fix(doctor): warn when stale Codex overrides shadow OAuth (#40143)

* fix(doctor): warn on stale codex provider overrides

* test(doctor): cover stored codex oauth warning path

* fix: narrow codex override doctor warning (#40143) (thanks @bde1)

* test: sync doctor e2e mocks after health-flow move (#40143) (thanks @bde1)

---------

Co-authored-by: bde1 <bde1@users.noreply.github.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>

.agents/skills/openclaw-parallels-smoke/SKILL.md

@@ -16,6 +16,7 @@ Use this skill for Parallels guest workflows and smoke interpretation. Do not lo
 - Pass `--json` for machine-readable summaries.
 - Per-phase logs land under `/tmp/openclaw-parallels-*`.
 - Do not run local and gateway agent turns in parallel on the same fresh workspace or session.
+- Do not run multiple smoke lanes against the same guest family at once. Tahoe lanes share the host HTTP port, and Windows/Linux lanes can collide on snapshot restore/start state if two jobs touch the same VM concurrently.
 - If `main` is moving under active multi-agent work, prefer a detached worktree pinned to one commit for long Parallels suites. The smoke scripts now verify the packed tgz commit instead of live `git rev-parse HEAD`, but a pinned worktree still avoids noisy rebuild/version drift during reruns.
 - For `openclaw update --channel dev` lanes, remember the guest clones GitHub `main`, not your local worktree. If a local fix exists but the rerun still fails inside the cloned dev checkout, do not treat that as disproof of the fix until the branch has been pushed.
 - For `prlctl exec`, pass the VM name before `--current-user` (`prlctl exec "$VM" --current-user ...`), not the other way around.
@@ -33,6 +34,8 @@ Use this skill for Parallels guest workflows and smoke interpretation. Do not lo
 - The aggregate npm-update wrapper must resolve the Linux VM with the same Ubuntu fallback policy as `parallels-linux-smoke.sh` before both fresh and update lanes. Treat any Ubuntu guest with major version `>= 24` as acceptable when the exact default VM is missing, preferring the closest version match. On Peter's current host today, missing `Ubuntu 24.04.3 ARM64` should fall back to `Ubuntu 25.10`.
 - On macOS same-guest update checks, restart the gateway after the npm upgrade before `gateway status` / `agent`; launchd can otherwise report a loaded service while the old process has exited and the fresh process is not RPC-ready yet.
 - On Windows same-guest update checks, restart the gateway after the npm upgrade before `gateway status` / `agent`; in-place global npm updates can otherwise leave stale hashed `dist/*` module imports alive in the running service.
+- In those Windows same-guest update checks, do not treat one nonzero `openclaw gateway restart` as definitive failure. Current login-item restarts can report failure before the background service becomes observable again; follow with a longer RPC-ready wait and use `gateway start` only as a recovery step if readiness still never returns.
+- After that Windows restart, do not trust one `gateway status --deep --require-rpc` call after a fixed sleep. Retry the RPC-ready probe for roughly 30 seconds and log each attempt; current guests can keep port `18789` bound while the fresh RPC endpoint is still coming up.
 - For Windows same-guest update checks, prefer the done-file/log-drain PowerShell runner pattern over one long-lived `prlctl exec ... powershell -EncodedCommand ...` transport. The guest can finish successfully while the outer `prlctl exec` still hangs.
 - The Windows same-guest update helper should write stage markers to its log before long steps like tgz download and `npm install -g` so the outer progress monitor does not sit on `waiting for first log line` during healthy but quiet installs.
 - Linux same-guest update verification should also export `HOME=/root`, pass `OPENAI_API_KEY` via `prlctl exec ... /usr/bin/env`, and use `openclaw agent --local`; the fresh Linux baseline does not rely on persisted gateway credentials.
@@ -56,6 +59,8 @@ Use this skill for Parallels guest workflows and smoke interpretation. Do not lo
 - On Peter's Tahoe VM, `fresh-latest-march-2026` can hang in `prlctl snapshot-switch`; if restore times out there, rerun with `--snapshot-hint 'macOS 26.3.1 latest'` before blaming auth or the harness.
 - `parallels-macos-smoke.sh` now retries `snapshot-switch` once after force-stopping a stuck running/suspended guest. If Tahoe still times out after that recovery path, then treat it as a real Parallels/host issue and rerun manually.
 - The macOS smoke should include a dashboard load phase after gateway health: resolve the tokenized URL with `openclaw dashboard --no-open`, verify the served HTML contains the Control UI title/root shell, then open Safari and require an established localhost TCP connection from Safari to the gateway port.
+- For Tahoe `fresh.gateway-status`, prefer non-TTY `prlctl exec --current-user ... openclaw gateway status ...` plus a few short retries. `prlctl enter` can spam TTY control bytes and hang the phase log even when the CLI itself is healthy.
+- If a Tahoe lane times out in `fresh.first-agent-turn` and the phase log stops right after `__OPENCLAW_RC__:0` from `models set`, suspect the `prlctl enter` / `expect` wrapper before blaming auth or the model lane. That pattern means the first guest command finished but the transport never released for the next `guest_current_user_cli` call.
 - If a packaged install regresses with `500` on `/`, `/healthz`, or `__openclaw/control-ui-config.json` after `fresh.install-main` or `upgrade.install-main`, suspect bundled plugin runtime deps resolving from the package root `node_modules` rather than `dist/extensions/*/node_modules`. Repro quickly with a real `npm pack`/global install lane before blaming dashboard auth or Safari.
 - `prlctl exec` is fine for deterministic repo commands, but use the guest Terminal or `prlctl enter` when installer parity or shell-sensitive behavior matters.
 - Multi-word `openclaw agent --message ...` checks should go through a guest shell wrapper (`guest_current_user_sh` / `guest_current_user_cli` or `/bin/sh -lc ...`), not raw `prlctl exec ... node openclaw.mjs ...`, or the message can be split into extra argv tokens and Commander reports `too many arguments for 'agent'`.
@@ -86,7 +91,7 @@ Use this skill for Parallels guest workflows and smoke interpretation. Do not lo
 - Fresh Windows tgz install phases should also use the background PowerShell runner plus done-file/log-drain pattern; do not rely on one long-lived `prlctl exec ... powershell ... npm install -g` transport for package installs.
 - Windows release-to-dev helpers should log `where pnpm` before and after the update and require `where pnpm` to succeed post-update. That proves the updater installed or enabled `pnpm` itself instead of depending on a smoke-only bootstrap.
 - Fresh Windows ref-mode onboard should use the same background PowerShell runner plus done-file/log-drain pattern as the npm-update helper, including startup materialization checks, host-side timeouts on short poll `prlctl exec` calls, and retry-on-poll-failure behavior for transient transport flakes.
-- Fresh Windows daemon-health reachability should use a hello-only gateway probe and a longer per-probe timeout than the default local attach path; full health RPCs are too eager during initial startup on current main.
+- Fresh Windows daemon-health reachability should use `openclaw gateway probe --json` with a longer timeout and treat `ok: true` as success; full `gateway status --require-rpc` checks are too eager during initial startup on current main.
 - Fresh Windows ref-mode agent verification should set `OPENAI_API_KEY` in the PowerShell environment before invoking `openclaw.cmd agent`, for the same pairing-required fallback reason as macOS.
 - The standalone Windows upgrade smoke lane should stop the managed gateway after `upgrade.install-main` and before `upgrade.onboard-ref`. Restarting before onboard can leave the old process alive on the pre-onboard token while onboard rewrites `~/.openclaw/openclaw.json`, which then fails `gateway-health` with `unauthorized: gateway token mismatch`.
 - If standalone Windows upgrade fails with a gateway token mismatch but `pnpm test:parallels:npm-update` passes, trust the mismatch as a standalone ref-onboard ordering bug first; the npm-update helper does not re-run ref-mode onboard on the same guest.

.agents/skills/openclaw-qa-testing/SKILL.md

@@ -39,7 +39,6 @@ pnpm openclaw qa suite \
   --provider-mode live-openai \
   --model openai/gpt-5.4 \
   --alt-model openai/gpt-5.4 \
-  --fast \
   --output-dir .artifacts/qa-e2e/run-all-live-openai-<tag>
 ```
 

.github/labeler.yml

@@ -257,6 +257,10 @@
   - changed-files:
       - any-glob-to-any-file:
           - "extensions/acpx/**"
+"extensions: arcee":
+  - changed-files:
+      - any-glob-to-any-file:
+          - "extensions/arcee/**"
 "extensions: byteplus":
   - changed-files:
       - any-glob-to-any-file:

.github/workflows/ci.yml

@@ -753,6 +753,11 @@ jobs:
         continue-on-error: true
         run: pnpm run lint:extensions:bundled
 
+      - name: Run extension package boundary TypeScript check
+        id: extension_package_boundary_tsc
+        continue-on-error: true
+        run: pnpm run test:extensions:package-boundary
+
       - name: Enforce safe external URL opening policy
         id: no_raw_window_open
         continue-on-error: true
@@ -797,6 +802,7 @@ jobs:
           EXTENSION_RELATIVE_OUTSIDE_PACKAGE_BOUNDARY_OUTCOME: ${{ steps.extension_relative_outside_package_boundary.outcome }}
           EXTENSION_CHANNEL_LINT_OUTCOME: ${{ steps.extension_channel_lint.outcome }}
           EXTENSION_BUNDLED_LINT_OUTCOME: ${{ steps.extension_bundled_lint.outcome }}
+          EXTENSION_PACKAGE_BOUNDARY_TSC_OUTCOME: ${{ steps.extension_package_boundary_tsc.outcome }}
           NO_RAW_WINDOW_OPEN_OUTCOME: ${{ steps.no_raw_window_open.outcome }}
           CONTROL_UI_I18N_OUTCOME: ${{ steps.control_ui_i18n.outcome == 'skipped' && 'success' || steps.control_ui_i18n.outcome }}
           GATEWAY_WATCH_REGRESSION_OUTCOME: ${{ steps.gateway_watch_regression.outcome }}
@@ -820,6 +826,7 @@ jobs:
             "extension-relative-outside-package-boundary|$EXTENSION_RELATIVE_OUTSIDE_PACKAGE_BOUNDARY_OUTCOME" \
             "lint:extensions:channels|$EXTENSION_CHANNEL_LINT_OUTCOME" \
             "lint:extensions:bundled|$EXTENSION_BUNDLED_LINT_OUTCOME" \
+            "test:extensions:package-boundary|$EXTENSION_PACKAGE_BOUNDARY_TSC_OUTCOME" \
             "lint:ui:no-raw-window-open|$NO_RAW_WINDOW_OPEN_OUTCOME" \
             "ui:i18n:check|$CONTROL_UI_I18N_OUTCOME" \
             "gateway-watch-regression|$GATEWAY_WATCH_REGRESSION_OUTCOME"; do

CHANGELOG.md

@@ -4,36 +4,102 @@ Docs: https://docs.openclaw.ai
 
 ## Unreleased
 
+## 2026.4.7
+
 ### Changes
 
+- CLI/infer: add a first-class `openclaw infer ...` hub for provider-backed inference workflows across model, media, web, and embedding tasks. Thanks @Takhoffman.
+- Tools/media generation: auto-fallback across auth-backed image, music, and video providers by default, preserve intent during provider switches, remap size/aspect/resolution/duration hints to the closest supported option, and surface provider capabilities plus mode-aware video-to-video support.
+- Memory/wiki: restore the bundled `memory-wiki` stack with plugin, CLI, sync/query/apply tooling, memory-host integration, structured claim/evidence fields, compiled digest retrieval, claim-health linting, contradiction clustering, staleness dashboards, and freshness-weighted search. Thanks @vincentkoc.
 - Plugins/webhooks: add a bundled webhook ingress plugin so external automation can create and drive bound TaskFlows through per-route shared-secret endpoints. (#61892) Thanks @mbelinky.
-- Tools/media: document per-provider music and video generation capabilities, and add shared live video-to-video sweep coverage for providers that support local reference clips.
+- Gateway/sessions: add persisted compaction checkpoints plus Sessions UI branch/restore actions so operators can inspect and recover pre-compaction session state. (#62146) Thanks @scoootscooob.
+- Compaction: add pluggable compaction provider registry so plugins can replace the built-in summarization pipeline. Configure via `agents.defaults.compaction.provider`; falls back to LLM summarization on provider failure. (#56224) Thanks @DhruvBhatia0.
+- Agents/system prompt: add `agents.defaults.systemPromptOverride` for controlled prompt experiments plus heartbeat prompt-section controls so heartbeat runtime behavior can stay enabled without injecting heartbeat instructions every turn.
+- Providers/Google: add Gemma 4 model support and keep Google fallback resolution on the requested provider path so native Google Gemma routes work again. (#61507) Thanks @eyjohn.
+- Providers/Google: preserve explicit thinking-off semantics for Gemma 4 while still enabling Gemma reasoning support in compatibility wrappers. (#62127) Thanks @romgenie.
+- Providers/Arcee AI: add a bundled Arcee AI provider plugin with Trinity catalog entries, OpenRouter support, and updated onboarding/auth guidance. (#62068) Thanks @arthurbr11.
+- Providers/Anthropic: restore Claude CLI as the preferred local Anthropic path in onboarding, model-auth guidance, doctor flows, and Docker Claude CLI live lanes again.
+- Providers/Ollama: detect vision capability from the `/api/show` response and set image input on models that support it so Ollama vision models accept image attachments. (#62193) Thanks @BruceMacD.
+- Memory/dreaming: ingest redacted session transcripts into the dreaming corpus with per-day session-corpus notes, cursor checkpointing, and promotion/doctor support. (#62227) Thanks @vignesh07.
+- Providers/inferrs: add string-content compatibility for stricter OpenAI-compatible chat backends, document `inferrs` setup with a full config example, and add troubleshooting guidance for local backends that pass direct probes but fail on full agent-runtime prompts.
+- Agents/context engine: expose prompt-cache runtime context to context engines and keep current-turn prompt-cache usage aligned with the active attempt instead of stale prior-turn assistant state. (#62179) Thanks @jalehman.
+- Plugin SDK/context engines: pass `availableTools` and `citationsMode` into `assemble()`, and expose memory-artifact and memory-prompt seams so companion plugins and non-legacy context engines can consume active memory state without reaching into internals. Thanks @vincentkoc.
+- ACP/ACPX plugin: bump the bundled `acpx` pin to `0.5.1` so plugin-local installs and strict version checks pick up the latest published runtime release. (#62148) Thanks @onutc.
+- Discord/events: allow `event-create` to accept a cover image URL or local file path, load and validate PNG/JPG/GIF event cover media, and pass the encoded image payload through Discord admin action/runtime paths. (#60883) Thanks @bittoby.
 
 ### Fixes
 
-- Providers/Google: recognize Gemma model ids in native Google forward-compat resolution, keep the requested provider when cloning fallback templates, and force Gemma reasoning off so Gemma 4 routes stop failing through the Google catalog fallback. (#61507) Thanks @eyjohn.
-- Providers/Anthropic: skip `service_tier` injection for OAuth-authenticated stream wrapper requests so Claude OAuth requests stop failing with HTTP 401. (#60356) thanks @openperf.
-- Agents/exec: preserve explicit `host=node` routing under elevated defaults when `tools.exec.host=auto`, and fail loud on invalid elevated cross-host overrides. (#61739) Thanks @obviyus.
-- Agents/history: suppress commentary-only visible-text leaks in streaming and chat history views, and keep sanitized SSE history sequence numbers monotonic after transcript-only refreshes. (#61829) Thanks @100yenadmin.
-- Plugins/Windows: load plugin entrypoints through `file://` import specifiers on Windows without breaking plugin SDK alias resolution, fixing `ERR_UNSUPPORTED_ESM_URL_SCHEME` for absolute plugin paths. (#61832) Thanks @Zeesejo.
-- Discord/forwarding: recover forwarded referenced message text and attachments when Discord omits snapshot payloads, so forwarded-message relays keep the original content. (#61670) Thanks @artwalker.
-- Plugins/install: preserve plugin-schema defaults during fresh-install raw config validation so bundled plugin installs stop failing when required fields rely on schema defaults. (#61856) Thanks @SuperMarioYL.
-- Slack/threading: keep legacy thread stickiness for real replies when older callers omit `isThreadReply`, while still honoring `replyToMode` for Slack's auto-created top-level `thread_ts`. (#61835) Thanks @kaonash.
-- Agents/message tool: add a `read` plus `threadId` discoverability hint when the configured channel actions support threaded message reads.
-- Docs/i18n: remove the zh-CN homepage redirect override so Mintlify can resolve the localized Chinese homepage without self-redirecting `/zh-CN/index`.
-- Agents/heartbeat: stop truncating live session transcripts after no-op heartbeat acks, move heartbeat cleanup to prompt assembly and compaction, and keep post-filter context-engine ingestion aligned with the real session baseline. (#60998) Thanks @nxmxbbd.
+- CLI/infer: keep provider-backed infer behavior aligned with actual runtime execution by fixing explicit TTS override handling, profile-aware gateway TTS prefs resolution, per-request transcription `prompt`/`language` overrides, image output MIME/extension mismatches, configured web-search fallback behavior, and agent-vs-CLI web-search execution drift.
+- Plugins/media: when `plugins.allow` is set, capability fallback now merges bundled capability plugin ids into the allowlist (not only `plugins.entries`), so media understanding providers such as OpenAI-compatible STT load for voice transcription without requiring `openai` in `plugins.allow`. (#62205) Thanks @neeravmakwana.
+- Agents/history and replies: buffer phaseless OpenAI WS text until a real assistant phase arrives, keep replay and SSE history sequence tracking aligned, hide commentary and leaked tool XML from user-visible history, and keep history-based follow-up replies on `final_answer` text only. (#61729, #61747, #61829, #61855, #61954) Thanks @100yenadmin and contributors.
+- Control UI: show `/tts` audio replies in webchat, detect mistaken `?token=` auth links with the correct `#token=` hint, and keep Copy, Canvas, and mobile exec-approval UI from covering chat content on narrow screens. (#54842, #61514, #61598) Thanks @neeravmakwana.
+- iOS/gateway: replace string-matched connection error UI with structured gateway connection problems, preserve actionable pairing/auth failures over later generic disconnect noise, and surface reusable problem banners and details across onboarding, settings, and root status surfaces. (#62650) Thanks @ngutman.
+- TUI: route `/status` through the shared session-status command, keep commentary hidden in history, strip raw envelope metadata from async command notices, preserve fallback streaming before per-attempt failures finalize, and restore Kitty keyboard state on exit or fatal crashes. (#49130, #59985, #60043, #61463) Thanks @biefan and contributors.
+- iOS/Watch exec approvals: keep Apple Watch review and approval recovery working while the iPhone is locked or backgrounded, including reconnect recovery, pending approval persistence, notification cleanup, and APNs-backed watch refresh recovery. (#61757) Thanks @ngutman.
+- Agents/context overflow: combine oversized and aggregate tool-result recovery in one pass and restore a total-context overflow backstop so recoverable sessions retry instead of failing early. (#61651) Thanks @Takhoffman.
+- Auth/OpenAI Codex OAuth: reload fresh on-disk credentials inside the locked refresh path and retry once after `refresh_token_reused` rotates only the stored refresh token, so relogin/restart recovery stops getting stuck on stale cached auth state. Thanks @owen-ever.
+- Auth/OpenAI Codex OAuth: keep native `/model ...@profile` selections on the target session and honor explicit user-locked auth profiles even when per-agent auth order excludes them. (#62744) Thanks @jalehman.
+- Providers/Anthropic: preserve thinking blocks for Claude Opus 4.5+, Sonnet 4.5+, and newer Claude 4-family models so prompt-cache prefixes keep matching, and skip `service_tier` injection on OAuth-authenticated stream wrapper requests so Claude OAuth streaming stops failing with HTTP 401. (#60356, #61793)
+- Agents/Claude CLI: surface nested API error messages from structured CLI output so billing/auth/provider failures show the real provider error instead of an opaque CLI failure.
+- Agents/exec: preserve explicit `host=node` routing under elevated defaults when `tools.exec.host=auto`, fail loud on invalid elevated cross-host overrides, and keep `strictInlineEval` commands blocked after approval timeouts instead of falling through to automatic execution. (#61739) Thanks @obviyus.
+- Nodes/exec approvals: keep `host=node` POSIX transport shell wrappers (`/bin/sh -lc ...`) aligned with inner-command allowlist analysis so allowlisted scripts stop prompting unnecessarily, while Windows `cmd.exe` wrapper runs stay approval-gated. (#62401) Thanks @ngutman.
+- Nodes/exec approvals: keep Windows `cmd.exe /c` wrapper runs approval-gated even when `env` carriers, including env-assignment carriers, wrap the shell invocation. (#62439) Thanks @ngutman.
+- Gateway tool/exec config: block model-facing `gateway config.apply` and `config.patch` writes from changing exec approval paths such as `safeBins`, `safeBinProfiles`, `safeBinTrustedDirs`, and `strictInlineEval`, while still allowing unchanged structured values through. (#62001) Thanks @eleqtrizit.
+- Host exec/env sanitization: block dangerous Java, Rust, Cargo, Git, Kubernetes, cloud credential, config-path, and Helm env overrides so host-run tools cannot be redirected to attacker-chosen code, config, credentials, or repository state. (#59119, #62002, #62291) Thanks @eleqtrizit and contributors.
+- Commands/allowlist: require owner authorization for `/allowlist add` and `/allowlist remove` before channel resolution, so non-owner but command-authorized senders can no longer persistently rewrite allowlist policy state. (#62383) Thanks @pgondhi987.
+- Feishu/docx uploads: honor `tools.fs.workspaceOnly` for local `upload_file` and `upload_image` paths by forwarding workspace-constrained `localRoots` into the media loader, so docx uploads can no longer read host-local files outside the workspace when workspace-only mode is active. (#62369) Thanks @pgondhi987.
+- Network/fetch guard: drop request bodies and body-describing headers on cross-origin `307` and `308` redirects by default, so attacker-controlled redirect hops cannot receive secret-bearing POST payloads from SSRF-guarded fetch flows unless a caller explicitly opts in. (#62357) Thanks @pgondhi987.
+- Browser/SSRF: treat main-frame `document` redirect hops as navigations even when Playwright does not flag them as `isNavigationRequest()`, so strict private-network blocking still stops forbidden redirect pivots before the browser reaches the internal target. (#62355) Thanks @pgondhi987.
+- Browser/node invoke: block persistent browser profile create, reset, and delete mutations through `browser.proxy` on both gateway-forwarded `node.invoke` and the node-host proxy path, even when no profile allowlist is configured. (#60489)
+- Gateway/node pairing: require a fresh pairing request when a previously paired node reconnects with additional declared commands, and keep the live session pinned to the earlier approved command set until the upgrade is approved. (#62658) Thanks @eleqtrizit.
+- Gateway/auth: invalidate existing shared-token and password WebSocket sessions when the configured secret rotates, so stale authenticated sockets cannot stay attached after token or password changes. (#62350) Thanks @pgondhi987.
+- MS Teams/security: validate file-consent upload URLs against HTTPS, Microsoft/SharePoint host allowlists, and private-IP DNS checks before uploading attachments, blocking SSRF-style consent-upload abuse. (#23596)
+- Media/base64 decode guards: enforce byte limits before decoding missed base64-backed Teams, Signal, QQ Bot, and image-tool payloads so oversized inbound media and data URLs no longer bypass pre-decode size checks. (#62007) Thanks @eleqtrizit.
+- Runtime event trust: mark background `notifyOnExit` summaries, ACP parent-stream relays, and wake-hook payloads as untrusted system events so lower-trust runtime output no longer re-enters later turns as trusted `System:` text. (#62003)
+- Auto-reply/media: allow managed generated-media `MEDIA:` paths from normal reply text again while still blocking arbitrary host-local media and document paths, so generated media keep delivering without reopening host-path injection holes.
+- Gateway/status and containers: auto-bind to `0.0.0.0` inside Docker and Podman environments, and probe local TLS gateways over `wss://` with self-signed fingerprint forwarding so container startup and loopback TLS status checks work again. (#61818, #61935) Thanks @openperf and contributors.
+- Gateway/OpenAI-compatible HTTP: abort in-flight `/v1/chat/completions` and `/v1/responses` turns when clients disconnect so abandoned HTTP requests stop wasting agent runtime. (#54388) Thanks @Lellansin.
 - macOS/gateway version: strip trailing commit metadata from CLI version output before semver parsing so the Mac app recognizes installed gateway versions like `OpenClaw 2026.4.2 (d74a122)` again. (#61111) Thanks @oliviareid-svg.
-- Memory/dreaming: strip managed Light Sleep and REM blocks before daily-note ingestion so dreaming summaries stop re-ingesting their own staged output into new candidates. (#61720) Thanks @MonkeyLeeT.
-- Plugins/Windows: disable native Jiti loading for setup and doctor contract registries on Windows so onboarding and config-doctor plugin probes stop crashing with `ERR_UNSUPPORTED_ESM_URL_SCHEME`. (#61836, #61853)
-- Gateway/history: seed SSE startup history and raw transcript sequence tracking from one initial transcript snapshot so first history events cannot diverge from subsequent message sequence numbering. (#61855) Thanks @100yenadmin.
-- Agents/context overflow: combine oversized and aggregate tool-result recovery in one repair pass, and restore a total-context overflow backstop during tool loops so recoverable sessions retry instead of failing early. (#61651) Thanks @Takhoffman.
-- Gateway/containers: auto-bind to `0.0.0.0` during container startup for Docker and Podman compatibility, while keeping host-side status and doctor checks on the hardened loopback default when `gateway.bind` is unset. (#61818) Thanks @openperf.
-- TUI/status: route `/status` through the shared session-status command and move the old gateway-wide diagnostic summary to `/gateway-status` (`/gwstatus`). Thanks @vincentkoc.
-- Agents/history: use one shared assistant-visible sanitizer across embedded delivery and chat-history extraction so leaked `<tool_call>` and `<tool_result>` XML blocks stay hidden from user-facing replies. (#61729) Thanks @openperf.
-- Gateway/TUI: defer terminal chat finalization for per-attempt lifecycle errors so fallback retries keep streaming before the run is marked failed. (#60043) Thanks @jwchmodx.
-- TUI/command messages: strip inbound envelope metadata before rendering command/system messages so async completion notices stop leaking raw wrappers into the operator terminal. (#59985) Thanks @MoerAI.
-- TUI/terminal: restore Kitty keyboard protocol and `modifyOtherKeys` state on TUI exit and fatal CLI crashes so parent shells stop inheriting broken keyboard input after `openclaw tui` exits. (#49130) Thanks @biefan.
-- Docs/i18n: relocalize final localized-page links after translation so generated locale pages stop keeping stale English-root links when targets appear later in the same run. (#61796) thanks @hxy91819.
+- Sessions/model selection: resolve the explicitly selected session model separately from runtime fallback resolution so session status and live model switching stay aligned with the chosen model.
+- Discord/ACP bindings: canonicalize DM conversation identity across inbound messages, component interactions, native commands, and current-conversation binding resolution so `--bind here` in Discord DMs keeps routing follow-up replies to the bound agent instead of falling back to the default agent.
+- Discord: recover forwarded referenced message text and attachments when snapshots are missing, use `ws://` again for gateway monitor sockets, stop forcing a hardcoded temperature for Codex-backed auto-thread titles, and harden voice receive recovery so rapid speaker restarts keep their next utterance. (#41536, #61670) Thanks @artwalker and contributors.
+- Slack/thread mentions: add `channels.slack.thread.requireExplicitMention` so Slack channels that already require mentions can also require explicit `@bot` mentions inside bot-participated threads. (#58276) Thanks @praktika-engineer.
+- Slack/threading: keep legacy thread stickiness for real replies when older callers omit `isThreadReply`, while still honoring `replyToMode` for Slack's auto-created top-level `thread_ts`. (#61835) Thanks @kaonash.
+- Slack/media: keep attachment downloads on the SSRF-guarded dispatcher path so Slack media fetching works on Node 22 without dropping pinned transport enforcement. (#62239) Thanks @openperf.
+- Matrix/onboarding: add an invite auto-join setup step with explicit off warnings and strict stable-target validation so new Matrix accounts stop silently ignoring invited rooms and fresh DM-style invites unless operators opt in. (#62168) Thanks @gumadeiras.
+- Matrix/formatting: preserve multi-paragraph and loose-list rendering in Element so numbered and bulleted Markdown keeps their content attached to the correct list item. (#60997) Thanks @gucasbrg.
+- Telegram/doctor: keep top-level access-control fallback in place during multi-account normalization while still promoting legacy default auth into `accounts.default`, so existing named bots keep inherited allowlists without dropping the legacy default bot. (#62263) Thanks @obviyus.
+- Plugins/loaders: centralize bundled `dist/**` Jiti native-load policy and keep channel, public-surface, facade, and config-metadata loader seams off native Jiti on Windows so onboarding and configure flows stop tripping `ERR_UNSUPPORTED_ESM_URL_SCHEME`. (#62286) Thanks @chen-zhang-cs-code.
+- Plugins/channels: keep bundled channel artifact and secret-contract loading stable under lazy loading, preserve plugin-schema defaults during install, and fix Windows `file://` plus native-Jiti plugin loader paths so onboarding, doctor, `openclaw secret`, and bundled plugin installs work again. (#61832, #61836, #61853, #61856) Thanks @Zeesejo and contributors.
+- Plugins/ClawHub: verify downloaded plugin archives against version metadata SHA-256, fail closed when archive integrity metadata is missing or malformed, and tighten fallback ZIP verification so plugin installs cannot proceed on mismatched or incomplete ClawHub package metadata. (#60517) Thanks @mappel-nv.
+- Plugins/provider hooks: stop recursive provider snapshot loads from overflowing the stack during plugin initialization, while still preserving cached nested provider-hook results. (#61922, #61938, #61946, #61951)
+- Docker/plugins: stop forcing bundled plugin discovery to `/app/extensions` in runtime images so packaged installs use compiled `dist/extensions` artifacts again and Node 24 containers do not boot through source-only plugin entry paths. Fixes #62044. (#62316) Thanks @gumadeiras.
+- Providers/Ollama: honor the selected provider's `baseUrl` during streaming so multi-Ollama setups stop routing every stream to the first configured Ollama endpoint. (#61678)
+- Providers/Ollama: stop warning that Ollama could not be reached when discovery only sees empty default local stubs, while still keeping real explicit Ollama overrides loud when the endpoint is unreachable.
+- Providers/xAI: recognize `api.grok.x.ai` as an xAI-native endpoint again and keep legacy `x_search` auth resolution working so older xAI web-search configs continue to load. (#61377) Thanks @jjjojoj.
+- Providers/Mistral: send `reasoning_effort` for `mistral/mistral-small-latest` (Mistral Small 4) with thinking-level mapping, and mark the catalog entry as reasoning-capable so adjustable reasoning matches Mistral’s Chat Completions API. (#62162) Thanks @neeravmakwana.
+- OpenAI TTS/Groq: send `wav` to Groq-compatible speech endpoints, honor explicit `responseFormat` overrides on OpenAI-compatible paths, and only mark voice-note output as voice-compatible when the actual format is `opus`. (#62233) Thanks @neeravmakwana.
+- Tools/web_fetch and web_search: fix `TypeError: fetch failed` caused by undici 8.0 enabling HTTP/2 by default; pinned SSRF-guard dispatchers now explicitly set `allowH2: false` to restore HTTP/1.1 behavior and keep the custom DNS-pinning lookup compatible. (#61738, #61777) Thanks @zozo123.
+- Tools/web search/Exa: show Exa Search in onboarding and configure provider pickers again by marking the bundled Exa provider as setup-visible. Thanks @vincentkoc.
+- Memory/vector recall: surface explicit warnings when `sqlite-vec` is unavailable or vector writes are degraded, and strip managed Light Sleep and REM blocks before daily-note ingestion so memory indexing and dreaming stop reporting false-success or re-ingesting staged output. (#61720) Thanks @MonkeyLeeT.
+- Memory/dreaming: make Dreams config reads and writes respect the selected memory slot plugin instead of always targeting `memory-core`. (#62275) Thanks @SnowSky1.
+- QQ Bot/media: route gateway-side attachment and fallback downloads through guarded QQ/Tencent HTTPS fetches so QQ media handling no longer follows arbitrary remote hosts.
+- Browser/remote CDP: retry the DevTools websocket once after remote browser restarts so healthy remote browser profiles do not fail availability checks during CDP warm-up. (#57397) Thanks @ThanhNguyxn07.
+- UI/light mode: target both root and nested WebKit scrollbar thumbs in the light theme so page-level and container scrollbars stay visible on light backgrounds. (#61753) Thanks @chziyue.
+- Agents/subagents: honor `sessions_spawn(lightContext: true)` for spawned subagent runs by preserving lightweight bootstrap context through the gateway and embedded runner instead of silently falling back to full workspace bootstrap injection. (#62264) Thanks @theSamPadilla.
+- Cron: load `jobId` into `id` when the on-disk store omits `id`, matching doctor migration and fixing `unknown cron job id` for hand-edited `jobs.json`. (#62246) Thanks @neeravmakwana.
+- Agents/model fallback: classify minimal HTTP 404 API errors (for example `404 status code (no body)`) as `model_not_found` so assistant failures throw into the fallback chain instead of stopping at the first fallback candidate. (#62119) Thanks @neeravmakwana.
+- BlueBubbles/network: respect explicit private-network opt-out for loopback and private `serverUrl` values across account resolution, status probes, monitor startup, and attachment downloads, while keeping public-host attachment hostname pinning intact. (#59373) Thanks @jpreagan.
+- Agents/heartbeat: keep heartbeat runs pinned to the main session so active subagent transcripts are not overwritten by heartbeat status messages. (#61803) Thanks @100yenadmin.
+- Agents/heartbeat: respect disabled heartbeat prompt guidance so operators can suppress heartbeat prompt instructions without disabling heartbeat runtime behavior.
+- Agents/compaction: stop compaction-wait aborts from re-entering prompt failover and replaying completed tool turns. (#62600) Thanks @i-dentifier.
+- Approvals/runtime: move native approval lifecycle assembly into shared core bootstrap/runtime seams driven by channel capabilities and runtime contexts, and remove the legacy bundled approval fallback wiring. (#62135) Thanks @gumadeiras.
+- Security/fetch-guard: stop rejecting operator-configured proxy hostnames against the target-scoped hostname allowlist in SSRF-guarded fetches, restoring proxy-based media downloads for Telegram and other channels. (#62312) Thanks @ademczuk.
+- Logging: make `logging.level` and `logging.consoleLevel` honor the documented severity threshold ordering again, and keep child loggers inheriting the parent `minLevel`. (#44646) Thanks @zhumengzhu.
+- Agents/sessions_send: pass `threadId` through announce delivery so cross-session notifications land in the correct Telegram forum topic instead of the group's general thread. (#62758) Thanks @jalehman.
+- Daemon/systemd: keep sudo systemctl calls scoped to the invoking user when machine-scoped systemctl fails, while still avoiding machine fallback for permission-denied user bus errors. (#62337) Thanks @Aftabbs.
+- Docs/i18n: relocalize final localized-page links after translation and remove the zh-CN homepage redirect override so localized Mintlify pages resolve to the correct language roots again. (#61796) Thanks @hxy91819.
+- Agents/exec: keep timed-out shell-backgrounded commands on the failed path and point long-running jobs to exec background/yield sessions so process polling is only suggested for registered sessions.
 
 ## 2026.4.5
 
@@ -45,6 +111,7 @@ Docs: https://docs.openclaw.ai
 
 - Agents/video generation: add the built-in `video_generate` tool so agents can create videos through configured providers and return the generated media directly in the reply.
 - Agents/music generation: ignore unsupported optional hints such as `durationSeconds` with a warning instead of hard-failing requests on providers like Google Lyria.
+- Providers/Arcee AI: add a bundled Arcee AI provider plugin with `ARCEEAI_API_KEY` onboarding, Trinity model catalog (mini, large-preview, large-thinking), OpenAI-compatible API support, and OpenRouter as an alternative auth path. (#62068) Thanks @arthurbr11.
 - Providers/ComfyUI: add a bundled `comfy` workflow media plugin for local ComfyUI and Comfy Cloud workflows, including shared `image_generate`, `video_generate`, and workflow-backed `music_generate` support, with prompt injection, optional reference-image upload, live tests, and output download.
 - Tools/music generation: add the built-in `music_generate` tool with bundled Google (Lyria) and MiniMax providers plus workflow-backed Comfy support, including async task tracking and follow-up delivery of finished audio.
 - Providers: add bundled Qwen, Fireworks AI, and StepFun providers, plus MiniMax TTS, Ollama Web Search, and MiniMax Search integrations for chat, speech, and search workflows. (#60032, #55921, #59318, #54648)
@@ -171,6 +238,7 @@ Docs: https://docs.openclaw.ai
 - Feishu/reasoning: only expose streamed reasoning previews when the session is explicitly `reasoning:stream`, so hidden reasoning traces do not surface on normal streaming sessions. Thanks @vincentkoc.
 - Discord: keep REST, webhook, and monitor traffic on the configured proxy, preserve component-only media sends, honor `@everyone` and `@here` mention gates, keep ACK reactions on the active account, and split voice connect/playback timeouts so auto-join is more reliable. (#57465, #60361, #60345) Thanks @geekhuashan.
 - WhatsApp: restore `channels.whatsapp.blockStreaming` and reset watchdog timeouts after reconnect so quiet chats stop falling into reconnect loops. (#60007, #60069) Thanks @MonkeyLeeT and @mcaxtr.
+- Browser/security: re-run SSRF safety checks after interaction-driven navigations and before snapshot reads so click, submit, keyboard, and current-page snapshot flows fail closed on disallowed destinations. (#62023) Thanks @eleqtrizit.
 - Memory: keep `memory-core` builtin embedding registration on the already-registered path so selecting `memory-core` no longer recurses through plugin discovery and crashes during startup. (#61402) Thanks @ngutman.
 - Agents/tool results: keep large `read` outputs visible longer, preserve the latest `read` output when older tool output can absorb the overflow budget, and fall back to Pi's normal overflow compaction/retry path before replacing a fresh `read` with a compacted stub. Thanks @vincentkoc.
 - Memory/QMD: prefer modern `qmd collection add --glob`, accept newer single-line JSON hit metadata while keeping legacy line fields, refresh QMD docs/doctor install guidance and model-override guidance, and keep older QMD releases working. Thanks @vincentkoc.
@@ -213,6 +281,7 @@ Docs: https://docs.openclaw.ai
 - Providers/OpenRouter failover: classify `403 “Key limit exceeded”` spending-limit responses as billing so model fallback continues instead of stopping on generic auth. (#59892) Thanks @rockcent.
 - Providers/Anthropic: keep `claude-cli/*` auth on live Claude CLI credentials at runtime, avoid persisting stale bearer-token profiles, and suppress macOS Keychain prompts during non-interactive Claude CLI setup. (#61234) Thanks @darkamenosa.
 - Providers/Anthropic: when Claude CLI auth becomes the default, write a real `claude-cli` auth profile so local and gateway agent runs can use Claude CLI immediately without missing-API-key failures. Thanks @vincentkoc.
+- Memory/dreaming: make Dreams config reads and writes respect the selected memory slot plugin (including `doctor.memory.status` and Control UI fallback state) instead of always targeting `memory-core`. (#62275) Thanks @SnowSky1.
 - Providers/Anthropic Vertex: honor `cacheRetention: “long”` with the real 1-hour prompt-cache TTL on Vertex AI endpoints, and default `anthropic-vertex` cache retention like direct Anthropic. (#60888) Thanks @affsantos.
 - Agents/Anthropic: preserve native `toolu_*` replay ids on direct Anthropic and Anthropic Vertex paths so cache-sensitive history stops rewriting known-valid Anthropic tool-use ids. (#52612)
 - Providers/Google: add model-level `cacheRetention` support for direct Gemini system prompts by creating, reusing, and refreshing `cachedContents` automatically on Google AI Studio runs. (#51372) Thanks @rafaelmariano-glitch.
@@ -767,6 +836,7 @@ Docs: https://docs.openclaw.ai
 - Agents/compaction: surface safeguard-specific cancel reasons and relabel benign manual `/compact` no-op cases as skipped instead of failed. (#51072) Thanks @afurm.
 - Docs: add `pnpm docs:check-links:anchors` for Mintlify anchor validation while keeping `scripts/docs-link-audit.mjs` as the stable link-audit entrypoint. (#55912) Thanks @velvet-shark.
 - Tavily: mark outbound API requests with `X-Client-Source: openclaw` so Tavily can attribute OpenClaw-originated traffic. (#55335) Thanks @lakshyaag-tavily.
+- Plugins/hooks: add async `requireApproval` to `before_tool_call` hooks, letting plugins pause tool execution and prompt the user for approval via the exec approval overlay, Telegram buttons, Discord interactions, or the `/approve` command on any channel. The `/approve` command now handles both exec and plugin approvals with automatic fallback. (#55339) Thanks @vaclavbelak and @joshavant.
 
 ### Fixes
 
@@ -926,6 +996,7 @@ Docs: https://docs.openclaw.ai
 - Security/path resolution: prefer non-user-writable absolute helper binaries for OpenClaw CLI, ffmpeg, and OpenSSL resolution so PATH hijacks cannot replace trusted helpers with attacker-controlled executables.
 - Security/gateway command scopes: require `operator.admin` before Telegram target writeback and Talk Voice `/voice set` config writes persist through gateway message flows.
 - Security/OpenShell mirror: exclude workspace `hooks/` from mirror sync so untrusted sandbox files cannot become trusted host hooks on gateway startup.
+- Exec env policy: block Mercurial config redirects, Rust compiler wrappers, and GNU make flag env vars in host exec sanitization so inherited env and request-scoped overrides cannot redirect build-tool execution.
 
 ## 2026.3.24-beta.2
 
@@ -1703,6 +1774,9 @@ Docs: https://docs.openclaw.ai
 - macOS overlays: fix VoiceWake, Talk, and Notify overlay exclusivity crashes by removing shared `inout` visibility mutation from `OverlayPanelFactory.present`, and add a repeated Talk overlay smoke test. (#39275, #39321) Thanks @fellanH.
 - macOS Talk Mode: set the speech recognition request `taskHint` to `.dictation` for mic capture, and add regression coverage for the request defaults. (#38445) Thanks @dmiv.
 - macOS release packaging: default `scripts/package-mac-app.sh` to universal binaries for `BUILD_CONFIG=release`, and clarify that `scripts/package-mac-dist.sh` already produces the release zip + DMG. (#33891) Thanks @cgdusek.
+- Tools/web search: restore Perplexity OpenRouter/Sonar compatibility for legacy `OPENROUTER_API_KEY`, `sk-or-...`, and explicit `perplexity.baseUrl` / `model` setups while keeping direct Perplexity keys on the native Search API path. (#39937) Thanks @obviyus.
+- Tools/web search: restore Perplexity OpenRouter/Sonar compatibility for legacy `OPENROUTER_API_KEY`, `sk-or-...`, and explicit `perplexity.baseUrl` / `model` setups while keeping direct Perplexity keys on the native Search API path. (#39937) Thanks @obviyus.
+- Doctor/Codex OAuth: warn only for legacy `models.providers.openai-codex` transport overrides that can shadow the built-in Codex OAuth path, while leaving supported custom proxies and header-only overrides alone. (#40143) Thanks @bde1.
 - Hooks/session-memory: keep `/new` and `/reset` memory artifacts in the bound agent workspace and align saved reset session keys with that workspace when stale main-agent keys leak into the hook path. (#39875) thanks @rbutera.
 - Sessions/model switch: clear stale cached `contextTokens` when a session changes models so status and runtime paths recompute against the active model window. (#38044) thanks @yuweuii.
 - ACP/session history: persist transcripts for successful ACP child runs, preserve exact transcript text, record ACP spawned-session lineage, and keep spawn-time transcript-path persistence best-effort so history storage failures do not block execution. (#40137) thanks @mbelinky.

Dockerfile

@@ -62,9 +62,10 @@ RUN corepack enable
 WORKDIR /app
 
 COPY package.json pnpm-lock.yaml pnpm-workspace.yaml .npmrc ./
+COPY openclaw.mjs ./
 COPY ui/package.json ./ui/package.json
 COPY patches ./patches
-COPY scripts/postinstall-bundled-plugins.mjs scripts/npm-runner.mjs ./scripts/
+COPY scripts/postinstall-bundled-plugins.mjs scripts/npm-runner.mjs scripts/windows-cmd-helpers.mjs ./scripts/
 
 COPY --from=ext-deps /out/ ./${OPENCLAW_BUNDLED_PLUGIN_DIR}/
 
@@ -102,7 +103,19 @@ RUN pnpm qa:lab:build
 # Prune dev dependencies and strip build-only metadata before copying
 # runtime assets into the final image.
 FROM build AS runtime-assets
-RUN CI=true pnpm prune --prod && \
+ARG OPENCLAW_EXTENSIONS
+ARG OPENCLAW_BUNDLED_PLUGIN_DIR
+# Keep the install layer frozen, but allow prune to run against the full copied
+# workspace tree subset used during `pnpm install`. The build stage only copied
+# the root, `ui`, and opted-in plugin manifests into the install layer, so
+# prune must not rediscover unrelated workspaces from the later full source
+# copy.
+RUN printf 'packages:\n  - .\n  - ui\n' > /tmp/pnpm-workspace.runtime.yaml && \
+    for ext in $OPENCLAW_EXTENSIONS; do \
+      printf '  - %s/%s\n' "$OPENCLAW_BUNDLED_PLUGIN_DIR" "$ext" >> /tmp/pnpm-workspace.runtime.yaml; \
+    done && \
+    cp /tmp/pnpm-workspace.runtime.yaml pnpm-workspace.yaml && \
+    CI=true NPM_CONFIG_FROZEN_LOCKFILE=false pnpm prune --prod && \
     find dist -type f \( -name '*.d.ts' -o -name '*.d.mts' -o -name '*.d.cts' -o -name '*.map' \) -delete
 
 # ── Runtime base images ─────────────────────────────────────────
@@ -159,10 +172,6 @@ COPY --from=runtime-assets --chown=node:node /app/skills ./skills
 COPY --from=runtime-assets --chown=node:node /app/docs ./docs
 COPY --from=runtime-assets --chown=node:node /app/qa ./qa
 
-# In npm-installed Docker images, prefer the copied source extension tree for
-# bundled discovery so package metadata that points at source entries stays valid.
-ENV OPENCLAW_BUNDLED_PLUGINS_DIR=/app/${OPENCLAW_BUNDLED_PLUGIN_DIR}
-
 # Keep pnpm available in the runtime image for container-local workflows.
 # Use a shared Corepack home so the non-root `node` user does not need a
 # first-run network fetch when invoking pnpm.

README.md

@@ -89,7 +89,7 @@ New install? Start here: [Getting started](https://docs.openclaw.ai/start/gettin
 
 - **[OpenAI](https://openai.com/)** (ChatGPT/Codex)
 
-Model note: while many providers/models are supported, for the best experience and lower prompt-injection risk use the strongest latest-generation model available to you. See [Onboarding](https://docs.openclaw.ai/start/onboarding).
+Model note: while many providers and models are supported, prefer a current flagship model from the provider you trust and already use. See [Onboarding](https://docs.openclaw.ai/start/onboarding).
 
 ## Models (selection + auth)
 
@@ -371,7 +371,7 @@ Minimal `~/.openclaw/openclaw.json` (model + defaults):
 ```json5
 {
   agent: {
-    model: "anthropic/claude-opus-4-6",
+    model: "<provider>/<model-id>",
   },
 }
 ```

appcast.xml

@@ -6,7 +6,7 @@
             <title>2026.4.5</title>
             <pubDate>Mon, 06 Apr 2026 04:55:17 +0100</pubDate>
             <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
-            <sparkle:version>2026040501</sparkle:version>
+            <sparkle:version>2026040590</sparkle:version>
             <sparkle:shortVersionString>2026.4.5</sparkle:shortVersionString>
             <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
             <description><![CDATA[<h2>OpenClaw 2026.4.5</h2>
@@ -436,4 +436,4 @@
             <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.4.1/OpenClaw-2026.4.1.zip" length="25841903" type="application/octet-stream" sparkle:edSignature="0TPiyshScmwDbgs626JU08NOUUFJmIsVFa5g0xmizfl64Fr+IoT4l/dkXarFqbZAJidtj5WN7Bff7fG8ye/7AA=="/>
         </item>
     </channel>
-</rss>
+</rss>

apps/android/app/build.gradle.kts

@@ -65,8 +65,8 @@ android {
         applicationId = "ai.openclaw.app"
         minSdk = 31
         targetSdk = 36
-        versionCode = 2026040601
-        versionName = "2026.4.6"
+        versionCode = 2026040701
+        versionName = "2026.4.7"
         ndk {
             // Support all major ABIs — native libs are tiny (~47 KB per ABI)
             abiFilters += listOf("armeabi-v7a", "arm64-v8a", "x86", "x86_64")

apps/ios/Config/Signing.xcconfig

@@ -3,19 +3,23 @@
 
 OPENCLAW_IOS_DEFAULT_TEAM = Y5PE65HELJ
 OPENCLAW_IOS_SELECTED_TEAM = $(OPENCLAW_IOS_DEFAULT_TEAM)
+OPENCLAW_DEVELOPMENT_TEAM = $(OPENCLAW_IOS_SELECTED_TEAM)
+OPENCLAW_CODE_SIGN_STYLE = Automatic
 OPENCLAW_APP_BUNDLE_ID = ai.openclaw.client
 OPENCLAW_WATCH_APP_BUNDLE_ID = ai.openclaw.client.watchkitapp
 OPENCLAW_WATCH_EXTENSION_BUNDLE_ID = ai.openclaw.client.watchkitapp.extension
 OPENCLAW_ACTIVITY_WIDGET_BUNDLE_ID = ai.openclaw.client.activitywidget
+OPENCLAW_WATCH_APP_PROFILE =
+OPENCLAW_WATCH_EXTENSION_PROFILE =
 
 // Local contributors can override this by running scripts/ios-configure-signing.sh.
 // Keep include after defaults: xcconfig is evaluated top-to-bottom.
 #include? "../.local-signing.xcconfig"
 #include? "../LocalSigning.xcconfig"
 
-CODE_SIGN_STYLE = Automatic
+CODE_SIGN_STYLE = $(OPENCLAW_CODE_SIGN_STYLE)
 CODE_SIGN_IDENTITY = Apple Development
-DEVELOPMENT_TEAM = $(OPENCLAW_IOS_SELECTED_TEAM)
+DEVELOPMENT_TEAM = $(OPENCLAW_DEVELOPMENT_TEAM)
 
-// Let Xcode manage provisioning for the selected local team.
+// Let Xcode manage provisioning for the selected local team unless a local override pins one.
 PROVISIONING_PROFILE_SPECIFIER =

apps/ios/Config/Version.xcconfig

@@ -1,8 +1,8 @@
 // Shared iOS version defaults.
 // Generated overrides live in build/Version.xcconfig (git-ignored).
 
-OPENCLAW_GATEWAY_VERSION = 2026.4.6
-OPENCLAW_MARKETING_VERSION = 2026.4.6
-OPENCLAW_BUILD_VERSION = 2026040601
+OPENCLAW_GATEWAY_VERSION = 2026.4.7
+OPENCLAW_MARKETING_VERSION = 2026.4.7
+OPENCLAW_BUILD_VERSION = 2026040701
 
 #include? "../build/Version.xcconfig"

apps/ios/LocalSigning.xcconfig.example

@@ -13,3 +13,5 @@ OPENCLAW_WATCH_EXTENSION_BUNDLE_ID = ai.openclaw.client.watchkitapp.extension
 // Leave empty with automatic signing.
 OPENCLAW_APP_PROFILE =
 OPENCLAW_SHARE_PROFILE =
+OPENCLAW_WATCH_APP_PROFILE =
+OPENCLAW_WATCH_EXTENSION_PROFILE =

apps/ios/README.md

@@ -148,6 +148,9 @@ pnpm ios:beta
 - Local/manual builds default to `OpenClawPushTransport=direct` and `OpenClawPushDistribution=local`.
 - Your selected team/profile must support Push Notifications for the app bundle ID you are signing.
 - If push capability or provisioning is wrong, APNs registration fails at runtime (check Xcode logs for `APNs registration failed`).
+- The gateway host also needs direct APNs auth configured separately with `OPENCLAW_APNS_TEAM_ID`, `OPENCLAW_APNS_KEY_ID`, and either `OPENCLAW_APNS_PRIVATE_KEY_P8` or `OPENCLAW_APNS_PRIVATE_KEY_PATH`.
+- Recommended gateway-host storage for the APNs `.p8` file is `~/.openclaw/credentials/apns/AuthKey_<KEYID>.p8` with restrictive permissions, then point `OPENCLAW_APNS_PRIVATE_KEY_PATH` at that file.
+- `apps/ios/fastlane/.env` only covers App Store Connect / Fastlane auth; it does not provide gateway APNs credentials for local direct-push testing.
 - Debug builds default to `OpenClawPushAPNsEnvironment=sandbox`; Release builds default to `production`.
 
 ## APNs Expectations For Official Builds

apps/ios/Sources/Gateway/GatewayConnectionIssue.swift

@@ -1,4 +1,5 @@
 import Foundation
+import OpenClawKit
 
 enum GatewayConnectionIssue: Equatable {
     case none
@@ -29,6 +30,37 @@ enum GatewayConnectionIssue: Equatable {
         return false
     }
 
+    static func detect(problem: GatewayConnectionProblem?) -> Self {
+        guard let problem else { return .none }
+        if problem.needsPairingApproval {
+            return .pairingRequired(requestId: problem.requestId)
+        }
+        if problem.needsCredentialUpdate {
+            return problem.kind == .gatewayAuthTokenMissing ? .tokenMissing : .unauthorized
+        }
+        switch problem.kind {
+        case .deviceIdentityRequired,
+            .deviceSignatureExpired,
+            .deviceNonceRequired,
+            .deviceNonceMismatch,
+            .deviceSignatureInvalid,
+            .devicePublicKeyInvalid,
+            .deviceIdMismatch,
+            .tailscaleIdentityMissing,
+            .tailscaleProxyMissing,
+            .tailscaleWhoisFailed,
+            .tailscaleIdentityMismatch,
+            .authRateLimited:
+            return .unauthorized
+        case .timeout, .connectionRefused, .reachabilityFailed, .websocketCancelled:
+            return .network
+        case .unknown:
+            return .unknown(problem.message)
+        default:
+            return .none
+        }
+    }
+
     static func detect(from statusText: String) -> Self {
         let trimmed = statusText.trimmingCharacters(in: .whitespacesAndNewlines)
         guard !trimmed.isEmpty else { return .none }

apps/ios/Sources/Gateway/GatewayProblemView.swift

@@ -0,0 +1,232 @@
+import OpenClawKit
+import SwiftUI
+import UIKit
+
+struct GatewayProblemBanner: View {
+    let problem: GatewayConnectionProblem
+    var primaryActionTitle: String?
+    var onPrimaryAction: (() -> Void)?
+    var onShowDetails: (() -> Void)?
+
+    var body: some View {
+        VStack(alignment: .leading, spacing: 12) {
+            HStack(alignment: .top, spacing: 10) {
+                Image(systemName: self.iconName)
+                    .font(.headline.weight(.semibold))
+                    .foregroundStyle(self.tint)
+                    .frame(width: 20)
+                    .padding(.top, 2)
+
+                VStack(alignment: .leading, spacing: 6) {
+                    HStack(alignment: .firstTextBaseline, spacing: 8) {
+                        Text(self.problem.title)
+                            .font(.subheadline.weight(.semibold))
+                            .multilineTextAlignment(.leading)
+                        Spacer(minLength: 0)
+                        Text(self.ownerLabel)
+                            .font(.caption.weight(.semibold))
+                            .foregroundStyle(.secondary)
+                    }
+
+                    Text(self.problem.message)
+                        .font(.footnote)
+                        .foregroundStyle(.secondary)
+                        .fixedSize(horizontal: false, vertical: true)
+
+                    if let requestId = self.problem.requestId {
+                        Text("Request ID: \(requestId)")
+                            .font(.system(.caption, design: .monospaced).weight(.medium))
+                            .foregroundStyle(.secondary)
+                            .textSelection(.enabled)
+                    }
+                }
+            }
+
+            HStack(spacing: 10) {
+                if let primaryActionTitle, let onPrimaryAction {
+                    Button(primaryActionTitle, action: onPrimaryAction)
+                        .buttonStyle(.borderedProminent)
+                        .controlSize(.small)
+                }
+                if let onShowDetails {
+                    Button("Details", action: onShowDetails)
+                        .buttonStyle(.bordered)
+                        .controlSize(.small)
+                }
+            }
+        }
+        .frame(maxWidth: .infinity, alignment: .leading)
+        .padding(14)
+        .background(
+            .thinMaterial,
+            in: RoundedRectangle(cornerRadius: 16, style: .continuous)
+        )
+    }
+
+    private var iconName: String {
+        switch self.problem.kind {
+        case .pairingRequired,
+            .pairingRoleUpgradeRequired,
+            .pairingScopeUpgradeRequired,
+            .pairingMetadataUpgradeRequired:
+            return "person.crop.circle.badge.clock"
+        case .timeout, .connectionRefused, .reachabilityFailed, .websocketCancelled:
+            return "wifi.exclamationmark"
+        case .deviceIdentityRequired,
+            .deviceSignatureExpired,
+            .deviceNonceRequired,
+            .deviceNonceMismatch,
+            .deviceSignatureInvalid,
+            .devicePublicKeyInvalid,
+            .deviceIdMismatch:
+            return "lock.shield"
+        default:
+            return "exclamationmark.triangle.fill"
+        }
+    }
+
+    private var tint: Color {
+        switch self.problem.kind {
+        case .pairingRequired,
+            .pairingRoleUpgradeRequired,
+            .pairingScopeUpgradeRequired,
+            .pairingMetadataUpgradeRequired:
+            return .orange
+        case .timeout, .connectionRefused, .reachabilityFailed, .websocketCancelled:
+            return .yellow
+        default:
+            return .red
+        }
+    }
+
+    private var ownerLabel: String {
+        switch self.problem.owner {
+        case .gateway:
+            return "Fix on gateway"
+        case .iphone:
+            return "Fix on iPhone"
+        case .both:
+            return "Check both"
+        case .network:
+            return "Check network"
+        case .unknown:
+            return "Needs attention"
+        }
+    }
+}
+
+struct GatewayProblemDetailsSheet: View {
+    @Environment(\.dismiss) private var dismiss
+
+    let problem: GatewayConnectionProblem
+    var primaryActionTitle: String?
+    var onPrimaryAction: (() -> Void)?
+
+    @State private var copyFeedback: String?
+
+    var body: some View {
+        NavigationStack {
+            List {
+                Section {
+                    VStack(alignment: .leading, spacing: 10) {
+                        Text(self.problem.title)
+                            .font(.title3.weight(.semibold))
+                        Text(self.problem.message)
+                            .font(.body)
+                            .foregroundStyle(.secondary)
+                        Text(self.ownerSummary)
+                            .font(.footnote.weight(.semibold))
+                            .foregroundStyle(.secondary)
+                    }
+                    .frame(maxWidth: .infinity, alignment: .leading)
+                    .padding(.vertical, 4)
+                }
+
+                if let requestId = self.problem.requestId {
+                    Section("Request") {
+                        Text(verbatim: requestId)
+                            .font(.system(.body, design: .monospaced))
+                            .textSelection(.enabled)
+                        Button("Copy request ID") {
+                            UIPasteboard.general.string = requestId
+                            self.copyFeedback = "Copied request ID"
+                        }
+                    }
+                }
+
+                if let actionCommand = self.problem.actionCommand {
+                    Section("Gateway command") {
+                        Text(verbatim: actionCommand)
+                            .font(.system(.body, design: .monospaced))
+                            .textSelection(.enabled)
+                        Button("Copy command") {
+                            UIPasteboard.general.string = actionCommand
+                            self.copyFeedback = "Copied command"
+                        }
+                    }
+                }
+
+                if let docsURL = self.problem.docsURL {
+                    Section("Help") {
+                        Link(destination: docsURL) {
+                            Label("Open docs", systemImage: "book")
+                        }
+                        Text(verbatim: docsURL.absoluteString)
+                            .font(.footnote)
+                            .foregroundStyle(.secondary)
+                            .textSelection(.enabled)
+                    }
+                }
+
+                if let technicalDetails = self.problem.technicalDetails {
+                    Section("Technical details") {
+                        Text(verbatim: technicalDetails)
+                            .font(.system(.footnote, design: .monospaced))
+                            .foregroundStyle(.secondary)
+                            .textSelection(.enabled)
+                    }
+                }
+
+                if let copyFeedback {
+                    Section {
+                        Text(copyFeedback)
+                            .font(.footnote)
+                            .foregroundStyle(.secondary)
+                    }
+                }
+            }
+            .navigationTitle("Connection problem")
+            .navigationBarTitleDisplayMode(.inline)
+            .toolbar {
+                ToolbarItem(placement: .topBarLeading) {
+                    if let primaryActionTitle, let onPrimaryAction {
+                        Button(primaryActionTitle) {
+                            self.dismiss()
+                            onPrimaryAction()
+                        }
+                    }
+                }
+                ToolbarItem(placement: .topBarTrailing) {
+                    Button("Done") {
+                        self.dismiss()
+                    }
+                }
+            }
+        }
+    }
+
+    private var ownerSummary: String {
+        switch self.problem.owner {
+        case .gateway:
+            return "Primary fix: gateway"
+        case .iphone:
+            return "Primary fix: this iPhone"
+        case .both:
+            return "Primary fix: check both this iPhone and the gateway"
+        case .network:
+            return "Primary fix: network or remote access"
+        case .unknown:
+            return "Primary fix: review details and retry"
+        }
+    }
+}

apps/ios/Sources/Gateway/GatewayQuickSetupSheet.swift

@@ -8,6 +8,7 @@ struct GatewayQuickSetupSheet: View {
     @AppStorage("onboarding.quickSetupDismissed") private var quickSetupDismissed: Bool = false
     @State private var connecting: Bool = false
     @State private var connectError: String?
+    @State private var showGatewayProblemDetails: Bool = false
 
     var body: some View {
         NavigationStack {
@@ -15,6 +16,14 @@ struct GatewayQuickSetupSheet: View {
                 Text("Connect to a Gateway?")
                     .font(.title2.bold())
 
+                if let gatewayProblem = self.appModel.lastGatewayProblem {
+                    GatewayProblemBanner(
+                        problem: gatewayProblem,
+                        onShowDetails: {
+                            self.showGatewayProblemDetails = true
+                        })
+                }
+
                 if let candidate = self.bestCandidate {
                     VStack(alignment: .leading, spacing: 6) {
                         Text(verbatim: candidate.name)
@@ -27,7 +36,7 @@ struct GatewayQuickSetupSheet: View {
                             // Use verbatim strings so Bonjour-provided values can't be interpreted as
                             // localized format strings (which can crash with Objective-C exceptions).
                             Text(verbatim: "Discovery: \(self.gatewayController.discoveryStatusText)")
-                            Text(verbatim: "Status: \(self.appModel.gatewayStatusText)")
+                            Text(verbatim: "Status: \(self.appModel.gatewayDisplayStatusText)")
                             Text(verbatim: "Node: \(self.appModel.nodeStatusText)")
                             Text(verbatim: "Operator: \(self.appModel.operatorStatusText)")
                         }
@@ -104,6 +113,11 @@ struct GatewayQuickSetupSheet: View {
                 }
             }
         }
+        .sheet(isPresented: self.$showGatewayProblemDetails) {
+            if let gatewayProblem = self.appModel.lastGatewayProblem {
+                GatewayProblemDetailsSheet(problem: gatewayProblem)
+            }
+        }
     }
 
     private var bestCandidate: GatewayDiscoveryModel.DiscoveredGateway? {

apps/ios/Sources/Onboarding/GatewayOnboardingView.swift

@@ -376,7 +376,7 @@ private struct ConnectionStatusBox: View {
         gatewayController: GatewayConnectionController
     ) -> [String] {
         var lines: [String] = [
-            "gateway: \(appModel.gatewayStatusText)",
+            "gateway: \(appModel.gatewayDisplayStatusText)",
             "discovery: \(gatewayController.discoveryStatusText)",
         ]
         lines.append("server: \(appModel.gatewayServerName ?? "—")")

apps/ios/Sources/Onboarding/OnboardingWizardView.swift

@@ -69,6 +69,7 @@ struct OnboardingWizardView: View {
     @State private var showQRScanner: Bool = false
     @State private var scannerError: String?
     @State private var selectedPhoto: PhotosPickerItem?
+    @State private var showGatewayProblemDetails: Bool = false
     @State private var lastPairingAutoResumeAttemptAt: Date?
     private static let pairingAutoResumeTicker = Timer.publish(every: 2.0, on: .main, in: .common).autoconnect()
 
@@ -86,6 +87,10 @@ struct OnboardingWizardView: View {
         self.step == .intro || self.step == .welcome || self.step == .success
     }
 
+    private var currentProblem: GatewayConnectionProblem? {
+        self.appModel.lastGatewayProblem
+    }
+
     var body: some View {
         NavigationStack {
             Group {
@@ -216,6 +221,16 @@ struct OnboardingWizardView: View {
                 }
             }
         }
+        .sheet(isPresented: self.$showGatewayProblemDetails) {
+            if let currentProblem = self.currentProblem {
+                GatewayProblemDetailsSheet(
+                    problem: currentProblem,
+                    primaryActionTitle: "Retry",
+                    onPrimaryAction: {
+                        Task { await self.retryLastAttempt() }
+                    })
+            }
+        }
         .onAppear {
             self.initializeState()
         }
@@ -250,39 +265,11 @@ struct OnboardingWizardView: View {
         .onChange(of: self.gatewayPassword) { _, newValue in
             self.saveGatewayCredentials(token: self.gatewayToken, password: newValue)
         }
+        .onChange(of: self.appModel.lastGatewayProblem) { _, newValue in
+            self.updateConnectionIssue(problem: newValue, statusText: self.appModel.gatewayStatusText)
+        }
         .onChange(of: self.appModel.gatewayStatusText) { _, newValue in
-            let next = GatewayConnectionIssue.detect(from: newValue)
-            // Avoid "flip-flopping" the UI by clearing actionable issues when the underlying connection
-            // transitions through intermediate statuses (e.g. Offline/Connecting while reconnect churns).
-            if self.issue.needsPairing, next.needsPairing {
-                // Keep the requestId sticky even if the status line omits it after we pause.
-                let mergedRequestId = next.requestId ?? self.issue.requestId ?? self.pairingRequestId
-                self.issue = .pairingRequired(requestId: mergedRequestId)
-            } else if self.issue.needsPairing, !next.needsPairing {
-                // Ignore non-pairing statuses until the user explicitly retries/scans again, or we connect.
-            } else if self.issue.needsAuthToken, !next.needsAuthToken, !next.needsPairing {
-                // Same idea for auth: once we learn credentials are missing/rejected, keep that sticky until
-                // the user retries/scans again or we successfully connect.
-            } else {
-                self.issue = next
-            }
-
-            if let requestId = next.requestId, !requestId.isEmpty {
-                self.pairingRequestId = requestId
-            }
-
-            // If the gateway tells us auth is missing/rejected, stop reconnect churn until the user intervenes.
-            if next.needsAuthToken {
-                self.appModel.gatewayAutoReconnectEnabled = false
-            }
-
-            if self.issue.needsAuthToken || self.issue.needsPairing {
-                self.step = .auth
-            }
-            if !newValue.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty {
-                self.connectMessage = newValue
-                self.statusLine = newValue
-            }
+            self.updateConnectionIssue(problem: self.appModel.lastGatewayProblem, statusText: newValue)
         }
         .onChange(of: self.appModel.gatewayServerName) { _, newValue in
             guard newValue != nil else { return }
@@ -509,7 +496,7 @@ struct OnboardingWizardView: View {
             Section {
                 LabeledContent("Mode", value: selectedMode.title)
                 LabeledContent("Discovery", value: self.gatewayController.discoveryStatusText)
-                LabeledContent("Status", value: self.appModel.gatewayStatusText)
+                LabeledContent("Status", value: self.appModel.gatewayDisplayStatusText)
                 LabeledContent("Progress", value: self.statusLine)
             } header: {
                 Text("Status")
@@ -612,7 +599,17 @@ struct OnboardingWizardView: View {
                     .autocorrectionDisabled()
                 SecureField("Gateway Password", text: self.$gatewayPassword)
 
-                if self.issue.needsAuthToken {
+                if let problem = self.currentProblem {
+                    GatewayProblemBanner(
+                        problem: problem,
+                        primaryActionTitle: "Retry connection",
+                        onPrimaryAction: {
+                            Task { await self.retryLastAttempt() }
+                        },
+                        onShowDetails: {
+                            self.showGatewayProblemDetails = true
+                        })
+                } else if self.issue.needsAuthToken {
                     Text("Gateway rejected credentials. Scan a fresh QR code or update token/password.")
                         .font(.footnote)
                         .foregroundStyle(.secondary)
@@ -635,14 +632,15 @@ struct OnboardingWizardView: View {
                     Text("Pairing Approval")
                 } footer: {
                     let requestLine: String = {
-                        if let id = self.issue.requestId, !id.isEmpty {
+                        if let id = self.currentProblem?.requestId ?? self.issue.requestId, !id.isEmpty {
                             return "Request ID: \(id)"
                         }
                         return "Request ID: check `openclaw devices list`."
                     }()
+                    let commandLine = self.currentProblem?.actionCommand ?? "openclaw devices approve <requestId>"
                     Text(
                         "Approve this device on the gateway.\n"
-                            + "1) `openclaw devices approve` (or `openclaw devices approve <requestId>`)\n"
+                            + "1) `\(commandLine)`\n"
                             + "2) `/pair approve` in your OpenClaw chat\n"
                             + "\(requestLine)\n"
                             + "OpenClaw will also retry automatically when you return to this app.")
@@ -824,6 +822,45 @@ struct OnboardingWizardView: View {
         self.resumeAfterPairingApprovalInBackground()
     }
 
+    private func updateConnectionIssue(problem: GatewayConnectionProblem?, statusText: String) {
+        let next = GatewayConnectionIssue.detect(problem: problem)
+        let fallback = next == .none ? GatewayConnectionIssue.detect(from: statusText) : next
+
+        // Avoid "flip-flopping" the UI by clearing actionable issues when the underlying connection
+        // transitions through intermediate statuses (e.g. Offline/Connecting while reconnect churns).
+        if self.issue.needsPairing, fallback.needsPairing {
+            let mergedRequestId = fallback.requestId ?? self.issue.requestId ?? self.pairingRequestId
+            self.issue = .pairingRequired(requestId: mergedRequestId)
+        } else if self.issue.needsPairing, !fallback.needsPairing {
+            // Ignore non-pairing statuses until the user explicitly retries/scans again, or we connect.
+        } else if self.issue.needsAuthToken, !fallback.needsAuthToken, !fallback.needsPairing {
+            // Same idea for auth: once we learn credentials are missing/rejected, keep that sticky until
+            // the user retries/scans again or we successfully connect.
+        } else {
+            self.issue = fallback
+        }
+
+        if let requestId = problem?.requestId ?? fallback.requestId, !requestId.isEmpty {
+            self.pairingRequestId = requestId
+        }
+
+        if self.issue.needsAuthToken || self.issue.needsPairing || problem?.pauseReconnect == true {
+            self.step = .auth
+        }
+
+        if let problem {
+            self.connectMessage = problem.message
+            self.statusLine = problem.message
+            return
+        }
+
+        let trimmedStatus = statusText.trimmingCharacters(in: .whitespacesAndNewlines)
+        if !trimmedStatus.isEmpty {
+            self.connectMessage = trimmedStatus
+            self.statusLine = trimmedStatus
+        }
+    }
+
     private func detectQRCode(from data: Data) -> String? {
         guard let ciImage = CIImage(data: data) else { return nil }
         let detector = CIDetector(

apps/ios/Sources/OpenClawApp.swift

@@ -15,6 +15,11 @@ private struct PendingWatchPromptAction {
 
 private typealias PendingExecApprovalPrompt = ExecApprovalNotificationPrompt
 
+@MainActor
+enum OpenClawAppModelRegistry {
+    static var appModel: NodeAppModel?
+}
+
 @MainActor
 final class OpenClawAppDelegate: NSObject, UIApplicationDelegate, @preconcurrency UNUserNotificationCenterDelegate {
     private let logger = Logger(subsystem: "ai.openclaw.ios", category: "Push")
@@ -24,10 +29,12 @@ final class OpenClawAppDelegate: NSObject, UIApplicationDelegate, @preconcurrenc
     private var pendingAPNsDeviceToken: Data?
     private var pendingWatchPromptActions: [PendingWatchPromptAction] = []
     private var pendingExecApprovalPrompts: [PendingExecApprovalPrompt] = []
+    private var pendingExecApprovalRequestedPushIDs: [String] = []
+    private var pendingExecApprovalResolvedPushIDs: [String] = []
 
     weak var appModel: NodeAppModel? {
         didSet {
-            guard let model = self.appModel else { return }
+            guard let model = self.resolvedAppModel() else { return }
             if let token = self.pendingAPNsDeviceToken {
                 self.pendingAPNsDeviceToken = nil
                 Task { @MainActor in
@@ -56,22 +63,56 @@ final class OpenClawAppDelegate: NSObject, UIApplicationDelegate, @preconcurrenc
                     }
                 }
             }
+            if !self.pendingExecApprovalRequestedPushIDs.isEmpty {
+                let pending = self.pendingExecApprovalRequestedPushIDs
+                self.pendingExecApprovalRequestedPushIDs.removeAll()
+                Task { @MainActor in
+                    for approvalId in pending {
+                        _ = await model.handleExecApprovalRequestedRemotePush(approvalId: approvalId)
+                    }
+                }
+            }
+            if !self.pendingExecApprovalResolvedPushIDs.isEmpty {
+                let pending = self.pendingExecApprovalResolvedPushIDs
+                self.pendingExecApprovalResolvedPushIDs.removeAll()
+                Task { @MainActor in
+                    for approvalId in pending {
+                        await model.handleExecApprovalResolvedRemotePush(approvalId: approvalId)
+                    }
+                }
+            }
         }
     }
 
+    private func resolvedAppModel() -> NodeAppModel? {
+        self.appModel ?? OpenClawAppModelRegistry.appModel
+    }
+
+#if DEBUG
+    func _test_resolvedAppModel() -> NodeAppModel? {
+        self.resolvedAppModel()
+    }
+#endif
+
     func application(
         _ application: UIApplication,
         didFinishLaunchingWithOptions launchOptions: [UIApplication.LaunchOptionsKey: Any]? = nil
     ) -> Bool
     {
+        GatewayDiagnostics.log("app delegate: didFinishLaunching")
+        if self.appModel == nil {
+            self.appModel = OpenClawAppModelRegistry.appModel
+        }
         self.registerBackgroundWakeRefreshTask()
-        UNUserNotificationCenter.current().delegate = self
+        let notificationCenter = UNUserNotificationCenter.current()
+        notificationCenter.delegate = self
+        ExecApprovalNotificationBridge.registerCategory(center: notificationCenter)
         application.registerForRemoteNotifications()
         return true
     }
 
     func application(_ application: UIApplication, didRegisterForRemoteNotificationsWithDeviceToken deviceToken: Data) {
-        if let appModel = self.appModel {
+        if let appModel = self.resolvedAppModel() {
             Task { @MainActor in
                 appModel.updateAPNsDeviceToken(deviceToken)
             }
@@ -98,12 +139,22 @@ final class OpenClawAppDelegate: NSObject, UIApplicationDelegate, @preconcurrenc
                 notificationCenter: notificationCenter)
             {
                 if let approvalId = ExecApprovalNotificationBridge.approvalID(from: userInfo) {
-                    self.appModel?.dismissPendingExecApprovalPrompt(approvalId: approvalId)
+                    if let appModel = self.resolvedAppModel() {
+                        await appModel.handleExecApprovalResolvedRemotePush(approvalId: approvalId)
+                    } else {
+                        self.pendingExecApprovalResolvedPushIDs.append(approvalId)
+                    }
                 }
                 completionHandler(.newData)
                 return
             }
-            guard let appModel = self.appModel else {
+            guard let appModel = self.resolvedAppModel() else {
+                if ExecApprovalNotificationBridge.payloadKind(userInfo: userInfo)
+                    == ExecApprovalNotificationBridge.requestedKind,
+                   let approvalId = ExecApprovalNotificationBridge.approvalID(from: userInfo)
+                {
+                    self.pendingExecApprovalRequestedPushIDs.append(approvalId)
+                }
                 self.logger.info("APNs wake skipped: appModel unavailable")
                 self.scheduleBackgroundWakeRefresh(afterSeconds: 90, reason: "silent_push_no_model")
                 completionHandler(.noData)
@@ -119,6 +170,7 @@ final class OpenClawAppDelegate: NSObject, UIApplicationDelegate, @preconcurrenc
     }
 
     func scenePhaseChanged(_ phase: ScenePhase) {
+        GatewayDiagnostics.log("app delegate: scene phase changed=\(String(describing: phase))")
         if phase == .background {
             self.scheduleBackgroundWakeRefresh(afterSeconds: 120, reason: "scene_background")
         }
@@ -163,7 +215,7 @@ final class OpenClawAppDelegate: NSObject, UIApplicationDelegate, @preconcurrenc
         self.backgroundWakeTask?.cancel()
 
         let wakeTask = Task { @MainActor [weak self] in
-            guard let self, let appModel = self.appModel else { return false }
+            guard let self, let appModel = self.resolvedAppModel() else { return false }
             return await appModel.handleBackgroundRefreshWake(trigger: "bg_app_refresh")
         }
         self.backgroundWakeTask = wakeTask
@@ -248,7 +300,7 @@ final class OpenClawAppDelegate: NSObject, UIApplicationDelegate, @preconcurrenc
     }
 
     private func routeWatchPromptAction(_ action: PendingWatchPromptAction) async {
-        guard let appModel = self.appModel else {
+        guard let appModel = self.resolvedAppModel() else {
             self.pendingWatchPromptActions.append(action)
             return
         }
@@ -261,7 +313,7 @@ final class OpenClawAppDelegate: NSObject, UIApplicationDelegate, @preconcurrenc
     }
 
     private func routeExecApprovalPrompt(_ prompt: PendingExecApprovalPrompt) {
-        guard let appModel = self.appModel else {
+        guard let appModel = self.resolvedAppModel() else {
             self.pendingExecApprovalPrompts.append(prompt)
             return
         }
@@ -561,6 +613,7 @@ struct OpenClawApp: App {
         Self.installUncaughtExceptionLogger()
         GatewaySettingsStore.bootstrapPersistence()
         let appModel = NodeAppModel()
+        OpenClawAppModelRegistry.appModel = appModel
         _appModel = State(initialValue: appModel)
         _gatewayController = State(initialValue: GatewayConnectionController(appModel: appModel))
     }

apps/ios/Sources/Push/ExecApprovalNotificationBridge.swift

@@ -8,9 +8,30 @@ struct ExecApprovalNotificationPrompt: Sendable, Equatable {
 enum ExecApprovalNotificationBridge {
     static let requestedKind = "exec.approval.requested"
     static let resolvedKind = "exec.approval.resolved"
+    static let categoryIdentifier = "openclaw.exec-approval"
+    static let reviewActionIdentifier = "openclaw.exec-approval.review"
 
     private static let localRequestPrefix = "exec.approval."
 
+    static func registerCategory(center: UNUserNotificationCenter = .current()) {
+        let category = UNNotificationCategory(
+            identifier: self.categoryIdentifier,
+            actions: [
+                UNNotificationAction(
+                    identifier: self.reviewActionIdentifier,
+                    title: "Review",
+                    options: [.foreground]),
+            ],
+            intentIdentifiers: [],
+            options: [])
+
+        center.getNotificationCategories { categories in
+            var updated = categories
+            updated.update(with: category)
+            center.setNotificationCategories(updated)
+        }
+    }
+
     static func shouldPresentNotification(userInfo: [AnyHashable: Any]) -> Bool {
         self.payloadKind(userInfo: userInfo) == self.requestedKind
     }
@@ -20,7 +41,11 @@ enum ExecApprovalNotificationBridge {
         userInfo: [AnyHashable: Any]
     ) -> ExecApprovalNotificationPrompt?
     {
-        guard actionIdentifier == UNNotificationDefaultActionIdentifier else { return nil }
+        guard actionIdentifier == UNNotificationDefaultActionIdentifier
+            || actionIdentifier == self.reviewActionIdentifier
+        else {
+            return nil
+        }
         guard self.payloadKind(userInfo: userInfo) == self.requestedKind else { return nil }
         guard let approvalId = self.approvalID(from: userInfo) else { return nil }
         return ExecApprovalNotificationPrompt(approvalId: approvalId)
@@ -71,7 +96,7 @@ enum ExecApprovalNotificationBridge {
         "\(self.localRequestPrefix)\(approvalId)"
     }
 
-    private static func payloadKind(userInfo: [AnyHashable: Any]) -> String {
+    static func payloadKind(userInfo: [AnyHashable: Any]) -> String {
         let raw = self.openClawPayload(userInfo: userInfo)?["kind"] as? String
         let trimmed = raw?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
         return trimmed.isEmpty ? "unknown" : trimmed

apps/ios/Sources/RootCanvas.swift

@@ -98,6 +98,9 @@ struct RootCanvas: View {
                 },
                 openSettings: {
                     self.presentedSheet = .settings
+                },
+                retryGatewayConnection: {
+                    Task { await self.gatewayController.connectLastKnown() }
                 })
                 .preferredColorScheme(.dark)
 
@@ -229,7 +232,7 @@ struct RootCanvas: View {
     private func updateCanvasDebugStatus() {
         self.appModel.screen.setDebugStatusEnabled(self.canvasDebugStatusEnabled)
         guard self.canvasDebugStatusEnabled else { return }
-        let title = self.appModel.gatewayStatusText.trimmingCharacters(in: .whitespacesAndNewlines)
+        let title = self.appModel.gatewayDisplayStatusText.trimmingCharacters(in: .whitespacesAndNewlines)
         let subtitle = self.appModel.gatewayServerName ?? self.appModel.gatewayRemoteAddress
         self.appModel.screen.updateDebugStatus(title: title, subtitle: subtitle)
     }
@@ -454,6 +457,7 @@ private struct CanvasContent: View {
     @AppStorage("talk.enabled") private var talkEnabled: Bool = false
     @AppStorage("talk.button.enabled") private var talkButtonEnabled: Bool = true
     @State private var showGatewayActions: Bool = false
+    @State private var showGatewayProblemDetails: Bool = false
     var systemColorScheme: ColorScheme
     var gatewayStatus: StatusPill.GatewayState
     var voiceWakeEnabled: Bool
@@ -462,6 +466,7 @@ private struct CanvasContent: View {
     var cameraHUDKind: NodeAppModel.CameraHUDKind?
     var openChat: () -> Void
     var openSettings: () -> Void
+    var retryGatewayConnection: () -> Void
 
     private var brightenButtons: Bool { self.systemColorScheme == .light }
     private var talkActive: Bool { self.appModel.talkMode.isEnabled || self.talkEnabled }
@@ -488,6 +493,8 @@ private struct CanvasContent: View {
                 onStatusTap: {
                     if self.gatewayStatus == .connected {
                         self.showGatewayActions = true
+                    } else if self.appModel.lastGatewayProblem != nil {
+                        self.showGatewayProblemDetails = true
                     } else {
                         self.openSettings()
                     }
@@ -504,13 +511,35 @@ private struct CanvasContent: View {
                     self.openSettings()
                 })
         }
+        .overlay(alignment: .top) {
+            if let gatewayProblem = self.appModel.lastGatewayProblem,
+               self.gatewayStatus != .connected
+            {
+                GatewayProblemBanner(
+                    problem: gatewayProblem,
+                    primaryActionTitle: gatewayProblem.retryable ? "Retry" : "Open Settings",
+                    onPrimaryAction: {
+                        if gatewayProblem.retryable {
+                            self.retryGatewayConnection()
+                        } else {
+                            self.openSettings()
+                        }
+                    },
+                    onShowDetails: {
+                        self.showGatewayProblemDetails = true
+                    })
+                    .padding(.horizontal, 12)
+                    .safeAreaPadding(.top, 10)
+                    .transition(.move(edge: .top).combined(with: .opacity))
+            }
+        }
         .overlay(alignment: .topLeading) {
             if let voiceWakeToastText, !voiceWakeToastText.isEmpty {
                 VoiceWakeToast(
                     command: voiceWakeToastText,
                     brighten: self.brightenButtons)
                     .padding(.leading, 10)
-                    .safeAreaPadding(.top, 58)
+                    .safeAreaPadding(.top, self.appModel.lastGatewayProblem == nil ? 58 : 132)
                     .transition(.move(edge: .top).combined(with: .opacity))
             }
         }
@@ -518,6 +547,16 @@ private struct CanvasContent: View {
             isPresented: self.$showGatewayActions,
             onDisconnect: { self.appModel.disconnectGateway() },
             onOpenSettings: { self.openSettings() })
+        .sheet(isPresented: self.$showGatewayProblemDetails) {
+            if let gatewayProblem = self.appModel.lastGatewayProblem {
+                GatewayProblemDetailsSheet(
+                    problem: gatewayProblem,
+                    primaryActionTitle: "Open Settings",
+                    onPrimaryAction: {
+                        self.openSettings()
+                    })
+            }
+        }
         .onAppear {
             // Keep the runtime talk state aligned with persisted toggle state on cold launch.
             if self.talkEnabled != self.appModel.talkMode.isEnabled {

apps/ios/Sources/RootTabs.swift

@@ -9,6 +9,7 @@ struct RootTabs: View {
     @State private var voiceWakeToastText: String?
     @State private var toastDismissTask: Task<Void, Never>?
     @State private var showGatewayActions: Bool = false
+    @State private var showGatewayProblemDetails: Bool = false
 
     var body: some View {
         TabView(selection: self.$selectedTab) {
@@ -32,6 +33,8 @@ struct RootTabs: View {
                 onTap: {
                     if self.gatewayStatus == .connected {
                         self.showGatewayActions = true
+                    } else if self.appModel.lastGatewayProblem != nil {
+                        self.showGatewayProblemDetails = true
                     } else {
                         self.selectedTab = 2
                     }
@@ -39,11 +42,29 @@ struct RootTabs: View {
                 .padding(.leading, 10)
                 .safeAreaPadding(.top, 10)
         }
+        .overlay(alignment: .top) {
+            if let gatewayProblem = self.appModel.lastGatewayProblem,
+               self.gatewayStatus != .connected
+            {
+                GatewayProblemBanner(
+                    problem: gatewayProblem,
+                    primaryActionTitle: "Open Settings",
+                    onPrimaryAction: {
+                        self.selectedTab = 2
+                    },
+                    onShowDetails: {
+                        self.showGatewayProblemDetails = true
+                    })
+                    .padding(.horizontal, 12)
+                    .safeAreaPadding(.top, 10)
+                    .transition(.move(edge: .top).combined(with: .opacity))
+            }
+        }
         .overlay(alignment: .topLeading) {
             if let voiceWakeToastText, !voiceWakeToastText.isEmpty {
                 VoiceWakeToast(command: voiceWakeToastText)
                     .padding(.leading, 10)
-                    .safeAreaPadding(.top, 58)
+                    .safeAreaPadding(.top, self.appModel.lastGatewayProblem == nil ? 58 : 132)
                     .transition(.move(edge: .top).combined(with: .opacity))
             }
         }
@@ -74,6 +95,16 @@ struct RootTabs: View {
             isPresented: self.$showGatewayActions,
             onDisconnect: { self.appModel.disconnectGateway() },
             onOpenSettings: { self.selectedTab = 2 })
+        .sheet(isPresented: self.$showGatewayProblemDetails) {
+            if let gatewayProblem = self.appModel.lastGatewayProblem {
+                GatewayProblemDetailsSheet(
+                    problem: gatewayProblem,
+                    primaryActionTitle: "Open Settings",
+                    onPrimaryAction: {
+                        self.selectedTab = 2
+                    })
+            }
+        }
     }
 
     private var gatewayStatus: StatusPill.GatewayState {

apps/ios/Sources/Services/NodeServiceProtocols.swift

@@ -88,6 +88,20 @@ struct WatchQuickReplyEvent: Sendable, Equatable {
     var transport: String
 }
 
+struct WatchExecApprovalResolveEvent: Sendable, Equatable {
+    var replyId: String
+    var approvalId: String
+    var decision: OpenClawWatchExecApprovalDecision
+    var sentAtMs: Int?
+    var transport: String
+}
+
+struct WatchExecApprovalSnapshotRequestEvent: Sendable, Equatable {
+    var requestId: String
+    var sentAtMs: Int?
+    var transport: String
+}
+
 struct WatchNotificationSendResult: Sendable, Equatable {
     var deliveredImmediately: Bool
     var queuedForDelivery: Bool
@@ -96,10 +110,22 @@ struct WatchNotificationSendResult: Sendable, Equatable {
 
 protocol WatchMessagingServicing: AnyObject, Sendable {
     func status() async -> WatchMessagingStatus
+    func setStatusHandler(_ handler: (@Sendable (WatchMessagingStatus) -> Void)?)
     func setReplyHandler(_ handler: (@Sendable (WatchQuickReplyEvent) -> Void)?)
+    func setExecApprovalResolveHandler(_ handler: (@Sendable (WatchExecApprovalResolveEvent) -> Void)?)
+    func setExecApprovalSnapshotRequestHandler(
+        _ handler: (@Sendable (WatchExecApprovalSnapshotRequestEvent) -> Void)?)
     func sendNotification(
         id: String,
         params: OpenClawWatchNotifyParams) async throws -> WatchNotificationSendResult
+    func sendExecApprovalPrompt(
+        _ message: OpenClawWatchExecApprovalPromptMessage) async throws -> WatchNotificationSendResult
+    func sendExecApprovalResolved(
+        _ message: OpenClawWatchExecApprovalResolvedMessage) async throws -> WatchNotificationSendResult
+    func sendExecApprovalExpired(
+        _ message: OpenClawWatchExecApprovalExpiredMessage) async throws -> WatchNotificationSendResult
+    func syncExecApprovalSnapshot(
+        _ message: OpenClawWatchExecApprovalSnapshotMessage) async throws -> WatchNotificationSendResult
 }
 
 extension CameraController: CameraServicing {}

apps/ios/Sources/Services/WatchConnectivityTransport.swift

@@ -0,0 +1,363 @@
+import Foundation
+import OSLog
+@preconcurrency import WatchConnectivity
+
+private struct WatchConnectivityTransportCallbacks {
+    var statusUpdateHandler: (@Sendable (WatchMessagingStatus) -> Void)?
+    var replyHandler: (@Sendable (WatchQuickReplyEvent) -> Void)?
+    var execApprovalResolveHandler: (@Sendable (WatchExecApprovalResolveEvent) -> Void)?
+    var execApprovalSnapshotRequestHandler: (@Sendable (WatchExecApprovalSnapshotRequestEvent) -> Void)?
+}
+
+private func sendReachableWatchMessage(_ payload: [String: Any], with session: WCSession) async throws {
+    // WatchConnectivity replies arrive on its own queue. Keep this continuation explicitly
+    // nonisolated so Swift 6 does not inherit a caller actor (for example MainActor) into the
+    // Objective-C callback boundary and trap on the reply callback executor check.
+    try await withCheckedThrowingContinuation(isolation: nil) {
+        (continuation: CheckedContinuation<Void, Error>) in
+        session.sendMessage(
+            payload,
+            replyHandler: { _ in
+                continuation.resume(returning: ())
+            },
+            errorHandler: { error in
+                continuation.resume(throwing: error)
+            }
+        )
+    }
+}
+
+final class WatchConnectivityTransport: NSObject, @unchecked Sendable {
+    nonisolated private static let logger = Logger(subsystem: "ai.openclaw", category: "watch.messaging")
+
+    private let session: WCSession?
+    private let callbacksLock = NSLock()
+    private var callbacks = WatchConnectivityTransportCallbacks()
+
+    override init() {
+        if WCSession.isSupported() {
+            self.session = WCSession.default
+        } else {
+            self.session = nil
+        }
+        super.init()
+        if let session = self.session {
+            session.delegate = self
+            session.activate()
+        }
+    }
+
+    nonisolated static func isSupportedOnDevice() -> Bool {
+        WCSession.isSupported()
+    }
+
+    nonisolated static func currentStatusSnapshot() -> WatchMessagingStatus {
+        guard WCSession.isSupported() else {
+            return WatchMessagingStatus(
+                supported: false,
+                paired: false,
+                appInstalled: false,
+                reachable: false,
+                activationState: "unsupported")
+        }
+        return self.status(for: WCSession.default)
+    }
+
+    func status() async -> WatchMessagingStatus {
+        await self.ensureActivated()
+        return self.currentStatusSnapshot()
+    }
+
+    func currentStatusSnapshot() -> WatchMessagingStatus {
+        guard let session = self.session else {
+            return WatchMessagingStatus(
+                supported: false,
+                paired: false,
+                appInstalled: false,
+                reachable: false,
+                activationState: "unsupported")
+        }
+        return Self.status(for: session)
+    }
+
+    func setStatusUpdateHandler(_ handler: (@Sendable (WatchMessagingStatus) -> Void)?) {
+        self.updateCallbacks { $0.statusUpdateHandler = handler }
+    }
+
+    func setReplyHandler(_ handler: (@Sendable (WatchQuickReplyEvent) -> Void)?) {
+        self.updateCallbacks { $0.replyHandler = handler }
+    }
+
+    func setExecApprovalResolveHandler(_ handler: (@Sendable (WatchExecApprovalResolveEvent) -> Void)?) {
+        self.updateCallbacks { $0.execApprovalResolveHandler = handler }
+    }
+
+    func setExecApprovalSnapshotRequestHandler(
+        _ handler: (@Sendable (WatchExecApprovalSnapshotRequestEvent) -> Void)?)
+    {
+        self.updateCallbacks { $0.execApprovalSnapshotRequestHandler = handler }
+    }
+
+    func sendPayload(_ payload: [String: Any]) async throws -> WatchNotificationSendResult {
+        await self.ensureActivated()
+        let session = try self.requireReadySession()
+        if session.isReachable {
+            do {
+                try await sendReachableWatchMessage(payload, with: session)
+                return WatchNotificationSendResult(
+                    deliveredImmediately: true,
+                    queuedForDelivery: false,
+                    transport: "sendMessage")
+            } catch {
+                Self.logger.error("watch sendMessage failed: \(error.localizedDescription, privacy: .public)")
+            }
+        }
+
+        _ = session.transferUserInfo(payload)
+        return WatchNotificationSendResult(
+            deliveredImmediately: false,
+            queuedForDelivery: true,
+            transport: "transferUserInfo")
+    }
+
+    func sendSnapshotPayload(_ payload: [String: Any]) async throws -> WatchNotificationSendResult {
+        await self.ensureActivated()
+        let session = try self.requireReadySession()
+        if session.isReachable {
+            do {
+                try await sendReachableWatchMessage(payload, with: session)
+                return WatchNotificationSendResult(
+                    deliveredImmediately: true,
+                    queuedForDelivery: false,
+                    transport: "sendMessage")
+            } catch {
+                Self.logger.error(
+                    "watch snapshot sendMessage failed: \(error.localizedDescription, privacy: .public)")
+            }
+        }
+
+        do {
+            try session.updateApplicationContext(payload)
+            return WatchNotificationSendResult(
+                deliveredImmediately: false,
+                queuedForDelivery: true,
+                transport: "applicationContext")
+        } catch {
+            Self.logger.error(
+                "watch updateApplicationContext failed: \(error.localizedDescription, privacy: .public)")
+            _ = session.transferUserInfo(payload)
+            return WatchNotificationSendResult(
+                deliveredImmediately: false,
+                queuedForDelivery: true,
+                transport: "transferUserInfo")
+        }
+    }
+
+    private func updateCallbacks(_ update: (inout WatchConnectivityTransportCallbacks) -> Void) {
+        self.callbacksLock.lock()
+        defer { self.callbacksLock.unlock() }
+        update(&self.callbacks)
+    }
+
+    private func callbacksSnapshot() -> WatchConnectivityTransportCallbacks {
+        self.callbacksLock.lock()
+        defer { self.callbacksLock.unlock() }
+        return self.callbacks
+    }
+
+    private func requireReadySession() throws -> WCSession {
+        guard let session = self.session else {
+            throw WatchMessagingError.unsupported
+        }
+        let snapshot = Self.status(for: session)
+        guard snapshot.paired else {
+            throw WatchMessagingError.notPaired
+        }
+        guard snapshot.appInstalled else {
+            throw WatchMessagingError.watchAppNotInstalled
+        }
+        return session
+    }
+
+    private func ensureActivated() async {
+        guard let session = self.session else { return }
+        if session.activationState == .activated {
+            return
+        }
+        session.activate()
+        for _ in 0..<8 {
+            if session.activationState == .activated {
+                return
+            }
+            try? await Task.sleep(nanoseconds: 100_000_000)
+        }
+    }
+
+    private func emitStatusUpdate(_ snapshot: WatchMessagingStatus) {
+        guard let handler = self.callbacksSnapshot().statusUpdateHandler else {
+            return
+        }
+        Task { @MainActor in
+            handler(snapshot)
+        }
+    }
+
+    private func emitReply(_ event: WatchQuickReplyEvent) {
+        guard let handler = self.callbacksSnapshot().replyHandler else {
+            return
+        }
+        Task { @MainActor in
+            handler(event)
+        }
+    }
+
+    private func emitExecApprovalResolve(_ event: WatchExecApprovalResolveEvent) {
+        guard let handler = self.callbacksSnapshot().execApprovalResolveHandler else {
+            return
+        }
+        Task { @MainActor in
+            handler(event)
+        }
+    }
+
+    private func emitExecApprovalSnapshotRequest(_ event: WatchExecApprovalSnapshotRequestEvent) {
+        guard let handler = self.callbacksSnapshot().execApprovalSnapshotRequestHandler else {
+            return
+        }
+        Task { @MainActor in
+            handler(event)
+        }
+    }
+
+    nonisolated private static func status(for session: WCSession) -> WatchMessagingStatus {
+        WatchMessagingStatus(
+            supported: true,
+            paired: session.isPaired,
+            appInstalled: session.isWatchAppInstalled,
+            reachable: session.isReachable,
+            activationState: self.activationStateLabel(session.activationState))
+    }
+
+    nonisolated private static func activationStateLabel(_ state: WCSessionActivationState) -> String {
+        switch state {
+        case .notActivated:
+            "notActivated"
+        case .inactive:
+            "inactive"
+        case .activated:
+            "activated"
+        @unknown default:
+            "unknown"
+        }
+    }
+}
+
+extension WatchConnectivityTransport: WCSessionDelegate {
+    func session(
+        _ session: WCSession,
+        activationDidCompleteWith activationState: WCSessionActivationState,
+        error: (any Error)?)
+    {
+        GatewayDiagnostics.log(
+            "watch messaging: activation complete state=\(Self.activationStateLabel(activationState)) error=\(error?.localizedDescription ?? "none")")
+        if let error {
+            Self.logger.error("watch activation failed: \(error.localizedDescription, privacy: .public)")
+        } else {
+            Self.logger.debug(
+                "watch activation state=\(Self.activationStateLabel(activationState), privacy: .public)")
+        }
+        self.emitStatusUpdate(Self.status(for: session))
+    }
+
+    func sessionDidBecomeInactive(_: WCSession) {}
+
+    func sessionDidDeactivate(_ session: WCSession) {
+        GatewayDiagnostics.log("watch messaging: session did deactivate; reactivating")
+        session.activate()
+        self.emitStatusUpdate(Self.status(for: session))
+    }
+
+    func session(_: WCSession, didReceiveMessage message: [String: Any]) {
+        let type = (message["type"] as? String) ?? "unknown"
+        GatewayDiagnostics.log("watch messaging: didReceiveMessage type=\(type)")
+        if let event = WatchMessagingPayloadCodec.parseQuickReplyPayload(message, transport: "sendMessage") {
+            self.emitReply(event)
+            return
+        }
+        if let event = WatchMessagingPayloadCodec.parseExecApprovalResolvePayload(
+            message,
+            transport: "sendMessage")
+        {
+            self.emitExecApprovalResolve(event)
+            return
+        }
+        if let event = WatchMessagingPayloadCodec.parseExecApprovalSnapshotRequestPayload(
+            message,
+            transport: "sendMessage")
+        {
+            self.emitExecApprovalSnapshotRequest(event)
+        }
+    }
+
+    func session(
+        _: WCSession,
+        didReceiveMessage message: [String: Any],
+        replyHandler: @escaping ([String: Any]) -> Void)
+    {
+        let type = (message["type"] as? String) ?? "unknown"
+        GatewayDiagnostics.log("watch messaging: didReceiveMessageWithReply type=\(type)")
+        if let event = WatchMessagingPayloadCodec.parseQuickReplyPayload(message, transport: "sendMessage") {
+            replyHandler(["ok": true])
+            self.emitReply(event)
+            return
+        }
+        if let event = WatchMessagingPayloadCodec.parseExecApprovalResolvePayload(
+            message,
+            transport: "sendMessage")
+        {
+            replyHandler(["ok": true])
+            self.emitExecApprovalResolve(event)
+            return
+        }
+        if let event = WatchMessagingPayloadCodec.parseExecApprovalSnapshotRequestPayload(
+            message,
+            transport: "sendMessage")
+        {
+            replyHandler(["ok": true])
+            self.emitExecApprovalSnapshotRequest(event)
+            return
+        }
+        replyHandler(["ok": false, "error": "unsupported_payload"])
+    }
+
+    func session(_: WCSession, didReceiveUserInfo userInfo: [String: Any]) {
+        let type = (userInfo["type"] as? String) ?? "unknown"
+        GatewayDiagnostics.log("watch messaging: didReceiveUserInfo type=\(type)")
+        if let event = WatchMessagingPayloadCodec.parseQuickReplyPayload(
+            userInfo,
+            transport: "transferUserInfo")
+        {
+            self.emitReply(event)
+            return
+        }
+        if let event = WatchMessagingPayloadCodec.parseExecApprovalResolvePayload(
+            userInfo,
+            transport: "transferUserInfo")
+        {
+            self.emitExecApprovalResolve(event)
+            return
+        }
+        if let event = WatchMessagingPayloadCodec.parseExecApprovalSnapshotRequestPayload(
+            userInfo,
+            transport: "transferUserInfo")
+        {
+            self.emitExecApprovalSnapshotRequest(event)
+        }
+    }
+
+    func sessionReachabilityDidChange(_ session: WCSession) {
+        GatewayDiagnostics.log(
+            "watch messaging: reachability changed reachable=\(session.isReachable) paired=\(session.isPaired) installed=\(session.isWatchAppInstalled)")
+        self.emitStatusUpdate(Self.status(for: session))
+    }
+}

apps/ios/Sources/Services/WatchMessagingPayloadCodec.swift

@@ -0,0 +1,219 @@
+import Foundation
+import OpenClawKit
+
+enum WatchMessagingPayloadCodec {
+    static func nowMs() -> Int {
+        Int(Date().timeIntervalSince1970 * 1000)
+    }
+
+    static func nonEmpty(_ value: String?) -> String? {
+        let trimmed = value?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
+        return trimmed.isEmpty ? nil : trimmed
+    }
+
+    static func encodeNotificationPayload(
+        id: String,
+        params: OpenClawWatchNotifyParams) -> [String: Any]
+    {
+        var payload: [String: Any] = [
+            "type": OpenClawWatchPayloadType.notify.rawValue,
+            "id": id,
+            "title": params.title,
+            "body": params.body,
+            "priority": params.priority?.rawValue ?? OpenClawNotificationPriority.active.rawValue,
+            "sentAtMs": nowMs(),
+        ]
+        if let promptId = nonEmpty(params.promptId) {
+            payload["promptId"] = promptId
+        }
+        if let sessionKey = nonEmpty(params.sessionKey) {
+            payload["sessionKey"] = sessionKey
+        }
+        if let kind = nonEmpty(params.kind) {
+            payload["kind"] = kind
+        }
+        if let details = nonEmpty(params.details) {
+            payload["details"] = details
+        }
+        if let expiresAtMs = params.expiresAtMs {
+            payload["expiresAtMs"] = expiresAtMs
+        }
+        if let risk = params.risk {
+            payload["risk"] = risk.rawValue
+        }
+        if let actions = params.actions, !actions.isEmpty {
+            payload["actions"] = actions.map { action in
+                var encoded: [String: Any] = [
+                    "id": action.id,
+                    "label": action.label,
+                ]
+                if let style = nonEmpty(action.style) {
+                    encoded["style"] = style
+                }
+                return encoded
+            }
+        }
+        return payload
+    }
+
+    static func encodeExecApprovalItem(_ item: OpenClawWatchExecApprovalItem) -> [String: Any] {
+        var payload: [String: Any] = [
+            "id": item.id,
+            "commandText": item.commandText,
+            "allowedDecisions": item.allowedDecisions.map(\.rawValue),
+        ]
+        if let commandPreview = nonEmpty(item.commandPreview) {
+            payload["commandPreview"] = commandPreview
+        }
+        if let host = nonEmpty(item.host) {
+            payload["host"] = host
+        }
+        if let nodeId = nonEmpty(item.nodeId) {
+            payload["nodeId"] = nodeId
+        }
+        if let agentId = nonEmpty(item.agentId) {
+            payload["agentId"] = agentId
+        }
+        if let expiresAtMs = item.expiresAtMs {
+            payload["expiresAtMs"] = expiresAtMs
+        }
+        if let risk = item.risk {
+            payload["risk"] = risk.rawValue
+        }
+        return payload
+    }
+
+    static func encodeExecApprovalPromptPayload(
+        _ message: OpenClawWatchExecApprovalPromptMessage) -> [String: Any]
+    {
+        var payload: [String: Any] = [
+            "type": OpenClawWatchPayloadType.execApprovalPrompt.rawValue,
+            "approval": encodeExecApprovalItem(message.approval),
+        ]
+        if let sentAtMs = message.sentAtMs {
+            payload["sentAtMs"] = sentAtMs
+        }
+        if let deliveryId = nonEmpty(message.deliveryId) {
+            payload["deliveryId"] = deliveryId
+        }
+        if message.resetResolvingState == true {
+            payload["resetResolvingState"] = true
+        }
+        return payload
+    }
+
+    static func encodeExecApprovalResolvedPayload(
+        _ message: OpenClawWatchExecApprovalResolvedMessage) -> [String: Any]
+    {
+        var payload: [String: Any] = [
+            "type": OpenClawWatchPayloadType.execApprovalResolved.rawValue,
+            "approvalId": message.approvalId,
+        ]
+        if let decision = message.decision {
+            payload["decision"] = decision.rawValue
+        }
+        if let resolvedAtMs = message.resolvedAtMs {
+            payload["resolvedAtMs"] = resolvedAtMs
+        }
+        if let source = nonEmpty(message.source) {
+            payload["source"] = source
+        }
+        return payload
+    }
+
+    static func encodeExecApprovalExpiredPayload(
+        _ message: OpenClawWatchExecApprovalExpiredMessage) -> [String: Any]
+    {
+        var payload: [String: Any] = [
+            "type": OpenClawWatchPayloadType.execApprovalExpired.rawValue,
+            "approvalId": message.approvalId,
+            "reason": message.reason.rawValue,
+        ]
+        if let expiredAtMs = message.expiredAtMs {
+            payload["expiredAtMs"] = expiredAtMs
+        }
+        return payload
+    }
+
+    static func encodeExecApprovalSnapshotPayload(
+        _ message: OpenClawWatchExecApprovalSnapshotMessage) -> [String: Any]
+    {
+        var payload: [String: Any] = [
+            "type": OpenClawWatchPayloadType.execApprovalSnapshot.rawValue,
+            "approvals": message.approvals.map(encodeExecApprovalItem),
+        ]
+        if let sentAtMs = message.sentAtMs {
+            payload["sentAtMs"] = sentAtMs
+        }
+        if let snapshotId = nonEmpty(message.snapshotId) {
+            payload["snapshotId"] = snapshotId
+        }
+        return payload
+    }
+
+    static func parseQuickReplyPayload(
+        _ payload: [String: Any],
+        transport: String) -> WatchQuickReplyEvent?
+    {
+        guard (payload["type"] as? String) == OpenClawWatchPayloadType.reply.rawValue else {
+            return nil
+        }
+        guard let actionId = nonEmpty(payload["actionId"] as? String) else {
+            return nil
+        }
+        let promptId = nonEmpty(payload["promptId"] as? String) ?? "unknown"
+        let replyId = nonEmpty(payload["replyId"] as? String) ?? UUID().uuidString
+        let actionLabel = nonEmpty(payload["actionLabel"] as? String)
+        let sessionKey = nonEmpty(payload["sessionKey"] as? String)
+        let note = nonEmpty(payload["note"] as? String)
+        let sentAtMs = (payload["sentAtMs"] as? Int) ?? (payload["sentAtMs"] as? NSNumber)?.intValue
+
+        return WatchQuickReplyEvent(
+            replyId: replyId,
+            promptId: promptId,
+            actionId: actionId,
+            actionLabel: actionLabel,
+            sessionKey: sessionKey,
+            note: note,
+            sentAtMs: sentAtMs,
+            transport: transport)
+    }
+
+    static func parseExecApprovalResolvePayload(
+        _ payload: [String: Any],
+        transport: String) -> WatchExecApprovalResolveEvent?
+    {
+        guard (payload["type"] as? String) == OpenClawWatchPayloadType.execApprovalResolve.rawValue else {
+            return nil
+        }
+        guard let approvalId = nonEmpty(payload["approvalId"] as? String),
+              let rawDecision = nonEmpty(payload["decision"] as? String),
+              let decision = OpenClawWatchExecApprovalDecision(rawValue: rawDecision)
+        else {
+            return nil
+        }
+        let replyId = nonEmpty(payload["replyId"] as? String) ?? UUID().uuidString
+        let sentAtMs = (payload["sentAtMs"] as? Int) ?? (payload["sentAtMs"] as? NSNumber)?.intValue
+        return WatchExecApprovalResolveEvent(
+            replyId: replyId,
+            approvalId: approvalId,
+            decision: decision,
+            sentAtMs: sentAtMs,
+            transport: transport)
+    }
+
+    static func parseExecApprovalSnapshotRequestPayload(
+        _ payload: [String: Any],
+        transport: String) -> WatchExecApprovalSnapshotRequestEvent?
+    {
+        guard (payload["type"] as? String) == OpenClawWatchPayloadType.execApprovalSnapshotRequest.rawValue else {
+            return nil
+        }
+        let requestId = nonEmpty(payload["requestId"] as? String) ?? UUID().uuidString
+        let sentAtMs = (payload["sentAtMs"] as? Int) ?? (payload["sentAtMs"] as? NSNumber)?.intValue
+        return WatchExecApprovalSnapshotRequestEvent(
+            requestId: requestId,
+            sentAtMs: sentAtMs,
+            transport: transport)
+    }
+}

apps/ios/Sources/Services/WatchMessagingService.swift

@@ -1,7 +1,5 @@
 import Foundation
 import OpenClawKit
-import OSLog
-@preconcurrency import WatchConnectivity
 
 enum WatchMessagingError: LocalizedError {
     case unsupported
@@ -21,272 +19,136 @@ enum WatchMessagingError: LocalizedError {
 }
 
 @MainActor
-final class WatchMessagingService: NSObject, @preconcurrency WatchMessagingServicing {
-    nonisolated private static let logger = Logger(subsystem: "ai.openclaw", category: "watch.messaging")
-    private let session: WCSession?
-    private var pendingActivationContinuations: [CheckedContinuation<Void, Never>] = []
+final class WatchMessagingService: @preconcurrency WatchMessagingServicing {
+    private let transport: WatchConnectivityTransport
+    private var statusHandler: (@Sendable (WatchMessagingStatus) -> Void)?
+    private var lastEmittedStatus: WatchMessagingStatus?
     private var replyHandler: (@Sendable (WatchQuickReplyEvent) -> Void)?
+    private var execApprovalResolveHandler: (@Sendable (WatchExecApprovalResolveEvent) -> Void)?
+    private var execApprovalSnapshotRequestHandler: (
+        @Sendable (WatchExecApprovalSnapshotRequestEvent) -> Void)?
 
-    override init() {
-        if WCSession.isSupported() {
-            self.session = WCSession.default
-        } else {
-            self.session = nil
+    init(transport: WatchConnectivityTransport = WatchConnectivityTransport()) {
+        self.transport = transport
+        self.transport.setStatusUpdateHandler { [weak self] snapshot in
+            Task { @MainActor [weak self] in
+                self?.emitStatusIfChanged(snapshot)
+            }
         }
-        super.init()
-        if let session = self.session {
-            session.delegate = self
-            session.activate()
+        self.transport.setReplyHandler { [weak self] event in
+            Task { @MainActor [weak self] in
+                self?.emitReply(event)
+            }
+        }
+        self.transport.setExecApprovalResolveHandler { [weak self] event in
+            Task { @MainActor [weak self] in
+                self?.emitExecApprovalResolve(event)
+            }
+        }
+        self.transport.setExecApprovalSnapshotRequestHandler { [weak self] event in
+            Task { @MainActor [weak self] in
+                self?.emitExecApprovalSnapshotRequest(event)
+            }
         }
     }
 
     nonisolated static func isSupportedOnDevice() -> Bool {
-        WCSession.isSupported()
+        WatchConnectivityTransport.isSupportedOnDevice()
     }
 
     nonisolated static func currentStatusSnapshot() -> WatchMessagingStatus {
-        guard WCSession.isSupported() else {
-            return WatchMessagingStatus(
-                supported: false,
-                paired: false,
-                appInstalled: false,
-                reachable: false,
-                activationState: "unsupported")
-        }
-        let session = WCSession.default
-        return status(for: session)
+        WatchConnectivityTransport.currentStatusSnapshot()
     }
 
     func status() async -> WatchMessagingStatus {
-        await self.ensureActivated()
-        guard let session = self.session else {
-            return WatchMessagingStatus(
-                supported: false,
-                paired: false,
-                appInstalled: false,
-                reachable: false,
-                activationState: "unsupported")
+        await self.transport.status()
+    }
+
+    func setStatusHandler(_ handler: (@Sendable (WatchMessagingStatus) -> Void)?) {
+        self.statusHandler = handler
+        guard let handler else {
+            self.lastEmittedStatus = nil
+            GatewayDiagnostics.log("watch messaging: cleared status handler")
+            return
         }
-        return Self.status(for: session)
+        let snapshot = self.transport.currentStatusSnapshot()
+        self.lastEmittedStatus = snapshot
+        GatewayDiagnostics.log(
+            "watch messaging: set status handler supported=\(snapshot.supported) paired=\(snapshot.paired) appInstalled=\(snapshot.appInstalled) reachable=\(snapshot.reachable) activation=\(snapshot.activationState)")
+        handler(snapshot)
     }
 
     func setReplyHandler(_ handler: (@Sendable (WatchQuickReplyEvent) -> Void)?) {
         self.replyHandler = handler
     }
 
+    func setExecApprovalResolveHandler(_ handler: (@Sendable (WatchExecApprovalResolveEvent) -> Void)?) {
+        self.execApprovalResolveHandler = handler
+    }
+
+    func setExecApprovalSnapshotRequestHandler(
+        _ handler: (@Sendable (WatchExecApprovalSnapshotRequestEvent) -> Void)?)
+    {
+        self.execApprovalSnapshotRequestHandler = handler
+    }
+
     func sendNotification(
         id: String,
         params: OpenClawWatchNotifyParams) async throws -> WatchNotificationSendResult
     {
-        await self.ensureActivated()
-        guard let session = self.session else {
-            throw WatchMessagingError.unsupported
-        }
-
-        let snapshot = Self.status(for: session)
-        guard snapshot.paired else { throw WatchMessagingError.notPaired }
-        guard snapshot.appInstalled else { throw WatchMessagingError.watchAppNotInstalled }
-
-        var payload: [String: Any] = [
-            "type": "watch.notify",
-            "id": id,
-            "title": params.title,
-            "body": params.body,
-            "priority": params.priority?.rawValue ?? OpenClawNotificationPriority.active.rawValue,
-            "sentAtMs": Int(Date().timeIntervalSince1970 * 1000),
-        ]
-        if let promptId = Self.nonEmpty(params.promptId) {
-            payload["promptId"] = promptId
-        }
-        if let sessionKey = Self.nonEmpty(params.sessionKey) {
-            payload["sessionKey"] = sessionKey
-        }
-        if let kind = Self.nonEmpty(params.kind) {
-            payload["kind"] = kind
-        }
-        if let details = Self.nonEmpty(params.details) {
-            payload["details"] = details
-        }
-        if let expiresAtMs = params.expiresAtMs {
-            payload["expiresAtMs"] = expiresAtMs
-        }
-        if let risk = params.risk {
-            payload["risk"] = risk.rawValue
-        }
-        if let actions = params.actions, !actions.isEmpty {
-            payload["actions"] = actions.map { action in
-                var encoded: [String: Any] = [
-                    "id": action.id,
-                    "label": action.label,
-                ]
-                if let style = Self.nonEmpty(action.style) {
-                    encoded["style"] = style
-                }
-                return encoded
-            }
-        }
-
-        if snapshot.reachable {
-            do {
-                try await self.sendReachableMessage(payload, with: session)
-                return WatchNotificationSendResult(
-                    deliveredImmediately: true,
-                    queuedForDelivery: false,
-                    transport: "sendMessage")
-            } catch {
-                Self.logger.error("watch sendMessage failed: \(error.localizedDescription, privacy: .public)")
-            }
-        }
-
-        _ = session.transferUserInfo(payload)
-        return WatchNotificationSendResult(
-            deliveredImmediately: false,
-            queuedForDelivery: true,
-            transport: "transferUserInfo")
+        let payload = WatchMessagingPayloadCodec.encodeNotificationPayload(id: id, params: params)
+        return try await self.transport.sendPayload(payload)
     }
 
-    private func sendReachableMessage(_ payload: [String: Any], with session: WCSession) async throws {
-        try await withCheckedThrowingContinuation { continuation in
-            session.sendMessage(
-                payload,
-                replyHandler: { _ in
-                    continuation.resume()
-                },
-                errorHandler: { error in
-                    continuation.resume(throwing: error)
-                }
-            )
+    func sendExecApprovalPrompt(
+        _ message: OpenClawWatchExecApprovalPromptMessage) async throws -> WatchNotificationSendResult
+    {
+        try await self.transport.sendPayload(
+            WatchMessagingPayloadCodec.encodeExecApprovalPromptPayload(message))
+    }
+
+    func sendExecApprovalResolved(
+        _ message: OpenClawWatchExecApprovalResolvedMessage) async throws -> WatchNotificationSendResult
+    {
+        try await self.transport.sendPayload(
+            WatchMessagingPayloadCodec.encodeExecApprovalResolvedPayload(message))
+    }
+
+    func sendExecApprovalExpired(
+        _ message: OpenClawWatchExecApprovalExpiredMessage) async throws -> WatchNotificationSendResult
+    {
+        try await self.transport.sendPayload(
+            WatchMessagingPayloadCodec.encodeExecApprovalExpiredPayload(message))
+    }
+
+    func syncExecApprovalSnapshot(
+        _ message: OpenClawWatchExecApprovalSnapshotMessage) async throws -> WatchNotificationSendResult
+    {
+        try await self.transport.sendSnapshotPayload(
+            WatchMessagingPayloadCodec.encodeExecApprovalSnapshotPayload(message))
+    }
+
+    private func emitStatusIfChanged(_ snapshot: WatchMessagingStatus) {
+        guard snapshot != self.lastEmittedStatus else {
+            return
         }
+        self.lastEmittedStatus = snapshot
+        GatewayDiagnostics.log(
+            "watch messaging: status supported=\(snapshot.supported) paired=\(snapshot.paired) appInstalled=\(snapshot.appInstalled) reachable=\(snapshot.reachable) activation=\(snapshot.activationState)")
+        self.statusHandler?(snapshot)
     }
 
     private func emitReply(_ event: WatchQuickReplyEvent) {
         self.replyHandler?(event)
     }
 
-    nonisolated private static func nonEmpty(_ value: String?) -> String? {
-        let trimmed = value?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
-        return trimmed.isEmpty ? nil : trimmed
+    private func emitExecApprovalResolve(_ event: WatchExecApprovalResolveEvent) {
+        self.execApprovalResolveHandler?(event)
     }
 
-    nonisolated private static func parseQuickReplyPayload(
-        _ payload: [String: Any],
-        transport: String) -> WatchQuickReplyEvent?
-    {
-        guard (payload["type"] as? String) == "watch.reply" else {
-            return nil
-        }
-        guard let actionId = nonEmpty(payload["actionId"] as? String) else {
-            return nil
-        }
-        let promptId = nonEmpty(payload["promptId"] as? String) ?? "unknown"
-        let replyId = nonEmpty(payload["replyId"] as? String) ?? UUID().uuidString
-        let actionLabel = nonEmpty(payload["actionLabel"] as? String)
-        let sessionKey = nonEmpty(payload["sessionKey"] as? String)
-        let note = nonEmpty(payload["note"] as? String)
-        let sentAtMs = (payload["sentAtMs"] as? Int) ?? (payload["sentAtMs"] as? NSNumber)?.intValue
-
-        return WatchQuickReplyEvent(
-            replyId: replyId,
-            promptId: promptId,
-            actionId: actionId,
-            actionLabel: actionLabel,
-            sessionKey: sessionKey,
-            note: note,
-            sentAtMs: sentAtMs,
-            transport: transport)
-    }
-
-    private func ensureActivated() async {
-        guard let session = self.session else { return }
-        if session.activationState == .activated { return }
-        session.activate()
-        await withCheckedContinuation { continuation in
-            self.pendingActivationContinuations.append(continuation)
-        }
-    }
-
-    nonisolated private static func status(for session: WCSession) -> WatchMessagingStatus {
-        WatchMessagingStatus(
-            supported: true,
-            paired: session.isPaired,
-            appInstalled: session.isWatchAppInstalled,
-            reachable: session.isReachable,
-            activationState: activationStateLabel(session.activationState))
-    }
-
-    nonisolated private static func activationStateLabel(_ state: WCSessionActivationState) -> String {
-        switch state {
-        case .notActivated:
-            "notActivated"
-        case .inactive:
-            "inactive"
-        case .activated:
-            "activated"
-        @unknown default:
-            "unknown"
-        }
+    private func emitExecApprovalSnapshotRequest(_ event: WatchExecApprovalSnapshotRequestEvent) {
+        GatewayDiagnostics.log(
+            "watch messaging: snapshot request id=\(event.requestId) transport=\(event.transport) sentAtMs=\(event.sentAtMs ?? -1)")
+        self.execApprovalSnapshotRequestHandler?(event)
     }
 }
-
-extension WatchMessagingService: WCSessionDelegate {
-    nonisolated func session(
-        _ session: WCSession,
-        activationDidCompleteWith activationState: WCSessionActivationState,
-        error: (any Error)?)
-    {
-        if let error {
-            Self.logger.error("watch activation failed: \(error.localizedDescription, privacy: .public)")
-        } else {
-            Self.logger.debug("watch activation state=\(Self.activationStateLabel(activationState), privacy: .public)")
-        }
-        // Always resume all waiters so callers never hang, even on error.
-        Task { @MainActor in
-            let waiters = self.pendingActivationContinuations
-            self.pendingActivationContinuations.removeAll()
-            for continuation in waiters {
-                continuation.resume()
-            }
-        }
-    }
-
-    nonisolated func sessionDidBecomeInactive(_ session: WCSession) {}
-
-    nonisolated func sessionDidDeactivate(_ session: WCSession) {
-        session.activate()
-    }
-
-    nonisolated func session(_: WCSession, didReceiveMessage message: [String: Any]) {
-        guard let event = Self.parseQuickReplyPayload(message, transport: "sendMessage") else {
-            return
-        }
-        Task { @MainActor in
-            self.emitReply(event)
-        }
-    }
-
-    nonisolated func session(
-        _: WCSession,
-        didReceiveMessage message: [String: Any],
-        replyHandler: @escaping ([String: Any]) -> Void)
-    {
-        guard let event = Self.parseQuickReplyPayload(message, transport: "sendMessage") else {
-            replyHandler(["ok": false, "error": "unsupported_payload"])
-            return
-        }
-        replyHandler(["ok": true])
-        Task { @MainActor in
-            self.emitReply(event)
-        }
-    }
-
-    nonisolated func session(_: WCSession, didReceiveUserInfo userInfo: [String: Any]) {
-        guard let event = Self.parseQuickReplyPayload(userInfo, transport: "transferUserInfo") else {
-            return
-        }
-        Task { @MainActor in
-            self.emitReply(event)
-        }
-    }
-
-    nonisolated func sessionReachabilityDidChange(_ session: WCSession) {}
-}

apps/ios/Sources/Settings/SettingsTab.swift

@@ -53,6 +53,7 @@ struct SettingsTab: View {
     @State private var selectedAgentPickerId: String = ""
 
     @State private var showResetOnboardingAlert: Bool = false
+    @State private var showGatewayProblemDetails: Bool = false
     @State private var activeFeatureHelp: FeatureHelp?
     @State private var suppressCredentialPersist: Bool = false
 
@@ -63,6 +64,20 @@ struct SettingsTab: View {
             Form {
                 Section {
                     DisclosureGroup(isExpanded: self.$gatewayExpanded) {
+                        if let gatewayProblem = self.appModel.lastGatewayProblem,
+                           !self.isGatewayConnected
+                        {
+                            GatewayProblemBanner(
+                                problem: gatewayProblem,
+                                primaryActionTitle: "Retry connection",
+                                onPrimaryAction: {
+                                    Task { await self.retryGatewayConnectionFromProblem() }
+                                },
+                                onShowDetails: {
+                                    self.showGatewayProblemDetails = true
+                                })
+                        }
+
                         if !self.isGatewayConnected {
                             Text(
                                 "1. Open a chat with your OpenClaw agent and send /pair\n"
@@ -123,7 +138,7 @@ struct SettingsTab: View {
                         if self.appModel.gatewayServerName == nil {
                             LabeledContent("Discovery", value: self.gatewayController.discoveryStatusText)
                         }
-                        LabeledContent("Status", value: self.appModel.gatewayStatusText)
+                        LabeledContent("Status", value: self.appModel.gatewayDisplayStatusText)
                         Toggle("Auto-connect on launch", isOn: self.$gatewayAutoConnect)
 
                         if let serverName = self.appModel.gatewayServerName {
@@ -402,6 +417,16 @@ struct SettingsTab: View {
                     .accessibilityLabel("Close")
                 }
             }
+            .sheet(isPresented: self.$showGatewayProblemDetails) {
+                if let gatewayProblem = self.appModel.lastGatewayProblem {
+                    GatewayProblemDetailsSheet(
+                        problem: gatewayProblem,
+                        primaryActionTitle: "Retry",
+                        onPrimaryAction: {
+                            Task { await self.retryGatewayConnectionFromProblem() }
+                        })
+                }
+            }
             .alert("Reset Onboarding?", isPresented: self.$showResetOnboardingAlert) {
                 Button("Reset", role: .destructive) {
                     self.resetOnboarding()
@@ -593,6 +618,9 @@ struct SettingsTab: View {
         if let server = self.appModel.gatewayServerName, self.isGatewayConnected {
             return server
         }
+        if let problem = self.appModel.lastGatewayProblem {
+            return problem.statusText
+        }
         let trimmed = self.appModel.gatewayStatusText.trimmingCharacters(in: .whitespacesAndNewlines)
         return trimmed.isEmpty ? "Not connected" : trimmed
     }
@@ -642,7 +670,7 @@ struct SettingsTab: View {
 
     private func gatewayDebugText() -> String {
         var lines: [String] = [
-            "gateway: \(self.appModel.gatewayStatusText)",
+            "gateway: \(self.appModel.gatewayDisplayStatusText)",
             "discovery: \(self.gatewayController.discoveryStatusText)",
         ]
         lines.append("server: \(self.appModel.gatewayServerName ?? "—")")
@@ -889,6 +917,9 @@ struct SettingsTab: View {
     }
 
     private var setupStatusLine: String? {
+        if let problem = self.appModel.lastGatewayProblem {
+            return problem.message
+        }
         let trimmedSetup = self.setupStatusText?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
         let gatewayStatus = self.appModel.gatewayStatusText.trimmingCharacters(in: .whitespacesAndNewlines)
         if let friendly = self.friendlyGatewayMessage(from: gatewayStatus) { return friendly }
@@ -987,6 +1018,14 @@ struct SettingsTab: View {
         SettingsNetworkingHelpers.httpURLString(host: host, port: port, fallback: fallback)
     }
 
+    private func retryGatewayConnectionFromProblem() async {
+        if self.manualGatewayEnabled || self.connectingGatewayID == "manual" {
+            await self.connectManual()
+            return
+        }
+        await self.connectLastKnown()
+    }
+
     private func resetOnboarding() {
         // Disconnect first so RootCanvas doesn't instantly mark onboarding complete again.
         self.appModel.disconnectGateway()

apps/ios/Sources/Status/GatewayStatusBuilder.swift

@@ -1,11 +1,24 @@
 import Foundation
+import OpenClawKit
 
 enum GatewayStatusBuilder {
     @MainActor
     static func build(appModel: NodeAppModel) -> StatusPill.GatewayState {
-        if appModel.gatewayServerName != nil { return .connected }
+        self.build(
+            gatewayServerName: appModel.gatewayServerName,
+            lastGatewayProblem: appModel.lastGatewayProblem,
+            gatewayStatusText: appModel.gatewayStatusText)
+    }
 
-        let text = appModel.gatewayStatusText.trimmingCharacters(in: .whitespacesAndNewlines)
+    static func build(
+        gatewayServerName: String?,
+        lastGatewayProblem: GatewayConnectionProblem?,
+        gatewayStatusText: String) -> StatusPill.GatewayState
+    {
+        if gatewayServerName != nil { return .connected }
+        if let lastGatewayProblem, lastGatewayProblem.pauseReconnect { return .error }
+
+        let text = gatewayStatusText.trimmingCharacters(in: .whitespacesAndNewlines)
         if text.localizedCaseInsensitiveContains("connecting") ||
             text.localizedCaseInsensitiveContains("reconnecting")
         {

apps/ios/Sources/Status/StatusActivityBuilder.swift

@@ -16,6 +16,31 @@ enum StatusActivityBuilder {
                 tint: .orange)
         }
 
+        if let gatewayProblem = appModel.lastGatewayProblem {
+            switch gatewayProblem.kind {
+            case .pairingRequired,
+                .pairingRoleUpgradeRequired,
+                .pairingScopeUpgradeRequired,
+                .pairingMetadataUpgradeRequired:
+                return StatusPill.Activity(
+                    title: "Approval pending",
+                    systemImage: "person.crop.circle.badge.clock",
+                    tint: .orange)
+            case .timeout, .connectionRefused, .reachabilityFailed, .websocketCancelled:
+                return StatusPill.Activity(
+                    title: "Check network",
+                    systemImage: "wifi.exclamationmark",
+                    tint: .orange)
+            default:
+                if gatewayProblem.pauseReconnect {
+                    return StatusPill.Activity(
+                        title: "Action required",
+                        systemImage: "exclamationmark.triangle.fill",
+                        tint: .orange)
+                }
+            }
+        }
+
         let gatewayStatus = appModel.gatewayStatusText.trimmingCharacters(in: .whitespacesAndNewlines)
         let gatewayLower = gatewayStatus.lowercased()
         if gatewayLower.contains("repair") {

apps/ios/Tests/ExecApprovalNotificationBridgeTests.swift

@@ -49,6 +49,32 @@ private final class MockNotificationCenter: NotificationCentering, @unchecked Se
         #expect(prompt == ExecApprovalNotificationPrompt(approvalId: "approval-123"))
     }
 
+    @Test func parsePromptMapsReviewAction() {
+        let prompt = ExecApprovalNotificationBridge.parsePrompt(
+            actionIdentifier: ExecApprovalNotificationBridge.reviewActionIdentifier,
+            userInfo: [
+                "openclaw": [
+                    "kind": ExecApprovalNotificationBridge.requestedKind,
+                    "approvalId": "approval-456",
+                ],
+            ])
+
+        #expect(prompt == ExecApprovalNotificationPrompt(approvalId: "approval-456"))
+    }
+
+    @Test func parsePromptIgnoresUnexpectedActionIdentifiers() {
+        let prompt = ExecApprovalNotificationBridge.parsePrompt(
+            actionIdentifier: "openclaw.exec-approval.allow-once",
+            userInfo: [
+                "openclaw": [
+                    "kind": ExecApprovalNotificationBridge.requestedKind,
+                    "approvalId": "approval-789",
+                ],
+            ])
+
+        #expect(prompt == nil)
+    }
+
     @Test @MainActor func handleResolvedPushRemovesMatchingNotifications() async {
         let center = MockNotificationCenter()
         center.delivered = [

apps/ios/Tests/GatewayStatusBuilderTests.swift

@@ -0,0 +1,36 @@
+import OpenClawKit
+import Testing
+@testable import OpenClaw
+
+@Suite struct GatewayStatusBuilderTests {
+    @Test func pausedProblemKeepsErrorStatus() {
+        let state = GatewayStatusBuilder.build(
+            gatewayServerName: nil,
+            lastGatewayProblem: GatewayConnectionProblem(
+                kind: .pairingRequired,
+                owner: .gateway,
+                title: "Pairing required",
+                message: "Approve this device before reconnecting.",
+                requestId: "req-123",
+                retryable: false,
+                pauseReconnect: true),
+            gatewayStatusText: "Reconnecting…")
+
+        #expect(state == .error)
+    }
+
+    @Test func transientProblemAllowsConnectingStatus() {
+        let state = GatewayStatusBuilder.build(
+            gatewayServerName: nil,
+            lastGatewayProblem: GatewayConnectionProblem(
+                kind: .timeout,
+                owner: .network,
+                title: "Connection timed out",
+                message: "The gateway did not respond before the connection timed out.",
+                retryable: true,
+                pauseReconnect: false),
+            gatewayStatusText: "Reconnecting…")
+
+        #expect(state == .connecting)
+    }
+}

apps/ios/Tests/NodeAppModelInvokeTests.swift

@@ -46,16 +46,37 @@ private final class MockWatchMessagingService: @preconcurrency WatchMessagingSer
         transport: "sendMessage")
     var sendError: Error?
     var lastSent: (id: String, params: OpenClawWatchNotifyParams)?
+    var lastSentExecApprovalPrompt: OpenClawWatchExecApprovalPromptMessage?
+    var lastSentExecApprovalResolved: OpenClawWatchExecApprovalResolvedMessage?
+    var lastSentExecApprovalExpired: OpenClawWatchExecApprovalExpiredMessage?
+    var lastSentExecApprovalSnapshot: OpenClawWatchExecApprovalSnapshotMessage?
+    private var statusHandler: (@Sendable (WatchMessagingStatus) -> Void)?
     private var replyHandler: (@Sendable (WatchQuickReplyEvent) -> Void)?
+    private var execApprovalResolveHandler: (@Sendable (WatchExecApprovalResolveEvent) -> Void)?
+    private var execApprovalSnapshotRequestHandler: (@Sendable (WatchExecApprovalSnapshotRequestEvent) -> Void)?
 
     func status() async -> WatchMessagingStatus {
         self.currentStatus
     }
 
+    func setStatusHandler(_ handler: (@Sendable (WatchMessagingStatus) -> Void)?) {
+        self.statusHandler = handler
+    }
+
     func setReplyHandler(_ handler: (@Sendable (WatchQuickReplyEvent) -> Void)?) {
         self.replyHandler = handler
     }
 
+    func setExecApprovalResolveHandler(_ handler: (@Sendable (WatchExecApprovalResolveEvent) -> Void)?) {
+        self.execApprovalResolveHandler = handler
+    }
+
+    func setExecApprovalSnapshotRequestHandler(
+        _ handler: (@Sendable (WatchExecApprovalSnapshotRequestEvent) -> Void)?)
+    {
+        self.execApprovalSnapshotRequestHandler = handler
+    }
+
     func sendNotification(id: String, params: OpenClawWatchNotifyParams) async throws -> WatchNotificationSendResult {
         self.lastSent = (id: id, params: params)
         if let sendError = self.sendError {
@@ -64,9 +85,57 @@ private final class MockWatchMessagingService: @preconcurrency WatchMessagingSer
         return self.nextSendResult
     }
 
+    func sendExecApprovalPrompt(
+        _ message: OpenClawWatchExecApprovalPromptMessage) async throws -> WatchNotificationSendResult
+    {
+        self.lastSentExecApprovalPrompt = message
+        if let sendError = self.sendError {
+            throw sendError
+        }
+        return self.nextSendResult
+    }
+
+    func sendExecApprovalResolved(
+        _ message: OpenClawWatchExecApprovalResolvedMessage) async throws -> WatchNotificationSendResult
+    {
+        self.lastSentExecApprovalResolved = message
+        if let sendError = self.sendError {
+            throw sendError
+        }
+        return self.nextSendResult
+    }
+
+    func sendExecApprovalExpired(
+        _ message: OpenClawWatchExecApprovalExpiredMessage) async throws -> WatchNotificationSendResult
+    {
+        self.lastSentExecApprovalExpired = message
+        if let sendError = self.sendError {
+            throw sendError
+        }
+        return self.nextSendResult
+    }
+
+    func syncExecApprovalSnapshot(
+        _ message: OpenClawWatchExecApprovalSnapshotMessage) async throws -> WatchNotificationSendResult
+    {
+        self.lastSentExecApprovalSnapshot = message
+        if let sendError = self.sendError {
+            throw sendError
+        }
+        return self.nextSendResult
+    }
+
     func emitReply(_ event: WatchQuickReplyEvent) {
         self.replyHandler?(event)
     }
+
+    func emitExecApprovalResolve(_ event: WatchExecApprovalResolveEvent) {
+        self.execApprovalResolveHandler?(event)
+    }
+
+    func emitExecApprovalSnapshotRequest(_ event: WatchExecApprovalSnapshotRequestEvent) {
+        self.execApprovalSnapshotRequestHandler?(event)
+    }
 }
 
 private final class MockBootstrapNotificationCenter: NotificationCentering, @unchecked Sendable {
@@ -184,6 +253,118 @@ private final class MockBootstrapNotificationCenter: NotificationCentering, @unc
         #expect(prompt.id == "approval-active")
     }
 
+    @Test @MainActor func presentingExecApprovalPromptSyncsWatchPrompt() async throws {
+        let watchService = MockWatchMessagingService()
+        let appModel = NodeAppModel(watchMessagingService: watchService)
+        let prompt = try #require(
+            NodeAppModel._test_makeExecApprovalPrompt(
+                id: "approval-watch-sync",
+                commandText: "npm publish",
+                allowedDecisions: ["allow-once", "deny"],
+                host: "gateway",
+                nodeId: "node-1",
+                agentId: "main",
+                expiresAtMs: 1234))
+
+        appModel._test_presentExecApprovalPrompt(prompt)
+        await Task.yield()
+
+        let sent = try #require(watchService.lastSentExecApprovalPrompt)
+        #expect(sent.approval.id == "approval-watch-sync")
+        #expect(sent.approval.allowedDecisions == [.allowOnce, .deny])
+        #expect(sent.approval.host == "gateway")
+        #expect(sent.approval.risk == nil)
+        #expect(sent.resetResolvingState != true)
+    }
+
+    @Test @MainActor func watchExecApprovalSnapshotRequestPublishesCachedApprovalsInBackground() async throws {
+        let watchService = MockWatchMessagingService()
+        let appModel = NodeAppModel(watchMessagingService: watchService)
+        let futureExpiryMs = Int(Date().timeIntervalSince1970 * 1000) + 60_000
+        appModel._test_presentExecApprovalPrompt(
+            try #require(
+                NodeAppModel._test_makeExecApprovalPrompt(
+                    id: "approval-watch-snapshot",
+                    commandText: "echo from watch",
+                    allowedDecisions: ["allow-once", "deny"],
+                    host: "gateway",
+                    nodeId: nil,
+                    agentId: nil,
+                    expiresAtMs: futureExpiryMs)))
+        await Task.yield()
+
+        appModel.setScenePhase(.background)
+        watchService.emitExecApprovalSnapshotRequest(
+            WatchExecApprovalSnapshotRequestEvent(
+                requestId: "snapshot-1",
+                sentAtMs: 111,
+                transport: "sendMessage"))
+        await Task.yield()
+
+        let snapshot = try #require(watchService.lastSentExecApprovalSnapshot)
+        #expect(snapshot.approvals.map(\.id) == ["approval-watch-snapshot"])
+    }
+
+    @Test @MainActor func watchExecApprovalSnapshotRequestSkipsForegroundRecovery() async throws {
+        let watchService = MockWatchMessagingService()
+        let appModel = NodeAppModel(watchMessagingService: watchService)
+        let futureExpiryMs = Int(Date().timeIntervalSince1970 * 1000) + 60_000
+        appModel._test_presentExecApprovalPrompt(
+            try #require(
+                NodeAppModel._test_makeExecApprovalPrompt(
+                    id: "approval-watch-foreground-skip",
+                    commandText: "echo foreground",
+                    allowedDecisions: ["allow-once", "deny"],
+                    host: "gateway",
+                    nodeId: nil,
+                    agentId: nil,
+                    expiresAtMs: futureExpiryMs)))
+        await Task.yield()
+        watchService.lastSentExecApprovalSnapshot = nil
+
+        watchService.emitExecApprovalSnapshotRequest(
+            WatchExecApprovalSnapshotRequestEvent(
+                requestId: "snapshot-foreground",
+                sentAtMs: 222,
+                transport: "sendMessage"))
+        await Task.yield()
+
+        #expect(watchService.lastSentExecApprovalSnapshot == nil)
+    }
+
+    @Test @MainActor func pendingWatchRecoveryIDsAreIncludedWithoutDeliveredNotifications() async {
+        NodeAppModel._test_resetPersistedWatchExecApprovalBridgeState()
+        defer { NodeAppModel._test_resetPersistedWatchExecApprovalBridgeState() }
+
+        let appModel = NodeAppModel(notificationCenter: MockBootstrapNotificationCenter())
+        appModel._test_recordPendingWatchExecApprovalRecoveryID("approval-watch-recovery")
+
+        let ids = await appModel._test_pendingExecApprovalIDsForWatchRecovery()
+        #expect(ids == ["approval-watch-recovery"])
+    }
+
+    @Test @MainActor func presentingExecApprovalPromptClearsPendingWatchRecoveryID() throws {
+        NodeAppModel._test_resetPersistedWatchExecApprovalBridgeState()
+        defer { NodeAppModel._test_resetPersistedWatchExecApprovalBridgeState() }
+
+        let appModel = NodeAppModel(notificationCenter: MockBootstrapNotificationCenter())
+        appModel._test_recordPendingWatchExecApprovalRecoveryID("approval-watch-clear")
+        #expect(appModel._test_pendingWatchExecApprovalRecoveryIDs() == ["approval-watch-clear"])
+
+        appModel._test_presentExecApprovalPrompt(
+            try #require(
+                NodeAppModel._test_makeExecApprovalPrompt(
+                    id: "approval-watch-clear",
+                    commandText: "echo clear",
+                    allowedDecisions: ["allow-once", "deny"],
+                    host: "gateway",
+                    nodeId: nil,
+                    agentId: nil,
+                    expiresAtMs: Int(Date().timeIntervalSince1970 * 1000) + 60_000)))
+
+        #expect(appModel._test_pendingWatchExecApprovalRecoveryIDs().isEmpty)
+    }
+
     @Test func approvalNotificationErrorClassificationPrefersStructuredDetails() {
         let staleError = GatewayResponseError(
             method: "exec.approval.get",
@@ -200,6 +381,48 @@ private final class MockBootstrapNotificationCenter: NotificationCentering, @unc
         #expect(NodeAppModel._test_isApprovalNotificationUnavailableError(unavailableError))
     }
 
+    @Test func backgroundAwareExecApprovalReconnectCoversWatchAndPushPaths() {
+        #expect(
+            NodeAppModel._test_shouldUseBackgroundAwareExecApprovalReconnect(
+                sourceReason: "watch_request",
+                isBackgrounded: true)
+        )
+        #expect(
+            NodeAppModel._test_shouldUseBackgroundAwareExecApprovalReconnect(
+                sourceReason: "push_request",
+                isBackgrounded: true)
+        )
+        #expect(
+            NodeAppModel._test_shouldUseBackgroundAwareExecApprovalReconnect(
+                sourceReason: "watch_resolve",
+                isBackgrounded: true)
+        )
+        #expect(
+            !NodeAppModel._test_shouldUseBackgroundAwareExecApprovalReconnect(
+                sourceReason: "direct",
+                isBackgrounded: true)
+        )
+        #expect(
+            !NodeAppModel._test_shouldUseBackgroundAwareExecApprovalReconnect(
+                sourceReason: "watch_request",
+                isBackgrounded: false)
+        )
+    }
+
+    @Test func watchExecApprovalHydrateFetchesOnlyMissingIDs() {
+        let idsToFetch = NodeAppModel._test_watchExecApprovalIDsNeedingFetch(
+            candidateIDs: ["cached", "pending", "cached", "other", "", "  pending  "],
+            cachedApprovalIDs: ["cached", "also-cached"])
+
+        #expect(idsToFetch == ["pending", "other"])
+    }
+
+    @Test func watchExecApprovalRetryPromptResetsResolvingStateOnlyForRetryReason() {
+        #expect(NodeAppModel._test_shouldResetWatchExecApprovalResolvingStateOnPrompt(reason: "resolve_retry"))
+        #expect(!NodeAppModel._test_shouldResetWatchExecApprovalResolvingStateOnPrompt(reason: "push_request"))
+        #expect(!NodeAppModel._test_shouldResetWatchExecApprovalResolvingStateOnPrompt(reason: "present_prompt"))
+    }
+
     @Test func operatorLoopWaitsForBootstrapHandoffBeforeUsingStoredToken() {
         #expect(
             !NodeAppModel._test_shouldStartOperatorGatewayLoop(
@@ -590,6 +813,7 @@ private final class MockBootstrapNotificationCenter: NotificationCentering, @unc
                 note: nil,
                 sentAtMs: 1234,
                 transport: "transferUserInfo"))
+        await Task.yield()
         #expect(appModel._test_queuedWatchReplyCount() == 1)
     }
 

apps/ios/Tests/OpenClawAppDelegateTests.swift

@@ -0,0 +1,26 @@
+import Testing
+@testable import OpenClaw
+
+@Suite(.serialized) struct OpenClawAppDelegateTests {
+    @Test @MainActor func resolvesRegistryModelBeforeViewTaskAssignsDelegateModel() {
+        let registryModel = NodeAppModel()
+        OpenClawAppModelRegistry.appModel = registryModel
+        defer { OpenClawAppModelRegistry.appModel = nil }
+
+        let delegate = OpenClawAppDelegate()
+
+        #expect(delegate._test_resolvedAppModel() === registryModel)
+    }
+
+    @Test @MainActor func prefersExplicitDelegateModelOverRegistryFallback() {
+        let registryModel = NodeAppModel()
+        let explicitModel = NodeAppModel()
+        OpenClawAppModelRegistry.appModel = registryModel
+        defer { OpenClawAppModelRegistry.appModel = nil }
+
+        let delegate = OpenClawAppDelegate()
+        delegate.appModel = explicitModel
+
+        #expect(delegate._test_resolvedAppModel() === explicitModel)
+    }
+}

apps/ios/WatchExtension/Sources/OpenClawWatchApp.swift

@@ -2,27 +2,79 @@ import SwiftUI
 
 @main
 struct OpenClawWatchApp: App {
+    @Environment(\.scenePhase) private var scenePhase
     @State private var inboxStore = WatchInboxStore()
     @State private var receiver: WatchConnectivityReceiver?
+    @State private var execApprovalRefreshTask: Task<Void, Never>?
 
     var body: some Scene {
         WindowGroup {
-            WatchInboxView(store: self.inboxStore) { action in
-                guard let receiver = self.receiver else { return }
-                let draft = self.inboxStore.makeReplyDraft(action: action)
-                self.inboxStore.markReplySending(actionLabel: action.label)
-                Task { @MainActor in
-                    let result = await receiver.sendReply(draft)
-                    self.inboxStore.markReplyResult(result, actionLabel: action.label)
-                }
-            }
+            WatchInboxView(
+                store: self.inboxStore,
+                onAction: { action in
+                    guard let receiver = self.receiver else { return }
+                    let draft = self.inboxStore.makeReplyDraft(action: action)
+                    self.inboxStore.markReplySending(actionLabel: action.label)
+                    Task { @MainActor in
+                        let result = await receiver.sendReply(draft)
+                        self.inboxStore.markReplyResult(result, actionLabel: action.label)
+                    }
+                },
+                onExecApprovalDecision: { approvalId, decision in
+                    guard let receiver = self.receiver else { return }
+                    self.inboxStore.markExecApprovalSending(approvalId: approvalId, decision: decision)
+                    Task { @MainActor in
+                        let result = await receiver.sendExecApprovalResolve(
+                            approvalId: approvalId,
+                            decision: decision)
+                        self.inboxStore.markExecApprovalSendResult(
+                            approvalId: approvalId,
+                            decision: decision,
+                            result: result)
+                    }
+                },
+                onRefreshExecApprovalReview: {
+                    self.refreshExecApprovalReview(force: true)
+                })
                 .task {
                     if self.receiver == nil {
                         let receiver = WatchConnectivityReceiver(store: self.inboxStore)
                         receiver.activate()
                         self.receiver = receiver
                     }
+                    self.refreshExecApprovalReview()
+                }
+                .onChange(of: self.scenePhase) { _, newPhase in
+                    guard newPhase == .active else { return }
+                    self.refreshExecApprovalReview()
                 }
         }
     }
+
+    private func refreshExecApprovalReview(force: Bool = false) {
+        guard let receiver = self.receiver else { return }
+        guard force || self.inboxStore.shouldAutoRequestExecApprovalSnapshot else { return }
+
+        self.execApprovalRefreshTask?.cancel()
+        self.execApprovalRefreshTask = Task { @MainActor in
+            self.inboxStore.beginExecApprovalReviewLoading()
+            for attempt in 0..<5 {
+                if Task.isCancelled { return }
+                await receiver.requestExecApprovalSnapshot()
+                if !self.inboxStore.execApprovals.isEmpty
+                    || self.inboxStore.hasCompletedExecApprovalSnapshotRefresh
+                {
+                    self.inboxStore.markExecApprovalReviewLoaded()
+                    return
+                }
+                if attempt < 4 {
+                    try? await Task.sleep(nanoseconds: 700_000_000)
+                }
+            }
+            if self.inboxStore.execApprovals.isEmpty {
+                self.inboxStore.markExecApprovalReviewUnavailable(
+                    "Couldn't load approval from your iPhone yet.")
+            }
+        }
+    }
 }

apps/ios/WatchExtension/Sources/WatchConnectivityReceiver.swift

@@ -52,6 +52,31 @@ final class WatchConnectivityReceiver: NSObject, @unchecked Sendable {
         }
     }
 
+    func requestExecApprovalSnapshot() async {
+        await self.ensureActivated()
+        guard let session = self.session else { return }
+        let request = WatchExecApprovalSnapshotRequestMessage(
+            requestId: UUID().uuidString,
+            sentAtMs: Self.nowMs())
+        let payload = Self.encodeSnapshotRequestPayload(request)
+        if session.isReachable {
+            do {
+                try await withCheckedThrowingContinuation(isolation: nil) {
+                    (continuation: CheckedContinuation<Void, Error>) in
+                    session.sendMessage(payload, replyHandler: { _ in
+                        continuation.resume(returning: ())
+                    }, errorHandler: { error in
+                        continuation.resume(throwing: error)
+                    })
+                }
+                return
+            } catch {
+                // Fall through to queued delivery.
+            }
+        }
+        _ = session.transferUserInfo(payload)
+    }
+
     func sendReply(_ draft: WatchReplyDraft) async -> WatchReplySendResult {
         await self.ensureActivated()
         guard let session = self.session else {
@@ -63,7 +88,7 @@ final class WatchConnectivityReceiver: NSObject, @unchecked Sendable {
         }
 
         var payload: [String: Any] = [
-            "type": "watch.reply",
+            "type": WatchPayloadType.reply.rawValue,
             "replyId": draft.replyId,
             "promptId": draft.promptId,
             "actionId": draft.actionId,
@@ -83,11 +108,38 @@ final class WatchConnectivityReceiver: NSObject, @unchecked Sendable {
             payload["note"] = note
         }
 
+        return await self.sendPayload(payload, session: session)
+    }
+
+    func sendExecApprovalResolve(
+        approvalId: String,
+        decision: WatchExecApprovalDecision) async -> WatchReplySendResult
+    {
+        await self.ensureActivated()
+        guard let session = self.session else {
+            return WatchReplySendResult(
+                deliveredImmediately: false,
+                queuedForDelivery: false,
+                transport: "none",
+                errorMessage: "watch session unavailable")
+        }
+
+        let payload = Self.encodeExecApprovalResolvePayload(
+            WatchExecApprovalResolveMessage(
+                approvalId: approvalId,
+                decision: decision,
+                replyId: UUID().uuidString,
+                sentAtMs: Self.nowMs()))
+        return await self.sendPayload(payload, session: session)
+    }
+
+    private func sendPayload(_ payload: [String: Any], session: WCSession) async -> WatchReplySendResult {
         if session.isReachable {
             do {
-                try await withCheckedThrowingContinuation { continuation in
+                try await withCheckedThrowingContinuation(isolation: nil) {
+                    (continuation: CheckedContinuation<Void, Error>) in
                     session.sendMessage(payload, replyHandler: { _ in
-                        continuation.resume()
+                        continuation.resume(returning: ())
                     }, errorHandler: { error in
                         continuation.resume(throwing: error)
                     })
@@ -110,6 +162,10 @@ final class WatchConnectivityReceiver: NSObject, @unchecked Sendable {
             errorMessage: nil)
     }
 
+    private static func nowMs() -> Int {
+        Int(Date().timeIntervalSince1970 * 1000)
+    }
+
     private static func normalizeObject(_ value: Any) -> [String: Any]? {
         if let object = value as? [String: Any] {
             return object
@@ -147,7 +203,9 @@ final class WatchConnectivityReceiver: NSObject, @unchecked Sendable {
     }
 
     private static func parseNotificationPayload(_ payload: [String: Any]) -> WatchNotifyMessage? {
-        guard let type = payload["type"] as? String, type == "watch.notify" else {
+        guard let type = payload["type"] as? String,
+              type == WatchPayloadType.notify.rawValue
+        else {
             return nil
         }
 
@@ -189,6 +247,153 @@ final class WatchConnectivityReceiver: NSObject, @unchecked Sendable {
             risk: risk,
             actions: actions)
     }
+
+    private static func parseExecApprovalDecision(_ value: Any?) -> WatchExecApprovalDecision? {
+        let raw = (value as? String)?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
+        return WatchExecApprovalDecision(rawValue: raw)
+    }
+
+    private static func parseExecApprovalItem(_ value: Any?) -> WatchExecApprovalItem? {
+        guard let payload = value.flatMap(Self.normalizeObject) else {
+            return nil
+        }
+        let id = (payload["id"] as? String)?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
+        let commandText = (payload["commandText"] as? String)?
+            .trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
+        guard !id.isEmpty, !commandText.isEmpty else {
+            return nil
+        }
+        let commandPreview = (payload["commandPreview"] as? String)?
+            .trimmingCharacters(in: .whitespacesAndNewlines)
+        let host = (payload["host"] as? String)?.trimmingCharacters(in: .whitespacesAndNewlines)
+        let nodeId = (payload["nodeId"] as? String)?.trimmingCharacters(in: .whitespacesAndNewlines)
+        let agentId = (payload["agentId"] as? String)?.trimmingCharacters(in: .whitespacesAndNewlines)
+        let expiresAtMs = (payload["expiresAtMs"] as? Int) ?? (payload["expiresAtMs"] as? NSNumber)?.intValue
+        let riskRaw = (payload["risk"] as? String)?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
+        let risk = WatchRiskLevel(rawValue: riskRaw)
+        let allowedDecisions = (payload["allowedDecisions"] as? [Any] ?? []).compactMap {
+            Self.parseExecApprovalDecision($0)
+        }
+        return WatchExecApprovalItem(
+            id: id,
+            commandText: commandText,
+            commandPreview: commandPreview,
+            host: host,
+            nodeId: nodeId,
+            agentId: agentId,
+            expiresAtMs: expiresAtMs,
+            allowedDecisions: allowedDecisions,
+            risk: risk)
+    }
+
+    private static func parseExecApprovalPromptPayload(
+        _ payload: [String: Any]) -> WatchExecApprovalPromptMessage?
+    {
+        guard let type = payload["type"] as? String,
+              type == WatchPayloadType.execApprovalPrompt.rawValue,
+              let approval = Self.parseExecApprovalItem(payload["approval"])
+        else {
+            return nil
+        }
+        let sentAtMs = (payload["sentAtMs"] as? Int) ?? (payload["sentAtMs"] as? NSNumber)?.intValue
+        let deliveryId = (payload["deliveryId"] as? String)?.trimmingCharacters(in: .whitespacesAndNewlines)
+        let resetResolvingState = payload["resetResolvingState"] as? Bool
+        return WatchExecApprovalPromptMessage(
+            approval: approval,
+            sentAtMs: sentAtMs,
+            deliveryId: deliveryId,
+            resetResolvingState: resetResolvingState)
+    }
+
+    private static func parseExecApprovalResolvedPayload(
+        _ payload: [String: Any]) -> WatchExecApprovalResolvedMessage?
+    {
+        guard let type = payload["type"] as? String,
+              type == WatchPayloadType.execApprovalResolved.rawValue
+        else {
+            return nil
+        }
+        let approvalId = (payload["approvalId"] as? String)?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
+        guard !approvalId.isEmpty else { return nil }
+        let decision = Self.parseExecApprovalDecision(payload["decision"])
+        let resolvedAtMs = (payload["resolvedAtMs"] as? Int)
+            ?? (payload["resolvedAtMs"] as? NSNumber)?.intValue
+        let source = (payload["source"] as? String)?.trimmingCharacters(in: .whitespacesAndNewlines)
+        return WatchExecApprovalResolvedMessage(
+            approvalId: approvalId,
+            decision: decision,
+            resolvedAtMs: resolvedAtMs,
+            source: source)
+    }
+
+    private static func parseExecApprovalExpiredPayload(
+        _ payload: [String: Any]) -> WatchExecApprovalExpiredMessage?
+    {
+        guard let type = payload["type"] as? String,
+              type == WatchPayloadType.execApprovalExpired.rawValue
+        else {
+            return nil
+        }
+        let approvalId = (payload["approvalId"] as? String)?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
+        let rawReason = (payload["reason"] as? String)?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
+        guard !approvalId.isEmpty,
+              let reason = WatchExecApprovalCloseReason(rawValue: rawReason)
+        else {
+            return nil
+        }
+        let expiredAtMs = (payload["expiredAtMs"] as? Int) ?? (payload["expiredAtMs"] as? NSNumber)?.intValue
+        return WatchExecApprovalExpiredMessage(
+            approvalId: approvalId,
+            reason: reason,
+            expiredAtMs: expiredAtMs)
+    }
+
+    private static func parseExecApprovalSnapshotPayload(
+        _ payload: [String: Any]) -> WatchExecApprovalSnapshotMessage?
+    {
+        guard let type = payload["type"] as? String,
+              type == WatchPayloadType.execApprovalSnapshot.rawValue
+        else {
+            return nil
+        }
+        let approvals = (payload["approvals"] as? [Any] ?? []).compactMap { item in
+            Self.parseExecApprovalItem(item)
+        }
+        let sentAtMs = (payload["sentAtMs"] as? Int) ?? (payload["sentAtMs"] as? NSNumber)?.intValue
+        let snapshotId = (payload["snapshotId"] as? String)?.trimmingCharacters(in: .whitespacesAndNewlines)
+        return WatchExecApprovalSnapshotMessage(
+            approvals: approvals,
+            sentAtMs: sentAtMs,
+            snapshotId: snapshotId)
+    }
+
+    private static func encodeSnapshotRequestPayload(
+        _ request: WatchExecApprovalSnapshotRequestMessage) -> [String: Any]
+    {
+        var payload: [String: Any] = [
+            "type": WatchPayloadType.execApprovalSnapshotRequest.rawValue,
+            "requestId": request.requestId,
+        ]
+        if let sentAtMs = request.sentAtMs {
+            payload["sentAtMs"] = sentAtMs
+        }
+        return payload
+    }
+
+    private static func encodeExecApprovalResolvePayload(
+        _ message: WatchExecApprovalResolveMessage) -> [String: Any]
+    {
+        var payload: [String: Any] = [
+            "type": WatchPayloadType.execApprovalResolve.rawValue,
+            "approvalId": message.approvalId,
+            "decision": message.decision.rawValue,
+            "replyId": message.replyId,
+        ]
+        if let sentAtMs = message.sentAtMs {
+            payload["sentAtMs"] = sentAtMs
+        }
+        return payload
+    }
 }
 
 extension WatchConnectivityReceiver: WCSessionDelegate {
@@ -196,13 +401,14 @@ extension WatchConnectivityReceiver: WCSessionDelegate {
         _: WCSession,
         activationDidCompleteWith _: WCSessionActivationState,
         error _: (any Error)?)
-    {}
+    {
+        Task {
+            await self.requestExecApprovalSnapshot()
+        }
+    }
 
     func session(_: WCSession, didReceiveMessage message: [String: Any]) {
-        guard let incoming = Self.parseNotificationPayload(message) else { return }
-        Task { @MainActor in
-            self.store.consume(message: incoming, transport: "sendMessage")
-        }
+        self.consumeIncomingPayload(message, transport: "sendMessage")
     }
 
     func session(
@@ -210,27 +416,47 @@ extension WatchConnectivityReceiver: WCSessionDelegate {
         didReceiveMessage message: [String: Any],
         replyHandler: @escaping ([String: Any]) -> Void)
     {
-        guard let incoming = Self.parseNotificationPayload(message) else {
-            replyHandler(["ok": false])
-            return
-        }
         replyHandler(["ok": true])
-        Task { @MainActor in
-            self.store.consume(message: incoming, transport: "sendMessage")
-        }
+        self.consumeIncomingPayload(message, transport: "sendMessage")
     }
 
     func session(_: WCSession, didReceiveUserInfo userInfo: [String: Any]) {
-        guard let incoming = Self.parseNotificationPayload(userInfo) else { return }
-        Task { @MainActor in
-            self.store.consume(message: incoming, transport: "transferUserInfo")
-        }
+        self.consumeIncomingPayload(userInfo, transport: "transferUserInfo")
     }
 
     func session(_: WCSession, didReceiveApplicationContext applicationContext: [String: Any]) {
-        guard let incoming = Self.parseNotificationPayload(applicationContext) else { return }
-        Task { @MainActor in
-            self.store.consume(message: incoming, transport: "applicationContext")
+        self.consumeIncomingPayload(applicationContext, transport: "applicationContext")
+    }
+
+    private func consumeIncomingPayload(_ payload: [String: Any], transport: String) {
+        if let incoming = Self.parseNotificationPayload(payload) {
+            Task { @MainActor in
+                self.store.consume(message: incoming, transport: transport)
+            }
+            return
+        }
+        if let prompt = Self.parseExecApprovalPromptPayload(payload) {
+            Task { @MainActor in
+                self.store.consume(execApprovalPrompt: prompt, transport: transport)
+            }
+            return
+        }
+        if let resolved = Self.parseExecApprovalResolvedPayload(payload) {
+            Task { @MainActor in
+                self.store.consume(execApprovalResolved: resolved)
+            }
+            return
+        }
+        if let expired = Self.parseExecApprovalExpiredPayload(payload) {
+            Task { @MainActor in
+                self.store.consume(execApprovalExpired: expired)
+            }
+            return
+        }
+        if let snapshot = Self.parseExecApprovalSnapshotPayload(payload) {
+            Task { @MainActor in
+                self.store.consume(execApprovalSnapshot: snapshot, transport: transport)
+            }
         }
     }
 }

apps/ios/WatchExtension/Sources/WatchInboxStore.swift

@@ -3,6 +3,86 @@ import Observation
 import UserNotifications
 import WatchKit
 
+enum WatchPayloadType: String, Codable, Sendable, Equatable {
+    case notify = "watch.notify"
+    case reply = "watch.reply"
+    case execApprovalPrompt = "watch.execApproval.prompt"
+    case execApprovalResolve = "watch.execApproval.resolve"
+    case execApprovalResolved = "watch.execApproval.resolved"
+    case execApprovalExpired = "watch.execApproval.expired"
+    case execApprovalSnapshot = "watch.execApproval.snapshot"
+    case execApprovalSnapshotRequest = "watch.execApproval.snapshotRequest"
+}
+
+enum WatchRiskLevel: String, Codable, Sendable, Equatable {
+    case low
+    case medium
+    case high
+}
+
+enum WatchExecApprovalDecision: String, Codable, Sendable, Equatable {
+    case allowOnce = "allow-once"
+    case deny
+}
+
+enum WatchExecApprovalCloseReason: String, Codable, Sendable, Equatable {
+    case expired
+    case notFound = "not-found"
+    case unavailable
+    case replaced
+    case resolved
+}
+
+struct WatchExecApprovalItem: Codable, Sendable, Equatable, Identifiable {
+    var id: String
+    var commandText: String
+    var commandPreview: String?
+    var host: String?
+    var nodeId: String?
+    var agentId: String?
+    var expiresAtMs: Int?
+    var allowedDecisions: [WatchExecApprovalDecision]
+    var risk: WatchRiskLevel?
+}
+
+struct WatchExecApprovalPromptMessage: Codable, Sendable, Equatable {
+    var approval: WatchExecApprovalItem
+    var sentAtMs: Int?
+    var deliveryId: String?
+    var resetResolvingState: Bool?
+}
+
+struct WatchExecApprovalResolvedMessage: Codable, Sendable, Equatable {
+    var approvalId: String
+    var decision: WatchExecApprovalDecision?
+    var resolvedAtMs: Int?
+    var source: String?
+}
+
+struct WatchExecApprovalExpiredMessage: Codable, Sendable, Equatable {
+    var approvalId: String
+    var reason: WatchExecApprovalCloseReason
+    var expiredAtMs: Int?
+}
+
+struct WatchExecApprovalSnapshotMessage: Codable, Sendable, Equatable {
+    var approvals: [WatchExecApprovalItem]
+    var sentAtMs: Int?
+    var snapshotId: String?
+}
+
+struct WatchExecApprovalSnapshotRequestMessage: Codable, Sendable, Equatable {
+    var requestId: String
+    var sentAtMs: Int?
+}
+
+struct WatchExecApprovalResolveMessage: Codable, Sendable, Equatable {
+    var approvalId: String
+    var decision: WatchExecApprovalDecision
+    var replyId: String
+    var sentAtMs: Int?
+}
+
 struct WatchPromptAction: Codable, Sendable, Equatable, Identifiable {
     var id: String
     var label: String
@@ -23,6 +103,18 @@ struct WatchNotifyMessage: Sendable {
     var actions: [WatchPromptAction]
 }
 
+struct WatchExecApprovalRecord: Codable, Sendable, Equatable, Identifiable {
+    var approval: WatchExecApprovalItem
+    var transport: String
+    var updatedAt: Date
+    var isResolving: Bool
+    var pendingDecision: WatchExecApprovalDecision?
+    var statusText: String?
+    var statusAt: Date?
+
+    var id: String { self.approval.id }
+}
+
 @MainActor @Observable final class WatchInboxStore {
     private struct PersistedState: Codable {
         var title: String
@@ -39,13 +131,20 @@ struct WatchNotifyMessage: Sendable {
         var actions: [WatchPromptAction]?
         var replyStatusText: String?
         var replyStatusAt: Date?
+        var execApprovals: [WatchExecApprovalRecord]
+        var selectedExecApprovalID: String?
+        var lastExecApprovalSnapshotID: String?
+        var lastExecApprovalOutcomeText: String?
+        var lastExecApprovalOutcomeAt: Date?
     }
 
-    private static let persistedStateKey = "watch.inbox.state.v1"
+    private static let persistedStateKey = "watch.inbox.state.v2"
+    private static let defaultTitle = "OpenClaw"
+    private static let defaultBody = "Waiting for messages from your iPhone."
     private let defaults: UserDefaults
 
-    var title = "OpenClaw"
-    var body = "Waiting for messages from your iPhone."
+    var title = WatchInboxStore.defaultTitle
+    var body = WatchInboxStore.defaultBody
     var transport = "none"
     var updatedAt: Date?
     var promptId: String?
@@ -58,16 +157,88 @@ struct WatchNotifyMessage: Sendable {
     var replyStatusText: String?
     var replyStatusAt: Date?
     var isReplySending = false
+    var execApprovals: [WatchExecApprovalRecord] = []
+    var selectedExecApprovalID: String?
+    var lastExecApprovalOutcomeText: String?
+    var lastExecApprovalOutcomeAt: Date?
+    var isExecApprovalReviewLoading = false
+    var execApprovalReviewStatusText: String?
+    var execApprovalReviewStatusAt: Date?
+    private var lastExecApprovalSnapshotID: String?
+    private var hasCompletedExecApprovalSnapshotRefreshInSession = false
     private var lastDeliveryKey: String?
 
     init(defaults: UserDefaults = .standard) {
         self.defaults = defaults
         self.restorePersistedState()
+        self.pruneExpiredExecApprovals(nowMs: Self.nowMs())
         Task {
             await self.ensureNotificationAuthorization()
         }
     }
 
+    var sortedExecApprovals: [WatchExecApprovalRecord] {
+        self.execApprovals.sorted { lhs, rhs in
+            let lhsExpires = lhs.approval.expiresAtMs ?? Int.max
+            let rhsExpires = rhs.approval.expiresAtMs ?? Int.max
+            if lhsExpires != rhsExpires {
+                return lhsExpires < rhsExpires
+            }
+            return lhs.updatedAt > rhs.updatedAt
+        }
+    }
+
+    var activeExecApproval: WatchExecApprovalRecord? {
+        if let selectedExecApprovalID,
+           let selected = self.execApprovals.first(where: { $0.id == selectedExecApprovalID })
+        {
+            return selected
+        }
+        return self.sortedExecApprovals.first
+    }
+
+    var shouldAutoRequestExecApprovalSnapshot: Bool {
+        self.execApprovals.isEmpty
+            && self.actions.isEmpty
+            && self.title == Self.defaultTitle
+            && self.body == Self.defaultBody
+            && !self.hasCompletedExecApprovalSnapshotRefreshInSession
+    }
+
+    var hasCompletedExecApprovalSnapshotRefresh: Bool {
+        self.hasCompletedExecApprovalSnapshotRefreshInSession
+    }
+
+    var shouldShowExecApprovalReviewStatus: Bool {
+        self.execApprovals.isEmpty && !(self.execApprovalReviewStatusText?.isEmpty ?? true)
+    }
+
+    func beginExecApprovalReviewLoading() {
+        guard self.execApprovals.isEmpty else {
+            self.markExecApprovalReviewLoaded()
+            return
+        }
+        self.isExecApprovalReviewLoading = true
+        self.execApprovalReviewStatusText = "Loading approval from iPhone…"
+        self.execApprovalReviewStatusAt = Date()
+    }
+
+    func markExecApprovalReviewLoaded() {
+        self.isExecApprovalReviewLoading = false
+        self.execApprovalReviewStatusText = nil
+        self.execApprovalReviewStatusAt = nil
+    }
+
+    func markExecApprovalReviewUnavailable(_ message: String) {
+        guard self.execApprovals.isEmpty else {
+            self.markExecApprovalReviewLoaded()
+            return
+        }
+        self.isExecApprovalReviewLoading = false
+        self.execApprovalReviewStatusText = message
+        self.execApprovalReviewStatusAt = Date()
+    }
+
     func consume(message: WatchNotifyMessage, transport: String) {
         let messageID = message.id?
             .trimmingCharacters(in: .whitespacesAndNewlines)
@@ -82,6 +253,7 @@ struct WatchNotifyMessage: Sendable {
         self.title = normalizedTitle
         self.body = message.body
         self.transport = transport
+        self.markExecApprovalReviewLoaded()
         self.updatedAt = Date()
         self.promptId = message.promptId
         self.sessionKey = message.sessionKey
@@ -105,6 +277,209 @@ struct WatchNotifyMessage: Sendable {
         }
     }
 
+    func consume(
+        execApprovalPrompt message: WatchExecApprovalPromptMessage,
+        transport: String)
+    {
+        self.pruneExpiredExecApprovals(nowMs: Self.nowMs())
+        self.upsertExecApproval(
+            message.approval,
+            transport: transport,
+            keepSelectionIfPossible: true,
+            resetResolvingState: message.resetResolvingState == true)
+        self.markExecApprovalReviewLoaded()
+        self.lastExecApprovalOutcomeText = nil
+        self.lastExecApprovalOutcomeAt = nil
+
+        Task {
+            await self.postLocalNotification(
+                identifier: "watch.execApproval.\(message.approval.id)",
+                title: "Exec approval required",
+                body: message.approval.commandPreview ?? message.approval.commandText,
+                risk: message.approval.risk?.rawValue)
+        }
+    }
+
+    func consume(
+        execApprovalSnapshot message: WatchExecApprovalSnapshotMessage,
+        transport: String)
+    {
+        let snapshotID = message.snapshotId?.trimmingCharacters(in: .whitespacesAndNewlines)
+        if let snapshotID, !snapshotID.isEmpty, snapshotID == self.lastExecApprovalSnapshotID {
+            return
+        }
+
+        let existingRecordsByID = Dictionary(
+            uniqueKeysWithValues: self.execApprovals.map { ($0.id, $0) })
+        self.execApprovals = message.approvals.map { approval in
+            self.mergedExecApprovalRecord(
+                approval: approval,
+                transport: transport,
+                existingRecord: existingRecordsByID[approval.id])
+        }
+        self.lastExecApprovalSnapshotID = snapshotID
+        self.hasCompletedExecApprovalSnapshotRefreshInSession = true
+        if let selectedExecApprovalID,
+           !self.execApprovals.contains(where: { $0.id == selectedExecApprovalID })
+        {
+            self.selectedExecApprovalID = self.sortedExecApprovals.first?.id
+        } else if self.selectedExecApprovalID == nil {
+            self.selectedExecApprovalID = self.sortedExecApprovals.first?.id
+        }
+        self.pruneExpiredExecApprovals(nowMs: Self.nowMs())
+        self.markExecApprovalReviewLoaded()
+        self.persistState()
+    }
+
+    func consume(execApprovalResolved message: WatchExecApprovalResolvedMessage) {
+        self.removeExecApproval(id: message.approvalId)
+        let statusText: String
+        switch message.decision {
+        case .allowOnce:
+            statusText = "Allowed once"
+        case .deny:
+            statusText = "Denied"
+        case nil:
+            statusText = "Approval resolved"
+        }
+        self.lastExecApprovalOutcomeText = statusText
+        self.lastExecApprovalOutcomeAt = Date()
+        self.persistState()
+    }
+
+    func consume(execApprovalExpired message: WatchExecApprovalExpiredMessage) {
+        self.removeExecApproval(id: message.approvalId)
+        let statusText: String
+        switch message.reason {
+        case .expired:
+            statusText = "Approval expired"
+        case .notFound:
+            statusText = "Approval no longer available"
+        case .resolved:
+            statusText = "Approval resolved elsewhere"
+        case .replaced:
+            statusText = "Approval replaced"
+        case .unavailable:
+            statusText = "Approval unavailable"
+        }
+        self.lastExecApprovalOutcomeText = statusText
+        self.lastExecApprovalOutcomeAt = Date()
+        self.persistState()
+    }
+
+    func selectExecApproval(id: String) {
+        let normalizedID = id.trimmingCharacters(in: .whitespacesAndNewlines)
+        guard !normalizedID.isEmpty else { return }
+        guard self.execApprovals.contains(where: { $0.id == normalizedID }) else { return }
+        self.selectedExecApprovalID = normalizedID
+        self.persistState()
+    }
+
+    func markExecApprovalSending(approvalId: String, decision: WatchExecApprovalDecision) {
+        guard let index = self.execApprovals.firstIndex(where: { $0.id == approvalId }) else { return }
+        self.execApprovals[index].isResolving = true
+        self.execApprovals[index].pendingDecision = decision
+        self.execApprovals[index].statusText = "Sending \(Self.decisionLabel(decision))…"
+        self.execApprovals[index].statusAt = Date()
+        self.persistState()
+    }
+
+    func markExecApprovalSendResult(
+        approvalId: String,
+        decision: WatchExecApprovalDecision,
+        result: WatchReplySendResult)
+    {
+        guard let index = self.execApprovals.firstIndex(where: { $0.id == approvalId }) else { return }
+        if let errorMessage = result.errorMessage, !errorMessage.isEmpty {
+            self.execApprovals[index].isResolving = false
+            self.execApprovals[index].statusText = "Failed: \(errorMessage)"
+        } else if result.deliveredImmediately {
+            self.execApprovals[index].isResolving = true
+            self.execApprovals[index].statusText = "\(Self.decisionLabel(decision)): sent"
+        } else if result.queuedForDelivery {
+            self.execApprovals[index].isResolving = true
+            self.execApprovals[index].statusText = "\(Self.decisionLabel(decision)): queued"
+        } else {
+            self.execApprovals[index].isResolving = true
+            self.execApprovals[index].statusText = "\(Self.decisionLabel(decision)): sent"
+        }
+        self.execApprovals[index].pendingDecision = result.errorMessage == nil ? decision : nil
+        self.execApprovals[index].statusAt = Date()
+        self.persistState()
+    }
+
+    private func upsertExecApproval(
+        _ approval: WatchExecApprovalItem,
+        transport: String,
+        keepSelectionIfPossible: Bool,
+        resetResolvingState: Bool = false)
+    {
+        if let index = self.execApprovals.firstIndex(where: { $0.id == approval.id }) {
+            self.execApprovals[index] = self.mergedExecApprovalRecord(
+                approval: approval,
+                transport: transport,
+                existingRecord: self.execApprovals[index],
+                resetResolvingState: resetResolvingState)
+        } else {
+            self.execApprovals.append(
+                self.mergedExecApprovalRecord(
+                    approval: approval,
+                    transport: transport,
+                    existingRecord: nil,
+                    resetResolvingState: resetResolvingState))
+        }
+        if !keepSelectionIfPossible || self.selectedExecApprovalID == nil {
+            self.selectedExecApprovalID = approval.id
+        }
+        self.persistState()
+    }
+
+    private func mergedExecApprovalRecord(
+        approval: WatchExecApprovalItem,
+        transport: String,
+        existingRecord: WatchExecApprovalRecord?,
+        resetResolvingState: Bool = false) -> WatchExecApprovalRecord
+    {
+        // Preserve in-flight state across ordinary snapshot/prompt refreshes so duplicate
+        // submissions stay disabled, but clear it when the iPhone explicitly republishes a
+        // prompt after a failed resolve so the watch can retry.
+        let isResolving = resetResolvingState ? false : (existingRecord?.isResolving ?? false)
+        let pendingDecision = resetResolvingState ? nil : existingRecord?.pendingDecision
+        let statusText = resetResolvingState ? nil : existingRecord?.statusText
+        let statusAt = resetResolvingState ? nil : existingRecord?.statusAt
+        return WatchExecApprovalRecord(
+            approval: approval,
+            transport: transport,
+            updatedAt: Date(),
+            isResolving: isResolving,
+            pendingDecision: pendingDecision,
+            statusText: statusText,
+            statusAt: statusAt)
+    }
+
+    private func removeExecApproval(id: String) {
+        let normalizedID = id.trimmingCharacters(in: .whitespacesAndNewlines)
+        guard !normalizedID.isEmpty else { return }
+        self.execApprovals.removeAll { $0.id == normalizedID }
+        if self.selectedExecApprovalID == normalizedID {
+            self.selectedExecApprovalID = self.sortedExecApprovals.first?.id
+        }
+        self.persistState()
+    }
+
+    private func pruneExpiredExecApprovals(nowMs: Int) {
+        self.execApprovals.removeAll { record in
+            guard let expiresAtMs = record.approval.expiresAtMs else { return false }
+            return expiresAtMs <= nowMs
+        }
+        if let selectedExecApprovalID,
+           !self.execApprovals.contains(where: { $0.id == selectedExecApprovalID })
+        {
+            self.selectedExecApprovalID = self.sortedExecApprovals.first?.id
+        }
+        self.persistState()
+    }
+
     private func restorePersistedState() {
         guard let data = self.defaults.data(forKey: Self.persistedStateKey),
             let state = try? JSONDecoder().decode(PersistedState.self, from: data)
@@ -126,10 +501,15 @@ struct WatchNotifyMessage: Sendable {
         self.actions = state.actions ?? []
         self.replyStatusText = state.replyStatusText
         self.replyStatusAt = state.replyStatusAt
+        self.execApprovals = state.execApprovals
+        self.selectedExecApprovalID = state.selectedExecApprovalID
+        self.lastExecApprovalSnapshotID = state.lastExecApprovalSnapshotID
+        self.lastExecApprovalOutcomeText = state.lastExecApprovalOutcomeText
+        self.lastExecApprovalOutcomeAt = state.lastExecApprovalOutcomeAt
     }
 
     private func persistState() {
-        guard let updatedAt = self.updatedAt else { return }
+        let updatedAt = self.updatedAt ?? self.lastExecApprovalOutcomeAt ?? Date()
         let state = PersistedState(
             title: self.title,
             body: self.body,
@@ -144,7 +524,12 @@ struct WatchNotifyMessage: Sendable {
             risk: self.risk,
             actions: self.actions,
             replyStatusText: self.replyStatusText,
-            replyStatusAt: self.replyStatusAt)
+            replyStatusAt: self.replyStatusAt,
+            execApprovals: self.execApprovals,
+            selectedExecApprovalID: self.selectedExecApprovalID,
+            lastExecApprovalSnapshotID: self.lastExecApprovalSnapshotID,
+            lastExecApprovalOutcomeText: self.lastExecApprovalOutcomeText,
+            lastExecApprovalOutcomeAt: self.lastExecApprovalOutcomeAt)
         guard let data = try? JSONEncoder().encode(state) else { return }
         self.defaults.set(data, forKey: Self.persistedStateKey)
     }
@@ -187,7 +572,7 @@ struct WatchNotifyMessage: Sendable {
             actionLabel: action.label,
             sessionKey: self.sessionKey,
             note: nil,
-            sentAtMs: Int(Date().timeIntervalSince1970 * 1000))
+            sentAtMs: Self.nowMs())
     }
 
     func markReplySending(actionLabel: String) {
@@ -227,4 +612,17 @@ struct WatchNotifyMessage: Sendable {
         _ = try? await UNUserNotificationCenter.current().add(request)
         WKInterfaceDevice.current().play(self.mapHapticRisk(risk))
     }
+
+    private static func decisionLabel(_ decision: WatchExecApprovalDecision) -> String {
+        switch decision {
+        case .allowOnce:
+            "Allow Once"
+        case .deny:
+            "Deny"
+        }
+    }
+
+    private static func nowMs() -> Int {
+        Int(Date().timeIntervalSince1970 * 1000)
+    }
 }

apps/ios/WatchExtension/Sources/WatchInboxView.swift

@@ -1,7 +1,246 @@
 import SwiftUI
 
 struct WatchInboxView: View {
-    @Bindable var store: WatchInboxStore
+    var store: WatchInboxStore
+    var onAction: ((WatchPromptAction) -> Void)?
+    var onExecApprovalDecision: ((String, WatchExecApprovalDecision) -> Void)?
+    var onRefreshExecApprovalReview: (() -> Void)?
+
+    var body: some View {
+        NavigationStack {
+            if self.store.sortedExecApprovals.count == 1,
+               let record = self.store.activeExecApproval
+            {
+                WatchExecApprovalDetailView(
+                    store: self.store,
+                    record: record,
+                    onDecision: self.onExecApprovalDecision)
+            } else if !self.store.sortedExecApprovals.isEmpty {
+                WatchExecApprovalListView(
+                    store: self.store,
+                    onDecision: self.onExecApprovalDecision)
+            } else if self.store.shouldShowExecApprovalReviewStatus {
+                WatchExecApprovalLoadingView(
+                    store: self.store,
+                    onRetry: self.onRefreshExecApprovalReview)
+            } else {
+                WatchGenericInboxView(store: self.store, onAction: self.onAction)
+            }
+        }
+    }
+}
+
+private struct WatchExecApprovalLoadingView: View {
+    var store: WatchInboxStore
+    var onRetry: (() -> Void)?
+
+    var body: some View {
+        ScrollView {
+            VStack(alignment: .leading, spacing: 10) {
+                Text("Exec approval")
+                    .font(.headline)
+
+                if self.store.isExecApprovalReviewLoading {
+                    ProgressView()
+                        .frame(maxWidth: .infinity, alignment: .leading)
+                }
+
+                if let statusText = self.store.execApprovalReviewStatusText, !statusText.isEmpty {
+                    Text(statusText)
+                        .font(.body)
+                        .fixedSize(horizontal: false, vertical: true)
+                }
+
+                if !self.store.isExecApprovalReviewLoading {
+                    Button("Retry") {
+                        self.onRetry?()
+                    }
+                }
+
+                Text("Keep your iPhone nearby and unlocked if review details take a moment to appear.")
+                    .font(.footnote)
+                    .foregroundStyle(.secondary)
+                    .fixedSize(horizontal: false, vertical: true)
+            }
+            .frame(maxWidth: .infinity, alignment: .leading)
+            .padding()
+        }
+        .navigationTitle("Exec approval")
+    }
+}
+
+private struct WatchExecApprovalListView: View {
+    var store: WatchInboxStore
+    var onDecision: ((String, WatchExecApprovalDecision) -> Void)?
+
+    var body: some View {
+        List {
+            Section("Exec approvals") {
+                ForEach(self.store.sortedExecApprovals) { record in
+                    NavigationLink {
+                        WatchExecApprovalDetailView(
+                            store: self.store,
+                            record: record,
+                            onDecision: self.onDecision)
+                    } label: {
+                        VStack(alignment: .leading, spacing: 4) {
+                            Text(record.approval.commandPreview ?? record.approval.commandText)
+                                .font(.headline)
+                                .lineLimit(2)
+                            Text(self.metadataLine(for: record))
+                                .font(.footnote)
+                                .foregroundStyle(.secondary)
+                                .lineLimit(2)
+                            if let statusText = record.statusText, !statusText.isEmpty {
+                                Text(statusText)
+                                    .font(.footnote)
+                                    .foregroundStyle(record.isResolving ? Color.secondary : Color.red)
+                                    .lineLimit(2)
+                            }
+                        }
+                    }
+                }
+            }
+
+            if let outcome = self.store.lastExecApprovalOutcomeText, !outcome.isEmpty {
+                Section("Last result") {
+                    Text(outcome)
+                        .font(.footnote)
+                        .foregroundStyle(.secondary)
+                }
+            }
+        }
+        .navigationTitle("Approvals")
+    }
+
+    private func metadataLine(for record: WatchExecApprovalRecord) -> String {
+        var parts: [String] = []
+        if let host = record.approval.host, !host.isEmpty {
+            parts.append(host)
+        }
+        if let nodeId = record.approval.nodeId, !nodeId.isEmpty {
+            parts.append(nodeId)
+        }
+        if let expiresText = Self.expiresText(record.approval.expiresAtMs) {
+            parts.append(expiresText)
+        }
+        return parts.isEmpty ? "Pending review" : parts.joined(separator: " · ")
+    }
+
+    private static func expiresText(_ expiresAtMs: Int?) -> String? {
+        guard let expiresAtMs else { return nil }
+        let deltaSeconds = max(0, (expiresAtMs - Int(Date().timeIntervalSince1970 * 1000)) / 1000)
+        if deltaSeconds < 60 {
+            return "Expires in <1m"
+        }
+        return "Expires in \(deltaSeconds / 60)m"
+    }
+}
+
+private struct WatchExecApprovalDetailView: View {
+    var store: WatchInboxStore
+    let record: WatchExecApprovalRecord
+    var onDecision: ((String, WatchExecApprovalDecision) -> Void)?
+
+    var body: some View {
+        ScrollView {
+            VStack(alignment: .leading, spacing: 10) {
+                Text(self.record.approval.commandText)
+                    .font(.headline)
+                    .fixedSize(horizontal: false, vertical: true)
+
+                if let host = self.record.approval.host, !host.isEmpty {
+                    self.metadataRow(label: "Host", value: host)
+                }
+                if let nodeId = self.record.approval.nodeId, !nodeId.isEmpty {
+                    self.metadataRow(label: "Node", value: nodeId)
+                }
+                if let agentId = self.record.approval.agentId, !agentId.isEmpty {
+                    self.metadataRow(label: "Agent", value: agentId)
+                }
+                if let expiresText = Self.expiresText(self.record.approval.expiresAtMs) {
+                    self.metadataRow(label: "Expires", value: expiresText)
+                }
+                if let riskText = self.riskText(self.record.approval.risk) {
+                    self.metadataRow(label: "Risk", value: riskText)
+                }
+
+                if let statusText = self.currentRecord?.statusText, !statusText.isEmpty {
+                    Text(statusText)
+                        .font(.footnote)
+                        .foregroundStyle((self.currentRecord?.isResolving ?? false) ? Color.secondary : Color.red)
+                }
+
+                if let currentRecord,
+                   currentRecord.approval.allowedDecisions.contains(.allowOnce)
+                {
+                    Button("Allow Once") {
+                        self.onDecision?(currentRecord.id, .allowOnce)
+                    }
+                    .disabled(currentRecord.isResolving)
+                }
+
+                if let currentRecord,
+                   currentRecord.approval.allowedDecisions.contains(.deny)
+                {
+                    Button(role: .destructive) {
+                        self.onDecision?(currentRecord.id, .deny)
+                    } label: {
+                        Text("Deny")
+                            .frame(maxWidth: .infinity)
+                    }
+                    .disabled(currentRecord.isResolving)
+                }
+            }
+            .frame(maxWidth: .infinity, alignment: .leading)
+            .padding()
+        }
+        .navigationTitle("Exec approval")
+        .onAppear {
+            self.store.selectExecApproval(id: self.record.id)
+        }
+    }
+
+    private var currentRecord: WatchExecApprovalRecord? {
+        self.store.execApprovals.first(where: { $0.id == self.record.id })
+    }
+
+    private func metadataRow(label: String, value: String) -> some View {
+        VStack(alignment: .leading, spacing: 2) {
+            Text(label)
+                .font(.caption2)
+                .foregroundStyle(.secondary)
+            Text(value)
+                .font(.footnote)
+                .fixedSize(horizontal: false, vertical: true)
+        }
+    }
+
+    private func riskText(_ risk: WatchRiskLevel?) -> String? {
+        switch risk {
+        case .high:
+            return "High"
+        case .medium:
+            return "Medium"
+        case .low:
+            return "Low"
+        case nil:
+            return nil
+        }
+    }
+
+    private static func expiresText(_ expiresAtMs: Int?) -> String? {
+        guard let expiresAtMs else { return nil }
+        let deltaSeconds = max(0, (expiresAtMs - Int(Date().timeIntervalSince1970 * 1000)) / 1000)
+        if deltaSeconds < 60 {
+            return "<1 minute"
+        }
+        return "\(deltaSeconds / 60) minutes"
+    }
+}
+
+private struct WatchGenericInboxView: View {
+    var store: WatchInboxStore
     var onAction: ((WatchPromptAction) -> Void)?
 
     private func role(for action: WatchPromptAction) -> ButtonRole? {
@@ -18,40 +257,46 @@ struct WatchInboxView: View {
     var body: some View {
         ScrollView {
             VStack(alignment: .leading, spacing: 8) {
-                Text(store.title)
+                Text(self.store.title)
                     .font(.headline)
                     .lineLimit(2)
 
-                Text(store.body)
+                Text(self.store.body)
                     .font(.body)
                     .fixedSize(horizontal: false, vertical: true)
 
-                if let details = store.details, !details.isEmpty {
+                if let details = self.store.details, !details.isEmpty {
                     Text(details)
                         .font(.footnote)
                         .foregroundStyle(.secondary)
                         .fixedSize(horizontal: false, vertical: true)
                 }
 
-                if !store.actions.isEmpty {
-                    ForEach(store.actions) { action in
+                if let outcome = self.store.lastExecApprovalOutcomeText, !outcome.isEmpty {
+                    Text(outcome)
+                        .font(.footnote)
+                        .foregroundStyle(.secondary)
+                }
+
+                if !self.store.actions.isEmpty {
+                    ForEach(self.store.actions) { action in
                         Button(role: self.role(for: action)) {
                             self.onAction?(action)
                         } label: {
                             Text(action.label)
                                 .frame(maxWidth: .infinity)
                         }
-                        .disabled(store.isReplySending)
+                        .disabled(self.store.isReplySending)
                     }
                 }
 
-                if let replyStatusText = store.replyStatusText, !replyStatusText.isEmpty {
+                if let replyStatusText = self.store.replyStatusText, !replyStatusText.isEmpty {
                     Text(replyStatusText)
                         .font(.footnote)
                         .foregroundStyle(.secondary)
                 }
 
-                if let updatedAt = store.updatedAt {
+                if let updatedAt = self.store.updatedAt {
                     Text("Updated \(updatedAt.formatted(date: .omitted, time: .shortened))")
                         .font(.footnote)
                         .foregroundStyle(.secondary)
@@ -60,5 +305,6 @@ struct WatchInboxView: View {
             .frame(maxWidth: .infinity, alignment: .leading)
             .padding()
         }
+        .navigationTitle("OpenClaw")
     }
 }

apps/ios/fastlane/SETUP.md

@@ -29,6 +29,8 @@ ASC_KEYCHAIN_SERVICE=openclaw-asc-key
 ASC_KEYCHAIN_ACCOUNT=YOUR_MAC_USERNAME
 ```
 
+Important: `apps/ios/fastlane/.env` is only for Fastlane/App Store Connect auth and optional beta-archive settings. It does **not** configure gateway-side direct APNs push delivery for local iOS builds.
+
 Optional app targeting variables (helpful if Fastlane cannot auto-resolve app by bundle):
 
 ```bash
@@ -53,6 +55,8 @@ IOS_DEVELOPMENT_TEAM=YOUR_TEAM_ID
 
 Tip: run `scripts/ios-team-id.sh` from repo root to print a Team ID for `.env`. The helper prefers the canonical OpenClaw team (`Y5PE65HELJ`) when present locally; otherwise it prefers the first non-personal team from your Xcode account (then personal team if needed). Fastlane uses this helper automatically if `IOS_DEVELOPMENT_TEAM` is missing.
 
+For local/manual iOS builds that stay on direct APNs, configure the gateway host separately with `OPENCLAW_APNS_TEAM_ID`, `OPENCLAW_APNS_KEY_ID`, and either `OPENCLAW_APNS_PRIVATE_KEY_P8` or `OPENCLAW_APNS_PRIVATE_KEY_PATH`. Those gateway runtime env vars are separate from Fastlane's `.env`.
+
 Validate auth:
 
 ```bash

apps/ios/project.yml

@@ -237,12 +237,19 @@ targets:
     configFiles:
       Debug: Config/Signing.xcconfig
       Release: Config/Signing.xcconfig
+    attributes:
+      DevelopmentTeam: "$(OPENCLAW_DEVELOPMENT_TEAM)"
+      ProvisioningStyle: "$(OPENCLAW_CODE_SIGN_STYLE)"
     settings:
       base:
         ASSETCATALOG_COMPILER_APPICON_NAME: AppIcon
+        CODE_SIGN_IDENTITY: "Apple Development"
+        CODE_SIGN_STYLE: "$(OPENCLAW_CODE_SIGN_STYLE)"
+        DEVELOPMENT_TEAM: "$(OPENCLAW_DEVELOPMENT_TEAM)"
         ENABLE_APPINTENTS_METADATA: NO
         ENABLE_APP_INTENTS_METADATA_GENERATION: NO
         PRODUCT_BUNDLE_IDENTIFIER: "$(OPENCLAW_WATCH_APP_BUNDLE_ID)"
+        PROVISIONING_PROFILE_SPECIFIER: "$(OPENCLAW_WATCH_APP_PROFILE)"
     info:
       path: WatchApp/Info.plist
       properties:
@@ -265,9 +272,16 @@ targets:
     configFiles:
       Debug: Config/Signing.xcconfig
       Release: Config/Signing.xcconfig
+    attributes:
+      DevelopmentTeam: "$(OPENCLAW_DEVELOPMENT_TEAM)"
+      ProvisioningStyle: "$(OPENCLAW_CODE_SIGN_STYLE)"
     settings:
       base:
+        CODE_SIGN_IDENTITY: "Apple Development"
+        CODE_SIGN_STYLE: "$(OPENCLAW_CODE_SIGN_STYLE)"
+        DEVELOPMENT_TEAM: "$(OPENCLAW_DEVELOPMENT_TEAM)"
         PRODUCT_BUNDLE_IDENTIFIER: "$(OPENCLAW_WATCH_EXTENSION_BUNDLE_ID)"
+        PROVISIONING_PROFILE_SPECIFIER: "$(OPENCLAW_WATCH_EXTENSION_PROFILE)"
     info:
       path: WatchExtension/Info.plist
       properties:

apps/macos/Sources/OpenClaw/HostEnvSecurityPolicy.generated.swift

@@ -6,155 +6,180 @@ import Foundation
 
 enum HostEnvSecurityPolicy {
     static let blockedKeys: Set<String> = [
-        "NODE_OPTIONS",
-        "NODE_PATH",
-        "PYTHONHOME",
-        "PYTHONPATH",
-        "PERL5LIB",
-        "PERL5OPT",
-        "RUBYLIB",
-        "RUBYOPT",
+        "_JAVA_OPTIONS",
+        "ANT_OPTS",
         "BASH_ENV",
-        "ENV",
         "BROWSER",
-        "GIT_EDITOR",
-        "GIT_EXTERNAL_DIFF",
-        "GIT_EXEC_PATH",
-        "GIT_SEQUENCE_EDITOR",
-        "GIT_TEMPLATE_DIR",
-        "GIT_SSL_NO_VERIFY",
-        "GIT_SSL_CAINFO",
-        "GIT_SSL_CAPATH",
-        "CC",
-        "CXX",
         "CARGO_BUILD_RUSTC",
+        "CARGO_BUILD_RUSTC_WRAPPER",
+        "CC",
         "CMAKE_C_COMPILER",
         "CMAKE_CXX_COMPILER",
+        "CXX",
+        "DOTNET_ADDITIONAL_DEPS",
+        "DOTNET_STARTUP_HOOKS",
+        "ENV",
+        "GCONV_PATH",
+        "GIT_ALTERNATE_OBJECT_DIRECTORIES",
+        "GIT_COMMON_DIR",
+        "GIT_DIR",
+        "GIT_EDITOR",
+        "GIT_EXEC_PATH",
+        "GIT_EXTERNAL_DIFF",
+        "GIT_INDEX_FILE",
+        "GIT_NAMESPACE",
+        "GIT_OBJECT_DIRECTORY",
+        "GIT_SEQUENCE_EDITOR",
+        "GIT_SSL_CAINFO",
+        "GIT_SSL_CAPATH",
+        "GIT_SSL_NO_VERIFY",
+        "GIT_TEMPLATE_DIR",
+        "GIT_WORK_TREE",
+        "GLIBC_TUNABLES",
+        "GRADLE_OPTS",
+        "HGRCPATH",
+        "IFS",
+        "JAVA_OPTS",
+        "JAVA_TOOL_OPTIONS",
+        "JDK_JAVA_OPTIONS",
+        "MAKEFLAGS",
+        "MAVEN_OPTS",
+        "MFLAGS",
+        "NODE_OPTIONS",
+        "NODE_PATH",
+        "PERL5LIB",
+        "PERL5OPT",
+        "PS4",
+        "PYTHONBREAKPOINT",
+        "PYTHONHOME",
+        "PYTHONPATH",
+        "RUBYLIB",
+        "RUBYOPT",
+        "RUSTC_WRAPPER",
+        "SBT_OPTS",
         "SHELL",
         "SHELLOPTS",
-        "PS4",
-        "GCONV_PATH",
-        "IFS",
-        "SSLKEYLOGFILE",
-        "JAVA_TOOL_OPTIONS",
-        "_JAVA_OPTIONS",
-        "JDK_JAVA_OPTIONS",
-        "PYTHONBREAKPOINT",
-        "DOTNET_STARTUP_HOOKS",
-        "DOTNET_ADDITIONAL_DEPS",
-        "GLIBC_TUNABLES",
-        "MAVEN_OPTS",
-        "SBT_OPTS",
-        "GRADLE_OPTS",
-        "ANT_OPTS"
+        "SSLKEYLOGFILE"
     ]
 
     static let blockedOverrideKeys: Set<String> = [
-        "HOME",
-        "GRADLE_USER_HOME",
-        "ZDOTDIR",
-        "GIT_SSH_COMMAND",
-        "GIT_SSH",
-        "GIT_PROXY_COMMAND",
-        "GIT_ASKPASS",
-        "GIT_SSL_NO_VERIFY",
-        "GIT_SSL_CAINFO",
-        "GIT_SSL_CAPATH",
-        "SSH_ASKPASS",
-        "LESSOPEN",
-        "LESSCLOSE",
-        "PAGER",
-        "MANPAGER",
-        "GIT_PAGER",
-        "EDITOR",
-        "VISUAL",
-        "FCEDIT",
-        "SUDO_EDITOR",
-        "PROMPT_COMMAND",
-        "HISTFILE",
-        "PERL5DB",
-        "PERL5DBCMD",
-        "OPENSSL_CONF",
-        "OPENSSL_ENGINES",
-        "PYTHONSTARTUP",
-        "WGETRC",
-        "CURL_HOME",
-        "CLASSPATH",
+        "ALL_PROXY",
+        "AWS_CONFIG_FILE",
+        "AWS_SHARED_CREDENTIALS_FILE",
+        "AWS_WEB_IDENTITY_TOKEN_FILE",
+        "AZURE_AUTH_LOCATION",
+        "BUN_CONFIG_REGISTRY",
+        "BUNDLE_GEMFILE",
+        "C_INCLUDE_PATH",
+        "CARGO_BUILD_RUSTC_WRAPPER",
+        "CARGO_HOME",
         "CGO_CFLAGS",
         "CGO_LDFLAGS",
-        "GOFLAGS",
+        "CLASSPATH",
+        "COMPOSER_HOME",
         "CORECLR_PROFILER_PATH",
-        "PHPRC",
-        "PHP_INI_SCAN_DIR",
-        "DENO_DIR",
-        "BUN_CONFIG_REGISTRY",
-        "YARN_RC_FILENAME",
-        "HTTP_PROXY",
-        "HTTPS_PROXY",
-        "ALL_PROXY",
-        "NO_PROXY",
-        "NODE_TLS_REJECT_UNAUTHORIZED",
-        "NODE_EXTRA_CA_CERTS",
-        "SSL_CERT_FILE",
-        "SSL_CERT_DIR",
-        "REQUESTS_CA_BUNDLE",
+        "CPATH",
+        "CPLUS_INCLUDE_PATH",
         "CURL_CA_BUNDLE",
+        "CURL_HOME",
+        "DENO_DIR",
+        "DOCKER_CERT_PATH",
+        "DOCKER_CONTEXT",
         "DOCKER_HOST",
         "DOCKER_TLS_VERIFY",
-        "DOCKER_CERT_PATH",
+        "EDITOR",
+        "FCEDIT",
+        "GEM_HOME",
+        "GEM_PATH",
+        "GIT_ALTERNATE_OBJECT_DIRECTORIES",
+        "GIT_ASKPASS",
+        "GIT_COMMON_DIR",
+        "GIT_DIR",
+        "GIT_INDEX_FILE",
+        "GIT_NAMESPACE",
+        "GIT_OBJECT_DIRECTORY",
+        "GIT_PAGER",
+        "GIT_PROXY_COMMAND",
+        "GIT_SSH",
+        "GIT_SSH_COMMAND",
+        "GIT_SSL_CAINFO",
+        "GIT_SSL_CAPATH",
+        "GIT_SSL_NO_VERIFY",
+        "GIT_WORK_TREE",
+        "GOENV",
+        "GOFLAGS",
+        "GONOPROXY",
+        "GONOSUMCHECK",
+        "GONOSUMDB",
+        "GOOGLE_APPLICATION_CREDENTIALS",
+        "GOPATH",
+        "GOPRIVATE",
+        "GOPROXY",
+        "GRADLE_USER_HOME",
+        "HELM_HOME",
+        "HGRCPATH",
+        "HISTFILE",
+        "HOME",
+        "HTTP_PROXY",
+        "HTTPS_PROXY",
+        "KUBECONFIG",
+        "LESSCLOSE",
+        "LESSOPEN",
+        "LIBRARY_PATH",
+        "LUA_CPATH",
+        "LUA_PATH",
+        "MAKEFLAGS",
+        "MANPAGER",
+        "MFLAGS",
+        "NO_PROXY",
+        "NODE_EXTRA_CA_CERTS",
+        "NODE_TLS_REJECT_UNAUTHORIZED",
+        "OBJC_INCLUDE_PATH",
+        "OPENSSL_CONF",
+        "OPENSSL_ENGINES",
+        "PAGER",
+        "PERL5DB",
+        "PERL5DBCMD",
+        "PHP_INI_SCAN_DIR",
+        "PHPRC",
+        "PIP_CONFIG_FILE",
+        "PIP_EXTRA_INDEX_URL",
+        "PIP_FIND_LINKS",
         "PIP_INDEX_URL",
         "PIP_PYPI_URL",
-        "PIP_EXTRA_INDEX_URL",
-        "PIP_CONFIG_FILE",
-        "PIP_FIND_LINKS",
         "PIP_TRUSTED_HOST",
+        "PROMPT_COMMAND",
+        "PYTHONSTARTUP",
+        "PYTHONUSERBASE",
+        "REQUESTS_CA_BUNDLE",
+        "RUSTC_WRAPPER",
+        "RUSTFLAGS",
+        "SSH_ASKPASS",
+        "SSL_CERT_DIR",
+        "SSL_CERT_FILE",
+        "SUDO_EDITOR",
+        "UV_DEFAULT_INDEX",
+        "UV_EXTRA_INDEX_URL",
         "UV_INDEX",
         "UV_INDEX_URL",
         "UV_PYTHON",
-        "UV_EXTRA_INDEX_URL",
-        "UV_DEFAULT_INDEX",
-        "DOCKER_HOST",
-        "DOCKER_TLS_VERIFY",
-        "DOCKER_CERT_PATH",
-        "DOCKER_CONTEXT",
-        "LIBRARY_PATH",
-        "CPATH",
-        "C_INCLUDE_PATH",
-        "CPLUS_INCLUDE_PATH",
-        "OBJC_INCLUDE_PATH",
-        "NODE_EXTRA_CA_CERTS",
-        "SSL_CERT_FILE",
-        "SSL_CERT_DIR",
-        "REQUESTS_CA_BUNDLE",
-        "CURL_CA_BUNDLE",
-        "GOPROXY",
-        "GONOSUMCHECK",
-        "GONOSUMDB",
-        "GONOPROXY",
-        "GOPRIVATE",
-        "GOENV",
-        "GOPATH",
-        "PYTHONUSERBASE",
         "VIRTUAL_ENV",
-        "LUA_PATH",
-        "LUA_CPATH",
-        "GEM_HOME",
-        "GEM_PATH",
-        "BUNDLE_GEMFILE",
-        "COMPOSER_HOME",
+        "VISUAL",
+        "WGETRC",
         "XDG_CONFIG_HOME",
-        "AWS_CONFIG_FILE"
+        "YARN_RC_FILENAME",
+        "ZDOTDIR"
     ]
 
     static let blockedOverridePrefixes: [String] = [
+        "CARGO_REGISTRIES_",
         "GIT_CONFIG_",
-        "NPM_CONFIG_",
-        "CARGO_REGISTRIES_"
+        "NPM_CONFIG_"
     ]
 
     static let blockedPrefixes: [String] = [
+        "BASH_FUNC_",
         "DYLD_",
-        "LD_",
-        "BASH_FUNC_"
+        "LD_"
     ]
 }

apps/macos/Sources/OpenClaw/Resources/Info.plist

@@ -15,9 +15,9 @@
     <key>CFBundlePackageType</key>
     <string>APPL</string>
     <key>CFBundleShortVersionString</key>
-    <string>2026.4.6</string>
+    <string>2026.4.7</string>
     <key>CFBundleVersion</key>
-    <string>2026040601</string>
+    <string>2026040701</string>
     <key>CFBundleIconFile</key>
     <string>OpenClaw</string>
     <key>CFBundleURLTypes</key>

apps/macos/Sources/OpenClawProtocol/GatewayModels.swift

@@ -537,6 +537,8 @@ public struct AgentParams: Codable, Sendable {
     public let besteffortdeliver: Bool?
     public let lane: String?
     public let extrasystemprompt: String?
+    public let bootstrapcontextmode: AnyCodable?
+    public let bootstrapcontextrunkind: AnyCodable?
     public let internalevents: [[String: AnyCodable]]?
     public let inputprovenance: [String: AnyCodable]?
     public let idempotencykey: String
@@ -566,6 +568,8 @@ public struct AgentParams: Codable, Sendable {
         besteffortdeliver: Bool?,
         lane: String?,
         extrasystemprompt: String?,
+        bootstrapcontextmode: AnyCodable?,
+        bootstrapcontextrunkind: AnyCodable?,
         internalevents: [[String: AnyCodable]]?,
         inputprovenance: [String: AnyCodable]?,
         idempotencykey: String,
@@ -594,6 +598,8 @@ public struct AgentParams: Codable, Sendable {
         self.besteffortdeliver = besteffortdeliver
         self.lane = lane
         self.extrasystemprompt = extrasystemprompt
+        self.bootstrapcontextmode = bootstrapcontextmode
+        self.bootstrapcontextrunkind = bootstrapcontextrunkind
         self.internalevents = internalevents
         self.inputprovenance = inputprovenance
         self.idempotencykey = idempotencykey
@@ -624,6 +630,8 @@ public struct AgentParams: Codable, Sendable {
         case besteffortdeliver = "bestEffortDeliver"
         case lane
         case extrasystemprompt = "extraSystemPrompt"
+        case bootstrapcontextmode = "bootstrapContextMode"
+        case bootstrapcontextrunkind = "bootstrapContextRunKind"
         case internalevents = "internalEvents"
         case inputprovenance = "inputProvenance"
         case idempotencykey = "idempotencyKey"
@@ -1327,6 +1335,236 @@ public struct SessionsResolveParams: Codable, Sendable {
     }
 }
 
+public struct SessionCompactionCheckpoint: Codable, Sendable {
+    public let checkpointid: String
+    public let sessionkey: String
+    public let sessionid: String
+    public let createdat: Int
+    public let reason: AnyCodable
+    public let tokensbefore: Int?
+    public let tokensafter: Int?
+    public let summary: String?
+    public let firstkeptentryid: String?
+    public let precompaction: [String: AnyCodable]
+    public let postcompaction: [String: AnyCodable]
+
+    public init(
+        checkpointid: String,
+        sessionkey: String,
+        sessionid: String,
+        createdat: Int,
+        reason: AnyCodable,
+        tokensbefore: Int?,
+        tokensafter: Int?,
+        summary: String?,
+        firstkeptentryid: String?,
+        precompaction: [String: AnyCodable],
+        postcompaction: [String: AnyCodable])
+    {
+        self.checkpointid = checkpointid
+        self.sessionkey = sessionkey
+        self.sessionid = sessionid
+        self.createdat = createdat
+        self.reason = reason
+        self.tokensbefore = tokensbefore
+        self.tokensafter = tokensafter
+        self.summary = summary
+        self.firstkeptentryid = firstkeptentryid
+        self.precompaction = precompaction
+        self.postcompaction = postcompaction
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case checkpointid = "checkpointId"
+        case sessionkey = "sessionKey"
+        case sessionid = "sessionId"
+        case createdat = "createdAt"
+        case reason
+        case tokensbefore = "tokensBefore"
+        case tokensafter = "tokensAfter"
+        case summary
+        case firstkeptentryid = "firstKeptEntryId"
+        case precompaction = "preCompaction"
+        case postcompaction = "postCompaction"
+    }
+}
+
+public struct SessionsCompactionListParams: Codable, Sendable {
+    public let key: String
+
+    public init(
+        key: String)
+    {
+        self.key = key
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case key
+    }
+}
+
+public struct SessionsCompactionGetParams: Codable, Sendable {
+    public let key: String
+    public let checkpointid: String
+
+    public init(
+        key: String,
+        checkpointid: String)
+    {
+        self.key = key
+        self.checkpointid = checkpointid
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case key
+        case checkpointid = "checkpointId"
+    }
+}
+
+public struct SessionsCompactionBranchParams: Codable, Sendable {
+    public let key: String
+    public let checkpointid: String
+
+    public init(
+        key: String,
+        checkpointid: String)
+    {
+        self.key = key
+        self.checkpointid = checkpointid
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case key
+        case checkpointid = "checkpointId"
+    }
+}
+
+public struct SessionsCompactionRestoreParams: Codable, Sendable {
+    public let key: String
+    public let checkpointid: String
+
+    public init(
+        key: String,
+        checkpointid: String)
+    {
+        self.key = key
+        self.checkpointid = checkpointid
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case key
+        case checkpointid = "checkpointId"
+    }
+}
+
+public struct SessionsCompactionListResult: Codable, Sendable {
+    public let ok: Bool
+    public let key: String
+    public let checkpoints: [SessionCompactionCheckpoint]
+
+    public init(
+        ok: Bool,
+        key: String,
+        checkpoints: [SessionCompactionCheckpoint])
+    {
+        self.ok = ok
+        self.key = key
+        self.checkpoints = checkpoints
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case ok
+        case key
+        case checkpoints
+    }
+}
+
+public struct SessionsCompactionGetResult: Codable, Sendable {
+    public let ok: Bool
+    public let key: String
+    public let checkpoint: SessionCompactionCheckpoint
+
+    public init(
+        ok: Bool,
+        key: String,
+        checkpoint: SessionCompactionCheckpoint)
+    {
+        self.ok = ok
+        self.key = key
+        self.checkpoint = checkpoint
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case ok
+        case key
+        case checkpoint
+    }
+}
+
+public struct SessionsCompactionBranchResult: Codable, Sendable {
+    public let ok: Bool
+    public let sourcekey: String
+    public let key: String
+    public let sessionid: String
+    public let checkpoint: SessionCompactionCheckpoint
+    public let entry: [String: AnyCodable]
+
+    public init(
+        ok: Bool,
+        sourcekey: String,
+        key: String,
+        sessionid: String,
+        checkpoint: SessionCompactionCheckpoint,
+        entry: [String: AnyCodable])
+    {
+        self.ok = ok
+        self.sourcekey = sourcekey
+        self.key = key
+        self.sessionid = sessionid
+        self.checkpoint = checkpoint
+        self.entry = entry
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case ok
+        case sourcekey = "sourceKey"
+        case key
+        case sessionid = "sessionId"
+        case checkpoint
+        case entry
+    }
+}
+
+public struct SessionsCompactionRestoreResult: Codable, Sendable {
+    public let ok: Bool
+    public let key: String
+    public let sessionid: String
+    public let checkpoint: SessionCompactionCheckpoint
+    public let entry: [String: AnyCodable]
+
+    public init(
+        ok: Bool,
+        key: String,
+        sessionid: String,
+        checkpoint: SessionCompactionCheckpoint,
+        entry: [String: AnyCodable])
+    {
+        self.ok = ok
+        self.key = key
+        self.sessionid = sessionid
+        self.checkpoint = checkpoint
+        self.entry = entry
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case ok
+        case key
+        case sessionid = "sessionId"
+        case checkpoint
+        case entry
+    }
+}
+
 public struct SessionsCreateParams: Codable, Sendable {
     public let key: String?
     public let agentid: String?

apps/shared/OpenClawKit/Sources/OpenClawKit/GatewayChannel.swift

@@ -624,11 +624,31 @@ public actor GatewayChannelActor {
             let detailCode = details?["code"]?.value as? String
             let canRetryWithDeviceToken = details?["canRetryWithDeviceToken"]?.value as? Bool ?? false
             let recommendedNextStep = details?["recommendedNextStep"]?.value as? String
+            let requestId = details?["requestId"]?.value as? String
+            let reason = details?["reason"]?.value as? String
+            let owner = details?["owner"]?.value as? String
+            let title = details?["title"]?.value as? String
+            let userMessage = details?["userMessage"]?.value as? String
+            let actionLabel = details?["actionLabel"]?.value as? String
+            let actionCommand = details?["actionCommand"]?.value as? String
+            let docsURLString = details?["docsUrl"]?.value as? String
+            let retryableOverride = details?["retryable"]?.value as? Bool
+            let pauseReconnectOverride = details?["pauseReconnect"]?.value as? Bool
             throw GatewayConnectAuthError(
                 message: msg,
                 detailCodeRaw: detailCode,
                 canRetryWithDeviceToken: canRetryWithDeviceToken,
-                recommendedNextStepRaw: recommendedNextStep)
+                recommendedNextStepRaw: recommendedNextStep,
+                requestId: requestId,
+                detailsReason: reason,
+                ownerRaw: owner,
+                titleOverride: title,
+                userMessageOverride: userMessage,
+                actionLabel: actionLabel,
+                actionCommand: actionCommand,
+                docsURLString: docsURLString,
+                retryableOverride: retryableOverride,
+                pauseReconnectOverride: pauseReconnectOverride)
         }
         guard let payload = res.payload else {
             throw NSError(

apps/shared/OpenClawKit/Sources/OpenClawKit/GatewayConnectionProblem.swift

@@ -0,0 +1,761 @@
+import Foundation
+
+public struct GatewayConnectionProblem: Equatable, Sendable {
+    public enum Kind: String, Equatable, Sendable {
+        case gatewayAuthTokenMissing
+        case gatewayAuthTokenMismatch
+        case gatewayAuthTokenNotConfigured
+        case gatewayAuthPasswordMissing
+        case gatewayAuthPasswordMismatch
+        case gatewayAuthPasswordNotConfigured
+        case bootstrapTokenInvalid
+        case deviceTokenMismatch
+        case pairingRequired
+        case pairingRoleUpgradeRequired
+        case pairingScopeUpgradeRequired
+        case pairingMetadataUpgradeRequired
+        case deviceIdentityRequired
+        case deviceSignatureExpired
+        case deviceNonceRequired
+        case deviceNonceMismatch
+        case deviceSignatureInvalid
+        case devicePublicKeyInvalid
+        case deviceIdMismatch
+        case tailscaleIdentityMissing
+        case tailscaleProxyMissing
+        case tailscaleWhoisFailed
+        case tailscaleIdentityMismatch
+        case authRateLimited
+        case timeout
+        case connectionRefused
+        case reachabilityFailed
+        case websocketCancelled
+        case unknown
+    }
+
+    public enum Owner: String, Equatable, Sendable {
+        case gateway
+        case iphone
+        case both
+        case network
+        case unknown
+    }
+
+    public let kind: Kind
+    public let owner: Owner
+    public let title: String
+    public let message: String
+    public let actionLabel: String?
+    public let actionCommand: String?
+    public let docsURL: URL?
+    public let requestId: String?
+    public let retryable: Bool
+    public let pauseReconnect: Bool
+    public let technicalDetails: String?
+
+    public init(
+        kind: Kind,
+        owner: Owner,
+        title: String,
+        message: String,
+        actionLabel: String? = nil,
+        actionCommand: String? = nil,
+        docsURL: URL? = nil,
+        requestId: String? = nil,
+        retryable: Bool,
+        pauseReconnect: Bool,
+        technicalDetails: String? = nil)
+    {
+        self.kind = kind
+        self.owner = owner
+        self.title = title
+        self.message = message
+        self.actionLabel = Self.trimmedOrNil(actionLabel)
+        self.actionCommand = Self.trimmedOrNil(actionCommand)
+        self.docsURL = docsURL
+        self.requestId = Self.trimmedOrNil(requestId)
+        self.retryable = retryable
+        self.pauseReconnect = pauseReconnect
+        self.technicalDetails = Self.trimmedOrNil(technicalDetails)
+    }
+
+    public var needsPairingApproval: Bool {
+        switch self.kind {
+        case .pairingRequired, .pairingRoleUpgradeRequired, .pairingScopeUpgradeRequired, .pairingMetadataUpgradeRequired:
+            return true
+        default:
+            return false
+        }
+    }
+
+    public var needsCredentialUpdate: Bool {
+        switch self.kind {
+        case .gatewayAuthTokenMissing,
+            .gatewayAuthTokenMismatch,
+            .gatewayAuthTokenNotConfigured,
+            .gatewayAuthPasswordMissing,
+            .gatewayAuthPasswordMismatch,
+            .gatewayAuthPasswordNotConfigured,
+            .bootstrapTokenInvalid,
+            .deviceTokenMismatch:
+            return true
+        default:
+            return false
+        }
+    }
+
+    public var statusText: String {
+        switch self.kind {
+        case .pairingRequired, .pairingRoleUpgradeRequired, .pairingScopeUpgradeRequired, .pairingMetadataUpgradeRequired:
+            if let requestId {
+                return "\(self.title) (request ID: \(requestId))"
+            }
+            return self.title
+        default:
+            return self.title
+        }
+    }
+
+    private static func trimmedOrNil(_ value: String?) -> String? {
+        let trimmed = value?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
+        return trimmed.isEmpty ? nil : trimmed
+    }
+}
+
+public enum GatewayConnectionProblemMapper {
+    public static func map(error: Error, preserving previousProblem: GatewayConnectionProblem? = nil) -> GatewayConnectionProblem? {
+        guard let nextProblem = self.rawMap(error) else {
+            return nil
+        }
+        guard let previousProblem else {
+            return nextProblem
+        }
+        if self.shouldPreserve(previousProblem: previousProblem, over: nextProblem) {
+            return previousProblem
+        }
+        return nextProblem
+    }
+
+    public static func shouldPreserve(previousProblem: GatewayConnectionProblem, over nextProblem: GatewayConnectionProblem) -> Bool {
+        if nextProblem.kind == .websocketCancelled {
+            return previousProblem.pauseReconnect || previousProblem.requestId != nil
+        }
+        return false
+    }
+
+    public static func shouldPreserve(previousProblem: GatewayConnectionProblem, overDisconnectReason reason: String) -> Bool {
+        let normalized = reason.trimmingCharacters(in: .whitespacesAndNewlines).lowercased()
+        guard !normalized.isEmpty else { return false }
+        if normalized.contains("cancelled") || normalized.contains("canceled") {
+            return previousProblem.pauseReconnect || previousProblem.requestId != nil
+        }
+        return false
+    }
+
+    private static func rawMap(_ error: Error) -> GatewayConnectionProblem? {
+        if let authError = error as? GatewayConnectAuthError {
+            return self.map(authError)
+        }
+        if let responseError = error as? GatewayResponseError {
+            return self.map(responseError)
+        }
+        return self.mapTransportError(error)
+    }
+
+    private static func map(_ authError: GatewayConnectAuthError) -> GatewayConnectionProblem {
+        let pairingCommand = self.approvalCommand(requestId: authError.requestId)
+
+        switch authError.detail {
+        case .authTokenMissing:
+            return self.problem(
+                kind: .gatewayAuthTokenMissing,
+                owner: .both,
+                title: authError.titleOverride ?? "Gateway token required",
+                message: authError.userMessageOverride
+                    ?? "This gateway requires an auth token, but this iPhone did not send one.",
+                actionLabel: authError.actionLabel ?? "Open Settings",
+                actionCommand: authError.actionCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/authentication"),
+                requestId: authError.requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        case .authTokenMismatch:
+            return self.problem(
+                kind: .gatewayAuthTokenMismatch,
+                owner: .both,
+                title: authError.titleOverride ?? "Gateway token is out of date",
+                message: authError.userMessageOverride
+                    ?? "The token on this iPhone does not match the gateway token.",
+                actionLabel: authError.actionLabel ?? (authError.canRetryWithDeviceToken ? "Retry once" : "Update gateway token"),
+                actionCommand: authError.actionCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/authentication"),
+                requestId: authError.requestId,
+                retryable: authError.retryableOverride ?? authError.canRetryWithDeviceToken,
+                pauseReconnect: authError.pauseReconnectOverride ?? !authError.canRetryWithDeviceToken,
+                authError: authError)
+        case .authTokenNotConfigured:
+            return self.problem(
+                kind: .gatewayAuthTokenNotConfigured,
+                owner: .gateway,
+                title: authError.titleOverride ?? "Gateway token is not configured",
+                message: authError.userMessageOverride
+                    ?? "This gateway is set to token auth, but no gateway token is configured on the gateway.",
+                actionLabel: authError.actionLabel ?? "Fix on gateway",
+                actionCommand: authError.actionCommand ?? "openclaw config set gateway.auth.token <new-token>",
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/authentication"),
+                requestId: authError.requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        case .authPasswordMissing:
+            return self.problem(
+                kind: .gatewayAuthPasswordMissing,
+                owner: .both,
+                title: authError.titleOverride ?? "Gateway password required",
+                message: authError.userMessageOverride
+                    ?? "This gateway requires a password, but this iPhone did not send one.",
+                actionLabel: authError.actionLabel ?? "Open Settings",
+                actionCommand: authError.actionCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/authentication"),
+                requestId: authError.requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        case .authPasswordMismatch:
+            return self.problem(
+                kind: .gatewayAuthPasswordMismatch,
+                owner: .both,
+                title: authError.titleOverride ?? "Gateway password is out of date",
+                message: authError.userMessageOverride
+                    ?? "The saved password on this iPhone does not match the gateway password.",
+                actionLabel: authError.actionLabel ?? "Update password",
+                actionCommand: authError.actionCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/authentication"),
+                requestId: authError.requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        case .authPasswordNotConfigured:
+            return self.problem(
+                kind: .gatewayAuthPasswordNotConfigured,
+                owner: .gateway,
+                title: authError.titleOverride ?? "Gateway password is not configured",
+                message: authError.userMessageOverride
+                    ?? "This gateway is set to password auth, but no gateway password is configured on the gateway.",
+                actionLabel: authError.actionLabel ?? "Fix on gateway",
+                actionCommand: authError.actionCommand ?? "openclaw config set gateway.auth.password <new-password>",
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/authentication"),
+                requestId: authError.requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        case .authBootstrapTokenInvalid:
+            return self.problem(
+                kind: .bootstrapTokenInvalid,
+                owner: .iphone,
+                title: authError.titleOverride ?? "Setup code expired",
+                message: authError.userMessageOverride
+                    ?? "The setup QR or bootstrap token is no longer valid.",
+                actionLabel: authError.actionLabel ?? "Scan QR again",
+                actionCommand: authError.actionCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/platforms/ios"),
+                requestId: authError.requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        case .authDeviceTokenMismatch:
+            return self.problem(
+                kind: .deviceTokenMismatch,
+                owner: .both,
+                title: authError.titleOverride ?? "This iPhone's saved device token is no longer valid",
+                message: authError.userMessageOverride
+                    ?? "The gateway rejected the stored device token for this role.",
+                actionLabel: authError.actionLabel ?? "Repair pairing",
+                actionCommand: authError.actionCommand ?? pairingCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/pairing"),
+                requestId: authError.requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        case .pairingRequired:
+            return self.pairingProblem(for: authError)
+        case .controlUiDeviceIdentityRequired, .deviceIdentityRequired:
+            return self.problem(
+                kind: .deviceIdentityRequired,
+                owner: .iphone,
+                title: authError.titleOverride ?? "Secure device identity is required",
+                message: authError.userMessageOverride
+                    ?? "This connection must include a signed device identity before the gateway can bind permissions to this iPhone.",
+                actionLabel: authError.actionLabel ?? "Retry from the app",
+                actionCommand: authError.actionCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/platforms/ios"),
+                requestId: authError.requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        case .deviceAuthSignatureExpired:
+            return self.problem(
+                kind: .deviceSignatureExpired,
+                owner: .iphone,
+                title: authError.titleOverride ?? "Secure handshake expired",
+                message: authError.userMessageOverride ?? "The device signature is too old to use.",
+                actionLabel: authError.actionLabel ?? "Check iPhone time",
+                actionCommand: authError.actionCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/troubleshooting"),
+                requestId: authError.requestId,
+                retryable: true,
+                pauseReconnect: true,
+                authError: authError)
+        case .deviceAuthNonceRequired:
+            return self.problem(
+                kind: .deviceNonceRequired,
+                owner: .iphone,
+                title: authError.titleOverride ?? "Secure handshake is incomplete",
+                message: authError.userMessageOverride
+                    ?? "The gateway expected a one-time challenge response, but the nonce was missing.",
+                actionLabel: authError.actionLabel ?? "Retry",
+                actionCommand: authError.actionCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/troubleshooting"),
+                requestId: authError.requestId,
+                retryable: true,
+                pauseReconnect: true,
+                authError: authError)
+        case .deviceAuthNonceMismatch:
+            return self.problem(
+                kind: .deviceNonceMismatch,
+                owner: .iphone,
+                title: authError.titleOverride ?? "Secure handshake did not match",
+                message: authError.userMessageOverride ?? "The challenge response was stale or mismatched.",
+                actionLabel: authError.actionLabel ?? "Retry",
+                actionCommand: authError.actionCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/troubleshooting"),
+                requestId: authError.requestId,
+                retryable: true,
+                pauseReconnect: true,
+                authError: authError)
+        case .deviceAuthSignatureInvalid, .deviceAuthInvalid:
+            return self.problem(
+                kind: .deviceSignatureInvalid,
+                owner: .iphone,
+                title: authError.titleOverride ?? "This device identity could not be verified",
+                message: authError.userMessageOverride
+                    ?? "The gateway could not verify the identity this iPhone presented.",
+                actionLabel: authError.actionLabel ?? "Re-pair this iPhone",
+                actionCommand: authError.actionCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/pairing"),
+                requestId: authError.requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        case .deviceAuthPublicKeyInvalid:
+            return self.problem(
+                kind: .devicePublicKeyInvalid,
+                owner: .iphone,
+                title: authError.titleOverride ?? "This device identity could not be verified",
+                message: authError.userMessageOverride
+                    ?? "The gateway could not verify the public key this iPhone presented.",
+                actionLabel: authError.actionLabel ?? "Re-pair this iPhone",
+                actionCommand: authError.actionCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/pairing"),
+                requestId: authError.requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        case .deviceAuthDeviceIdMismatch:
+            return self.problem(
+                kind: .deviceIdMismatch,
+                owner: .iphone,
+                title: authError.titleOverride ?? "This device identity could not be verified",
+                message: authError.userMessageOverride
+                    ?? "The gateway rejected the device identity because the device ID did not match.",
+                actionLabel: authError.actionLabel ?? "Re-pair this iPhone",
+                actionCommand: authError.actionCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/pairing"),
+                requestId: authError.requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        case .authTailscaleIdentityMissing:
+            return self.problem(
+                kind: .tailscaleIdentityMissing,
+                owner: .network,
+                title: authError.titleOverride ?? "Tailscale identity check failed",
+                message: authError.userMessageOverride
+                    ?? "This connection expected Tailscale identity headers, but they were not available.",
+                actionLabel: authError.actionLabel ?? "Turn on Tailscale",
+                actionCommand: authError.actionCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/tailscale"),
+                requestId: authError.requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        case .authTailscaleProxyMissing:
+            return self.problem(
+                kind: .tailscaleProxyMissing,
+                owner: .network,
+                title: authError.titleOverride ?? "Tailscale identity check failed",
+                message: authError.userMessageOverride
+                    ?? "The gateway expected a Tailscale auth proxy, but it was not configured.",
+                actionLabel: authError.actionLabel ?? "Review Tailscale setup",
+                actionCommand: authError.actionCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/tailscale"),
+                requestId: authError.requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        case .authTailscaleWhoisFailed:
+            return self.problem(
+                kind: .tailscaleWhoisFailed,
+                owner: .network,
+                title: authError.titleOverride ?? "Tailscale identity check failed",
+                message: authError.userMessageOverride
+                    ?? "The gateway could not verify this Tailscale client identity.",
+                actionLabel: authError.actionLabel ?? "Review Tailscale setup",
+                actionCommand: authError.actionCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/tailscale"),
+                requestId: authError.requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        case .authTailscaleIdentityMismatch:
+            return self.problem(
+                kind: .tailscaleIdentityMismatch,
+                owner: .network,
+                title: authError.titleOverride ?? "Tailscale identity check failed",
+                message: authError.userMessageOverride
+                    ?? "The forwarded Tailscale identity did not match the verified identity.",
+                actionLabel: authError.actionLabel ?? "Review Tailscale setup",
+                actionCommand: authError.actionCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/tailscale"),
+                requestId: authError.requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        case .authRateLimited:
+            return self.problem(
+                kind: .authRateLimited,
+                owner: .gateway,
+                title: authError.titleOverride ?? "Too many failed attempts",
+                message: authError.userMessageOverride
+                    ?? "The gateway is temporarily refusing new auth attempts after repeated failures.",
+                actionLabel: authError.actionLabel ?? "Wait and retry",
+                actionCommand: authError.actionCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/troubleshooting"),
+                requestId: authError.requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        case .authRequired, .authUnauthorized, .none:
+            return self.problem(
+                kind: .unknown,
+                owner: authError.ownerRaw.flatMap { self.owner(from: $0) } ?? .unknown,
+                title: authError.titleOverride ?? "Gateway rejected the connection",
+                message: authError.userMessageOverride ?? authError.message,
+                actionLabel: authError.actionLabel,
+                actionCommand: authError.actionCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: nil),
+                requestId: authError.requestId,
+                retryable: authError.retryableOverride ?? false,
+                pauseReconnect: authError.pauseReconnectOverride ?? authError.isNonRecoverable,
+                authError: authError)
+        }
+    }
+
+    private static func map(_ responseError: GatewayResponseError) -> GatewayConnectionProblem? {
+        let code = responseError.code.trimmingCharacters(in: .whitespacesAndNewlines).uppercased()
+        if code == "NOT_PAIRED" || responseError.detailsReason == "not-paired" {
+            let authError = GatewayConnectAuthError(
+                message: responseError.message,
+                detailCodeRaw: GatewayConnectAuthDetailCode.pairingRequired.rawValue,
+                canRetryWithDeviceToken: false,
+                recommendedNextStepRaw: nil,
+                requestId: self.stringValue(responseError.details["requestId"]?.value),
+                detailsReason: responseError.detailsReason,
+                ownerRaw: nil,
+                titleOverride: nil,
+                userMessageOverride: nil,
+                actionLabel: nil,
+                actionCommand: nil,
+                docsURLString: nil,
+                retryableOverride: nil,
+                pauseReconnectOverride: nil)
+            return self.map(authError)
+        }
+        return nil
+    }
+
+    private static func mapTransportError(_ error: Error) -> GatewayConnectionProblem? {
+        let nsError = error as NSError
+        let rawMessage = nsError.userInfo[NSLocalizedDescriptionKey] as? String ?? nsError.localizedDescription
+        let lower = rawMessage.trimmingCharacters(in: .whitespacesAndNewlines).lowercased()
+        if lower.isEmpty {
+            return nil
+        }
+
+        let urlErrorCode = URLError.Code(rawValue: nsError.code)
+        if nsError.domain == URLError.errorDomain {
+            switch urlErrorCode {
+            case .timedOut:
+                return GatewayConnectionProblem(
+                    kind: .timeout,
+                    owner: .network,
+                    title: "Connection timed out",
+                    message: "The gateway did not respond before the connection timed out.",
+                    actionLabel: "Retry",
+                    actionCommand: nil,
+                    docsURL: URL(string: "https://docs.openclaw.ai/gateway/troubleshooting"),
+                    retryable: true,
+                    pauseReconnect: false,
+                    technicalDetails: rawMessage)
+            case .cannotConnectToHost:
+                return GatewayConnectionProblem(
+                    kind: .connectionRefused,
+                    owner: .network,
+                    title: "Gateway refused the connection",
+                    message: "The gateway host was reachable, but it refused the connection.",
+                    actionLabel: "Retry",
+                    actionCommand: nil,
+                    docsURL: URL(string: "https://docs.openclaw.ai/gateway/troubleshooting"),
+                    retryable: true,
+                    pauseReconnect: false,
+                    technicalDetails: rawMessage)
+            case .cannotFindHost, .dnsLookupFailed, .notConnectedToInternet, .networkConnectionLost, .internationalRoamingOff, .callIsActive, .dataNotAllowed:
+                return GatewayConnectionProblem(
+                    kind: .reachabilityFailed,
+                    owner: .network,
+                    title: "Gateway is not reachable",
+                    message: "OpenClaw could not reach the gateway over the current network.",
+                    actionLabel: "Check network",
+                    actionCommand: nil,
+                    docsURL: URL(string: "https://docs.openclaw.ai/gateway/troubleshooting"),
+                    retryable: true,
+                    pauseReconnect: false,
+                    technicalDetails: rawMessage)
+            case .cancelled:
+                return GatewayConnectionProblem(
+                    kind: .websocketCancelled,
+                    owner: .network,
+                    title: "Connection interrupted",
+                    message: "The connection to the gateway was interrupted before setup completed.",
+                    actionLabel: "Retry",
+                    actionCommand: nil,
+                    docsURL: URL(string: "https://docs.openclaw.ai/gateway/troubleshooting"),
+                    retryable: true,
+                    pauseReconnect: false,
+                    technicalDetails: rawMessage)
+            default:
+                break
+            }
+        }
+
+        if lower.contains("timed out") {
+            return GatewayConnectionProblem(
+                kind: .timeout,
+                owner: .network,
+                title: "Connection timed out",
+                message: "The gateway did not respond before the connection timed out.",
+                actionLabel: "Retry",
+                actionCommand: nil,
+                docsURL: URL(string: "https://docs.openclaw.ai/gateway/troubleshooting"),
+                retryable: true,
+                pauseReconnect: false,
+                technicalDetails: rawMessage)
+        }
+        if lower.contains("connection refused") || lower.contains("refused") {
+            return GatewayConnectionProblem(
+                kind: .connectionRefused,
+                owner: .network,
+                title: "Gateway refused the connection",
+                message: "The gateway host was reachable, but it refused the connection.",
+                actionLabel: "Retry",
+                actionCommand: nil,
+                docsURL: URL(string: "https://docs.openclaw.ai/gateway/troubleshooting"),
+                retryable: true,
+                pauseReconnect: false,
+                technicalDetails: rawMessage)
+        }
+        if lower.contains("cannot find host") || lower.contains("could not connect") || lower.contains("network is unreachable") {
+            return GatewayConnectionProblem(
+                kind: .reachabilityFailed,
+                owner: .network,
+                title: "Gateway is not reachable",
+                message: "OpenClaw could not reach the gateway over the current network.",
+                actionLabel: "Check network",
+                actionCommand: nil,
+                docsURL: URL(string: "https://docs.openclaw.ai/gateway/troubleshooting"),
+                retryable: true,
+                pauseReconnect: false,
+                technicalDetails: rawMessage)
+        }
+        if lower.contains("cancelled") || lower.contains("canceled") {
+            return GatewayConnectionProblem(
+                kind: .websocketCancelled,
+                owner: .network,
+                title: "Connection interrupted",
+                message: "The connection to the gateway was interrupted before setup completed.",
+                actionLabel: "Retry",
+                actionCommand: nil,
+                docsURL: URL(string: "https://docs.openclaw.ai/gateway/troubleshooting"),
+                retryable: true,
+                pauseReconnect: false,
+                technicalDetails: rawMessage)
+        }
+        return nil
+    }
+
+    private static func pairingProblem(for authError: GatewayConnectAuthError) -> GatewayConnectionProblem {
+        let requestId = authError.requestId
+        let pairingCommand = self.approvalCommand(requestId: requestId)
+
+        switch authError.detailsReason {
+        case "role-upgrade":
+            return self.problem(
+                kind: .pairingRoleUpgradeRequired,
+                owner: .gateway,
+                title: authError.titleOverride ?? "Additional approval required",
+                message: authError.userMessageOverride
+                    ?? "This iPhone is already paired, but it is requesting a new role that was not previously approved.",
+                actionLabel: authError.actionLabel ?? "Approve on gateway",
+                actionCommand: authError.actionCommand ?? pairingCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/pairing"),
+                requestId: requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        case "scope-upgrade":
+            return self.problem(
+                kind: .pairingScopeUpgradeRequired,
+                owner: .gateway,
+                title: authError.titleOverride ?? "Additional permissions required",
+                message: authError.userMessageOverride
+                    ?? "This iPhone is already paired, but it is requesting new permissions that require approval.",
+                actionLabel: authError.actionLabel ?? "Approve on gateway",
+                actionCommand: authError.actionCommand ?? pairingCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/pairing"),
+                requestId: requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        case "metadata-upgrade":
+            return self.problem(
+                kind: .pairingMetadataUpgradeRequired,
+                owner: .gateway,
+                title: authError.titleOverride ?? "Device approval needs refresh",
+                message: authError.userMessageOverride
+                    ?? "The gateway detected a change in this device's approved identity metadata and requires re-approval.",
+                actionLabel: authError.actionLabel ?? "Approve on gateway",
+                actionCommand: authError.actionCommand ?? pairingCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/pairing"),
+                requestId: requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        default:
+            return self.problem(
+                kind: .pairingRequired,
+                owner: .gateway,
+                title: authError.titleOverride ?? "This iPhone is not approved yet",
+                message: authError.userMessageOverride
+                    ?? "The gateway received the connection request, but this device must be approved first.",
+                actionLabel: authError.actionLabel ?? "Approve on gateway",
+                actionCommand: authError.actionCommand ?? pairingCommand,
+                docsURL: self.docsURL(authError.docsURLString, fallback: "https://docs.openclaw.ai/gateway/pairing"),
+                requestId: requestId,
+                retryable: false,
+                pauseReconnect: true,
+                authError: authError)
+        }
+    }
+
+    private static func problem(
+        kind: GatewayConnectionProblem.Kind,
+        owner: GatewayConnectionProblem.Owner,
+        title: String,
+        message: String,
+        actionLabel: String?,
+        actionCommand: String?,
+        docsURL: URL?,
+        requestId: String?,
+        retryable: Bool,
+        pauseReconnect: Bool,
+        authError: GatewayConnectAuthError)
+        -> GatewayConnectionProblem
+    {
+        GatewayConnectionProblem(
+            kind: kind,
+            owner: authError.ownerRaw.flatMap(self.owner(from:)) ?? owner,
+            title: title,
+            message: message,
+            actionLabel: actionLabel,
+            actionCommand: actionCommand,
+            docsURL: docsURL,
+            requestId: requestId,
+            retryable: authError.retryableOverride ?? retryable,
+            pauseReconnect: authError.pauseReconnectOverride ?? pauseReconnect,
+            technicalDetails: self.technicalDetails(for: authError))
+    }
+
+    private static func approvalCommand(requestId: String?) -> String {
+        if let requestId = self.nonEmpty(requestId) {
+            return "openclaw devices approve \(requestId)"
+        }
+        return "openclaw devices list"
+    }
+
+    private static func technicalDetails(for authError: GatewayConnectAuthError) -> String? {
+        var parts: [String] = []
+        if let detail = self.nonEmpty(authError.detailCodeRaw) {
+            parts.append(detail)
+        }
+        if let reason = self.nonEmpty(authError.detailsReason) {
+            parts.append("reason=\(reason)")
+        }
+        if let requestId = self.nonEmpty(authError.requestId) {
+            parts.append("requestId=\(requestId)")
+        }
+        if let nextStep = self.nonEmpty(authError.recommendedNextStepRaw) {
+            parts.append("next=\(nextStep)")
+        }
+        if authError.canRetryWithDeviceToken {
+            parts.append("deviceTokenRetry=true")
+        }
+        return parts.isEmpty ? nil : parts.joined(separator: " · ")
+    }
+
+    private static func docsURL(_ preferred: String?, fallback: String?) -> URL? {
+        if let preferred = self.nonEmpty(preferred), let url = URL(string: preferred) {
+            return url
+        }
+        if let fallback = self.nonEmpty(fallback), let url = URL(string: fallback) {
+            return url
+        }
+        return nil
+    }
+
+    private static func owner(from raw: String) -> GatewayConnectionProblem.Owner? {
+        switch raw.trimmingCharacters(in: .whitespacesAndNewlines).lowercased() {
+        case "gateway":
+            return .gateway
+        case "iphone", "ios", "device":
+            return .iphone
+        case "both":
+            return .both
+        case "network":
+            return .network
+        case "unknown", "":
+            return .unknown
+        default:
+            return nil
+        }
+    }
+
+    private static func stringValue(_ value: Any?) -> String? {
+        self.nonEmpty(value as? String)
+    }
+
+    private static func nonEmpty(_ value: String?) -> String? {
+        let trimmed = value?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
+        return trimmed.isEmpty ? nil : trimmed
+    }
+}

apps/shared/OpenClawKit/Sources/OpenClawKit/GatewayErrors.swift

@@ -43,12 +43,32 @@ public struct GatewayConnectAuthError: LocalizedError, Sendable {
     public let detailCodeRaw: String?
     public let recommendedNextStepRaw: String?
     public let canRetryWithDeviceToken: Bool
+    public let requestId: String?
+    public let detailsReason: String?
+    public let ownerRaw: String?
+    public let titleOverride: String?
+    public let userMessageOverride: String?
+    public let actionLabel: String?
+    public let actionCommand: String?
+    public let docsURLString: String?
+    public let retryableOverride: Bool?
+    public let pauseReconnectOverride: Bool?
 
     public init(
         message: String,
         detailCodeRaw: String?,
         canRetryWithDeviceToken: Bool,
-        recommendedNextStepRaw: String? = nil)
+        recommendedNextStepRaw: String? = nil,
+        requestId: String? = nil,
+        detailsReason: String? = nil,
+        ownerRaw: String? = nil,
+        titleOverride: String? = nil,
+        userMessageOverride: String? = nil,
+        actionLabel: String? = nil,
+        actionCommand: String? = nil,
+        docsURLString: String? = nil,
+        retryableOverride: Bool? = nil,
+        pauseReconnectOverride: Bool? = nil)
     {
         let trimmedMessage = message.trimmingCharacters(in: .whitespacesAndNewlines)
         let trimmedDetailCode = detailCodeRaw?.trimmingCharacters(in: .whitespacesAndNewlines)
@@ -59,19 +79,54 @@ public struct GatewayConnectAuthError: LocalizedError, Sendable {
         self.canRetryWithDeviceToken = canRetryWithDeviceToken
         self.recommendedNextStepRaw =
             trimmedRecommendedNextStep?.isEmpty == false ? trimmedRecommendedNextStep : nil
+        self.requestId = Self.trimmedOrNil(requestId)
+        self.detailsReason = Self.trimmedOrNil(detailsReason)
+        self.ownerRaw = Self.trimmedOrNil(ownerRaw)
+        self.titleOverride = Self.trimmedOrNil(titleOverride)
+        self.userMessageOverride = Self.trimmedOrNil(userMessageOverride)
+        self.actionLabel = Self.trimmedOrNil(actionLabel)
+        self.actionCommand = Self.trimmedOrNil(actionCommand)
+        self.docsURLString = Self.trimmedOrNil(docsURLString)
+        self.retryableOverride = retryableOverride
+        self.pauseReconnectOverride = pauseReconnectOverride
     }
 
     public init(
         message: String,
         detailCode: String?,
         canRetryWithDeviceToken: Bool,
-        recommendedNextStep: String? = nil)
+        recommendedNextStep: String? = nil,
+        requestId: String? = nil,
+        detailsReason: String? = nil,
+        ownerRaw: String? = nil,
+        titleOverride: String? = nil,
+        userMessageOverride: String? = nil,
+        actionLabel: String? = nil,
+        actionCommand: String? = nil,
+        docsURLString: String? = nil,
+        retryableOverride: Bool? = nil,
+        pauseReconnectOverride: Bool? = nil)
     {
         self.init(
             message: message,
             detailCodeRaw: detailCode,
             canRetryWithDeviceToken: canRetryWithDeviceToken,
-            recommendedNextStepRaw: recommendedNextStep)
+            recommendedNextStepRaw: recommendedNextStep,
+            requestId: requestId,
+            detailsReason: detailsReason,
+            ownerRaw: ownerRaw,
+            titleOverride: titleOverride,
+            userMessageOverride: userMessageOverride,
+            actionLabel: actionLabel,
+            actionCommand: actionCommand,
+            docsURLString: docsURLString,
+            retryableOverride: retryableOverride,
+            pauseReconnectOverride: pauseReconnectOverride)
+    }
+
+    private static func trimmedOrNil(_ value: String?) -> String? {
+        let trimmed = value?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
+        return trimmed.isEmpty ? nil : trimmed
     }
 
     public var detailCode: String? { self.detailCodeRaw }

apps/shared/OpenClawKit/Sources/OpenClawKit/WatchCommands.swift

@@ -5,12 +5,36 @@ public enum OpenClawWatchCommand: String, Codable, Sendable {
     case notify = "watch.notify"
 }
 
+public enum OpenClawWatchPayloadType: String, Codable, Sendable, Equatable {
+    case notify = "watch.notify"
+    case reply = "watch.reply"
+    case execApprovalPrompt = "watch.execApproval.prompt"
+    case execApprovalResolve = "watch.execApproval.resolve"
+    case execApprovalResolved = "watch.execApproval.resolved"
+    case execApprovalExpired = "watch.execApproval.expired"
+    case execApprovalSnapshot = "watch.execApproval.snapshot"
+    case execApprovalSnapshotRequest = "watch.execApproval.snapshotRequest"
+}
+
 public enum OpenClawWatchRisk: String, Codable, Sendable, Equatable {
     case low
     case medium
     case high
 }
 
+public enum OpenClawWatchExecApprovalDecision: String, Codable, Sendable, Equatable {
+    case allowOnce = "allow-once"
+    case deny
+}
+
+public enum OpenClawWatchExecApprovalCloseReason: String, Codable, Sendable, Equatable {
+    case expired
+    case notFound = "not-found"
+    case unavailable
+    case replaced
+    case resolved
+}
+
 public struct OpenClawWatchAction: Codable, Sendable, Equatable {
     public var id: String
     public var label: String
@@ -23,6 +47,151 @@ public struct OpenClawWatchAction: Codable, Sendable, Equatable {
     }
 }
 
+public struct OpenClawWatchExecApprovalItem: Codable, Sendable, Equatable, Identifiable {
+    public var id: String
+    public var commandText: String
+    public var commandPreview: String?
+    public var host: String?
+    public var nodeId: String?
+    public var agentId: String?
+    public var expiresAtMs: Int?
+    public var allowedDecisions: [OpenClawWatchExecApprovalDecision]
+    public var risk: OpenClawWatchRisk?
+
+    public init(
+        id: String,
+        commandText: String,
+        commandPreview: String? = nil,
+        host: String? = nil,
+        nodeId: String? = nil,
+        agentId: String? = nil,
+        expiresAtMs: Int? = nil,
+        allowedDecisions: [OpenClawWatchExecApprovalDecision] = [],
+        risk: OpenClawWatchRisk? = nil)
+    {
+        self.id = id
+        self.commandText = commandText
+        self.commandPreview = commandPreview
+        self.host = host
+        self.nodeId = nodeId
+        self.agentId = agentId
+        self.expiresAtMs = expiresAtMs
+        self.allowedDecisions = allowedDecisions
+        self.risk = risk
+    }
+}
+
+public struct OpenClawWatchExecApprovalPromptMessage: Codable, Sendable, Equatable {
+    public var type: OpenClawWatchPayloadType
+    public var approval: OpenClawWatchExecApprovalItem
+    public var sentAtMs: Int?
+    public var deliveryId: String?
+    public var resetResolvingState: Bool?
+
+    public init(
+        approval: OpenClawWatchExecApprovalItem,
+        sentAtMs: Int? = nil,
+        deliveryId: String? = nil,
+        resetResolvingState: Bool? = nil)
+    {
+        self.type = .execApprovalPrompt
+        self.approval = approval
+        self.sentAtMs = sentAtMs
+        self.deliveryId = deliveryId
+        self.resetResolvingState = resetResolvingState
+    }
+}
+
+public struct OpenClawWatchExecApprovalResolveMessage: Codable, Sendable, Equatable {
+    public var type: OpenClawWatchPayloadType
+    public var approvalId: String
+    public var decision: OpenClawWatchExecApprovalDecision
+    public var replyId: String
+    public var sentAtMs: Int?
+
+    public init(
+        approvalId: String,
+        decision: OpenClawWatchExecApprovalDecision,
+        replyId: String,
+        sentAtMs: Int? = nil)
+    {
+        self.type = .execApprovalResolve
+        self.approvalId = approvalId
+        self.decision = decision
+        self.replyId = replyId
+        self.sentAtMs = sentAtMs
+    }
+}
+
+public struct OpenClawWatchExecApprovalResolvedMessage: Codable, Sendable, Equatable {
+    public var type: OpenClawWatchPayloadType
+    public var approvalId: String
+    public var decision: OpenClawWatchExecApprovalDecision?
+    public var resolvedAtMs: Int?
+    public var source: String?
+
+    public init(
+        approvalId: String,
+        decision: OpenClawWatchExecApprovalDecision? = nil,
+        resolvedAtMs: Int? = nil,
+        source: String? = nil)
+    {
+        self.type = .execApprovalResolved
+        self.approvalId = approvalId
+        self.decision = decision
+        self.resolvedAtMs = resolvedAtMs
+        self.source = source
+    }
+}
+
+public struct OpenClawWatchExecApprovalExpiredMessage: Codable, Sendable, Equatable {
+    public var type: OpenClawWatchPayloadType
+    public var approvalId: String
+    public var reason: OpenClawWatchExecApprovalCloseReason
+    public var expiredAtMs: Int?
+
+    public init(
+        approvalId: String,
+        reason: OpenClawWatchExecApprovalCloseReason,
+        expiredAtMs: Int? = nil)
+    {
+        self.type = .execApprovalExpired
+        self.approvalId = approvalId
+        self.reason = reason
+        self.expiredAtMs = expiredAtMs
+    }
+}
+
+public struct OpenClawWatchExecApprovalSnapshotMessage: Codable, Sendable, Equatable {
+    public var type: OpenClawWatchPayloadType
+    public var approvals: [OpenClawWatchExecApprovalItem]
+    public var sentAtMs: Int?
+    public var snapshotId: String?
+
+    public init(
+        approvals: [OpenClawWatchExecApprovalItem],
+        sentAtMs: Int? = nil,
+        snapshotId: String? = nil)
+    {
+        self.type = .execApprovalSnapshot
+        self.approvals = approvals
+        self.sentAtMs = sentAtMs
+        self.snapshotId = snapshotId
+    }
+}
+
+public struct OpenClawWatchExecApprovalSnapshotRequestMessage: Codable, Sendable, Equatable {
+    public var type: OpenClawWatchPayloadType
+    public var requestId: String
+    public var sentAtMs: Int?
+
+    public init(requestId: String, sentAtMs: Int? = nil) {
+        self.type = .execApprovalSnapshotRequest
+        self.requestId = requestId
+        self.sentAtMs = sentAtMs
+    }
+}
+
 public struct OpenClawWatchStatusPayload: Codable, Sendable, Equatable {
     public var supported: Bool
     public var paired: Bool

apps/shared/OpenClawKit/Sources/OpenClawProtocol/GatewayModels.swift

@@ -537,6 +537,8 @@ public struct AgentParams: Codable, Sendable {
     public let besteffortdeliver: Bool?
     public let lane: String?
     public let extrasystemprompt: String?
+    public let bootstrapcontextmode: AnyCodable?
+    public let bootstrapcontextrunkind: AnyCodable?
     public let internalevents: [[String: AnyCodable]]?
     public let inputprovenance: [String: AnyCodable]?
     public let idempotencykey: String
@@ -566,6 +568,8 @@ public struct AgentParams: Codable, Sendable {
         besteffortdeliver: Bool?,
         lane: String?,
         extrasystemprompt: String?,
+        bootstrapcontextmode: AnyCodable?,
+        bootstrapcontextrunkind: AnyCodable?,
         internalevents: [[String: AnyCodable]]?,
         inputprovenance: [String: AnyCodable]?,
         idempotencykey: String,
@@ -594,6 +598,8 @@ public struct AgentParams: Codable, Sendable {
         self.besteffortdeliver = besteffortdeliver
         self.lane = lane
         self.extrasystemprompt = extrasystemprompt
+        self.bootstrapcontextmode = bootstrapcontextmode
+        self.bootstrapcontextrunkind = bootstrapcontextrunkind
         self.internalevents = internalevents
         self.inputprovenance = inputprovenance
         self.idempotencykey = idempotencykey
@@ -624,6 +630,8 @@ public struct AgentParams: Codable, Sendable {
         case besteffortdeliver = "bestEffortDeliver"
         case lane
         case extrasystemprompt = "extraSystemPrompt"
+        case bootstrapcontextmode = "bootstrapContextMode"
+        case bootstrapcontextrunkind = "bootstrapContextRunKind"
         case internalevents = "internalEvents"
         case inputprovenance = "inputProvenance"
         case idempotencykey = "idempotencyKey"
@@ -1327,6 +1335,236 @@ public struct SessionsResolveParams: Codable, Sendable {
     }
 }
 
+public struct SessionCompactionCheckpoint: Codable, Sendable {
+    public let checkpointid: String
+    public let sessionkey: String
+    public let sessionid: String
+    public let createdat: Int
+    public let reason: AnyCodable
+    public let tokensbefore: Int?
+    public let tokensafter: Int?
+    public let summary: String?
+    public let firstkeptentryid: String?
+    public let precompaction: [String: AnyCodable]
+    public let postcompaction: [String: AnyCodable]
+
+    public init(
+        checkpointid: String,
+        sessionkey: String,
+        sessionid: String,
+        createdat: Int,
+        reason: AnyCodable,
+        tokensbefore: Int?,
+        tokensafter: Int?,
+        summary: String?,
+        firstkeptentryid: String?,
+        precompaction: [String: AnyCodable],
+        postcompaction: [String: AnyCodable])
+    {
+        self.checkpointid = checkpointid
+        self.sessionkey = sessionkey
+        self.sessionid = sessionid
+        self.createdat = createdat
+        self.reason = reason
+        self.tokensbefore = tokensbefore
+        self.tokensafter = tokensafter
+        self.summary = summary
+        self.firstkeptentryid = firstkeptentryid
+        self.precompaction = precompaction
+        self.postcompaction = postcompaction
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case checkpointid = "checkpointId"
+        case sessionkey = "sessionKey"
+        case sessionid = "sessionId"
+        case createdat = "createdAt"
+        case reason
+        case tokensbefore = "tokensBefore"
+        case tokensafter = "tokensAfter"
+        case summary
+        case firstkeptentryid = "firstKeptEntryId"
+        case precompaction = "preCompaction"
+        case postcompaction = "postCompaction"
+    }
+}
+
+public struct SessionsCompactionListParams: Codable, Sendable {
+    public let key: String
+
+    public init(
+        key: String)
+    {
+        self.key = key
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case key
+    }
+}
+
+public struct SessionsCompactionGetParams: Codable, Sendable {
+    public let key: String
+    public let checkpointid: String
+
+    public init(
+        key: String,
+        checkpointid: String)
+    {
+        self.key = key
+        self.checkpointid = checkpointid
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case key
+        case checkpointid = "checkpointId"
+    }
+}
+
+public struct SessionsCompactionBranchParams: Codable, Sendable {
+    public let key: String
+    public let checkpointid: String
+
+    public init(
+        key: String,
+        checkpointid: String)
+    {
+        self.key = key
+        self.checkpointid = checkpointid
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case key
+        case checkpointid = "checkpointId"
+    }
+}
+
+public struct SessionsCompactionRestoreParams: Codable, Sendable {
+    public let key: String
+    public let checkpointid: String
+
+    public init(
+        key: String,
+        checkpointid: String)
+    {
+        self.key = key
+        self.checkpointid = checkpointid
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case key
+        case checkpointid = "checkpointId"
+    }
+}
+
+public struct SessionsCompactionListResult: Codable, Sendable {
+    public let ok: Bool
+    public let key: String
+    public let checkpoints: [SessionCompactionCheckpoint]
+
+    public init(
+        ok: Bool,
+        key: String,
+        checkpoints: [SessionCompactionCheckpoint])
+    {
+        self.ok = ok
+        self.key = key
+        self.checkpoints = checkpoints
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case ok
+        case key
+        case checkpoints
+    }
+}
+
+public struct SessionsCompactionGetResult: Codable, Sendable {
+    public let ok: Bool
+    public let key: String
+    public let checkpoint: SessionCompactionCheckpoint
+
+    public init(
+        ok: Bool,
+        key: String,
+        checkpoint: SessionCompactionCheckpoint)
+    {
+        self.ok = ok
+        self.key = key
+        self.checkpoint = checkpoint
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case ok
+        case key
+        case checkpoint
+    }
+}
+
+public struct SessionsCompactionBranchResult: Codable, Sendable {
+    public let ok: Bool
+    public let sourcekey: String
+    public let key: String
+    public let sessionid: String
+    public let checkpoint: SessionCompactionCheckpoint
+    public let entry: [String: AnyCodable]
+
+    public init(
+        ok: Bool,
+        sourcekey: String,
+        key: String,
+        sessionid: String,
+        checkpoint: SessionCompactionCheckpoint,
+        entry: [String: AnyCodable])
+    {
+        self.ok = ok
+        self.sourcekey = sourcekey
+        self.key = key
+        self.sessionid = sessionid
+        self.checkpoint = checkpoint
+        self.entry = entry
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case ok
+        case sourcekey = "sourceKey"
+        case key
+        case sessionid = "sessionId"
+        case checkpoint
+        case entry
+    }
+}
+
+public struct SessionsCompactionRestoreResult: Codable, Sendable {
+    public let ok: Bool
+    public let key: String
+    public let sessionid: String
+    public let checkpoint: SessionCompactionCheckpoint
+    public let entry: [String: AnyCodable]
+
+    public init(
+        ok: Bool,
+        key: String,
+        sessionid: String,
+        checkpoint: SessionCompactionCheckpoint,
+        entry: [String: AnyCodable])
+    {
+        self.ok = ok
+        self.key = key
+        self.sessionid = sessionid
+        self.checkpoint = checkpoint
+        self.entry = entry
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case ok
+        case key
+        case sessionid = "sessionId"
+        case checkpoint
+        case entry
+    }
+}
+
 public struct SessionsCreateParams: Codable, Sendable {
     public let key: String?
     public let agentid: String?

apps/shared/OpenClawKit/Tests/OpenClawKitTests/GatewayErrorsTests.swift

@@ -1,3 +1,4 @@
+import Foundation
 import OpenClawKit
 import Testing
 
@@ -11,4 +12,81 @@ import Testing
         #expect(error.isNonRecoverable)
         #expect(error.detail == .authBootstrapTokenInvalid)
     }
+
+    @Test func connectAuthErrorPreservesStructuredMetadata() {
+        let error = GatewayConnectAuthError(
+            message: "pairing required",
+            detailCode: GatewayConnectAuthDetailCode.pairingRequired.rawValue,
+            canRetryWithDeviceToken: false,
+            recommendedNextStep: "review_auth_configuration",
+            requestId: "req-123",
+            detailsReason: "scope-upgrade",
+            ownerRaw: "gateway",
+            titleOverride: "Additional permissions required",
+            userMessageOverride: "Approve the requested permissions on the gateway, then reconnect.",
+            actionLabel: "Approve on gateway",
+            actionCommand: "openclaw devices approve req-123",
+            docsURLString: "https://docs.openclaw.ai/gateway/pairing",
+            retryableOverride: false,
+            pauseReconnectOverride: true)
+
+        #expect(error.requestId == "req-123")
+        #expect(error.detailsReason == "scope-upgrade")
+        #expect(error.ownerRaw == "gateway")
+        #expect(error.titleOverride == "Additional permissions required")
+        #expect(error.actionCommand == "openclaw devices approve req-123")
+        #expect(error.docsURLString == "https://docs.openclaw.ai/gateway/pairing")
+        #expect(error.pauseReconnectOverride == true)
+    }
+
+    @Test func pairingProblemUsesStructuredRequestMetadata() {
+        let error = GatewayConnectAuthError(
+            message: "pairing required",
+            detailCode: GatewayConnectAuthDetailCode.pairingRequired.rawValue,
+            canRetryWithDeviceToken: false,
+            requestId: "req-123",
+            detailsReason: "scope-upgrade")
+
+        let problem = GatewayConnectionProblemMapper.map(error: error)
+
+        #expect(problem?.kind == .pairingScopeUpgradeRequired)
+        #expect(problem?.requestId == "req-123")
+        #expect(problem?.pauseReconnect == true)
+        #expect(problem?.actionCommand == "openclaw devices approve req-123")
+    }
+
+    @Test func cancelledTransportDoesNotReplaceStructuredPairingProblem() {
+        let pairing = GatewayConnectAuthError(
+            message: "pairing required",
+            detailCode: GatewayConnectAuthDetailCode.pairingRequired.rawValue,
+            canRetryWithDeviceToken: false,
+            requestId: "req-123")
+        let previousProblem = GatewayConnectionProblemMapper.map(error: pairing)
+        let cancelled = NSError(
+            domain: URLError.errorDomain,
+            code: URLError.cancelled.rawValue,
+            userInfo: [NSLocalizedDescriptionKey: "gateway receive: cancelled"])
+
+        let preserved = GatewayConnectionProblemMapper.map(error: cancelled, preserving: previousProblem)
+
+        #expect(preserved?.kind == .pairingRequired)
+        #expect(preserved?.requestId == "req-123")
+    }
+
+    @Test func unmappedTransportErrorClearsStaleStructuredProblem() {
+        let pairing = GatewayConnectAuthError(
+            message: "pairing required",
+            detailCode: GatewayConnectAuthDetailCode.pairingRequired.rawValue,
+            canRetryWithDeviceToken: false,
+            requestId: "req-123")
+        let previousProblem = GatewayConnectionProblemMapper.map(error: pairing)
+        let unknownTransport = NSError(
+            domain: NSURLErrorDomain,
+            code: -1202,
+            userInfo: [NSLocalizedDescriptionKey: "certificate chain validation failed"])
+
+        let mapped = GatewayConnectionProblemMapper.map(error: unknownTransport, preserving: previousProblem)
+
+        #expect(mapped == nil)
+    }
 }

docs/.generated/config-baseline.sha256

@@ -1,4 +1,4 @@
-1c74540dd152c55dbda3e5dee1e37008ee3e6aabb0608e571292832c7a1c012c  config-baseline.json
-7e30316f2326b7d07b71d7b8a96049a74b81428921299b5c4b5aa3d080e03305  config-baseline.core.json
-66edc86a9d16db1b9e9e7dd99b7032e2d9bcfb9ff210256a21f4b4f088cb3dc1  config-baseline.channel.json
-d6ebc4948499b997c4a3727cf31849d4a598de9f1a4c197417dcc0b0ec1b734f  config-baseline.plugin.json
+d21efc7ef1d28ed3bc3fa2cdb09dea275513dcb5539b47bd71158d6a89bd3e99  config-baseline.json
+c3dd9fb8a0059dba411c4d88a6b84ca28af1e0b1925c669058ef9f38c6d2718b  config-baseline.core.json
+d22f4414b79ee03d896e58d875c80523bcc12303cbacb1700261e6ec73945187  config-baseline.channel.json
+483d4f3c1d516719870ad6f2aba6779b9950f85471ee77b9994a077a7574a892  config-baseline.plugin.json

docs/.generated/plugin-sdk-api-baseline.sha256

@@ -1,2 +1,2 @@
-23bfae10a189a7d0548bc7213a9180841bbb1125e97ce1d2d0b7a765773a92fd  plugin-sdk-api-baseline.json
-6c64b352b19368015c867b4c16225d676110544943497238c2f78602ad2fb519  plugin-sdk-api-baseline.jsonl
+467a44dd86fa7e2f62e0ba6cf0a2127001876dc21c31d695a87a91ea4d147101  plugin-sdk-api-baseline.json
+0004e7feade04914beea79ae96b343448e2e77fbd4e743cd652ea516852d86ad  plugin-sdk-api-baseline.jsonl

docs/channels/groups.md

@@ -227,7 +227,10 @@ Quick mental model (evaluation order for group messages):
 
 Group messages require a mention unless overridden per group. Defaults live per subsystem under `*.groups."*"`.
 
-Replying to a bot message counts as an implicit mention (when the channel supports reply metadata). This applies to Telegram, WhatsApp, Slack, Discord, and Microsoft Teams.
+Replying to a bot message counts as an implicit mention when the channel
+supports reply metadata. Quoting a bot message can also count as an implicit
+mention on channels that expose quote metadata. Current built-in cases include
+Telegram, WhatsApp, Slack, Discord, Microsoft Teams, and ZaloUser.
 
 ```json5
 {

docs/channels/matrix.md

@@ -61,13 +61,17 @@ What the Matrix wizard actually asks for:
 - optional device name
 - whether to enable E2EE
 - whether to configure Matrix room access now
+- whether to configure Matrix invite auto-join now
+- when invite auto-join is enabled, whether it should be `allowlist`, `always`, or `off`
 
 Wizard behavior that matters:
 
-- If Matrix auth env vars already exist for the selected account, and that account does not already have auth saved in config, the wizard offers an env shortcut and only writes `enabled: true` for that account.
+- If Matrix auth env vars already exist for the selected account, and that account does not already have auth saved in config, the wizard offers an env shortcut so setup can keep auth in env vars instead of copying secrets into config.
 - When you add another Matrix account interactively, the entered account name is normalized into the account ID used in config and env vars. For example, `Ops Bot` becomes `ops-bot`.
 - DM allowlist prompts accept full `@user:server` values immediately. Display names only work when live directory lookup finds one exact match; otherwise the wizard asks you to retry with a full Matrix ID.
 - Room allowlist prompts accept room IDs and aliases directly. They can also resolve joined-room names live, but unresolved names are only kept as typed during setup and are ignored later by runtime allowlist resolution. Prefer `!room:server` or `#alias:server`.
+- The wizard now shows an explicit warning before the invite auto-join step because `channels.matrix.autoJoin` defaults to `off`; agents will not join invited rooms or fresh DM-style invites unless you set it.
+- In invite auto-join allowlist mode, use only stable invite targets: `!roomId:server`, `#alias:server`, or `*`. Plain room names are rejected.
 - Runtime room/session identity uses the stable Matrix room ID. Room-declared aliases are only used as lookup inputs, not as the long-term session key or stable group identity.
 - To resolve room names before saving them, use `openclaw channels resolve --channel matrix "Project Room"`.
 
@@ -77,6 +81,8 @@ Wizard behavior that matters:
 If you leave it unset, the bot will not join invited rooms or fresh DM-style invites, so it will not appear in new groups or invited DMs unless you join manually first.
 
 Set `autoJoin: "allowlist"` together with `autoJoinAllowlist` to restrict which invites it accepts, or set `autoJoin: "always"` if you want it to join every invite.
+
+In `allowlist` mode, `autoJoinAllowlist` only accepts `!roomId:server`, `#alias:server`, or `*`.
 </Warning>
 
 Allowlist example:
@@ -874,7 +880,8 @@ See [Pairing](/channels/pairing) for the shared DM pairing flow and storage layo
 
 ## Exec approvals
 
-Matrix can act as an exec approval client for a Matrix account.
+Matrix can act as a native approval client for a Matrix account. The native
+DM/channel routing knobs still live under exec approval config:
 
 - `channels.matrix.execApprovals.enabled`
 - `channels.matrix.execApprovals.approvers` (optional; falls back to `channels.matrix.dm.allowFrom`)
@@ -882,13 +889,14 @@ Matrix can act as an exec approval client for a Matrix account.
 - `channels.matrix.execApprovals.agentFilter`
 - `channels.matrix.execApprovals.sessionFilter`
 
-Approvers must be Matrix user IDs such as `@owner:example.org`. Matrix auto-enables native exec approvals when `enabled` is unset or `"auto"` and at least one approver can be resolved, either from `execApprovals.approvers` or from `channels.matrix.dm.allowFrom`. Set `enabled: false` to disable Matrix as a native approval client explicitly. Approval requests otherwise fall back to other configured approval routes or the exec approval fallback policy.
+Approvers must be Matrix user IDs such as `@owner:example.org`. Matrix auto-enables native approvals when `enabled` is unset or `"auto"` and at least one approver can be resolved. Exec approvals use `execApprovals.approvers` first and can fall back to `channels.matrix.dm.allowFrom`. Plugin approvals authorize through `channels.matrix.dm.allowFrom`. Set `enabled: false` to disable Matrix as a native approval client explicitly. Approval requests otherwise fall back to other configured approval routes or the approval fallback policy.
 
-Native Matrix routing is exec-only today:
+Matrix native routing now supports both approval kinds:
 
-- `channels.matrix.execApprovals.*` controls native DM/channel routing for exec approvals only.
-- Plugin approvals still use shared same-chat `/approve` plus any configured `approvals.plugin` forwarding.
-- Matrix can still reuse `channels.matrix.dm.allowFrom` for plugin-approval authorization when it can infer approvers safely, but it does not expose a separate native plugin-approval DM/channel fanout path.
+- `channels.matrix.execApprovals.*` controls the native DM/channel fanout mode for Matrix approval prompts.
+- Exec approvals use the exec approver set from `execApprovals.approvers` or `channels.matrix.dm.allowFrom`.
+- Plugin approvals use the Matrix DM allowlist from `channels.matrix.dm.allowFrom`.
+- Matrix reaction shortcuts and message updates apply to both exec and plugin approvals.
 
 Delivery rules:
 
@@ -904,9 +912,9 @@ Matrix approval prompts seed reaction shortcuts on the primary approval message:
 
 Approvers can react on that message or use the fallback slash commands: `/approve <id> allow-once`, `/approve <id> allow-always`, or `/approve <id> deny`.
 
-Only resolved approvers can approve or deny. Channel delivery includes the command text, so only enable `channel` or `both` in trusted rooms.
+Only resolved approvers can approve or deny. For exec approvals, channel delivery includes the command text, so only enable `channel` or `both` in trusted rooms.
 
-Matrix approval prompts reuse the shared core approval planner. The Matrix-specific native surface is transport only for exec approvals: room/DM routing and message send/update/delete behavior.
+Matrix approval prompts reuse the shared core approval planner. The Matrix-specific native surface handles room/DM routing, reactions, and message send/update/delete behavior for both exec and plugin approvals.
 
 Per-account override:
 

docs/channels/qa-channel.md

@@ -75,10 +75,13 @@ self-check, and writes a Markdown report under `.artifacts/qa-e2e/`.
 Private debugger UI:
 
 ```bash
-pnpm qa:lab:build
-pnpm openclaw qa ui
+pnpm qa:lab:up
 ```
 
+That one command builds the QA site, starts the Docker-backed gateway + QA Lab
+stack, and prints the QA Lab URL. From that site you can pick scenarios, choose
+the model lane, launch individual runs, and watch results live.
+
 Full repo-backed QA suite:
 
 ```bash
@@ -96,10 +99,10 @@ Current scope is intentionally narrow:
 - threaded routing grammar
 - channel-owned message actions
 - Markdown reporting
+- Docker-backed QA site with run controls
 
 Follow-up work will add:
 
-- Dockerized OpenClaw orchestration
 - provider/model matrix execution
 - richer scenario discovery
 - OpenClaw-native orchestration later

docs/channels/slack.md

@@ -399,7 +399,7 @@ Current Slack message actions include `send`, `upload-file`, `download-file`, `r
 
     - explicit app mention (`<@botId>`)
     - mention regex patterns (`agents.list[].groupChat.mentionPatterns`, fallback `messages.groupChat.mentionPatterns`)
-    - implicit reply-to-bot thread behavior
+    - implicit reply-to-bot thread behavior (disabled when `thread.requireExplicitMention` is `true`)
 
     Per-channel controls (`channels.slack.channels.<id>`; names only via startup resolution or `dangerouslyAllowNameMatching`):
 
@@ -423,6 +423,7 @@ Current Slack message actions include `send`, `upload-file`, `download-file`, `r
 - Thread replies can create thread session suffixes (`:thread:<threadTs>`) when applicable.
 - `channels.slack.thread.historyScope` default is `thread`; `thread.inheritParent` default is `false`.
 - `channels.slack.thread.initialHistoryLimit` controls how many existing thread messages are fetched when a new thread session starts (default `20`; set `0` to disable).
+- `channels.slack.thread.requireExplicitMention` (default `false`): when `true`, suppress implicit thread mentions so the bot only responds to explicit `@bot` mentions inside threads, even when the bot already participated in the thread. Without this, replies in a bot-participated thread bypass `requireMention` gating.
 
 Reply threading controls:
 

docs/channels/zalouser.md

@@ -124,6 +124,7 @@ Example:
 - `channels.zalouser.groups.<group>.requireMention` controls whether group replies require a mention.
 - Resolution order: exact group id/name -> normalized group slug -> `*` -> default (`true`).
 - This applies both to allowlisted groups and open group mode.
+- Quoting a bot message counts as an implicit mention for group activation.
 - Authorized control commands (for example `/new`) can bypass mention gating.
 - When a group message is skipped because mention is required, OpenClaw stores it as pending group history and includes it on the next processed group message.
 - Group history limit defaults to `messages.groupChat.historyLimit` (fallback `50`). You can override per account with `channels.zalouser.historyLimit`.

docs/cli/index.md

@@ -35,6 +35,7 @@ This page describes the current CLI behavior. If commands change, update this do
 - [`logs`](/cli/logs)
 - [`system`](/cli/system)
 - [`models`](/cli/models)
+- [`infer`](/cli/infer)
 - [`memory`](/cli/memory)
 - [`directory`](/cli/directory)
 - [`nodes`](/cli/nodes)
@@ -248,6 +249,16 @@ openclaw [--dev] [--profile <name>] <command>
     fallbacks list|add|remove|clear
     image-fallbacks list|add|remove|clear
     scan
+  infer (alias: capability)
+    list
+    inspect
+    model run|list|inspect|providers|auth login|logout|status
+    image generate|edit|describe|describe-many|providers
+    audio transcribe|providers
+    tts convert|voices|providers|status|enable|disable|set-provider
+    video generate|describe|providers
+    web search|fetch|providers
+    embedding create|providers
     auth add|login|login-github-copilot|setup-token|paste-token
     auth order get|set|clear
   sandbox

docs/cli/infer.md

@@ -0,0 +1,280 @@
+---
+summary: "Infer-first CLI for provider-backed model, image, audio, TTS, video, web, and embedding workflows"
+read_when:
+  - Adding or modifying `openclaw infer` commands
+  - Designing stable headless capability automation
+title: "Inference CLI"
+---
+
+# Inference CLI
+
+`openclaw infer` is the canonical headless surface for provider-backed inference workflows.
+
+It intentionally exposes capability families, not raw gateway RPC names and not raw agent tool ids.
+
+## Turn infer into a skill
+
+Copy and paste this to an agent:
+
+```text
+Read https://docs.openclaw.ai/cli/infer, then create a skill that routes my common workflows to `openclaw infer`.
+Focus on model runs, image generation, video generation, audio transcription, TTS, web search, and embeddings.
+```
+
+A good infer-based skill should:
+
+- map common user intents to the correct infer subcommand
+- include a few canonical infer examples for the workflows it covers
+- prefer `openclaw infer ...` in examples and suggestions
+- avoid re-documenting the entire infer surface inside the skill body
+
+Typical infer-focused skill coverage:
+
+- `openclaw infer model run`
+- `openclaw infer image generate`
+- `openclaw infer audio transcribe`
+- `openclaw infer tts convert`
+- `openclaw infer web search`
+- `openclaw infer embedding create`
+
+## Why use infer
+
+`openclaw infer` provides one consistent CLI for provider-backed inference tasks inside OpenClaw.
+
+Benefits:
+
+- Use the providers and models already configured in OpenClaw instead of wiring up one-off wrappers for each backend.
+- Keep model, image, audio transcription, TTS, video, web, and embedding workflows under one command tree.
+- Use a stable `--json` output shape for scripts, automation, and agent-driven workflows.
+- Prefer a first-party OpenClaw surface when the task is fundamentally "run inference."
+- Use the normal local path without requiring the gateway for most infer commands.
+
+## Command tree
+
+```text
+ openclaw infer
+  list
+  inspect
+
+  model
+    run
+    list
+    inspect
+    providers
+    auth login
+    auth logout
+    auth status
+
+  image
+    generate
+    edit
+    describe
+    describe-many
+    providers
+
+  audio
+    transcribe
+    providers
+
+  tts
+    convert
+    voices
+    providers
+    status
+    enable
+    disable
+    set-provider
+
+  video
+    generate
+    describe
+    providers
+
+  web
+    search
+    fetch
+    providers
+
+  embedding
+    create
+    providers
+```
+
+## Common tasks
+
+This table maps common inference tasks to the corresponding infer command.
+
+| Task                    | Command                                                                | Notes                                                |
+| ----------------------- | ---------------------------------------------------------------------- | ---------------------------------------------------- |
+| Run a text/model prompt | `openclaw infer model run --prompt "..." --json`                       | Uses the normal local path by default                |
+| Generate an image       | `openclaw infer image generate --prompt "..." --json`                  | Use `image edit` when starting from an existing file |
+| Describe an image file  | `openclaw infer image describe --file ./image.png --json`              | `--model` must be `<provider/model>`                 |
+| Transcribe audio        | `openclaw infer audio transcribe --file ./memo.m4a --json`             | `--model` must be `<provider/model>`                 |
+| Synthesize speech       | `openclaw infer tts convert --text "..." --output ./speech.mp3 --json` | `tts status` is gateway-oriented                     |
+| Generate a video        | `openclaw infer video generate --prompt "..." --json`                  |                                                      |
+| Describe a video file   | `openclaw infer video describe --file ./clip.mp4 --json`               | `--model` must be `<provider/model>`                 |
+| Search the web          | `openclaw infer web search --query "..." --json`                       |                                                      |
+| Fetch a web page        | `openclaw infer web fetch --url https://example.com --json`            |                                                      |
+| Create embeddings       | `openclaw infer embedding create --text "..." --json`                  |                                                      |
+
+## Behavior
+
+- `openclaw infer ...` is the primary CLI surface for these workflows.
+- Use `--json` when the output will be consumed by another command or script.
+- Use `--provider` or `--model provider/model` when a specific backend is required.
+- For `image describe`, `audio transcribe`, and `video describe`, `--model` must use the form `<provider/model>`.
+- Stateless execution commands default to local.
+- Gateway-managed state commands default to gateway.
+- The normal local path does not require the gateway to be running.
+
+## Model
+
+Use `model` for provider-backed text inference and model/provider inspection.
+
+```bash
+openclaw infer model run --prompt "Reply with exactly: smoke-ok" --json
+openclaw infer model run --prompt "Summarize this changelog entry" --provider openai --json
+openclaw infer model providers --json
+openclaw infer model inspect --name gpt-5.4 --json
+```
+
+Notes:
+
+- `model run` reuses the agent runtime so provider/model overrides behave like normal agent execution.
+- `model auth login`, `model auth logout`, and `model auth status` manage saved provider auth state.
+
+## Image
+
+Use `image` for generation, edit, and description.
+
+```bash
+openclaw infer image generate --prompt "friendly lobster illustration" --json
+openclaw infer image generate --prompt "cinematic product photo of headphones" --json
+openclaw infer image describe --file ./photo.jpg --json
+openclaw infer image describe --file ./ui-screenshot.png --model openai/gpt-4.1-mini --json
+```
+
+Notes:
+
+- Use `image edit` when starting from existing input files.
+- For `image describe`, `--model` must be `<provider/model>`.
+
+## Audio
+
+Use `audio` for file transcription.
+
+```bash
+openclaw infer audio transcribe --file ./memo.m4a --json
+openclaw infer audio transcribe --file ./team-sync.m4a --language en --prompt "Focus on names and action items" --json
+openclaw infer audio transcribe --file ./memo.m4a --model openai/whisper-1 --json
+```
+
+Notes:
+
+- `audio transcribe` is for file transcription, not realtime session management.
+- `--model` must be `<provider/model>`.
+
+## TTS
+
+Use `tts` for speech synthesis and TTS provider state.
+
+```bash
+openclaw infer tts convert --text "hello from openclaw" --output ./hello.mp3 --json
+openclaw infer tts convert --text "Your build is complete" --output ./build-complete.mp3 --json
+openclaw infer tts providers --json
+openclaw infer tts status --json
+```
+
+Notes:
+
+- `tts status` defaults to gateway because it reflects gateway-managed TTS state.
+- Use `tts providers`, `tts voices`, and `tts set-provider` to inspect and configure TTS behavior.
+
+## Video
+
+Use `video` for generation and description.
+
+```bash
+openclaw infer video generate --prompt "cinematic sunset over the ocean" --json
+openclaw infer video generate --prompt "slow drone shot over a forest lake" --json
+openclaw infer video describe --file ./clip.mp4 --json
+openclaw infer video describe --file ./clip.mp4 --model openai/gpt-4.1-mini --json
+```
+
+Notes:
+
+- `--model` must be `<provider/model>` for `video describe`.
+
+## Web
+
+Use `web` for search and fetch workflows.
+
+```bash
+openclaw infer web search --query "OpenClaw docs" --json
+openclaw infer web search --query "OpenClaw infer web providers" --json
+openclaw infer web fetch --url https://docs.openclaw.ai/cli/infer --json
+openclaw infer web providers --json
+```
+
+Notes:
+
+- Use `web providers` to inspect available, configured, and selected providers.
+
+## Embedding
+
+Use `embedding` for vector creation and embedding provider inspection.
+
+```bash
+openclaw infer embedding create --text "friendly lobster" --json
+openclaw infer embedding create --text "customer support ticket: delayed shipment" --model openai/text-embedding-3-large --json
+openclaw infer embedding providers --json
+```
+
+## JSON output
+
+Infer commands normalize JSON output under a shared envelope:
+
+```json
+{
+  "ok": true,
+  "capability": "image.generate",
+  "transport": "local",
+  "provider": "openai",
+  "model": "gpt-image-1",
+  "attempts": [],
+  "outputs": []
+}
+```
+
+Top-level fields are stable:
+
+- `ok`
+- `capability`
+- `transport`
+- `provider`
+- `model`
+- `attempts`
+- `outputs`
+- `error`
+
+## Common pitfalls
+
+```bash
+# Bad
+openclaw infer media image generate --prompt "friendly lobster"
+
+# Good
+openclaw infer image generate --prompt "friendly lobster"
+```
+
+```bash
+# Bad
+openclaw infer audio transcribe --file ./memo.m4a --model whisper-1 --json
+
+# Good
+openclaw infer audio transcribe --file ./memo.m4a --model openai/whisper-1 --json
+```
+
+## Notes
+
+- `openclaw capability ...` is an alias for `openclaw infer ...`.

docs/concepts/compaction.md

@@ -41,6 +41,71 @@ Before compacting, OpenClaw automatically reminds the agent to save important
 notes to [memory](/concepts/memory) files. This prevents context loss.
 </Info>
 
+Use the `agents.defaults.compaction` setting in your `openclaw.json` to configure compaction behavior (mode, target tokens, etc.).
+Compaction summarization preserves opaque identifiers by default (`identifierPolicy: "strict"`). You can override this with `identifierPolicy: "off"` or provide custom text with `identifierPolicy: "custom"` and `identifierInstructions`.
+
+You can optionally specify a different model for compaction summarization via `agents.defaults.compaction.model`. This is useful when your primary model is a local or small model and you want compaction summaries produced by a more capable model. The override accepts any `provider/model-id` string:
+
+```json
+{
+  "agents": {
+    "defaults": {
+      "compaction": {
+        "model": "openrouter/anthropic/claude-sonnet-4-6"
+      }
+    }
+  }
+}
+```
+
+This also works with local models, for example a second Ollama model dedicated to summarization or a fine-tuned compaction specialist:
+
+```json
+{
+  "agents": {
+    "defaults": {
+      "compaction": {
+        "model": "ollama/llama3.1:8b"
+      }
+    }
+  }
+}
+```
+
+When unset, compaction uses the agent’s primary model.
+
+## Pluggable compaction providers
+
+Plugins can register a custom compaction provider via `registerCompactionProvider()` on the plugin API. When a provider is registered and configured, OpenClaw delegates summarization to it instead of the built-in LLM pipeline.
+
+To use a registered provider, set the provider id in your config:
+
+```json
+{
+  "agents": {
+    "defaults": {
+      "compaction": {
+        "provider": "my-provider"
+      }
+    }
+  }
+}
+```
+
+Setting a `provider` automatically forces `mode: "safeguard"`. Providers receive the same compaction instructions and identifier-preservation policy as the built-in path, and OpenClaw still preserves recent-turn and split-turn suffix context after provider output. If the provider fails or returns an empty result, OpenClaw falls back to built-in LLM summarization.
+
+## Auto-compaction (default on)
+
+When a session nears or exceeds the model’s context window, OpenClaw triggers auto-compaction and may retry the original request using the compacted context.
+
+You’ll see:
+
+- `🧹 Auto-compaction complete` in verbose mode
+- `/status` showing `🧹 Compactions: <count>`
+
+Before compaction, OpenClaw can run a **silent memory flush** turn to store
+durable notes to disk. See [Memory](/concepts/memory) for details and config.
+
 ## Manual compaction
 
 Type `/compact` in any chat to force a compaction. Add instructions to guide

docs/concepts/context-engine.md

@@ -115,6 +115,8 @@ engine is used automatically.
 A plugin can register a context engine using the plugin API:
 
 ```ts
+import { buildMemorySystemPromptAddition } from "openclaw/plugin-sdk/core";
+
 export default function register(api) {
   api.registerContextEngine("my-engine", () => ({
     info: {
@@ -128,12 +130,15 @@ export default function register(api) {
       return { ingested: true };
     },
 
-    async assemble({ sessionId, messages, tokenBudget }) {
+    async assemble({ sessionId, messages, tokenBudget, availableTools, citationsMode }) {
       // Return messages that fit the budget
       return {
         messages: buildContext(messages, tokenBudget),
         estimatedTokens: countTokens(messages),
-        systemPromptAddition: "Use lcm_grep to search history...",
+        systemPromptAddition: buildMemorySystemPromptAddition({
+          availableTools: availableTools ?? new Set(),
+          citationsMode,
+        }),
       };
     },
 
@@ -248,7 +253,13 @@ OpenClaw resolves when it needs a context engine.
 - **Memory plugins** (`plugins.slots.memory`) are separate from context engines.
   Memory plugins provide search/retrieval; context engines control what the
   model sees. They can work together — a context engine might use memory
-  plugin data during assembly.
+  plugin data during assembly. Plugin engines that want the active memory
+  prompt path should prefer `buildMemorySystemPromptAddition(...)` from
+  `openclaw/plugin-sdk/core`, which converts the active memory prompt sections
+  into a ready-to-prepend `systemPromptAddition`. If an engine needs lower-level
+  control, it can still pull raw lines from
+  `openclaw/plugin-sdk/memory-host-core` via
+  `buildActiveMemoryPromptSection(...)`.
 - **Session pruning** (trimming old tool results in-memory) still runs
   regardless of which context engine is active.
 

docs/concepts/model-providers.md

@@ -360,7 +360,7 @@ OpenClaw ships with the pi‑ai catalog. These providers require **no**
     - or `npm install -g @google/gemini-cli`
   - Enable: `openclaw plugins enable google`
   - Login: `openclaw models auth login --provider google-gemini-cli --set-default`
-  - Default model: `google-gemini-cli/gemini-3.1-pro-preview`
+  - Default model: `google-gemini-cli/gemini-3-flash-preview`
   - Note: you do **not** paste a client id or secret into `openclaw.json`. The CLI login flow stores
     tokens in auth profiles on the gateway host.
   - If requests fail after login, set `GOOGLE_CLOUD_PROJECT` or `GOOGLE_CLOUD_PROJECT_ID` on the gateway host.

docs/concepts/qa-e2e-automation.md

@@ -21,20 +21,42 @@ Current pieces:
 - `qa/`: repo-backed seed assets for the kickoff task and baseline QA
   scenarios.
 
-The long-term goal is a two-pane QA site:
+The current QA operator flow is a two-pane QA site:
 
 - Left: Gateway dashboard (Control UI) with the agent.
 - Right: QA Lab, showing the Slack-ish transcript and scenario plan.
 
-That lets an operator or automation loop give the agent a QA mission, observe
-real channel behavior, and record what worked, failed, or stayed blocked.
+Run it with:
+
+```bash
+pnpm qa:lab:up
+```
+
+That builds the QA site, starts the Docker-backed gateway lane, and exposes the
+QA Lab page where an operator or automation loop can give the agent a QA
+mission, observe real channel behavior, and record what worked, failed, or
+stayed blocked.
+
+For faster QA Lab UI iteration without rebuilding the Docker image each time,
+start the stack with a bind-mounted QA Lab bundle:
+
+```bash
+pnpm openclaw qa docker-build-image
+pnpm qa:lab:build
+pnpm qa:lab:up:fast
+pnpm qa:lab:watch
+```
+
+`qa:lab:up:fast` keeps the Docker services on a prebuilt image and bind-mounts
+`extensions/qa-lab/web/dist` into the `qa-lab` container. `qa:lab:watch`
+rebuilds that bundle on change, and the browser auto-reloads when the QA Lab
+asset hash changes.
 
 ## Repo-backed seeds
 
 Seed assets live in `qa/`:
 
-- `qa/QA_KICKOFF_TASK.md`
-- `qa/seed-scenarios.json`
+- `qa/scenarios.md`
 
 These are intentionally in git so the QA plan is visible to both humans and the
 agent. The baseline list should stay broad enough to cover:

docs/concepts/system-prompt.md

@@ -43,7 +43,7 @@ The prompt is intentionally compact and uses fixed sections:
 - **Sandbox** (when enabled): indicates sandboxed runtime, sandbox paths, and whether elevated exec is available.
 - **Current Date & Time**: user-local time, timezone, and time format.
 - **Reply Tags**: optional reply tag syntax for supported providers.
-- **Heartbeats**: heartbeat prompt and ack behavior.
+- **Heartbeats**: heartbeat prompt and ack behavior, when heartbeats are enabled for the default agent.
 - **Runtime**: host, OS, node, model, repo root (when detected), thinking level (one line).
 - **Reasoning**: current visibility level + /reasoning toggle hint.
 
@@ -103,10 +103,12 @@ Bootstrap files are trimmed and appended under **Project Context** so the model
 - `BOOTSTRAP.md` (only on brand-new workspaces)
 - `MEMORY.md` when present, otherwise `memory.md` as a lowercase fallback
 
-All of these files are **injected into the context window** on every turn, which
-means they consume tokens. Keep them concise — especially `MEMORY.md`, which can
-grow over time and lead to unexpectedly high context usage and more frequent
-compaction.
+All of these files are **injected into the context window** on every turn unless
+a file-specific gate applies. `HEARTBEAT.md` is omitted on normal runs when
+heartbeats are disabled for the default agent or
+`agents.defaults.heartbeat.includeSystemPromptSection` is false. Keep injected
+files concise — especially `MEMORY.md`, which can grow over time and lead to
+unexpectedly high context usage and more frequent compaction.
 
 > **Note:** `memory/*.md` daily files are **not** injected automatically. They
 > are accessed on demand via the `memory_search` and `memory_get` tools, so they

docs/docs.json

@@ -76,6 +76,10 @@
       "source": "/plugins/agent-tools",
       "destination": "/plugins/building-plugins#registering-agent-tools"
     },
+    {
+      "source": "/cli/capability",
+      "destination": "/cli/infer"
+    },
     {
       "source": "/tools/capability-cookbook",
       "destination": "/plugins/architecture"
@@ -1158,6 +1162,7 @@
               {
                 "group": "Tools",
                 "pages": [
+                  "tools/media-overview",
                   "tools/apply-patch",
                   {
                     "group": "Web Browser",
@@ -1230,6 +1235,7 @@
                 "pages": [
                   "providers/alibaba",
                   "providers/anthropic",
+                  "providers/arcee",
                   "providers/bedrock",
                   "providers/bedrock-mantle",
                   "providers/chutes",

docs/gateway/cli-backends.md

@@ -214,8 +214,10 @@ The bundled OpenAI plugin also registers a default for `codex-cli`:
 The bundled Google plugin also registers a default for `google-gemini-cli`:
 
 - `command: "gemini"`
-- `args: ["--prompt", "--output-format", "json"]`
-- `resumeArgs: ["--resume", "{sessionId}", "--prompt", "--output-format", "json"]`
+- `args: ["--output-format", "json", "--prompt", "{prompt}"]`
+- `resumeArgs: ["--resume", "{sessionId}", "--output-format", "json", "--prompt", "{prompt}"]`
+- `imageArg: "@"`
+- `imagePathScope: "workspace"`
 - `modelArg: "--model"`
 - `sessionMode: "existing"`
 - `sessionIdFields: ["session_id", "sessionId"]`
@@ -251,8 +253,9 @@ opt into a generated MCP config overlay with `bundleMcp: true`.
 
 Current bundled behavior:
 
-- `codex-cli`: no bundle MCP overlay
-- `google-gemini-cli`: no bundle MCP overlay
+- `claude-cli`: generated strict MCP config file
+- `codex-cli`: inline config overrides for `mcp_servers`
+- `google-gemini-cli`: generated Gemini system settings file
 
 When bundle MCP is enabled, OpenClaw:
 
@@ -260,8 +263,8 @@ When bundle MCP is enabled, OpenClaw:
 - authenticates the bridge with a per-session token (`OPENCLAW_MCP_TOKEN`)
 - scopes tool access to the current session, account, and channel context
 - loads enabled bundle-MCP servers for the current workspace
-- merges them with any existing backend `--mcp-config`
-- rewrites the CLI args to pass `--strict-mcp-config --mcp-config <generated-file>`
+- merges them with any existing backend MCP config/settings shape
+- rewrites the launch config using the backend-owned integration mode from the owning extension
 
 If no MCP servers are enabled, OpenClaw still injects a strict config when a
 backend opts into bundle MCP so background runs stay isolated.

docs/gateway/configuration-reference.md

@@ -1160,6 +1160,7 @@ Periodic heartbeat runs.
     defaults: {
       compaction: {
         mode: "safeguard", // default | safeguard
+        provider: "my-provider", // id of a registered compaction provider plugin (optional)
         timeoutSeconds: 900,
         reserveTokensFloor: 24000,
         identifierPolicy: "strict", // strict | off | custom
@@ -1180,6 +1181,7 @@ Periodic heartbeat runs.
 ```
 
 - `mode`: `default` or `safeguard` (chunked summarization for long histories). See [Compaction](/concepts/compaction).
+- `provider`: id of a registered compaction provider plugin. When set, the provider's `summarize()` is called instead of built-in LLM summarization. Falls back to built-in on failure. Setting a provider forces `mode: "safeguard"`. See [Compaction](/concepts/compaction).
 - `timeoutSeconds`: maximum seconds allowed for a single compaction operation before OpenClaw aborts it. Default: `900`.
 - `identifierPolicy`: `strict` (default), `off`, or `custom`. `strict` prepends built-in opaque identifier retention guidance during compaction summarization.
 - `identifierInstructions`: optional custom identifier-preservation text used when `identifierPolicy=custom`.
@@ -2349,6 +2351,7 @@ OpenClaw uses the built-in model catalog. Add custom providers via `models.provi
 - `models.providers.*.models.*.contextWindow`: native model context window metadata.
 - `models.providers.*.models.*.contextTokens`: optional runtime context cap. Use this when you want a smaller effective context budget than the model's native `contextWindow`.
 - `models.providers.*.models.*.compat.supportsDeveloperRole`: optional compatibility hint. For `api: "openai-completions"` with a non-empty non-native `baseUrl` (host not `api.openai.com`), OpenClaw forces this to `false` at runtime. Empty/omitted `baseUrl` keeps default OpenAI behavior.
+- `models.providers.*.models.*.compat.requiresStringContent`: optional compatibility hint for string-only OpenAI-compatible chat endpoints. When `true`, OpenClaw flattens pure text `messages[].content` arrays into plain strings before sending the request.
 - `plugins.entries.amazon-bedrock.config.discovery`: Bedrock auto-discovery settings root.
 - `plugins.entries.amazon-bedrock.config.discovery.enabled`: turn implicit discovery on/off.
 - `plugins.entries.amazon-bedrock.config.discovery.region`: AWS region for discovery.

docs/gateway/doctor.md

@@ -66,6 +66,7 @@ cat ~/.openclaw/openclaw.json
 - Talk config migration from legacy flat `talk.*` fields into `talk.provider` + `talk.providers.<provider>`.
 - Browser migration checks for legacy Chrome extension configs and Chrome MCP readiness.
 - OpenCode provider override warnings (`models.providers.opencode` / `models.providers.opencode-go`).
+- Codex OAuth shadowing warnings (`models.providers.openai-codex`).
 - OAuth TLS prerequisites check for OpenAI Codex OAuth profiles.
 - Legacy on-disk state migration (sessions/agent dir/WhatsApp auth).
 - Legacy plugin manifest contract key migration (`speechProviders`, `realtimeTranscriptionProviders`, `realtimeVoiceProviders`, `mediaUnderstandingProviders`, `imageGenerationProviders`, `videoGenerationProviders`, `webFetchProviders`, `webSearchProviders` → `contracts`).
@@ -212,6 +213,16 @@ doctor prints platform-specific fix guidance. On macOS with a Homebrew Node, the
 fix is usually `brew postinstall ca-certificates`. With `--deep`, the probe runs
 even if the gateway is healthy.
 
+### 2c) Codex OAuth provider overrides
+
+If you previously added legacy OpenAI transport settings under
+`models.providers.openai-codex`, they can shadow the built-in Codex OAuth
+provider path that newer releases use automatically. Doctor warns when it sees
+those old transport settings alongside Codex OAuth so you can remove or rewrite
+the stale transport override and get the built-in routing/fallback behavior
+back. Custom proxies and header-only overrides are still supported and do not
+trigger this warning.
+
 ### 3) Legacy state migrations (disk layout)
 
 Doctor can migrate older on-disk layouts into the current structure:

docs/gateway/heartbeat.md

@@ -54,7 +54,10 @@ Example config:
 - Prompt body (configurable via `agents.defaults.heartbeat.prompt`):
   `Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not infer or repeat old tasks from prior chats. If nothing needs attention, reply HEARTBEAT_OK.`
 - The heartbeat prompt is sent **verbatim** as the user message. The system
-  prompt includes a “Heartbeat” section and the run is flagged internally.
+  prompt includes a “Heartbeat” section only when heartbeats are enabled for the
+  default agent, and the run is flagged internally.
+- When heartbeats are disabled with `0m`, normal runs also omit `HEARTBEAT.md`
+  from bootstrap context so the model does not see heartbeat-only instructions.
 - Active hours (`heartbeat.activeHours`) are checked in the configured timezone.
   Outside the window, heartbeats are skipped until the next tick inside the window.
 
@@ -330,6 +333,11 @@ If a `HEARTBEAT.md` file exists in the workspace, the default prompt tells the
 agent to read it. Think of it as your “heartbeat checklist”: small, stable, and
 safe to include every 30 minutes.
 
+On normal runs, `HEARTBEAT.md` is only injected when heartbeat guidance is
+enabled for the default agent. Disabling the heartbeat cadence with `0m` or
+setting `includeSystemPromptSection: false` omits it from normal bootstrap
+context.
+
 If `HEARTBEAT.md` exists but is effectively empty (only blank lines and markdown
 headers like `# Heading`), OpenClaw skips the heartbeat run to save API calls.
 That skip is reported as `reason=empty-heartbeat-file`.

docs/gateway/local-models.md

@@ -155,9 +155,30 @@ Behavior note for local/proxied `/v1` backends:
 - hidden OpenClaw attribution headers (`originator`, `version`, `User-Agent`)
   are not injected on these custom proxy URLs
 
+Compatibility notes for stricter OpenAI-compatible backends:
+
+- Some servers accept only string `messages[].content` on Chat Completions, not
+  structured content-part arrays. Set
+  `models.providers.<provider>.models[].compat.requiresStringContent: true` for
+  those endpoints.
+- Some smaller or stricter local backends are unstable with OpenClaw's full
+  agent-runtime prompt shape, especially when tool schemas are included. If the
+  backend works for tiny direct `/v1/chat/completions` calls but fails on normal
+  OpenClaw agent turns, try
+  `models.providers.<provider>.models[].compat.supportsTools: false` first.
+- If the backend still fails only on larger OpenClaw runs, the remaining issue
+  is usually upstream model/server capacity or a backend bug, not OpenClaw's
+  transport layer.
+
 ## Troubleshooting
 
 - Gateway can reach the proxy? `curl http://127.0.0.1:1234/v1/models`.
 - LM Studio model unloaded? Reload; cold start is a common “hanging” cause.
 - Context errors? Lower `contextWindow` or raise your server limit.
+- OpenAI-compatible server returns `messages[].content ... expected a string`?
+  Add `compat.requiresStringContent: true` on that model entry.
+- Direct tiny `/v1/chat/completions` calls work, but `openclaw infer model run`
+  fails on Gemma or another local model? Disable tool schemas first with
+  `compat.supportsTools: false`, then retest. If the server still crashes only
+  on larger OpenClaw prompts, treat it as an upstream server/model limitation.
 - Safety: local models skip provider-side filters; keep agents narrow and compaction on to limit prompt injection blast radius.

docs/gateway/protocol.md

@@ -381,16 +381,18 @@ implemented in `src/gateway/server-methods/*.ts`.
 
 #### Approval families
 
-- `exec.approval.request` and `exec.approval.resolve` cover one-shot exec
-  approval requests.
+- `exec.approval.request`, `exec.approval.get`, `exec.approval.list`, and
+  `exec.approval.resolve` cover one-shot exec approval requests plus pending
+  approval lookup/replay.
 - `exec.approval.waitDecision` waits on one pending exec approval and returns
   the final decision (or `null` on timeout).
 - `exec.approvals.get` and `exec.approvals.set` manage gateway exec approval
   policy snapshots.
 - `exec.approvals.node.get` and `exec.approvals.node.set` manage node-local exec
   approval policy via node relay commands.
-- `plugin.approval.request`, `plugin.approval.waitDecision`, and
-  `plugin.approval.resolve` cover plugin-defined approval flows.
+- `plugin.approval.request`, `plugin.approval.list`,
+  `plugin.approval.waitDecision`, and `plugin.approval.resolve` cover
+  plugin-defined approval flows.
 
 #### Other major families
 

docs/gateway/troubleshooting.md

@@ -59,6 +59,61 @@ Related:
 - [/reference/token-use](/reference/token-use)
 - [/help/faq#why-am-i-seeing-http-429-ratelimiterror-from-anthropic](/help/faq#why-am-i-seeing-http-429-ratelimiterror-from-anthropic)
 
+## Local OpenAI-compatible backend passes direct probes but agent runs fail
+
+Use this when:
+
+- `curl ... /v1/models` works
+- tiny direct `/v1/chat/completions` calls work
+- OpenClaw model runs fail only on normal agent turns
+
+```bash
+curl http://127.0.0.1:1234/v1/models
+curl http://127.0.0.1:1234/v1/chat/completions \
+  -H 'content-type: application/json' \
+  -d '{"model":"<id>","messages":[{"role":"user","content":"hi"}],"stream":false}'
+openclaw infer model run --model <provider/model> --prompt "hi" --json
+openclaw logs --follow
+```
+
+Look for:
+
+- direct tiny calls succeed, but OpenClaw runs fail only on larger prompts
+- backend errors about `messages[].content` expecting a string
+- backend crashes that appear only with larger prompt-token counts or full agent
+  runtime prompts
+
+Common signatures:
+
+- `messages[...].content: invalid type: sequence, expected a string` → backend
+  rejects structured Chat Completions content parts. Fix: set
+  `models.providers.<provider>.models[].compat.requiresStringContent: true`.
+- direct tiny requests succeed, but OpenClaw agent runs fail with backend/model
+  crashes (for example Gemma on some `inferrs` builds) → OpenClaw transport is
+  likely already correct; the backend is failing on the larger agent-runtime
+  prompt shape.
+- failures shrink after disabling tools but do not disappear → tool schemas were
+  part of the pressure, but the remaining issue is still upstream model/server
+  capacity or a backend bug.
+
+Fix options:
+
+1. Set `compat.requiresStringContent: true` for string-only Chat Completions backends.
+2. Set `compat.supportsTools: false` for models/backends that cannot handle
+   OpenClaw's tool schema surface reliably.
+3. Lower prompt pressure where possible: smaller workspace bootstrap, shorter
+   session history, lighter local model, or a backend with stronger long-context
+   support.
+4. If tiny direct requests keep passing while OpenClaw agent turns still crash
+   inside the backend, treat it as an upstream server/model limitation and file
+   a repro there with the accepted payload shape.
+
+Related:
+
+- [/gateway/local-models](/gateway/local-models)
+- [/gateway/configuration#models](/gateway/configuration#models)
+- [/gateway/configuration-reference#openai-compatible-endpoints](/gateway/configuration-reference#openai-compatible-endpoints)
+
 ## No replies
 
 If channels are up but nothing answers, check routing and policy before reconnecting anything.

docs/help/faq.md

@@ -657,6 +657,31 @@ for usage/billing and raise limits as needed.
     OpenClaw supports **OpenAI Code (Codex)** via OAuth (ChatGPT sign-in). Onboarding can run the OAuth flow and will set the default model to `openai-codex/gpt-5.4` when appropriate. See [Model providers](/concepts/model-providers) and [Onboarding (CLI)](/start/wizard).
   </Accordion>
 
+  <Accordion title="Why does ChatGPT GPT-5.4 not unlock openai/gpt-5.4 in OpenClaw?">
+    OpenClaw treats the two routes separately:
+
+    - `openai-codex/gpt-5.4` = ChatGPT/Codex OAuth
+    - `openai/gpt-5.4` = direct OpenAI Platform API
+
+    In OpenClaw, ChatGPT/Codex sign-in is wired to the `openai-codex/*` route,
+    not the direct `openai/*` route. If you want the direct API path in
+    OpenClaw, set `OPENAI_API_KEY` (or the equivalent OpenAI provider config).
+    If you want ChatGPT/Codex sign-in in OpenClaw, use `openai-codex/*`.
+
+  </Accordion>
+
+  <Accordion title="Why can Codex OAuth limits differ from ChatGPT web?">
+    `openai-codex/*` uses the Codex OAuth route, and its usable quota windows are
+    OpenAI-managed and plan-dependent. In practice, those limits can differ from
+    the ChatGPT website/app experience, even when both are tied to the same account.
+
+    OpenClaw can show the currently visible provider usage/quota windows in
+    `openclaw models status`, but it does not invent or normalize ChatGPT-web
+    entitlements into direct API access. If you want the direct OpenAI Platform
+    billing/limit path, use `openai/*` with an API key.
+
+  </Accordion>
+
   <Accordion title="Do you support OpenAI subscription auth (Codex OAuth)?">
     Yes. OpenClaw fully supports **OpenAI Code (Codex) subscription OAuth**.
     OpenAI explicitly allows subscription OAuth usage in external tools/workflows
@@ -676,7 +701,7 @@ for usage/billing and raise limits as needed.
        - npm: `npm install -g @google/gemini-cli`
     2. Enable the plugin: `openclaw plugins enable google`
     3. Login: `openclaw models auth login --provider google-gemini-cli --set-default`
-    4. Default model after login: `google-gemini-cli/gemini-3.1-pro-preview`
+    4. Default model after login: `google-gemini-cli/gemini-3-flash-preview`
     5. If requests fail, set `GOOGLE_CLOUD_PROJECT` or `GOOGLE_CLOUD_PROJECT_ID` on the gateway host
 
     This stores OAuth tokens in auth profiles on the gateway host. Details: [Model providers](/concepts/model-providers).
@@ -1791,8 +1816,8 @@ for usage/billing and raise limits as needed.
 
     - `config.schema.lookup`: inspect one config subtree with its shallow schema node, matched UI hint, and immediate child summaries before writing
     - `config.get`: fetch the current snapshot + hash
-    - `config.patch`: safe partial update (preferred for most RPC edits)
-    - `config.apply`: validate + replace the full config, then restart
+    - `config.patch`: safe partial update (preferred for most RPC edits); hot-reloads when possible and restarts when required
+    - `config.apply`: validate + replace the full config; hot-reloads when possible and restarts when required
     - The owner-only `gateway` runtime tool still refuses to rewrite `tools.exec.ask` / `tools.exec.security`; legacy `tools.bash.*` aliases normalize to the same protected exec paths
 
   </Accordion>
@@ -2229,7 +2254,7 @@ for usage/billing and raise limits as needed.
     Quickest setup:
 
     1. Install Ollama from `https://ollama.com/download`
-    2. Pull a local model such as `ollama pull glm-4.7-flash`
+    2. Pull a local model such as `ollama pull gemma4`
     3. If you want cloud models too, run `ollama signin`
     4. Run `openclaw onboard` and choose `Ollama`
     5. Pick `Local` or `Cloud + Local`

docs/help/scripts.md

@@ -21,6 +21,32 @@ Use these when a task is clearly tied to a script; otherwise prefer the CLI.
 
 Auth monitoring is covered in [Authentication](/gateway/authentication). The scripts under `scripts/` are optional extras for systemd/Termux phone workflows.
 
+## GitHub read helper
+
+Use `scripts/gh-read` when you want `gh` to use a GitHub App installation token for repo-scoped read calls while leaving normal `gh` on your personal login for write actions.
+
+Required env:
+
+- `OPENCLAW_GH_READ_APP_ID`
+- `OPENCLAW_GH_READ_PRIVATE_KEY_FILE`
+
+Optional env:
+
+- `OPENCLAW_GH_READ_INSTALLATION_ID` when you want to skip repo-based installation lookup
+- `OPENCLAW_GH_READ_PERMISSIONS` as a comma-separated override for the read permission subset to request
+
+Repo resolution order:
+
+- `gh ... -R owner/repo`
+- `GH_REPO`
+- `git remote origin`
+
+Examples:
+
+- `scripts/gh-read pr view 123`
+- `scripts/gh-read run list -R openclaw/openclaw`
+- `scripts/gh-read api repos/openclaw/openclaw/pulls/123`
+
 ## When adding scripts
 
 - Keep scripts focused and documented.

docs/help/testing.md

@@ -26,6 +26,7 @@ Most days:
 - Faster local full-suite run on a roomy machine: `pnpm test:max`
 - Direct Vitest watch loop: `pnpm test:watch`
 - Direct file targeting now routes extension/channel paths too: `pnpm test extensions/discord/src/monitor/message-handler.preflight.test.ts`
+- Docker-backed QA site: `pnpm qa:lab:up`
 
 When you touch tests or want extra confidence:
 
@@ -46,7 +47,7 @@ Think of the suites as “increasing realism” (and increasing flakiness/cost):
 ### Unit / integration (default)
 
 - Command: `pnpm test`
-- Config: native Vitest `projects` via `vitest.config.ts`
+- Config: ten sequential shard runs (`vitest.full-*.config.ts`) over the existing scoped Vitest projects
 - Files: core/unit inventories under `src/**/*.test.ts`, `packages/**/*.test.ts`, `test/**/*.test.ts`, and the whitelisted `ui` node tests covered by `vitest.unit.config.ts`
 - Scope:
   - Pure unit tests
@@ -57,9 +58,13 @@ Think of the suites as “increasing realism” (and increasing flakiness/cost):
   - No real keys required
   - Should be fast and stable
 - Projects note:
-  - Untargeted `pnpm test` still uses the native Vitest root `projects` config.
+  - Untargeted `pnpm test` now runs eleven smaller shard configs (`core-unit-src`, `core-unit-security`, `core-unit-ui`, `core-unit-support`, `core-support-boundary`, `core-contracts`, `core-bundled`, `core-runtime`, `agentic`, `auto-reply`, `extensions`) instead of one giant native root-project process. This cuts peak RSS on loaded machines and avoids auto-reply/extension work starving unrelated suites.
+  - `pnpm test --watch` still uses the native root `vitest.config.ts` project graph, because a multi-shard watch loop is not practical.
   - `pnpm test`, `pnpm test:watch`, and `pnpm test:perf:imports` route explicit file/directory targets through scoped lanes first, so `pnpm test extensions/discord/src/monitor/message-handler.preflight.test.ts` avoids paying the full root project startup tax.
   - `pnpm test:changed` expands changed git paths into the same scoped lanes when the diff only touches routable source/test files; config/setup edits still fall back to the broad root-project rerun.
+  - Selected `plugin-sdk` and `commands` tests also route through dedicated light lanes that skip `test/setup-openclaw-runtime.ts`; stateful/runtime-heavy files stay on the existing lanes.
+  - Selected `plugin-sdk` and `commands` helper source files also map changed-mode runs to explicit sibling tests in those light lanes, so helper edits avoid rerunning the full heavy suite for that directory.
+  - `auto-reply` now has three dedicated buckets: top-level core helpers, top-level `reply.*` integration tests, and the `src/auto-reply/reply/**` subtree. This keeps the heaviest reply harness work off the cheap status/chunk/token tests.
 - Embedded runner note:
   - When you change message-tool discovery inputs or compaction runtime context,
     keep both levels of coverage.
@@ -75,7 +80,7 @@ Think of the suites as “increasing realism” (and increasing flakiness/cost):
   - Base Vitest config now defaults to `threads`.
   - The shared Vitest config also fixes `isolate: false` and uses the non-isolated runner across the root projects, e2e, and live configs.
   - The root UI lane keeps its `jsdom` setup and optimizer, but now runs on the shared non-isolated runner too.
-  - `pnpm test` inherits the same `threads` + `isolate: false` defaults from the root `vitest.config.ts` projects config.
+  - Each `pnpm test` shard inherits the same `threads` + `isolate: false` defaults from the shared Vitest config.
   - The shared `scripts/run-vitest.mjs` launcher now also adds `--no-maglev` for Vitest child Node processes by default to reduce V8 compile churn during big local runs. Set `OPENCLAW_VITEST_ENABLE_MAGLEV=1` if you need to compare against stock V8 behavior.
 - Fast-local iteration note:
   - `pnpm test:changed` routes through scoped lanes when the changed paths map cleanly to a smaller suite.
@@ -86,6 +91,8 @@ Think of the suites as “increasing realism” (and increasing flakiness/cost):
 - Perf-debug note:
   - `pnpm test:perf:imports` enables Vitest import-duration reporting plus import-breakdown output.
   - `pnpm test:perf:imports:changed` scopes the same profiling view to files changed since `origin/main`.
+- `pnpm test:perf:changed:bench -- --ref <git-ref>` compares routed `test:changed` against the native root-project path for that committed diff and prints wall time plus macOS max RSS.
+- `pnpm test:perf:changed:bench -- --worktree` benchmarks the current dirty tree by routing the changed file list through `scripts/test-projects.mjs` and the root Vitest config.
   - `pnpm test:perf:profile:main` writes a main-thread CPU profile for Vitest/Vite startup and transform overhead.
   - `pnpm test:perf:profile:runner` writes runner CPU+heap profiles for the unit suite with file parallelism disabled.
 
@@ -246,17 +253,17 @@ openclaw models list
 openclaw models list --json
 ```
 
-## Live: CLI backend smoke (Codex CLI or other local CLIs)
+## Live: CLI backend smoke (Claude, Codex, Gemini, or other local CLIs)
 
 - Test: `src/gateway/gateway-cli-backend.live.test.ts`
 - Goal: validate the Gateway + agent pipeline using a local CLI backend, without touching your default config.
+- Backend-specific smoke defaults live with the owning extension's `cli-backend.ts` definition.
 - Enable:
   - `pnpm test:live` (or `OPENCLAW_LIVE_TEST=1` if invoking Vitest directly)
   - `OPENCLAW_LIVE_CLI_BACKEND=1`
 - Defaults:
-  - Model: `codex-cli/gpt-5.4`
-  - Command: `codex`
-  - Args: `["exec","--json","--color","never","--sandbox","read-only","--skip-git-repo-check"]`
+  - Default provider/model: `claude-cli/claude-sonnet-4-6`
+  - Command/args/image behavior come from the owning CLI backend plugin metadata.
 - Overrides (optional):
   - `OPENCLAW_LIVE_CLI_BACKEND_MODEL="codex-cli/gpt-5.4"`
   - `OPENCLAW_LIVE_CLI_BACKEND_COMMAND="/full/path/to/codex"`
@@ -265,6 +272,7 @@ openclaw models list --json
   - `OPENCLAW_LIVE_CLI_BACKEND_IMAGE_ARG="--image"` to pass image file paths as CLI args instead of prompt injection.
   - `OPENCLAW_LIVE_CLI_BACKEND_IMAGE_MODE="repeat"` (or `"list"`) to control how image args are passed when `IMAGE_ARG` is set.
   - `OPENCLAW_LIVE_CLI_BACKEND_RESUME_PROBE=1` to send a second turn and validate resume flow.
+  - `OPENCLAW_LIVE_CLI_BACKEND_MODEL_SWITCH_PROBE=0` to disable the default Claude Sonnet -> Opus same-session continuity probe (set to `1` to force it on when the selected model supports a switch target).
 
 Example:
 
@@ -280,11 +288,21 @@ Docker recipe:
 pnpm test:docker:live-cli-backend
 ```
 
+Single-provider Docker recipes:
+
+```bash
+pnpm test:docker:live-cli-backend:claude
+pnpm test:docker:live-cli-backend:codex
+pnpm test:docker:live-cli-backend:gemini
+```
+
 Notes:
 
 - The Docker runner lives at `scripts/test-live-cli-backend-docker.sh`.
 - It runs the live CLI-backend smoke inside the repo Docker image as the non-root `node` user.
-- For `codex-cli`, it installs the Linux `@openai/codex` package into a cached writable prefix at `OPENCLAW_DOCKER_CLI_TOOLS_DIR` (default: `~/.cache/openclaw/docker-cli-tools`).
+- It resolves CLI smoke metadata from the owning extension, then installs the matching Linux CLI package (`@anthropic-ai/claude-code`, `@openai/codex`, or `@google/gemini-cli`) into a cached writable prefix at `OPENCLAW_DOCKER_CLI_TOOLS_DIR` (default: `~/.cache/openclaw/docker-cli-tools`).
+- The live CLI-backend smoke now exercises the same end-to-end flow for Claude, Codex, and Gemini: text turn, image classification turn, then MCP `cron` tool call verified through the gateway CLI.
+- Claude's default smoke also patches the session from Sonnet to Opus and verifies the resumed session still remembers an earlier note.
 
 ## Live: ACP bind smoke (`/acp spawn ... --bind here`)
 
@@ -298,12 +316,15 @@ Notes:
   - `pnpm test:live src/gateway/gateway-acp-bind.live.test.ts`
   - `OPENCLAW_LIVE_ACP_BIND=1`
 - Defaults:
-  - ACP agent: `claude`
+  - ACP agents in Docker: `claude,codex,gemini`
+  - ACP agent for direct `pnpm test:live ...`: `claude`
   - Synthetic channel: Slack DM-style conversation context
   - ACP backend: `acpx`
 - Overrides:
   - `OPENCLAW_LIVE_ACP_BIND_AGENT=claude`
   - `OPENCLAW_LIVE_ACP_BIND_AGENT=codex`
+  - `OPENCLAW_LIVE_ACP_BIND_AGENT=gemini`
+  - `OPENCLAW_LIVE_ACP_BIND_AGENTS=claude,codex,gemini`
   - `OPENCLAW_LIVE_ACP_BIND_AGENT_COMMAND='npx -y @agentclientprotocol/claude-agent-acp@<version>'`
 - Notes:
   - This lane uses the gateway `chat.send` surface with admin-only synthetic originating-route fields so tests can attach message-channel context without pretending to deliver externally.
@@ -323,10 +344,20 @@ Docker recipe:
 pnpm test:docker:live-acp-bind
 ```
 
+Single-agent Docker recipes:
+
+```bash
+pnpm test:docker:live-acp-bind:claude
+pnpm test:docker:live-acp-bind:codex
+pnpm test:docker:live-acp-bind:gemini
+```
+
 Docker notes:
 
 - The Docker runner lives at `scripts/test-live-acp-bind-docker.sh`.
-- It sources `~/.profile`, stages the matching CLI auth material into the container, installs `acpx` into a writable npm prefix, then installs the requested live CLI (`@anthropic-ai/claude-code` or `@openai/codex`) if missing.
+- By default, it runs the ACP bind smoke against all supported live CLI agents in sequence: `claude`, `codex`, then `gemini`.
+- Use `OPENCLAW_LIVE_ACP_BIND_AGENTS=claude`, `OPENCLAW_LIVE_ACP_BIND_AGENTS=codex`, or `OPENCLAW_LIVE_ACP_BIND_AGENTS=gemini` to narrow the matrix.
+- It sources `~/.profile`, stages the matching CLI auth material into the container, installs `acpx` into a writable npm prefix, then installs the requested live CLI (`@anthropic-ai/claude-code`, `@openai/codex`, or `@google/gemini-cli`) if missing.
 - Inside Docker, the runner sets `OPENCLAW_LIVE_ACP_BIND_ACPX_COMMAND=$HOME/.npm-global/bin/acpx` so acpx keeps provider env vars from the sourced profile available to the child harness CLI.
 
 ### Recommended live recipes
@@ -419,7 +450,7 @@ Live tests discover credentials the same way the CLI does. Practical implication
 - Per-agent auth profiles: `~/.openclaw/agents/<agentId>/agent/auth-profiles.json` (this is what “profile keys” means in the live tests)
 - Config: `~/.openclaw/openclaw.json` (or `OPENCLAW_CONFIG_PATH`)
 - Legacy state dir: `~/.openclaw/credentials/` (copied into the staged live home when present, but not the main profile-key store)
-- Live local runs copy the active config, per-agent `auth-profiles.json` files, legacy `credentials/`, and supported external CLI auth dirs into a temp test home by default; `agents.*.workspace` / `agentDir` path overrides are stripped in that staged config so probes stay off your real host workspace.
+- Live local runs copy the active config, per-agent `auth-profiles.json` files, legacy `credentials/`, and supported external CLI auth dirs into a temp test home by default; staged live homes skip `workspace/` and `sandboxes/`, and `agents.*.workspace` / `agentDir` path overrides are stripped so probes stay off your real host workspace.
 
 If you want to rely on env keys (e.g. exported in your `~/.profile`), run local tests after `source ~/.profile`, or use the Docker runners below (they can mount `~/.profile` into the container).
 
@@ -447,6 +478,7 @@ If you want to rely on env keys (e.g. exported in your `~/.profile`), run local
 
 - Test: `src/image-generation/runtime.live.test.ts`
 - Command: `pnpm test:live src/image-generation/runtime.live.test.ts`
+- Harness: `pnpm test:live:media image`
 - Scope:
   - Enumerates every registered image-generation provider plugin
   - Loads missing provider env vars from your login shell (`~/.profile`) before probing
@@ -471,6 +503,7 @@ If you want to rely on env keys (e.g. exported in your `~/.profile`), run local
 
 - Test: `extensions/music-generation-providers.live.test.ts`
 - Enable: `OPENCLAW_LIVE_TEST=1 pnpm test:live -- extensions/music-generation-providers.live.test.ts`
+- Harness: `pnpm test:live:media music`
 - Scope:
   - Exercises the shared bundled music-generation provider path
   - Currently covers Google and MiniMax
@@ -494,6 +527,7 @@ If you want to rely on env keys (e.g. exported in your `~/.profile`), run local
 
 - Test: `extensions/video-generation-providers.live.test.ts`
 - Enable: `OPENCLAW_LIVE_TEST=1 pnpm test:live -- extensions/video-generation-providers.live.test.ts`
+- Harness: `pnpm test:live:media video`
 - Scope:
   - Exercises the shared bundled video-generation provider path
   - Loads provider env vars from your login shell (`~/.profile`) before probing
@@ -501,20 +535,39 @@ If you want to rely on env keys (e.g. exported in your `~/.profile`), run local
   - Skips providers with no usable auth/profile/model
   - Runs both declared runtime modes when available:
     - `generate` with prompt-only input
-    - `imageToVideo` when the provider declares `capabilities.imageToVideo.enabled`
+    - `imageToVideo` when the provider declares `capabilities.imageToVideo.enabled` and the selected provider/model accepts buffer-backed local image input in the shared sweep
     - `videoToVideo` when the provider declares `capabilities.videoToVideo.enabled` and the selected provider/model accepts buffer-backed local video input in the shared sweep
+  - Current declared-but-skipped `imageToVideo` providers in the shared sweep:
+    - `vydra` because bundled `veo3` is text-only and bundled `kling` requires a remote image URL
+  - Provider-specific Vydra coverage:
+    - `OPENCLAW_LIVE_TEST=1 OPENCLAW_LIVE_VYDRA_VIDEO=1 pnpm test:live -- extensions/vydra/vydra.live.test.ts`
+    - that file runs `veo3` text-to-video plus a `kling` lane that uses a remote image URL fixture by default
   - Current `videoToVideo` live coverage:
-    - `google`
-    - `openai`
     - `runway` only when the selected model is `runway/gen4_aleph`
   - Current declared-but-skipped `videoToVideo` providers in the shared sweep:
     - `alibaba`, `qwen`, `xai` because those paths currently require remote `http(s)` / MP4 reference URLs
+    - `google` because the current shared Gemini/Veo lane uses local buffer-backed input and that path is not accepted in the shared sweep
+    - `openai` because the current shared lane lacks org-specific video inpaint/remix access guarantees
 - Optional narrowing:
   - `OPENCLAW_LIVE_VIDEO_GENERATION_PROVIDERS="google,openai,runway"`
   - `OPENCLAW_LIVE_VIDEO_GENERATION_MODELS="google/veo-3.1-fast-generate-preview,openai/sora-2,runway/gen4_aleph"`
 - Optional auth behavior:
   - `OPENCLAW_LIVE_REQUIRE_PROFILE_KEYS=1` to force profile-store auth and ignore env-only overrides
 
+## Media live harness
+
+- Command: `pnpm test:live:media`
+- Purpose:
+  - Runs the shared image, music, and video live suites through one repo-native entrypoint
+  - Auto-loads missing provider env vars from `~/.profile`
+  - Auto-narrows each suite to providers that currently have usable auth by default
+  - Reuses `scripts/test-live.mjs`, so heartbeat and quiet-mode behavior stay consistent
+- Examples:
+  - `pnpm test:live:media`
+  - `pnpm test:live:media image video --providers openai,google,minimax`
+  - `pnpm test:live:media video --video-providers openai,runway --all-providers`
+  - `pnpm test:live:media music --quiet`
+
 ## Docker runners (optional "works in Linux" checks)
 
 These Docker runners split into two buckets:

docs/help/troubleshooting.md

@@ -42,6 +42,21 @@ If you see:
 `HTTP 429: rate_limit_error: Extra usage is required for long context requests`,
 go to [/gateway/troubleshooting#anthropic-429-extra-usage-required-for-long-context](/gateway/troubleshooting#anthropic-429-extra-usage-required-for-long-context).
 
+## Local OpenAI-compatible backend works directly but fails in OpenClaw
+
+If your local or self-hosted `/v1` backend answers small direct
+`/v1/chat/completions` probes but fails on `openclaw infer model run` or normal
+agent turns:
+
+1. If the error mentions `messages[].content` expecting a string, set
+   `models.providers.<provider>.models[].compat.requiresStringContent: true`.
+2. If the backend still fails only on OpenClaw agent turns, set
+   `models.providers.<provider>.models[].compat.supportsTools: false` and retry.
+3. If tiny direct calls still work but larger OpenClaw prompts crash the
+   backend, treat the remaining issue as an upstream model/server limitation and
+   continue in the deep runbook:
+   [/gateway/troubleshooting#local-openai-compatible-backend-passes-direct-probes-but-agent-runs-fail](/gateway/troubleshooting#local-openai-compatible-backend-passes-direct-probes-but-agent-runs-fail)
+
 ## Plugin install fails with missing openclaw extensions
 
 If install fails with `package.json missing openclaw.extensions`, the plugin package

docs/plans/2026-04-05-002-refactor-real-plugin-sdk-workspace-plan.md

@@ -1,5 +1,5 @@
 ---
-title: refactor: Make plugin-sdk a real workspace package incrementally
+title: "refactor: Make plugin-sdk a real workspace package incrementally"
 type: refactor
 status: active
 date: 2026-04-05

docs/platforms/ios.md

@@ -161,6 +161,22 @@ export OPENCLAW_APNS_KEY_ID="KEYID"
 export OPENCLAW_APNS_PRIVATE_KEY_P8="$(cat /path/to/AuthKey_KEYID.p8)"
 ```
 
+These are gateway-host runtime env vars, not Fastlane settings. `apps/ios/fastlane/.env` only stores
+App Store Connect / TestFlight auth such as `ASC_KEY_ID` and `ASC_ISSUER_ID`; it does not configure
+direct APNs delivery for local iOS builds.
+
+Recommended gateway-host storage:
+
+```bash
+mkdir -p ~/.openclaw/credentials/apns
+chmod 700 ~/.openclaw/credentials/apns
+mv /path/to/AuthKey_KEYID.p8 ~/.openclaw/credentials/apns/AuthKey_KEYID.p8
+chmod 600 ~/.openclaw/credentials/apns/AuthKey_KEYID.p8
+export OPENCLAW_APNS_PRIVATE_KEY_PATH="$HOME/.openclaw/credentials/apns/AuthKey_KEYID.p8"
+```
+
+Do not commit the `.p8` file or place it under the repo checkout.
+
 ## Discovery paths
 
 ### Bonjour (LAN)

docs/plugins/architecture.md

@@ -609,8 +609,9 @@ conversation, and it runs after core approval handling finishes.
 
 Provider plugins now have two layers:
 
-- manifest metadata: `providerAuthEnvVars` for cheap env-auth lookup before
-  runtime load, plus `providerAuthChoices` for cheap onboarding/auth-choice
+- manifest metadata: `providerAuthEnvVars` for cheap provider env-auth lookup
+  before runtime load, `channelEnvVars` for cheap channel env/setup lookup
+  before runtime load, plus `providerAuthChoices` for cheap onboarding/auth-choice
   labels and CLI flag metadata before runtime load
 - config-time hooks: `catalog` / legacy `discovery` plus `applyConfigDefaults`
 - runtime hooks: `normalizeModelId`, `normalizeTransport`,
@@ -645,6 +646,10 @@ one-flag auth wiring without loading provider runtime. Keep provider runtime
 `envVars` for operator-facing hints such as onboarding labels or OAuth
 client-id/client-secret setup vars.
 
+Use manifest `channelEnvVars` when a channel has env-driven auth or setup that
+generic shell-env fallback, config/status checks, or setup prompts should see
+without loading channel runtime.
+
 ### Hook order and usage
 
 For model/provider plugins, OpenClaw calls hooks in this rough order.
@@ -1115,7 +1120,8 @@ authoring plugins:
   `openclaw/plugin-sdk/secret-input`, and
   `openclaw/plugin-sdk/webhook-ingress` for shared setup/auth/reply/webhook
   wiring. `channel-inbound` is the shared home for debounce, mention matching,
-  envelope formatting, and inbound envelope context helpers.
+  inbound mention-policy helpers, envelope formatting, and inbound envelope
+  context helpers.
   `channel-setup` is the narrow optional-install setup seam.
   `setup-runtime` is the runtime-safe setup surface used by `setupEntry` /
   deferred startup, including the import-safe setup patch adapters.
@@ -1128,6 +1134,9 @@ authoring plugins:
   `openclaw/plugin-sdk/channel-config-schema`,
   `openclaw/plugin-sdk/telegram-command-config`,
   `openclaw/plugin-sdk/channel-policy`,
+  `openclaw/plugin-sdk/approval-gateway-runtime`,
+  `openclaw/plugin-sdk/approval-handler-adapter-runtime`,
+  `openclaw/plugin-sdk/approval-handler-runtime`,
   `openclaw/plugin-sdk/approval-runtime`,
   `openclaw/plugin-sdk/config-runtime`,
   `openclaw/plugin-sdk/infra-runtime`,
@@ -1146,9 +1155,9 @@ authoring plugins:
   assistant-visible-text stripping, markdown render/chunking helpers, redaction
   helpers, directive-tag helpers, and safe-text utilities.
 - Approval-specific channel seams should prefer one `approvalCapability`
-  contract on the plugin. Core then reads approval auth, delivery, render, and
-  native-routing behavior through that one capability instead of mixing
-  approval behavior into unrelated plugin fields.
+  contract on the plugin. Core then reads approval auth, delivery, render,
+  native-routing, and lazy native-handler behavior through that one capability
+  instead of mixing approval behavior into unrelated plugin fields.
 - `openclaw/plugin-sdk/channel-runtime` is deprecated and remains only as a
   compatibility shim for older plugins. New code should import the narrower
   generic primitives instead, and repo code should not add new imports of the
@@ -1488,14 +1497,23 @@ Use this when your plugin needs to replace or extend the default context
 pipeline rather than just add memory search or hooks.
 
 ```ts
+import { buildMemorySystemPromptAddition } from "openclaw/plugin-sdk/core";
+
 export default function (api) {
   api.registerContextEngine("lossless-claw", () => ({
     info: { id: "lossless-claw", name: "Lossless Claw", ownsCompaction: true },
     async ingest() {
       return { ingested: true };
     },
-    async assemble({ messages }) {
-      return { messages, estimatedTokens: 0 };
+    async assemble({ messages, availableTools, citationsMode }) {
+      return {
+        messages,
+        estimatedTokens: 0,
+        systemPromptAddition: buildMemorySystemPromptAddition({
+          availableTools: availableTools ?? new Set(),
+          citationsMode,
+        }),
+      };
     },
     async compact() {
       return { ok: true, compacted: false };
@@ -1508,7 +1526,10 @@ If your engine does **not** own the compaction algorithm, keep `compact()`
 implemented and delegate it explicitly:
 
 ```ts
-import { delegateCompactionToRuntime } from "openclaw/plugin-sdk/core";
+import {
+  buildMemorySystemPromptAddition,
+  delegateCompactionToRuntime,
+} from "openclaw/plugin-sdk/core";
 
 export default function (api) {
   api.registerContextEngine("my-memory-engine", () => ({
@@ -1520,8 +1541,15 @@ export default function (api) {
     async ingest() {
       return { ingested: true };
     },
-    async assemble({ messages }) {
-      return { messages, estimatedTokens: 0 };
+    async assemble({ messages, availableTools, citationsMode }) {
+      return {
+        messages,
+        estimatedTokens: 0,
+        systemPromptAddition: buildMemorySystemPromptAddition({
+          availableTools: availableTools ?? new Set(),
+          citationsMode,
+        }),
+      };
     },
     async compact(params) {
       return await delegateCompactionToRuntime(params);

docs/plugins/manifest.md

@@ -93,6 +93,9 @@ Those belong in your plugin code and `package.json`.
   "providerAuthEnvVars": {
     "openrouter": ["OPENROUTER_API_KEY"]
   },
+  "channelEnvVars": {
+    "openrouter-chatops": ["OPENROUTER_CHATOPS_TOKEN"]
+  },
   "providerAuthChoices": [
     {
       "provider": "openrouter",
@@ -142,6 +145,7 @@ Those belong in your plugin code and `package.json`.
 | `modelSupport`                      | No       | `object`                         | Manifest-owned shorthand model-family metadata used to auto-load the plugin before runtime.                                                                                                                  |
 | `cliBackends`                       | No       | `string[]`                       | CLI inference backend ids owned by this plugin. Used for startup auto-activation from explicit config refs.                                                                                                  |
 | `providerAuthEnvVars`               | No       | `Record<string, string[]>`       | Cheap provider-auth env metadata that OpenClaw can inspect without loading plugin code.                                                                                                                      |
+| `channelEnvVars`                    | No       | `Record<string, string[]>`       | Cheap channel env metadata that OpenClaw can inspect without loading plugin code. Use this for env-driven channel setup or auth surfaces that generic startup/config helpers should see.                     |
 | `providerAuthChoices`               | No       | `object[]`                       | Cheap auth-choice metadata for onboarding pickers, preferred-provider resolution, and simple CLI flag wiring.                                                                                                |
 | `contracts`                         | No       | `object`                         | Static bundled capability snapshot for speech, realtime transcription, realtime voice, media-understanding, image-generation, music-generation, video-generation, web-fetch, web search, and tool ownership. |
 | `channelConfigs`                    | No       | `Record<string, object>`         | Manifest-owned channel config metadata merged into discovery and validation surfaces before runtime loads.                                                                                                   |
@@ -436,6 +440,9 @@ See [Configuration reference](/gateway/configuration) for the full `plugins.*` s
 - `providerAuthEnvVars` is the cheap metadata path for auth probes, env-marker
   validation, and similar provider-auth surfaces that should not boot plugin
   runtime just to inspect env names.
+- `channelEnvVars` is the cheap metadata path for shell-env fallback, setup
+  prompts, and similar channel surfaces that should not boot plugin runtime
+  just to inspect env names.
 - `providerAuthChoices` is the cheap metadata path for auth-choice pickers,
   `--auth-choice` resolution, preferred-provider mapping, and simple onboarding
   CLI flag registration before provider runtime loads. For runtime wizard

docs/plugins/sdk-channel-plugins.md

@@ -60,22 +60,34 @@ Most channel plugins do not need approval-specific code.
 
 - Core owns same-chat `/approve`, shared approval button payloads, and generic fallback delivery.
 - Prefer one `approvalCapability` object on the channel plugin when the channel needs approval-specific behavior.
+- `ChannelPlugin.approvals` is removed. Put approval delivery/native/render/auth facts on `approvalCapability`.
+- `plugin.auth` is login/logout only; core no longer reads approval auth hooks from that object.
 - `approvalCapability.authorizeActorAction` and `approvalCapability.getActionAvailabilityState` are the canonical approval-auth seam.
-- If your channel exposes native exec approvals, implement `approvalCapability.getActionAvailabilityState` even when the native transport lives entirely under `approvalCapability.native`. Core uses that availability hook to distinguish `enabled` vs `disabled`, decide whether the initiating channel supports native approvals, and include the channel in native-client fallback guidance.
+- Use `approvalCapability.getActionAvailabilityState` for same-chat approval auth availability.
+- If your channel exposes native exec approvals, use `approvalCapability.getExecInitiatingSurfaceState` for the initiating-surface/native-client state when it differs from same-chat approval auth. Core uses that exec-specific hook to distinguish `enabled` vs `disabled`, decide whether the initiating channel supports native exec approvals, and include the channel in native-client fallback guidance. `createApproverRestrictedNativeApprovalCapability(...)` fills this in for the common case.
 - Use `outbound.shouldSuppressLocalPayloadPrompt` or `outbound.beforeDeliverPayload` for channel-specific payload lifecycle behavior such as hiding duplicate local approval prompts or sending typing indicators before delivery.
 - Use `approvalCapability.delivery` only for native approval routing or fallback suppression.
+- Use `approvalCapability.nativeRuntime` for channel-owned native approval facts. Keep it lazy on hot channel entrypoints with `createLazyChannelApprovalNativeRuntimeAdapter(...)`, which can import your runtime module on demand while still letting core assemble the approval lifecycle.
 - Use `approvalCapability.render` only when a channel truly needs custom approval payloads instead of the shared renderer.
 - Use `approvalCapability.describeExecApprovalSetup` when the channel wants the disabled-path reply to explain the exact config knobs needed to enable native exec approvals. The hook receives `{ channel, channelLabel, accountId }`; named-account channels should render account-scoped paths such as `channels.<channel>.accounts.<id>.execApprovals.*` instead of top-level defaults.
 - If a channel can infer stable owner-like DM identities from existing config, use `createResolvedApproverActionAuthAdapter` from `openclaw/plugin-sdk/approval-runtime` to restrict same-chat `/approve` without adding approval-specific core logic.
-- If a channel needs native approval delivery, keep channel code focused on target normalization and transport hooks. Use `createChannelExecApprovalProfile`, `createChannelNativeOriginTargetResolver`, `createChannelApproverDmTargetResolver`, `createApproverRestrictedNativeApprovalCapability`, and `createChannelNativeApprovalRuntime` from `openclaw/plugin-sdk/approval-runtime` so core owns request filtering, routing, dedupe, expiry, and gateway subscription.
+- If a channel needs native approval delivery, keep channel code focused on target normalization plus transport/presentation facts. Use `createChannelExecApprovalProfile`, `createChannelNativeOriginTargetResolver`, `createChannelApproverDmTargetResolver`, and `createApproverRestrictedNativeApprovalCapability` from `openclaw/plugin-sdk/approval-runtime`. Put the channel-specific facts behind `approvalCapability.nativeRuntime`, ideally via `createChannelApprovalNativeRuntimeAdapter(...)` or `createLazyChannelApprovalNativeRuntimeAdapter(...)`, so core can assemble the handler and own request filtering, routing, dedupe, expiry, gateway subscription, and routed-elsewhere notices. `nativeRuntime` is split into a few smaller seams:
+- `availability` — whether the account is configured and whether a request should be handled
+- `presentation` — map the shared approval view model into pending/resolved/expired native payloads or final actions
+- `transport` — prepare targets plus send/update/delete native approval messages
+- `interactions` — optional bind/unbind/clear-action hooks for native buttons or reactions
+- `observe` — optional delivery diagnostics hooks
+- If the channel needs runtime-owned objects such as a client, token, Bolt app, or webhook receiver, register them through `openclaw/plugin-sdk/channel-runtime-context`. The generic runtime-context registry lets core bootstrap capability-driven handlers from channel startup state without adding approval-specific wrapper glue.
+- Reach for the lower-level `createChannelApprovalHandler` or `createChannelNativeApprovalRuntime` only when the capability-driven seam is not expressive enough yet.
 - Native approval channels must route both `accountId` and `approvalKind` through those helpers. `accountId` keeps multi-account approval policy scoped to the right bot account, and `approvalKind` keeps exec vs plugin approval behavior available to the channel without hardcoded branches in core.
+- Core now owns approval reroute notices too. Channel plugins should not send their own "approval went to DMs / another channel" follow-up messages from `createChannelNativeApprovalRuntime`; instead, expose accurate origin + approver-DM routing through the shared approval capability helpers and let core aggregate actual deliveries before posting any notice back to the initiating chat.
 - Preserve the delivered approval id kind end-to-end. Native clients should not
   guess or rewrite exec vs plugin approval routing from channel-local state.
 - Different approval kinds can intentionally expose different native surfaces.
   Current bundled examples:
   - Slack keeps native approval routing available for both exec and plugin ids.
-  - Matrix keeps native DM/channel routing for exec approvals only and leaves
-    plugin approvals on the shared same-chat `/approve` path.
+  - Matrix keeps the same native DM/channel routing and reaction UX for exec
+    and plugin approvals, while still letting auth differ by approval kind.
 - `createApproverRestrictedNativeApprovalAdapter` still exists as a compatibility wrapper, but new code should prefer the capability builder and expose `approvalCapability` on the plugin.
 
 For hot channel entrypoints, prefer the narrower runtime subpaths when you only
@@ -84,8 +96,12 @@ need one part of that family:
 - `openclaw/plugin-sdk/approval-auth-runtime`
 - `openclaw/plugin-sdk/approval-client-runtime`
 - `openclaw/plugin-sdk/approval-delivery-runtime`
+- `openclaw/plugin-sdk/approval-gateway-runtime`
+- `openclaw/plugin-sdk/approval-handler-adapter-runtime`
+- `openclaw/plugin-sdk/approval-handler-runtime`
 - `openclaw/plugin-sdk/approval-native-runtime`
 - `openclaw/plugin-sdk/approval-reply-runtime`
+- `openclaw/plugin-sdk/channel-runtime-context`
 
 Likewise, prefer `openclaw/plugin-sdk/setup-runtime`,
 `openclaw/plugin-sdk/setup-adapter-runtime`,
@@ -108,9 +124,15 @@ For setup specifically:
 - `openclaw/plugin-sdk/channel-setup` covers the optional-install setup
   builders plus a few setup-safe primitives:
   `createOptionalChannelSetupSurface`, `createOptionalChannelSetupAdapter`,
-  `createOptionalChannelSetupWizard`, `DEFAULT_ACCOUNT_ID`,
-  `createTopLevelChannelDmPolicy`, `setSetupChannelEnabled`, and
-  `splitSetupEntries`
+
+If your channel supports env-driven setup or auth and generic startup/config
+flows should know those env names before runtime loads, declare them in the
+plugin manifest with `channelEnvVars`. Keep channel runtime `envVars` or local
+constants for operator-facing copy only.
+`createOptionalChannelSetupWizard`, `DEFAULT_ACCOUNT_ID`,
+`createTopLevelChannelDmPolicy`, `setSetupChannelEnabled`, and
+`splitSetupEntries`
+
 - use the broader `openclaw/plugin-sdk/setup` seam only when you also need the
   heavier shared setup/config helpers such as
   `moveSingleAccountChannelSectionToDefaultAccount(...)`
@@ -146,6 +168,87 @@ surfaces:
 
 Auth-only channels can usually stop at the default path: core handles approvals and the plugin just exposes outbound/auth capabilities. Native approval channels such as Matrix, Slack, Telegram, and custom chat transports should use the shared native helpers instead of rolling their own approval lifecycle.
 
+## Inbound mention policy
+
+Keep inbound mention handling split in two layers:
+
+- plugin-owned evidence gathering
+- shared policy evaluation
+
+Use `openclaw/plugin-sdk/channel-inbound` for the shared layer.
+
+Good fit for plugin-local logic:
+
+- reply-to-bot detection
+- quoted-bot detection
+- thread-participation checks
+- service/system-message exclusions
+- platform-native caches needed to prove bot participation
+
+Good fit for the shared helper:
+
+- `requireMention`
+- explicit mention result
+- implicit mention allowlist
+- command bypass
+- final skip decision
+
+Preferred flow:
+
+1. Compute local mention facts.
+2. Pass those facts into `resolveInboundMentionDecision({ facts, policy })`.
+3. Use `decision.effectiveWasMentioned`, `decision.shouldBypassMention`, and `decision.shouldSkip` in your inbound gate.
+
+```typescript
+import {
+  implicitMentionKindWhen,
+  matchesMentionWithExplicit,
+  resolveInboundMentionDecision,
+} from "openclaw/plugin-sdk/channel-inbound";
+
+const mentionMatch = matchesMentionWithExplicit(text, {
+  mentionRegexes,
+  mentionPatterns,
+});
+
+const facts = {
+  canDetectMention: true,
+  wasMentioned: mentionMatch.matched,
+  hasAnyMention: mentionMatch.hasExplicitMention,
+  implicitMentionKinds: [
+    ...implicitMentionKindWhen("reply_to_bot", isReplyToBot),
+    ...implicitMentionKindWhen("quoted_bot", isQuoteOfBot),
+  ],
+};
+
+const decision = resolveInboundMentionDecision({
+  facts,
+  policy: {
+    isGroup,
+    requireMention,
+    allowedImplicitMentionKinds: requireExplicitMention ? [] : ["reply_to_bot", "quoted_bot"],
+    allowTextCommands,
+    hasControlCommand,
+    commandAuthorized,
+  },
+});
+
+if (decision.shouldSkip) return;
+```
+
+`api.runtime.channel.mentions` exposes the same shared mention helpers for
+bundled channel plugins that already depend on runtime injection:
+
+- `buildMentionRegexes`
+- `matchesMentionPatterns`
+- `matchesMentionWithExplicit`
+- `implicitMentionKindWhen`
+- `resolveInboundMentionDecision`
+
+The older `resolveMentionGating*` helpers remain on
+`openclaw/plugin-sdk/channel-inbound` as compatibility exports only. New code
+should use `resolveInboundMentionDecision({ facts, policy })`.
+
 ## Walkthrough
 
 <Steps>

docs/plugins/sdk-migration.md

@@ -67,6 +67,32 @@ Current bundled provider examples:
 ## How to migrate
 
 <Steps>
+  <Step title="Migrate approval-native handlers to capability facts">
+    Approval-capable channel plugins now expose native approval behavior through
+    `approvalCapability.nativeRuntime` plus the shared runtime-context registry.
+
+    Key changes:
+
+    - Replace `approvalCapability.handler.loadRuntime(...)` with
+      `approvalCapability.nativeRuntime`
+    - Move approval-specific auth/delivery off legacy `plugin.auth` /
+      `plugin.approvals` wiring and onto `approvalCapability`
+    - `ChannelPlugin.approvals` has been removed from the public channel-plugin
+      contract; move delivery/native/render fields onto `approvalCapability`
+    - `plugin.auth` remains for channel login/logout flows only; approval auth
+      hooks there are no longer read by core
+    - Register channel-owned runtime objects such as clients, tokens, or Bolt
+      apps through `openclaw/plugin-sdk/channel-runtime-context`
+    - Do not send plugin-owned reroute notices from native approval handlers;
+      core now owns routed-elsewhere notices from actual delivery results
+    - When passing `channelRuntime` into `createChannelManager(...)`, provide a
+      real `createPluginRuntime().channel` surface. Partial stubs are rejected.
+
+    See `/plugins/sdk-channel-plugins` for the current approval capability
+    layout.
+
+  </Step>
+
   <Step title="Audit Windows wrapper fallback behavior">
     If your plugin uses `openclaw/plugin-sdk/windows-spawn`, unresolved Windows
     `.cmd`/`.bat` wrappers now fail closed unless you explicitly pass
@@ -201,8 +227,12 @@ Current bundled provider examples:
   | `plugin-sdk/approval-auth-runtime` | Approval auth helpers | Approver resolution, same-chat action auth |
   | `plugin-sdk/approval-client-runtime` | Approval client helpers | Native exec approval profile/filter helpers |
   | `plugin-sdk/approval-delivery-runtime` | Approval delivery helpers | Native approval capability/delivery adapters |
+  | `plugin-sdk/approval-gateway-runtime` | Approval gateway helpers | Shared approval gateway-resolution helper |
+  | `plugin-sdk/approval-handler-adapter-runtime` | Approval adapter helpers | Lightweight native approval adapter loading helpers for hot channel entrypoints |
+  | `plugin-sdk/approval-handler-runtime` | Approval handler helpers | Broader approval handler runtime helpers; prefer the narrower adapter/gateway seams when they are enough |
   | `plugin-sdk/approval-native-runtime` | Approval target helpers | Native approval target/account binding helpers |
   | `plugin-sdk/approval-reply-runtime` | Approval reply helpers | Exec/plugin approval reply payload helpers |
+  | `plugin-sdk/channel-runtime-context` | Channel runtime-context helpers | Generic channel runtime-context register/get/watch helpers |
   | `plugin-sdk/security-runtime` | Security helpers | Shared trust, DM gating, external-content, and secret-collection helpers |
   | `plugin-sdk/ssrf-policy` | SSRF policy helpers | Host allowlist and private-network policy helpers |
   | `plugin-sdk/ssrf-runtime` | SSRF runtime helpers | Pinned-dispatcher, guarded fetch, SSRF policy helpers |
@@ -249,7 +279,8 @@ Current bundled provider examples:
   | `plugin-sdk/provider-onboard` | Provider onboarding patches | Onboarding config helpers |
   | `plugin-sdk/provider-http` | Provider HTTP helpers | Generic provider HTTP/endpoint capability helpers |
   | `plugin-sdk/provider-web-fetch` | Provider web-fetch helpers | Web-fetch provider registration/cache helpers |
-  | `plugin-sdk/provider-web-search` | Provider web-search helpers | Web-search provider registration/cache/config helpers |
+  | `plugin-sdk/provider-web-search-contract` | Provider web-search contract helpers | Narrow web-search config/credential contract helpers such as `enablePluginInConfig`, `resolveProviderWebSearchPluginConfig`, and scoped credential setters/getters |
+  | `plugin-sdk/provider-web-search` | Provider web-search helpers | Web-search provider registration/cache/runtime helpers |
   | `plugin-sdk/provider-tools` | Provider tool/schema compat helpers | `ProviderToolCompatFamily`, `buildProviderToolCompatFamilyHooks`, Gemini schema cleanup + diagnostics, and xAI compat helpers such as `resolveXaiModelCompatPatch` / `applyXaiModelCompat` |
   | `plugin-sdk/provider-usage` | Provider usage helpers | `fetchClaudeUsage`, `fetchGeminiUsage`, `fetchGithubCopilotUsage`, and other provider usage helpers |
   | `plugin-sdk/provider-stream` | Provider stream wrapper helpers | `ProviderStreamFamily`, `buildProviderStreamFamilyHooks`, `composeProviderStreamWrappers`, stream wrapper types, and shared Anthropic/Bedrock/Google/Kilocode/Moonshot/OpenAI/OpenRouter/Z.A.I/MiniMax/Copilot wrapper helpers |

docs/plugins/sdk-overview.md

@@ -108,12 +108,13 @@ explicitly promotes one as public.
     | `plugin-sdk/group-access` | Shared group-access decision helpers |
     | `plugin-sdk/direct-dm` | Shared direct-DM auth/guard helpers |
     | `plugin-sdk/interactive-runtime` | Interactive reply payload normalization/reduction helpers |
-    | `plugin-sdk/channel-inbound` | Debounce, mention matching, envelope helpers |
+    | `plugin-sdk/channel-inbound` | Inbound debounce, mention matching, mention-policy helpers, and envelope helpers |
     | `plugin-sdk/channel-send-result` | Reply result types |
     | `plugin-sdk/channel-actions` | `createMessageToolButtonsSchema`, `createMessageToolCardSchema` |
     | `plugin-sdk/channel-targets` | Target parsing/matching helpers |
     | `plugin-sdk/channel-contract` | Channel contract types |
     | `plugin-sdk/channel-feedback` | Feedback/reaction wiring |
+    | `plugin-sdk/channel-secret-runtime` | Narrow secret-contract helpers such as `collectSimpleChannelFieldAssignments`, `getChannelSurface`, `pushAssignment`, and secret target types |
   </Accordion>
 
   <Accordion title="Provider subpaths">
@@ -132,8 +133,10 @@ explicitly promotes one as public.
     | `plugin-sdk/provider-model-shared` | `ProviderReplayFamily`, `buildProviderReplayFamilyHooks`, `normalizeModelCompat`, shared replay-policy builders, provider-endpoint helpers, and model-id normalization helpers such as `normalizeNativeXaiModelId` |
     | `plugin-sdk/provider-catalog-shared` | `findCatalogTemplate`, `buildSingleProviderApiKeyCatalog`, `supportsNativeStreamingUsageCompat`, `applyProviderNativeStreamingUsageCompat` |
     | `plugin-sdk/provider-http` | Generic provider HTTP/endpoint capability helpers |
+    | `plugin-sdk/provider-web-fetch-contract` | Narrow web-fetch config/selection contract helpers such as `enablePluginInConfig` and `WebFetchProviderPlugin` |
     | `plugin-sdk/provider-web-fetch` | Web-fetch provider registration/cache helpers |
-    | `plugin-sdk/provider-web-search` | Web-search provider registration/cache/config helpers |
+    | `plugin-sdk/provider-web-search-contract` | Narrow web-search config/credential contract helpers such as `enablePluginInConfig`, `resolveProviderWebSearchPluginConfig`, and scoped credential setters/getters |
+    | `plugin-sdk/provider-web-search` | Web-search provider registration/cache/runtime helpers |
     | `plugin-sdk/provider-tools` | `ProviderToolCompatFamily`, `buildProviderToolCompatFamilyHooks`, Gemini schema cleanup + diagnostics, and xAI compat helpers such as `resolveXaiModelCompatPatch` / `applyXaiModelCompat` |
     | `plugin-sdk/provider-usage` | `fetchClaudeUsage` and similar |
     | `plugin-sdk/provider-stream` | `ProviderStreamFamily`, `buildProviderStreamFamilyHooks`, `composeProviderStreamWrappers`, stream wrapper types, and shared Anthropic/Bedrock/Google/Kilocode/Moonshot/OpenAI/OpenRouter/Z.A.I/MiniMax/Copilot wrapper helpers |
@@ -148,12 +151,17 @@ explicitly promotes one as public.
     | `plugin-sdk/approval-auth-runtime` | Approver resolution and same-chat action-auth helpers |
     | `plugin-sdk/approval-client-runtime` | Native exec approval profile/filter helpers |
     | `plugin-sdk/approval-delivery-runtime` | Native approval capability/delivery adapters |
+    | `plugin-sdk/approval-gateway-runtime` | Shared approval gateway-resolution helper |
+    | `plugin-sdk/approval-handler-adapter-runtime` | Lightweight native approval adapter loading helpers for hot channel entrypoints |
+    | `plugin-sdk/approval-handler-runtime` | Broader approval handler runtime helpers; prefer the narrower adapter/gateway seams when they are enough |
     | `plugin-sdk/approval-native-runtime` | Native approval target + account-binding helpers |
     | `plugin-sdk/approval-reply-runtime` | Exec/plugin approval reply payload helpers |
     | `plugin-sdk/command-auth-native` | Native command auth + native session-target helpers |
     | `plugin-sdk/command-detection` | Shared command detection helpers |
     | `plugin-sdk/command-surface` | Command-body normalization and command-surface helpers |
     | `plugin-sdk/allow-from` | `formatAllowFromLowercase` |
+    | `plugin-sdk/channel-secret-runtime` | Narrow secret-contract collection helpers for channel/plugin secret surfaces |
+    | `plugin-sdk/secret-ref-runtime` | Narrow `coerceSecretRef` and SecretRef typing helpers for secret-contract/config parsing |
     | `plugin-sdk/security-runtime` | Shared trust, DM gating, external-content, and secret-collection helpers |
     | `plugin-sdk/ssrf-policy` | Host allowlist and private-network SSRF policy helpers |
     | `plugin-sdk/ssrf-runtime` | Pinned-dispatcher, SSRF-guarded fetch, and SSRF policy helpers |
@@ -167,6 +175,7 @@ explicitly promotes one as public.
     | --- | --- |
     | `plugin-sdk/runtime` | Broad runtime/logging/backup/plugin-install helpers |
     | `plugin-sdk/runtime-env` | Narrow runtime env, logger, timeout, retry, and backoff helpers |
+    | `plugin-sdk/channel-runtime-context` | Generic channel runtime-context registration and lookup helpers |
     | `plugin-sdk/runtime-store` | `createPluginRuntimeStore` |
     | `plugin-sdk/plugin-runtime` | Shared plugin command/hook/http/interactive helpers |
     | `plugin-sdk/hook-runtime` | Shared webhook/internal hook pipeline helpers |
@@ -381,6 +390,7 @@ AI CLI backend such as `codex-cli`.
 | Method                                     | What it registers                     |
 | ------------------------------------------ | ------------------------------------- |
 | `api.registerContextEngine(id, factory)`   | Context engine (one active at a time) |
+| `api.registerMemoryCapability(capability)` | Unified memory capability             |
 | `api.registerMemoryPromptSection(builder)` | Memory prompt section builder         |
 | `api.registerMemoryFlushPlan(resolver)`    | Memory flush plan resolver            |
 | `api.registerMemoryRuntime(runtime)`       | Memory runtime adapter                |
@@ -391,8 +401,13 @@ AI CLI backend such as `codex-cli`.
 | ---------------------------------------------- | ---------------------------------------------- |
 | `api.registerMemoryEmbeddingProvider(adapter)` | Memory embedding adapter for the active plugin |
 
+- `registerMemoryCapability` is the preferred exclusive memory-plugin API.
+- `registerMemoryCapability` may also expose `publicArtifacts.listArtifacts(...)`
+  so companion plugins can consume exported memory artifacts through
+  `openclaw/plugin-sdk/memory-host-core` instead of reaching into a specific
+  memory plugin's private layout.
 - `registerMemoryPromptSection`, `registerMemoryFlushPlan`, and
-  `registerMemoryRuntime` are exclusive to memory plugins.
+  `registerMemoryRuntime` are legacy-compatible exclusive memory-plugin APIs.
 - `registerMemoryEmbeddingProvider` lets the active memory plugin register one
   or more embedding adapter ids (for example `openai`, `gemini`, or a custom
   plugin-defined id).

docs/plugins/sdk-runtime.md

@@ -330,6 +330,46 @@ api.runtime.tools.registerMemoryCli(/* ... */);
 
 Channel-specific runtime helpers (available when a channel plugin is loaded).
 
+`api.runtime.channel.mentions` is the shared inbound mention-policy surface for
+bundled channel plugins that use runtime injection:
+
+```typescript
+const mentionMatch = api.runtime.channel.mentions.matchesMentionWithExplicit(text, {
+  mentionRegexes,
+  mentionPatterns,
+});
+
+const decision = api.runtime.channel.mentions.resolveInboundMentionDecision({
+  facts: {
+    canDetectMention: true,
+    wasMentioned: mentionMatch.matched,
+    implicitMentionKinds: api.runtime.channel.mentions.implicitMentionKindWhen(
+      "reply_to_bot",
+      isReplyToBot,
+    ),
+  },
+  policy: {
+    isGroup,
+    requireMention,
+    allowTextCommands,
+    hasControlCommand,
+    commandAuthorized,
+  },
+});
+```
+
+Available mention helpers:
+
+- `buildMentionRegexes`
+- `matchesMentionPatterns`
+- `matchesMentionWithExplicit`
+- `implicitMentionKindWhen`
+- `resolveInboundMentionDecision`
+
+`api.runtime.channel.mentions` intentionally does not expose the older
+`resolveMentionGating*` compatibility helpers. Prefer the normalized
+`{ facts, policy }` path.
+
 ## Storing runtime references
 
 Use `createPluginRuntimeStore` to store the runtime reference for use outside

docs/providers/arcee.md

@@ -0,0 +1,87 @@
+---
+title: "Arcee AI"
+summary: "Arcee AI setup (auth + model selection)"
+read_when:
+  - You want to use Arcee AI with OpenClaw
+  - You need the API key env var or CLI auth choice
+---
+
+# Arcee AI
+
+[Arcee AI](https://arcee.ai) provides access to the Trinity family of mixture-of-experts models through an OpenAI-compatible API. All Trinity models are Apache 2.0 licensed.
+
+Arcee AI models can be accessed directly via the Arcee platform or through [OpenRouter](/providers/openrouter).
+
+- Provider: `arcee`
+- Auth: `ARCEEAI_API_KEY` (direct) or `OPENROUTER_API_KEY` (via OpenRouter)
+- API: OpenAI-compatible
+- Base URL: `https://api.arcee.ai/api/v1` (direct) or `https://openrouter.ai/api/v1` (OpenRouter)
+
+## Quick start
+
+1. Get an API key from [Arcee AI](https://chat.arcee.ai/) or [OpenRouter](https://openrouter.ai/keys).
+
+2. Set the API key (recommended: store it for the Gateway):
+
+```bash
+# Direct (Arcee platform)
+openclaw onboard --auth-choice arceeai-api-key
+
+# Via OpenRouter
+openclaw onboard --auth-choice arceeai-openrouter
+```
+
+3. Set a default model:
+
+```json5
+{
+  agents: {
+    defaults: {
+      model: { primary: "arcee/trinity-large-thinking" },
+    },
+  },
+}
+```
+
+## Non-interactive example
+
+```bash
+# Direct (Arcee platform)
+openclaw onboard --non-interactive \
+  --mode local \
+  --auth-choice arceeai-api-key \
+  --arceeai-api-key "$ARCEEAI_API_KEY"
+
+# Via OpenRouter
+openclaw onboard --non-interactive \
+  --mode local \
+  --auth-choice arceeai-openrouter \
+  --openrouter-api-key "$OPENROUTER_API_KEY"
+```
+
+## Environment note
+
+If the Gateway runs as a daemon (launchd/systemd), make sure `ARCEEAI_API_KEY`
+(or `OPENROUTER_API_KEY`) is available to that process (for example, in
+`~/.openclaw/.env` or via `env.shellEnv`).
+
+## Built-in catalog
+
+OpenClaw currently ships this bundled Arcee catalog:
+
+| Model ref                      | Name                   | Input | Context | Cost (in/out per 1M) | Notes                                     |
+| ------------------------------ | ---------------------- | ----- | ------- | -------------------- | ----------------------------------------- |
+| `arcee/trinity-large-thinking` | Trinity Large Thinking | text  | 256K    | $0.25 / $0.90        | Default model; reasoning enabled          |
+| `arcee/trinity-large-preview`  | Trinity Large Preview  | text  | 128K    | $0.25 / $1.00        | General-purpose; 400B params, 13B active  |
+| `arcee/trinity-mini`           | Trinity Mini 26B       | text  | 128K    | $0.045 / $0.15       | Fast and cost-efficient; function calling |
+
+The same model refs work for both direct and OpenRouter setups (for example `arcee/trinity-large-thinking`).
+
+The onboarding preset sets `arcee/trinity-large-thinking` as the default model.
+
+## Supported features
+
+- Streaming
+- Tool use / function calling
+- Structured output (JSON mode and JSON schema)
+- Extended thinking (Trinity Large Thinking)

docs/providers/google.md

@@ -52,7 +52,7 @@ An alternative provider `google-gemini-cli` uses PKCE OAuth instead of an API
 key. This is an unofficial integration; some users report account
 restrictions. Use at your own risk.
 
-- Default model: `google-gemini-cli/gemini-3.1-pro-preview`
+- Default model: `google-gemini-cli/gemini-3-flash-preview`
 - Alias: `gemini-cli`
 - Install prerequisite: local Gemini CLI available as `gemini`
   - Homebrew: `brew install gemini-cli`

docs/providers/index.md

@@ -29,6 +29,7 @@ Looking for chat channel docs (WhatsApp/Telegram/Discord/Slack/Mattermost (plugi
 - [Alibaba Model Studio](/providers/alibaba)
 - [Amazon Bedrock](/providers/bedrock)
 - [Anthropic (API + Claude CLI)](/providers/anthropic)
+- [Arcee AI (Trinity models)](/providers/arcee)
 - [BytePlus (International)](/concepts/model-providers#byteplus-international)
 - [Chutes](/providers/chutes)
 - [ComfyUI](/providers/comfy)
@@ -41,6 +42,7 @@ Looking for chat channel docs (WhatsApp/Telegram/Discord/Slack/Mattermost (plugi
 - [Google (Gemini)](/providers/google)
 - [Groq (LPU inference)](/providers/groq)
 - [Hugging Face (Inference)](/providers/huggingface)
+- [inferrs (local models)](/providers/inferrs)
 - [Kilocode](/providers/kilocode)
 - [LiteLLM (unified gateway)](/providers/litellm)
 - [MiniMax](/providers/minimax)

docs/providers/inferrs.md

@@ -0,0 +1,173 @@
+---
+summary: "Run OpenClaw through inferrs (OpenAI-compatible local server)"
+read_when:
+  - You want to run OpenClaw against a local inferrs server
+  - You are serving Gemma or another model through inferrs
+  - You need the exact OpenClaw compat flags for inferrs
+title: "inferrs"
+---
+
+# inferrs
+
+[inferrs](https://github.com/ericcurtin/inferrs) can serve local models behind an
+OpenAI-compatible `/v1` API. OpenClaw works with `inferrs` through the generic
+`openai-completions` path.
+
+`inferrs` is currently best treated as a custom self-hosted OpenAI-compatible
+backend, not a dedicated OpenClaw provider plugin.
+
+## Quick start
+
+1. Start `inferrs` with a model.
+
+Example:
+
+```bash
+inferrs serve gg-hf-gg/gemma-4-E2B-it \
+  --host 127.0.0.1 \
+  --port 8080 \
+  --device metal
+```
+
+2. Verify the server is reachable.
+
+```bash
+curl http://127.0.0.1:8080/health
+curl http://127.0.0.1:8080/v1/models
+```
+
+3. Add an explicit OpenClaw provider entry and point your default model at it.
+
+## Full config example
+
+This example uses Gemma 4 on a local `inferrs` server.
+
+```json5
+{
+  agents: {
+    defaults: {
+      model: { primary: "inferrs/gg-hf-gg/gemma-4-E2B-it" },
+      models: {
+        "inferrs/gg-hf-gg/gemma-4-E2B-it": {
+          alias: "Gemma 4 (inferrs)",
+        },
+      },
+    },
+  },
+  models: {
+    mode: "merge",
+    providers: {
+      inferrs: {
+        baseUrl: "http://127.0.0.1:8080/v1",
+        apiKey: "inferrs-local",
+        api: "openai-completions",
+        models: [
+          {
+            id: "gg-hf-gg/gemma-4-E2B-it",
+            name: "Gemma 4 E2B (inferrs)",
+            reasoning: false,
+            input: ["text"],
+            cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+            contextWindow: 131072,
+            maxTokens: 4096,
+            compat: {
+              requiresStringContent: true,
+            },
+          },
+        ],
+      },
+    },
+  },
+}
+```
+
+## Why `requiresStringContent` matters
+
+Some `inferrs` Chat Completions routes accept only string
+`messages[].content`, not structured content-part arrays.
+
+If OpenClaw runs fail with an error like:
+
+```text
+messages[1].content: invalid type: sequence, expected a string
+```
+
+set:
+
+```json5
+compat: {
+  requiresStringContent: true
+}
+```
+
+OpenClaw will flatten pure text content parts into plain strings before sending
+the request.
+
+## Gemma and tool-schema caveat
+
+Some current `inferrs` + Gemma combinations accept small direct
+`/v1/chat/completions` requests but still fail on full OpenClaw agent-runtime
+turns.
+
+If that happens, try this first:
+
+```json5
+compat: {
+  requiresStringContent: true,
+  supportsTools: false
+}
+```
+
+That disables OpenClaw's tool schema surface for the model and can reduce prompt
+pressure on stricter local backends.
+
+If tiny direct requests still work but normal OpenClaw agent turns continue to
+crash inside `inferrs`, the remaining issue is usually upstream model/server
+behavior rather than OpenClaw's transport layer.
+
+## Manual smoke test
+
+Once configured, test both layers:
+
+```bash
+curl http://127.0.0.1:8080/v1/chat/completions \
+  -H 'content-type: application/json' \
+  -d '{"model":"gg-hf-gg/gemma-4-E2B-it","messages":[{"role":"user","content":"What is 2 + 2?"}],"stream":false}'
+
+openclaw infer model run \
+  --model inferrs/gg-hf-gg/gemma-4-E2B-it \
+  --prompt "What is 2 + 2? Reply with one short sentence." \
+  --json
+```
+
+If the first command works but the second fails, use the troubleshooting notes
+below.
+
+## Troubleshooting
+
+- `curl /v1/models` fails: `inferrs` is not running, not reachable, or not
+  bound to the expected host/port.
+- `messages[].content ... expected a string`: set
+  `compat.requiresStringContent: true`.
+- Direct tiny `/v1/chat/completions` calls pass, but `openclaw infer model run`
+  fails: try `compat.supportsTools: false`.
+- OpenClaw no longer gets schema errors, but `inferrs` still crashes on larger
+  agent turns: treat it as an upstream `inferrs` or model limitation and reduce
+  prompt pressure or switch local backend/model.
+
+## Proxy-style behavior
+
+`inferrs` is treated as a proxy-style OpenAI-compatible `/v1` backend, not a
+native OpenAI endpoint.
+
+- native OpenAI-only request shaping does not apply here
+- no `service_tier`, no Responses `store`, no prompt-cache hints, and no
+  OpenAI reasoning-compat payload shaping
+- hidden OpenClaw attribution headers (`originator`, `version`, `User-Agent`)
+  are not injected on custom `inferrs` base URLs
+
+## See also
+
+- [Local models](/gateway/local-models)
+- [Gateway troubleshooting](/gateway/troubleshooting#local-openai-compatible-backend-passes-direct-probes-but-agent-runs-fail)
+- [Model providers](/concepts/model-providers)

docs/providers/mistral.md

@@ -33,15 +33,15 @@ openclaw onboard --mistral-api-key "$MISTRAL_API_KEY"
 
 OpenClaw currently ships this bundled Mistral catalog:
 
-| Model ref                        | Input       | Context | Max output | Notes                    |
-| -------------------------------- | ----------- | ------- | ---------- | ------------------------ |
-| `mistral/mistral-large-latest`   | text, image | 262,144 | 16,384     | Default model            |
-| `mistral/mistral-medium-2508`    | text, image | 262,144 | 8,192      | Mistral Medium 3.1       |
-| `mistral/mistral-small-latest`   | text, image | 128,000 | 16,384     | Smaller multimodal model |
-| `mistral/pixtral-large-latest`   | text, image | 128,000 | 32,768     | Pixtral                  |
-| `mistral/codestral-latest`       | text        | 256,000 | 4,096      | Coding                   |
-| `mistral/devstral-medium-latest` | text        | 262,144 | 32,768     | Devstral 2               |
-| `mistral/magistral-small`        | text        | 128,000 | 40,000     | Reasoning-enabled        |
+| Model ref                        | Input       | Context | Max output | Notes                                                            |
+| -------------------------------- | ----------- | ------- | ---------- | ---------------------------------------------------------------- |
+| `mistral/mistral-large-latest`   | text, image | 262,144 | 16,384     | Default model                                                    |
+| `mistral/mistral-medium-2508`    | text, image | 262,144 | 8,192      | Mistral Medium 3.1                                               |
+| `mistral/mistral-small-latest`   | text, image | 128,000 | 16,384     | Mistral Small 4; adjustable reasoning via API `reasoning_effort` |
+| `mistral/pixtral-large-latest`   | text, image | 128,000 | 32,768     | Pixtral                                                          |
+| `mistral/codestral-latest`       | text        | 256,000 | 4,096      | Coding                                                           |
+| `mistral/devstral-medium-latest` | text        | 262,144 | 32,768     | Devstral 2                                                       |
+| `mistral/magistral-small`        | text        | 128,000 | 40,000     | Reasoning-enabled                                                |
 
 ## Config snippet (audio transcription with Voxtral)
 
@@ -58,6 +58,17 @@ OpenClaw currently ships this bundled Mistral catalog:
 }
 ```
 
+## Adjustable reasoning (`mistral-small-latest`)
+
+`mistral/mistral-small-latest` maps to Mistral Small 4 and supports [adjustable reasoning](https://docs.mistral.ai/capabilities/reasoning/adjustable) on the Chat Completions API via `reasoning_effort` (`none` minimizes extra thinking in the output; `high` surfaces full thinking traces before the final answer).
+
+OpenClaw maps the session **thinking** level to Mistral’s API:
+
+- **off** / **minimal** → `none`
+- **low** / **medium** / **high** / **xhigh** / **adaptive** → `high`
+
+Other bundled Mistral catalog models do not use this parameter; keep using `magistral-*` models when you want Mistral’s native reasoning-first behavior.
+
 ## Notes
 
 - Mistral auth uses `MISTRAL_API_KEY`.

docs/providers/models.md

@@ -54,7 +54,7 @@ model as `provider/model`.
 
 - `anthropic-vertex` - implicit Anthropic on Google Vertex support when Vertex credentials are available; no separate onboarding auth choice
 - `copilot-proxy` - local VS Code Copilot Proxy bridge; use `openclaw onboard --auth-choice copilot-proxy`
-- `google-gemini-cli` - unofficial Gemini CLI OAuth flow; requires a local `gemini` install (`brew install gemini-cli` or `npm install -g @google/gemini-cli`); default model `google-gemini-cli/gemini-3.1-pro-preview`; use `openclaw onboard --auth-choice google-gemini-cli` or `openclaw models auth login --provider google-gemini-cli --set-default`
+- `google-gemini-cli` - unofficial Gemini CLI OAuth flow; requires a local `gemini` install (`brew install gemini-cli` or `npm install -g @google/gemini-cli`); default model `google-gemini-cli/gemini-3-flash-preview`; use `openclaw onboard --auth-choice google-gemini-cli` or `openclaw models auth login --provider google-gemini-cli --set-default`
 
 For the full provider catalog (xAI, Groq, Mistral, etc.) and advanced configuration,
 see [Model providers](/concepts/model-providers).

docs/providers/nvidia.md

@@ -1,14 +1,14 @@
 ---
 summary: "Use NVIDIA's OpenAI-compatible API in OpenClaw"
 read_when:
-  - You want to use NVIDIA models in OpenClaw
+  - You want to use open models in OpenClaw for free
   - You need NVIDIA_API_KEY setup
 title: "NVIDIA"
 ---
 
 # NVIDIA
 
-NVIDIA provides an OpenAI-compatible API at `https://integrate.api.nvidia.com/v1` for Nemotron and NeMo models. Authenticate with an API key from [NVIDIA NGC](https://catalog.ngc.nvidia.com/).
+NVIDIA provides an OpenAI-compatible API at `https://integrate.api.nvidia.com/v1` for open models for free. Authenticate with an API key from [build.nvidia.com](https://build.nvidia.com/settings/api-keys).
 
 ## CLI setup
 
@@ -17,7 +17,7 @@ Export the key once, then run onboarding and set an NVIDIA model:
 ```bash
 export NVIDIA_API_KEY="nvapi-..."
 openclaw onboard --auth-choice skip
-openclaw models set nvidia/nvidia/llama-3.1-nemotron-70b-instruct
+openclaw models set nvidia/nvidia/nemotron-3-super-120b-a12b
 ```
 
 If you still pass `--token`, remember it lands in shell history and `ps` output; prefer the env var when possible.
@@ -37,7 +37,7 @@ If you still pass `--token`, remember it lands in shell history and `ps` output;
   },
   agents: {
     defaults: {
-      model: { primary: "nvidia/nvidia/llama-3.1-nemotron-70b-instruct" },
+      model: { primary: "nvidia/nvidia/nemotron-3-super-120b-a12b" },
     },
   },
 }
@@ -45,14 +45,15 @@ If you still pass `--token`, remember it lands in shell history and `ps` output;
 
 ## Model IDs
 
-| Model ref                                            | Name                                     | Context | Max output |
-| ---------------------------------------------------- | ---------------------------------------- | ------- | ---------- |
-| `nvidia/nvidia/llama-3.1-nemotron-70b-instruct`      | NVIDIA Llama 3.1 Nemotron 70B Instruct   | 131,072 | 4,096      |
-| `nvidia/meta/llama-3.3-70b-instruct`                 | Meta Llama 3.3 70B Instruct              | 131,072 | 4,096      |
-| `nvidia/nvidia/mistral-nemo-minitron-8b-8k-instruct` | NVIDIA Mistral NeMo Minitron 8B Instruct | 8,192   | 2,048      |
+| Model ref                                  | Name                         | Context | Max output |
+| ------------------------------------------ | ---------------------------- | ------- | ---------- |
+| `nvidia/nvidia/nemotron-3-super-120b-a12b` | NVIDIA Nemotron 3 Super 120B | 262,144 | 8,192      |
+| `nvidia/moonshotai/kimi-k2.5`              | Kimi K2.5                    | 262,144 | 8,192      |
+| `nvidia/minimaxai/minimax-m2.5`            | Minimax M2.5                 | 196,608 | 8,192      |
+| `nvidia/z-ai/glm5`                         | GLM 5                        | 202,752 | 8,192      |
 
 ## Notes
 
-- OpenAI-compatible `/v1` endpoint; use an API key from NVIDIA NGC.
+- OpenAI-compatible `/v1` endpoint; use an API key from [build.nvidia.com](https://build.nvidia.com/).
 - Provider auto-enables when `NVIDIA_API_KEY` is set.
 - The bundled catalog is static; costs default to `0` in source.

docs/providers/ollama.md

@@ -57,7 +57,7 @@ openclaw onboard --non-interactive \
 2. Pull a local model if you want local inference:
 
 ```bash
-ollama pull glm-4.7-flash
+ollama pull gemma4
 # or
 ollama pull gpt-oss:20b
 # or
@@ -78,12 +78,12 @@ openclaw onboard
 
 - `Local`: local models only
 - `Cloud + Local`: local models plus cloud models
-- Cloud models such as `kimi-k2.5:cloud`, `minimax-m2.5:cloud`, and `glm-5:cloud` do **not** require a local `ollama pull`
+- Cloud models such as `kimi-k2.5:cloud`, `minimax-m2.7:cloud`, and `glm-5.1:cloud` do **not** require a local `ollama pull`
 
 OpenClaw currently suggests:
 
-- local default: `glm-4.7-flash`
-- cloud defaults: `kimi-k2.5:cloud`, `minimax-m2.5:cloud`, `glm-5:cloud`
+- local default: `gemma4`
+- cloud defaults: `kimi-k2.5:cloud`, `minimax-m2.7:cloud`, `glm-5.1:cloud`
 
 5. If you prefer manual setup, enable Ollama for OpenClaw directly (any value works; Ollama doesn't require a real key):
 
@@ -99,7 +99,7 @@ openclaw config set models.providers.ollama.apiKey "ollama-local"
 
 ```bash
 openclaw models list
-openclaw models set ollama/glm-4.7-flash
+openclaw models set ollama/gemma4
 ```
 
 7. Or set the default in config:
@@ -108,7 +108,7 @@ openclaw models set ollama/glm-4.7-flash
 {
   agents: {
     defaults: {
-      model: { primary: "ollama/glm-4.7-flash" },
+      model: { primary: "ollama/gemma4" },
     },
   },
 }
@@ -229,7 +229,7 @@ Once configured, all your Ollama models are available:
 
 ## Cloud models
 
-Cloud models let you run cloud-hosted models (for example `kimi-k2.5:cloud`, `minimax-m2.5:cloud`, `glm-5:cloud`) alongside your local models.
+Cloud models let you run cloud-hosted models (for example `kimi-k2.5:cloud`, `minimax-m2.7:cloud`, `glm-5.1:cloud`) alongside your local models.
 
 To use cloud models, select **Cloud + Local** mode during setup. The wizard checks whether you are signed in and opens a browser sign-in flow when needed. If authentication cannot be verified, the wizard falls back to local model defaults.
 
@@ -355,7 +355,7 @@ To add models:
 
 ```bash
 ollama list  # See what's installed
-ollama pull glm-4.7-flash
+ollama pull gemma4
 ollama pull gpt-oss:20b
 ollama pull llama3.3     # Or another model
 ```

docs/providers/openai.md

@@ -28,6 +28,7 @@ Config key:
 Allowed values:
 
 - `"friendly"`: default; enable the OpenAI-specific overlay.
+- `"on"`: alias for `"friendly"`.
 - `"off"`: disable the overlay and use the base OpenClaw prompt only.
 
 Scope:
@@ -77,11 +78,20 @@ You can also set it directly with the config CLI:
 openclaw config set plugins.entries.openai.config.personality off
 ```
 
+OpenClaw normalizes this setting case-insensitively at runtime, so values like
+`"Off"` still disable the friendly overlay.
+
 ## Option A: OpenAI API key (OpenAI Platform)
 
 **Best for:** direct API access and usage-based billing.
 Get your API key from the OpenAI dashboard.
 
+Route summary:
+
+- `openai/gpt-5.4` = direct OpenAI Platform API route
+- Requires `OPENAI_API_KEY` (or equivalent OpenAI provider config)
+- In OpenClaw, ChatGPT/Codex sign-in is routed through `openai-codex/*`, not `openai/*`
+
 ### CLI setup
 
 ```bash
@@ -172,6 +182,12 @@ parameters, provider selection, and failover behavior.
 **Best for:** using ChatGPT/Codex subscription access instead of an API key.
 Codex cloud requires ChatGPT sign-in, while the Codex CLI supports ChatGPT or API key sign-in.
 
+Route summary:
+
+- `openai-codex/gpt-5.4` = ChatGPT/Codex OAuth route
+- Uses ChatGPT/Codex sign-in, not a direct OpenAI Platform API key
+- Provider-side limits for `openai-codex/*` can differ from the ChatGPT web/app experience
+
 ### CLI setup (Codex OAuth)
 
 ```bash
@@ -193,6 +209,10 @@ openclaw models auth login --provider openai-codex
 OpenAI's current Codex docs list `gpt-5.4` as the current Codex model. OpenClaw
 maps that to `openai-codex/gpt-5.4` for ChatGPT/Codex OAuth usage.
 
+This route is intentionally separate from `openai/gpt-5.4`. If you want the
+direct OpenAI Platform API path, use `openai/*` with an API key. If you want
+ChatGPT/Codex sign-in, use `openai-codex/*`.
+
 If onboarding reuses an existing Codex CLI login, those credentials stay
 managed by Codex CLI. On expiry, OpenClaw re-reads the external Codex source
 first and, when the provider can refresh it, writes the refreshed credential

docs/providers/vydra.md

@@ -85,8 +85,28 @@ Notes:
 
 - `vydra/veo3` is bundled as text-to-video only.
 - `vydra/kling` currently requires a remote image URL reference. Local file uploads are rejected up front.
+- Vydra's current `kling` HTTP route has been inconsistent about whether it requires `image_url` or `video_url`; the bundled provider maps the same remote image URL into both fields.
 - The bundled plugin stays conservative and does not forward undocumented style knobs such as aspect ratio, resolution, watermark, or generated audio.
 
+Provider-specific live coverage:
+
+```bash
+OPENCLAW_LIVE_TEST=1 \
+OPENCLAW_LIVE_VYDRA_VIDEO=1 \
+pnpm test:live -- extensions/vydra/vydra.live.test.ts
+```
+
+The bundled Vydra live file now covers:
+
+- `vydra/veo3` text-to-video
+- `vydra/kling` image-to-video using a remote image URL
+
+Override the remote image fixture when needed:
+
+```bash
+export OPENCLAW_LIVE_VYDRA_KLING_IMAGE_URL="https://example.com/reference.png"
+```
+
 See [Video Generation](/tools/video-generation) for shared tool behavior.
 
 ## Speech synthesis

docs/refactor/qa.md

@@ -0,0 +1,524 @@
+# QA Refactor
+
+Status: foundational migration landed.
+
+## Goal
+
+Move OpenClaw QA from a split-definition model to a single source of truth:
+
+- scenario metadata
+- prompts sent to the model
+- setup and teardown
+- harness logic
+- assertions and success criteria
+- artifacts and report hints
+
+The desired end state is a generic QA harness that loads powerful scenario definition files instead of hardcoding most behavior in TypeScript.
+
+## Current State
+
+Primary source of truth now lives in `qa/scenarios.md`.
+
+Implemented:
+
+- `qa/scenarios.md`
+  - canonical QA pack
+  - operator identity
+  - kickoff mission
+  - scenario metadata
+  - handler bindings
+- `extensions/qa-lab/src/scenario-catalog.ts`
+  - markdown pack parser + zod validation
+- `extensions/qa-lab/src/qa-agent-bootstrap.ts`
+  - plan rendering from the markdown pack
+- `extensions/qa-lab/src/qa-agent-workspace.ts`
+  - seeds generated compatibility files plus `QA_SCENARIOS.md`
+- `extensions/qa-lab/src/suite.ts`
+  - selects executable scenarios through markdown-defined handler bindings
+- QA bus protocol + UI
+  - generic inline attachments for image/video/audio/file rendering
+
+Remaining split surfaces:
+
+- `extensions/qa-lab/src/suite.ts`
+  - still owns most executable custom handler logic
+- `extensions/qa-lab/src/report.ts`
+  - still derives report structure from runtime outputs
+
+So the source-of-truth split is fixed, but execution is still mostly handler-backed rather than fully declarative.
+
+## What The Real Scenario Surface Looks Like
+
+Reading the current suite shows a few distinct scenario classes.
+
+### Simple interaction
+
+- channel baseline
+- DM baseline
+- threaded follow-up
+- model switch
+- approval followthrough
+- reaction/edit/delete
+
+### Config and runtime mutation
+
+- config patch skill disable
+- config apply restart wake-up
+- config restart capability flip
+- runtime inventory drift check
+
+### Filesystem and repo assertions
+
+- source/docs discovery report
+- build Lobster Invaders
+- generated image artifact lookup
+
+### Memory orchestration
+
+- memory recall
+- memory tools in channel context
+- memory failure fallback
+- session memory ranking
+- thread memory isolation
+- memory dreaming sweep
+
+### Tool and plugin integration
+
+- MCP plugin-tools call
+- skill visibility
+- skill hot install
+- native image generation
+- image roundtrip
+- image understanding from attachment
+
+### Multi-turn and multi-actor
+
+- subagent handoff
+- subagent fanout synthesis
+- restart recovery style flows
+
+These categories matter because they drive DSL requirements. A flat list of prompt + expected text is not enough.
+
+## Direction
+
+### Single source of truth
+
+Use `qa/scenarios.md` as the authored source of truth.
+
+The pack should stay:
+
+- human-readable in review
+- machine-parseable
+- rich enough to drive:
+  - suite execution
+  - QA workspace bootstrap
+  - QA Lab UI metadata
+  - docs/discovery prompts
+  - report generation
+
+### Preferred authoring format
+
+Use markdown as the top-level format, with structured YAML inside it.
+
+Recommended shape:
+
+- YAML frontmatter
+  - id
+  - title
+  - surface
+  - tags
+  - docs refs
+  - code refs
+  - model/provider overrides
+  - prerequisites
+- prose sections
+  - objective
+  - notes
+  - debugging hints
+- fenced YAML blocks
+  - setup
+  - steps
+  - assertions
+  - cleanup
+
+This gives:
+
+- better PR readability than giant JSON
+- richer context than pure YAML
+- strict parsing and zod validation
+
+Raw JSON is acceptable only as an intermediate generated form.
+
+## Proposed Scenario File Shape
+
+Example:
+
+````md
+---
+id: image-generation-roundtrip
+title: Image generation roundtrip
+surface: image
+tags: [media, image, roundtrip]
+models:
+  primary: openai/gpt-5.4
+requires:
+  tools: [image_generate]
+  plugins: [openai, qa-channel]
+docsRefs:
+  - docs/help/testing.md
+  - docs/concepts/model-providers.md
+codeRefs:
+  - extensions/qa-lab/src/suite.ts
+  - src/gateway/chat-attachments.ts
+---
+
+# Objective
+
+Verify generated media is reattached on the follow-up turn.
+
+# Setup
+
+```yaml scenario.setup
+- action: config.patch
+  patch:
+    agents:
+      defaults:
+        imageGenerationModel:
+          primary: openai/gpt-image-1
+- action: session.create
+  key: agent:qa:image-roundtrip
+```
+
+# Steps
+
+```yaml scenario.steps
+- action: agent.send
+  session: agent:qa:image-roundtrip
+  message: |
+    Image generation check: generate a QA lighthouse image and summarize it in one short sentence.
+- action: artifact.capture
+  kind: generated-image
+  promptSnippet: Image generation check
+  saveAs: lighthouseImage
+- action: agent.send
+  session: agent:qa:image-roundtrip
+  message: |
+    Roundtrip image inspection check: describe the generated lighthouse attachment in one short sentence.
+  attachments:
+    - fromArtifact: lighthouseImage
+```
+
+# Expect
+
+```yaml scenario.expect
+- assert: outbound.textIncludes
+  value: lighthouse
+- assert: requestLog.matches
+  where:
+    promptIncludes: Roundtrip image inspection check
+  imageInputCountGte: 1
+- assert: artifact.exists
+  ref: lighthouseImage
+```
+````
+
+## Runner Capabilities The DSL Must Cover
+
+Based on the current suite, the generic runner needs more than prompt execution.
+
+### Environment and setup actions
+
+- `bus.reset`
+- `gateway.waitHealthy`
+- `channel.waitReady`
+- `session.create`
+- `thread.create`
+- `workspace.writeSkill`
+
+### Agent turn actions
+
+- `agent.send`
+- `agent.wait`
+- `bus.injectInbound`
+- `bus.injectOutbound`
+
+### Config and runtime actions
+
+- `config.get`
+- `config.patch`
+- `config.apply`
+- `gateway.restart`
+- `tools.effective`
+- `skills.status`
+
+### File and artifact actions
+
+- `file.write`
+- `file.read`
+- `file.delete`
+- `file.touchTime`
+- `artifact.captureGeneratedImage`
+- `artifact.capturePath`
+
+### Memory and cron actions
+
+- `memory.indexForce`
+- `memory.searchCli`
+- `doctor.memory.status`
+- `cron.list`
+- `cron.run`
+- `cron.waitCompletion`
+- `sessionTranscript.write`
+
+### MCP actions
+
+- `mcp.callTool`
+
+### Assertions
+
+- `outbound.textIncludes`
+- `outbound.inThread`
+- `outbound.notInRoot`
+- `tool.called`
+- `tool.notPresent`
+- `skill.visible`
+- `skill.disabled`
+- `file.contains`
+- `memory.contains`
+- `requestLog.matches`
+- `sessionStore.matches`
+- `cron.managedPresent`
+- `artifact.exists`
+
+## Variables and Artifact References
+
+The DSL must support saved outputs and later references.
+
+Examples from the current suite:
+
+- create a thread, then reuse `threadId`
+- create a session, then reuse `sessionKey`
+- generate an image, then attach the file on the next turn
+- generate a wake marker string, then assert that it appears later
+
+Needed capabilities:
+
+- `saveAs`
+- `${vars.name}`
+- `${artifacts.name}`
+- typed references for paths, session keys, thread ids, markers, tool outputs
+
+Without variable support, the harness will keep leaking scenario logic back into TypeScript.
+
+## What Should Stay As Escape Hatches
+
+A fully pure declarative runner is not realistic in phase 1.
+
+Some scenarios are inherently orchestration-heavy:
+
+- memory dreaming sweep
+- config apply restart wake-up
+- config restart capability flip
+- generated image artifact resolution by timestamp/path
+- discovery-report evaluation
+
+These should use explicit custom handlers for now.
+
+Recommended rule:
+
+- 85-90% declarative
+- explicit `customHandler` steps for the hard remainder
+- named and documented custom handlers only
+- no anonymous inline code in the scenario file
+
+That keeps the generic engine clean while still allowing progress.
+
+## Architecture Change
+
+### Current
+
+Scenario markdown already is the source of truth for:
+
+- suite execution
+- workspace bootstrap files
+- QA Lab UI scenario catalog
+- report metadata
+- discovery prompts
+
+Generated compatibility:
+
+- seeded workspace still includes `QA_KICKOFF_TASK.md`
+- seeded workspace still includes `QA_SCENARIO_PLAN.md`
+- seeded workspace now also includes `QA_SCENARIOS.md`
+
+## Refactor Plan
+
+### Phase 1: loader and schema
+
+Done.
+
+- added `qa/scenarios.md`
+- added parser for named markdown YAML pack content
+- validated with zod
+- switched consumers to the parsed pack
+- removed repo-level `qa/seed-scenarios.json` and `qa/QA_KICKOFF_TASK.md`
+
+### Phase 2: generic engine
+
+- split `extensions/qa-lab/src/suite.ts` into:
+  - loader
+  - engine
+  - action registry
+  - assertion registry
+  - custom handlers
+- keep existing helper functions as engine operations
+
+Deliverable:
+
+- engine executes simple declarative scenarios
+
+Start with scenarios that are mostly prompt + wait + assert:
+
+- threaded follow-up
+- image understanding from attachment
+- skill visibility and invocation
+- channel baseline
+
+Deliverable:
+
+- first real markdown-defined scenarios shipping through the generic engine
+
+### Phase 4: migrate medium scenarios
+
+- image generation roundtrip
+- memory tools in channel context
+- session memory ranking
+- subagent handoff
+- subagent fanout synthesis
+
+Deliverable:
+
+- variables, artifacts, tool assertions, request-log assertions proven out
+
+### Phase 5: keep hard scenarios on custom handlers
+
+- memory dreaming sweep
+- config apply restart wake-up
+- config restart capability flip
+- runtime inventory drift
+
+Deliverable:
+
+- same authoring format, but with explicit custom-step blocks where needed
+
+### Phase 6: delete hardcoded scenario map
+
+Once the pack coverage is good enough:
+
+- remove most scenario-specific TypeScript branching from `extensions/qa-lab/src/suite.ts`
+
+## Fake Slack / Rich Media Support
+
+The current QA bus is text-first.
+
+Relevant files:
+
+- `extensions/qa-channel/src/protocol.ts`
+- `extensions/qa-lab/src/bus-state.ts`
+- `extensions/qa-lab/src/bus-queries.ts`
+- `extensions/qa-lab/src/bus-server.ts`
+- `extensions/qa-lab/web/src/ui-render.ts`
+
+Today the QA bus supports:
+
+- text
+- reactions
+- threads
+
+It does not yet model inline media attachments.
+
+### Needed transport contract
+
+Add a generic QA bus attachment model:
+
+```ts
+type QaBusAttachment = {
+  id: string;
+  kind: "image" | "video" | "audio" | "file";
+  mimeType: string;
+  fileName?: string;
+  inline?: boolean;
+  url?: string;
+  contentBase64?: string;
+  width?: number;
+  height?: number;
+  durationMs?: number;
+  altText?: string;
+  transcript?: string;
+};
+```
+
+Then add `attachments?: QaBusAttachment[]` to:
+
+- `QaBusMessage`
+- `QaBusInboundMessageInput`
+- `QaBusOutboundMessageInput`
+
+### Why generic first
+
+Do not build a Slack-only media model.
+
+Instead:
+
+- one generic QA transport model
+- multiple renderers on top of it
+  - current QA Lab chat
+  - future fake Slack web
+  - any other fake transport views
+
+This prevents duplicate logic and lets media scenarios stay transport-agnostic.
+
+### UI work needed
+
+Update the QA UI to render:
+
+- inline image preview
+- inline audio player
+- inline video player
+- file attachment chip
+
+The current UI can already render threads and reactions, so attachment rendering should layer onto the same message card model.
+
+### Scenario work enabled by media transport
+
+Once attachments flow through QA bus, we can add richer fake-chat scenarios:
+
+- inline image reply in fake Slack
+- audio attachment understanding
+- video attachment understanding
+- mixed attachment ordering
+- thread reply with media retained
+
+## Recommendation
+
+The next implementation chunk should be:
+
+1. add markdown scenario loader + zod schema
+2. generate the current catalog from markdown
+3. migrate a few simple scenarios first
+4. add generic QA bus attachment support
+5. render inline image in the QA UI
+6. then expand to audio and video
+
+This is the smallest path that proves both goals:
+
+- generic markdown-defined QA
+- richer fake messaging surfaces
+
+## Open Questions
+
+- whether scenario files should allow embedded markdown prompt templates with variable interpolation
+- whether setup/cleanup should be named sections or just ordered action lists
+- whether artifact references should be strongly typed in schema or string-based
+- whether custom handlers should live in one registry or per-surface registries
+- whether the generated JSON compatibility file should remain checked in during migration

docs/reference/secretref-credential-surface.md

@@ -41,7 +41,6 @@ Scope intent:
 - `talk.providers.*.apiKey`
 - `messages.tts.providers.*.apiKey`
 - `tools.web.fetch.firecrawl.apiKey`
-- `plugins.entries.firecrawl.config.webFetch.apiKey`
 - `plugins.entries.brave.config.webSearch.apiKey`
 - `plugins.entries.google.config.webSearch.apiKey`
 - `plugins.entries.xai.config.webSearch.apiKey`

docs/reference/session-management-compaction.md

@@ -275,6 +275,21 @@ Implementation: `ensurePiCompactionReserveTokens()` in `src/agents/pi-settings.t
 
 ---
 
+## Pluggable compaction providers
+
+Plugins can register a compaction provider via `registerCompactionProvider()` on the plugin API. When `agents.defaults.compaction.provider` is set to a registered provider id, the safeguard extension delegates summarization to that provider instead of the built-in `summarizeInStages` pipeline.
+
+- `provider`: id of a registered compaction provider plugin. Leave unset for default LLM summarization.
+- Setting a `provider` forces `mode: "safeguard"`.
+- Providers receive the same compaction instructions and identifier-preservation policy as the built-in path.
+- The safeguard still preserves recent-turn and split-turn suffix context after provider output.
+- If the provider fails or returns an empty result, OpenClaw falls back to built-in LLM summarization automatically.
+- Abort/timeout signals are re-thrown (not swallowed) to respect caller cancellation.
+
+Source: `src/plugins/compaction-provider.ts`, `src/agents/pi-hooks/compaction-safeguard.ts`.
+
+---
+
 ## User-visible surfaces
 
 You can observe compaction and session state via:

docs/reference/test.md

@@ -13,13 +13,18 @@ title: "Tests"
 - `pnpm test:coverage`: Runs the unit suite with V8 coverage (via `vitest.unit.config.ts`). Global thresholds are 70% lines/branches/functions/statements. Coverage excludes integration-heavy entrypoints (CLI wiring, gateway/telegram bridges, webchat static server) to keep the target focused on unit-testable logic.
 - `pnpm test:coverage:changed`: Runs unit coverage only for files changed since `origin/main`.
 - `pnpm test:changed`: expands changed git paths into scoped Vitest lanes when the diff only touches routable source/test files. Config/setup changes still fall back to the native root projects run so wiring edits rerun broadly when needed.
-- `pnpm test`: routes explicit file/directory targets through scoped Vitest lanes, but still falls back to the native root projects run when you do a full untargeted sweep.
+- `pnpm test`: routes explicit file/directory targets through scoped Vitest lanes. Untargeted runs now execute eleven sequential shard configs (`vitest.full-core-unit-src.config.ts`, `vitest.full-core-unit-security.config.ts`, `vitest.full-core-unit-ui.config.ts`, `vitest.full-core-unit-support.config.ts`, `vitest.full-core-support-boundary.config.ts`, `vitest.full-core-contracts.config.ts`, `vitest.full-core-bundled.config.ts`, `vitest.full-core-runtime.config.ts`, `vitest.full-agentic.config.ts`, `vitest.full-auto-reply.config.ts`, `vitest.full-extensions.config.ts`) instead of one giant root-project process.
+- Selected `plugin-sdk` and `commands` test files now route through dedicated light lanes that keep only `test/setup.ts`, leaving runtime-heavy cases on their existing lanes.
+- Selected `plugin-sdk` and `commands` helper source files also map `pnpm test:changed` to explicit sibling tests in those light lanes, so small helper edits avoid rerunning the heavy runtime-backed suites.
+- `auto-reply` now also splits into three dedicated configs (`core`, `top-level`, `reply`) so the reply harness does not dominate the lighter top-level status/token/helper tests.
 - Base Vitest config now defaults to `pool: "threads"` and `isolate: false`, with the shared non-isolated runner enabled across the repo configs.
 - `pnpm test:channels` runs `vitest.channels.config.ts`.
 - `pnpm test:extensions` runs `vitest.extensions.config.ts`.
 - `pnpm test:extensions`: runs extension/plugin suites.
 - `pnpm test:perf:imports`: enables Vitest import-duration + import-breakdown reporting, while still using scoped lane routing for explicit file/directory targets.
 - `pnpm test:perf:imports:changed`: same import profiling, but only for files changed since `origin/main`.
+- `pnpm test:perf:changed:bench -- --ref <git-ref>` benchmarks the routed changed-mode path against the native root-project run for the same committed git diff.
+- `pnpm test:perf:changed:bench -- --worktree` benchmarks the current worktree change set without committing first.
 - `pnpm test:perf:profile:main`: writes a CPU profile for the Vitest main thread (`.artifacts/vitest-main-profile`).
 - `pnpm test:perf:profile:runner`: writes CPU + heap profiles for the unit runner (`.artifacts/vitest-runner-profile`).
 - Gateway integration: opt-in via `OPENCLAW_TEST_INCLUDE_GATEWAY=1 pnpm test` or `pnpm test:gateway`.

docs/tools/acp-agents.md

@@ -774,6 +774,19 @@ Security and trust notes:
 Custom `mcpServers` still work as before. The built-in plugin-tools bridge is an
 additional opt-in convenience, not a replacement for generic MCP server config.
 
+### Runtime timeout configuration
+
+The bundled `acpx` plugin defaults embedded runtime turns to a 120-second
+timeout. This gives slower harnesses such as Gemini CLI enough time to complete
+ACP startup and initialization. Override it if your host needs a different
+runtime limit:
+
+```bash
+openclaw config set plugins.entries.acpx.config.timeoutSeconds 180
+```
+
+Restart the gateway after changing this value.
+
 ## Permission configuration
 
 ACP sessions run non-interactively — there is no TTY to approve or deny file-write and shell-exec permission prompts. The acpx plugin provides two config keys that control how permissions are handled: