:54:33 +00:00
BB-fat 0771292336 fix(dsh-plugin-browserskill): keep the terminal result card for multi-block results
browser_screenshot on an image-capable route returns text + image
blocks; the shared result presenter required exactly one text block and
bailed to the generic card (tool name + raw args). Project the first
text block instead so the terminal card shows in both modes.
2026-08-13 18:06:57 +00:00
BB-fat 54869cabd0 fix(dsh-plugin-browserskill): include the bsk error hint in the thrown message
The daemon's JSON error envelope carries an actionable hint (e.g.
'choose an input, textarea, or contenteditable element from the latest
snapshot'), but the thrown BskError only embedded the message field, so
the model-facing error text never showed the hint. Append it.
2026-08-13 17:56:16 +00:00
BB-fat 2de7c5c6ff fix(dsh-plugin-browserskill): enforce the session cap before spawning
The concurrency cap was checked in registry.add() AFTER
`bsk session start` had already created the session, so a rejected
start leaked a live session outside the plugin's tracking (found by the
real-browser e2e: the rejected third session stayed in
`bsk session list` after dispose). Check capacity before spawning;
registry.add() keeps the same check as a backstop.
2026-08-13 15:27:29 +00:00
BB-fat 703fc64399 feat(packages): add dsh-plugin-browserskill — DeepSeek Harness tools for bsk
Add a new monorepo package that registers BrowserSkill (bsk) browser
automation as model-visible tools in DeepSeek Harness (dsh):

- 11 tools mapping to bsk CLI --json commands: session start/stop/list,
  navigate, snapshot, observe, click, fill, press, screenshot, emulate
- multi-session support: optional session arg with a current-session
  pointer, session id echoed in every result, configurable concurrency
  cap (default 5), and dispose-time cleanup of plugin-started sessions
- cancellation: exec.signal aborts kill the underlying bsk child process
- terminal-style UI cards (command line as the call card, output as the
  result card); screenshots inline the PNG through the host attachment
  store when the model route accepts image input, else return the path
- config: bskPath / defaultTimeoutMs / maxSessions via Schemastery schema
- install guidance when the bsk binary is missing; bsk JSON error
  envelopes (code/message/hint) surfaced to the model
- unit tests mock the bsk runner (no real browser required); the root
  lint script now also runs the package's typecheck + tests so the
  existing CI frontend job covers the new package (a dedicated CI job
  diff is provided in the PR; the pushing token lacks workflow scope)
2026-08-13 15:04:52 +00:00
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
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
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
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 c095128218 fix(extension): CI problem fixed, tab logic fixed 2026-07-24 14:07:33 +08:00
Ljy-0827 f73a0e9fb3 fix(runtime): incorrectly takeover the browser when user open up different tab within the same window 2026-07-24 14:07:33 +08:00
Ljy-0827 4e44fb2823 fix(runtime): fix early control return and update lifecycle 2026-07-24 14:07:33 +08:00
“haonan” 585308df45 feat(record): add popup quick-actions launcher and make record --url optional
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.
2026-07-22 13:27:30 +08:00
“haonan” ac028a7a18 feat: add bsk record for semantic user-action traces
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.
2026-07-22 11:27:30 +08:00
NianJiuZst ed6d14eab3 fix(extension): fail closed on borrow confirmation 2026-07-10 22:01:46 +08:00
BB-fat f60d1e65a7 Merge pull request #12 from NianJiuZst/codex/issue-10-pr-ci
Add PR CI workflow
2026-07-10 00:23:36 +08:00
BB-fatandCursor 3c936982a3 Fix Biome and Stylelint formatting so pnpm lint passes.
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-10 00:21:19 +08:00
NianJiuZst fa3133a094 Add PR CI workflow 2026-07-09 12:42:42 +08:00
BB-fat f1036a860c Initial public release 2026-06-22 17:36:26 +08:00