fix(agents): forward all RunClaudeCliAgent params to runCliAgent

* fix(browser): guard interaction-driven navigations

* fix(browser): avoid rechecking unchanged interaction urls

* fix(browser): guard delayed interaction navigations

* fix(browser): guard interaction-driven navigations for full action duration

* fix(browser): avoid waiting on interaction grace timer

* fix(browser): ignore same-document hash-only URL changes in navigation guard

* fix(browser): dedupe interaction nav guards

* fix(browser): guard same-URL reloads in interaction navigation listeners

* docs(changelog): add interaction navigation guard entry

* fix(browser): drop duplicate ssrfPolicy props

* fix(browser): tighten interaction navigation guards

---------

Co-authored-by: Devin Robison <drobison@nvidia.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

@@ -15,6 +15,7 @@ Use this skill for `qa-lab` / `qa-channel` work. Repo-local QA only.
 - `qa/QA_KICKOFF_TASK.md`
 - `qa/seed-scenarios.json`
 - `extensions/qa-lab/src/suite.ts`
+- `extensions/qa-lab/src/character-eval.ts`
 
 ## Model policy
 
@@ -48,6 +49,71 @@ pnpm openclaw qa suite \
 5. If the user wants to watch the live UI, find the current `openclaw-qa` listen port and report `http://127.0.0.1:<port>`.
 6. If a scenario fails, fix the product or harness root cause, then rerun the full lane.
 
+## Character evals
+
+Use `qa character-eval` for style/persona/vibe checks across multiple live models.
+
+```bash
+pnpm openclaw qa character-eval \
+  --model openai/gpt-5.4,thinking=xhigh \
+  --model openai/gpt-5.2,thinking=xhigh \
+  --model anthropic/claude-opus-4-6,thinking=high \
+  --model anthropic/claude-sonnet-4-6,thinking=high \
+  --model minimax/MiniMax-M2.7,thinking=high \
+  --model zai/glm-5.1,thinking=high \
+  --model moonshot/kimi-k2.5,thinking=high \
+  --model qwen/qwen3.6-plus,thinking=high \
+  --model xiaomi/mimo-v2-pro,thinking=high \
+  --model google/gemini-3.1-pro-preview,thinking=high \
+  --model codex-cli/<codex-model>,thinking=high \
+  --judge-model openai/gpt-5.4,thinking=xhigh,fast \
+  --judge-model anthropic/claude-opus-4-6,thinking=high \
+  --concurrency 8 \
+  --judge-concurrency 8 \
+  --output-dir .artifacts/qa-e2e/character-eval-<tag>
+```
+
+- Runs local QA gateway child processes, not Docker.
+- Preferred model spec syntax is `provider/model,thinking=<level>[,fast|,no-fast|,fast=<bool>]` for both `--model` and `--judge-model`.
+- Do not add new examples with separate `--model-thinking`; keep that flag as legacy compatibility only.
+- Defaults to candidate models `openai/gpt-5.4`, `openai/gpt-5.2`, `anthropic/claude-opus-4-6`, `anthropic/claude-sonnet-4-6`, `minimax/MiniMax-M2.7`, `zai/glm-5.1`, `moonshot/kimi-k2.5`, `qwen/qwen3.6-plus`, `xiaomi/mimo-v2-pro`, and `google/gemini-3.1-pro-preview` when no `--model` is passed.
+- Candidate thinking defaults to `high`, with `xhigh` for OpenAI models that support it. Prefer inline `--model provider/model,thinking=<level>`; `--thinking <level>` and `--model-thinking <provider/model=level>` remain compatibility shims.
+- OpenAI candidate refs default to fast mode so priority processing is used where supported. Use inline `,fast`, `,no-fast`, or `,fast=false` for one model; use `--fast` only to force fast mode for every candidate.
+- Judges default to `openai/gpt-5.4,thinking=xhigh,fast` and `anthropic/claude-opus-4-6,thinking=high`.
+- Report includes judge ranking, run stats, durations, and full transcripts; do not include raw judge replies. Duration is benchmark context, not a grading signal.
+- Candidate and judge concurrency default to 8. Use `--concurrency <n>` and `--judge-concurrency <n>` to override when local gateways or provider limits need a gentler lane.
+- Scenario source should stay markdown-driven under `qa/scenarios/`.
+- For isolated character/persona evals, write the persona into `SOUL.md` and blank `IDENTITY.md` in the scenario flow. Use `SOUL.md + IDENTITY.md` only when intentionally testing how the normal OpenClaw identity combines with the character.
+- Keep prompts natural and task-shaped. The candidate model should receive character setup through `SOUL.md`, then normal user turns such as chat, workspace help, and small file tasks; do not ask "how would you react?" or tell the model it is in an eval.
+- Prefer at least one real task, such as creating or editing a tiny workspace artifact, so the transcript captures character under normal tool use instead of pure roleplay.
+
+## Codex CLI model lane
+
+Use model refs shaped like `codex-cli/<codex-model>` whenever QA should exercise Codex as a model backend.
+
+Examples:
+
+```bash
+pnpm openclaw qa suite \
+  --provider-mode live-frontier \
+  --model codex-cli/<codex-model> \
+  --alt-model codex-cli/<codex-model> \
+  --scenario <scenario-id> \
+  --output-dir .artifacts/qa-e2e/codex-<tag>
+```
+
+```bash
+pnpm openclaw qa manual \
+  --model codex-cli/<codex-model> \
+  --message "Reply exactly: CODEX_OK"
+```
+
+- Treat the concrete Codex model name as user/config input; do not hardcode it in source, docs examples, or scenarios.
+- Live QA preserves `CODEX_HOME` so Codex CLI auth/config works while keeping `HOME` and `OPENCLAW_HOME` sandboxed.
+- Mock QA should scrub `CODEX_HOME`.
+- If Codex returns fallback/auth text every turn, first check `CODEX_HOME`, `~/.profile`, and gateway child logs before changing scenario assertions.
+- For model comparison, include `codex-cli/<codex-model>` as another candidate in `qa character-eval`; the report should label it as an opaque model name.
+
 ## Repo facts
 
 - Seed scenarios live in `qa/`.

.github/workflows/ci.yml

@@ -450,6 +450,7 @@ jobs:
 
       - name: Run ${{ matrix.task }} (${{ matrix.runtime }})
         env:
+          OPENCLAW_TEST_PROJECTS_PARALLEL: 3
           TASK: ${{ matrix.task }}
         shell: bash
         run: |
@@ -548,6 +549,10 @@ jobs:
           TASK: ${{ matrix.task }}
         run: |
           echo "OPENCLAW_VITEST_MAX_WORKERS=2" >> "$GITHUB_ENV"
+          if [ "$TASK" = "test" ]; then
+            echo "OPENCLAW_TEST_PROJECTS_LEAF_SHARDS=1" >> "$GITHUB_ENV"
+            echo "OPENCLAW_TEST_SKIP_FULL_EXTENSIONS_SHARD=1" >> "$GITHUB_ENV"
+          fi
           if [ "$TASK" = "channels" ]; then
             echo "OPENCLAW_VITEST_MAX_WORKERS=1" >> "$GITHUB_ENV"
           fi
@@ -753,6 +758,11 @@ 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 +807,7 @@ 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: ${{ steps.gateway_watch_regression.outcome }}
@@ -820,6 +831,7 @@ jobs:
             "extension-relative-outside-package-boundary|$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
@@ -935,6 +947,7 @@ jobs:
       NODE_OPTIONS: --max-old-space-size=6144
       # Keep total concurrency predictable on the 32 vCPU runner.
       OPENCLAW_VITEST_MAX_WORKERS: 1
+      OPENCLAW_TEST_SKIP_FULL_EXTENSIONS_SHARD: 1
     defaults:
       run:
         shell: bash

CHANGELOG.md

@@ -6,82 +6,152 @@ Docs: https://docs.openclaw.ai
 
 ### Changes
 
-- 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 generation: preserve intent across auth-backed image, music, and video provider fallback, remap size, aspect ratio, resolution, and duration hints to the closest supported option, and surface explicit provider capabilities plus mode-aware video-to-video support.
-- Memory/wiki: restore the bundled `memory-wiki` stack with plugin, CLI, sync/query/apply tooling, and memory-host integration for wiki-backed memory workflows.
-- 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/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/Anthropic: restore Claude CLI as the preferred local Anthropic path in onboarding, model-auth guidance, doctor flows, and Docker Claude CLI live lanes again.
-- 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.
-- Tools/media generation: auto-fallback across auth-backed image, music, and video providers by default, and remap fallback size, aspect ratio, resolution, and duration hints to the closest supported option instead of dropping intent on provider switches.
-- Tools/media generation: report applied fallback geometry and duration settings consistently in tool results, add a shared normalization contract for image/music/video runtimes, and simplify the bundled image-generation-core runtime test to only verify the plugin-sdk re-export seam.
-- 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.
-- 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.
-- Plugins/memory: add a public memory-artifact export seam to the unified memory capability so companion plugins like `memory-wiki` can bridge the active memory plugin without reaching into `memory-core` internals. Thanks @vincentkoc.
-- Memory/wiki: add structured claim/evidence fields plus compiled agent digest artifacts so `memory-wiki` behaves more like a persistent knowledge layer and less like markdown-only page storage. Thanks @vincentkoc.
-- Memory/wiki: add claim-health linting, contradiction clustering, staleness-aware dashboards, and freshness-weighted wiki search so `memory-wiki` can act more like a maintained belief layer than a passive markdown dump. Thanks @vincentkoc.
-- Memory/wiki: use compiled digest artifacts as the first-pass wiki index for search/get flows, and resolve claim ids back to owning pages so agents can retrieve knowledge by belief identity instead of only by file path. Thanks @vincentkoc.
-- Memory/wiki: add an opt-in `context.includeCompiledDigestPrompt` flag so memory prompt supplements can append a compact compiled wiki snapshot for legacy prompt assembly and context engines that explicitly consume memory prompt sections. Thanks @vincentkoc.
-- Memory/wiki: add task-backed `wiki import` with automatic local-file and markdown-vault detection so existing note stores can be backfilled into source pages with shared task progress instead of ad hoc one-off ingest flows. Thanks @vincentkoc.
-- Memory/wiki: keep imported Obsidian and Logseq notes readable by preserving markdown note bodies plus imported tags, aliases, and link hints instead of flattening every vault note into a fenced text blob. Thanks @vincentkoc.
-- Memory/wiki: use imported vault tags, aliases, and link hints in the compiled digest and wiki search ranking so imported Obsidian and Logseq notes are easier to recall by their original note metadata. Thanks @vincentkoc.
-- Memory/wiki: use imported vault aliases and link hints when building `## Related` backlinks so imported Obsidian and Logseq notes can reconnect their note graph after import. Thanks @vincentkoc.
-- Memory/wiki: let `wiki_get` and metadata updates resolve imported vault titles and aliases directly, so imported notes stay addressable by their original note names instead of only generated paths. Thanks @vincentkoc.
-- Memory/wiki: upgrade `reports/import-review.md` to flag duplicate imported titles and aliases plus obviously low-signal notes, so large vault imports are easier to triage before promotion or synthesis work. Thanks @vincentkoc.
-- Memory/wiki: add duplicate-body clustering to `reports/import-review.md` so large vault imports can surface copied or renamed notes even when titles and aliases differ. Thanks @vincentkoc.
-- Memory/wiki: preserve imported markdown vault relative paths in digest, lookup, and related-link reconstruction so imported note identity survives search and `wiki_get`. Thanks @vincentkoc.
-- Memory/wiki: auto-detect and import ChatGPT export JSON files as conversation source pages instead of misclassifying them as generic local files. Thanks @vincentkoc.
-- Plugin SDK/context engines: pass `availableTools` and `citationsMode` into `assemble()`, and expose `buildMemorySystemPromptAddition(...)` so non-legacy context engines can adopt the active memory prompt path without reimplementing it. Thanks @vincentkoc.
+- iOS: pin release versioning to an explicit CalVer in `apps/ios/version.json`, keep TestFlight iteration on the same short version until maintainers intentionally promote the next gateway version, and add the documented `pnpm ios:version:pin -- --from-gateway` workflow for release trains. (#63001) Thanks @ngutman.
+- Plugins/provider-auth: let provider manifests declare `providerAuthAliases` so provider variants can share env vars, auth profiles, config-backed auth, and API-key onboarding choices without core-specific wiring.
+- Memory/dreaming: add a grounded REM backfill lane with historical `rem-harness --path`, diary commit, and reset flows so old daily notes can be replayed safely into `DREAMS.md`. Thanks @mbelinky.
+- Memory/dreaming: harden grounded diary extraction so `What Happened`, `Reflections`, and durable candidates suppress operational noise and preserve more atomic lasting facts. Thanks @mbelinky.
+- Control UI/dreaming: add a structured diary view with timeline navigation, backfill/reset controls, and traceable dreaming summaries. Thanks @mbelinky.
 
 ### Fixes
 
+- Control UI: guard stale session-history reloads during fast session switches so the selected session and rendered transcript stay in sync. (#62975) Thanks @scoootscooob.
+- Slack/media: preserve bearer auth across same-origin `files.slack.com` redirects while still stripping it on cross-origin Slack CDN hops, so `url_private_download` image attachments load again. (#62960) Thanks @vincentkoc.
+- Gateway/node exec events: mark remote node `exec.started`, `exec.finished`, and `exec.denied` summaries as untrusted system events and sanitize node-provided command/output/reason text before enqueueing them, so remote node output cannot inject trusted `System:` content into later turns. (#62659) Thanks @eleqtrizit.
+- Agents/timeouts: make the LLM idle timeout inherit `agents.defaults.timeoutSeconds` when configured, disable the unconfigured idle watchdog for cron runs, and point idle-timeout errors at `agents.defaults.llm.idleTimeoutSeconds`. Thanks @drvoss.
+- Security/dotenv: expand workspace `.env` filtering to block runtime-control variables like gateway routing, ClawHub endpoints/tokens, browser executable overrides, and skip/disable control families, so untrusted repositories cannot steer OpenClaw runtime behavior through repo-local dotenv files. (#62660) Thanks @eleqtrizit.
+- Agents/failover: classify Z.ai vendor code `1311` as billing and `1113` as auth, including long wrapped `1311` payloads, so these errors stop falling through to generic failover handling. (#49552) Thanks @1bcMax.
+- Browser/security: block browser-control module override and skip-server env vars from untrusted workspace `.env` files, and reject unsafe URL-style browser control override specifiers before lazy loading, so repo-local dotenv state cannot steer browser control module loading. (#62663) Thanks @eleqtrizit.
+- QQBot/media-tags: support HTML entity-encoded angle brackets (`&lt;`/`&gt;`) in media-tag regexes so entity-escaped `<qqimg>` tags from upstream are correctly parsed and normalized. (#60493) Thanks @ylc0919.
+- npm packaging: mirror bundled Slack, Telegram, Discord, and Feishu channel runtime deps at the root and harden published-install verification so fresh installs fail fast on manifest drift instead of missing-module crashes. (#63065) Thanks @scoootscooob.
+- npm packaging: derive required root runtime mirrors from bundled plugin manifests and built root chunks, then install packed release tarballs without the repo `node_modules` so release checks catch missing plugin deps before publish.
+- Reply/doctor: resolve reply-run SecretRefs before preflight helpers touch config, surface gateway OAuth reauth failures to users, and make `openclaw doctor` call out exact reauth commands.
+- Android/pairing: clear stale setup-code auth on new QR scans, bootstrap operator and node sessions from fresh pairing, prefer stored device tokens after bootstrap handoff, and pause pairing auto-retry while the app is backgrounded so scan-once Android pairing recovers reliably again. (#63199) Thanks @obviyus.
+- Auto-reply/NO_REPLY: strip glued leading `NO_REPLY` tokens before reply normalization and ACP-visible streaming so silent sentinel text no longer leaks into user-visible replies while preserving substantive `NO_REPLY ...` text. Thanks @frankekn.
+- Gateway/sessions: clear auto-fallback-pinned model overrides on `/reset` and `/new` while still preserving explicit user model selections, including legacy sessions created before override-source tracking existed. (#63155) Thanks @frankekn.
+- Codex CLI: pass OpenClaw's system prompt through Codex's `model_instructions_file` config override so fresh Codex CLI sessions receive the same prompt guidance as Claude CLI sessions.
+- Matrix/gateway: wait for Matrix sync readiness before marking startup successful, keep Matrix background handler failures contained, and route fatal Matrix sync stops through channel-level restart handling instead of crashing the whole gateway. (#62779) Thanks @gumadeiras.
+- Browser/security: re-run blocked-destination safety checks after interaction-driven main-frame navigations from click, evaluate, hook-triggered click, and batched action flows, so browser interactions cannot bypass the SSRF quarantine when they land on forbidden URLs. (#63226) Thanks @eleqtrizit.
+
+## 2026.4.8
+
+### Fixes
+
+- Telegram/setup: load setup and secret contracts through packaged top-level sidecars so installed npm builds no longer try to import missing `dist/extensions/telegram/src/*` files during gateway startup.
+- Bundled channels/setup: load shared secret contracts through packaged top-level sidecars across BlueBubbles, Feishu, Google Chat, IRC, Matrix, Mattermost, Microsoft Teams, Nextcloud Talk, Slack, and Zalo so installed npm builds no longer rely on missing `dist/extensions/*/src/*` files during gateway startup.
+- Bundled plugins: align packaged plugin compatibility metadata with the release version so bundled channels and providers load on OpenClaw 2026.4.8.
+- Agents/progress: keep `update_plan` available for OpenAI-family runs while returning compact success payloads and allowing `tools.experimental.planTool=false` to opt out.
+- Agents/exec: keep `/exec` current-default reporting aligned with real runtime behavior so `host=auto` sessions surface the correct host-aware fallback policy (`full/off` on gateway or node, `deny/off` on sandbox) instead of stale stricter defaults.
+- Slack: honor ambient HTTP(S) proxy settings for Socket Mode WebSocket connections, including NO_PROXY exclusions, so proxy-only deployments can connect without a monkey patch. (#62878) Thanks @mjamiv.
+- Slack/actions: pass the already resolved read token into `downloadFile` so SecretRef-backed bot tokens no longer fail after a raw config re-read. (#62097) Thanks @martingarramon.
+- Network/fetch guard: skip target DNS pinning when trusted env-proxy mode is active so proxy-only sandboxes can let the trusted proxy resolve outbound hosts. (#59007) Thanks @cluster2600.
+
+## 2026.4.7-1
+
+## 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.
+- 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.
+- Plugins/provider-auth: expose runtime-ready provider auth through `openclaw/plugin-sdk/provider-auth-runtime` so native plugins and context engines can resolve request-ready credentials after provider-owned runtime exchanges like GitHub Copilot device-token-to-bearer flows. (#62753) Thanks @jalehman.
+
+### Fixes
+
+- 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.
-- 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.
-- 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, @afurm, and @openperf.
-- 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 @SuperMarioYL.
-- 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.
-- 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)
-- 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/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.
-- 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, @MoerAI, @jwchmodx, and @100yenadmin.
-- 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.
-- Memory/wiki: follow `current_node` when importing ChatGPT export mapping trees so imported conversation transcripts stop pulling in stale alternate branches. Thanks @vincentkoc.
-- Memory/wiki: extract readable text from object-shaped ChatGPT export message parts so imported conversation transcripts stop dropping rich content blocks. Thanks @vincentkoc.
-- Memory/wiki: preserve conversation turn order for ChatGPT imports when timestamps are missing or tied, so imported transcripts stop scrambling equal-time messages and current-branch lineage. Thanks @vincentkoc.
-- Memory/wiki: skip hidden and tool-role ChatGPT export messages during import so conversation source pages stop filling up with export-only scaffolding. Thanks @vincentkoc.
-- Memory/wiki: skip ChatGPT export conversations that end up with no readable visible turns, so imports stop generating empty placeholder source pages from hidden/tool-only records. Thanks @vincentkoc.
+- 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.
+- Agents/OpenAI: default missing reasoning effort to `high` on OpenAI Responses, WebSocket, and compatible completions transports, while still honoring explicit per-run reasoning levels.
+- 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.
-- 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)
-- 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.
-- 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 @ThanhNguyxn07.
-- 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.
-- 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 @wit-oc.
-- 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.
-- 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.
-- 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.
-- 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.
+- 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.
+- Plugins/onboarding auth choices: prevent untrusted workspace plugins from colliding with bundled provider auth-choice ids during non-interactive onboarding, so bundled provider setup keeps operator secrets out of untrusted workspace plugin handlers unless those plugins are explicitly trusted. (#62368) 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)
-- 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.
-- 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.
-- 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.
-- 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)
-- Exec/runtime events: mark background `notifyOnExit` summaries and ACP parent-stream relays as untrusted system events so lower-trust runtime output no longer re-enters later turns as trusted `System:` text.
-- Hooks/wake: queue direct and mapped wake-hook payloads as untrusted system events so external wake content no longer enters the main session as trusted input. (#62003)
+- 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.
+- 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.
-- 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.
-- 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.
-- 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.
-- 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.
+- 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.
-- 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.
+- 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.
+- Agents/model resolution: let explicit `openai-codex/gpt-5.4` selection prefer provider runtime metadata when it reports a larger context window, keeping configured Codex runs aligned with the live provider limits. (#62694) Thanks @ruclaw7.
+- Agents/model resolution: keep explicit-model runtime comparisons on the configured workspace plugin registry, so workspace-installed providers do not silently fall back to stale explicit metadata during runtime model lookup.
+- Providers/Z.AI: default onboarding and endpoint detection to GLM-5.1 instead of GLM-5. (#61998) Thanks @serg0x.
+- Reply execution: prefer the active runtime snapshot over stale queued reply config during embedded reply and follow-up execution so SecretRef-backed reply turns stop crashing after secrets have already resolved. (#62693) Thanks @mbelinky.
+- Android/manual connect: allow blank port input only for TLS manual gateway endpoints so standard HTTPS Tailscale hosts default to `443` without silently changing cleartext manual connects. (#63134) Thanks @Tyler-RNG.
+- Matrix/agents: hide owner-only `set-profile` from embedded agent channel-action discovery so non-owner runs stop advertising profile updates they cannot execute. (#62662) Thanks @eleqtrizit.
 
 ## 2026.4.5
 
@@ -220,6 +290,7 @@ 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.
@@ -262,6 +333,7 @@ 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.
@@ -816,6 +888,7 @@ 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
 
@@ -1753,6 +1826,9 @@ 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.

appcast.xml

@@ -2,6 +2,136 @@
 <rss xmlns:sparkle="http://www.andymatuschak.org/xml-namespaces/sparkle" version="2.0">
     <channel>
         <title>OpenClaw</title>
+        <item>
+            <title>2026.4.8</title>
+            <pubDate>Wed, 08 Apr 2026 06:12:50 +0000</pubDate>
+            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
+            <sparkle:version>2026040890</sparkle:version>
+            <sparkle:shortVersionString>2026.4.8</sparkle:shortVersionString>
+            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
+            <description><![CDATA[<h2>OpenClaw 2026.4.8</h2>
+<h3>Fixes</h3>
+<ul>
+<li>Telegram/setup: load setup and secret contracts through packaged top-level sidecars so installed npm builds no longer try to import missing <code>dist/extensions/telegram/src/*</code> files during gateway startup.</li>
+<li>Bundled channels/setup: load shared secret contracts through packaged top-level sidecars across BlueBubbles, Feishu, Google Chat, IRC, Matrix, Mattermost, Microsoft Teams, Nextcloud Talk, Slack, and Zalo so installed npm builds no longer rely on missing <code>dist/extensions/*/src/*</code> files during gateway startup.</li>
+<li>Bundled plugins: align packaged plugin compatibility metadata with the release version so bundled channels and providers load on OpenClaw 2026.4.8.</li>
+<li>Agents/progress: keep <code>update_plan</code> available for OpenAI-family runs while returning compact success payloads and allowing <code>tools.experimental.planTool=false</code> to opt out.</li>
+<li>Agents/exec: keep <code>/exec</code> current-default reporting aligned with real runtime behavior so <code>host=auto</code> sessions surface the correct host-aware fallback policy (<code>full/off</code> on gateway or node, <code>deny/off</code> on sandbox) instead of stale stricter defaults.</li>
+<li>Slack: honor ambient HTTP(S) proxy settings for Socket Mode WebSocket connections, including NO_PROXY exclusions, so proxy-only deployments can connect without a monkey patch. (#62878) Thanks @mjamiv.</li>
+<li>Slack/actions: pass the already resolved read token into <code>downloadFile</code> so SecretRef-backed bot tokens no longer fail after a raw config re-read. (#62097) Thanks @martingarramon.</li>
+<li>Network/fetch guard: skip target DNS pinning when trusted env-proxy mode is active so proxy-only sandboxes can let the trusted proxy resolve outbound hosts. (#59007) Thanks @cluster2600.</li>
+</ul>
+<p><a href="https://github.com/openclaw/openclaw/blob/main/CHANGELOG.md">View full changelog</a></p>
+]]></description>
+            <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.4.8/OpenClaw-2026.4.8.zip" length="25324810" type="application/octet-stream" sparkle:edSignature="aogl3hJf+FeRvQj0W4WDGMQnIRPpxXPQam50U7SBT3ljA1CeSbIGsnaj20aLF0Qc9DikPEXt5AEg7LMOen4+BQ=="/>
+        </item>
+        <item>
+            <title>2026.4.7</title>
+            <pubDate>Wed, 08 Apr 2026 02:54:26 +0000</pubDate>
+            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
+            <sparkle:version>2026040790</sparkle:version>
+            <sparkle:shortVersionString>2026.4.7</sparkle:shortVersionString>
+            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
+            <description><![CDATA[<h2>OpenClaw 2026.4.7</h2>
+<h3>Changes</h3>
+<ul>
+<li>CLI/infer: add a first-class <code>openclaw infer ...</code> hub for provider-backed inference workflows across model, media, web, and embedding tasks. Thanks @Takhoffman.</li>
+<li>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.</li>
+<li>Memory/wiki: restore the bundled <code>memory-wiki</code> 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.</li>
+<li>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.</li>
+<li>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.</li>
+<li>Compaction: add pluggable compaction provider registry so plugins can replace the built-in summarization pipeline. Configure via <code>agents.defaults.compaction.provider</code>; falls back to LLM summarization on provider failure. (#56224) Thanks @DhruvBhatia0.</li>
+<li>Agents/system prompt: add <code>agents.defaults.systemPromptOverride</code> for controlled prompt experiments plus heartbeat prompt-section controls so heartbeat runtime behavior can stay enabled without injecting heartbeat instructions every turn.</li>
+<li>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.</li>
+<li>Providers/Google: preserve explicit thinking-off semantics for Gemma 4 while still enabling Gemma reasoning support in compatibility wrappers. (#62127) Thanks @romgenie.</li>
+<li>Providers/Arcee AI: add a bundled Arcee AI provider plugin with Trinity catalog entries, OpenRouter support, and updated onboarding/auth guidance. (#62068) Thanks @arthurbr11.</li>
+<li>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.</li>
+<li>Providers/Ollama: detect vision capability from the <code>/api/show</code> response and set image input on models that support it so Ollama vision models accept image attachments. (#62193) Thanks @BruceMacD.</li>
+<li>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.</li>
+<li>Providers/inferrs: add string-content compatibility for stricter OpenAI-compatible chat backends, document <code>inferrs</code> setup with a full config example, and add troubleshooting guidance for local backends that pass direct probes but fail on full agent-runtime prompts.</li>
+<li>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.</li>
+<li>Plugin SDK/context engines: pass <code>availableTools</code> and <code>citationsMode</code> into <code>assemble()</code>, 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.</li>
+<li>ACP/ACPX plugin: bump the bundled <code>acpx</code> pin to <code>0.5.1</code> so plugin-local installs and strict version checks pick up the latest published runtime release. (#62148) Thanks @onutc.</li>
+<li>Discord/events: allow <code>event-create</code> 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.</li>
+</ul>
+<h3>Fixes</h3>
+<ul>
+<li>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 <code>prompt</code>/<code>language</code> overrides, image output MIME/extension mismatches, configured web-search fallback behavior, and agent-vs-CLI web-search execution drift.</li>
+<li>Plugins/media: when <code>plugins.allow</code> is set, capability fallback now merges bundled capability plugin ids into the allowlist (not only <code>plugins.entries</code>), so media understanding providers such as OpenAI-compatible STT load for voice transcription without requiring <code>openai</code> in <code>plugins.allow</code>. (#62205) Thanks @neeravmakwana.</li>
+<li>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 <code>final_answer</code> text only. (#61729, #61747, #61829, #61855, #61954) Thanks @100yenadmin and contributors.</li>
+<li>Control UI: show <code>/tts</code> audio replies in webchat, detect mistaken <code>?token=</code> auth links with the correct <code>#token=</code> hint, and keep Copy, Canvas, and mobile exec-approval UI from covering chat content on narrow screens. (#54842, #61514, #61598) Thanks @neeravmakwana.</li>
+<li>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.</li>
+<li>TUI: route <code>/status</code> 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.</li>
+<li>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.</li>
+<li>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.</li>
+<li>Auth/OpenAI Codex OAuth: reload fresh on-disk credentials inside the locked refresh path and retry once after <code>refresh_token_reused</code> rotates only the stored refresh token, so relogin/restart recovery stops getting stuck on stale cached auth state. Thanks @owen-ever.</li>
+<li>Auth/OpenAI Codex OAuth: keep native <code>/model ...@profile</code> selections on the target session and honor explicit user-locked auth profiles even when per-agent auth order excludes them. (#62744) Thanks @jalehman.</li>
+<li>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 <code>service_tier</code> injection on OAuth-authenticated stream wrapper requests so Claude OAuth streaming stops failing with HTTP 401. (#60356, #61793)</li>
+<li>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.</li>
+<li>Agents/exec: preserve explicit <code>host=node</code> routing under elevated defaults when <code>tools.exec.host=auto</code>, fail loud on invalid elevated cross-host overrides, and keep <code>strictInlineEval</code> commands blocked after approval timeouts instead of falling through to automatic execution. (#61739) Thanks @obviyus.</li>
+<li>Nodes/exec approvals: keep <code>host=node</code> POSIX transport shell wrappers (<code>/bin/sh -lc ...</code>) aligned with inner-command allowlist analysis so allowlisted scripts stop prompting unnecessarily, while Windows <code>cmd.exe</code> wrapper runs stay approval-gated. (#62401) Thanks @ngutman.</li>
+<li>Nodes/exec approvals: keep Windows <code>cmd.exe /c</code> wrapper runs approval-gated even when <code>env</code> carriers, including env-assignment carriers, wrap the shell invocation. (#62439) Thanks @ngutman.</li>
+<li>Gateway tool/exec config: block model-facing <code>gateway config.apply</code> and <code>config.patch</code> writes from changing exec approval paths such as <code>safeBins</code>, <code>safeBinProfiles</code>, <code>safeBinTrustedDirs</code>, and <code>strictInlineEval</code>, while still allowing unchanged structured values through. (#62001) Thanks @eleqtrizit.</li>
+<li>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.</li>
+<li>Commands/allowlist: require owner authorization for <code>/allowlist add</code> and <code>/allowlist remove</code> before channel resolution, so non-owner but command-authorized senders can no longer persistently rewrite allowlist policy state. (#62383) Thanks @pgondhi987.</li>
+<li>Feishu/docx uploads: honor <code>tools.fs.workspaceOnly</code> for local <code>upload_file</code> and <code>upload_image</code> paths by forwarding workspace-constrained <code>localRoots</code> 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.</li>
+<li>Network/fetch guard: drop request bodies and body-describing headers on cross-origin <code>307</code> and <code>308</code> 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.</li>
+<li>Browser/SSRF: treat main-frame <code>document</code> redirect hops as navigations even when Playwright does not flag them as <code>isNavigationRequest()</code>, so strict private-network blocking still stops forbidden redirect pivots before the browser reaches the internal target. (#62355) Thanks @pgondhi987.</li>
+<li>Browser/node invoke: block persistent browser profile create, reset, and delete mutations through <code>browser.proxy</code> on both gateway-forwarded <code>node.invoke</code> and the node-host proxy path, even when no profile allowlist is configured. (#60489)</li>
+<li>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.</li>
+<li>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.</li>
+<li>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)</li>
+<li>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.</li>
+<li>Runtime event trust: mark background <code>notifyOnExit</code> 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 <code>System:</code> text. (#62003)</li>
+<li>Auto-reply/media: allow managed generated-media <code>MEDIA:</code> 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.</li>
+<li>Gateway/status and containers: auto-bind to <code>0.0.0.0</code> inside Docker and Podman environments, and probe local TLS gateways over <code>wss://</code> with self-signed fingerprint forwarding so container startup and loopback TLS status checks work again. (#61818, #61935) Thanks @openperf and contributors.</li>
+<li>Gateway/OpenAI-compatible HTTP: abort in-flight <code>/v1/chat/completions</code> and <code>/v1/responses</code> turns when clients disconnect so abandoned HTTP requests stop wasting agent runtime. (#54388) Thanks @Lellansin.</li>
+<li>macOS/gateway version: strip trailing commit metadata from CLI version output before semver parsing so the Mac app recognizes installed gateway versions like <code>OpenClaw 2026.4.2 (d74a122)</code> again. (#61111) Thanks @oliviareid-svg.</li>
+<li>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.</li>
+<li>Discord/ACP bindings: canonicalize DM conversation identity across inbound messages, component interactions, native commands, and current-conversation binding resolution so <code>--bind here</code> in Discord DMs keeps routing follow-up replies to the bound agent instead of falling back to the default agent.</li>
+<li>Discord: recover forwarded referenced message text and attachments when snapshots are missing, use <code>ws://</code> 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.</li>
+<li>Slack/thread mentions: add <code>channels.slack.thread.requireExplicitMention</code> so Slack channels that already require mentions can also require explicit <code>@bot</code> mentions inside bot-participated threads. (#58276) Thanks @praktika-engineer.</li>
+<li>Slack/threading: keep legacy thread stickiness for real replies when older callers omit <code>isThreadReply</code>, while still honoring <code>replyToMode</code> for Slack's auto-created top-level <code>thread_ts</code>. (#61835) Thanks @kaonash.</li>
+<li>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.</li>
+<li>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.</li>
+<li>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.</li>
+<li>Telegram/doctor: keep top-level access-control fallback in place during multi-account normalization while still promoting legacy default auth into <code>accounts.default</code>, so existing named bots keep inherited allowlists without dropping the legacy default bot. (#62263) Thanks @obviyus.</li>
+<li>Plugins/loaders: centralize bundled <code>dist/**</code> 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 <code>ERR_UNSUPPORTED_ESM_URL_SCHEME</code>. (#62286) Thanks @chen-zhang-cs-code.</li>
+<li>Plugins/channels: keep bundled channel artifact and secret-contract loading stable under lazy loading, preserve plugin-schema defaults during install, and fix Windows <code>file://</code> plus native-Jiti plugin loader paths so onboarding, doctor, <code>openclaw secret</code>, and bundled plugin installs work again. (#61832, #61836, #61853, #61856) Thanks @Zeesejo and contributors.</li>
+<li>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.</li>
+<li>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)</li>
+<li>Docker/plugins: stop forcing bundled plugin discovery to <code>/app/extensions</code> in runtime images so packaged installs use compiled <code>dist/extensions</code> artifacts again and Node 24 containers do not boot through source-only plugin entry paths. Fixes #62044. (#62316) Thanks @gumadeiras.</li>
+<li>Providers/Ollama: honor the selected provider's <code>baseUrl</code> during streaming so multi-Ollama setups stop routing every stream to the first configured Ollama endpoint. (#61678)</li>
+<li>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.</li>
+<li>Providers/xAI: recognize <code>api.grok.x.ai</code> as an xAI-native endpoint again and keep legacy <code>x_search</code> auth resolution working so older xAI web-search configs continue to load. (#61377) Thanks @jjjojoj.</li>
+<li>Providers/Mistral: send <code>reasoning_effort</code> for <code>mistral/mistral-small-latest</code> (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.</li>
+<li>OpenAI TTS/Groq: send <code>wav</code> to Groq-compatible speech endpoints, honor explicit <code>responseFormat</code> overrides on OpenAI-compatible paths, and only mark voice-note output as voice-compatible when the actual format is <code>opus</code>. (#62233) Thanks @neeravmakwana.</li>
+<li>Tools/web_fetch and web_search: fix <code>TypeError: fetch failed</code> caused by undici 8.0 enabling HTTP/2 by default; pinned SSRF-guard dispatchers now explicitly set <code>allowH2: false</code> to restore HTTP/1.1 behavior and keep the custom DNS-pinning lookup compatible. (#61738, #61777) Thanks @zozo123.</li>
+<li>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.</li>
+<li>Memory/vector recall: surface explicit warnings when <code>sqlite-vec</code> 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.</li>
+<li>Memory/dreaming: make Dreams config reads and writes respect the selected memory slot plugin instead of always targeting <code>memory-core</code>. (#62275) Thanks @SnowSky1.</li>
+<li>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.</li>
+<li>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.</li>
+<li>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.</li>
+<li>Agents/subagents: honor <code>sessions_spawn(lightContext: true)</code> 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.</li>
+<li>Cron: load <code>jobId</code> into <code>id</code> when the on-disk store omits <code>id</code>, matching doctor migration and fixing <code>unknown cron job id</code> for hand-edited <code>jobs.json</code>. (#62246) Thanks @neeravmakwana.</li>
+<li>Agents/model fallback: classify minimal HTTP 404 API errors (for example <code>404 status code (no body)</code>) as <code>model_not_found</code> so assistant failures throw into the fallback chain instead of stopping at the first fallback candidate. (#62119) Thanks @neeravmakwana.</li>
+<li>BlueBubbles/network: respect explicit private-network opt-out for loopback and private <code>serverUrl</code> values across account resolution, status probes, monitor startup, and attachment downloads, while keeping public-host attachment hostname pinning intact. (#59373) Thanks @jpreagan.</li>
+<li>Agents/heartbeat: keep heartbeat runs pinned to the main session so active subagent transcripts are not overwritten by heartbeat status messages. (#61803) Thanks @100yenadmin.</li>
+<li>Agents/heartbeat: respect disabled heartbeat prompt guidance so operators can suppress heartbeat prompt instructions without disabling heartbeat runtime behavior.</li>
+<li>Agents/compaction: stop compaction-wait aborts from re-entering prompt failover and replaying completed tool turns. (#62600) Thanks @i-dentifier.</li>
+<li>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.</li>
+<li>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.</li>
+<li>Logging: make <code>logging.level</code> and <code>logging.consoleLevel</code> honor the documented severity threshold ordering again, and keep child loggers inheriting the parent <code>minLevel</code>. (#44646) Thanks @zhumengzhu.</li>
+<li>Agents/sessions_send: pass <code>threadId</code> through announce delivery so cross-session notifications land in the correct Telegram forum topic instead of the group's general thread. (#62758) Thanks @jalehman.</li>
+<li>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.</li>
+<li>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.</li>
+<li>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.</li>
+</ul>
+<p><a href="https://github.com/openclaw/openclaw/blob/main/CHANGELOG.md">View full changelog</a></p>
+]]></description>
+            <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.4.7/OpenClaw-2026.4.7.zip" length="25324827" type="application/octet-stream" sparkle:edSignature="RyFWRz1trE/qvOiInD4vR6je9wx7fUTtHpZ94W8rMlZDByux9CyXOm/Anai96b9KyjTeQyC7YnJp5SRnYY3iCg=="/>
+        </item>
         <item>
             <title>2026.4.5</title>
             <pubDate>Mon, 06 Apr 2026 04:55:17 +0100</pubDate>
@@ -250,190 +380,5 @@
 ]]></description>
             <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.4.5/OpenClaw-2026.4.5.zip" length="25050620" type="application/octet-stream" sparkle:edSignature="gVbB/73byllY0utwGIi3P5t0FyvLldeR0Uq2pAa6LTBr8VyZlwNCZ2xPlt2zDFshSUBFKxicYzohOmfJ28ACBg=="/>
         </item>
-        <item>
-            <title>2026.4.2</title>
-            <pubDate>Thu, 02 Apr 2026 18:57:54 +0000</pubDate>
-            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
-            <sparkle:version>2026040290</sparkle:version>
-            <sparkle:shortVersionString>2026.4.2</sparkle:shortVersionString>
-            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
-            <description><![CDATA[<h2>OpenClaw 2026.4.2</h2>
-<h3>Breaking</h3>
-<ul>
-<li>Plugins/xAI: move <code>x_search</code> settings from the legacy core <code>tools.web.x_search.*</code> path to the plugin-owned <code>plugins.entries.xai.config.xSearch.*</code> path, standardize <code>x_search</code> auth on <code>plugins.entries.xai.config.webSearch.apiKey</code> / <code>XAI_API_KEY</code>, and migrate legacy config with <code>openclaw doctor --fix</code>. (#59674) Thanks @vincentkoc.</li>
-<li>Plugins/web fetch: move Firecrawl <code>web_fetch</code> config from the legacy core <code>tools.web.fetch.firecrawl.*</code> path to the plugin-owned <code>plugins.entries.firecrawl.config.webFetch.*</code> path, route <code>web_fetch</code> fallback through the new fetch-provider boundary instead of a Firecrawl-only core branch, and migrate legacy config with <code>openclaw doctor --fix</code>. (#59465) Thanks @vincentkoc.</li>
-</ul>
-<h3>Changes</h3>
-<ul>
-<li>Tasks/Task Flow: restore the core Task Flow substrate with managed-vs-mirrored sync modes, durable flow state/revision tracking, and <code>openclaw flows</code> inspection/recovery primitives so background orchestration can persist and be operated separately from plugin authoring layers. (#58930) Thanks @mbelinky.</li>
-<li>Tasks/Task Flow: add managed child task spawning plus sticky cancel intent, so external orchestrators can stop scheduling immediately and let parent Task Flows settle to <code>cancelled</code> once active child tasks finish. (#59610) Thanks @mbelinky.</li>
-<li>Plugins/Task Flow: add a bound <code>api.runtime.taskFlow</code> seam so plugins and trusted authoring layers can create and drive managed Task Flows from host-resolved OpenClaw context without passing owner identifiers on each call. (#59622) Thanks @mbelinky.</li>
-<li>Android/assistant: add assistant-role entrypoints plus Google Assistant App Actions metadata so Android can launch OpenClaw from the assistant trigger and hand prompts into the chat composer. (#59596) Thanks @obviyus.</li>
-<li>Exec defaults: make gateway/node host exec default to YOLO mode by requesting <code>security=full</code> with <code>ask=off</code>, and align host approval-file fallbacks plus docs/doctor reporting with that no-prompt default.</li>
-<li>Providers/runtime: add provider-owned replay hook surfaces for transcript policy, replay cleanup, and reasoning-mode dispatch. (#59143) Thanks @jalehman.</li>
-<li>Plugins/hooks: add <code>before_agent_reply</code> so plugins can short-circuit the LLM with synthetic replies after inline actions. (#20067) Thanks @JoshuaLelon.</li>
-<li>Channels/session routing: move provider-specific session conversation grammar into plugin-owned session-key surfaces, preserving Telegram topic routing and Feishu scoped inheritance across bootstrap, model override, restart, and tool-policy paths.</li>
-<li>Feishu/comments: add a dedicated Drive comment-event flow with comment-thread context resolution, in-thread replies, and <code>feishu_drive</code> comment actions for document collaboration workflows. (#58497) Thanks @wittam-01.</li>
-<li>Matrix/plugin: emit spec-compliant <code>m.mentions</code> metadata across text sends, media captions, edits, poll fallback text, and action-driven edits so Matrix mentions notify reliably in clients like Element. (#59323) Thanks @gumadeiras.</li>
-<li>Diffs: add plugin-owned <code>viewerBaseUrl</code> so viewer links can use a stable proxy/public origin without passing <code>baseUrl</code> on every tool call. (#59341) Related #59227. Thanks @gumadeiras.</li>
-<li>Agents/compaction: resolve <code>agents.defaults.compaction.model</code> consistently for manual <code>/compact</code> and other context-engine compaction paths, so engine-owned compaction uses the configured override model across runtime entrypoints. (#56710) Thanks @oliviareid-svg.</li>
-<li>Agents/compaction: add <code>agents.defaults.compaction.notifyUser</code> so the <code>🧹 Compacting context...</code> start notice is opt-in instead of always being shown. (#54251) Thanks @oguricap0327.</li>
-<li>WhatsApp/reactions: add <code>reactionLevel</code> guidance for agent reactions. Thanks @mcaxtr.</li>
-<li>Exec approvals/channels: auto-enable DM-first native chat approvals when supported channels can infer approvers from existing owner config, while keeping channel fanout explicit and clarifying forwarding versus native approval client config.</li>
-</ul>
-<h3>Fixes</h3>
-<ul>
-<li>Providers/transport policy: centralize request auth, proxy, TLS, and header shaping across shared HTTP, stream, and websocket paths, block insecure TLS/runtime transport overrides, and keep proxy-hop TLS separate from target mTLS settings. (#59682) Thanks @vincentkoc.</li>
-<li>Providers/Copilot: classify native GitHub Copilot API hosts in the shared provider endpoint resolver and harden token-derived proxy endpoint parsing so Copilot base URL routing stays centralized and fails closed on malformed hints. (#59644) Thanks @vincentkoc.</li>
-<li>Providers/streaming headers: centralize default and attribution header merging across OpenAI websocket, embedded-runner, and proxy stream paths so provider-specific headers stay consistent and caller overrides only win where intended. (#59542) Thanks @vincentkoc.</li>
-<li>Providers/media HTTP: centralize base URL normalization, default auth/header injection, and explicit header override handling across shared OpenAI-compatible audio, Deepgram audio, Gemini media/image, and Moonshot video request paths. (#59469) Thanks @vincentkoc.</li>
-<li>Providers/OpenAI-compatible routing: centralize native-vs-proxy request policy so hidden attribution and related OpenAI-family defaults only apply on verified native endpoints across stream, websocket, and shared audio HTTP paths. (#59433) Thanks @vincentkoc.</li>
-<li>Providers/Anthropic routing: centralize native-vs-proxy endpoint classification for direct Anthropic <code>service_tier</code> handling so spoofed or proxied hosts do not inherit native Anthropic defaults. (#59608) Thanks @vincentkoc.</li>
-<li>Gateway/exec loopback: restore legacy-role fallback for empty paired-device token maps and allow silent local role upgrades so local exec and node clients stop failing with pairing-required errors after <code>2026.3.31</code>. (#59092) Thanks @openperf.</li>
-<li>Agents/subagents: pin admin-only subagent gateway calls to <code>operator.admin</code> while keeping <code>agent</code> at least privilege, so <code>sessions_spawn</code> no longer dies on loopback scope-upgrade pairing with <code>close(1008) "pairing required"</code>. (#59555) Thanks @openperf.</li>
-<li>Exec approvals/config: strip invalid <code>security</code>, <code>ask</code>, and <code>askFallback</code> values from <code>~/.openclaw/exec-approvals.json</code> during normalization so malformed policy enums fall back cleanly to the documented defaults instead of corrupting runtime policy resolution. (#59112) Thanks @openperf.</li>
-<li>Exec approvals/doctor: report host policy sources from the real approvals file path and ignore malformed host override values when attributing effective policy conflicts. (#59367) Thanks @gumadeiras.</li>
-<li>Exec/runtime: treat <code>tools.exec.host=auto</code> as routing-only, keep implicit no-config exec on sandbox when available or gateway otherwise, and reject per-call host overrides that would bypass the configured sandbox or host target. (#58897) Thanks @vincentkoc.</li>
-<li>Slack/mrkdwn formatting: add built-in Slack mrkdwn guidance in inbound context so Slack replies stop falling back to generic Markdown patterns that render poorly in Slack. (#59100) Thanks @jadewon.</li>
-<li>WhatsApp/presence: send <code>unavailable</code> presence on connect in self-chat mode so personal-phone users stop losing all push notifications while the gateway is running. (#59410) Thanks @mcaxtr.</li>
-<li>WhatsApp/media: add HTML, XML, and CSS to the MIME map and fall back gracefully for unknown media types instead of dropping the attachment. (#51562) Thanks @bobbyt74.</li>
-<li>Matrix/onboarding: restore guided setup in <code>openclaw channels add</code> and <code>openclaw configure --section channels</code>, while keeping custom plugin wizards on the shared <code>setupWizard</code> seam. (#59462) Thanks @gumadeiras.</li>
-<li>Matrix/streaming: keep live partial previews for the current assistant block while preserving completed block updates as separate messages when <code>channels.matrix.blockStreaming</code> is enabled. (#59384) Thanks @gumadeiras.</li>
-<li>Feishu/comment threads: harden document comment-thread delivery so whole-document comments fall back to <code>add_comment</code>, delayed reply lookups retry more reliably, and user-visible replies avoid reasoning/planning spillover. (#59129) Thanks @wittam-01.</li>
-<li>MS Teams/streaming: strip already-streamed text from fallback block delivery when replies exceed the 4000-character streaming limit so long responses stop duplicating content. (#59297) Thanks @bradgroux.</li>
-<li>Slack/thread context: filter thread starter and history by the effective conversation allowlist without dropping valid open-room, DM, or group DM context. (#58380) Thanks @jacobtomlinson.</li>
-<li>Mattermost/probes: route status probes through the SSRF guard and honor <code>allowPrivateNetwork</code> so connectivity checks stay safe for self-hosted Mattermost deployments. (#58529) Thanks @mappel-nv.</li>
-<li>Zalo/webhook replay: scope replay dedupe key by chat and sender so reused message IDs across different chats or senders no longer collide, and harden metadata reads for partially missing payloads. (#58444)</li>
-<li>QQBot/structured payloads: restrict local file paths to QQ Bot-owned media storage, block traversal outside that root, reduce path leakage in logs, and keep inline image data URLs working. (#58453) Thanks @jacobtomlinson.</li>
-<li>Image generation/providers: route OpenAI, MiniMax, and fal image requests through the shared provider HTTP transport path so custom base URLs, guarded private-network routing, and provider request defaults stay aligned with the rest of provider HTTP. Thanks @vincentkoc.</li>
-<li>Image generation/providers: stop inferring private-network access from configured OpenAI, MiniMax, and fal image base URLs, and cap shared HTTP error-body reads so hostile or misconfigured endpoints fail closed without relaxing SSRF policy or buffering unbounded error payloads. Thanks @vincentkoc.</li>
-<li>Browser/host inspection: keep static Chrome inspection helpers out of the activated browser runtime so <code>openclaw doctor browser</code> and related checks do not eagerly load the bundled browser plugin. (#59471) Thanks @vincentkoc.</li>
-<li>Browser/CDP: normalize trailing-dot localhost absolute-form hosts before loopback checks so remote CDP websocket URLs like <code>ws://localhost.:...</code> rewrite back to the configured remote host. (#59236) Thanks @mappel-nv.</li>
-<li>Agents/output sanitization: strip namespaced <code>antml:thinking</code> blocks from user-visible text so Anthropic-style internal monologue tags do not leak into replies. (#59550) Thanks @obviyus.</li>
-<li>Kimi Coding/tools: normalize Anthropic tool payloads into the OpenAI-compatible function shape Kimi Coding expects so tool calls stop losing required arguments. (#59440) Thanks @obviyus.</li>
-<li>Image tool/paths: resolve relative local media paths against the agent <code>workspaceDir</code> instead of <code>process.cwd()</code> so inputs like <code>inbox/receipt.png</code> pass the local-path allowlist reliably. (#57222) Thanks Priyansh Gupta.</li>
-<li>Podman/launch: remove noisy container output from <code>scripts/run-openclaw-podman.sh</code> and align the Podman install guidance with the quieter startup flow. (#59368) Thanks @sallyom.</li>
-<li>Plugins/runtime: keep LINE reply directives and browser-backed cleanup/reset flows working even when those plugins are disabled while tightening bundled plugin activation guards. (#59412) Thanks @vincentkoc.</li>
-<li>ACP/gateway reconnects: keep ACP prompts alive across transient websocket drops while still failing boundedly when reconnect recovery does not complete. (#59473) Thanks @obviyus.</li>
-<li>ACP/gateway reconnects: reject stale pre-ack ACP prompts after reconnect grace expiry so callers fail cleanly instead of hanging indefinitely when the gateway never confirms the run.</li>
-<li>Gateway/session kill: enforce HTTP operator scopes on session kill requests and gate authorization before session lookup so unauthenticated callers cannot probe session existence. (#59128) Thanks @jacobtomlinson.</li>
-<li>MS Teams/logging: format non-<code>Error</code> failures with the shared unknown-error helper so logs stop collapsing caught SDK or Axios objects into <code>[object Object]</code>. (#59321) Thanks @bradgroux.</li>
-<li>Channels/setup: ignore untrusted workspace channel plugins during setup resolution so a shadowing workspace plugin cannot override built-in channel setup/login flows unless explicitly trusted in config. (#59158) Thanks @mappel-nv.</li>
-<li>Exec/Windows: restore allowlist enforcement with quote-aware <code>argPattern</code> matching across gateway and node exec, and surface accurate dynamic pre-approved executable hints in the exec tool description. (#56285) Thanks @kpngr.</li>
-<li>Gateway: prune empty <code>node-pending-work</code> state entries after explicit acknowledgments and natural expiry so the per-node state map no longer grows indefinitely. (#58179) Thanks @gavyngong.</li>
-<li>Webhooks/secret comparison: replace ad-hoc timing-safe secret comparisons across BlueBubbles, Feishu, Mattermost, Telegram, Twilio, and Zalo webhook handlers with the shared <code>safeEqualSecret</code> helper and reject empty auth tokens in BlueBubbles. (#58432) Thanks @eleqtrizit.</li>
-<li>OpenShell/mirror: constrain <code>remoteWorkspaceDir</code> and <code>remoteAgentWorkspaceDir</code> to the managed <code>/sandbox</code> and <code>/agent</code> roots, and keep mirror sync from overwriting or removing user-added shell roots during config synchronization. (#58515) Thanks @eleqtrizit.</li>
-<li>Plugins/activation: preserve explicit, auto-enabled, and default activation provenance plus reason metadata across CLI, gateway bootstrap, and status surfaces so plugin enablement state stays accurate after auto-enable resolution. (#59641) Thanks @vincentkoc.</li>
-<li>Exec/env: block additional host environment override pivots for package roots, language runtimes, compiler include paths, and credential/config locations so request-scoped exec cannot redirect trusted toolchains or config lookups. (#59233) Thanks @drobison00.</li>
-<li>Dotenv/workspace overrides: block workspace <code>.env</code> files from overriding <code>OPENCLAW_PINNED_PYTHON</code> and <code>OPENCLAW_PINNED_WRITE_PYTHON</code> so trusted helper interpreters cannot be redirected by repo-local env injection. (#58473) Thanks @eleqtrizit.</li>
-<li>Plugins/install: accept JSON5 syntax in <code>openclaw.plugin.json</code> and bundle <code>plugin.json</code> manifests during install/validation, so third-party plugins with trailing commas, comments, or unquoted keys no longer fail to install. (#59084) Thanks @singleGanghood.</li>
-<li>Telegram/exec approvals: rewrite shared <code>/approve … allow-always</code> callback payloads to <code>/approve … always</code> before Telegram button rendering so plugin approval IDs still fit Telegram's <code>callback_data</code> limit and keep the Allow Always action visible. (#59217) Thanks @jameslcowan.</li>
-<li>Cron/exec timeouts: surface timed-out <code>exec</code> and <code>bash</code> failures in isolated cron runs even when <code>verbose: off</code>, including custom session-target cron jobs, so scheduled runs stop failing silently. (#58247) Thanks @skainguyen1412.</li>
-<li>Telegram/exec approvals: fall back to the origin session key for async approval followups and keep resume-failure status delivery sanitized so Telegram followups still land without leaking raw exec metadata. (#59351) Thanks @seonang.</li>
-<li>Node-host/exec approvals: bind <code>pnpm dlx</code> invocations through the approval planner's mutable-script path so the effective runtime command is resolved for approval instead of being left unbound. (#58374)</li>
-<li>Exec/node hosts: stop forwarding the gateway workspace cwd to remote node exec when no workdir was explicitly requested, so cross-platform node approvals fall back to the node default cwd instead of failing with <code>SYSTEM_RUN_DENIED</code>. (#58977) Thanks @Starhappysh.</li>
-<li>Exec approvals/channels: decouple initiating-surface approval availability from native delivery enablement so Telegram, Slack, and Discord still expose approvals when approvers exist and native target routing is configured separately. (#59776) Thanks @joelnishanth.</li>
-</ul>
-<h3>Changes</h3>
-<ul>
-<li>macOS/Voice Wake: add the Voice Wake option to trigger Talk Mode. (#58490) Thanks @SmoothExec.</li>
-<li>Tasks/chat: add <code>/tasks</code> as a chat-native background task board for the current session, with recent task details and agent-local fallback counts when no linked tasks are visible. Related #54226. Thanks @vincentkoc.</li>
-<li>Web search/SearXNG: add the bundled SearXNG provider plugin for <code>web_search</code> with configurable host support. (#57317) Thanks @cgdusek.</li>
-<li>Telegram/errors: add configurable <code>errorPolicy</code> and <code>errorCooldownMs</code> controls so Telegram can suppress repeated delivery errors per account, chat, and topic without muting distinct failures. (#51914) Thanks @chinar-amrutkar</li>
-<li>Gateway/webchat: make <code>chat.history</code> text truncation configurable with <code>gateway.webchat.chatHistoryMaxChars</code> and per-request <code>maxChars</code>, while preserving silent-reply filtering and existing default payload limits. (#58900)</li>
-<li>Amazon Bedrock/Guardrails: add Bedrock Guardrails support to the bundled provider. (#58588) Thanks @MikeORed.</li>
-<li>ZAI/models: add <code>glm-5.1</code> and <code>glm-5v-turbo</code> to the bundled Z.AI provider catalog. (#58793) Thanks @tomsun28</li>
-<li>Agents/default params: add <code>agents.defaults.params</code> for global default provider parameters. (#58548) Thanks @lpender.</li>
-<li>Agents/failover: cap prompt-side and assistant-side same-provider auth-profile retries for rate-limit failures before cross-provider model fallback, add the <code>auth.cooldowns.rateLimitedProfileRotations</code> knob, and document the new fallback behavior. (#58707) Thanks @Forgely3D</li>
-<li>Agents/compaction: resolve <code>agents.defaults.compaction.model</code> consistently for manual <code>/compact</code> and other context-engine compaction paths, so engine-owned compaction uses the configured override model across runtime entrypoints. (#56710) Thanks @oliviareid-svg</li>
-<li>Cron/tools allowlist: add <code>openclaw cron --tools</code> for per-job tool allowlists. (#58504) Thanks @andyk-ms.</li>
-</ul>
-<h3>Fixes</h3>
-<ul>
-<li>Chat/error replies: stop leaking raw provider/runtime failures into external chat channels, return a friendly retry message instead, and add a specific <code>/new</code> hint for Bedrock toolResult/toolUse session mismatches. (#58831) Thanks @ImLukeF.</li>
-<li>Sessions/model switching: keep <code>/model</code> changes queued behind busy runs instead of interrupting the active turn, and retarget queued followups so later work picks up the new model as soon as the current turn finishes.</li>
-<li>Web UI/OpenResponses: preserve rewritten stream snapshots in webchat and keep OpenResponses final streamed text aligned when models rewind earlier output. (#58641) Thanks @neeravmakwana</li>
-<li>Discord/inbound media: pass Discord attachment and sticker downloads through the shared idle-timeout and worker-abort path so slow or stuck inbound media fetches stop hanging message processing. (#58593) Thanks @aquaright1</li>
-<li>Telegram/retries: keep non-idempotent sends on the strict safe-send path, retry wrapped pre-connect failures, and preserve <code>429</code> / <code>retry_after</code> backoff for safe delivery retries. (#51895) Thanks @chinar-amrutkar</li>
-<li>Telegram/exec approvals: route topic-aware exec approval followups through Telegram-owned threading and approval-target parsing, so forum-topic approvals stay in the originating topic instead of falling back to the root chat. (#58783)</li>
-<li>Telegram/local Bot API: preserve media MIME types for absolute-path downloads so local audio files still trigger transcription and other MIME-based handling. (#54603) Thanks @jzakirov</li>
-<li>Channels/WhatsApp: pass inbound message timestamp to model context so the AI can see when WhatsApp messages were sent. (#58590) Thanks @Maninae</li>
-<li>QQBot/voice: lazy-load <code>silk-wasm</code> in <code>audio-convert.ts</code> so qqbot still starts when the optional voice dependency is missing, while voice encode/decode degrades gracefully instead of crashing at module load time. (#58829) Thanks @WideLee.</li>
-</ul>
-<p><a href="https://github.com/openclaw/openclaw/blob/main/CHANGELOG.md">View full changelog</a></p>
-]]></description>
-            <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.4.2/OpenClaw-2026.4.2.zip" length="25843797" type="application/octet-stream" sparkle:edSignature="bNNXr4BJEU8W7ghXOujLJTYHZL2PL/r/p4llGBw0BFL+46mJ2Bir+IK8XQaCj5zp+O5JSuh5mY+Y/Nrq6TR7Cg=="/>
-        </item>
-        <item>
-            <title>2026.4.1</title>
-            <pubDate>Wed, 01 Apr 2026 17:14:12 +0000</pubDate>
-            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
-            <sparkle:version>2026040190</sparkle:version>
-            <sparkle:shortVersionString>2026.4.1</sparkle:shortVersionString>
-            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
-            <description><![CDATA[<h2>OpenClaw 2026.4.1</h2>
-<h3>Changes</h3>
-<ul>
-<li>Tasks/chat: add <code>/tasks</code> as a chat-native background task board for the current session, with recent task details and agent-local fallback counts when no linked tasks are visible. Related #54226. Thanks @vincentkoc.</li>
-<li>Web search/SearXNG: add the bundled SearXNG provider plugin for <code>web_search</code> with configurable host support. (#57317) Thanks @cgdusek.</li>
-<li>Amazon Bedrock/Guardrails: add Bedrock Guardrails support to the bundled provider. (#58588) Thanks @MikeORed.</li>
-<li>macOS/Voice Wake: add the Voice Wake option to trigger Talk Mode. (#58490) Thanks @SmoothExec.</li>
-<li>Feishu/comments: add a dedicated Drive comment-event flow with comment-thread context resolution, in-thread replies, and <code>feishu_drive</code> comment actions for document collaboration workflows. (#58497) Thanks @wittam-01.</li>
-<li>Gateway/webchat: make <code>chat.history</code> text truncation configurable with <code>gateway.webchat.chatHistoryMaxChars</code> and per-request <code>maxChars</code>, while preserving silent-reply filtering and existing default payload limits. (#58900)</li>
-<li>Agents/default params: add <code>agents.defaults.params</code> for global default provider parameters. (#58548) Thanks @lpender.</li>
-<li>Agents/failover: cap prompt-side and assistant-side same-provider auth-profile retries for rate-limit failures before cross-provider model fallback, add the <code>auth.cooldowns.rateLimitedProfileRotations</code> knob, and document the new fallback behavior. (#58707) Thanks @Forgely3D</li>
-<li>Cron/tools allowlist: add <code>openclaw cron --tools</code> for per-job tool allowlists. (#58504) Thanks @andyk-ms.</li>
-<li>Channels/session routing: move provider-specific session conversation grammar into plugin-owned session-key surfaces, preserving Telegram topic routing and Feishu scoped inheritance across bootstrap, model override, restart, and tool-policy paths.</li>
-<li>WhatsApp/reactions: add <code>reactionLevel</code> guidance for agent reactions. Thanks @mcaxtr.</li>
-<li>Telegram/errors: add configurable <code>errorPolicy</code> and <code>errorCooldownMs</code> controls so Telegram can suppress repeated delivery errors per account, chat, and topic without muting distinct failures. (#51914) Thanks @chinar-amrutkar</li>
-<li>ZAI/models: add <code>glm-5.1</code> and <code>glm-5v-turbo</code> to the bundled Z.AI provider catalog. (#58793) Thanks @tomsun28</li>
-<li>Agents/compaction: resolve <code>agents.defaults.compaction.model</code> consistently for manual <code>/compact</code> and other context-engine compaction paths, so engine-owned compaction uses the configured override model across runtime entrypoints. (#56710) Thanks @oliviareid-svg</li>
-</ul>
-<h3>Fixes</h3>
-<ul>
-<li>Chat/error replies: stop leaking raw provider/runtime failures into external chat channels, return a friendly retry message instead, and add a specific <code>/new</code> hint for Bedrock toolResult/toolUse session mismatches. (#58831) Thanks @ImLukeF.</li>
-<li>Gateway/reload: ignore startup config writes by persisted hash in the config reloader so generated auth tokens and seeded Control UI origins do not trigger a restart loop, while real <code>gateway.auth.*</code> edits still require restart. (#58678) Thanks @yelog</li>
-<li>Tasks/gateway: keep the task registry maintenance sweep from stalling the gateway event loop under synchronous SQLite pressure, so upgraded gateways stop hanging about a minute after startup. (#58670) Thanks @openperf</li>
-<li>Tasks/status: hide stale completed background tasks from <code>/status</code> and <code>session_status</code>, prefer live task context, and show recent failures only when no active work remains. (#58661) Thanks @vincentkoc</li>
-<li>Tasks/gateway: re-check the current task record before maintenance marks runs lost or prunes them, so a task heartbeat or cleanup update that lands during a sweep no longer gets overwritten by stale snapshot state.</li>
-<li>Exec/approvals: honor <code>exec-approvals.json</code> security defaults when inline or configured tool policy is unset, and keep Slack and Discord native approval handling aligned with inferred approvers and real channel enablement so remote exec stops falling into false approval timeouts and disabled states. Thanks @scoootscooob and @vincentkoc.</li>
-<li>Exec/approvals: make <code>allow-always</code> persist as durable user-approved trust instead of behaving like <code>allow-once</code>, reuse exact-command trust on shell-wrapper paths that cannot safely persist an executable allowlist entry, keep static allowlist entries from silently bypassing <code>ask:"always"</code>, and require explicit approval when Windows cannot build an allowlist execution plan instead of hard-dead-ending remote exec. Thanks @scoootscooob and @vincentkoc.</li>
-<li>Exec/cron: resolve isolated cron no-route approval dead-ends from the effective host fallback policy when trusted automation is allowed, and make <code>openclaw doctor</code> warn when <code>tools.exec</code> is broader than <code>~/.openclaw/exec-approvals.json</code> so stricter host-policy conflicts are explicit. Thanks @scoootscooob and @vincentkoc.</li>
-<li>Sessions/model switching: keep <code>/model</code> changes queued behind busy runs instead of interrupting the active turn, and retarget queued followups so later work picks up the new model as soon as the current turn finishes.</li>
-<li>Gateway/HTTP: skip failing HTTP request stages so one broken facade no longer forces every HTTP endpoint to return 500. (#58746) Thanks @yelog</li>
-<li>Gateway/nodes: stop pinning live node commands to the approved node-pair record. Node pairing remains a trust/token flow, while per-node <code>system.run</code> policy stays in that node's exec approvals config. Fixes #58824.</li>
-<li>WebChat/exec approvals: use native approval UI guidance in agent system prompts instead of telling agents to paste manual <code>/approve</code> commands in webchat sessions. Thanks @vincentkoc.</li>
-<li>Web UI/OpenResponses: preserve rewritten stream snapshots in webchat and keep OpenResponses final streamed text aligned when models rewind earlier output. (#58641) Thanks @neeravmakwana</li>
-<li>Discord/inbound media: pass Discord attachment and sticker downloads through the shared idle-timeout and worker-abort path so slow or stuck inbound media fetches stop hanging message processing. (#58593) Thanks @aquaright1</li>
-<li>Telegram/retries: keep non-idempotent sends on the strict safe-send path, retry wrapped pre-connect failures, and preserve <code>429</code> / <code>retry_after</code> backoff for safe delivery retries. (#51895) Thanks @chinar-amrutkar</li>
-<li>Telegram/exec approvals: route topic-aware exec approval followups through Telegram-owned threading and approval-target parsing, so forum-topic approvals stay in the originating topic instead of falling back to the root chat. (#58783)</li>
-<li>Telegram/local Bot API: preserve media MIME types for absolute-path downloads so local audio files still trigger transcription and other MIME-based handling. (#54603) Thanks @jzakirov</li>
-<li>Channels/WhatsApp: pass inbound message timestamp to model context so the AI can see when WhatsApp messages were sent. (#58590) Thanks @Maninae</li>
-<li>Channels/QQ Bot: keep <code>/bot-logs</code> export gated behind a truly explicit QQBot allowlist, rejecting wildcard and mixed wildcard entries while preserving the real framework command path. Thanks @vincentkoc.</li>
-<li>Channels/plugins: keep bundled channel plugins loadable from legacy <code>channels.<id></code> config even under restrictive plugin allowlists, and make <code>openclaw doctor</code> warn only on real plugin blockers instead of misleading setup guidance. (#58873) Thanks @obviyus</li>
-<li>Plugins/bundled runtimes: restore externalized bundled plugin runtime dependency staging across packed installs, Docker builds, and local runtime staging so bundled plugins keep their declared runtime deps after the 2026.3.31 externalization change. (#58782)</li>
-<li>LINE/runtime: resolve the packaged runtime contract from the built <code>dist/plugins/runtime</code> layout so LINE channels start correctly again after global npm installs on <code>2026.3.31</code>. (#58799) Thanks @vincentkoc.</li>
-<li>MiniMax/plugins: auto-enable the bundled MiniMax plugin for API-key auth/config so MiniMax image generation and other plugin-owned capabilities load without manual plugin allowlisting. (#57127) Thanks @tars90percent.</li>
-<li>Ollama/model picker: show only Ollama models after provider selection in the CLI picker. (#55290) Thanks @Luckymingxuan.</li>
-<li>CDP/profiles: prefer <code>cdpPort</code> over stale WebSocket URLs so browser automation reconnects cleanly. (#58499) Thanks @Mlightsnow.</li>
-<li>Media/paths: resolve relative <code>MEDIA</code> paths against the agent workspace so local attachment references keep working. (#58624) Thanks @aquaright1.</li>
-<li>Memory/session indexing: keep full reindexes from skipping session transcripts when sync is triggered by <code>session-start</code> or <code>watch</code>, so restart-driven reindexes preserve session memory. (#39732) Thanks @upupc</li>
-<li>Memory/QMD: prefer <code>--mask</code> over <code>--glob</code> when creating QMD collections so default memory collections keep their intended patterns and stop colliding on restart. (#58643) Thanks @GitZhangChi.</li>
-<li>Subagents/tasks: keep subagent completion and cleanup from crashing when task-registry writes fail, so a corrupt or missing task row no longer takes down the gateway during lifecycle finalization. Thanks @vincentkoc.</li>
-<li>Sandbox/browser: compare browser runtime inspection against <code>agents.defaults.sandbox.browser.image</code> so <code>openclaw sandbox list --browser</code> stops reporting healthy browser containers as image mismatches. (#58759) Thanks @sandpile.</li>
-<li>Plugins/install: forward <code>--dangerously-force-unsafe-install</code> through archive and npm-spec plugin installs so the documented override reaches the security scanner on those install paths. (#58879) Thanks @ryanlee-gemini.</li>
-<li>Auto-reply/commands: strip inbound metadata before slash command detection so wrapped <code>/model</code>, <code>/new</code>, and <code>/status</code> commands are recognized. (#58725) Thanks @Mlightsnow.</li>
-<li>Agents/Anthropic: preserve thinking blocks and signatures across replay, cache-control patching, and context pruning so compacted Anthropic sessions continue working instead of failing on later turns. (#58916) Thanks @obviyus</li>
-<li>Agents/failover: unify structured and raw provider error classification so provider-specific <code>400</code>/<code>422</code> payloads no longer get forced into generic format failures before retry, billing, or compaction logic can inspect them. (#58856) Thanks @aaron-he-zhu.</li>
-<li>Auth profiles/store: coerce misplaced SecretRef objects out of plaintext <code>key</code> and <code>token</code> fields during store load so agents without ACP runtime stop crashing on <code>.trim()</code> after upgrade. (#58923) Thanks @openperf.</li>
-<li>ACPX/runtime: repair <code>queue owner unavailable</code> session recovery by replacing dead named sessions and resuming the backend session when ACPX exposes a stable session id, so the first ACP prompt no longer inherits a dead handle. (#58669) Thanks @neeravmakwana</li>
-<li>ACPX/runtime: retry dead-session queue-owner repair without <code>--resume-session</code> when the reported ACPX session id is stale, so recovery still creates a fresh named session instead of failing session init. Thanks @obviyus.</li>
-<li>Auth/OpenAI Codex: persist plugin-refreshed OAuth credentials to <code>auth-profiles.json</code> before returning them, so rotated Codex refresh tokens survive restart and stop falling into <code>refresh_token_reused</code> loops. (#53082)</li>
-<li>Discord/gateway: hand reconnect ownership back to Carbon, keep runtime status aligned with close/reconnect state, and force-stop sockets that open without reaching READY so Discord monitors recover promptly instead of waiting on stale health timeouts. (#59019) Thanks @obviyus</li>
-</ul>
-<p><a href="https://github.com/openclaw/openclaw/blob/main/CHANGELOG.md">View full changelog</a></p>
-]]></description>
-            <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 = 2026040901
+        versionName = "2026.4.9"
         ndk {
             // Support all major ABIs — native libs are tiny (~47 KB per ABI)
             abiFilters += listOf("armeabi-v7a", "arm64-v8a", "x86", "x86_64")

apps/android/app/src/main/java/ai/openclaw/app/MainViewModel.kt

@@ -204,6 +204,10 @@ class MainViewModel(app: Application) : AndroidViewModel(app) {
     prefs.setGatewayPassword(value)
   }
 
+  fun resetGatewaySetupAuth() {
+    ensureRuntime().resetGatewaySetupAuth()
+  }
+
   fun setOnboardingCompleted(value: Boolean) {
     if (value) {
       ensureRuntime()

apps/android/app/src/main/java/ai/openclaw/app/NodeRuntime.kt

@@ -556,6 +556,12 @@ class NodeRuntime(
   fun setGatewayToken(value: String) = prefs.setGatewayToken(value)
   fun setGatewayBootstrapToken(value: String) = prefs.setGatewayBootstrapToken(value)
   fun setGatewayPassword(value: String) = prefs.setGatewayPassword(value)
+  fun resetGatewaySetupAuth() {
+    prefs.clearGatewaySetupAuth()
+    val deviceId = identityStore.loadOrCreate().deviceId
+    deviceAuthStore.clearToken(deviceId, "node")
+    deviceAuthStore.clearToken(deviceId, "operator")
+  }
   fun setOnboardingCompleted(value: Boolean) = prefs.setOnboardingCompleted(value)
   val lastDiscoveredStableId: StateFlow<String> = prefs.lastDiscoveredStableId
   val canvasDebugStatusEnabled: StateFlow<Boolean> = prefs.canvasDebugStatusEnabled
@@ -1325,8 +1331,6 @@ internal fun resolveOperatorSessionConnectAuth(
 
   val storedToken = storedOperatorToken?.trim()?.takeIf { it.isNotEmpty() }
   if (storedToken != null) {
-    // Bootstrap can seed the operator token, but operator should reconnect
-    // through the stored device-token path rather than bootstrap auth itself.
     return NodeRuntime.GatewayConnectAuth(
       token = null,
       bootstrapToken = null,
@@ -1334,6 +1338,15 @@ internal fun resolveOperatorSessionConnectAuth(
     )
   }
 
+  val explicitBootstrapToken = auth.bootstrapToken?.trim()?.takeIf { it.isNotEmpty() }
+  if (explicitBootstrapToken != null) {
+    return NodeRuntime.GatewayConnectAuth(
+      token = null,
+      bootstrapToken = explicitBootstrapToken,
+      password = null,
+    )
+  }
+
   return null
 }
 

apps/android/app/src/main/java/ai/openclaw/app/SecurePrefs.kt

@@ -402,6 +402,18 @@ class SecurePrefs(
     securePrefs.edit { putString(key, password.trim()) }
   }
 
+  fun clearGatewaySetupAuth() {
+    val instanceId = _instanceId.value
+    securePrefs.edit {
+      remove("gateway.manual.token")
+      remove("gateway.token.$instanceId")
+      remove("gateway.bootstrapToken.$instanceId")
+      remove("gateway.password.$instanceId")
+    }
+    _gatewayToken.value = ""
+    _gatewayBootstrapToken.value = ""
+  }
+
   fun loadGatewayTlsFingerprint(stableId: String): String? {
     val key = "gateway.tls.$stableId"
     return plainPrefs.getString(key, null)?.trim()?.takeIf { it.isNotEmpty() }

apps/android/app/src/main/java/ai/openclaw/app/ui/ConnectTabScreen.kt

@@ -38,6 +38,7 @@ import androidx.compose.material3.SwitchDefaults
 import androidx.compose.material3.Text
 import androidx.compose.material3.TextButton
 import androidx.compose.runtime.Composable
+import androidx.compose.runtime.LaunchedEffect
 import androidx.compose.runtime.collectAsState
 import androidx.compose.runtime.getValue
 import androidx.compose.runtime.mutableStateOf
@@ -140,8 +141,13 @@ fun ConnectTabScreen(viewModel: MainViewModel) {
     }
 
   val showDiagnostics = !isConnected && gatewayStatusHasDiagnostics(statusText)
+  val pairingRequired = !isConnected && gatewayStatusLooksLikePairing(statusText)
   val statusLabel = gatewayStatusForDisplay(statusText)
 
+  PairingAutoRetryEffect(enabled = pairingRequired) {
+    viewModel.refreshGatewayConnection()
+  }
+
   Column(
     modifier = Modifier.verticalScroll(rememberScrollState()).padding(horizontal = 20.dp, vertical = 16.dp),
     verticalArrangement = Arrangement.spacedBy(14.dp),
@@ -278,6 +284,9 @@ fun ConnectTabScreen(viewModel: MainViewModel) {
           }
 
           validationText = null
+          if (inputMode == ConnectInputMode.SetupCode) {
+            viewModel.resetGatewaySetupAuth()
+          }
           viewModel.setManualEnabled(true)
           viewModel.setManualHost(config.host)
           viewModel.setManualPort(config.port)
@@ -319,8 +328,17 @@ fun ConnectTabScreen(viewModel: MainViewModel) {
           modifier = Modifier.fillMaxWidth().padding(horizontal = 14.dp, vertical = 14.dp),
           verticalArrangement = Arrangement.spacedBy(10.dp),
         ) {
-          Text("Last gateway error", style = mobileHeadline, color = mobileWarning)
+          Text(if (pairingRequired) "Pairing required" else "Last gateway error", style = mobileHeadline, color = mobileWarning)
           Text(statusLabel, style = mobileBody.copy(fontFamily = FontFamily.Monospace), color = mobileText)
+          if (pairingRequired) {
+            Text(
+              "Approve this phone on the gateway. OpenClaw retries automatically while this screen stays open.",
+              style = mobileCallout,
+              color = mobileTextSecondary,
+            )
+            CommandBlock("openclaw devices list")
+            CommandBlock("openclaw devices approve <requestId>")
+          }
           Text("OpenClaw Android ${openClawAndroidVersionLabel()}", style = mobileCaption1, color = mobileTextSecondary)
           Button(
             onClick = {
@@ -464,14 +482,18 @@ fun ConnectTabScreen(viewModel: MainViewModel) {
               colors = outlinedColors(),
             )
 
-            Text("Port", style = mobileCaption1.copy(fontWeight = FontWeight.SemiBold), color = mobileTextSecondary)
+            Text(
+              if (manualTlsInput) "Port (optional, defaults to 443)" else "Port",
+              style = mobileCaption1.copy(fontWeight = FontWeight.SemiBold),
+              color = mobileTextSecondary,
+            )
             OutlinedTextField(
               value = manualPortInput,
               onValueChange = {
                 manualPortInput = it
                 validationText = null
               },
-              placeholder = { Text("18789", style = mobileBody, color = mobileTextTertiary) },
+              placeholder = { Text(if (manualTlsInput) "443" else "18789", style = mobileBody, color = mobileTextTertiary) },
               modifier = Modifier.fillMaxWidth(),
               singleLine = true,
               keyboardOptions = KeyboardOptions(keyboardType = KeyboardType.Number),

apps/android/app/src/main/java/ai/openclaw/app/ui/GatewayConfigResolver.kt

@@ -235,15 +235,21 @@ internal fun gatewayEndpointValidationMessage(
       when (source) {
         GatewayEndpointInputSource.SETUP_CODE -> "Setup code has invalid gateway URL."
         GatewayEndpointInputSource.QR_SCAN -> "QR code did not contain a valid setup code."
-        GatewayEndpointInputSource.MANUAL -> "Enter a valid manual host and port to connect."
+        GatewayEndpointInputSource.MANUAL -> "Enter a valid manual endpoint to connect."
       }
   }
 }
 
 internal fun composeGatewayManualUrl(hostInput: String, portInput: String, tls: Boolean): String? {
   val host = hostInput.trim()
-  val port = portInput.trim().toIntOrNull() ?: return null
-  if (host.isEmpty() || port !in 1..65535) return null
+  if (host.isEmpty()) return null
+  val portTrimmed = portInput.trim()
+  val port = if (portTrimmed.isEmpty()) {
+    if (tls) 443 else return null
+  } else {
+    portTrimmed.toIntOrNull() ?: return null
+  }
+  if (port !in 1..65535) return null
   val scheme = if (tls) "https" else "http"
   return "$scheme://$host:$port"
 }

apps/android/app/src/main/java/ai/openclaw/app/ui/GatewayPairingRetry.kt

@@ -0,0 +1,45 @@
+package ai.openclaw.app.ui
+
+import androidx.compose.runtime.Composable
+import androidx.compose.runtime.DisposableEffect
+import androidx.compose.runtime.LaunchedEffect
+import androidx.compose.runtime.getValue
+import androidx.compose.runtime.mutableStateOf
+import androidx.compose.runtime.remember
+import androidx.compose.runtime.setValue
+import androidx.lifecycle.Lifecycle
+import androidx.lifecycle.LifecycleEventObserver
+import androidx.lifecycle.compose.LocalLifecycleOwner
+import kotlinx.coroutines.delay
+
+internal const val PAIRING_AUTO_RETRY_MS = 6_000L
+
+@Composable
+internal fun PairingAutoRetryEffect(enabled: Boolean, onRetry: () -> Unit) {
+  val lifecycleOwner = LocalLifecycleOwner.current
+  var lifecycleStarted by
+    remember(lifecycleOwner) {
+      mutableStateOf(lifecycleOwner.lifecycle.currentState.isAtLeast(Lifecycle.State.STARTED))
+    }
+
+  DisposableEffect(lifecycleOwner) {
+    val observer =
+      LifecycleEventObserver { _, _ ->
+        lifecycleStarted = lifecycleOwner.lifecycle.currentState.isAtLeast(Lifecycle.State.STARTED)
+      }
+    lifecycleOwner.lifecycle.addObserver(observer)
+    onDispose {
+      lifecycleOwner.lifecycle.removeObserver(observer)
+    }
+  }
+
+  LaunchedEffect(enabled, lifecycleStarted) {
+    if (!enabled || !lifecycleStarted) {
+      return@LaunchedEffect
+    }
+    while (true) {
+      delay(PAIRING_AUTO_RETRY_MS)
+      onRetry()
+    }
+  }
+}

apps/android/app/src/main/java/ai/openclaw/app/ui/OnboardingFlow.kt

@@ -576,6 +576,7 @@ fun OnboardingFlow(viewModel: MainViewModel, modifier: Modifier = Modifier) {
                       return@addOnSuccessListener
                     }
                     setupCode = scannedSetupCode.setupCode
+                    viewModel.resetGatewaySetupAuth()
                     gatewayInputMode = GatewayInputMode.SetupCode
                     gatewayError = null
                     attemptedConnect = false
@@ -737,6 +738,7 @@ fun OnboardingFlow(viewModel: MainViewModel, modifier: Modifier = Modifier) {
             )
           OnboardingStep.FinalCheck ->
             FinalStep(
+              viewModel = viewModel,
               parsedGateway = parseGatewayEndpoint(gatewayUrl),
               statusText = statusText,
               isConnected = canFinishOnboarding,
@@ -812,6 +814,7 @@ fun OnboardingFlow(viewModel: MainViewModel, modifier: Modifier = Modifier) {
                       )
                     return@Button
                   }
+                  viewModel.resetGatewaySetupAuth()
                   gatewayUrl = parsedSetup.url
                   viewModel.setGatewayBootstrapToken(parsedSetup.bootstrapToken.orEmpty())
                   val sharedToken = parsedSetup.token.orEmpty().trim()
@@ -887,6 +890,12 @@ fun OnboardingFlow(viewModel: MainViewModel, modifier: Modifier = Modifier) {
                   }
                   val token = persistedGatewayToken.trim()
                   val password = gatewayPassword.trim()
+                  val bootstrapToken =
+                    if (gatewayInputMode == GatewayInputMode.SetupCode) {
+                      decodeGatewaySetupCode(setupCode)?.bootstrapToken?.trim()?.ifEmpty { null }
+                    } else {
+                      null
+                    }
                   attemptedConnect = true
                   viewModel.setManualEnabled(true)
                   viewModel.setManualHost(parsed.config.host)
@@ -894,6 +903,9 @@ fun OnboardingFlow(viewModel: MainViewModel, modifier: Modifier = Modifier) {
                   viewModel.setManualTls(parsed.config.tls)
                   if (gatewayInputMode == GatewayInputMode.Manual) {
                     viewModel.setGatewayBootstrapToken("")
+                  } else {
+                    viewModel.resetGatewaySetupAuth()
+                    viewModel.setGatewayBootstrapToken(bootstrapToken.orEmpty())
                   }
                   if (token.isNotEmpty()) {
                     viewModel.setGatewayToken(token)
@@ -904,12 +916,7 @@ fun OnboardingFlow(viewModel: MainViewModel, modifier: Modifier = Modifier) {
                   viewModel.connect(
                     GatewayEndpoint.manual(host = parsed.config.host, port = parsed.config.port),
                     token = token.ifEmpty { null },
-                    bootstrapToken =
-                      if (gatewayInputMode == GatewayInputMode.SetupCode) {
-                        decodeGatewaySetupCode(setupCode)?.bootstrapToken?.trim()?.ifEmpty { null }
-                      } else {
-                        null
-                      },
+                    bootstrapToken = bootstrapToken,
                     password = password.ifEmpty { null },
                   )
                 },
@@ -1148,11 +1155,15 @@ private fun GatewayStep(
               onboardingTextFieldColors(),
           )
 
-          Text("PORT", style = onboardingCaption1Style.copy(letterSpacing = 0.9.sp), color = onboardingTextSecondary)
+          Text(
+            if (manualTls) "PORT (optional, defaults to 443)" else "PORT",
+            style = onboardingCaption1Style.copy(letterSpacing = 0.9.sp),
+            color = onboardingTextSecondary,
+          )
           OutlinedTextField(
             value = manualPort,
             onValueChange = onManualPortChange,
-            placeholder = { Text("18789", color = onboardingTextTertiary, style = onboardingBodyStyle) },
+            placeholder = { Text(if (manualTls) "443" else "18789", color = onboardingTextTertiary, style = onboardingBodyStyle) },
             modifier = Modifier.fillMaxWidth(),
             singleLine = true,
             keyboardOptions = KeyboardOptions(keyboardType = KeyboardType.Number),
@@ -1562,6 +1573,7 @@ private fun PermissionToggleRow(
 
 @Composable
 private fun FinalStep(
+  viewModel: MainViewModel,
   parsedGateway: GatewayEndpointConfig?,
   statusText: String,
   isConnected: Boolean,
@@ -1577,6 +1589,10 @@ private fun FinalStep(
   val showDiagnostics = gatewayStatusHasDiagnostics(statusText)
   val pairingRequired = gatewayStatusLooksLikePairing(statusText)
 
+  PairingAutoRetryEffect(enabled = pairingRequired && attemptedConnect) {
+    viewModel.refreshGatewayConnection()
+  }
+
   Column(verticalArrangement = Arrangement.spacedBy(10.dp)) {
     Text("Review", style = onboardingTitle1Style, color = onboardingText)
 
@@ -1757,7 +1773,11 @@ private fun FinalStep(
           if (pairingRequired) {
             CommandBlock("openclaw devices list")
             CommandBlock("openclaw devices approve <requestId>")
-            Text("Then tap Connect again.", style = onboardingCalloutStyle, color = onboardingTextSecondary)
+            Text(
+              "OpenClaw retries automatically while this screen stays open.",
+              style = onboardingCalloutStyle,
+              color = onboardingTextSecondary,
+            )
           }
         }
       }

apps/android/app/src/test/java/ai/openclaw/app/GatewayBootstrapAuthTest.kt

@@ -1,6 +1,8 @@
 package ai.openclaw.app
 
 import ai.openclaw.app.gateway.GatewayEndpoint
+import ai.openclaw.app.gateway.DeviceAuthStore
+import ai.openclaw.app.gateway.DeviceIdentityStore
 import ai.openclaw.app.gateway.GatewaySession
 import ai.openclaw.app.gateway.GatewayTlsProbeFailure
 import ai.openclaw.app.gateway.GatewayTlsProbeResult
@@ -21,14 +23,14 @@ import java.util.UUID
 @Config(sdk = [34])
 class GatewayBootstrapAuthTest {
   @Test
-  fun skipsOperatorSessionWhenOnlyBootstrapAuthExists() {
-    assertFalse(
+  fun connectsOperatorSessionWhenOnlyBootstrapAuthExists() {
+    assertTrue(
       shouldConnectOperatorSession(
         NodeRuntime.GatewayConnectAuth(token = "", bootstrapToken = "bootstrap-1", password = ""),
         storedOperatorToken = "",
       ),
     )
-    assertFalse(
+    assertTrue(
       shouldConnectOperatorSession(
         NodeRuntime.GatewayConnectAuth(token = null, bootstrapToken = "bootstrap-1", password = null),
         storedOperatorToken = null,
@@ -75,6 +77,20 @@ class GatewayBootstrapAuthTest {
     assertEquals(NodeRuntime.GatewayConnectAuth(token = null, bootstrapToken = null, password = null), resolved)
   }
 
+  @Test
+  fun resolveOperatorSessionConnectAuthUsesBootstrapWhenNoStoredOperatorTokenExists() {
+    val resolved =
+      resolveOperatorSessionConnectAuth(
+        auth = NodeRuntime.GatewayConnectAuth(token = null, bootstrapToken = "bootstrap-1", password = null),
+        storedOperatorToken = null,
+      )
+
+    assertEquals(
+      NodeRuntime.GatewayConnectAuth(token = null, bootstrapToken = "bootstrap-1", password = null),
+      resolved,
+    )
+  }
+
   @Test
   fun resolveOperatorSessionConnectAuthPrefersExplicitSharedAuth() {
     val resolved =
@@ -152,7 +168,7 @@ class GatewayBootstrapAuthTest {
 
       assertEquals("fp-1", prefs.loadGatewayTlsFingerprint(endpoint.stableId))
       assertEquals("setup-bootstrap-token", desiredBootstrapToken(runtime, "nodeSession"))
-      assertNull(desiredBootstrapToken(runtime, "operatorSession"))
+      assertEquals("setup-bootstrap-token", desiredBootstrapToken(runtime, "operatorSession"))
     }
 
   @Test
@@ -178,6 +194,33 @@ class GatewayBootstrapAuthTest {
     assertNull(runtime.pendingGatewayTrust.value)
   }
 
+  @Test
+  fun resetGatewaySetupAuth_clearsStoredGatewayAndDeviceTokens() {
+    val app = RuntimeEnvironment.getApplication()
+    val securePrefs =
+      app.getSharedPreferences(
+        "openclaw.node.secure.test.${UUID.randomUUID()}",
+        android.content.Context.MODE_PRIVATE,
+      )
+    val prefs = SecurePrefs(app, securePrefsOverride = securePrefs)
+    val runtime = NodeRuntime(app, prefs)
+    val deviceId = DeviceIdentityStore(app).loadOrCreate().deviceId
+    val authStore = DeviceAuthStore(prefs)
+    prefs.setGatewayToken("stale-shared-token")
+    prefs.setGatewayBootstrapToken("stale-bootstrap-token")
+    prefs.setGatewayPassword("stale-password")
+    authStore.saveToken(deviceId, "node", "stale-node-token")
+    authStore.saveToken(deviceId, "operator", "stale-operator-token")
+
+    runtime.resetGatewaySetupAuth()
+
+    assertNull(prefs.loadGatewayToken())
+    assertNull(prefs.loadGatewayBootstrapToken())
+    assertNull(prefs.loadGatewayPassword())
+    assertNull(authStore.loadToken(deviceId, "node"))
+    assertNull(authStore.loadToken(deviceId, "operator"))
+  }
+
   private fun waitForGatewayTrustPrompt(runtime: NodeRuntime): NodeRuntime.GatewayTrustPrompt {
     repeat(50) {
       runtime.pendingGatewayTrust.value?.let { return it }

apps/android/app/src/test/java/ai/openclaw/app/SecurePrefsTest.kt

@@ -2,6 +2,7 @@ package ai.openclaw.app
 
 import android.content.Context
 import org.junit.Assert.assertEquals
+import org.junit.Assert.assertNull
 import org.junit.Test
 import org.junit.runner.RunWith
 import org.robolectric.RobolectricTestRunner
@@ -35,4 +36,24 @@ class SecurePrefsTest {
     assertEquals("bootstrap-token", prefs.loadGatewayBootstrapToken())
     assertEquals("bootstrap-token", prefs.gatewayBootstrapToken.value)
   }
+
+  @Test
+  fun clearGatewaySetupAuth_removesStoredGatewayAuth() {
+    val context = RuntimeEnvironment.getApplication()
+    val securePrefs = context.getSharedPreferences("openclaw.node.secure.test.clear", Context.MODE_PRIVATE)
+    securePrefs.edit().clear().commit()
+    val prefs = SecurePrefs(context, securePrefsOverride = securePrefs)
+
+    prefs.setGatewayToken("shared-token")
+    prefs.setGatewayBootstrapToken("bootstrap-token")
+    prefs.setGatewayPassword("password-token")
+
+    prefs.clearGatewaySetupAuth()
+
+    assertEquals("", prefs.gatewayToken.value)
+    assertEquals("", prefs.gatewayBootstrapToken.value)
+    assertNull(prefs.loadGatewayToken())
+    assertNull(prefs.loadGatewayBootstrapToken())
+    assertNull(prefs.loadGatewayPassword())
+  }
 }

apps/android/app/src/test/java/ai/openclaw/app/ui/GatewayConfigResolverTest.kt

@@ -464,6 +464,42 @@ class GatewayConfigResolverTest {
     assertEquals(false, resolved?.tls)
   }
 
+  @Test
+  fun composeGatewayManualUrlDefaultsPortTo443WhenTlsAndPortBlank() {
+    val url = composeGatewayManualUrl("mydevice.tail1234.ts.net", "", tls = true)
+
+    assertEquals("https://mydevice.tail1234.ts.net:443", url)
+  }
+
+  @Test
+  fun composeGatewayManualUrlRejectsBlankPortWhenTlsIsOff() {
+    val url = composeGatewayManualUrl("127.0.0.1", "", tls = false)
+
+    assertNull(url)
+  }
+
+  @Test
+  fun resolveGatewayConnectConfigManualAcceptsTailscaleHostWithoutPort() {
+    val resolved =
+      resolveGatewayConnectConfig(
+        useSetupCode = false,
+        setupCode = "",
+        savedManualHost = "",
+        savedManualPort = "",
+        savedManualTls = true,
+        manualHostInput = "mydevice.tail1234.ts.net",
+        manualPortInput = "",
+        manualTlsInput = true,
+        fallbackBootstrapToken = "",
+        fallbackToken = "",
+        fallbackPassword = "",
+      )
+
+    assertEquals("mydevice.tail1234.ts.net", resolved?.host)
+    assertEquals(443, resolved?.port)
+    assertEquals(true, resolved?.tls)
+  }
+
   private fun encodeSetupCode(payloadJson: String): String {
     return Base64.getUrlEncoder().withoutPadding().encodeToString(payloadJson.toByteArray(Charsets.UTF_8))
   }

apps/ios/CHANGELOG.md

@@ -0,0 +1,13 @@
+# OpenClaw iOS Changelog
+
+## Unreleased
+
+### Added
+
+### Changed
+
+### Fixed
+
+## 2026.4.6 - 2026-04-06
+
+First App Store release of OpenClaw for iPhone. Pair with your OpenClaw Gateway to use chat, voice, sharing, and device actions from iOS.

apps/ios/Config/Version.xcconfig

@@ -1,8 +1,9 @@
 // Shared iOS version defaults.
-// Generated overrides live in build/Version.xcconfig (git-ignored).
+// Source of truth: apps/ios/version.json
+// Generated by scripts/ios-sync-versioning.ts.
 
-OPENCLAW_GATEWAY_VERSION = 2026.4.6
+OPENCLAW_IOS_VERSION = 2026.4.6
 OPENCLAW_MARKETING_VERSION = 2026.4.6
-OPENCLAW_BUILD_VERSION = 2026040601
+OPENCLAW_BUILD_VERSION = 1
 
 #include? "../build/Version.xcconfig"

apps/ios/README.md

@@ -64,10 +64,14 @@ Release behavior:
 - Beta release uses canonical `ai.openclaw.client*` bundle IDs through a temporary generated xcconfig in `apps/ios/build/BetaRelease.xcconfig`.
 - Beta release also switches the app to `OpenClawPushTransport=relay`, `OpenClawPushDistribution=official`, and `OpenClawPushAPNsEnvironment=production`.
 - The beta flow does not modify `apps/ios/.local-signing.xcconfig` or `apps/ios/LocalSigning.xcconfig`.
-- Root `package.json.version` is the only version source for iOS.
-- A root version like `2026.4.1-beta.1` becomes:
-  - `CFBundleShortVersionString = 2026.4.1`
-  - `CFBundleVersion = next TestFlight build number for 2026.4.1`
+- `apps/ios/version.json` is the pinned iOS release version source.
+- `apps/ios/CHANGELOG.md` is the iOS-only changelog and release-note source.
+- The pinned iOS version must use CalVer like `2026.4.10`.
+- That pinned value becomes:
+  - `CFBundleShortVersionString = 2026.4.10`
+  - `CFBundleVersion = next TestFlight build number for 2026.4.10`
+- Changing the root gateway version does not change the iOS app version until you explicitly pin from the gateway.
+- See `apps/ios/VERSIONING.md` for the full workflow.
 
 Required env for beta builds:
 
@@ -120,25 +124,74 @@ This should create `apps/ios/fastlane/.env` with the non-secret ASC variables wh
 export OPENCLAW_PUSH_RELAY_BASE_URL=https://relay.example.com
 ```
 
-4. Upload the beta:
+4. If you are starting a brand-new production release train, pin iOS to the current gateway version first:
+
+```bash
+pnpm ios:version:pin -- --from-gateway
+```
+
+5. Upload the beta:
 
 ```bash
 pnpm ios:beta
 ```
 
-5. Expected behavior:
-   - Fastlane reads `package.json.version`
+6. Expected behavior:
+   - Fastlane reads `apps/ios/version.json`
+   - verifies synced iOS versioning artifacts
    - resolves the next TestFlight build number for that short version
    - generates `apps/ios/build/BetaRelease.xcconfig`
    - archives `OpenClaw`
    - uploads the IPA to TestFlight
 
-6. Expected outputs after a successful run:
+7. Expected outputs after a successful run:
    - `apps/ios/build/beta/OpenClaw-<version>.ipa`
    - `apps/ios/build/beta/OpenClaw-<version>.app.dSYM.zip`
    - Fastlane log line like `Uploaded iOS beta: version=<version> short=<short> build=<build>`
 
-7. If this is a fresh clone on a maintainer machine that already works elsewhere, it is OK to copy the non-secret `apps/ios/fastlane/.env` from another trusted local clone on the same Mac. The Keychain-backed private key remains machine-local and is not stored in the repo.
+8. If this is a fresh clone on a maintainer machine that already works elsewhere, it is OK to copy the non-secret `apps/ios/fastlane/.env` from another trusted local clone on the same Mac. The Keychain-backed private key remains machine-local and is not stored in the repo.
+
+## iOS Versioning Workflow
+
+- Pinned iOS release version: `apps/ios/version.json`
+- iOS-only changelog: `apps/ios/CHANGELOG.md`
+- Generated checked-in artifacts:
+  - `apps/ios/Config/Version.xcconfig`
+  - `apps/ios/fastlane/metadata/en-US/release_notes.txt`
+- Useful commands:
+
+```bash
+pnpm ios:version
+pnpm ios:version:check
+pnpm ios:version:sync
+pnpm ios:version:pin -- --from-gateway
+pnpm ios:version:pin -- --version 2026.4.10
+```
+
+Recommended flow:
+
+### TestFlight iteration on an existing train
+
+1. Keep `apps/ios/version.json` pinned to the current train version.
+2. Update `apps/ios/CHANGELOG.md`, usually under `## Unreleased` while iterating.
+3. Run `pnpm ios:version:sync` after changelog changes.
+4. Upload more TestFlight builds with `pnpm ios:beta`.
+5. Let Fastlane bump only the numeric build number.
+
+### Starting the next production release train
+
+1. Pin iOS to the current gateway version:
+
+```bash
+pnpm ios:version:pin -- --from-gateway
+```
+
+2. Update `apps/ios/CHANGELOG.md` for the new release as needed.
+3. Run `pnpm ios:version:sync`.
+4. Submit the first TestFlight build for that newly pinned version.
+5. Keep iterating on that same version until the release candidate is ready.
+
+See `apps/ios/VERSIONING.md` for the detailed spec.
 
 ## APNs Expectations For Local/Manual Builds
 

apps/ios/Sources/Device/DeviceInfoHelper.swift

@@ -50,9 +50,11 @@ enum DeviceInfoHelper {
         return trimmed.isEmpty ? "unknown" : trimmed
     }
 
-    /// App marketing version only, e.g. "2026.2.0" or "dev".
+    /// Canonical app version when present, otherwise the Apple marketing version.
     static func appVersion() -> String {
-        Bundle.main.infoDictionary?["CFBundleShortVersionString"] as? String ?? "dev"
+        (Bundle.main.infoDictionary?["OpenClawCanonicalVersion"] as? String)
+            ?? (Bundle.main.infoDictionary?["CFBundleShortVersionString"] as? String)
+            ?? "dev"
     }
 
     /// App build string, e.g. "123" or "".

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/Info.plist

@@ -24,6 +24,8 @@
 	<string>APPL</string>
 	<key>CFBundleShortVersionString</key>
 	<string>$(OPENCLAW_MARKETING_VERSION)</string>
+	<key>OpenClawCanonicalVersion</key>
+	<string>$(OPENCLAW_IOS_VERSION)</string>
 	<key>CFBundleURLTypes</key>
 	<array>
 		<dict>

apps/ios/Sources/Model/NodeAppModel.swift

@@ -120,6 +120,10 @@ final class NodeAppModel {
     // multiple pending requests and cause the onboarding UI to "flip-flop".
     var gatewayPairingPaused: Bool = false
     var gatewayPairingRequestId: String?
+    private(set) var lastGatewayProblem: GatewayConnectionProblem?
+    var gatewayDisplayStatusText: String {
+        self.lastGatewayProblem?.statusText ?? self.gatewayStatusText
+    }
     var seamColorHex: String?
     private var mainSessionBaseKey: String = "main"
     var selectedAgentId: String?
@@ -1815,6 +1819,7 @@ extension NodeAppModel {
         self.gatewayAutoReconnectEnabled = false
         self.gatewayPairingPaused = false
         self.gatewayPairingRequestId = nil
+        self.lastGatewayProblem = nil
         self.nodeGatewayTask?.cancel()
         self.nodeGatewayTask = nil
         self.operatorGatewayTask?.cancel()
@@ -1848,6 +1853,7 @@ private extension NodeAppModel {
         self.gatewayAutoReconnectEnabled = true
         self.gatewayPairingPaused = false
         self.gatewayPairingRequestId = nil
+        self.lastGatewayProblem = nil
         self.nodeGatewayTask?.cancel()
         self.operatorGatewayTask?.cancel()
         self.gatewayHealthMonitor.stop()
@@ -1866,6 +1872,38 @@ private extension NodeAppModel {
         self.apnsLastRegisteredTokenHex = nil
     }
 
+    func clearGatewayConnectionProblem() {
+        self.lastGatewayProblem = nil
+        self.gatewayPairingPaused = false
+        self.gatewayPairingRequestId = nil
+    }
+
+    func applyGatewayConnectionProblem(_ problem: GatewayConnectionProblem) {
+        self.lastGatewayProblem = problem
+        self.gatewayStatusText = problem.statusText
+        self.gatewayServerName = nil
+        self.gatewayRemoteAddress = nil
+        self.gatewayConnected = false
+        self.showLocalCanvasOnDisconnect()
+        if problem.pauseReconnect {
+            self.gatewayAutoReconnectEnabled = false
+        }
+        if problem.needsPairingApproval {
+            self.gatewayPairingPaused = true
+            self.gatewayPairingRequestId = problem.requestId
+        } else {
+            self.gatewayPairingPaused = false
+            self.gatewayPairingRequestId = nil
+        }
+    }
+
+    func shouldKeepGatewayProblemStatus(forDisconnectReason reason: String) -> Bool {
+        guard let lastGatewayProblem else { return false }
+        return GatewayConnectionProblemMapper.shouldPreserve(
+            previousProblem: lastGatewayProblem,
+            overDisconnectReason: reason)
+    }
+
     func shouldStartOperatorGatewayLoop(
         token: String?,
         bootstrapToken: String?,
@@ -2162,6 +2200,7 @@ private extension NodeAppModel {
                         onConnected: { [weak self] in
                             guard let self else { return }
                             await MainActor.run {
+                                self.clearGatewayConnectionProblem()
                                 self.gatewayStatusText = "Connected"
                                 self.gatewayServerName = url.host ?? "gateway"
                                 self.gatewayConnected = true
@@ -2218,7 +2257,13 @@ private extension NodeAppModel {
                         onDisconnected: { [weak self] reason in
                             guard let self else { return }
                             await MainActor.run {
-                                self.gatewayStatusText = "Disconnected: \(reason)"
+                                if self.shouldKeepGatewayProblemStatus(forDisconnectReason: reason),
+                                   let lastGatewayProblem = self.lastGatewayProblem
+                                {
+                                    self.gatewayStatusText = lastGatewayProblem.statusText
+                                } else {
+                                    self.gatewayStatusText = "Disconnected: \(reason)"
+                                }
                                 self.gatewayServerName = nil
                                 self.gatewayRemoteAddress = nil
                                 self.gatewayConnected = false
@@ -2257,50 +2302,25 @@ private extension NodeAppModel {
                     }
 
                     attempt += 1
-                    await MainActor.run {
-                        self.gatewayStatusText = "Gateway error: \(error.localizedDescription)"
-                        self.gatewayServerName = nil
-                        self.gatewayRemoteAddress = nil
-                        self.gatewayConnected = false
-                        self.showLocalCanvasOnDisconnect()
+                    let problem = await MainActor.run {
+                        let nextProblem = GatewayConnectionProblemMapper.map(
+                            error: error,
+                            preserving: self.lastGatewayProblem)
+                        if let nextProblem {
+                            self.applyGatewayConnectionProblem(nextProblem)
+                        } else {
+                            self.lastGatewayProblem = nil
+                            self.gatewayStatusText = "Gateway error: \(error.localizedDescription)"
+                            self.gatewayServerName = nil
+                            self.gatewayRemoteAddress = nil
+                            self.gatewayConnected = false
+                            self.showLocalCanvasOnDisconnect()
+                        }
+                        return nextProblem
                     }
                     GatewayDiagnostics.log("gateway connect error: \(error.localizedDescription)")
 
-                    // If auth is missing/rejected, pause reconnect churn until the user intervenes.
-                    // Reconnect loops only spam the same failing handshake and make onboarding noisy.
-                    let lower = error.localizedDescription.lowercased()
-                    if lower.contains("unauthorized") || lower.contains("gateway token missing") {
-                        await MainActor.run {
-                            self.gatewayAutoReconnectEnabled = false
-                        }
-                    }
-
-                    // If pairing is required, stop reconnect churn. The user must approve the request
-                    // on the gateway before another connect attempt will succeed, and retry loops can
-                    // generate multiple pending requests.
-                    if lower.contains("not_paired") || lower.contains("pairing required") {
-                        let requestId: String? = {
-                            // GatewayResponseError for connect decorates the message with `(requestId: ...)`.
-                            // Keep this resilient since other layers may wrap the text.
-                            let text = error.localizedDescription
-                            guard let start = text.range(of: "(requestId: ")?.upperBound else { return nil }
-                            guard let end = text[start...].firstIndex(of: ")") else { return nil }
-                            let raw = String(text[start..<end]).trimmingCharacters(in: .whitespacesAndNewlines)
-                            return raw.isEmpty ? nil : raw
-                        }()
-                        await MainActor.run {
-                            self.gatewayAutoReconnectEnabled = false
-                            self.gatewayPairingPaused = true
-                            self.gatewayPairingRequestId = requestId
-                            if let requestId, !requestId.isEmpty {
-                                self.gatewayStatusText =
-                                    "Pairing required (requestId: \(requestId)). "
-                                        + "Approve on gateway and return to OpenClaw."
-                            } else {
-                                self.gatewayStatusText =
-                                    "Pairing required. Approve on gateway and return to OpenClaw."
-                            }
-                        }
+                    if problem?.needsPairingApproval == true {
                         // Hard stop the underlying WebSocket watchdog reconnects so the UI stays stable and
                         // we don't generate multiple pending requests while waiting for approval.
                         pausedForPairingApproval = true
@@ -2311,6 +2331,10 @@ private extension NodeAppModel {
                         break
                     }
 
+                    if problem?.pauseReconnect == true {
+                        continue
+                    }
+
                     let sleepSeconds = min(8.0, 0.5 * pow(1.7, Double(attempt)))
                     try? await Task.sleep(nanoseconds: UInt64(sleepSeconds * 1_000_000_000))
                 }
@@ -2322,6 +2346,7 @@ private extension NodeAppModel {
             }
 
             await MainActor.run {
+                self.lastGatewayProblem = nil
                 self.gatewayStatusText = "Offline"
                 self.gatewayServerName = nil
                 self.gatewayRemoteAddress = nil

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/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/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/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/VERSIONING.md

@@ -0,0 +1,150 @@
+# OpenClaw iOS Versioning
+
+OpenClaw iOS uses a **pinned CalVer release version** instead of reading the current gateway version automatically on every build.
+
+## Goals
+
+- keep TestFlight submissions on one stable app version while iterating
+- change only `CFBundleVersion` during normal TestFlight iteration
+- promote the iOS release version to the current gateway version only when a maintainer chooses to do that
+- keep Apple bundle fields valid for App Store Connect
+- generate App Store release notes from an iOS-owned changelog
+
+## Version model
+
+The pinned iOS release version lives in `apps/ios/version.json`.
+
+Supported pinned format:
+
+- `YYYY.M.D`
+
+Examples:
+
+- `2026.4.6`
+- `2026.4.10`
+
+The root gateway version in `package.json` may still be one of:
+
+- `YYYY.M.D`
+- `YYYY.M.D-beta.N`
+- `YYYY.M.D-N`
+
+When you pin iOS from the gateway version, the iOS tooling strips the gateway suffix and keeps only the base CalVer.
+
+Examples:
+
+- gateway `2026.4.10` -> iOS `2026.4.10`
+- gateway `2026.4.10-beta.3` -> iOS `2026.4.10`
+- gateway `2026.4.10-2` -> iOS `2026.4.10`
+
+## Apple bundle mapping
+
+Pinned iOS version `2026.4.10` maps to:
+
+- `CFBundleShortVersionString = 2026.4.10`
+- `CFBundleVersion = numeric build number only`
+
+`CFBundleShortVersionString` stays fixed for a TestFlight train until you intentionally pin a newer iOS release version.
+
+## Source of truth and generated files
+
+### Source files
+
+- `apps/ios/version.json`
+  - pinned iOS release version
+- `apps/ios/CHANGELOG.md`
+  - iOS-only changelog and release-note source
+- `apps/ios/VERSIONING.md`
+  - workflow and constraints
+
+### Generated or derived files
+
+- `apps/ios/Config/Version.xcconfig`
+  - checked-in defaults derived from `apps/ios/version.json`
+- `apps/ios/fastlane/metadata/en-US/release_notes.txt`
+  - generated from `apps/ios/CHANGELOG.md`
+- `apps/ios/build/Version.xcconfig`
+  - local gitignored build override generated per build or beta prep
+
+## Tooling surfaces
+
+### Version parsing and sync tooling
+
+- `scripts/lib/ios-version.ts`
+  - validates pinned iOS CalVer
+  - normalizes gateway version -> pinned iOS CalVer
+  - renders checked-in xcconfig and release notes
+- `scripts/ios-version.ts`
+  - CLI for JSON, shell, or single-field version reads
+- `scripts/ios-sync-versioning.ts`
+  - syncs checked-in derived files from the pinned iOS version
+- `scripts/ios-pin-version.ts`
+  - explicitly pins iOS to a chosen release version or the current gateway version
+
+### Build and beta flow
+
+- `scripts/ios-write-version-xcconfig.sh`
+  - reads the pinned iOS version
+  - writes the local numeric build override file in `apps/ios/build/Version.xcconfig`
+- `scripts/ios-beta-prepare.sh`
+  - prepares beta signing and bundle settings against the pinned iOS version
+- `apps/ios/fastlane/Fastfile`
+  - resolves version metadata from the pinned iOS helper
+  - increments TestFlight build numbers for the pinned short version
+
+## Release-note resolution order
+
+When generating `apps/ios/fastlane/metadata/en-US/release_notes.txt`, the tooling reads the first available changelog section in this order:
+
+1. exact pinned version, for example `## 2026.4.10`
+2. `## Unreleased`
+
+Recommended workflow:
+
+- while iterating on a TestFlight train, keep pending notes under `## Unreleased`
+- before the production release, move or copy the final notes under `## <pinned version>` and run sync again
+
+## Common commands
+
+```bash
+pnpm ios:version
+pnpm ios:version:check
+pnpm ios:version:sync
+pnpm ios:version:pin -- --from-gateway
+pnpm ios:version:pin -- --version 2026.4.10
+```
+
+## Normal TestFlight iteration workflow
+
+1. keep `apps/ios/version.json` pinned to the current TestFlight train version
+2. update `apps/ios/CHANGELOG.md` under `## Unreleased` while iterating
+3. upload more betas with the usual flow
+4. let Fastlane increment only `CFBundleVersion`
+
+This keeps the TestFlight version stable while review is in flight.
+
+## New release promotion workflow
+
+When you want the next production iOS release to align with the current gateway release:
+
+1. pin iOS from the root gateway version:
+
+```bash
+pnpm ios:version:pin -- --from-gateway
+```
+
+2. review the generated changes in:
+   - `apps/ios/version.json`
+   - `apps/ios/Config/Version.xcconfig`
+   - `apps/ios/fastlane/metadata/en-US/release_notes.txt`
+3. update `apps/ios/CHANGELOG.md` for the new release if needed
+4. run `pnpm ios:version:sync` again if the changelog changed
+5. submit the first TestFlight build for that newly pinned version
+6. keep iterating only by build number until the release candidate is ready
+7. release that reviewed TestFlight build to production
+
+## Important invariant
+
+Fastlane and Xcode should consume only the pinned iOS version from `apps/ios/version.json`.
+
+Changing `package.json.version` alone must not change the iOS app version until a maintainer explicitly runs the pin step.

apps/ios/fastlane/Fastfile

@@ -95,35 +95,60 @@ def ios_root
   File.expand_path("..", __dir__)
 end
 
-def normalize_release_version(raw_value)
-  version = raw_value.to_s.strip.sub(/\Av/, "")
-  UI.user_error!("Missing root package.json version.") unless env_present?(version)
-  unless version.match?(/\A\d+\.\d+\.\d+(?:[.-]?beta[.-]\d+)?\z/i)
-    UI.user_error!("Invalid package.json version '#{raw_value}'. Expected YYYY.M.D or YYYY.M.D-beta.N.")
+def read_ios_version_metadata
+  script_path = File.join(repo_root, "scripts", "ios-version.ts")
+  stdout, stderr, status = Open3.capture3(
+    "node",
+    "--import",
+    "tsx",
+    script_path,
+    "--json",
+    chdir: repo_root
+  )
+
+  unless status.success?
+    detail = stderr.to_s.strip
+    detail = stdout.to_s.strip if detail.empty?
+    UI.user_error!("Failed to read iOS version metadata: #{detail}")
   end
 
-  version
-end
+  parsed = JSON.parse(stdout)
+  version = parsed["canonicalVersion"].to_s.strip
+  short_version = parsed["marketingVersion"].to_s.strip
+  if !env_present?(version) || !env_present?(short_version)
+    UI.user_error!("iOS version helper returned incomplete metadata.")
+  end
 
-def read_root_package_version
-  package_json_path = File.join(repo_root, "package.json")
-  UI.user_error!("Missing package.json at #{package_json_path}.") unless File.exist?(package_json_path)
-
-  parsed = JSON.parse(File.read(package_json_path))
-  normalize_release_version(parsed["version"])
+  {
+    short_version: short_version,
+    version: version
+  }
 rescue JSON::ParserError => e
-  UI.user_error!("Invalid package.json at #{package_json_path}: #{e.message}")
+  UI.user_error!("Invalid JSON from iOS version helper: #{e.message}")
 end
 
-def short_release_version(version)
-  normalize_release_version(version).sub(/([.-]?beta[.-]\d+)\z/i, "")
+def sync_ios_versioning!
+  script_path = File.join(repo_root, "scripts", "ios-sync-versioning.ts")
+  stdout, stderr, status = Open3.capture3(
+    "node",
+    "--import",
+    "tsx",
+    script_path,
+    "--check",
+    chdir: repo_root
+  )
+  return if status.success?
+
+  detail = stderr.to_s.strip
+  detail = stdout.to_s.strip if detail.empty?
+  UI.user_error!("iOS versioning artifacts are stale. Run `pnpm ios:version:sync`.\n#{detail}")
 end
 
 def shell_join(parts)
   Shellwords.join(parts.compact)
 end
 
-def resolve_beta_build_number(api_key:, version:)
+def resolve_beta_build_number(api_key:, short_version:)
   explicit = ENV["IOS_BETA_BUILD_NUMBER"]
   if env_present?(explicit)
     UI.user_error!("Invalid IOS_BETA_BUILD_NUMBER '#{explicit}'. Expected digits only.") unless explicit.match?(/\A\d+\z/)
@@ -131,7 +156,6 @@ def resolve_beta_build_number(api_key:, version:)
     return explicit
   end
 
-  short_version = short_release_version(version)
   latest_build = latest_testflight_build_number(
     api_key: api_key,
     app_identifier: BETA_APP_IDENTIFIER,
@@ -244,15 +268,18 @@ platform :ios do
     require_api_key = options[:require_api_key] == true
     needs_api_key = require_api_key || beta_build_number_needs_asc_auth?
     api_key = needs_api_key ? asc_api_key : nil
-    version = read_root_package_version
-    build_number = resolve_beta_build_number(api_key: api_key, version: version)
+    sync_ios_versioning!
+    version_metadata = read_ios_version_metadata
+    version = version_metadata[:version]
+    short_version = version_metadata[:short_version]
+    build_number = resolve_beta_build_number(api_key: api_key, short_version: short_version)
     beta_xcconfig = prepare_beta_release!(version: version, build_number: build_number)
 
     {
       api_key: api_key,
       beta_xcconfig: beta_xcconfig,
       build_number: build_number,
-      short_version: short_release_version(version),
+      short_version: short_version,
       version: version
     }
   end
@@ -286,6 +313,7 @@ platform :ios do
 
   desc "Upload App Store metadata (and optionally screenshots)"
   lane :metadata do
+    sync_ios_versioning!
     api_key = asc_api_key
     clear_empty_env_var("APP_STORE_CONNECT_API_KEY_PATH")
     app_identifier = ENV["ASC_APP_IDENTIFIER"]

apps/ios/fastlane/SETUP.md

@@ -109,13 +109,19 @@ cd apps/ios
 fastlane ios auth_check
 ```
 
-4. Set the official/TestFlight relay URL before release:
+4. If you are starting a brand-new production release train, pin iOS to the current gateway version:
+
+```bash
+pnpm ios:version:pin -- --from-gateway
+```
+
+5. Set the official/TestFlight relay URL before release:
 
 ```bash
 export OPENCLAW_PUSH_RELAY_BASE_URL=https://relay.example.com
 ```
 
-5. Upload:
+6. Upload:
 
 ```bash
 pnpm ios:beta
@@ -129,9 +135,15 @@ Quick verification after upload:
 
 Versioning rules:
 
-- Root `package.json.version` is the single source of truth for iOS
-- Use `YYYY.M.D` for stable versions and `YYYY.M.D-beta.N` for beta versions
-- Fastlane stamps `CFBundleShortVersionString` to `YYYY.M.D`
+- `apps/ios/version.json` is the pinned iOS release version source
+- `apps/ios/CHANGELOG.md` is the iOS-only changelog and release-note source
+- Supported pinned iOS versions use CalVer: `YYYY.M.D`
+- `pnpm ios:version:pin -- --from-gateway` promotes the current root gateway version into the pinned iOS release version
+- Fastlane uses the pinned iOS version only; changing `package.json.version` alone does not change the iOS app version
+- Fastlane sets `CFBundleShortVersionString` to the pinned iOS version, for example `2026.4.10`
 - Fastlane resolves `CFBundleVersion` as the next integer TestFlight build number for that short version
+- Run `pnpm ios:version:sync` after changing `apps/ios/version.json` or `apps/ios/CHANGELOG.md`
+- `pnpm ios:version:check` validates that checked-in iOS version artifacts are in sync
 - The beta flow regenerates `apps/ios/OpenClaw.xcodeproj` from `apps/ios/project.yml` before archiving
 - Local beta signing uses a temporary generated xcconfig and leaves local development signing overrides untouched
+- See `apps/ios/VERSIONING.md` for the detailed workflow

apps/ios/fastlane/metadata/README.md

@@ -36,6 +36,9 @@ Or set `APP_STORE_CONNECT_API_KEY_PATH`.
 ## Notes
 
 - Locale files live under `metadata/en-US/`.
+- `release_notes.txt` is generated from `apps/ios/CHANGELOG.md`; after changelog updates, run `pnpm ios:version:sync`.
+- Release notes resolve from `## <pinned iOS version>` first, then fall back to `## Unreleased` while a TestFlight train is still in progress.
+- When starting a new production release train, pin the iOS version first with `pnpm ios:version:pin -- --from-gateway`.
 - `privacy_url.txt` is set to `https://openclaw.ai/privacy`.
 - If app lookup fails in `deliver`, set one of:
   - `ASC_APP_IDENTIFIER` (bundle ID)

apps/ios/project.yml

@@ -119,6 +119,7 @@ targets:
             CFBundleURLSchemes:
               - openclaw
         CFBundleShortVersionString: "$(OPENCLAW_MARKETING_VERSION)"
+        OpenClawCanonicalVersion: "$(OPENCLAW_IOS_VERSION)"
         CFBundleVersion: "$(OPENCLAW_BUILD_VERSION)"
         UILaunchScreen: {}
         UIApplicationSceneManifest:

apps/ios/version.json

@@ -0,0 +1,3 @@
+{
+  "version": "2026.4.6"
+}

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

@@ -6,165 +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",
-        "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",
-        "MAKEFLAGS",
-        "MFLAGS",
-        "SBT_OPTS",
-        "GRADLE_OPTS",
-        "ANT_OPTS",
-        "HGRCPATH"
+        "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",
-        "MAKEFLAGS",
-        "MFLAGS",
+        "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",
-        "HGRCPATH",
-        "PYTHONUSERBASE",
-        "RUSTC_WRAPPER",
         "VIRTUAL_ENV",
-        "LUA_PATH",
-        "LUA_CPATH",
-        "GEM_HOME",
-        "GEM_PATH",
-        "BUNDLE_GEMFILE",
-        "COMPOSER_HOME",
-        "CARGO_BUILD_RUSTC_WRAPPER",
+        "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>2026.4.9</string>
     <key>CFBundleVersion</key>
-    <string>2026040601</string>
+    <string>2026040901</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"

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/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"

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 @@
-64ff922efc6146d867f3858141772094a8a72cba99a8fd61878551175dd8c822  config-baseline.json
-5d0ce975352ff2b03077f6d71e9fe99ab0f0b118da0f72d47dc989c83f13d668  config-baseline.core.json
-d22f4414b79ee03d896e58d875c80523bcc12303cbacb1700261e6ec73945187  config-baseline.channel.json
-1891bcb68d80ab8b7546a2946b5a9d82b18c3e92ffd2c834d15928e73fa11564  config-baseline.plugin.json
+0a75b57f5dbb0bb1488eacb47111ee22ff42dd3747bfe07bb69c9445d5e55c3e  config-baseline.json
+ff15bb8b4231fc80174249ae89bcb61439d7adda5ee6be95e4d304680253a59f  config-baseline.core.json
+7f42b22b46c487d64aaac46001ba9d9096cf7bf0b1c263a54d39946303ff5018  config-baseline.channel.json
+483d4f3c1d516719870ad6f2aba6779b9950f85471ee77b9994a077a7574a892  config-baseline.plugin.json

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

@@ -1,2 +1,2 @@
-3d483bffbe5abb831df3b1efdf40e1ae0d22d644853a7629ecdaa6d535386ee6  plugin-sdk-api-baseline.json
-eebeff7cc3ca490d3cae268ea97c5968f37f50fe1a9c7eabeeab85a4ae66a9d9  plugin-sdk-api-baseline.jsonl
+763d2709dd26f4ec7d5807b2f1781b7f58cb115d2b0a9c9235a6c2c7b3788c1f  plugin-sdk-api-baseline.json
+87ab9ec219f037b13a8f42378d1fed02701d4035da0e5eca8a091626e8426523  plugin-sdk-api-baseline.jsonl

docs/.i18n/glossary.zh-CN.json

@@ -183,6 +183,14 @@
     "source": "Doctor",
     "target": "Doctor"
   },
+  {
+    "source": "Memory Wiki",
+    "target": "Memory Wiki"
+  },
+  {
+    "source": "wiki",
+    "target": "wiki"
+  },
   {
     "source": "Polls",
     "target": "投票"

docs/channels/discord.md

@@ -1003,6 +1003,8 @@ Core examples:
 - moderation: `timeout`, `kick`, `ban`
 - presence: `setPresence`
 
+The `event-create` action accepts an optional `image` parameter (URL or local file path) to set the scheduled event cover image.
+
 Action gates live under `channels.discord.actions.*`.
 
 Default gate behavior:

docs/channels/matrix.md

@@ -8,7 +8,7 @@ title: "Matrix"
 
 # Matrix
 
-Matrix is the Matrix bundled channel plugin for OpenClaw.
+Matrix is a bundled channel plugin for OpenClaw.
 It uses the official `matrix-js-sdk` and supports DMs, rooms, threads, media, reactions, polls, location, and E2EE.
 
 ## Bundled plugin
@@ -53,27 +53,23 @@ openclaw channels add
 openclaw configure --section channels
 ```
 
-What the Matrix wizard actually asks for:
+The Matrix wizard asks for:
 
 - homeserver URL
 - auth method: access token or password
-- user ID only when you choose password auth
+- user ID (password auth only)
 - 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`
+- whether to configure room access and invite auto-join
 
-Wizard behavior that matters:
+Key wizard behaviors:
 
-- 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.
+- If Matrix auth env vars already exist and that account does not already have auth saved in config, the wizard offers an env shortcut to keep auth in env vars.
+- Account names are normalized to the account ID. For example, `Ops Bot` becomes `ops-bot`.
+- DM allowlist entries accept `@user:server` directly; display names only work when live directory lookup finds one exact match.
+- Room allowlist entries accept room IDs and aliases directly. Prefer `!room:server` or `#alias:server`; unresolved names are ignored at runtime by allowlist resolution.
 - 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"`.
+- To resolve room names before saving, use `openclaw channels resolve --channel matrix "Project Room"`.
 
 <Warning>
 `channels.matrix.autoJoin` defaults to `off`.
@@ -220,12 +216,9 @@ This is a practical baseline config with DM pairing, room allowlist, and E2EE en
 }
 ```
 
-`autoJoin` applies to Matrix invites in general, not only room/group invites.
-That includes fresh DM-style invites. At invite time, OpenClaw does not reliably know whether the
-invited room will end up being treated as a DM or a group, so all invites go through the same
-`autoJoin` decision first. `dm.policy` still applies after the bot has joined and the room is
-classified as a DM, so `autoJoin` controls join behavior while `dm.policy` controls reply/access
-behavior.
+`autoJoin` applies to all Matrix invites, including DM-style invites. OpenClaw cannot reliably
+classify an invited room as a DM or group at invite time, so all invites go through `autoJoin`
+first. `dm.policy` applies after the bot has joined and the room is classified as a DM.
 
 ## Streaming previews
 
@@ -420,11 +413,7 @@ For Tuwunel, use the same setup flow and push-rule API call shown above:
 - If normal Matrix notifications already work for that user, the user token + `pushrules` call above is the main setup step.
 - If notifications seem to disappear while the user is active on another device, check whether `suppress_push_when_active` is enabled. Tuwunel added this option in Tuwunel 1.4.2 on September 12, 2025, and it can intentionally suppress pushes to other devices while one device is active.
 
-## Encryption and verification
-
-In encrypted (E2EE) rooms, outbound image events use `thumbnail_file` so image previews are encrypted alongside the full attachment. Unencrypted rooms still use plain `thumbnail_url`. No configuration is needed — the plugin detects E2EE state automatically.
-
-### Bot to bot rooms
+## Bot-to-bot rooms
 
 By default, Matrix messages from other configured OpenClaw Matrix accounts are ignored.
 
@@ -453,6 +442,10 @@ Use `allowBots` when you intentionally want inter-agent Matrix traffic:
 
 Use strict room allowlists and mention requirements when enabling bot-to-bot traffic in shared rooms.
 
+## Encryption and verification
+
+In encrypted (E2EE) rooms, outbound image events use `thumbnail_file` so image previews are encrypted alongside the full attachment. Unencrypted rooms still use plain `thumbnail_url`. No configuration is needed — the plugin detects E2EE state automatically.
+
 Enable encryption:
 
 ```json5
@@ -493,8 +486,6 @@ Bootstrap cross-signing and verification state:
 openclaw matrix verify bootstrap
 ```
 
-Multi-account support: use `channels.matrix.accounts` with per-account credentials and optional `name`. See [Configuration reference](/gateway/configuration-reference#multi-account-all-channels) for the shared pattern.
-
 Verbose bootstrap diagnostics:
 
 ```bash
@@ -625,64 +616,11 @@ That pass tries to reuse the current secret storage and cross-signing identity f
 If startup finds broken bootstrap state and `channels.matrix.password` is configured, OpenClaw can attempt a stricter repair path.
 If the current device is already owner-signed, OpenClaw preserves that identity instead of resetting it automatically.
 
-Upgrading from the previous public Matrix plugin:
+See [Matrix migration](/install/migrating-matrix) for the full upgrade flow, limits, recovery commands, and common migration messages.
 
-- OpenClaw automatically reuses the same Matrix account, access token, and device identity when possible.
-- Before any actionable Matrix migration changes run, OpenClaw creates or reuses a recovery snapshot under `~/Backups/openclaw-migrations/`.
-- If you use multiple Matrix accounts, set `channels.matrix.defaultAccount` before upgrading from the old flat-store layout so OpenClaw knows which account should receive that shared legacy state.
-- If the previous plugin stored a Matrix room-key backup decryption key locally, startup or `openclaw doctor --fix` will import it into the new recovery-key flow automatically.
-- If the Matrix access token changed after migration was prepared, startup now scans sibling token-hash storage roots for pending legacy restore state before giving up on the automatic backup restore.
-- If the Matrix access token changes later for the same account, homeserver, and user, OpenClaw now prefers reusing the most complete existing token-hash storage root instead of starting from an empty Matrix state directory.
-- On the next gateway start, backed-up room keys are restored automatically into the new crypto store.
-- If the old plugin had local-only room keys that were never backed up, OpenClaw will warn clearly. Those keys cannot be exported automatically from the previous rust crypto store, so some old encrypted history may remain unavailable until recovered manually.
-- See [Matrix migration](/install/migrating-matrix) for the full upgrade flow, limits, recovery commands, and common migration messages.
+### Verification notices
 
-Encrypted runtime state is organized under per-account, per-user token-hash roots in
-`~/.openclaw/matrix/accounts/<account>/<homeserver>__<user>/<token-hash>/`.
-That directory contains the sync store (`bot-storage.json`), crypto store (`crypto/`),
-recovery key file (`recovery-key.json`), IndexedDB snapshot (`crypto-idb-snapshot.json`),
-thread bindings (`thread-bindings.json`), and startup verification state (`startup-verification.json`)
-when those features are in use.
-When the token changes but the account identity stays the same, OpenClaw reuses the best existing
-root for that account/homeserver/user tuple so prior sync state, crypto state, thread bindings,
-and startup verification state remain visible.
-
-### Node crypto store model
-
-Matrix E2EE in this plugin uses the official `matrix-js-sdk` Rust crypto path in Node.
-That path expects IndexedDB-backed persistence when you want crypto state to survive restarts.
-
-OpenClaw currently provides that in Node by:
-
-- using `fake-indexeddb` as the IndexedDB API shim expected by the SDK
-- restoring the Rust crypto IndexedDB contents from `crypto-idb-snapshot.json` before `initRustCrypto`
-- persisting the updated IndexedDB contents back to `crypto-idb-snapshot.json` after init and during runtime
-- serializing snapshot restore and persist against `crypto-idb-snapshot.json` with an advisory file lock so gateway runtime persistence and CLI maintenance do not race on the same snapshot file
-
-This is compatibility/storage plumbing, not a custom crypto implementation.
-The snapshot file is sensitive runtime state and is stored with restrictive file permissions.
-Under OpenClaw's security model, the gateway host and local OpenClaw state directory are already inside the trusted operator boundary, so this is primarily an operational durability concern rather than a separate remote trust boundary.
-
-Planned improvement:
-
-- add SecretRef support for persistent Matrix key material so recovery keys and related store-encryption secrets can be sourced from OpenClaw secrets providers instead of only local files
-
-## Profile management
-
-Update the Matrix self-profile for the selected account with:
-
-```bash
-openclaw matrix profile set --name "OpenClaw Assistant"
-openclaw matrix profile set --avatar-url https://cdn.example.org/avatar.png
-```
-
-Add `--account <id>` when you want to target a named Matrix account explicitly.
-
-Matrix accepts `mxc://` avatar URLs directly. When you pass an `http://` or `https://` avatar URL, OpenClaw uploads it to Matrix first and stores the resolved `mxc://` URL back into `channels.matrix.avatarUrl` (or the selected account override).
-
-## Automatic verification notices
-
-Matrix now posts verification lifecycle notices directly into the strict DM verification room as `m.notice` messages.
+Matrix posts verification lifecycle notices directly into the strict DM verification room as `m.notice` messages.
 That includes:
 
 - verification request notices
@@ -714,27 +652,31 @@ Remove stale OpenClaw-managed devices with:
 openclaw matrix devices prune-stale
 ```
 
-### Direct Room Repair
+### Crypto store
 
-If direct-message state gets out of sync, OpenClaw can end up with stale `m.direct` mappings that point at old solo rooms instead of the live DM. Inspect the current mapping for a peer with:
+Matrix E2EE uses the official `matrix-js-sdk` Rust crypto path in Node, with `fake-indexeddb` as the IndexedDB shim. Crypto state is persisted to a snapshot file (`crypto-idb-snapshot.json`) and restored on startup. The snapshot file is sensitive runtime state stored with restrictive file permissions.
+
+Encrypted runtime state lives under per-account, per-user token-hash roots in
+`~/.openclaw/matrix/accounts/<account>/<homeserver>__<user>/<token-hash>/`.
+That directory contains the sync store (`bot-storage.json`), crypto store (`crypto/`),
+recovery key file (`recovery-key.json`), IndexedDB snapshot (`crypto-idb-snapshot.json`),
+thread bindings (`thread-bindings.json`), and startup verification state (`startup-verification.json`).
+When the token changes but the account identity stays the same, OpenClaw reuses the best existing
+root for that account/homeserver/user tuple so prior sync state, crypto state, thread bindings,
+and startup verification state remain visible.
+
+## Profile management
+
+Update the Matrix self-profile for the selected account with:
 
 ```bash
-openclaw matrix direct inspect --user-id @alice:example.org
+openclaw matrix profile set --name "OpenClaw Assistant"
+openclaw matrix profile set --avatar-url https://cdn.example.org/avatar.png
 ```
 
-Repair it with:
+Add `--account <id>` when you want to target a named Matrix account explicitly.
 
-```bash
-openclaw matrix direct repair --user-id @alice:example.org
-```
-
-Repair keeps the Matrix-specific logic inside the plugin:
-
-- it prefers a strict 1:1 DM that is already mapped in `m.direct`
-- otherwise it falls back to any currently joined strict 1:1 DM with that user
-- if no healthy DM exists, it creates a fresh direct room and rewrites `m.direct` to point at it
-
-The repair flow does not delete old rooms automatically. It only picks the healthy DM and updates the mapping so new Matrix sends, verification notices, and other direct-message flows target the right room again.
+Matrix accepts `mxc://` avatar URLs directly. When you pass an `http://` or `https://` avatar URL, OpenClaw uploads it to Matrix first and stores the resolved `mxc://` URL back into `channels.matrix.avatarUrl` (or the selected account override).
 
 ## Threads
 
@@ -748,10 +690,10 @@ Matrix supports native Matrix threads for both automatic replies and message-too
 - `threadReplies: "always"` keeps room replies in a thread rooted at the triggering message and routes that conversation through the matching thread-scoped session from the first triggering message.
 - `dm.threadReplies` overrides the top-level setting for DMs only. For example, you can keep room threads isolated while keeping DMs flat.
 - Inbound threaded messages include the thread root message as extra agent context.
-- Message-tool sends now auto-inherit the current Matrix thread when the target is the same room, or the same DM user target, unless an explicit `threadId` is provided.
+- Message-tool sends auto-inherit the current Matrix thread when the target is the same room, or the same DM user target, unless an explicit `threadId` is provided.
 - Same-session DM user-target reuse only kicks in when the current session metadata proves the same DM peer on the same Matrix account; otherwise OpenClaw falls back to normal user-scoped routing.
 - When OpenClaw sees a Matrix DM room collide with another DM room on the same shared Matrix DM session, it posts a one-time `m.notice` in that room with the `/focus` escape hatch when thread bindings are enabled and the `dm.sessionScope` hint.
-- Runtime thread bindings are supported for Matrix. `/focus`, `/unfocus`, `/agents`, `/session idle`, `/session max-age`, and thread-bound `/acp spawn` now work in Matrix rooms and DMs.
+- Runtime thread bindings are supported for Matrix. `/focus`, `/unfocus`, `/agents`, `/session idle`, `/session max-age`, and thread-bound `/acp spawn` work in Matrix rooms and DMs.
 - Top-level Matrix room/DM `/focus` creates a new Matrix thread and binds it to the target session when `threadBindings.spawnSubagentSessions=true`.
 - Running `/focus` or `/acp spawn --thread here` inside an existing Matrix thread binds that current thread instead.
 
@@ -772,7 +714,7 @@ Notes:
 - `--bind here` does not create a child Matrix thread.
 - `threadBindings.spawnAcpSessions` is only required for `/acp spawn --thread auto|here`, where OpenClaw needs to create or bind a child Matrix thread.
 
-### Thread Binding Config
+### Thread binding config
 
 Matrix inherits global defaults from `session.threadBindings`, and also supports per-channel overrides:
 
@@ -816,16 +758,15 @@ Reaction notification mode resolves in this order:
 - `channels["matrix"].reactionNotifications`
 - default: `own`
 
-Current behavior:
+Behavior:
 
 - `reactionNotifications: "own"` forwards added `m.reaction` events when they target bot-authored Matrix messages.
 - `reactionNotifications: "off"` disables reaction system events.
-- Reaction removals are still not synthesized into system events because Matrix surfaces those as redactions, not as standalone `m.reaction` removals.
+- Reaction removals are not synthesized into system events because Matrix surfaces those as redactions, not as standalone `m.reaction` removals.
 
 ## History context
 
-- `channels.matrix.historyLimit` controls how many recent room messages are included as `InboundHistory` when a Matrix room message triggers the agent.
-- It falls back to `messages.groupChat.historyLimit`. If both are unset, the effective default is `0`, so mention-gated room messages are not buffered. Set `0` to disable.
+- `channels.matrix.historyLimit` controls how many recent room messages are included as `InboundHistory` when a Matrix room message triggers the agent. Falls back to `messages.groupChat.historyLimit`; if both are unset, the effective default is `0`. Set `0` to disable.
 - Matrix room history is room-only. DMs keep using normal session history.
 - Matrix room history is pending-only: OpenClaw buffers room messages that did not trigger a reply yet, then snapshots that window when a mention or other trigger arrives.
 - The current trigger message is not included in `InboundHistory`; it stays in the main inbound body for that turn.
@@ -842,7 +783,7 @@ Matrix supports the shared `contextVisibility` control for supplemental room con
 This setting affects supplemental context visibility, not whether the inbound message itself can trigger a reply.
 Trigger authorization still comes from `groupPolicy`, `groups`, `groupAllowFrom`, and DM policy settings.
 
-## DM and room policy example
+## DM and room policy
 
 ```json5
 {
@@ -878,9 +819,32 @@ If an unapproved Matrix user keeps messaging you before approval, OpenClaw reuse
 
 See [Pairing](/channels/pairing) for the shared DM pairing flow and storage layout.
 
+## Direct room repair
+
+If direct-message state gets out of sync, OpenClaw can end up with stale `m.direct` mappings that point at old solo rooms instead of the live DM. Inspect the current mapping for a peer with:
+
+```bash
+openclaw matrix direct inspect --user-id @alice:example.org
+```
+
+Repair it with:
+
+```bash
+openclaw matrix direct repair --user-id @alice:example.org
+```
+
+The repair flow:
+
+- prefers a strict 1:1 DM that is already mapped in `m.direct`
+- falls back to any currently joined strict 1:1 DM with that user
+- creates a fresh direct room and rewrites `m.direct` if no healthy DM exists
+
+The repair flow does not delete old rooms automatically. It only picks the healthy DM and updates the mapping so new Matrix sends, verification notices, and other direct-message flows target the right room again.
+
 ## 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`)
@@ -888,13 +852,14 @@ 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 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:
 
@@ -910,9 +875,7 @@ 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.
-
-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.
+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.
 
 Per-account override:
 
@@ -920,7 +883,7 @@ Per-account override:
 
 Related docs: [Exec approvals](/tools/exec-approvals)
 
-## Multi-account example
+## Multi-account
 
 ```json5
 {
@@ -951,7 +914,7 @@ Related docs: [Exec approvals](/tools/exec-approvals)
 ```
 
 Top-level `channels.matrix` values act as defaults for named accounts unless an account overrides them.
-You can scope inherited room entries to one Matrix account with `groups.<room>.account` (or legacy `rooms.<room>.account`).
+You can scope inherited room entries to one Matrix account with `groups.<room>.account`.
 Entries without `account` stay shared across all Matrix accounts, and entries with `account: "default"` still work when the default account is configured directly on top-level `channels.matrix.*`.
 Partial shared auth defaults do not create a separate implicit default account by themselves. OpenClaw only synthesizes the top-level `default` account when that default has fresh auth (`homeserver` plus `accessToken`, or `homeserver` plus `userId` and `password`); named accounts can still stay discoverable from `homeserver` plus `userId` when cached credentials satisfy auth later.
 If Matrix already has exactly one named account, or `defaultAccount` points at an existing named account key, single-account-to-multi-account repair/setup promotion preserves that account instead of creating a fresh `accounts.default` entry. Only Matrix auth/bootstrap keys move into that promoted account; shared delivery-policy keys stay at the top level.
@@ -959,6 +922,8 @@ Set `defaultAccount` when you want OpenClaw to prefer one named Matrix account f
 If you configure multiple named accounts, set `defaultAccount` or pass `--account <id>` for CLI commands that rely on implicit account selection.
 Pass `--account <id>` to `openclaw matrix verify ...` and `openclaw matrix devices ...` when you want to override that implicit selection for one command.
 
+See [Configuration reference](/gateway/configuration-reference#multi-account-all-channels) for the shared multi-account pattern.
+
 ## Private/LAN homeservers
 
 By default, OpenClaw blocks private/internal Matrix homeservers for SSRF protection unless you
@@ -1040,43 +1005,42 @@ Live directory lookup uses the logged-in Matrix account:
 - `password`: password for password-based login. Plaintext values and SecretRef values are supported.
 - `deviceId`: explicit Matrix device ID.
 - `deviceName`: device display name for password login.
-- `avatarUrl`: stored self-avatar URL for profile sync and `set-profile` updates.
-- `initialSyncLimit`: startup sync event limit.
+- `avatarUrl`: stored self-avatar URL for profile sync and `profile set` updates.
+- `initialSyncLimit`: maximum number of events fetched during startup sync.
 - `encryption`: enable E2EE.
-- `allowlistOnly`: force allowlist-only behavior for DMs and rooms.
+- `allowlistOnly`: when `true`, upgrades `open` room policy to `allowlist`, and forces all active DM policies except `disabled` (including `pairing` and `open`) to `allowlist`. Does not affect `disabled` policies.
 - `allowBots`: allow messages from other configured OpenClaw Matrix accounts (`true` or `"mentions"`).
 - `groupPolicy`: `open`, `allowlist`, or `disabled`.
 - `contextVisibility`: supplemental room-context visibility mode (`all`, `allowlist`, `allowlist_quote`).
-- `groupAllowFrom`: allowlist of user IDs for room traffic.
-- `groupAllowFrom` entries should be full Matrix user IDs. Unresolved names are ignored at runtime.
+- `groupAllowFrom`: allowlist of user IDs for room traffic. Entries should be full Matrix user IDs; unresolved names are ignored at runtime.
 - `historyLimit`: max room messages to include as group history context. Falls back to `messages.groupChat.historyLimit`; if both are unset, the effective default is `0`. Set `0` to disable.
 - `replyToMode`: `off`, `first`, `all`, or `batched`.
 - `markdown`: optional Markdown rendering configuration for outbound Matrix text.
-- `streaming`: `off` (default), `partial`, `quiet`, `true`, or `false`. `partial` and `true` enable preview-first draft updates with normal Matrix text messages. `quiet` uses non-notifying preview notices for self-hosted push-rule setups.
+- `streaming`: `off` (default), `"partial"`, `"quiet"`, `true`, or `false`. `"partial"` and `true` enable preview-first draft updates with normal Matrix text messages. `"quiet"` uses non-notifying preview notices for self-hosted push-rule setups. `false` is equivalent to `"off"`.
 - `blockStreaming`: `true` enables separate progress messages for completed assistant blocks while draft preview streaming is active.
 - `threadReplies`: `off`, `inbound`, or `always`.
 - `threadBindings`: per-channel overrides for thread-bound session routing and lifecycle.
 - `startupVerification`: automatic self-verification request mode on startup (`if-unverified`, `off`).
 - `startupVerificationCooldownHours`: cooldown before retrying automatic startup verification requests.
-- `textChunkLimit`: outbound message chunk size.
-- `chunkMode`: `length` or `newline`.
-- `responsePrefix`: optional message prefix for outbound replies.
+- `textChunkLimit`: outbound message chunk size in characters (applies when `chunkMode` is `length`).
+- `chunkMode`: `length` splits messages by character count; `newline` splits at line boundaries.
+- `responsePrefix`: optional string prepended to all outbound replies for this channel.
 - `ackReaction`: optional ack reaction override for this channel/account.
 - `ackReactionScope`: optional ack reaction scope override (`group-mentions`, `group-all`, `direct`, `all`, `none`, `off`).
 - `reactionNotifications`: inbound reaction notification mode (`own`, `off`).
-- `mediaMaxMb`: media size cap in MB for Matrix media handling. It applies to outbound sends and inbound media processing.
-- `autoJoin`: invite auto-join policy (`always`, `allowlist`, `off`). Default: `off`. This applies to Matrix invites in general, including DM-style invites, not only room/group invites. OpenClaw makes this decision at invite time, before it can reliably classify the joined room as a DM or a group.
+- `mediaMaxMb`: media size cap in MB for outbound sends and inbound media processing.
+- `autoJoin`: invite auto-join policy (`always`, `allowlist`, `off`). Default: `off`. Applies to all Matrix invites, including DM-style invites.
 - `autoJoinAllowlist`: rooms/aliases allowed when `autoJoin` is `allowlist`. Alias entries are resolved to room IDs during invite handling; OpenClaw does not trust alias state claimed by the invited room.
 - `dm`: DM policy block (`enabled`, `policy`, `allowFrom`, `sessionScope`, `threadReplies`).
 - `dm.policy`: controls DM access after OpenClaw has joined the room and classified it as a DM. It does not change whether an invite is auto-joined.
-- `dm.allowFrom` entries should be full Matrix user IDs unless you already resolved them through live directory lookup.
+- `dm.allowFrom`: entries should be full Matrix user IDs unless you already resolved them through live directory lookup.
 - `dm.sessionScope`: `per-user` (default) or `per-room`. Use `per-room` when you want each Matrix DM room to keep separate context even if the peer is the same.
 - `dm.threadReplies`: DM-only thread policy override (`off`, `inbound`, `always`). It overrides the top-level `threadReplies` setting for both reply placement and session isolation in DMs.
 - `execApprovals`: Matrix-native exec approval delivery (`enabled`, `approvers`, `target`, `agentFilter`, `sessionFilter`).
 - `execApprovals.approvers`: Matrix user IDs allowed to approve exec requests. Optional when `dm.allowFrom` already identifies the approvers.
 - `execApprovals.target`: `dm | channel | both` (default: `dm`).
 - `accounts`: named per-account overrides. Top-level `channels.matrix` values act as defaults for these entries.
-- `groups`: per-room policy map. Prefer room IDs or aliases; unresolved room names are ignored at runtime. Session/group identity uses the stable room ID after resolution, while human-readable labels still come from room names.
+- `groups`: per-room policy map. Prefer room IDs or aliases; unresolved room names are ignored at runtime. Session/group identity uses the stable room ID after resolution.
 - `groups.<room>.account`: restrict one inherited room entry to a specific Matrix account in multi-account setups.
 - `groups.<room>.allowBots`: room-level override for configured-bot senders (`true` or `"mentions"`).
 - `groups.<room>.users`: per-room sender allowlist.

docs/channels/slack.md

@@ -463,9 +463,11 @@ Notes:
 - `block`: append chunked preview updates.
 - `progress`: show progress status text while generating, then send final text.
 
-`channels.slack.nativeStreaming` controls Slack native text streaming when `streaming` is `partial` (default: `true`).
+`channels.slack.streaming.nativeTransport` controls Slack native text streaming when `channels.slack.streaming.mode` is `partial` (default: `true`).
 
-- A reply thread must be available for native text streaming to appear. Thread selection still follows `replyToMode`. Without one, the normal draft preview is used.
+- A reply thread must be available for native text streaming and Slack assistant thread status to appear. Thread selection still follows `replyToMode`.
+- Channel and group-chat roots can still use the normal draft preview when native streaming is unavailable.
+- Top-level Slack DMs stay off-thread by default, so they do not show the thread-style preview; use thread replies or `typingReaction` if you want visible progress there.
 - Media and non-text payloads fall back to normal delivery.
 - If streaming fails mid-reply, OpenClaw falls back to normal delivery for remaining payloads.
 
@@ -475,8 +477,10 @@ Use draft preview instead of Slack native text streaming:
 {
   channels: {
     slack: {
-      streaming: "partial",
-      nativeStreaming: false,
+      streaming: {
+        mode: "partial",
+        nativeTransport: false,
+      },
     },
   },
 }
@@ -484,8 +488,9 @@ Use draft preview instead of Slack native text streaming:
 
 Legacy keys:
 
-- `channels.slack.streamMode` (`replace | status_final | append`) is auto-migrated to `channels.slack.streaming`.
-- boolean `channels.slack.streaming` is auto-migrated to `channels.slack.nativeStreaming`.
+- `channels.slack.streamMode` (`replace | status_final | append`) is auto-migrated to `channels.slack.streaming.mode`.
+- boolean `channels.slack.streaming` is auto-migrated to `channels.slack.streaming.mode` and `channels.slack.streaming.nativeTransport`.
+- legacy `channels.slack.nativeStreaming` is auto-migrated to `channels.slack.streaming.nativeTransport`.
 
 ## Typing reaction fallback
 
@@ -687,7 +692,7 @@ Primary reference:
   - compatibility toggle: `dangerouslyAllowNameMatching` (break-glass; keep off unless needed)
   - channel access: `groupPolicy`, `channels.*`, `channels.*.users`, `channels.*.requireMention`
   - threading/history: `replyToMode`, `replyToModeByChatType`, `thread.*`, `historyLimit`, `dmHistoryLimit`, `dms.*.historyLimit`
-  - delivery: `textChunkLimit`, `chunkMode`, `mediaMaxMb`, `streaming`, `nativeStreaming`
+  - delivery: `textChunkLimit`, `chunkMode`, `mediaMaxMb`, `streaming`, `streaming.nativeTransport`
   - ops/features: `configWrites`, `commands.native`, `slashCommand.*`, `actions.*`, `userToken`, `userTokenReadOnly`
 
 ## Troubleshooting

docs/cli/index.md

@@ -35,7 +35,9 @@ 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)
+- [`wiki`](/cli/wiki)
 - [`directory`](/cli/directory)
 - [`nodes`](/cli/nodes)
 - [`devices`](/cli/devices)
@@ -161,6 +163,19 @@ openclaw [--dev] [--profile <name>] <command>
     status
     index
     search
+  wiki
+    status
+    doctor
+    init
+    ingest
+    compile
+    lint
+    search
+    get
+    apply
+    bridge import
+    unsafe-local import
+    obsidian status|search|open|command|daily
   message
     send
     broadcast
@@ -248,6 +263,16 @@ 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/cli/memory.md

@@ -15,6 +15,8 @@ Provided by the active memory plugin (default: `memory-core`; set `plugins.slots
 Related:
 
 - Memory concept: [Memory](/concepts/memory)
+- Memory wiki: [Memory Wiki](/plugins/memory-wiki)
+- Wiki CLI: [wiki](/cli/wiki)
 - Plugins: [Plugins](/tools/plugin)
 
 ## Examples

docs/cli/onboard.md

@@ -115,7 +115,7 @@ Interactive onboarding behavior with reference mode:
 
 Non-interactive Z.AI endpoint choices:
 
-Note: `--auth-choice zai-api-key` now auto-detects the best Z.AI endpoint for your key (prefers the general API with `zai/glm-5`).
+Note: `--auth-choice zai-api-key` now auto-detects the best Z.AI endpoint for your key (prefers the general API with `zai/glm-5.1`).
 If you specifically want the GLM Coding Plan endpoints, pick `zai-coding-global` or `zai-coding-cn`.
 
 ```bash

docs/cli/wiki.md

@@ -0,0 +1,214 @@
+---
+summary: "CLI reference for `openclaw wiki` (memory-wiki vault status, search, compile, lint, apply, bridge, and Obsidian helpers)"
+read_when:
+  - You want to use the memory-wiki CLI
+  - You are documenting or changing `openclaw wiki`
+title: "wiki"
+---
+
+# `openclaw wiki`
+
+Inspect and maintain the `memory-wiki` vault.
+
+Provided by the bundled `memory-wiki` plugin.
+
+Related:
+
+- [Memory Wiki plugin](/plugins/memory-wiki)
+- [Memory Overview](/concepts/memory)
+- [CLI: memory](/cli/memory)
+
+## What it is for
+
+Use `openclaw wiki` when you want a compiled knowledge vault with:
+
+- wiki-native search and page reads
+- provenance-rich syntheses
+- contradiction and freshness reports
+- bridge imports from the active memory plugin
+- optional Obsidian CLI helpers
+
+## Common commands
+
+```bash
+openclaw wiki status
+openclaw wiki doctor
+openclaw wiki init
+openclaw wiki ingest ./notes/alpha.md
+openclaw wiki compile
+openclaw wiki lint
+openclaw wiki search "alpha"
+openclaw wiki get entity.alpha --from 1 --lines 80
+
+openclaw wiki apply synthesis "Alpha Summary" \
+  --body "Short synthesis body" \
+  --source-id source.alpha
+
+openclaw wiki apply metadata entity.alpha \
+  --source-id source.alpha \
+  --status review \
+  --question "Still active?"
+
+openclaw wiki bridge import
+openclaw wiki unsafe-local import
+
+openclaw wiki obsidian status
+openclaw wiki obsidian search "alpha"
+openclaw wiki obsidian open syntheses/alpha-summary.md
+openclaw wiki obsidian command workspace:quick-switcher
+openclaw wiki obsidian daily
+```
+
+## Commands
+
+### `wiki status`
+
+Inspect current vault mode, health, and Obsidian CLI availability.
+
+Use this first when you are unsure whether the vault is initialized, bridge mode
+is healthy, or Obsidian integration is available.
+
+### `wiki doctor`
+
+Run wiki health checks and surface configuration or vault problems.
+
+Typical issues include:
+
+- bridge mode enabled without public memory artifacts
+- invalid or missing vault layout
+- missing external Obsidian CLI when Obsidian mode is expected
+
+### `wiki init`
+
+Create the wiki vault layout and starter pages.
+
+This initializes the root structure, including top-level indexes and cache
+directories.
+
+### `wiki ingest <path-or-url>`
+
+Import content into the wiki source layer.
+
+Notes:
+
+- URL ingest is controlled by `ingest.allowUrlIngest`
+- imported source pages keep provenance in frontmatter
+- auto-compile can run after ingest when enabled
+
+### `wiki compile`
+
+Rebuild indexes, related blocks, dashboards, and compiled digests.
+
+This writes stable machine-facing artifacts under:
+
+- `.openclaw-wiki/cache/agent-digest.json`
+- `.openclaw-wiki/cache/claims.jsonl`
+
+If `render.createDashboards` is enabled, compile also refreshes report pages.
+
+### `wiki lint`
+
+Lint the vault and report:
+
+- structural issues
+- provenance gaps
+- contradictions
+- open questions
+- low-confidence pages/claims
+- stale pages/claims
+
+Run this after meaningful wiki updates.
+
+### `wiki search <query>`
+
+Search wiki content.
+
+Behavior depends on config:
+
+- `search.backend`: `shared` or `local`
+- `search.corpus`: `wiki`, `memory`, or `all`
+
+Use `wiki search` when you want wiki-specific ranking or provenance details.
+For one broad shared recall pass, prefer `openclaw memory search` when the
+active memory plugin exposes shared search.
+
+### `wiki get <lookup>`
+
+Read a wiki page by id or relative path.
+
+Examples:
+
+```bash
+openclaw wiki get entity.alpha
+openclaw wiki get syntheses/alpha-summary.md --from 1 --lines 80
+```
+
+### `wiki apply`
+
+Apply narrow mutations without freeform page surgery.
+
+Supported flows include:
+
+- create/update a synthesis page
+- update page metadata
+- attach source ids
+- add questions
+- add contradictions
+- update confidence/status
+- write structured claims
+
+This command exists so the wiki can evolve safely without manually editing
+managed blocks.
+
+### `wiki bridge import`
+
+Import public memory artifacts from the active memory plugin into bridge-backed
+source pages.
+
+Use this in `bridge` mode when you want the latest exported memory artifacts
+pulled into the wiki vault.
+
+### `wiki unsafe-local import`
+
+Import from explicitly configured local paths in `unsafe-local` mode.
+
+This is intentionally experimental and same-machine only.
+
+### `wiki obsidian ...`
+
+Obsidian helper commands for vaults running in Obsidian-friendly mode.
+
+Subcommands:
+
+- `status`
+- `search`
+- `open`
+- `command`
+- `daily`
+
+These require the official `obsidian` CLI on `PATH` when
+`obsidian.useOfficialCli` is enabled.
+
+## Practical usage guidance
+
+- Use `wiki search` + `wiki get` when provenance and page identity matter.
+- Use `wiki apply` instead of hand-editing managed generated sections.
+- Use `wiki lint` before trusting contradictory or low-confidence content.
+- Use `wiki compile` after bulk imports or source changes when you want fresh
+  dashboards and compiled digests immediately.
+- Use `wiki bridge import` when bridge mode depends on newly exported memory
+  artifacts.
+
+## Configuration tie-ins
+
+`openclaw wiki` behavior is shaped by:
+
+- `plugins.entries.memory-wiki.config.vaultMode`
+- `plugins.entries.memory-wiki.config.search.backend`
+- `plugins.entries.memory-wiki.config.search.corpus`
+- `plugins.entries.memory-wiki.config.bridge.*`
+- `plugins.entries.memory-wiki.config.obsidian.*`
+- `plugins.entries.memory-wiki.config.render.*`
+- `plugins.entries.memory-wiki.config.context.includeCompiledDigestPrompt`
+
+See [Memory Wiki plugin](/plugins/memory-wiki) for the full config model.

docs/concepts/agent-loop.md

@@ -151,6 +151,7 @@ See [Plugin hooks](/plugins/architecture#provider-runtime-hooks) for the hook AP
 
 - `agent.wait` default: 30s (just the wait). `timeoutMs` param overrides.
 - Agent runtime: `agents.defaults.timeoutSeconds` default 172800s (48 hours); enforced in `runEmbeddedPiAgent` abort timer.
+- LLM idle timeout: `agents.defaults.llm.idleTimeoutSeconds` aborts a model request when no response chunks arrive before the idle window. Set it explicitly for slow local models or reasoning/tool-call providers; set it to 0 to disable. If it is not set, OpenClaw uses `agents.defaults.timeoutSeconds` when configured, otherwise 60s. Cron-triggered runs with no explicit LLM or agent timeout disable the idle watchdog and rely on the cron outer timeout.
 
 ## Where things can end early
 

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/dreaming.md

@@ -42,7 +42,7 @@ These phases are internal implementation details, not separate user-configured
 Light phase ingests recent daily memory signals and recall traces, dedupes them,
 and stages candidate lines.
 
-- Reads from short-term recall state and recent daily memory files.
+- Reads from short-term recall state, recent daily memory files, and redacted session transcripts when available.
 - Writes a managed `## Light Sleep` block when storage includes inline output.
 - Records reinforcement signals for later deep ranking.
 - Never writes to `MEMORY.md`.
@@ -66,6 +66,13 @@ REM phase extracts patterns and reflective signals.
 - Records REM reinforcement signals used by deep ranking.
 - Never writes to `MEMORY.md`.
 
+## Session transcript ingestion
+
+Dreaming can ingest redacted session transcripts into the dreaming corpus. When
+transcripts are available, they are fed into the light phase alongside daily
+memory signals and recall traces. Personal and sensitive content is redacted
+before ingestion.
+
 ## Dream Diary
 
 Dreaming also keeps a narrative **Dream Diary** in `DREAMS.md`.

docs/concepts/memory.md

@@ -40,6 +40,26 @@ The agent has two tools for working with memory:
 
 Both tools are provided by the active memory plugin (default: `memory-core`).
 
+## Memory Wiki companion plugin
+
+If you want durable memory to behave more like a maintained knowledge base than
+just raw notes, use the bundled `memory-wiki` plugin.
+
+`memory-wiki` compiles durable knowledge into a wiki vault with:
+
+- deterministic page structure
+- structured claims and evidence
+- contradiction and freshness tracking
+- generated dashboards
+- compiled digests for agent/runtime consumers
+- wiki-native tools like `wiki_search`, `wiki_get`, `wiki_apply`, and `wiki_lint`
+
+It does not replace the active memory plugin. The active memory plugin still
+owns recall, promotion, and dreaming. `memory-wiki` adds a provenance-rich
+knowledge layer beside it.
+
+See [Memory Wiki](/plugins/memory-wiki).
+
 ## Memory search
 
 When an embedding provider is configured, `memory_search` uses **hybrid
@@ -73,6 +93,15 @@ multi-agent awareness. Plugin install.
 </Card>
 </CardGroup>
 
+## Knowledge wiki layer
+
+<CardGroup cols={1}>
+<Card title="Memory Wiki" icon="book" href="/plugins/memory-wiki">
+Compiles durable memory into a provenance-rich wiki vault with claims,
+dashboards, bridge mode, and Obsidian-friendly workflows.
+</Card>
+</CardGroup>
+
 ## Automatic memory flush
 
 Before [compaction](/concepts/compaction) summarizes your conversation, OpenClaw
@@ -117,6 +146,7 @@ openclaw memory index --force   # Rebuild the index
 - [Builtin Memory Engine](/concepts/memory-builtin) -- default SQLite backend
 - [QMD Memory Engine](/concepts/memory-qmd) -- advanced local-first sidecar
 - [Honcho Memory](/concepts/memory-honcho) -- AI-native cross-session memory
+- [Memory Wiki](/plugins/memory-wiki) -- compiled knowledge vault and wiki-native tools
 - [Memory Search](/concepts/memory-search) -- search pipeline, providers, and
   tuning
 - [Dreaming (experimental)](/concepts/dreaming) -- background promotion

docs/concepts/model-providers.md

@@ -23,10 +23,11 @@ For model selection rules, see [/concepts/models](/concepts/models).
 - Provider plugins can inject model catalogs via `registerProvider({ catalog })`;
   OpenClaw merges that output into `models.providers` before writing
   `models.json`.
-- Provider manifests can declare `providerAuthEnvVars` so generic env-based
-  auth probes do not need to load plugin runtime. The remaining core env-var
-  map is now just for non-plugin/core providers and a few generic-precedence
-  cases such as Anthropic API-key-first onboarding.
+- Provider manifests can declare `providerAuthEnvVars` and
+  `providerAuthAliases` so generic env-based auth probes and provider variants
+  do not need to load plugin runtime. The remaining core env-var map is now
+  just for non-plugin/core providers and a few generic-precedence cases such
+  as Anthropic API-key-first onboarding.
 - Provider plugins can also own provider runtime behavior via
   `normalizeModelId`, `normalizeTransport`, `normalizeConfig`,
   `applyNativeStreamingUsageCompat`, `resolveConfigApiKey`,
@@ -360,7 +361,7 @@ 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.
@@ -371,7 +372,7 @@ OpenClaw ships with the pi‑ai catalog. These providers require **no**
 
 - Provider: `zai`
 - Auth: `ZAI_API_KEY`
-- Example model: `zai/glm-5`
+- Example model: `zai/glm-5.1`
 - CLI: `openclaw onboard --auth-choice zai-api-key`
   - Aliases: `z.ai/*` and `z-ai/*` normalize to `zai/*`
   - `zai-api-key` auto-detects the matching Z.AI endpoint; `zai-coding-global`, `zai-coding-cn`, `zai-global`, and `zai-cn` force a specific surface

docs/concepts/qa-e2e-automation.md

@@ -56,8 +56,8 @@ asset hash changes.
 
 Seed assets live in `qa/`:
 
-- `qa/QA_KICKOFF_TASK.md`
-- `qa/seed-scenarios.json`
+- `qa/scenarios/index.md`
+- `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:
@@ -82,6 +82,56 @@ The report should answer:
 - What stayed blocked
 - What follow-up scenarios are worth adding
 
+For character and style checks, run the same scenario across multiple live model
+refs and write a judged Markdown report:
+
+```bash
+pnpm openclaw qa character-eval \
+  --model openai/gpt-5.4,thinking=xhigh \
+  --model openai/gpt-5.2,thinking=xhigh \
+  --model anthropic/claude-opus-4-6,thinking=high \
+  --model anthropic/claude-sonnet-4-6,thinking=high \
+  --model minimax/MiniMax-M2.7,thinking=high \
+  --model zai/glm-5.1,thinking=high \
+  --model moonshot/kimi-k2.5,thinking=high \
+  --model qwen/qwen3.6-plus,thinking=high \
+  --model xiaomi/mimo-v2-pro,thinking=high \
+  --model google/gemini-3.1-pro-preview,thinking=high \
+  --judge-model openai/gpt-5.4,thinking=xhigh,fast \
+  --judge-model anthropic/claude-opus-4-6,thinking=high \
+  --concurrency 8 \
+  --judge-concurrency 8
+```
+
+The command runs local QA gateway child processes, not Docker. Character eval
+scenarios should set the persona through `SOUL.md`, then run ordinary user turns
+such as chat, workspace help, and small file tasks. The candidate model should
+not be told that it is being evaluated. The command preserves each full
+transcript, records basic run stats, then asks the judge models in fast mode with
+`xhigh` reasoning to rank the runs by naturalness, vibe, and humor.
+Candidate runs default to `high` thinking, with `xhigh` for OpenAI models that
+support it. Override a specific candidate inline with
+`--model provider/model,thinking=<level>`. `--thinking <level>` still sets a
+global fallback, and the older `--model-thinking <provider/model=level>` form is
+kept for compatibility.
+OpenAI candidate refs default to fast mode so priority processing is used where
+the provider supports it. Add `,fast`, `,no-fast`, or `,fast=false` inline when a
+single candidate or judge needs an override. Pass `--fast` only when you want to
+force fast mode on for every candidate model. Candidate and judge durations are
+recorded in the report for benchmark analysis, but judge prompts explicitly say
+not to rank by speed.
+Candidate and judge model runs both default to concurrency 8. Lower
+`--concurrency` or `--judge-concurrency` when provider limits or local gateway
+pressure make a run too noisy.
+When no candidate `--model` is passed, the character eval defaults to
+`openai/gpt-5.4`, `openai/gpt-5.2`, `anthropic/claude-opus-4-6`,
+`anthropic/claude-sonnet-4-6`, `minimax/MiniMax-M2.7`, `zai/glm-5.1`,
+`moonshot/kimi-k2.5`, `qwen/qwen3.6-plus`, `xiaomi/mimo-v2-pro`, and
+`google/gemini-3.1-pro-preview`.
+When no `--judge-model` is passed, the judges default to
+`openai/gpt-5.4,thinking=xhigh,fast` and
+`anthropic/claude-opus-4-6,thinking=high`.
+
 ## Related docs
 
 - [Testing](/help/testing)

docs/concepts/streaming.md

@@ -126,13 +126,14 @@ Modes:
 
 Slack-only:
 
-- `channels.slack.nativeStreaming` toggles Slack native streaming API calls when `streaming=partial` (default: `true`).
+- `channels.slack.streaming.nativeTransport` toggles Slack native streaming API calls when `channels.slack.streaming.mode="partial"` (default: `true`).
+- Slack native streaming and Slack assistant thread status require a reply thread target; top-level DMs do not show that thread-style preview.
 
 Legacy key migration:
 
 - Telegram: `streamMode` + boolean `streaming` auto-migrate to `streaming` enum.
 - Discord: `streamMode` + boolean `streaming` auto-migrate to `streaming` enum.
-- Slack: `streamMode` auto-migrates to `streaming` enum; boolean `streaming` auto-migrates to `nativeStreaming`.
+- Slack: `streamMode` auto-migrates to `streaming.mode`; boolean `streaming` auto-migrates to `streaming.mode` plus `streaming.nativeTransport`; legacy `nativeStreaming` auto-migrates to `streaming.nativeTransport`.
 
 ### Runtime behavior
 

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"

docs/gateway/cli-backends.md

@@ -124,6 +124,9 @@ The provider id becomes the left side of your model ref:
           sessionMode: "existing",
           sessionIdFields: ["session_id", "conversation_id"],
           systemPromptArg: "--system",
+          // Codex-style CLIs can point at a prompt file instead:
+          // systemPromptFileConfigArg: "-c",
+          // systemPromptFileConfigKey: "model_instructions_file",
           systemPromptWhen: "first",
           imageArg: "--image",
           imageMode: "repeat",
@@ -150,6 +153,12 @@ told us OpenClaw-style Claude CLI usage is allowed again, so OpenClaw treats
 a new policy.
 </Note>
 
+The bundled OpenAI `codex-cli` backend passes OpenClaw's system prompt through
+Codex's `model_instructions_file` config override (`-c
+model_instructions_file="..."`). Codex does not expose a Claude-style
+`--append-system-prompt` flag, so OpenClaw writes the assembled prompt to a
+temporary file for each fresh Codex CLI session.
+
 ## Sessions
 
 - If the CLI supports sessions, set `sessionArg` (e.g. `--session-id`) or
@@ -214,8 +223,10 @@ 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 +262,9 @@ 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 +272,8 @@ 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

@@ -1,6 +1,6 @@
 ---
 title: "Configuration Reference"
-summary: "Complete reference for every OpenClaw config key, defaults, and channel settings"
+summary: "Gateway config reference for core OpenClaw keys, defaults, and links to dedicated subsystem references"
 read_when:
   - You need exact field-level config semantics or defaults
   - You are validating channel, model, gateway, or tool config blocks
@@ -8,7 +8,21 @@ read_when:
 
 # Configuration Reference
 
-Every field available in `~/.openclaw/openclaw.json`. For a task-oriented overview, see [Configuration](/gateway/configuration).
+Core config reference for `~/.openclaw/openclaw.json`. For a task-oriented overview, see [Configuration](/gateway/configuration).
+
+This page covers the main OpenClaw config surfaces and links out when a subsystem has its own deeper reference. It does **not** try to inline every channel/plugin-owned command catalog or every deep memory/QMD knob on one page.
+
+Code truth:
+
+- `openclaw config schema` prints the live JSON Schema used for validation and Control UI, with bundled/plugin/channel metadata merged in when available
+- `config.schema.lookup` returns one path-scoped schema node for drill-down tooling
+- `pnpm config:docs:check` / `pnpm config:docs:gen` validate the config-doc baseline hash against the current schema surface
+
+Dedicated deep references:
+
+- [Memory configuration reference](/reference/memory-config) for `agents.defaults.memorySearch.*`, `memory.qmd.*`, `memory.citations`, and dreaming config under `plugins.entries.memory-core.config.dreaming`
+- [Slash Commands](/tools/slash-commands) for the current built-in + bundled command catalog
+- owning channel/plugin pages for channel-specific command surfaces
 
 Config format is **JSON5** (comments + trailing commas allowed). All fields are optional — OpenClaw uses safe defaults when omitted.
 
@@ -426,8 +440,10 @@ WhatsApp runs through the gateway's web channel (Baileys Web). It starts automat
       typingReaction: "hourglass_flowing_sand",
       textChunkLimit: 4000,
       chunkMode: "length",
-      streaming: "partial", // off | partial | block | progress (preview mode)
-      nativeStreaming: true, // use Slack native streaming API when streaming=partial
+      streaming: {
+        mode: "partial", // off | partial | block | progress
+        nativeTransport: true, // use Slack native streaming API when mode=partial
+      },
       mediaMaxMb: 20,
       execApprovals: {
         enabled: "auto", // true | false | "auto"
@@ -452,13 +468,14 @@ WhatsApp runs through the gateway's web channel (Baileys Web). It starts automat
   resolve the secret value.
 - `configWrites: false` blocks Slack-initiated config writes.
 - Optional `channels.slack.defaultAccount` overrides default account selection when it matches a configured account id.
-- `channels.slack.streaming` is the canonical stream mode key. Legacy `streamMode` and boolean `streaming` values are auto-migrated.
+- `channels.slack.streaming.mode` is the canonical Slack stream mode key. `channels.slack.streaming.nativeTransport` controls Slack's native streaming transport. Legacy `streamMode`, boolean `streaming`, and `nativeStreaming` values are auto-migrated.
 - Use `user:<id>` (DM) or `channel:<id>` for delivery targets.
 
 **Reaction notification modes:** `off`, `own` (default), `all`, `allowlist` (from `reactionAllowlist`).
 
 **Thread session isolation:** `thread.historyScope` is per-thread (default) or shared across channel. `thread.inheritParent` copies parent channel transcript to new threads.
 
+- Slack native streaming plus the Slack assistant-style "is typing..." thread status require a reply thread target. Top-level DMs stay off-thread by default, so they use `typingReaction` or normal delivery instead of the thread-style preview.
 - `typingReaction` adds a temporary reaction to the inbound Slack message while a reply is running, then removes it on completion. Use a Slack emoji shortcode such as `"hourglass_flowing_sand"`.
 - `channels.slack.execApprovals`: Slack-native exec approval delivery and approver authorization. Same schema as Discord: `enabled` (`true`/`false`/`"auto"`), `approvers` (Slack user IDs), `agentFilter`, `sessionFilter`, and `target` (`"dm"`, `"channel"`, or `"both"`).
 
@@ -814,12 +831,18 @@ Include your own number in `allowFrom` to enable self-chat mode (ignores native
 {
   commands: {
     native: "auto", // register native commands when supported
+    nativeSkills: "auto", // register native skill commands when supported
     text: true, // parse /commands in chat messages
     bash: false, // allow ! (alias: /bash)
     bashForegroundMs: 2000,
     config: false, // allow /config
+    mcp: false, // allow /mcp
+    plugins: false, // allow /plugins
     debug: false, // allow /debug
-    restart: false, // allow /restart + gateway restart tool
+    restart: true, // allow /restart + gateway restart tool
+    ownerAllowFrom: ["discord:123456789012345678"],
+    ownerDisplay: "raw", // raw | hash
+    ownerDisplaySecret: "${OWNER_ID_HASH_SECRET}",
     allowFrom: {
       "*": ["user1"],
       discord: ["user:123"],
@@ -831,16 +854,32 @@ Include your own number in `allowFrom` to enable self-chat mode (ignores native
 
 <Accordion title="Command details">
 
+- This block configures command surfaces. For the current built-in + bundled command catalog, see [Slash Commands](/tools/slash-commands).
+- This page is a **config-key reference**, not the full command catalog. Channel/plugin-owned commands such as QQ Bot `/bot-ping` `/bot-help` `/bot-logs`, LINE `/card`, device-pair `/pair`, memory `/dreaming`, phone-control `/phone`, and Talk `/voice` are documented in their channel/plugin pages plus [Slash Commands](/tools/slash-commands).
 - Text commands must be **standalone** messages with leading `/`.
 - `native: "auto"` turns on native commands for Discord/Telegram, leaves Slack off.
+- `nativeSkills: "auto"` turns on native skill commands for Discord/Telegram, leaves Slack off.
 - Override per channel: `channels.discord.commands.native` (bool or `"auto"`). `false` clears previously registered commands.
+- Override native skill registration per channel with `channels.<provider>.commands.nativeSkills`.
 - `channels.telegram.customCommands` adds extra Telegram bot menu entries.
 - `bash: true` enables `! <cmd>` for host shell. Requires `tools.elevated.enabled` and sender in `tools.elevated.allowFrom.<channel>`.
 - `config: true` enables `/config` (reads/writes `openclaw.json`). For gateway `chat.send` clients, persistent `/config set|unset` writes also require `operator.admin`; read-only `/config show` stays available to normal write-scoped operator clients.
+- `mcp: true` enables `/mcp` for OpenClaw-managed MCP server config under `mcp.servers`.
+- `plugins: true` enables `/plugins` for plugin discovery, install, and enable/disable controls.
 - `channels.<provider>.configWrites` gates config mutations per channel (default: true).
 - For multi-account channels, `channels.<provider>.accounts.<id>.configWrites` also gates writes that target that account (for example `/allowlist --config --account <id>` or `/config set channels.<provider>.accounts.<id>...`).
+- `restart: false` disables `/restart` and gateway restart tool actions. Default: `true`.
+- `ownerAllowFrom` is the explicit owner allowlist for owner-only commands/tools. It is separate from `allowFrom`.
+- `ownerDisplay: "hash"` hashes owner ids in the system prompt. Set `ownerDisplaySecret` to control hashing.
 - `allowFrom` is per-provider. When set, it is the **only** authorization source (channel allowlists/pairing and `useAccessGroups` are ignored).
 - `useAccessGroups: false` allows commands to bypass access-group policies when `allowFrom` is not set.
+- Command docs map:
+  - built-in + bundled catalog: [Slash Commands](/tools/slash-commands)
+  - channel-specific command surfaces: [Channels](/channels)
+  - QQ Bot commands: [QQ Bot](/channels/qqbot)
+  - pairing commands: [Pairing](/channels/pairing)
+  - LINE card command: [LINE](/channels/line)
+  - memory dreaming: [Dreaming](/concepts/dreaming)
 
 </Accordion>
 
@@ -1049,7 +1088,7 @@ Time format in system prompt. Default: `auto` (OS preference).
   - Typical values: `qwen/wan2.6-t2v`, `qwen/wan2.6-i2v`, `qwen/wan2.6-r2v`, `qwen/wan2.6-r2v-flash`, or `qwen/wan2.7-r2v`.
   - If omitted, `video_generate` can still infer an auth-backed provider default. It tries the current default provider first, then the remaining registered video-generation providers in provider-id order.
   - If you select a provider/model directly, configure the matching provider auth/API key too.
-  - The bundled Qwen video-generation provider currently supports up to 1 output video, 1 input image, 4 input videos, 10 seconds duration, and provider-level `size`, `aspectRatio`, `resolution`, `audio`, and `watermark` options.
+  - The bundled Qwen video-generation provider supports up to 1 output video, 1 input image, 4 input videos, 10 seconds duration, and provider-level `size`, `aspectRatio`, `resolution`, `audio`, and `watermark` options.
 - `pdfModel`: accepts either a string (`"provider/model"`) or an object (`{ primary, fallbacks }`).
   - Used by the `pdf` tool for model routing.
   - If omitted, the PDF tool falls back to `imageModel`, then to the resolved session/default model.
@@ -1117,6 +1156,20 @@ Optional CLI backends for text-only fallback runs (no tool calls). Useful as a b
 - Sessions supported when `sessionArg` is set.
 - Image pass-through supported when `imageArg` accepts file paths.
 
+### `agents.defaults.systemPromptOverride`
+
+Replace the entire OpenClaw-assembled system prompt with a fixed string. Set at the default level (`agents.defaults.systemPromptOverride`) or per agent (`agents.list[].systemPromptOverride`). Per-agent values take precedence; an empty or whitespace-only value is ignored. Useful for controlled prompt experiments.
+
+```json5
+{
+  agents: {
+    defaults: {
+      systemPromptOverride: "You are a helpful assistant.",
+    },
+  },
+}
+```
+
 ### `agents.defaults.heartbeat`
 
 Periodic heartbeat runs.
@@ -1129,6 +1182,7 @@ Periodic heartbeat runs.
         every: "30m", // 0m disables
         model: "openai/gpt-5.4-mini",
         includeReasoning: false,
+        includeSystemPromptSection: true, // default: true; false omits the Heartbeat section from the system prompt
         lightContext: false, // default: false; true keeps only HEARTBEAT.md from workspace bootstrap files
         isolatedSession: false, // default: false; true runs each heartbeat in a fresh session (no conversation history)
         session: "main",
@@ -1145,6 +1199,7 @@ Periodic heartbeat runs.
 ```
 
 - `every`: duration string (ms/s/m/h). Default: `30m` (API-key auth) or `1h` (OAuth auth). Set to `0m` to disable.
+- `includeSystemPromptSection`: when false, omits the Heartbeat section from the system prompt and skips `HEARTBEAT.md` injection into bootstrap context. Default: `true`.
 - `suppressToolErrorWarnings`: when true, suppresses tool error warning payloads during heartbeat runs.
 - `directPolicy`: direct/DM delivery policy. `allow` (default) permits direct-target delivery. `block` suppresses direct-target delivery and emits `reason=dm-blocked`.
 - `lightContext`: when true, heartbeat runs use lightweight bootstrap context and keep only `HEARTBEAT.md` from workspace bootstrap files.
@@ -1160,6 +1215,7 @@ 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 +1236,7 @@ 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`.
@@ -1501,7 +1558,7 @@ noVNC observer access uses VNC auth by default and OpenClaw emits a short-lived
 
 </Accordion>
 
-Browser sandboxing and `sandbox.docker.binds` are currently Docker-only.
+Browser sandboxing and `sandbox.docker.binds` are Docker-only.
 
 Build images:
 
@@ -1778,7 +1835,7 @@ See [Multi-Agent Sandbox & Tools](/tools/multi-agent-sandbox-tools) for preceden
 - **`parentForkMaxTokens`**: max parent-session `totalTokens` allowed when creating a forked thread session (default `100000`).
   - If parent `totalTokens` is above this value, OpenClaw starts a fresh thread session instead of inheriting parent transcript history.
   - Set `0` to disable this guard and always allow parent forking.
-- **`mainKey`**: legacy field. Runtime now always uses `"main"` for the main direct-chat bucket.
+- **`mainKey`**: legacy field. Runtime always uses `"main"` for the main direct-chat bucket.
 - **`agentToAgent.maxPingPongTurns`**: maximum reply-back turns between agents during agent-to-agent exchanges (integer, range: `0`–`5`). `0` disables ping-pong chaining.
 - **`sendPolicy`**: match by `channel`, `chatType` (`direct|group|channel`, with legacy `dm` alias), `keyPrefix`, or `rawKeyPrefix`. First deny wins.
 - **`maintenance`**: session-store cleanup + retention controls.
@@ -1902,7 +1959,7 @@ Batches rapid text-only messages from the same sender into a single agent turn.
 }
 ```
 
-- `auto` controls auto-TTS. `/tts off|always|inbound|tagged` overrides per session.
+- `auto` controls the default auto-TTS mode: `off`, `always`, `inbound`, or `tagged`. `/tts on|off` can override local prefs, and `/tts status` shows the effective state.
 - `summaryModel` overrides `agents.defaults.model.primary` for auto-summary.
 - `modelOverrides` is enabled by default; `modelOverrides.allowProvider` defaults to `false` (opt-in).
 - API keys fall back to `ELEVENLABS_API_KEY`/`XI_API_KEY` and `OPENAI_API_KEY`.
@@ -2257,7 +2314,7 @@ Experimental built-in tool flags. Default off unless a runtime-specific auto-ena
 Notes:
 
 - `planTool`: enables the structured `update_plan` tool for non-trivial multi-step work tracking.
-- Default: `false` for non-OpenAI providers. OpenAI and OpenAI Codex runs auto-enable it.
+- Default: `false` for non-OpenAI providers. OpenAI and OpenAI Codex runs auto-enable it when unset; set `false` to disable that auto-enable.
 - When enabled, the system prompt also adds usage guidance so the model only uses it for substantial work and keeps at most one step `in_progress`.
 
 ### `agents.defaults.subagents`
@@ -2349,6 +2406,7 @@ 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.
@@ -2473,8 +2531,8 @@ Set `ZAI_API_KEY`. `z.ai/*` and `z-ai/*` are accepted aliases. Shortcut: `opencl
 For the China endpoint: `baseUrl: "https://api.moonshot.cn/v1"` or `openclaw onboard --auth-choice moonshot-api-key-cn`.
 
 Native Moonshot endpoints advertise streaming usage compatibility on the shared
-`openai-completions` transport, and OpenClaw now keys that off endpoint
-capabilities rather than the built-in provider id alone.
+`openai-completions` transport, and OpenClaw keys that off endpoint capabilities
+rather than the built-in provider id alone.
 
 </Accordion>
 
@@ -2574,7 +2632,7 @@ Base URL should omit `/v1` (Anthropic client appends it). Shortcut: `openclaw on
 Set `MINIMAX_API_KEY`. Shortcuts:
 `openclaw onboard --auth-choice minimax-global-api` or
 `openclaw onboard --auth-choice minimax-cn-api`.
-The model catalog now defaults to M2.7 only.
+The model catalog defaults to M2.7 only.
 On the Anthropic-compatible streaming path, OpenClaw disables MiniMax thinking
 by default unless you explicitly set `thinking` yourself. `/fast on` or
 `params.fastMode: true` rewrites `MiniMax-M2.7` to
@@ -2673,6 +2731,12 @@ See [Local Models](/gateway/local-models). TL;DR: run a large local model via LM
   - `enabled`: master dreaming switch (default `false`).
   - `frequency`: cron cadence for each full dreaming sweep (`"0 3 * * *"` by default).
   - phase policy and thresholds are implementation details (not user-facing config keys).
+- Full memory config lives in [Memory configuration reference](/reference/memory-config):
+  - `agents.defaults.memorySearch.*`
+  - `memory.backend`
+  - `memory.citations`
+  - `memory.qmd.*`
+  - `plugins.entries.memory-core.config.dreaming`
 - Enabled Claude bundle plugins can also contribute embedded Pi defaults from `settings.json`; OpenClaw applies those as sanitized agent settings, not as raw OpenClaw config patches.
 - `plugins.slots.memory`: pick the active memory plugin id, or `"none"` to disable memory plugins.
 - `plugins.slots.contextEngine`: pick the active context engine plugin id; defaults to `"legacy"` unless you install and select another engine.
@@ -3574,7 +3638,7 @@ Applies only to one-shot cron jobs. Recurring jobs use separate failure handling
 - `to`: explicit announce target or webhook URL. Required for webhook mode.
 - `accountId`: optional account override for delivery.
 - Per-job `delivery.failureDestination` overrides this global default.
-- When neither global nor per-job failure destination is set, jobs that already deliver via `announce` now fall back to that primary announce target on failure.
+- When neither global nor per-job failure destination is set, jobs that already deliver via `announce` fall back to that primary announce target on failure.
 - `delivery.failureDestination` is only supported for `sessionTarget="isolated"` jobs unless the job's primary `delivery.mode` is `"webhook"`.
 
 See [Cron Jobs](/automation/cron-jobs). Isolated cron executions are tracked as [background tasks](/automation/tasks).

docs/gateway/configuration.md

@@ -72,6 +72,8 @@ Schema tooling notes:
 
 - `openclaw config schema` prints the same JSON Schema family used by Control UI
   and config validation.
+- Treat that schema output as the canonical machine-readable contract for
+  `openclaw.json`; this overview and the configuration reference summarize it.
 - Field `title` and `description` values are carried into the schema output for
   editor and form tooling.
 - Nested object, wildcard (`*`), and array-item (`[]`) entries inherit the same
@@ -84,6 +86,8 @@ Schema tooling notes:
   summaries for drill-down tooling.
 - Runtime plugin/channel schemas are merged in when the gateway can load the
   current manifest registry.
+- `pnpm config:docs:check` detects drift between docs-facing config baseline
+  artifacts and the current schema surface.
 
 When validation fails:
 

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:
@@ -312,6 +323,11 @@ Anthropic setup-token path.
 Refresh prompts only appear when running interactively (TTY); `--non-interactive`
 skips refresh attempts.
 
+When an OAuth refresh fails permanently (for example `refresh_token_reused`,
+`invalid_grant`, or a provider telling you to sign in again), doctor reports
+that re-auth is required and prints the exact `openclaw models auth login --provider ...`
+command to run.
+
 Doctor also reports auth profiles that are temporarily unusable due to:
 
 - short cooldowns (rate limits/timeouts/auth failures)

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

@@ -701,7 +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).
@@ -1816,8 +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>
@@ -2254,7 +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

@@ -272,6 +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:
 
@@ -300,6 +301,8 @@ 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.
 - 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`)
 
@@ -447,7 +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).
 

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/plugins/architecture.md

@@ -610,9 +610,10 @@ conversation, and it runs after core approval handling finishes.
 Provider plugins now have two layers:
 
 - 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
+  before runtime load, `providerAuthAliases` for provider variants that share
+  auth, `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`,
   `normalizeConfig`,
@@ -640,8 +641,10 @@ needing a whole custom inference transport.
 
 Use manifest `providerAuthEnvVars` when the provider has env-based credentials
 that generic auth/status/model-picker paths should see without loading plugin
-runtime. Use manifest `providerAuthChoices` when onboarding/auth-choice CLI
-surfaces should know the provider's choice id, group labels, and simple
+runtime. Use manifest `providerAuthAliases` when one provider id should reuse
+another provider id's env vars, auth profiles, config-backed auth, and API-key
+onboarding choice. Use manifest `providerAuthChoices` when onboarding/auth-choice
+CLI surfaces should know the provider's choice id, group labels, and simple
 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.
@@ -1134,6 +1137,9 @@ 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`,
@@ -1152,9 +1158,9 @@ 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

docs/plugins/manifest.md

@@ -93,6 +93,9 @@ Those belong in your plugin code and `package.json`.
   "providerAuthEnvVars": {
     "openrouter": ["OPENROUTER_API_KEY"]
   },
+  "providerAuthAliases": {
+    "openrouter-coding": "openrouter"
+  },
   "channelEnvVars": {
     "openrouter-chatops": ["OPENROUTER_CHATOPS_TOKEN"]
   },
@@ -145,6 +148,7 @@ 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.                                                                                                                      |
+| `providerAuthAliases`               | No       | `Record<string, string>`         | Provider ids that should reuse another provider id for auth lookup, for example a coding provider that shares the base provider API key and auth profiles.                                                   |
 | `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. |
@@ -440,6 +444,9 @@ 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.
+- `providerAuthAliases` lets provider variants reuse another provider's auth
+  env vars, auth profiles, config-backed auth, and API-key onboarding choice
+  without hardcoding that relationship in core.
 - `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.

docs/plugins/memory-wiki.md

@@ -0,0 +1,357 @@
+---
+summary: "memory-wiki: compiled knowledge vault with provenance, claims, dashboards, and bridge mode"
+read_when:
+  - You want persistent knowledge beyond plain MEMORY.md notes
+  - You are configuring the bundled memory-wiki plugin
+  - You want to understand wiki_search, wiki_get, or bridge mode
+title: "Memory Wiki"
+---
+
+# Memory Wiki
+
+`memory-wiki` is a bundled plugin that turns durable memory into a compiled
+knowledge vault.
+
+It does **not** replace the active memory plugin. The active memory plugin still
+owns recall, promotion, indexing, and dreaming. `memory-wiki` sits beside it
+and compiles durable knowledge into a navigable wiki with deterministic pages,
+structured claims, provenance, dashboards, and machine-readable digests.
+
+Use it when you want memory to behave more like a maintained knowledge layer and
+less like a pile of Markdown files.
+
+## What it adds
+
+- A dedicated wiki vault with deterministic page layout
+- Structured claim and evidence metadata, not just prose
+- Page-level provenance, confidence, contradictions, and open questions
+- Compiled digests for agent/runtime consumers
+- Wiki-native search/get/apply/lint tools
+- Optional bridge mode that imports public artifacts from the active memory plugin
+- Optional Obsidian-friendly render mode and CLI integration
+
+## How it fits with memory
+
+Think of the split like this:
+
+| Layer                                                   | Owns                                                                                       |
+| ------------------------------------------------------- | ------------------------------------------------------------------------------------------ |
+| Active memory plugin (`memory-core`, QMD, Honcho, etc.) | Recall, semantic search, promotion, dreaming, memory runtime                               |
+| `memory-wiki`                                           | Compiled wiki pages, provenance-rich syntheses, dashboards, wiki-specific search/get/apply |
+
+If the active memory plugin exposes shared recall artifacts, OpenClaw can search
+both layers in one pass with `memory_search corpus=all`.
+
+When you need wiki-specific ranking, provenance, or direct page access, use the
+wiki-native tools instead.
+
+## Vault modes
+
+`memory-wiki` supports three vault modes:
+
+### `isolated`
+
+Own vault, own sources, no dependency on `memory-core`.
+
+Use this when you want the wiki to be its own curated knowledge store.
+
+### `bridge`
+
+Reads public memory artifacts and memory events from the active memory plugin
+through public plugin SDK seams.
+
+Use this when you want the wiki to compile and organize the memory plugin's
+exported artifacts without reaching into private plugin internals.
+
+Bridge mode can index:
+
+- exported memory artifacts
+- dream reports
+- daily notes
+- memory root files
+- memory event logs
+
+### `unsafe-local`
+
+Explicit same-machine escape hatch for local private paths.
+
+This mode is intentionally experimental and non-portable. Use it only when you
+understand the trust boundary and specifically need local filesystem access that
+bridge mode cannot provide.
+
+## Vault layout
+
+The plugin initializes a vault like this:
+
+```text
+<vault>/
+  AGENTS.md
+  WIKI.md
+  index.md
+  inbox.md
+  entities/
+  concepts/
+  syntheses/
+  sources/
+  reports/
+  _attachments/
+  _views/
+  .openclaw-wiki/
+```
+
+Managed content stays inside generated blocks. Human note blocks are preserved.
+
+The main page groups are:
+
+- `sources/` for imported raw material and bridge-backed pages
+- `entities/` for durable things, people, systems, projects, and objects
+- `concepts/` for ideas, abstractions, patterns, and policies
+- `syntheses/` for compiled summaries and maintained rollups
+- `reports/` for generated dashboards
+
+## Structured claims and evidence
+
+Pages can carry structured `claims` frontmatter, not just freeform text.
+
+Each claim can include:
+
+- `id`
+- `text`
+- `status`
+- `confidence`
+- `evidence[]`
+- `updatedAt`
+
+Evidence entries can include:
+
+- `sourceId`
+- `path`
+- `lines`
+- `weight`
+- `note`
+- `updatedAt`
+
+This is what makes the wiki act more like a belief layer than a passive note
+dump. Claims can be tracked, scored, contested, and resolved back to sources.
+
+## Compile pipeline
+
+The compile step reads wiki pages, normalizes summaries, and emits stable
+machine-facing artifacts under:
+
+- `.openclaw-wiki/cache/agent-digest.json`
+- `.openclaw-wiki/cache/claims.jsonl`
+
+These digests exist so agents and runtime code do not have to scrape Markdown
+pages.
+
+Compiled output also powers:
+
+- first-pass wiki indexing for search/get flows
+- claim-id lookup back to owning pages
+- compact prompt supplements
+- report/dashboard generation
+
+## Dashboards and health reports
+
+When `render.createDashboards` is enabled, compile maintains dashboards under
+`reports/`.
+
+Built-in reports include:
+
+- `reports/open-questions.md`
+- `reports/contradictions.md`
+- `reports/low-confidence.md`
+- `reports/claim-health.md`
+- `reports/stale-pages.md`
+
+These reports track things like:
+
+- contradiction note clusters
+- competing claim clusters
+- claims missing structured evidence
+- low-confidence pages and claims
+- stale or unknown freshness
+- pages with unresolved questions
+
+## Search and retrieval
+
+`memory-wiki` supports two search backends:
+
+- `shared`: use the shared memory search flow when available
+- `local`: search the wiki locally
+
+It also supports three corpora:
+
+- `wiki`
+- `memory`
+- `all`
+
+Important behavior:
+
+- `wiki_search` and `wiki_get` use compiled digests as a first pass when possible
+- claim ids can resolve back to the owning page
+- contested/stale/fresh claims influence ranking
+- provenance labels can survive into results
+
+Practical rule:
+
+- use `memory_search corpus=all` for one broad recall pass
+- use `wiki_search` + `wiki_get` when you care about wiki-specific ranking,
+  provenance, or page-level belief structure
+
+## Agent tools
+
+The plugin registers these tools:
+
+- `wiki_status`
+- `wiki_search`
+- `wiki_get`
+- `wiki_apply`
+- `wiki_lint`
+
+What they do:
+
+- `wiki_status`: current vault mode, health, Obsidian CLI availability
+- `wiki_search`: search wiki pages and, when configured, shared memory corpora
+- `wiki_get`: read a wiki page by id/path or fall back to shared memory corpus
+- `wiki_apply`: narrow synthesis/metadata mutations without freeform page surgery
+- `wiki_lint`: structural checks, provenance gaps, contradictions, open questions
+
+The plugin also registers a non-exclusive memory corpus supplement, so shared
+`memory_search` and `memory_get` can reach the wiki when the active memory
+plugin supports corpus selection.
+
+## Prompt and context behavior
+
+When `context.includeCompiledDigestPrompt` is enabled, memory prompt sections
+append a compact compiled snapshot from `agent-digest.json`.
+
+That snapshot is intentionally small and high-signal:
+
+- top pages only
+- top claims only
+- contradiction count
+- question count
+- confidence/freshness qualifiers
+
+This is opt-in because it changes prompt shape and is mainly useful for context
+engines or legacy prompt assembly that explicitly consume memory supplements.
+
+## Configuration
+
+Put config under `plugins.entries.memory-wiki.config`:
+
+```json5
+{
+  plugins: {
+    entries: {
+      "memory-wiki": {
+        enabled: true,
+        config: {
+          vaultMode: "isolated",
+          vault: {
+            path: "~/.openclaw/wiki/main",
+            renderMode: "obsidian",
+          },
+          obsidian: {
+            enabled: true,
+            useOfficialCli: true,
+            vaultName: "OpenClaw Wiki",
+            openAfterWrites: false,
+          },
+          bridge: {
+            enabled: false,
+            readMemoryArtifacts: true,
+            indexDreamReports: true,
+            indexDailyNotes: true,
+            indexMemoryRoot: true,
+            followMemoryEvents: true,
+          },
+          ingest: {
+            autoCompile: true,
+            maxConcurrentJobs: 1,
+            allowUrlIngest: true,
+          },
+          search: {
+            backend: "shared",
+            corpus: "wiki",
+          },
+          context: {
+            includeCompiledDigestPrompt: false,
+          },
+          render: {
+            preserveHumanBlocks: true,
+            createBacklinks: true,
+            createDashboards: true,
+          },
+        },
+      },
+    },
+  },
+}
+```
+
+Key toggles:
+
+- `vaultMode`: `isolated`, `bridge`, `unsafe-local`
+- `vault.renderMode`: `native` or `obsidian`
+- `bridge.readMemoryArtifacts`: import active memory plugin public artifacts
+- `bridge.followMemoryEvents`: include event logs in bridge mode
+- `search.backend`: `shared` or `local`
+- `search.corpus`: `wiki`, `memory`, or `all`
+- `context.includeCompiledDigestPrompt`: append compact digest snapshot to memory prompt sections
+- `render.createBacklinks`: generate deterministic related blocks
+- `render.createDashboards`: generate dashboard pages
+
+## CLI
+
+`memory-wiki` also exposes a top-level CLI surface:
+
+```bash
+openclaw wiki status
+openclaw wiki doctor
+openclaw wiki init
+openclaw wiki ingest ./notes/alpha.md
+openclaw wiki compile
+openclaw wiki lint
+openclaw wiki search "alpha"
+openclaw wiki get entity.alpha
+openclaw wiki apply synthesis "Alpha Summary" --body "..." --source-id source.alpha
+openclaw wiki bridge import
+openclaw wiki obsidian status
+```
+
+See [CLI: wiki](/cli/wiki) for the full command reference.
+
+## Obsidian support
+
+When `vault.renderMode` is `obsidian`, the plugin writes Obsidian-friendly
+Markdown and can optionally use the official `obsidian` CLI.
+
+Supported workflows include:
+
+- status probing
+- vault search
+- opening a page
+- invoking an Obsidian command
+- jumping to the daily note
+
+This is optional. The wiki still works in native mode without Obsidian.
+
+## Recommended workflow
+
+1. Keep your active memory plugin for recall/promotion/dreaming.
+2. Enable `memory-wiki`.
+3. Start with `isolated` mode unless you explicitly want bridge mode.
+4. Use `wiki_search` / `wiki_get` when provenance matters.
+5. Use `wiki_apply` for narrow syntheses or metadata updates.
+6. Run `wiki_lint` after meaningful changes.
+7. Turn on dashboards if you want stale/contradiction visibility.
+
+## Related docs
+
+- [Memory Overview](/concepts/memory)
+- [CLI: memory](/cli/memory)
+- [CLI: wiki](/cli/wiki)
+- [Plugin SDK overview](/plugins/sdk-overview)

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`,

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 |
@@ -232,6 +262,7 @@ Current bundled provider examples:
   | `plugin-sdk/request-url` | Request URL helpers | Extract string URLs from request-like inputs |
   | `plugin-sdk/run-command` | Timed command helpers | Timed command runner with normalized stdout/stderr |
   | `plugin-sdk/param-readers` | Param readers | Common tool/CLI param readers |
+  | `plugin-sdk/tool-payload` | Tool payload extraction | Extract normalized payloads from tool result objects |
   | `plugin-sdk/tool-send` | Tool send extraction | Extract canonical send target fields from tool args |
   | `plugin-sdk/temp-path` | Temp path helpers | Shared temp-download path helpers |
   | `plugin-sdk/logging-core` | Logging helpers | Subsystem logger and redaction helpers |
@@ -249,7 +280,8 @@ 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-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-config-contract` | Provider web-search config helpers | Narrow web-search config/credential helpers for providers that do not need plugin-enable wiring |
+  | `plugin-sdk/provider-web-search-contract` | Provider web-search contract helpers | Narrow web-search config/credential contract helpers such as `createWebSearchProviderContractFields`, `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 |

docs/plugins/sdk-overview.md

@@ -135,7 +135,8 @@ explicitly promotes one as public.
     | `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-contract` | Narrow web-search config/credential contract helpers such as `enablePluginInConfig`, `resolveProviderWebSearchPluginConfig`, and scoped credential setters/getters |
+    | `plugin-sdk/provider-web-search-config-contract` | Narrow web-search config/credential helpers for providers that do not need plugin-enable wiring |
+    | `plugin-sdk/provider-web-search-contract` | Narrow web-search config/credential contract helpers such as `createWebSearchProviderContractFields`, `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 |
@@ -151,6 +152,9 @@ 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 |
@@ -172,6 +176,7 @@ 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 |
@@ -196,6 +201,7 @@ explicitly promotes one as public.
     | `plugin-sdk/request-url` | Extract string URLs from fetch/request-like inputs |
     | `plugin-sdk/run-command` | Timed command runner with normalized stdout/stderr results |
     | `plugin-sdk/param-readers` | Common tool/CLI param readers |
+    | `plugin-sdk/tool-payload` | Extract normalized payloads from tool result objects |
     | `plugin-sdk/tool-send` | Extract canonical send target fields from tool args |
     | `plugin-sdk/temp-path` | Shared temp-download path helpers |
     | `plugin-sdk/logging-core` | Subsystem logger and redaction helpers |
@@ -383,13 +389,13 @@ AI CLI backend such as `codex-cli`.
 
 ### Exclusive slots
 
-| 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                |
+| Method                                     | What it registers                                                                                                                                         |
+| ------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `api.registerContextEngine(id, factory)`   | Context engine (one active at a time). The `assemble()` callback receives `availableTools` and `citationsMode` so the engine can tailor prompt additions. |
+| `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                                                                                                                                    |
 
 ### Memory embedding adapters
 

docs/plugins/sdk-provider-plugins.md

@@ -58,6 +58,9 @@ API key auth, and dynamic model resolution.
       "providerAuthEnvVars": {
         "acme-ai": ["ACME_AI_API_KEY"]
       },
+      "providerAuthAliases": {
+        "acme-ai-coding": "acme-ai"
+      },
       "providerAuthChoices": [
         {
           "provider": "acme-ai",
@@ -80,9 +83,10 @@ API key auth, and dynamic model resolution.
     </CodeGroup>
 
     The manifest declares `providerAuthEnvVars` so OpenClaw can detect
-    credentials without loading your plugin runtime. `modelSupport` is optional
-    and lets OpenClaw auto-load your provider plugin from shorthand model ids
-    like `acme-large` before runtime hooks exist. If you publish the
+    credentials without loading your plugin runtime. Add `providerAuthAliases`
+    when a provider variant should reuse another provider id's auth. `modelSupport`
+    is optional and lets OpenClaw auto-load your provider plugin from shorthand
+    model ids like `acme-large` before runtime hooks exist. If you publish the
     provider on ClawHub, those `openclaw.compat` and `openclaw.build` fields
     are required in `package.json`.
 
@@ -707,7 +711,7 @@ Do not use the legacy skill-only publish alias here; plugin packages should use
 ```
 <bundled-plugin-root>/acme-ai/
 ├── package.json              # openclaw.providers metadata
-├── openclaw.plugin.json      # Manifest with providerAuthEnvVars
+├── openclaw.plugin.json      # Manifest with provider auth metadata
 ├── index.ts                  # definePluginEntry + registerProvider
 └── src/
     ├── provider.test.ts      # Tests

docs/providers/glm.md

@@ -35,7 +35,7 @@ openclaw onboard --auth-choice zai-cn
 ```json5
 {
   env: { ZAI_API_KEY: "sk-..." },
-  agents: { defaults: { model: { primary: "zai/glm-5" } } },
+  agents: { defaults: { model: { primary: "zai/glm-5.1" } } },
 }
 ```
 
@@ -64,5 +64,5 @@ OpenClaw currently seeds the bundled `zai` provider with these GLM refs:
 ## Notes
 
 - GLM versions and availability can change; check Z.AI's docs for the latest.
-- Default bundled model ref is `zai/glm-5`.
+- Default bundled model ref is `zai/glm-5.1`.
 - For provider details, see [/providers/zai](/providers/zai).

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`
@@ -98,6 +98,9 @@ Gemini CLI JSON usage notes:
 | Video understanding    | Yes               |
 | Web search (Grounding) | Yes               |
 | Thinking/reasoning     | Yes (Gemini 3.1+) |
+| Gemma 4 models         | Yes               |
+
+Gemma 4 models (for example `gemma-4-26b-a4b-it`) support thinking mode. OpenClaw rewrites `thinkingBudget` to a supported Google `thinkingLevel` for Gemma 4. Setting thinking to `off` preserves thinking disabled instead of mapping to `MINIMAL`.
 
 ## Direct Gemini cache reuse
 

docs/providers/index.md

@@ -42,6 +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 google/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/google/gemma-4-E2B-it" },
+      models: {
+        "inferrs/google/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: "google/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":"google/gemma-4-E2B-it","messages":[{"role":"user","content":"What is 2 + 2?"}],"stream":false}'
+
+openclaw infer model run \
+  --model inferrs/google/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/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" },
     },
   },
 }
@@ -119,7 +119,8 @@ openclaw models set ollama/glm-4.7-flash
 When you set `OLLAMA_API_KEY` (or an auth profile) and **do not** define `models.providers.ollama`, OpenClaw discovers models from the local Ollama instance at `http://127.0.0.1:11434`:
 
 - Queries `/api/tags`
-- Uses best-effort `/api/show` lookups to read `contextWindow` when available
+- Uses best-effort `/api/show` lookups to read `contextWindow` and detect capabilities (including vision) when available
+- Models with a `vision` capability reported by `/api/show` are marked as image-capable (`input: ["text", "image"]`), so OpenClaw auto-injects images into the prompt for those models
 - Marks `reasoning` with a model-name heuristic (`r1`, `reasoning`, `think`)
 - Sets `maxTokens` to the default Ollama max-token cap used by OpenClaw
 - Sets all costs to `0`
@@ -229,7 +230,7 @@ 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 +356,7 @@ 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/zai.md

@@ -36,7 +36,7 @@ openclaw onboard --auth-choice zai-cn
 ```json5
 {
   env: { ZAI_API_KEY: "sk-..." },
-  agents: { defaults: { model: { primary: "zai/glm-5" } } },
+  agents: { defaults: { model: { primary: "zai/glm-5.1" } } },
 }
 ```
 
@@ -65,7 +65,7 @@ OpenClaw currently seeds the bundled `zai` provider with:
 ## Notes
 
 - GLM models are available as `zai/<model>` (example: `zai/glm-5`).
-- Default bundled model ref: `zai/glm-5`
+- Default bundled model ref: `zai/glm-5.1`
 - Unknown `glm-5*` ids still forward-resolve on the bundled provider path by
   synthesizing provider-owned metadata from the `glm-4.7` template when the id
   matches the current GLM-5 family shape.

docs/refactor/qa.md

@@ -0,0 +1,530 @@
+# 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/index.md` plus one file per
+scenario under `qa/scenarios/*.md`.
+
+Implemented:
+
+- `qa/scenarios/index.md`
+  - canonical QA pack metadata
+  - operator identity
+  - kickoff mission
+- `qa/scenarios/*.md`
+  - one markdown file per scenario
+  - scenario metadata
+  - handler bindings
+  - scenario-specific execution config
+- `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/index.md` plus `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/index.md`
+- split scenarios into `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/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/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:

docs/tools/exec-approvals.md

@@ -557,8 +557,8 @@ Shared behavior:
 - Slack approvers can be explicit (`execApprovals.approvers`) or inferred from `commands.ownerAllowFrom`
 - Slack native buttons preserve approval id kind, so `plugin:` ids can resolve plugin approvals
   without a second Slack-local fallback layer
-- Matrix native DM/channel routing is exec-only; Matrix plugin approvals stay on the shared
-  same-chat `/approve` and optional `approvals.plugin` forwarding paths
+- Matrix native DM/channel routing and reaction shortcuts handle both exec and plugin approvals;
+  plugin authorization still comes from `channels.matrix.dm.allowFrom`
 - the requester does not need to be an approver
 - the originating chat can approve directly with `/approve` when that chat already supports commands and replies
 - native Discord approval buttons route by approval id kind: `plugin:` ids go

docs/tools/slash-commands.md

@@ -39,7 +39,10 @@ They run immediately, are stripped before the model sees the message, and the re
     mcp: false,
     plugins: false,
     debug: false,
-    restart: false,
+    restart: true,
+    ownerAllowFrom: ["discord:123456789012345678"],
+    ownerDisplay: "raw",
+    ownerDisplaySecret: "${OWNER_ID_HASH_SECRET}",
     allowFrom: {
       "*": ["user1"],
       discord: ["user:123"],
@@ -64,6 +67,10 @@ They run immediately, are stripped before the model sees the message, and the re
 - `commands.mcp` (default `false`) enables `/mcp` (reads/writes OpenClaw-managed MCP config under `mcp.servers`).
 - `commands.plugins` (default `false`) enables `/plugins` (plugin discovery/status plus install + enable/disable controls).
 - `commands.debug` (default `false`) enables `/debug` (runtime-only overrides).
+- `commands.restart` (default `true`) enables `/restart` plus gateway restart tool actions.
+- `commands.ownerAllowFrom` (optional) sets the explicit owner allowlist for owner-only command/tool surfaces. This is separate from `commands.allowFrom`.
+- `commands.ownerDisplay` controls how owner ids appear in the system prompt: `raw` or `hash`.
+- `commands.ownerDisplaySecret` optionally sets the HMAC secret used when `commands.ownerDisplay="hash"`.
 - `commands.allowFrom` (optional) sets a per-provider allowlist for command authorization. When configured, it is the
   only authorization source for commands and directives (channel allowlists/pairing and `commands.useAccessGroups`
   are ignored). Use `"*"` for a global default; provider-specific keys override it.
@@ -71,65 +78,94 @@ They run immediately, are stripped before the model sees the message, and the re
 
 ## Command list
 
-Text + native (when enabled):
+Current source-of-truth:
 
-- `/help`
-- `/commands`
-- `/tools [compact|verbose]` (show what the current agent can use right now; `verbose` adds descriptions)
-- `/skill <name> [input]` (run a skill by name)
-- `/status` (show current status; includes provider usage/quota for the current model provider when available)
-- `/tasks` (list background tasks for the current session; shows active and recent task details with agent-local fallback counts)
-- `/allowlist` (list/add/remove allowlist entries)
-- `/approve <id> <decision>` (resolve exec approval prompts; use the pending approval message for the available decisions)
-- `/context [list|detail|json]` (explain “context”; `detail` shows per-file + per-tool + per-skill + system prompt size)
-- `/btw <question>` (ask an ephemeral side question about the current session without changing future session context; see [/tools/btw](/tools/btw))
-- `/export-session [path]` (alias: `/export`) (export current session to HTML with full system prompt)
-- `/whoami` (show your sender id; alias: `/id`)
-- `/session idle <duration|off>` (manage inactivity auto-unfocus for focused thread bindings)
-- `/session max-age <duration|off>` (manage hard max-age auto-unfocus for focused thread bindings)
-- `/subagents list|kill|log|info|send|steer|spawn` (inspect, control, or spawn sub-agent runs for the current session)
-- `/acp spawn|cancel|steer|close|status|set-mode|set|cwd|permissions|timeout|model|reset-options|doctor|install|sessions` (inspect and control ACP runtime sessions)
-- `/agents` (list thread-bound agents for this session)
-- `/focus <target>` (Discord: bind this thread, or a new thread, to a session/subagent target)
-- `/unfocus` (Discord: remove the current thread binding)
-- `/kill <id|#|all>` (immediately abort one or all running sub-agents for this session; no confirmation message)
-- `/steer <id|#> <message>` (steer a running sub-agent immediately: in-run when possible, otherwise abort current work and restart on the steer message)
-- `/tell <id|#> <message>` (alias for `/steer`)
-- `/config show|get|set|unset` (persist config to disk, owner-only; requires `commands.config: true`)
-- `/mcp show|get|set|unset` (manage OpenClaw MCP server config, owner-only; requires `commands.mcp: true`)
-- `/plugins list|show|get|install|enable|disable` (inspect discovered plugins, install new ones, and toggle enablement; owner-only for writes; requires `commands.plugins: true`)
-  - `/plugin` is an alias for `/plugins`.
-  - `/plugin install <spec>` accepts the same plugin specs as `openclaw plugins install`: local path/archive, npm package, or `clawhub:<pkg>`.
-  - Enable/disable writes still reply with a restart hint. On a watched foreground gateway, OpenClaw may perform that restart automatically right after the write.
-- `/debug show|set|unset|reset` (runtime overrides, owner-only; requires `commands.debug: true`)
-- `/usage off|tokens|full|cost` (per-response usage footer or local cost summary)
-- `/tts off|always|inbound|tagged|status|provider|limit|summary|audio` (control TTS; see [/tts](/tools/tts))
-  - Discord: native command is `/voice` (Discord reserves `/tts`); text `/tts` still works.
-- `/stop`
-- `/restart`
-- `/dock-telegram` (alias: `/dock_telegram`) (switch replies to Telegram)
-- `/dock-discord` (alias: `/dock_discord`) (switch replies to Discord)
-- `/dock-slack` (alias: `/dock_slack`) (switch replies to Slack)
-- `/activation mention|always` (groups only)
-- `/send on|off|inherit` (owner-only)
-- `/reset` or `/new [model]` (optional model hint; remainder is passed through)
-- `/think <off|minimal|low|medium|high|xhigh>` (dynamic choices by model/provider; aliases: `/thinking`, `/t`)
-- `/fast status|on|off` (omitting the arg shows the current effective fast-mode state)
-- `/verbose on|full|off` (alias: `/v`)
-- `/reasoning on|off|stream` (alias: `/reason`; when on, sends a separate message prefixed `Reasoning:`; `stream` = Telegram draft only)
-- `/elevated on|off|ask|full` (alias: `/elev`; `full` skips exec approvals)
-- `/exec host=<auto|sandbox|gateway|node> security=<deny|allowlist|full> ask=<off|on-miss|always> node=<id>` (send `/exec` to show current)
-- `/model <name>` (alias: `/models`; or `/<alias>` from `agents.defaults.models.*.alias`)
-- `/queue <mode>` (plus options like `debounce:2s cap:25 drop:summarize`; send `/queue` to see current settings)
-- `/bash <command>` (host-only; alias for `! <command>`; requires `commands.bash: true` + `tools.elevated` allowlists)
-- `/dreaming [on|off|status|help]` (toggle global dreaming or show status; see [Dreaming](/concepts/dreaming))
+- core built-ins come from `src/auto-reply/commands-registry.shared.ts`
+- generated dock commands come from `src/auto-reply/commands-registry.data.ts`
+- plugin commands come from plugin `registerCommand()` calls
+- actual availability on your gateway still depends on config flags, channel surface, and installed/enabled plugins
 
-Text-only:
+### Core built-in commands
 
-- `/compact [instructions]` (see [/concepts/compaction](/concepts/compaction))
-- `! <command>` (host-only; one at a time; use `!poll` + `!stop` for long-running jobs)
-- `!poll` (check output / status; accepts optional `sessionId`; `/bash poll` also works)
-- `!stop` (stop the running bash job; accepts optional `sessionId`; `/bash stop` also works)
+Built-in commands available today:
+
+- `/new [model]` starts a new session; `/reset` is the reset alias.
+- `/compact [instructions]` compacts the session context. See [/concepts/compaction](/concepts/compaction).
+- `/stop` aborts the current run.
+- `/session idle <duration|off>` and `/session max-age <duration|off>` manage thread-binding expiry.
+- `/think <off|minimal|low|medium|high|xhigh>` sets the thinking level. Aliases: `/thinking`, `/t`.
+- `/verbose on|off|full` toggles verbose output. Alias: `/v`.
+- `/fast [status|on|off]` shows or sets fast mode.
+- `/reasoning [on|off|stream]` toggles reasoning visibility. Alias: `/reason`.
+- `/elevated [on|off|ask|full]` toggles elevated mode. Alias: `/elev`.
+- `/exec host=<auto|sandbox|gateway|node> security=<deny|allowlist|full> ask=<off|on-miss|always> node=<id>` shows or sets exec defaults.
+- `/model [name|#|status]` shows or sets the model.
+- `/models [provider] [page] [limit=<n>|size=<n>|all]` lists providers or models for a provider.
+- `/queue <mode>` manages queue behavior (`steer`, `interrupt`, `followup`, `collect`, `steer-backlog`) plus options like `debounce:2s cap:25 drop:summarize`.
+- `/help` shows the short help summary.
+- `/commands` shows the generated command catalog.
+- `/tools [compact|verbose]` shows what the current agent can use right now.
+- `/status` shows runtime status, including provider usage/quota when available.
+- `/tasks` lists active/recent background tasks for the current session.
+- `/context [list|detail|json]` explains how context is assembled.
+- `/export-session [path]` exports the current session to HTML. Alias: `/export`.
+- `/whoami` shows your sender id. Alias: `/id`.
+- `/skill <name> [input]` runs a skill by name.
+- `/allowlist [list|add|remove] ...` manages allowlist entries. Text-only.
+- `/approve <id> <decision>` resolves exec approval prompts.
+- `/btw <question>` asks a side question without changing future session context. See [/tools/btw](/tools/btw).
+- `/subagents list|kill|log|info|send|steer|spawn` manages sub-agent runs for the current session.
+- `/acp spawn|cancel|steer|close|sessions|status|set-mode|set|cwd|permissions|timeout|model|reset-options|doctor|install|help` manages ACP sessions and runtime options.
+- `/focus <target>` binds the current Discord thread or Telegram topic/conversation to a session target.
+- `/unfocus` removes the current binding.
+- `/agents` lists thread-bound agents for the current session.
+- `/kill <id|#|all>` aborts one or all running sub-agents.
+- `/steer <id|#> <message>` sends steering to a running sub-agent. Alias: `/tell`.
+- `/config show|get|set|unset` reads or writes `openclaw.json`. Owner-only. Requires `commands.config: true`.
+- `/mcp show|get|set|unset` reads or writes OpenClaw-managed MCP server config under `mcp.servers`. Owner-only. Requires `commands.mcp: true`.
+- `/plugins list|inspect|show|get|install|enable|disable` inspects or mutates plugin state. `/plugin` is an alias. Owner-only for writes. Requires `commands.plugins: true`.
+- `/debug show|set|unset|reset` manages runtime-only config overrides. Owner-only. Requires `commands.debug: true`.
+- `/usage off|tokens|full|cost` controls the per-response usage footer or prints a local cost summary.
+- `/tts on|off|status|provider|limit|summary|audio|help` controls TTS. See [/tools/tts](/tools/tts).
+- `/restart` restarts OpenClaw when enabled. Default: enabled; set `commands.restart: false` to disable it.
+- `/activation mention|always` sets group activation mode.
+- `/send on|off|inherit` sets send policy. Owner-only.
+- `/bash <command>` runs a host shell command. Text-only. Alias: `! <command>`. Requires `commands.bash: true` plus `tools.elevated` allowlists.
+- `!poll [sessionId]` checks a background bash job.
+- `!stop [sessionId]` stops a background bash job.
+
+### Generated dock commands
+
+Dock commands are generated from channel plugins with native-command support. Current bundled set:
+
+- `/dock-discord` (alias: `/dock_discord`)
+- `/dock-mattermost` (alias: `/dock_mattermost`)
+- `/dock-slack` (alias: `/dock_slack`)
+- `/dock-telegram` (alias: `/dock_telegram`)
+
+### Bundled plugin commands
+
+Bundled plugins can add more slash commands. Current bundled commands in this repo:
+
+- `/dreaming [on|off|status|help]` toggles memory dreaming. See [Dreaming](/concepts/dreaming).
+- `/pair [qr|status|pending|approve|cleanup|notify]` manages device pairing/setup flow. See [Pairing](/channels/pairing).
+- `/phone status|arm <camera|screen|writes|all> [duration]|disarm` temporarily arms high-risk phone node commands.
+- `/voice status|list [limit]|set <voiceId|name>` manages Talk voice config. On Discord, the native command name is `/talkvoice`.
+- `/card ...` sends LINE rich card presets. See [LINE](/channels/line).
+- QQBot-only commands:
+  - `/bot-ping`
+  - `/bot-version`
+  - `/bot-help`
+  - `/bot-upgrade`
+  - `/bot-logs`
+
+### Dynamic skill commands
+
+User-invocable skills are also exposed as slash commands:
+
+- `/skill <name> [input]` always works as the generic entrypoint.
+- skills may also appear as direct commands like `/prose` when the skill/plugin registers them.
+- native skill-command registration is controlled by `commands.nativeSkills` and `channels.<provider>.commands.nativeSkills`.
 
 Notes:
 
@@ -140,6 +176,8 @@ Notes:
 - In multi-account channels, config-targeted `/allowlist --account <id>` and `/config set channels.<provider>.accounts.<id>...` also honor the target account's `configWrites`.
 - `/usage` controls the per-response usage footer; `/usage cost` prints a local cost summary from OpenClaw session logs.
 - `/restart` is enabled by default; set `commands.restart: false` to disable it.
+- `/plugins install <spec>` accepts the same plugin specs as `openclaw plugins install`: local path/archive, npm package, or `clawhub:<pkg>`.
+- `/plugins enable|disable` updates plugin config and may prompt for a restart.
 - Discord-only native command: `/vc join|leave|status` controls voice channels (requires `channels.discord.voice` and native commands; not available as text).
 - Discord thread-binding commands (`/focus`, `/unfocus`, `/agents`, `/session idle`, `/session max-age`) require effective thread bindings to be enabled (`session.threadBindings.enabled` and/or `channels.discord.threadBindings.enabled`).
 - ACP command reference and runtime behavior: [ACP Agents](/tools/acp-agents).

docs/tools/tts.md

@@ -59,7 +59,7 @@ so that provider must also be authenticated if you enable summaries.
 ## Is it enabled by default?
 
 No. Auto‑TTS is **off** by default. Enable it in config with
-`messages.tts.auto` or per session with `/tts always` (alias: `/tts on`).
+`messages.tts.auto` or locally with `/tts on`.
 
 When `messages.tts.provider` is unset, OpenClaw picks the first configured
 speech provider in registry auto-select order.
@@ -411,9 +411,7 @@ Discord note: `/tts` is a built-in Discord command, so OpenClaw registers
 
 ```
 /tts off
-/tts always
-/tts inbound
-/tts tagged
+/tts on
 /tts status
 /tts provider openai
 /tts limit 2000
@@ -425,7 +423,9 @@ Notes:
 
 - Commands require an authorized sender (allowlist/owner rules still apply).
 - `commands.text` or native command registration must be enabled.
-- `off|always|inbound|tagged` are per‑session toggles (`/tts on` is an alias for `/tts always`).
+- Config `messages.tts.auto` accepts `off|always|inbound|tagged`.
+- `/tts on` writes the local TTS preference to `always`; `/tts off` writes it to `off`.
+- Use config when you want `inbound` or `tagged` defaults.
 - `limit` and `summary` are stored in local prefs, not the main config.
 - `/tts audio` generates a one-off audio reply (does not toggle TTS on).
 - `/tts status` includes fallback visibility for the latest attempt: