- Strip (meeting-style multi-session layout): one item per session
(mini frame + id + status dot), horizontal row with scroll overflow;
hover reveals a per-item interrupt button that acts without
refocusing; click pins the focus view (pin badge, click again to
release); auto-follow picks the most recently active session but
never steals focus for errored or dead sessions (red edge / greyed
item instead).
- Edge states: the host flips an availability flag after repeated
global capture failures (client shows 'browser unavailable', keeps
the last frame, greys interrupt, and recovers on the next success);
a session_not_found envelope marks the session dead (no more frame
requests, grey strip item, removable as usual); lastError now clears
when the next action starts or succeeds.
- State/SSE wire gains { available } and an 'availability' event;
SessionObservation gains dead?.
Tests (+8, 97 total): host availability flip, dead marking +
instrumentation drop + clean removal, lastError lifecycle; client
strip render/pin/unpin/auto-follow, error no-steal, unavailable strip,
dead grey, strip-item interrupt without refocus.
Client half of the PiP observation window, wired to the host
ObservationService over the /bsk-observation HTTP+SSE seam:
- ObservationClientStore: initial state fetch + SSE increments +
on-demand thumbnail blob loading (session-authorized readAttachment,
same path as the toolview) + interrupt POST. All I/O injectable.
- ObservationOverlay registered into the shell.overlay list seat (the
sanctioned frame-wide surface; root is off-limits). Hidden with no
owned sessions; appears on first start; vanishes when all stop.
- Focus view: status row (green/grey/red dot + session + action + mm:ss
ticking), breathing thumbnail (new frames fade in, failures keep the
last frame with a warning badge, pre-navigate placeholder), and the
action area.
- Interrupt: single click, no confirm; greys into 'Interrupting…' and
back; disabled when nothing is in flight; one-time tooltip explains
the semantics (stops the current action only; the run continues).
- Card: drag-move via the header, corner-handle resize (min 240x180,
max 80% viewport), both clamped and kept for the page lifetime;
collapsible status capsule.
- PiP: Pop out (user gesture) opens Document PiP with the card's
current size, portals the same content in, and clones the document's
style nodes; pagehide falls back to the card with state intact;
unsupported browsers hide the button; nothing auto-pops.
Tests (+17, 89 total): store (fetch/SSE apply/malformed frames/
thumbnail lifecycle/interrupt wire/stop cleanup) and overlay (hidden->
visible lifecycle, status row, thumbnail via loader, interrupt
disabled/active/hint-once, capsule, resize clamps, move clamps, PiP
unsupported, PiP pop/fallback). Styling follows web-styling (dsw-alias
tokens, CSS Modules, focus-visible, reduced-motion).
Per-session live observation for owned sessions only, feeding the
upcoming client overlay:
- State model: SessionObservation (sessionId/url/action/since/
thumbnailAttachmentId/lastError), one entry per owned session;
added on start, removed on stop, cleared on dispose.
- Instrumentation: the shared runBsk wrapper begins/ends an action
(tool name mapped to a verb) around every model-facing call and tags
the child with its session id; action end triggers an immediate
thumbnail refresh.
- Thumbnail loop: 1.5s cadence while active, 8s idle downclock, x3
failure backoff, silent frame retention on errors; captures run
OUTSIDE the instrumentation (no action events, no current-pointer
movement) and land in the attachment store by reference.
- Interrupt: runner.killFor(tag) kills exactly the tagged in-flight bsk
children — chat-Stop-equivalent semantics for the current or a named
owned session; foreign ids and the no-in-flight case return false.
- Remote seam: dsh 0.1's Typert Remote pipeline and forwarded-event
allowlist are closed to out-of-tree packages, so state/events/
interrupt are served over the documented webServer route seam:
GET /bsk-observation/state, GET /bsk-observation/events (SSE),
POST /bsk-observation/interrupt; routes mount only when a webServer
service exists (headless compositions skip them).
- Config: observationEnabled (true), thumbnailIntervalMs (1500),
idleIntervalMs (8000).
Tests (+13, 72 total): state machine + event stream, cadence fast/idle/
backoff, headless no-store silence, observation-traffic isolation,
interrupt routing (default/specified/none/foreign), HTTP route
handlers, disabled-webServer no-op.
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.
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.
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/).
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.
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.
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.
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)
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.
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
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
The per-user pipe name embedded %USERNAME% verbatim
(\\.\pipe\bsk-daemon-{user}-{hash}). When the username contains
apostrophes (e.g. z'z'f'l'g'y), NPFS behaviour diverges between create
and open: the daemon's CreateNamedPipeW reports success and logs that it
is listening, yet every client CreateFileW on the same name fails with
ERROR_FILE_NOT_FOUND / ERROR_PATH_NOT_FOUND, so the CLI can never reach
the daemon (issue #75).
The name is now hash-only (\\.\pipe\bsk-daemon-{hash}); the hash
already covers user + home, so uniqueness and per-user/BSK_HOME
isolation are unchanged, and no raw username characters can reach NPFS.
The pipe name is exchanged exclusively through daemon.json (the CLI
never computes it), so old/new CLI/daemon combinations stay compatible.
Unit tests pin the safe character set for apostrophe/space/Unicode
usernames and the per-(user, home) uniqueness.
Fixes#75
`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 first-run installers (install.sh, install.ps1) downloaded and
extracted the bsk release archive with no integrity check, even though
the in-app `bsk update` path treats a sha256 checksum as mandatory
(update.rs bails with "does not include a sha256 checksum; cannot
safely auto-update"). The release version.json already carries a
per-asset sha256 (render-version-json.mjs renders with --dist), so the
installers can verify the same way.
Both installers now fetch version.json once (pinned and latest), read
`assets[<platform>].sha256`, and verify the downloaded archive's sha256
before extracting:
- install.sh: POSIX sed to parse the field (no jq dependency), and
sha256sum/shasum to compute the digest.
- install.ps1: Invoke-RestMethod + Get-FileHash.
A checksum mismatch is fatal (fail-closed, matching `bsk update`). A
missing manifest/checksum, or the absence of a sha256 tool, only skips
verification with a warning, so the first-run bootstrap still works on
minimal/offline machines.
Validation: `sh -n` / `bash -n`; functional test of the sed extraction
against a realistic version.json and of compute_sha256 against
sha256sum. The installers are not exercised by CI (no shell harness).
Co-authored-by: Claude <noreply@anthropic.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.
* fix(update): run periodic update check in daemon so hints actually fire
The CLI spawned a detached thread to refresh ~/.bsk/update-check.json,
but the process exits as soon as the command finishes, killing the
thread before the fetch could complete — so the cache was never
written and the new-version hint never showed.
Move the periodic check into the daemon: a tokio task ticks every
30 minutes (down from 24h), refreshes the cache when missing/stale,
and logs failures at warn/info into the daemon log. The CLI path is
now read-only: it prints the hint only from a fresh cache and never
spawns threads or touches the network.
* fix(update): decouple daemon refresh window so checks truly run every 30min
The refresh decision reused the 30min tick interval as its freshness
window, and with is_fresh()'s inclusive bound a cache written just
after tick N still counted as fresh at tick N+1 — so in steady state
the daemon only refetched every other tick (~60min).
Judge staleness against DAEMON_REFRESH_WINDOW (25min = 5/6 of the
tick) instead: every 30min tick now finds the cache stale and really
refreshes, while a daemon restarted with a younger-than-25min cache
still skips its first tick. CLI hint freshness semantics
(UPDATE_CHECK_INTERVAL = 30min) are unchanged.
* feat(install-skill): add Kimi Code harness support
Add kimi-code to the install-skill harness list: installs the bundled SKILL.md into ~/.kimi/skills (Kimi Code CLI's brand-group user skills directory, highest priority per https://github.com/MoonshotAI/kimi-cli/blob/main/docs/en/customization/skills.md). Detection signals: ~/.kimi directory and kimi/kimi-cli on PATH. Aliases: kimi, kimi-code, kimi-cli, kimicode, kimi_cli.
* fix(install-skill): point kimi-code harness at ~/.kimi-code and honor KIMI_CODE_HOME
Kimi Code CLI's canonical repo is MoonshotAI/kimi-code: user-level skills live in $KIMI_CODE_HOME/skills (default ~/.kimi-code/skills), not kimi-cli's ~/.kimi/skills. Detection checks the kimi-code home dir (env-aware label) and the kimi binary on PATH. Serialize env-mutating kimi tests with a shared mutex to avoid a parallel-test race on KIMI_CODE_HOME.
* 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
BB-fat