* feat(onboard): add browser-first guided handoff
* chore: drop release-only CHANGELOG edit from browser-handoff branch
* fix(onboard): make browser handoff reach the gateway on real installs
The presence probe connected as a raw shared-auth client with a possibly
SecretRef-managed token, which the gateway rejects as an unpaired Control UI
client ("device identity required"), so the handoff never fired and always
fell through to the terminal hatch. Read presence as a CLI-mode loopback client
(the trusted path every openclaw command uses) so operator.read is granted, and
share that one auth path between the reachability gate and the wait loop. Also
short-circuit when gateway.controlUi.enabled is false so onboarding does not open
a dead dashboard URL and block for the full timeout.
* fix(onboard): share resolved target between handoff gate and wait
The reachability preflight now resolves the same target (and shared secret) the
wait loop uses, and presents the configured secret to the CLI-mode presence
read. Known remaining limitation: on fresh quickstart gateways whose auth token
is written to config but resolved differently at runtime, the presence read is
rejected with a token mismatch and the handoff falls back to the terminal hatch.
Tracked for follow-up before enabling the browser handoff by default.
* docs(onboarding): mark phase 3 browser handoff as held with diagnosis
* docs(onboarding): phase 3 proven end-to-end; token-mismatch hold was a test artifact
* fix(onboard): satisfy docs-map and test-type gates for the handoff branch
* refactor(onboard): split guided manual stage
* feat(linux): add Quick Chat floating composer to the Tauri companion
- frameless transparent always-on-top quickchat window (on-demand, canvas
pattern), positioned top-third on the cursor monitor, CSS fade+zoom in/out
- global shortcut Ctrl+Shift+Space on X11 (GNOME reserves Alt+Space); tray
'Quick Chat' item is the Wayland entry point; blur/Esc/close-request hide
- sends via the CLI agent turn with --message-file staged 0600 (argv is
world-readable procfs) and cleaned up after the turn; failures surface as
desktop notifications; Ctrl+Enter also opens the dashboard
- default-agent identity chip (emoji/monogram) from agents list --json, 60s cache
- window-scoped capability + permission set; window-state denylist; docs
* chore(linux): register quickchat.js as a knip native-asset entry
* feat(onboarding): recommend plugins and skills from installed apps
Scan installed macOS apps during classic onboarding (TCC-free), gather
candidates from official catalogs + ClawHub search, let the configured
model pick genuine matches, and offer an opt-in multiselect install step.
Adds a device.apps node-host command (default-off sharing, Android-parity
envelope) so remote gateways can request a paired Mac's inventory, and a
wizard.appRecommendations kill switch. Custom setup-inference completions
no longer inherit the 32-token verification-probe output cap.
* feat(onboarding): recommend apps in guided flow
* fix(onboarding): harden app recommendations against ClawHub self-promotion
Third-party ClawHub skills are never pre-selected regardless of model tier
(publisher-controlled listing text reaches the matcher prompt and could
promote itself); their labels now say they install third-party code.
Installed-app scans follow symlinked .app bundles. Matcher output stays
bounded by the resolved model's own maxTokens budget (documented invariant).
* fix(onboarding): key official catalog candidates by resolved plugin id
Real catalog entries are package manifests without a top-level id; keying the
candidate map and channel/provider classification by entry.id collapsed the
whole official catalog into one undefined-keyed entry, so no official plugin
or channel was ever recommended. Regression test runs against the bundled
catalogs.
* fix(onboarding): satisfy lint, types, deadcode, and migration gates
Split the guided-onboarding test into a self-contained custodian suite to stay
under max-lines. Narrow app-recommendation exports (drop dead node-payload
normalizer, unexport internal types/helpers, route candidate tests through the
public API), replace map-spread with a helper, unexport device.apps result
types, add installedAppsSharing to node-host migration expectations, cast the
wizard multiselect mock, and regenerate the docs map.
* test(onboarding): register new live test in the shard classifier
* feat(onboard): guided onboarding becomes the custodian flow
Question zero asks for discovery consent up front (full access recommended,
guarded asks once or configures manually; persisted as wizard.accessMode and
honored on reruns). Discovery quietly collects auto-ladder failures into one
summary with details behind 'See other options', quips about detected coding
agents, and announces the working route as a default with an easy undo.
After inference and the memory offer (skipped when discovery was declined),
fresh installs auto-apply the standard setup plan and hatch the agent
directly in the terminal; configured installs (pre-existing model or gateway
config) stay verification-only and never reinstall or restart the Gateway
service. Setup-apply failures fall back to the conversational chat.
Remote-gateway onboarding keeps its legacy chat handoff explicitly.
listManualSetupInferenceOptions lists manual providers without scanning.
* docs(onboarding): add custodian redesign implementation plan (living doc)
* docs: regenerate docs map for onboarding-redesign page
* feat(mac): add Quick Chat floating composer with global shortcut
- Spotlight-style non-activating key panel on Option+Space (KeyboardShortcuts
3.0.1 exact-pinned, recorder row in Settings -> General) plus a menu bar item
- shows the main-session agent identity via agent.identity.get with a
'main session' chip; Return sends via chat.send reusing the idempotency key
on ambiguous retries; Cmd+Return also opens full chat; Shift+Return newline
- targeted permission strip (notifications/accessibility/screen recording)
with a scoped 1s status poll while visible; grant flow keeps the bar alive
and avoids PermissionMonitor's AppleScript probe
- extract shared ChatSendStatus acceptance mapping; TalkModeRuntime adopts it
- rename anchored-panel 'quick chat' wording to 'compact chat panel'; docs
* chore(mac): regenerate docs map and native i18n inventory for Quick Chat
* ci: retrigger checks after stalled push event
* chore(mac): refresh native locale artifacts for Quick Chat strings
* chore(android): regenerate locale strings for refreshed shared translations
* feat(llama-cpp): add in-process text inference
* test(llama-cpp): narrow setup provider fixture
* fix(llama-cpp): trim public surface and refresh docs map
* fix(llama-cpp): import Context type in inference test
* docs(lobster): enumerate injected workflow env vars and clarify step-output access (#82281)
* docs(lobster): refresh workflow environment docs map
Clarify how shells handle nonexistent step-output variables and regenerate the generated docs map for the new section.
Co-authored-by: Shubhankar Tripathy <reach2shubhankar@gmail.com>
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* feat(canvas): let widget buttons send prompts into web chat
Inline show_widget documents get a sendPrompt(text) bridge: a private
MessageChannel offered to the Control UI before widget code runs. The chat
adopts only the first offer per frame, requires transient user activation,
a visible focused frame, plain text (no slash commands), and rate limits
10 prompts/minute per widget. Accepted prompts run the normal user send
path of the owning chat pane.
* fix(canvas): appease lint/knip/docs gates for widget prompts
Split widget prompt tests into their own file, drive validation and rate
limits through the real port path instead of exported internals, use
addEventListener on the adopted port, and regenerate docs_map.
* fix(canvas): install widget listeners per window for non-isolated tests
Module-boolean listener flags broke in shared vitest workers where each test
file gets a fresh jsdom window; key installation by window instead and give
port flushing more headroom.
* fix(line): run post-ack webhook processing on its own admitted work root
LINE acks the webhook and dispatches event processing fire-and-forget on
the same async chain. The HTTP request admission that chain inherited is
released as soon as the route handler returns, and a released admission
refuses subordinate queue work - so every LINE inbound agent turn fails
with "GatewayDrainingError: Gateway is draining; new tasks are not
accepted" even though the gateway is healthy. DMs, group mentions, and
postbacks are all affected; the user-visible symptom is the bot replying
"Sorry, I encountered an error processing your message." to everything.
Add runDetachedWebhookWork to the plugin-sdk webhook-request-guards
surface (a thin wrapper over the gateway independent-root continuation,
the same shape core uses in gateway/server/hooks.ts) and route all three
LINE ack-first dispatch sites through it: the gateway monitor handler
(the live path), and the createLineNodeWebhookHandler / Express
middleware handlers (public webhook building blocks an embedder can
register under the gateway). #65375 unified these three into one ack-first
pattern; keeping the detach consistent avoids re-introducing the same
latent defect in the two that are not on the live gateway path today.
The continuation is reserved synchronously while the request is still
admitted, so the detached processing stays accepted and a real restart
drain can wait for it instead of stranding it mid-turn.
Tests pin every layer: the guards suite proves detached post-ack work is
admitted after the request admission is released (and that the inherited
chain without the helper is refused); the monitor lifecycle suite and the
webhook-node suite assert each dispatch site goes through the detached
root. Red/green verified: reverting any dispatch fails its test.
* fix(plugin-sdk): account for runDetachedWebhookWork in public surface budget
* fix(channels): track detached webhook processing
Co-authored-by: 許元豪 <146086744+edenfunf@users.noreply.github.com>
* docs: refresh generated docs map
* chore(plugin-sdk): refresh API baseline
* fix(webhooks): preserve post-ack ordering
* test(plugin-sdk): satisfy detached work lint
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Adds a Discord Activities integration so an agent can show a self-contained
HTML widget to Discord users, opened as a sandboxed Activity inside the client.
Off by default: routes, the discord_widget tool, and the launch handler register
only when channels.discord.activities is configured. OAuth identifies the user
and gates on the account allowlist; widget lookup is capability- or
instance-validated; token exchange is rate-limited; widget HTML runs in a
no-network sandboxed iframe.
* feat(linux): canvas via CLI-node + Tauri app IPC bridge
* refactor: extract gateway helper modules
* build(linux-canvas): register plugin package in lockfile
* fix(linux-canvas): move canvas advertise test out of core, regen docs/protocol/deadcode
* fix(gateway): break node-catalog/registry import cycle via leaf normalize module; add canvas glossary term
* style: oxfmt invoke.ts and runtime.ts after buildNodeEventParams extraction
* fix(linux): load Canvas WebView via dedicated data_directory context
Wry's Linux/WebKitGTK incognito mode discards Tauri's registered
WebContext (wry webkitgtk/mod.rs), so the Canvas window got a fresh
ephemeral context without the openclaw-canvas:// scheme handler — the
bundled A2UI page never committed (stayed about:blank) and every A2UI
command timed out. Use an isolated cache-backed data_directory instead,
which keeps the protocol handler while still isolating Canvas storage
from the dashboard window.
* fix(linux): keep Canvas WebView ephemeral via incognito + data_directory
Autoreview flagged that a dedicated data_directory alone persists Canvas
browser state (cookies, localStorage, IndexedDB, service workers) across
restarts, so an agent that navigates Canvas to a site could leak an
authenticated session into a later session. iOS uses a non-persistent
store; Linux should match.
Add .incognito(true) alongside .data_directory(): the distinct directory
gives Tauri a fresh WebContext key so it still attaches the
openclaw-canvas:// protocol closure, and incognito makes Wry swap in a
fresh *ephemeral* context carrying those protocols. Live-verified on a
Wayland/WebKitGTK box: the bundled page still loads
(location.href=openclaw-canvas://localhost/index.html, openclawA2UI
present, A2UI renders) and the canvas-webview dir holds no persistent
cookie/storage files.
User-facing name is now OpenClaw (the system speaks); internal code name is
system-agent. Gateway methods crestodian.* -> openclaw.chat/openclaw.setup.*,
agent tool -> openclaw, reserved agent ids openclaw + retired crestodian.
openclaw setup routes: onboarding flags -> onboard, -m/--yes -> system agent,
bare configured interactive -> OpenClaw chat, unconfigured -> onboarding.
Hidden crestodian CLI and /crestodian TUI aliases kept; docs moved to
docs/cli/openclaw.md with redirect stub. macOS/Android strings in lockstep.
Refs #107237
Plugins can register api.registerMcpServerConnectionResolver({serverName,
resolve}) to bind an MCP server's transport (url/headers) to the trusted
sender of each message. Server identity stays static; only the connection
is per-requester. Runtimes are cached per (sessionId, channel, accountId,
senderId); runs without a trusted requester fail closed (cron, subagent,
heartbeat). Resolved credentials never enter fingerprints or logs. Static
servers keep the existing session-scoped lifecycle byte-for-byte.
Enables per-user hosted MCP sessions (e.g. per-user OAuth email/calendar)
in multi-sender channels like Slack.
Refs #106229
* feat(linux): add node device capabilities
* fix(linux-node): actionable pending-approval error + node-host advertise integration test
* fix(linux-node): map geoclue access-denied to LOCATION_DISABLED; floor camera maxWidth to avoid zero-height scale
* fix(linux-node): clamp small camera maxWidth to 2 instead of default
* docs(linux-node): clarify where-am-i -t is a process timeout, not update throttle
* refactor(gateway): extract legacy-node filter + rejection hint to fit LOC ratchet; docs-map + deadcode baseline
* fix(gateway): drop now-unused DEFAULT_DANGEROUS_NODE_COMMANDS import after hint extraction
* test(node-host): drop imports orphaned by removed error-code test
Adds consistent manual Workboard movement across CLI, slash commands, and agent tools while preserving operator authority and agent claim isolation.
Co-authored-by: Ross I4JU <ross@i4ju.ch>
* fix(channels): time-gate progress drafts and defer narration until visible
Progress drafts started immediately on the second work event, so the 5s
initial delay never filtered small fast tasks and Discord showed narrated
status for turns that finish in seconds. The gate is now purely time-based
(explicit startNow paths like approvals/patches are unchanged), and the
progress narrator no longer spends utility-model completions before the
channel draft is visible - notes buffer so the first visible narration has
full context.
Surface: src/channels/streaming.ts gate, src/auto-reply/reply/progress-narrator.ts,
Discord draft-preview wiring; test updates across discord/matrix/msteams/slack.
Refs #105872
* feat(channels): model-preamble status headline for progress drafts
In progress mode the draft's status line is now the model's own typed pre-tool
preamble whenever it is fresh (always on, no new config); utility-model
narration fills the slot only when the model has been quiet for ~20s or emits
no preamble. Preambles never start the draft early - the time gate still owns
the small-vs-big decision - and narration generation is suppressed while a
fresh preamble exists, saving utility calls. Discord and Telegram render the
headline; the opt-in streaming.progress.commentary lane and its receipt
counters are unchanged.
Refs #105872
* refactor(channels): split status-text and telegram preview helpers to honor the LOC ratchet
The LOC ratchet forbids raising baseline entries, so the headline feature's
growth is paid for with clean splits: reasoning/commentary text normalization
moves to src/channels/progress-draft-status-text.ts, Telegram progress preview
rendering to extensions/telegram/src/progress-draft-preview.ts, and small
ownership moves (formatCompactionModelRef, resolveFollowupAbortSignal, shared
CLI preamble gate, Discord preamble item-event handling) shrink the runners
back under their pins. Baseline entries lowered to exact new counts; the
compositor entry is removed (424 lines, under the 500 ceiling).
Refs #105872
* test(auto-reply): add resolveFollowupAbortSignal to the queue mock factory
The explicit ./queue.js vi.mock factory must export every binding prod touches;
the relocated resolveFollowupAbortSignal was missing and failed the whole
followup-runner suite.
Refs #105872
* fix(channels): sanitize preamble headlines and retry skipped narration
Review findings: preamble headlines now strip inline delivery directives and
reject silent-control tokens (NO_REPLY) before rendering, sharing the
commentary sanitizer; rejected input keeps the previous valid headline. The
narrator schedules cancellation-aware retries when a run is skipped for draft
invisibility or preamble freshness, so single long tool calls still narrate
and the ~20s utility filler fires without needing another event. Silent
preambles no longer stamp freshness or add narration notes.
Refs #105872
* fix(channels): bound narrator visibility polling and gate Telegram headline mode on accepted preambles
Visibility retries stop after 30 one-second attempts (turn completion has no
narrator disposal signal) and re-arm on new activity; Telegram derives its
headline-rendering state from the compositor's sanitized headline instead of
raw payload text, so directive-only or NO_REPLY preambles keep structured
tool-line rendering. Docs scope the preamble headline to Discord and Telegram.
Refs #105872
* fix(telegram): read headline state from the compositor at render time
The progressHeadlineActive mirror flag was set after pushPreambleHeadline had
already rendered, so the first valid preamble arriving after the draft opened
rendered through the structured-line path and the headline never appeared
until the next event. The renderer and formatLine now read the compositor's
sanitized hasStatusHeadline directly and the mirror flag is deleted; adds an
ordering regression test. LOC baseline lowered to the exact new count.
Refs #105872
* fix(channels): let the opt-in commentary lane own preambles and scope narration docs to Discord
With streaming.progress.commentary enabled, the status headline would replace
the documented interleaved 💬 lines for any turn with a preamble (the exact
event the lane consumes). The compositor headline now declines when the
commentary lane is enabled, preserving that lane's shipped shape, and docs
state the utility-model filler is Discord-only today (Telegram's headline is
preamble-only; it has no narrator wiring).
Refs #105872
* fix(msteams): cancel the pending progress gate at finalize
With the purely time-based gate, every fast Teams progress turn leaves a
pending 5s start timer; the SDK resets its stream id on close, so a late
timer fired renderInformativeUpdate against the closed stream and posted a
stale working card below the final answer. finalize() now cancels the gate
and the informative renderer refuses to run once final text is queued.
Refs #105872
* docs(channels): record the headline-vs-commentary ownership decision inline
Refs #105872
* style: oxfmt the late review-fix rounds
Four files from the final review-fix commits were never oxfmt-formatted and
failed the shared CI formatting step; baseline lowered for the one-line
telegram shrink.
Refs #105872
* fix(channels): harden progress draft lifecycle
* fix(channels): refresh repeated preamble items
* fix(plugin-sdk): expose progress lifecycle options
* style(auto-reply): simplify narrator reset
* docs(channels): refresh progress draft docs map
* fix(auto-reply): clear queued narrator request context
* fix(discord): cancel delayed progress gate at final
* docs: refresh plugin sdk api baseline
