ewilliams28/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-08-12 21:53:00 -06:00
Code Issues Packages Projects Releases Wiki Activity

feat(onboarding): recommend plugins and skills from installed apps (#109668)

Browse Source 
* 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
This commit is contained in:
Peter Steinberger
2026-07-17 14:07:59 +01:00
committed by GitHub
parent 8020dd3e08
commit da69daeb72
47 changed files with 2323 additions and 192 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/start/onboarding-redesign.md
+12 -12
View File
@@ -42,15 +42,15 @@ Design principles (decided, do not relitigate casually):
## Phases
| # | Phase | Surface | Status |
| --- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------ | -------------------------------------------------------------------------- |
| 1 | Installed-app plugin recommendations (scan, candidates, AI matcher, wizard step, `device.apps` node command) | service + classic wizard | PR [#109668](https://github.com/openclaw/openclaw/pull/109668) — in review |
| 2 | CLI custodian spine (question zero, discovery theater, auto-apply + hatch) | guided CLI | PR [#109841](https://github.com/openclaw/openclaw/pull/109841) — in review |
| 3 | Browser-first handoff (GUI-session detection, wait-for-dashboard-connect, TUI as fallback) | CLI → web | planned |
| 4 | Web custodian surface (option-card renderer shared with the question tool, scripted pre-AI states over `openclaw.chat`, post-wizard chat handoff) | Control UI | planned |
| 5 | Hatch and bootstrap (blank-agent creation, self-naming, self-drawn avatar via image-gen when available, recommendations as the last bootstrap step, self-learning opt-in) | agent bootstrap | planned |
| 6 | Custodian presence (pinned sidebar entry, Settings dock with event-reactive commentary, channel summon and agent-down recovery, weak-model script) | web + channels | planned |
| 7 | Resilience (custodian reachable on broken config, partial-surface salvage, auto-doctor) | gateway | follow-up |
| # | Phase | Surface | Status |
| --- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------- | --------------------------------------------------------------------------------------------------------------- |
| 1 | Installed-app plugin recommendations (scan, candidates, AI matcher, wizard step, `device.apps` node command) | classic + guided CLI | PR [#109668](https://github.com/openclaw/openclaw/pull/109668) — in review |
| 2 | CLI custodian spine (question zero, discovery theater, auto-apply + hatch) | guided CLI | merged ([`a83ed13204f1`](https://github.com/openclaw/openclaw/commit/a83ed13204f118adf1009e5ac88d5afe1905b86c)) |
| 3 | Browser-first handoff (GUI-session detection, wait-for-dashboard-connect, TUI as fallback) | CLI → web | planned |
| 4 | Web custodian surface (option-card renderer shared with the question tool, scripted pre-AI states over `openclaw.chat`, post-wizard chat handoff) | Control UI | planned |
| 5 | Hatch and bootstrap (blank-agent creation, self-naming, self-drawn avatar via image-gen when available, recommendations as the last bootstrap step, self-learning opt-in) | agent bootstrap | planned |
| 6 | Custodian presence (pinned sidebar entry, Settings dock with event-reactive commentary, channel summon and agent-down recovery, weak-model script) | web + channels | planned |
| 7 | Resilience (custodian reachable on broken config, partial-surface salvage, auto-doctor) | gateway | follow-up |
## Implementation notes per phase
@@ -63,9 +63,9 @@ Design principles (decided, do not relitigate casually):
the model rejects coincidental name overlaps.
- Node command `device.apps` (TS node-host, Android envelope parity), sharing
off by default; gateway kill switch `wizard.appRecommendations`.
- Delivery currently lives in the classic wizard
(`src/wizard/setup.app-recommendations.ts`); it re-targets to the bootstrap
tail in phase 5 (the service already takes an injectable inventory source).
- Delivery lives in the classic wizard and guided custodian flow
(`src/wizard/setup.app-recommendations.ts`); re-targeting to the bootstrap
tail remains phase 5 (the service already takes an injectable inventory source).
- Also fixed: custom `completeSetupInference` prompts no longer inherit the
32-token verification-probe output cap.
docs/start/wizard-cli-reference.md
+6
View File
@@ -351,6 +351,12 @@ Some channels are delivered as plugins. When selected during setup, the wizard
prompts to install the plugin (npm or local path) before channel configuration.
</Note>
### Installed app recommendations
After the model access check succeeds, classic interactive onboarding on macOS scans application names and bundle IDs without requesting macOS privacy permissions. It searches the official plugin catalogs and ClawHub, then asks the configured model to reject false name matches and recommend relevant plugins or skills. Recommended matches are selected by default; optional matches require an explicit selection.
The results screen lists the detected applications and shows: "App names were matched using your configured model and ClawHub search." Set `wizard.appRecommendations` to `false` to disable both this onboarding step and Gateway access to node app inventories. The scan is not used in quickstart or non-macOS onboarding.
## Non-interactive setup
`--non-interactive` requires `--accept-risk` (acknowledges that agents are