* 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(mattermost): add thread.requireExplicitMention to opt out of thread auto-follow
Mattermost treats any reply in a thread the bot has participated in as an
implicit mention, so requireMention only gates the first message and the bot
then answers follow-ups addressed to other people for the participation TTL.
Slack exposes channels.slack.thread.requireExplicitMention for exactly this;
Mattermost had no equivalent and its strict schema rejected the key.
Add channels.mattermost.thread.requireExplicitMention (channel + per-account),
mirroring Slack. When set, thread participation no longer counts as a mention.
Default (unset/false) keeps today's auto-follow behavior unchanged.
Related: #108269
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(channels): add implicit mention policy foundation
* feat(channels): unify implicit mention policy
Co-authored-by: leon <dodoma0919@gmail.com>
* refactor(channels): keep implicit policy inside evaluator
* fix(channels): use exported implicit mention type
* chore(channels): satisfy extension lint
* fix(config): break implicit mention type cycle
* fix(plugin-sdk): account for implicit mention config export
* refactor(config): isolate implicit mention schema
* chore(plugin-sdk): align implicit mention surface budget
* fix(config): remove unused schema re-export
---------
Co-authored-by: leon <dodoma0919@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Phase 3 of #107237. Removes config.apply/config.patch/restart from the
regular-agent gateway tool (mirroring Phase 2's update.run removal); only
config.get and config.schema.lookup reads remain. Persistent config changes
and restarts now go exclusively through the human-approved openclaw
delegation path — closing the last unmediated agent config-write surface.
gateway stays owner-only/control-plane gated (config reads expose secrets and
host topology). Legacy setups can re-enable writes via the existing per-agent
tool allowlist; no new config key. Net -2271 LOC.
Refs #107237
* fix(config): reject zero-value resetArchiveRetention to prevent silent data loss
* fix: add braces to guard clauses for curly lint rule
* fix: normalize numeric values and cover pruneAfter fallback in migration
* fix: reject zero-value pruneAfter at schema level to close fallback gap
* fix: independently check and repair both retention fields in migration
* fix: split doctor diagnostics into field-specific rules and messages
* fix: remove unused local in migration test helper
* fix: repair 5 lint errors (curly braces, zero-fraction, narrow value)
* fix(doctor): rewrite zero resetArchiveRetention to false instead of deleting it
Deleting a zero resetArchiveRetention caused the runtime to fall back to
pruneAfter (default 30d), which contradicted the doctor output that
claimed archives would be kept indefinitely. Only an explicit false
value produces indefinite retention per the documented schema.
- P1: Rewrite zero resetArchiveRetention to false in the doctor
migration apply callback, matching the promised indefinite-retention
behavior.
- P3: Update the pruneAfter rule warning to describe eligible
stale/non-preserved session entries instead of "all sessions".
* fix(config): repair zero retention safely
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Co-authored-by: Peter Steinberger <peter@steipete.me>
A regular openclaw doctor run buried findings under healthy-state noise:
wizard banner, skills/plugins inventory boxes, healthy confirmations,
per-skill install hints, identical per-agent model-auth boxes, and one
warning line per stale plugin config path.
Doctor now prints problems and fixes only: security/Claude CLI notes are
silent when healthy, plugins box lists only errored ids, unusable skills
collapse to a count plus name list, model-auth findings aggregate across
agents with (agents: ...) attribution, and stale plugins.allow/deny/entries
references group into one line. Inventory stays in openclaw skills check,
openclaw plugins list, openclaw security audit, and openclaw models status.
docs/gateway/doctor.md updated.
Explains dispatching sessions to ephemeral cloud machines: what runs
where, cloudWorkers profile configuration (crabbox provider, setup
command, bundle vs npm install channels), sessions.dispatch usage, the
security model (closed ingress, minted credentials, host-key pinning,
epoch fencing, CAS transcripts), and troubleshooting from the live AWS
E2E.
Stops the legacy run-log dual-write, auto-imports remaining rows and drops
the table at state-DB open (table-presence guard: self-heals downgrade
round-trips), keeps the newest 2000 terminal runs per job in the ledger,
retires cron.runLog config via doctor, and moves live-run cancellation to
src/cron behind the shared task control seam.
Part 2 of 2 for #106041.
* feat(gateway-protocol): add session placement schema
Closed state discriminator for session execution placement (local/requested/provisioning/syncing/starting/active/draining/reconciling/reclaimed/failed), sessions.dispatch params, and worker-admission transcript/live cursor extensions. Swift protocol models mirror the schema.
* feat(state): add worker session placement table
worker_session_placements rows carry placement state, transition generation, worker ownership metadata, ACK cursors, and the turn claim columns used for atomic admission.
* feat(cloud-workers): add durable placement state machine store
SQLite-backed placement store split by concern: state table (placement-state), discriminated record types + shape invariants (placement-record), row codec + CAS transition values (placement-row-codec), atomic turn-claim admission/release/waiters (placement-turn-claims), and lifecycle CAS transitions (placement-store).
* feat(cloud-workers): sync workspaces and attach sessions to worker environments
Environment service session attachment + turn credentials, tunnel workspace commands over a dedicated SSH runner, and git/plain workspace sync into $HOME/.openclaw-worker/workspaces with an immutable manifest. Symlink escapes are rejected locally before transfer (macOS openrsync stat-fails them opaquely) and again by the remote manifest guard.
* feat(worker): run one-shot embedded turns from launch descriptors
Worker runtime executes a single embedded turn from a stdin launch descriptor and reports completed/failed/fenced on stdout for the gateway launcher. Terminal lifecycle live events are deferred past the final transcript flush; transcript projection helpers are shared via transcript-message instead of duplicated in the runtime.
* feat(cloud-workers): dispatch placements and route worker turns
Dispatch service drives local->requested->provisioning->syncing->starting->active with failure teardown (placement-dispatch-failure) and restart/runtime recovery incl. lost-worker reclaim (placement-dispatch-recovery). Worker turn launcher claims the placement turn atomically, builds a windowed launch descriptor (worker-turn-payload), runs the remote one-shot worker, and reconciles the committed transcript; agent runners route turns through the session placement admission provider.
* feat(gateway): expose session placement RPCs and startup reconciliation
sessions.dispatch RPC with lifecycle admission barriers, operator-facing placement projection on session listings, placement-aware session reset guard, and startup/interval reconciliation wiring for worker placements.
Config surface worktrees.cleanup.{maxCount,maxTotalSizeGb} (0/unset disables),
enforced by hourly gc, worktrees.gc RPC, and openclaw worktrees gc: least
recently active session/Workboard worktrees are snapshotted and removed until
count and total size fit. Manual worktrees, live locks, run leases, and active
session owners are never limit-evicted. Settings -> Worktrees gains a Cleanup
section with debounced, quota-aware stepper controls. Closes#106213.
agents.list[].model was agent-tunable while agents.defaults.model was
refused — the same capability gated by config shape (partially reverts
the defaults-spelling removal from #90145; token/auth/exec paths stay
protected). The bare refusal string also caused agents to misread the
injection boundary as an authorization failure and argue with the owner;
it now states the contract, the remedy, and the agent-tunable paths.
Guard moved to gateway-config-guard.ts (gateway-tool.ts 652->390).
Closes#106059
Peter Steinberger