Fix subagent wake loops and native /subagents targeting

* fix(feishu): comprehensive reply mechanism fix — outbound replyToId forwarding + topic-aware reply targeting

- Forward replyToId from ChannelOutboundContext through sendText/sendMedia
  to sendMessageFeishu/sendMarkdownCardFeishu/sendMediaFeishu, enabling
  reply-to-message via the message tool.

- Fix group reply targeting: use ctx.messageId (triggering message) in
  normal groups to prevent silent topic thread creation (#32980). Preserve
  ctx.rootId targeting for topic-mode groups (group_topic/group_topic_sender)
  and groups with explicit replyInThread config.

- Add regression tests for both fixes.

Fixes #32980
Fixes #32958
Related #19784

* fix: normalize Feishu delivery.to before comparing with messaging tool targets

- Add normalizeDeliveryTarget helper to strip user:/chat: prefixes for Feishu
- Apply normalization in matchesMessagingToolDeliveryTarget before comparison
- This ensures cron duplicate suppression works when session uses prefixed targets
  (user:ou_xxx) but messaging tool extract uses normalized bare IDs (ou_xxx)

Fixes review comment on PR #32755

(cherry picked from commit fc20106f16)

* fix(feishu): catch thrown SDK errors for withdrawn reply targets

The Feishu Lark SDK can throw exceptions (SDK errors with .code or
AxiosErrors with .response.data.code) for withdrawn/deleted reply
targets, in addition to returning error codes in the response object.

Wrap reply calls in sendMessageFeishu and sendCardFeishu with
try-catch to handle thrown withdrawn/not-found errors (230011,
231003) and fall back to client.im.message.create, matching the
existing response-level fallback behavior.

Also extract sendFallbackDirect helper to deduplicate the
direct-send fallback block across both functions.

Closes #33496

(cherry picked from commit ad0901aec1)

* feishu: forward outbound reply target context

(cherry picked from commit c129a691fcf552a1cebe1e8a22ea8611ffc3b377)

* feishu extension: tighten reply target fallback semantics

(cherry picked from commit f85ec610f267020b66713c09e648ec004b2e26f1)

* fix(feishu): align synthesized fallback typing and changelog attribution

* test(feishu): cover group_topic_sender reply targeting

---------

Co-authored-by: Xu Zimo <xuzimojimmy@163.com>
Co-authored-by: Munem Hashmi <munem.hashmi@gmail.com>
Co-authored-by: bmendonca3 <bmendonca3@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>

.dockerignore

@@ -51,6 +51,10 @@ vendor/
 # Keep the rest of apps/ and vendor/ excluded to avoid a large build context.
 !apps/shared/
 !apps/shared/OpenClawKit/
+!apps/shared/OpenClawKit/Sources/
+!apps/shared/OpenClawKit/Sources/OpenClawKit/
+!apps/shared/OpenClawKit/Sources/OpenClawKit/Resources/
+!apps/shared/OpenClawKit/Sources/OpenClawKit/Resources/tool-display.json
 !apps/shared/OpenClawKit/Tools/
 !apps/shared/OpenClawKit/Tools/CanvasA2UI/
 !apps/shared/OpenClawKit/Tools/CanvasA2UI/**

.github/actionlint.yaml

@@ -8,6 +8,7 @@ self-hosted-runner:
     - blacksmith-8vcpu-windows-2025
     - blacksmith-16vcpu-ubuntu-2404
     - blacksmith-16vcpu-windows-2025
+    - blacksmith-32vcpu-windows-2025
     - blacksmith-16vcpu-ubuntu-2404-arm
 
 # Ignore patterns for known issues

.github/actions/setup-node-env/action.yml

@@ -1,7 +1,7 @@
 name: Setup Node environment
 description: >
   Initialize submodules with retry, install Node 22, pnpm, optionally Bun,
-  and run pnpm install. Requires actions/checkout to run first.
+  and optionally run pnpm install. Requires actions/checkout to run first.
 inputs:
   node-version:
     description: Node.js version to install.
@@ -15,6 +15,14 @@ inputs:
     description: Whether to install Bun alongside Node.
     required: false
     default: "true"
+  use-sticky-disk:
+    description: Use Blacksmith sticky disks for pnpm store caching.
+    required: false
+    default: "false"
+  install-deps:
+    description: Whether to run pnpm install after environment setup.
+    required: false
+    default: "true"
   frozen-lockfile:
     description: Whether to use --frozen-lockfile for install.
     required: false
@@ -40,19 +48,20 @@ runs:
       uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
       with:
         node-version: ${{ inputs.node-version }}
-        check-latest: true
+        check-latest: false
 
     - name: Setup pnpm + cache store
       uses: ./.github/actions/setup-pnpm-store-cache
       with:
         pnpm-version: ${{ inputs.pnpm-version }}
         cache-key-suffix: "node22"
+        use-sticky-disk: ${{ inputs.use-sticky-disk }}
 
     - name: Setup Bun
       if: inputs.install-bun == 'true'
       uses: oven-sh/setup-bun@v2
       with:
-        bun-version: "1.3.9+cf6cdbbba"
+        bun-version: "1.3.9"
 
     - name: Runtime versions
       shell: bash
@@ -63,10 +72,12 @@ runs:
         if command -v bun &>/dev/null; then bun -v; fi
 
     - name: Capture node path
+      if: inputs.install-deps == 'true'
       shell: bash
       run: echo "NODE_BIN=$(dirname "$(node -p "process.execPath")")" >> "$GITHUB_ENV"
 
     - name: Install dependencies
+      if: inputs.install-deps == 'true'
       shell: bash
       env:
         CI: "true"

.github/actions/setup-pnpm-store-cache/action.yml

@@ -9,6 +9,18 @@ inputs:
     description: Suffix appended to the cache key.
     required: false
     default: "node22"
+  use-sticky-disk:
+    description: Use Blacksmith sticky disks instead of actions/cache for pnpm store.
+    required: false
+    default: "false"
+  use-restore-keys:
+    description: Whether to use restore-keys fallback for actions/cache.
+    required: false
+    default: "true"
+  use-actions-cache:
+    description: Whether to restore/save pnpm store with actions/cache.
+    required: false
+    default: "true"
 runs:
   using: composite
   steps:
@@ -38,7 +50,22 @@ runs:
       shell: bash
       run: echo "path=$(pnpm store path --silent)" >> "$GITHUB_OUTPUT"
 
-    - name: Restore pnpm store cache
+    - name: Mount pnpm store sticky disk
+      if: inputs.use-sticky-disk == 'true'
+      uses: useblacksmith/stickydisk@v1
+      with:
+        key: ${{ github.repository }}-pnpm-store-${{ runner.os }}-${{ inputs.cache-key-suffix }}
+        path: ${{ steps.pnpm-store.outputs.path }}
+
+    - name: Restore pnpm store cache (exact key only)
+      if: inputs.use-actions-cache == 'true' && inputs.use-sticky-disk != 'true' && inputs.use-restore-keys != 'true'
+      uses: actions/cache@v4
+      with:
+        path: ${{ steps.pnpm-store.outputs.path }}
+        key: ${{ runner.os }}-pnpm-store-${{ inputs.cache-key-suffix }}-${{ hashFiles('pnpm-lock.yaml') }}
+
+    - name: Restore pnpm store cache (with fallback keys)
+      if: inputs.use-actions-cache == 'true' && inputs.use-sticky-disk != 'true' && inputs.use-restore-keys == 'true'
       uses: actions/cache@v4
       with:
         path: ${{ steps.pnpm-store.outputs.path }}

.github/workflows/ci.yml

@@ -32,12 +32,13 @@ jobs:
   # Push to main keeps broad coverage.
   changed-scope:
     needs: [docs-scope]
-    if: needs.docs-scope.outputs.docs_only != 'true'
+    if: github.event_name == 'pull_request' && needs.docs-scope.outputs.docs_only != 'true'
     runs-on: blacksmith-16vcpu-ubuntu-2404
     outputs:
       run_node: ${{ steps.scope.outputs.run_node }}
       run_macos: ${{ steps.scope.outputs.run_macos }}
       run_android: ${{ steps.scope.outputs.run_android }}
+      run_windows: ${{ steps.scope.outputs.run_windows }}
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -57,75 +58,11 @@ jobs:
             BASE="${{ github.event.pull_request.base.sha }}"
           fi
 
-          CHANGED="$(git diff --name-only "$BASE" HEAD 2>/dev/null || echo "UNKNOWN")"
-          if [ "$CHANGED" = "UNKNOWN" ] || [ -z "$CHANGED" ]; then
-            # Fail-safe: run broad checks if detection fails.
-            echo "run_node=true" >> "$GITHUB_OUTPUT"
-            echo "run_macos=true" >> "$GITHUB_OUTPUT"
-            echo "run_android=true" >> "$GITHUB_OUTPUT"
-            exit 0
-          fi
-
-          run_node=false
-          run_macos=false
-          run_android=false
-          has_non_docs=false
-          has_non_native_non_docs=false
-
-          while IFS= read -r path; do
-            [ -z "$path" ] && continue
-            case "$path" in
-              docs/*|*.md|*.mdx)
-                continue
-                ;;
-              *)
-                has_non_docs=true
-                ;;
-            esac
-
-            case "$path" in
-              # Generated protocol models are already covered by protocol:check and
-              # should not force the full native macOS lane.
-              apps/macos/Sources/OpenClawProtocol/*|apps/shared/OpenClawKit/Sources/OpenClawProtocol/*)
-                ;;
-              apps/macos/*|apps/ios/*|apps/shared/*|Swabble/*)
-                run_macos=true
-                ;;
-            esac
-
-            case "$path" in
-              apps/android/*|apps/shared/*)
-                run_android=true
-                ;;
-            esac
-
-            case "$path" in
-              src/*|test/*|extensions/*|packages/*|scripts/*|ui/*|.github/*|openclaw.mjs|package.json|pnpm-lock.yaml|pnpm-workspace.yaml|tsconfig*.json|vitest*.ts|tsdown.config.ts|.oxlintrc.json|.oxfmtrc.jsonc)
-                run_node=true
-                ;;
-            esac
-
-            case "$path" in
-              apps/android/*|apps/ios/*|apps/macos/*|apps/shared/*|Swabble/*|appcast.xml)
-                ;;
-              *)
-                has_non_native_non_docs=true
-                ;;
-            esac
-          done <<< "$CHANGED"
-
-          # If there are non-doc files outside native app trees, keep Node checks enabled.
-          if [ "$run_node" = false ] && [ "$has_non_docs" = true ] && [ "$has_non_native_non_docs" = true ]; then
-            run_node=true
-          fi
-
-          echo "run_node=${run_node}" >> "$GITHUB_OUTPUT"
-          echo "run_macos=${run_macos}" >> "$GITHUB_OUTPUT"
-          echo "run_android=${run_android}" >> "$GITHUB_OUTPUT"
+          node scripts/ci-changed-scope.mjs --base "$BASE" --head HEAD
 
   # Build dist once for Node-relevant changes and share it with downstream jobs.
   build-artifacts:
-    needs: [docs-scope, changed-scope, check]
+    needs: [docs-scope, changed-scope]
     if: needs.docs-scope.outputs.docs_only != 'true' && (github.event_name == 'push' || needs.changed-scope.outputs.run_node == 'true')
     runs-on: blacksmith-16vcpu-ubuntu-2404
     steps:
@@ -138,6 +75,7 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           install-bun: "false"
+          use-sticky-disk: "true"
 
       - name: Build dist
         run: pnpm build
@@ -164,6 +102,7 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           install-bun: "false"
+          use-sticky-disk: "true"
 
       - name: Download dist artifact
         uses: actions/download-artifact@v4
@@ -175,7 +114,7 @@ jobs:
         run: pnpm release:check
 
   checks:
-    needs: [docs-scope, changed-scope, check]
+    needs: [docs-scope, changed-scope]
     if: needs.docs-scope.outputs.docs_only != 'true' && (github.event_name == 'push' || needs.changed-scope.outputs.run_node == 'true')
     runs-on: blacksmith-16vcpu-ubuntu-2404
     strategy:
@@ -207,6 +146,7 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           install-bun: "${{ matrix.runtime == 'bun' }}"
+          use-sticky-disk: "true"
 
       - name: Configure Node test resources
         if: (github.event_name != 'push' || matrix.runtime != 'bun') && matrix.task == 'test' && matrix.runtime == 'node'
@@ -223,8 +163,8 @@ jobs:
   # Types, lint, and format check.
   check:
     name: "check"
-    needs: [docs-scope]
-    if: needs.docs-scope.outputs.docs_only != 'true'
+    needs: [docs-scope, changed-scope]
+    if: needs.docs-scope.outputs.docs_only != 'true' && (github.event_name == 'push' || needs.changed-scope.outputs.run_node == 'true')
     runs-on: blacksmith-16vcpu-ubuntu-2404
     steps:
       - name: Checkout
@@ -236,6 +176,7 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           install-bun: "false"
+          use-sticky-disk: "true"
 
       - name: Check types and lint and oxfmt
         run: pnpm check
@@ -275,6 +216,7 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           install-bun: "false"
+          use-sticky-disk: "true"
 
       - name: Run ${{ matrix.tool }} dead-code scan
         run: ${{ matrix.command }}
@@ -300,6 +242,7 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           install-bun: "false"
+          use-sticky-disk: "true"
 
       - name: Check docs
         run: pnpm check:docs
@@ -342,6 +285,8 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           install-bun: "false"
+          use-sticky-disk: "false"
+          install-deps: "false"
 
       - name: Setup Python
         uses: actions/setup-python@v5
@@ -385,15 +330,15 @@ jobs:
         run: pre-commit run --all-files pnpm-audit-prod
 
   checks-windows:
-    needs: [docs-scope, changed-scope, build-artifacts, check]
-    if: needs.docs-scope.outputs.docs_only != 'true' && (github.event_name == 'push' || needs.changed-scope.outputs.run_node == 'true')
-    runs-on: blacksmith-16vcpu-windows-2025
+    needs: [docs-scope, changed-scope]
+    if: needs.docs-scope.outputs.docs_only != 'true' && (github.event_name == 'push' || needs.changed-scope.outputs.run_windows == 'true')
+    runs-on: blacksmith-32vcpu-windows-2025
     timeout-minutes: 45
     env:
-      NODE_OPTIONS: --max-old-space-size=4096
-      # Keep total concurrency predictable on the 16 vCPU runner:
-      # `scripts/test-parallel.mjs` runs some vitest suites in parallel processes.
-      OPENCLAW_TEST_WORKERS: 2
+      NODE_OPTIONS: --max-old-space-size=6144
+      # Keep total concurrency predictable on the 32 vCPU runner.
+      # Windows shard 2 has shown intermittent instability at 2 workers.
+      OPENCLAW_TEST_WORKERS: 1
     defaults:
       run:
         shell: bash
@@ -401,26 +346,36 @@ jobs:
       fail-fast: false
       matrix:
         include:
-          - runtime: node
-            task: lint
-            shard_index: 0
-            shard_count: 1
-            command: pnpm lint
           - runtime: node
             task: test
             shard_index: 1
-            shard_count: 2
-            command: pnpm canvas:a2ui:bundle && pnpm test
+            shard_count: 6
+            command: pnpm test
           - runtime: node
             task: test
             shard_index: 2
-            shard_count: 2
-            command: pnpm canvas:a2ui:bundle && pnpm test
+            shard_count: 6
+            command: pnpm test
           - runtime: node
-            task: protocol
-            shard_index: 0
-            shard_count: 1
-            command: pnpm protocol:check
+            task: test
+            shard_index: 3
+            shard_count: 6
+            command: pnpm test
+          - runtime: node
+            task: test
+            shard_index: 4
+            shard_count: 6
+            command: pnpm test
+          - runtime: node
+            task: test
+            shard_index: 5
+            shard_count: 6
+            command: pnpm test
+          - runtime: node
+            task: test
+            shard_index: 6
+            shard_count: 6
+            command: pnpm test
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -446,31 +401,22 @@ jobs:
             Write-Warning "Failed to apply Defender exclusions, continuing. $($_.Exception.Message)"
           }
 
-      - name: Download dist artifact (lint lane)
-        if: matrix.task == 'lint'
-        uses: actions/download-artifact@v4
-        with:
-          name: dist-build
-          path: dist/
-
-      - name: Verify dist artifact (lint lane)
-        if: matrix.task == 'lint'
-        run: |
-          set -euo pipefail
-          test -s dist/index.js
-          test -s dist/plugin-sdk/index.js
-
       - name: Setup Node.js
         uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
         with:
           node-version: 22.x
-          check-latest: true
+          check-latest: false
 
       - name: Setup pnpm + cache store
         uses: ./.github/actions/setup-pnpm-store-cache
         with:
           pnpm-version: "10.23.0"
           cache-key-suffix: "node22"
+          # Sticky disk mount currently retries/fails on every shard and adds ~50s
+          # before install while still yielding zero pnpm store reuse.
+          use-sticky-disk: "false"
+          use-restore-keys: "false"
+          use-actions-cache: "false"
 
       - name: Runtime versions
         run: |
@@ -489,7 +435,7 @@ jobs:
           which node
           node -v
           pnpm -v
-          pnpm install --frozen-lockfile --ignore-scripts=false --config.engine-strict=false --config.enable-pre-post-scripts=true || pnpm install --frozen-lockfile --ignore-scripts=false --config.engine-strict=false --config.enable-pre-post-scripts=true
+          pnpm install --frozen-lockfile --prefer-offline --ignore-scripts=false --config.engine-strict=false --config.enable-pre-post-scripts=true || pnpm install --frozen-lockfile --prefer-offline --ignore-scripts=false --config.engine-strict=false --config.enable-pre-post-scripts=true
 
       - name: Configure test shard (Windows)
         if: matrix.task == 'test'
@@ -497,6 +443,10 @@ jobs:
           echo "OPENCLAW_TEST_SHARDS=${{ matrix.shard_count }}" >> "$GITHUB_ENV"
           echo "OPENCLAW_TEST_SHARD_INDEX=${{ matrix.shard_index }}" >> "$GITHUB_ENV"
 
+      - name: Build A2UI bundle (Windows)
+        if: matrix.task == 'test'
+        run: pnpm canvas:a2ui:bundle
+
       - name: Run ${{ matrix.task }} (${{ matrix.runtime }})
         run: ${{ matrix.command }}
 
@@ -738,7 +688,7 @@ jobs:
           PY
 
   android:
-    needs: [docs-scope, changed-scope, check]
+    needs: [docs-scope, changed-scope]
     if: needs.docs-scope.outputs.docs_only != 'true' && (github.event_name == 'push' || needs.changed-scope.outputs.run_android == 'true')
     runs-on: blacksmith-16vcpu-ubuntu-2404
     strategy:

.github/workflows/docker-release.yml

@@ -34,8 +34,8 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v4
 
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+      - name: Set up Docker Builder
+        uses: useblacksmith/setup-docker-builder@v1
 
       - name: Login to GitHub Container Registry
         uses: docker/login-action@v3
@@ -92,14 +92,12 @@ jobs:
 
       - name: Build and push amd64 image
         id: build
-        uses: docker/build-push-action@v6
+        uses: useblacksmith/build-push-action@v2
         with:
           context: .
           platforms: linux/amd64
           tags: ${{ steps.tags.outputs.value }}
           labels: ${{ steps.labels.outputs.value }}
-          cache-from: type=registry,ref=${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-cache:amd64
-          cache-to: type=registry,ref=${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-cache:amd64,mode=max
           provenance: false
           push: true
 
@@ -115,8 +113,8 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v4
 
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+      - name: Set up Docker Builder
+        uses: useblacksmith/setup-docker-builder@v1
 
       - name: Login to GitHub Container Registry
         uses: docker/login-action@v3
@@ -173,14 +171,12 @@ jobs:
 
       - name: Build and push arm64 image
         id: build
-        uses: docker/build-push-action@v6
+        uses: useblacksmith/build-push-action@v2
         with:
           context: .
           platforms: linux/arm64
           tags: ${{ steps.tags.outputs.value }}
           labels: ${{ steps.labels.outputs.value }}
-          cache-from: type=registry,ref=${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-cache:arm64
-          cache-to: type=registry,ref=${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-cache:arm64,mode=max
           provenance: false
           push: true
 

.github/workflows/install-smoke.yml

@@ -44,10 +44,14 @@ jobs:
         with:
           pnpm-version: "10.23.0"
           cache-key-suffix: "node22"
+          use-sticky-disk: "true"
 
       - name: Install pnpm deps (minimal)
         run: pnpm install --ignore-scripts --frozen-lockfile
 
+      - name: Set up Docker Builder
+        uses: useblacksmith/setup-docker-builder@v1
+
       - name: Run root Dockerfile CLI smoke
         run: |
           docker build -t openclaw-dockerfile-smoke:local -f Dockerfile .

.github/workflows/sandbox-common-smoke.yml

@@ -26,6 +26,9 @@ jobs:
         with:
           submodules: false
 
+      - name: Set up Docker Builder
+        uses: useblacksmith/setup-docker-builder@v1
+
       - name: Build minimal sandbox base (USER sandbox)
         shell: bash
         run: |

.github/workflows/stale.yml

@@ -0,0 +1,155 @@
+name: Stale
+
+on:
+  schedule:
+    - cron: "17 3 * * *"
+  workflow_dispatch:
+
+permissions: {}
+
+jobs:
+  stale:
+    permissions:
+      issues: write
+      pull-requests: write
+    runs-on: blacksmith-16vcpu-ubuntu-2404
+    steps:
+      - uses: actions/create-github-app-token@d72941d797fd3113feb6b93fd0dec494b13a2547 # v1
+        id: app-token
+        continue-on-error: true
+        with:
+          app-id: "2729701"
+          private-key: ${{ secrets.GH_APP_PRIVATE_KEY }}
+      - uses: actions/create-github-app-token@d72941d797fd3113feb6b93fd0dec494b13a2547 # v1
+        id: app-token-fallback
+        if: steps.app-token.outcome == 'failure'
+        with:
+          app-id: "2971289"
+          private-key: ${{ secrets.GH_APP_PRIVATE_KEY_FALLBACK }}
+      - name: Mark stale issues and pull requests
+        uses: actions/stale@v9
+        with:
+          repo-token: ${{ steps.app-token.outputs.token || steps.app-token-fallback.outputs.token }}
+          days-before-issue-stale: 7
+          days-before-issue-close: 5
+          days-before-pr-stale: 5
+          days-before-pr-close: 3
+          stale-issue-label: stale
+          stale-pr-label: stale
+          exempt-issue-labels: enhancement,maintainer,pinned,security,no-stale
+          exempt-pr-labels: maintainer,no-stale
+          operations-per-run: 10000
+          exempt-all-assignees: true
+          remove-stale-when-updated: true
+          stale-issue-message: |
+            This issue has been automatically marked as stale due to inactivity.
+            Please add updates or it will be closed.
+          stale-pr-message: |
+            This pull request has been automatically marked as stale due to inactivity.
+            Please add updates or it will be closed.
+          close-issue-message: |
+            Closing due to inactivity.
+            If this is still an issue, please retry on the latest OpenClaw release and share updated details.
+            If you are absolutely sure it still happens on the latest release, open a new issue with fresh repro steps.
+          close-issue-reason: not_planned
+          close-pr-message: |
+            Closing due to inactivity.
+            If you believe this PR should be revived, post in #pr-thunderdome-dangerzone on Discord to talk to a maintainer.
+            That channel is the escape hatch for high-quality PRs that get auto-closed.
+
+  lock-closed-issues:
+    permissions:
+      issues: write
+    runs-on: blacksmith-16vcpu-ubuntu-2404
+    steps:
+      - uses: actions/create-github-app-token@d72941d797fd3113feb6b93fd0dec494b13a2547 # v1
+        id: app-token
+        with:
+          app-id: "2729701"
+          private-key: ${{ secrets.GH_APP_PRIVATE_KEY }}
+      - name: Lock closed issues after 48h of no comments
+        uses: actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b # v7
+        with:
+          github-token: ${{ steps.app-token.outputs.token }}
+          script: |
+            const lockAfterHours = 48;
+            const lockAfterMs = lockAfterHours * 60 * 60 * 1000;
+            const perPage = 100;
+            const cutoffMs = Date.now() - lockAfterMs;
+            const { owner, repo } = context.repo;
+
+            let locked = 0;
+            let inspected = 0;
+
+            let page = 1;
+            while (true) {
+              const { data: issues } = await github.rest.issues.listForRepo({
+                owner,
+                repo,
+                state: "closed",
+                sort: "updated",
+                direction: "desc",
+                per_page: perPage,
+                page,
+              });
+
+              if (issues.length === 0) {
+                break;
+              }
+
+              for (const issue of issues) {
+                if (issue.pull_request) {
+                  continue;
+                }
+                if (issue.locked) {
+                  continue;
+                }
+                if (!issue.closed_at) {
+                  continue;
+                }
+
+                inspected += 1;
+                const closedAtMs = Date.parse(issue.closed_at);
+                if (!Number.isFinite(closedAtMs)) {
+                  continue;
+                }
+                if (closedAtMs > cutoffMs) {
+                  continue;
+                }
+
+                let lastCommentMs = 0;
+                if (issue.comments > 0) {
+                  const { data: comments } = await github.rest.issues.listComments({
+                    owner,
+                    repo,
+                    issue_number: issue.number,
+                    per_page: 1,
+                    page: 1,
+                    sort: "created",
+                    direction: "desc",
+                  });
+
+                  if (comments.length > 0) {
+                    lastCommentMs = Date.parse(comments[0].created_at);
+                  }
+                }
+
+                const lastActivityMs = Math.max(closedAtMs, lastCommentMs || 0);
+                if (lastActivityMs > cutoffMs) {
+                  continue;
+                }
+
+                await github.rest.issues.lock({
+                  owner,
+                  repo,
+                  issue_number: issue.number,
+                  lock_reason: "resolved",
+                });
+
+                locked += 1;
+              }
+
+              page += 1;
+            }
+
+            core.info(`Inspected ${inspected} closed issues; locked ${locked}.`);

.gitignore

@@ -27,6 +27,7 @@ mise.toml
 apps/android/.gradle/
 apps/android/app/build/
 apps/android/.cxx/
+apps/android/.kotlin/
 
 # Bun build artifacts
 *.bun-build
@@ -94,7 +95,7 @@ USER.md
 !.agent/workflows/
 /local/
 package-lock.json
-.claude/settings.local.json
+.claude/
 .agents/
 .agents
 .agent/

.pi/extensions/prompt-url-widget.ts

@@ -114,6 +114,17 @@ export default function promptUrlWidgetExtension(pi: ExtensionAPI) {
     }
   };
 
+  const renderPromptMatch = (ctx: ExtensionContext, match: PromptMatch) => {
+    setWidget(ctx, match);
+    applySessionName(ctx, match);
+    void fetchGhMetadata(pi, match.kind, match.url).then((meta) => {
+      const title = meta?.title?.trim();
+      const authorText = formatAuthor(meta?.author);
+      setWidget(ctx, match, title, authorText);
+      applySessionName(ctx, match, title);
+    });
+  };
+
   pi.on("before_agent_start", async (event, ctx) => {
     if (!ctx.hasUI) {
       return;
@@ -123,14 +134,7 @@ export default function promptUrlWidgetExtension(pi: ExtensionAPI) {
       return;
     }
 
-    setWidget(ctx, match);
-    applySessionName(ctx, match);
-    void fetchGhMetadata(pi, match.kind, match.url).then((meta) => {
-      const title = meta?.title?.trim();
-      const authorText = formatAuthor(meta?.author);
-      setWidget(ctx, match, title, authorText);
-      applySessionName(ctx, match, title);
-    });
+    renderPromptMatch(ctx, match);
   });
 
   pi.on("session_switch", async (_event, ctx) => {
@@ -177,14 +181,7 @@ export default function promptUrlWidgetExtension(pi: ExtensionAPI) {
       return;
     }
 
-    setWidget(ctx, match);
-    applySessionName(ctx, match);
-    void fetchGhMetadata(pi, match.kind, match.url).then((meta) => {
-      const title = meta?.title?.trim();
-      const authorText = formatAuthor(meta?.author);
-      setWidget(ctx, match, title, authorText);
-      applySessionName(ctx, match, title);
-    });
+    renderPromptMatch(ctx, match);
   };
 
   pi.on("session_start", async (_event, ctx) => {

.pi/prompts/landpr.md

@@ -9,7 +9,7 @@ Input
   - If ambiguous: ask.
 
 Do (end-to-end)
-Goal: PR must end in GitHub state = MERGED (never CLOSED). Use `gh pr merge` with `--rebase` or `--squash`.
+Goal: PR must end in GitHub state = MERGED (never CLOSED). Prefer `gh pr merge --squash`; use `--rebase` only when preserving commit history is required.
 
 1. Assign PR to self:
    - `gh pr edit <PR> --add-assignee @me`
@@ -37,8 +37,8 @@ Goal: PR must end in GitHub state = MERGED (never CLOSED). Use `gh pr merge` wit
    - Implement fixes + add/adjust tests
    - Update `CHANGELOG.md` and mention `#<PR>` + `@$contrib`
 9. Decide merge strategy:
-   - Rebase if we want to preserve commit history
-   - Squash if we want a single clean commit
+   - Squash (preferred): use when we want a single clean commit
+   - Rebase: use only when we explicitly want to preserve commit history
    - If unclear, ask
 10. Full gate (BEFORE commit):
     - `pnpm lint && pnpm build && pnpm test`
@@ -54,8 +54,8 @@ Goal: PR must end in GitHub state = MERGED (never CLOSED). Use `gh pr merge` wit
     ```
 
 13. Merge PR (must show MERGED on GitHub):
-    - Rebase: `gh pr merge <PR> --rebase`
-    - Squash: `gh pr merge <PR> --squash`
+    - Squash (preferred): `gh pr merge <PR> --squash`
+    - Rebase (history-preserving fallback): `gh pr merge <PR> --rebase`
     - Never `gh pr close` (closing is wrong)
 14. Sync main:
     - `git checkout main`

AGENTS.md

@@ -5,6 +5,7 @@
 - GitHub issues/comments/PR comments: use literal multiline strings or `-F - <<'EOF'` (or $'...') for real newlines; never embed "\\n".
 - GitHub comment footgun: never use `gh issue/pr comment -b "..."` when body contains backticks or shell chars. Always use single-quoted heredoc (`-F - <<'EOF'`) so no command substitution/escaping corruption.
 - GitHub linking footgun: don’t wrap issue/PR refs like `#24643` in backticks when you want auto-linking. Use plain `#24643` (optionally add full URL).
+- GitHub searching footgun: don't limit yourself to the first 500 issues or PRs when wanting to search all. Unless you're supposed to look at the most recent, keep going until you've reached the last page in the search
 - Security advisory analysis: before triage/severity decisions, read `SECURITY.md` to align with OpenClaw's trust model and design boundaries.
 
 ## Project Structure & Module Organization
@@ -75,6 +76,8 @@
 - Language: TypeScript (ESM). Prefer strict typing; avoid `any`.
 - Formatting/linting via Oxlint and Oxfmt; run `pnpm check` before commits.
 - Never add `@ts-nocheck` and do not disable `no-explicit-any`; fix root causes and update Oxlint/Oxfmt config only when required.
+- Dynamic import guardrail: do not mix `await import("x")` and static `import ... from "x"` for the same module in production code paths. If you need lazy loading, create a dedicated `*.runtime.ts` boundary (that re-exports from `x`) and dynamically import that boundary from lazy callers only.
+- Dynamic import verification: after refactors that touch lazy-loading/module boundaries, run `pnpm build` and check for `[INEFFECTIVE_DYNAMIC_IMPORT]` warnings before submitting.
 - Never share class behavior via prototype mutation (`applyPrototypeMixins`, `Object.defineProperty` on `.prototype`, or exporting `Class.prototype` for merges). Use explicit inheritance/composition (`A extends B extends C`) or helper composition so TypeScript can typecheck.
 - If this pattern is needed, stop and get explicit approval before shipping; default behavior is to split/refactor into an explicit class hierarchy and keep members strongly typed.
 - In tests, prefer per-instance stubs over prototype mutation (`SomeClass.prototype.method = ...`) unless a test explicitly documents why prototype-level patching is required.

CHANGELOG.md

@@ -2,26 +2,337 @@
 
 Docs: https://docs.openclaw.ai
 
-## 2026.3.2 (Unreleased)
+## 2026.3.3
 
 ### Changes
 
-- Outbound adapters/plugins: add shared `sendPayload` support across direct-text-media, Discord, Slack, WhatsApp, Zalo, and Zalouser with multi-media iteration and chunk-aware text fallback. (#30144) Thanks @nohat.
-- Zalo Personal plugin (`@openclaw/zalouser`): rebuilt channel runtime to use native `zca-js` integration in-process, removing external CLI transport usage and keeping QR/login + send/listen flows fully inside OpenClaw.
-- CLI/Config validation: add `openclaw config validate` (with `--json`) to validate config files before gateway startup, and include detailed invalid-key paths in startup invalid-config errors. (#31220) thanks @Sid-Qin.
-- Sessions/Attachments: add inline file attachment support for `sessions_spawn` (subagent runtime only) with base64/utf8 encoding, transcript content redaction, lifecycle cleanup, and configurable limits via `tools.sessions_spawn.attachments`. (#16761) Thanks @napetrov.
-- Agents/Thinking defaults: set `adaptive` as the default thinking level for Anthropic Claude 4.6 models (including Bedrock Claude 4.6 refs) while keeping other reasoning-capable models at `low` unless explicitly configured.
+- Web UI/i18n: add Spanish (`es`) locale support in the Control UI, including locale detection, lazy loading, and language picker labels across supported locales. (#35038) Thanks @DaoPromociones.
+- Discord/allowBots mention gating: add `allowBots: "mentions"` to only accept bot-authored messages that mention the bot. Thanks @thewilloftheshadow.
+- Docs/Web search: remove outdated Brave free-tier wording and replace prescriptive AI ToS guidance with neutral compliance language in Brave setup docs. (#26860) Thanks @HenryLoenwind.
+- Tools/Web search: switch Perplexity provider to Search API with structured results plus new language/region/time filters. (#33822) Thanks @kesku.
+- Tools/Diffs guidance loading: move diffs usage guidance from unconditional prompt-hook injection to the plugin companion skill path, reducing unrelated-turn prompt noise while keeping diffs tool behavior unchanged. (#32630) thanks @sircrumpet.
+- Agents/tool-result truncation: preserve important tail diagnostics by using head+tail truncation for oversized tool results while keeping configurable truncation options. (#20076) thanks @jlwestsr.
+- Telegram/topic agent routing: support per-topic `agentId` overrides in forum groups and DM topics so topics can route to dedicated agents with isolated sessions. (#33647; based on #31513) Thanks @kesor and @Sid-Qin.
+- Slack/DM typing feedback: add `channels.slack.typingReaction` so Socket Mode DMs can show reaction-based processing status even when Slack native assistant typing is unavailable. (#19816) Thanks @dalefrieswthat.
+
+### Fixes
+
+- Security/dependency audit: patch transitive Hono vulnerabilities by pinning `hono` to `4.12.5` and `@hono/node-server` to `1.19.10` in production resolution paths. Thanks @shakkernerd.
+- Security/dependency audit: bump `tar` to `7.5.10` (from `7.5.9`) to address the high-severity hardlink path traversal advisory (`GHSA-qffp-2rhf-9h96`). Thanks @shakkernerd.
+- Auto-reply/system events: restore runtime system events to the message timeline (`System:` lines), preserve think-hint parsing with prepended events, and carry events into deferred followup/collect/steer-backlog prompts to keep cache behavior stable without dropping queued metadata. (#34794) Thanks @anisoptera.
+- Security/audit account handling: avoid prototype-chain account IDs in audit validation by using own-property checks for `accounts`. (#34982) Thanks @HOYALIM.
+- Agents/session usage tracking: preserve accumulated usage metadata on embedded Pi runner error exits so failed turns still update session `totalTokens` from real usage instead of stale prior values. (#34275) thanks @RealKai42.
+- Subagents/announce completion scoping: scope nested direct-child completion aggregation to the current requester run window, add coverage for completion-reply capture and steer-restart frozen-field resets, remove flaky waitFor polling from lifecycle retry-grace tests, align nested ended-session fallback e2e fixtures, and document nested announce delivery semantics for internal orchestration paths. Thanks @tyler6204.
+- Nodes/system.run approval hardening: use explicit argv-mutation signaling when regenerating prepared `rawCommand`, and cover the `system.run.prepare -> system.run` handoff so direct PATH-based `nodes.run` commands no longer fail with `rawCommand does not match command`. (#33137) thanks @Sid-Qin.
+- Models/custom provider headers: propagate `models.providers.<name>.headers` across inline, fallback, and registry-found model resolution so header-authenticated proxies consistently receive configured request headers. (#27490) thanks @Sid-Qin.
+- Ollama/custom provider headers: forward resolved model headers into native Ollama stream requests so header-authenticated Ollama proxies receive configured request headers. (#24337) thanks @echoVic.
+- Daemon/systemd install robustness: treat `systemctl --user is-enabled` exit-code-4 `not-found` responses as not-enabled by combining stderr/stdout detail parsing, so Ubuntu fresh installs no longer fail with `systemctl is-enabled unavailable`. (#33634) Thanks @Yuandiaodiaodiao.
+- Slack/system-event session routing: resolve reaction/member/pin/interaction system-event session keys through channel/account bindings (with sender-aware DM routing) so inbound Slack events target the correct agent session in multi-account setups instead of defaulting to `agent:main`. (#34045) Thanks @paulomcg, @daht-mad and @vincentkoc.
+- Gateway/HTTP tools invoke media compatibility: preserve raw media payload access for direct `/tools/invoke` clients by allowing media `nodes` invoke commands only in HTTP tool context, while keeping agent-context media invoke blocking to prevent base64 prompt bloat. (#34365) Thanks @obviyus.
+- Agents/Nodes media outputs: add dedicated `photos_latest` action handling, block media-returning `nodes invoke` commands, keep metadata-only `camera.list` invoke allowed, and normalize empty `photos_latest` results to a consistent response shape to prevent base64 context bloat. (#34332) Thanks @obviyus.
+- TUI/session-key canonicalization: normalize `openclaw tui --session` values to lowercase so uppercase session names no longer drop real-time streaming updates due to gateway/TUI key mismatches. (#33866, #34013) thanks @lynnzc.
+- Outbound/send config threading: pass resolved SecretRef config through outbound adapters and helper send paths so send flows do not reload unresolved runtime config. (#33987) Thanks @joshavant.
+- Sessions/subagent attachments: remove `attachments[].content.maxLength` from `sessions_spawn` schema to avoid llama.cpp GBNF repetition overflow, and preflight UTF-8 byte size before buffer allocation while keeping runtime file-size enforcement unchanged. (#33648) Thanks @anisoptera.
+- Runtime/tool-state stability: recover from dangling Anthropic `tool_use` after compaction, serialize long-running Discord handler runs without blocking new inbound events, and prevent stale busy snapshots from suppressing stuck-channel recovery. (from #33630, #33583) Thanks @kevinWangSheng and @theotarr.
+- ACP/Discord startup hardening: clean up stuck ACP worker children on gateway restart, unbind stale ACP thread bindings during Discord startup reconciliation, and add per-thread listener watchdog timeouts so wedged turns cannot block later messages. (#33699) Thanks @dutifulbob.
+- Extensions/media local-root propagation: consistently forward `mediaLocalRoots` through extension `sendMedia` adapters (Google Chat, Slack, iMessage, Signal, WhatsApp), preserving non-local media behavior while restoring local attachment resolution from configured roots. Synthesis of #33581, #33545, #33540, #33536, #33528. Thanks @bmendonca3.
+- Gateway/security default response headers: add `Permissions-Policy: camera=(), microphone=(), geolocation=()` to baseline gateway HTTP security headers for all responses. (#30186) thanks @habakan.
+- Plugins/startup loading: lazily initialize plugin runtime, split startup-critical plugin SDK imports into `openclaw/plugin-sdk/core` and `openclaw/plugin-sdk/telegram`, and preserve `api.runtime` reflection semantics for plugin compatibility. (#28620) thanks @hmemcpy.
+- Plugins/startup performance: reduce bursty plugin discovery/manifest overhead with short in-process caches, skip importing bundled memory plugins that are disabled by slot selection, and speed legacy root `openclaw/plugin-sdk` compatibility via runtime root-alias routing while preserving backward compatibility. Thanks @gumadeiras.
+- Build/lazy runtime boundaries: replace ineffective dynamic import sites with dedicated lazy runtime boundaries across Slack slash handling, Telegram audit, CLI send deps, memory fallback, and outbound delivery paths while preserving behavior. (#33690) thanks @gumadeiras.
+- Config/heartbeat legacy-path handling: auto-migrate top-level `heartbeat` into `agents.defaults.heartbeat` (with merge semantics that preserve explicit defaults), and keep startup failures on non-migratable legacy entries in the detailed invalid-config path instead of generic migration-failed errors. (#32706) thanks @xiwan.
+- Plugins/SDK subpath parity: expand plugin SDK subpaths across bundled channels/extensions (Discord, Slack, Signal, iMessage, WhatsApp, LINE, and bundled companion plugins), with build/export/type/runtime wiring so scoped imports resolve consistently in source and dist while preserving compatibility. (#33737) thanks @gumadeiras.
+- Plugins/bundled scoped-import migration: migrate bundled plugins from monolithic `openclaw/plugin-sdk` imports to scoped subpaths (or `openclaw/plugin-sdk/core`) across registration and startup-sensitive runtime files, add CI/release guardrails to prevent regressions, and keep root `openclaw/plugin-sdk` support for external/community plugins. Thanks @gumadeiras.
+- Routing/session duplicate suppression synthesis: align shared session delivery-context inheritance, channel-paired route-field merges, and reply-surface target matching so dmScope=main turns avoid cross-surface duplicate replies while thread-aware forwarding keeps intended routing semantics. (from #33629, #26889, #17337, #33250) Thanks @Yuandiaodiaodiao, @kevinwildenradt, @Glucksberg, and @bmendonca3.
+- Routing/legacy session route inheritance: preserve external route metadata inheritance for legacy channel session keys (`agent:<agent>:<channel>:<peer>` and `...:thread:<id>`) so `chat.send` does not incorrectly fall back to webchat when valid delivery context exists. Follow-up to #33786.
+- Routing/legacy route guard tightening: require legacy session-key channel hints to match the saved delivery channel before inheriting external routing metadata, preventing custom namespaced keys like `agent:<agent>:work:<ticket>` from inheriting stale non-webchat routes.
+- Security/auth labels: remove token and API-key snippets from user-facing auth status labels so `/status` and `/models` do not expose credential fragments. (#33262) thanks @cu1ch3n.
+- Auth/credential semantics: align profile eligibility + probe diagnostics with SecretRef/expiry rules and harden browser download atomic writes. (#33733) thanks @joshavant.
+- Security/audit denyCommands guidance: suggest likely exact node command IDs for unknown `gateway.nodes.denyCommands` entries so ineffective denylist entries are easier to correct. (#29713) thanks @liquidhorizon88-bot.
+- Docs/security hardening guidance: document Docker `DOCKER-USER` + UFW policy and add cross-linking from Docker install docs for VPS/public-host setups. (#27613) thanks @dorukardahan.
+- Docs/security threat-model links: replace relative `.md` links with Mintlify-compatible root-relative routes in security docs to prevent broken internal navigation. (#27698) thanks @clawdoo.
+- iOS/Voice timing safety: guard system speech start/finish callbacks to the active utterance to avoid misattributed start events during rapid stop/restart cycles. (#33304) thanks @mbelinky; original implementation direction by @ngutman.
+- iOS/Talk incremental speech pacing: allow long punctuation-free assistant chunks to start speaking at safe whitespace boundaries so voice responses begin sooner instead of waiting for terminal punctuation. (#33305) thanks @mbelinky; original implementation by @ngutman.
+- iOS/Watch reply reliability: make watch session activation waiters robust under concurrent requests so status/send calls no longer hang intermittently, and align delegate callbacks with Swift 6 actor safety. (#33306) thanks @mbelinky; original implementation by @Rocuts.
+- Docs/tool-loop detection config keys: align `docs/tools/loop-detection.md` examples and field names with the current `tools.loopDetection` schema to prevent copy-paste validation failures from outdated keys. (#33182) Thanks @Mylszd.
+- Gateway/session agent discovery: include disk-scanned agent IDs in `listConfiguredAgentIds` even when `agents.list` is configured, so disk-only/ACP agent sessions remain visible in gateway session aggregation and listings. (#32831) thanks @Sid-Qin.
+- Discord/inbound debouncer: skip bot-own MESSAGE_CREATE events before they reach the debounce queue to avoid self-triggered slowdowns in busy servers. Thanks @thewilloftheshadow.
+- Discord/Agent-scoped media roots: pass `mediaLocalRoots` through Discord monitor reply delivery (message + component interaction paths) so local media attachments honor per-agent workspace roots instead of falling back to default global roots. Thanks @thewilloftheshadow.
+- Discord/slash command handling: intercept text-based slash commands in channels, register plugin commands as native, and send fallback acknowledgments for empty slash runs so interactions do not hang. Thanks @thewilloftheshadow.
+- Discord/thread session lifecycle: reset thread-scoped sessions when a thread is archived so reopening a thread starts fresh without deleting transcript history. Thanks @thewilloftheshadow.
+- Discord/presence defaults: send an online presence update on ready when no custom presence is configured so bots no longer appear offline by default. Thanks @thewilloftheshadow.
+- Discord/typing cleanup: stop typing indicators after silent/NO_REPLY runs by marking the run complete before dispatch idle cleanup. Thanks @thewilloftheshadow.
+- Discord/config SecretRef typing: align Discord account token config typing with SecretInput so SecretRef tokens typecheck. (#32490) Thanks @scoootscooob.
+- Discord/voice messages: request upload slots with JSON fetch calls so voice message uploads no longer fail with content-type errors. Thanks @thewilloftheshadow.
+- Discord/voice decoder fallback: drop the native Opus dependency and use opusscript for voice decoding to avoid native-opus installs. Thanks @thewilloftheshadow.
+- Discord/auto presence health signal: add runtime availability-driven presence updates plus connected-state reporting to improve health monitoring and operator visibility. (#33277) Thanks @thewilloftheshadow.
+- Telegram/draft-stream boundary stability: materialize DM draft previews at assistant-message/tool boundaries, serialize lane-boundary callbacks before final delivery, and scope preview cleanup to the active preview so multi-step Telegram streams no longer lose, overwrite, or leave stale preview bubbles. (#33842) Thanks @ngutman.
+- Telegram/DM draft finalization reliability: require verified final-text draft emission before treating preview finalization as delivered, and fall back to normal payload send when final draft delivery is not confirmed (preventing missing final responses and preserving media/button delivery). (#32118) Thanks @OpenCils.
+- Telegram/DM draft final delivery: materialize text-only `sendMessageDraft` previews into one permanent final message and skip duplicate final payload sends, while preserving fallback behavior when materialization fails. (#34318) Thanks @Brotherinlaw-13.
+- Telegram/draft preview boundary + silent-token reliability: stabilize answer-lane message boundaries across late-partial/message-start races, preserve/reset finalized preview state at the correct boundaries, and suppress `NO_REPLY` lead-fragment leaks without broad heartbeat-prefix false positives. (#33169) Thanks @obviyus.
+- Discord/audit wildcard warnings: ignore "\*" wildcard keys when counting unresolved guild channels so doctor/status no longer warns on allow-all configs. (#33125) Thanks @thewilloftheshadow.
+- Discord/channel resolution: default bare numeric recipients to channels, harden allowlist numeric ID handling with safe fallbacks, and avoid inbound WS heartbeat stalls. (#33142) Thanks @thewilloftheshadow.
+- Discord/chunk delivery reliability: preserve chunk ordering when using a REST client and retry chunk sends on 429/5xx using account retry settings. (#33226) Thanks @thewilloftheshadow.
+- Discord/mention handling: add id-based mention formatting + cached rewrites, resolve inbound mentions to display names, and add optional ignoreOtherMentions gating (excluding @everyone/@here). (#33224) Thanks @thewilloftheshadow.
+- Discord/media SSRF allowlist: allow Discord CDN hostnames (including wildcard domains) in inbound media SSRF policy to prevent proxy/VPN fake-ip blocks. (#33275) Thanks @thewilloftheshadow.
+- Telegram/device pairing notifications: auto-arm one-shot notify on `/pair qr`, auto-ping on new pairing requests, and add manual fallback via `/pair approve latest` if the ping does not arrive. (#33299) thanks @mbelinky.
+- Exec heartbeat routing: scope exec-triggered heartbeat wakes to agent session keys so unrelated agents are no longer awakened by exec events, while preserving legacy unscoped behavior for non-canonical session keys. (#32724) thanks @altaywtf
+- macOS/Tailscale remote gateway discovery: add a Tailscale Serve fallback peer probe path (`wss://<peer>.ts.net`) when Bonjour and wide-area DNS-SD discovery return no gateways, and refresh both discovery paths from macOS onboarding. (#32860) Thanks @ngutman.
+- iOS/Gateway keychain hardening: move gateway metadata and TLS fingerprints to device keychain storage with safer migration behavior and rollback-safe writes to reduce credential loss risk during upgrades. (#33029) thanks @mbelinky.
+- iOS/Concurrency stability: replace risky shared-state access in camera and gateway connection paths with lock-protected access patterns to reduce crash risk under load. (#33241) thanks @mbelinky.
+- iOS/Security guardrails: limit production API-key sourcing to app config and make deep-link confirmation prompts safer by coalescing queued requests instead of silently dropping them. (#33031) thanks @mbelinky.
+- iOS/TTS playback fallback: keep voice playback resilient by switching from PCM to MP3 when provider format support is unavailable, while avoiding sticky fallback on generic local playback errors. (#33032) thanks @mbelinky.
+- Plugin outbound/text-only adapter compatibility: allow direct-delivery channel plugins that only implement `sendText` (without `sendMedia`) to remain outbound-capable, gracefully fall back to text delivery for media payloads when `sendMedia` is absent, and fail explicitly for media-only payloads with no text fallback. (#32788) thanks @liuxiaopai-ai.
+- Telegram/multi-account default routing clarity: warn only for ambiguous (2+) account setups without an explicit default, add `openclaw doctor` warnings for missing/invalid multi-account defaults across channels, and document explicit-default guidance for channel routing and Telegram config. (#32544) thanks @Sid-Qin.
+- Telegram/plugin outbound hook parity: run `message_sending` + `message_sent` in Telegram reply delivery, include reply-path hook metadata (`mediaUrls`, `threadId`), and report `message_sent.success=false` when hooks blank text and no outbound message is delivered. (#32649) Thanks @KimGLee.
+- CLI/Coding-agent reliability: switch default `claude-cli` non-interactive args to `--permission-mode bypassPermissions`, auto-normalize legacy `--dangerously-skip-permissions` backend overrides to the modern permission-mode form, align coding-agent + live-test docs with the non-PTY Claude path, and emit session system-event heartbeat notices when CLI watchdog no-output timeouts terminate runs. (#28610, #31149, #34055). Thanks @niceysam, @cryptomaltese and @vincentkoc.
+- ACP/ACPX session bootstrap: retry with `sessions new` when `sessions ensure` returns no session identifiers so ACP spawns avoid `NO_SESSION`/`ACP_TURN_FAILED` failures on affected agents. (#28786, #31338, #34055). Thanks @Sid-Qin and @vincentkoc.
+- ACP/sessions_spawn parent stream visibility: add `streamTo: "parent"` for `runtime: "acp"` to forward initial child-run progress/no-output/completion updates back into the requester session as system events (instead of direct child delivery), and emit a tail-able session-scoped relay log (`<sessionId>.acp-stream.jsonl`, returned as `streamLogPath` when available), improving orchestrator visibility for blocked or long-running harness turns. (#34310, #29909; reopened from #34055). Thanks @vincentkoc.
+- Agents/bootstrap truncation warning handling: unify bootstrap budget/truncation analysis across embedded + CLI runtime, `/context`, and `openclaw doctor`; add `agents.defaults.bootstrapPromptTruncationWarning` (`off|once|always`, default `once`) and persist warning-signature metadata so truncation warnings are consistent and deduped across turns. (#32769) Thanks @gumadeiras.
+- Agents/Skills runtime loading: propagate run config into embedded attempt and compaction skill-entry loading so explicitly enabled bundled companion skills are discovered consistently when skill snapshots do not already provide resolved entries. Thanks @gumadeiras.
+- Agents/Session startup date grounding: substitute `YYYY-MM-DD` placeholders in startup/post-compaction AGENTS context and append runtime current-time lines for `/new` and `/reset` prompts so daily-memory references resolve correctly. (#32381) Thanks @chengzhichao-xydt.
+- Agents/Compaction template heading alignment: update AGENTS template section names to `Session Startup`/`Red Lines` and keep legacy `Every Session`/`Safety` fallback extraction so post-compaction context remains intact across template versions. (#25098) thanks @echoVic.
+- Agents/Compaction continuity: expand staged-summary merge instructions to preserve active task status, batch progress, latest user request, and follow-up commitments so compaction handoffs retain in-flight work context. (#8903) thanks @joetomasone.
+- Agents/Compaction safeguard structure hardening: require exact fallback summary headings, sanitize untrusted compaction instruction text before prompt embedding, and keep structured sections when preserving all turns. (#25555) thanks @rodrigouroz.
+- Gateway/status self version reporting: make Gateway self version in `openclaw status` prefer runtime `VERSION` (while preserving explicit `OPENCLAW_VERSION` override), preventing stale post-upgrade app version output. (#32655) thanks @liuxiaopai-ai.
+- Memory/QMD index isolation: set `QMD_CONFIG_DIR` alongside `XDG_CONFIG_HOME` so QMD config state stays per-agent despite upstream XDG handling bugs, preventing cross-agent collection indexing and excess disk/CPU usage. (#27028) thanks @HenryLoenwind.
+- Memory/local embedding initialization hardening: add regression coverage for transient initialization retry and mixed `embedQuery` + `embedBatch` concurrent startup to lock single-flight initialization behavior. (#15639) thanks @SubtleSpark.
+- CLI/Coding-agent reliability: switch default `claude-cli` non-interactive args to `--permission-mode bypassPermissions`, auto-normalize legacy `--dangerously-skip-permissions` backend overrides to the modern permission-mode form, align coding-agent + live-test docs with the non-PTY Claude path, and emit session system-event heartbeat notices when CLI watchdog no-output timeouts terminate runs. Related to #28261. Landed from contributor PRs #28610 and #31149. Thanks @niceysam, @cryptomaltese and @vincentkoc.
+- ACP/ACPX session bootstrap: retry with `sessions new` when `sessions ensure` returns no session identifiers so ACP spawns avoid `NO_SESSION`/`ACP_TURN_FAILED` failures on affected agents. Related to #28786. Landed from contributor PR #31338. Thanks @Sid-Qin and @vincentkoc.
+- LINE/auth boundary hardening synthesis: enforce strict LINE webhook authn/z boundary semantics across pairing-store account scoping, DM/group allowlist separation, fail-closed webhook auth/runtime behavior, and replay/duplication controls (including in-flight replay reservation and post-success dedupe marking). (from #26701, #26683, #25978, #17593, #16619, #31990, #26047, #30584, #18777) Thanks @bmendonca3, @davidahmann, @harshang03, @haosenwang1018, @liuxiaopai-ai, @coygeek, and @Takhoffman.
+- LINE/media download synthesis: fix file-media download handling and M4A audio classification across overlapping LINE regressions. (from #26386, #27761, #27787, #29509, #29755, #29776, #29785, #32240) Thanks @kevinWangSheng, @loiie45e, @carrotRakko, @Sid-Qin, @codeafridi, and @bmendonca3.
+- LINE/context and routing synthesis: fix group/room peer routing and command-authorization context propagation, and keep processing later events in mixed-success webhook batches. (from #21955, #24475, #27035, #28286) Thanks @lailoo, @mcaxtr, @jervyclaw, @Glucksberg, and @Takhoffman.
+- LINE/status/config/webhook synthesis: fix status false positives from snapshot/config state and accept LINE webhook HEAD probes for compatibility. (from #10487, #25726, #27537, #27908, #31387) Thanks @BlueBirdBack, @stakeswky, @loiie45e, @puritysb, and @mcaxtr.
+- LINE cleanup/test follow-ups: fold cleanup/test learnings into the synthesis review path while keeping runtime changes focused on regression fixes. (from #17630, #17289) Thanks @Clawborn and @davidahmann.
+
+## 2026.3.2
+
+### Changes
+
+- Secrets/SecretRef coverage: expand SecretRef support across the full supported user-supplied credential surface (64 targets total), including runtime collectors, `openclaw secrets` planning/apply/audit flows, onboarding SecretInput UX, and related docs; unresolved refs now fail fast on active surfaces while inactive surfaces report non-blocking diagnostics. (#29580) Thanks @joshavant.
 - Tools/PDF analysis: add a first-class `pdf` tool with native Anthropic and Google PDF provider support, extraction fallback for non-native models, configurable defaults (`agents.defaults.pdfModel`, `pdfMaxBytesMb`, `pdfMaxPages`), and docs/tests covering routing, validation, and registration. (#31319) Thanks @tyler6204.
+- Outbound adapters/plugins: add shared `sendPayload` support across direct-text-media, Discord, Slack, WhatsApp, Zalo, and Zalouser with multi-media iteration and chunk-aware text fallback. (#30144) Thanks @nohat.
+- Models/MiniMax: add first-class `MiniMax-M2.5-highspeed` support across built-in provider catalogs, onboarding flows, and MiniMax OAuth plugin defaults, while keeping legacy `MiniMax-M2.5-Lightning` compatibility for existing configs.
+- Sessions/Attachments: add inline file attachment support for `sessions_spawn` (subagent runtime only) with base64/utf8 encoding, transcript content redaction, lifecycle cleanup, and configurable limits via `tools.sessions_spawn.attachments`. (#16761) Thanks @napetrov.
+- Telegram/Streaming defaults: default `channels.telegram.streaming` to `partial` (from `off`) so new Telegram setups get live preview streaming out of the box, with runtime fallback to message-edit preview when native drafts are unavailable.
+- Telegram/DM streaming: use `sendMessageDraft` for private preview streaming, keep reasoning/answer preview lanes separated in DM reasoning-stream mode. (#31824) Thanks @obviyus.
+- Telegram/voice mention gating: add optional `disableAudioPreflight` on group/topic config to skip mention-detection preflight transcription for inbound voice notes where operators want text-only mention checks. (#23067) Thanks @yangnim21029.
+- CLI/Config validation: add `openclaw config validate` (with `--json`) to validate config files before gateway startup, and include detailed invalid-key paths in startup invalid-config errors. (#31220) thanks @Sid-Qin.
+- Tools/Diffs: add PDF file output support and rendering quality customization controls (`fileQuality`, `fileScale`, `fileMaxWidth`) for generated diff artifacts, and document PDF as the preferred option when messaging channels compress images. (#31342) Thanks @gumadeiras.
+- Memory/Ollama embeddings: add `memorySearch.provider = "ollama"` and `memorySearch.fallback = "ollama"` support, honor `models.providers.ollama` settings for memory embedding requests, and document Ollama embedding usage. (#26349) Thanks @nico-hoff.
+- Zalo Personal plugin (`@openclaw/zalouser`): rebuilt channel runtime to use native `zca-js` integration in-process, removing external CLI transport usage and keeping QR/login + send/listen flows fully inside OpenClaw.
+- Plugin SDK/channel extensibility: expose `channelRuntime` on `ChannelGatewayContext` so external channel plugins can access shared runtime helpers (reply/routing/session/text/media/commands) without internal imports. (#25462) Thanks @guxiaobo.
+- Plugin runtime/STT: add `api.runtime.stt.transcribeAudioFile(...)` so extensions can transcribe local audio files through OpenClaw's configured media-understanding audio providers. (#22402) Thanks @benthecarman.
+- Plugin hooks/session lifecycle: include `sessionKey` in `session_start`/`session_end` hook events and contexts so plugins can correlate lifecycle callbacks with routing identity. (#26394) Thanks @tempeste.
+- Hooks/message lifecycle: add internal hook events `message:transcribed` and `message:preprocessed`, plus richer outbound `message:sent` context (`isGroup`, `groupId`) for group-conversation correlation and post-transcription automations. (#9859) Thanks @Drickon.
+- Media understanding/audio echo: add optional `tools.media.audio.echoTranscript` + `echoFormat` to send a pre-agent transcript confirmation message to the originating chat, with echo disabled by default. (#32150) Thanks @AytuncYildizli.
+- Plugin runtime/system: expose `runtime.system.requestHeartbeatNow(...)` so extensions can wake targeted sessions immediately after enqueueing system events. (#19464) Thanks @AustinEral.
+- Plugin runtime/events: expose `runtime.events.onAgentEvent` and `runtime.events.onSessionTranscriptUpdate` for extension-side subscriptions, and isolate transcript-listener failures so one faulty listener cannot break the entire update fanout. (#16044) Thanks @scifantastic.
+- CLI/Banner taglines: add `cli.banner.taglineMode` (`random` | `default` | `off`) to control funny tagline behavior in startup output, with docs + FAQ guidance and regression tests for config override behavior.
+
+### Breaking
+
+- **BREAKING:** Onboarding now defaults `tools.profile` to `messaging` for new local installs (interactive + non-interactive). New setups no longer start with broad coding/system tools unless explicitly configured.
+- **BREAKING:** ACP dispatch now defaults to enabled unless explicitly disabled (`acp.dispatch.enabled=false`). If you need to pause ACP turn routing while keeping `/acp` controls, set `acp.dispatch.enabled=false`. Docs: https://docs.openclaw.ai/tools/acp-agents
+- **BREAKING:** Plugin SDK removed `api.registerHttpHandler(...)`. Plugins must register explicit HTTP routes via `api.registerHttpRoute({ path, auth, match, handler })`, and dynamic webhook lifecycles should use `registerPluginHttpRoute(...)`.
+- **BREAKING:** Zalo Personal plugin (`@openclaw/zalouser`) no longer depends on external `zca`-compatible CLI binaries (`openzca`, `zca-cli`) for runtime send/listen/login; operators should use `openclaw channels login --channel zalouser` after upgrade to refresh sessions in the new JS-native path.
+
+### Fixes
+
+- Feishu/Outbound render mode: respect Feishu account `renderMode` in outbound sends so card mode (and auto-detected markdown tables/code blocks) uses markdown card delivery instead of always sending plain text. (#31562) Thanks @arkyu2077.
+- Plugin command/runtime hardening: validate and normalize plugin command name/description at registration boundaries, and guard Telegram native menu normalization paths so malformed plugin command specs cannot crash startup (`trim` on undefined). (#31997) Fixes #31944. Thanks @liuxiaopai-ai.
+- Telegram: guard duplicate-token checks and gateway startup token normalization when account tokens are missing, preventing `token.trim()` crashes during status/start flows. (#31973) Thanks @ningding97.
+- Discord/lifecycle startup status: push an immediate `connected` status snapshot when the gateway is already connected before lifecycle debug listeners attach, with abort-guarding to avoid contradictory status flips during pre-aborted startup. (#32336) Thanks @mitchmcalister.
+- Feishu/inbound mention normalization: preserve all inbound mention semantics by normalizing Feishu mention placeholders into explicit `<at user_id=\"...\">name</at>` tags (instead of stripping them), improving multi-mention context fidelity in agent prompts while retaining bot/self mention disambiguation. (#30252) Thanks @Lanfei.
+- Feishu/multi-app mention routing: guard mention detection in multi-bot groups by validating mention display name alongside bot `open_id`, preventing false-positive self-mentions from Feishu WebSocket remapping so only the actually mentioned bot responds under `requireMention`. (#30315) Thanks @teaguexiao.
+- Feishu/session-memory hook parity: trigger the shared `before_reset` session-memory hook path when Feishu `/new` and `/reset` commands execute so reset flows preserve memory behavior consistent with other channels. (#31437) Thanks @Linux2010.
+- Feishu/LINE group system prompts: forward per-group `systemPrompt` config into inbound context `GroupSystemPrompt` for Feishu and LINE group/room events so configured group-specific behavior actually applies at dispatch time. (#31713) Thanks @whiskyboy.
+- Mentions/Slack formatting hardening: add null-safe guards for runtime text normalization paths so malformed/undefined text payloads do not crash mention stripping or mrkdwn conversion. (#31865) Thanks @stone-jin.
+- Feishu/Plugin sdk compatibility: add safe webhook default fallbacks when loading Feishu monitor state so mixed-version installs no longer crash if older `openclaw/plugin-sdk` builds omit webhook default constants. (#31606)
+- Feishu/group broadcast dispatch: add configurable multi-agent group broadcast dispatch with observer-session isolation, cross-account dedupe safeguards, and non-mention history buffering rules that avoid duplicate replay in broadcast/topic workflows. (#29575) Thanks @ohmyskyhigh.
+- Gateway/Subagent TLS pairing: allow authenticated local `gateway-client` backend self-connections to skip device pairing while still requiring pairing for non-local/direct-host paths, restoring `sessions_spawn` with `gateway.tls.enabled=true` in Docker/LAN setups. Fixes #30740. Thanks @Sid-Qin and @vincentkoc.
+- Browser/CDP startup diagnostics: include Chrome stderr output and a Linux no-sandbox hint in startup timeout errors so failed launches are easier to diagnose. (#29312) Thanks @veast.
+- Synology Chat/webhook ingress hardening: enforce bounded body reads (size + timeout) via shared request-body guards to prevent unauthenticated slow-body hangs before token validation. (#25831) Thanks @bmendonca3.
+- Feishu/Dedup restart resilience: warm persistent dedup state into memory on monitor startup so retry events after gateway restart stay suppressed without requiring initial on-disk probe misses. (#31605)
+- Voice-call/runtime lifecycle: prevent `EADDRINUSE` loops by resetting failed runtime promises, making webhook `start()` idempotent with the actual bound port, and fully cleaning up webhook/tunnel/tailscale resources after startup failures. (#32395) Thanks @scoootscooob.
+- Gateway/Security hardening: tie loopback-origin dev allowance to actual local socket clients (not Host header claims), add explicit warnings/metrics when `gateway.controlUi.dangerouslyAllowHostHeaderOriginFallback` accepts websocket origins, harden safe-regex detection for quantified ambiguous alternation patterns (for example `(a|aa)+`), and bound large regex-evaluation inputs for session-filter and log-redaction paths.
+- Gateway/Plugin HTTP hardening: require explicit `auth` for plugin route registration, add route ownership guards for duplicate `path+match` registrations, centralize plugin path matching/auth logic into dedicated modules, and share webhook target-route lifecycle wiring across channel monitors to avoid stale or conflicting registrations. Thanks @tdjackey for reporting.
+- Browser/Profile defaults: prefer `openclaw` profile over `chrome` in headless/no-sandbox environments unless an explicit `defaultProfile` is configured. (#14944) Thanks @BenediktSchackenberg.
+- Gateway/WS security: keep plaintext `ws://` loopback-only by default, with explicit break-glass private-network opt-in via `OPENCLAW_ALLOW_INSECURE_PRIVATE_WS=1`; align onboarding/client/call validation and tests to this strict-default policy. (#28670) Thanks @dashed, @vincentkoc.
+- OpenAI Codex OAuth/TLS prerequisites: add an OAuth TLS cert-chain preflight with actionable remediation for cert trust failures, and gate doctor TLS prerequisite probing to OpenAI Codex OAuth-configured installs (or explicit `doctor --deep`) to avoid unconditional outbound probe latency. (#32051) Thanks @alexfilatov.
+- Security/Webhook request hardening: enforce auth-before-body parsing for BlueBubbles and Google Chat webhook handlers, add strict pre-auth body/time budgets for webhook auth paths (including LINE signature verification), and add shared in-flight/request guardrails plus regression tests/lint checks to prevent reintroducing unauthenticated slow-body DoS patterns. Thanks @GCXWLP for reporting.
+- CLI/Config validation and routing hardening: dedupe `openclaw config validate` failures to a single authoritative report, expose allowed-values metadata/hints across core Zod and plugin AJV validation (including `--json` fields), sanitize terminal-rendered validation text, and make command-path parsing root-option-aware across preaction/route/lazy registration (including routed `config get/unset` with split root options). Thanks @gumadeiras.
+- Browser/Extension relay reconnect tolerance: keep `/json/version` and `/cdp` reachable during short MV3 worker disconnects when attached targets still exist, and retain clients across reconnect grace windows. (#30232) Thanks @Sid-Qin.
+- CLI/Browser start timeout: honor `openclaw browser --timeout <ms> start` and stop by removing the fixed 15000ms override so slower Chrome startups can use caller-provided timeouts. (#22412, #23427) Thanks @vincentkoc.
+- Synology Chat/gateway lifecycle: keep `startAccount` pending until abort for inactive and active account paths to prevent webhook route restart loops under gateway supervision. (#23074) Thanks @druide67.
+- Exec approvals/allowlist matching: escape regex metacharacters in path-pattern literals (while preserving glob wildcards), preventing crashes on allowlisted executables like `/usr/bin/g++` and correctly matching mixed wildcard/literal token paths. (#32162) Thanks @stakeswky.
+- Synology Chat/webhook compatibility: accept JSON and alias payload fields, allow token resolution from body/query/header sources, and ACK webhook requests with `204` to avoid persistent `Processing...` states in Synology Chat clients. (#26635) Thanks @memphislee09-source.
+- Voice-call/Twilio signature verification: retry signature validation across deterministic URL port variants (with/without port) to handle mixed Twilio signing behavior behind reverse proxies and non-standard ports. (#25140) Thanks @drvoss.
+- Slack/Bolt startup compatibility: remove invalid `message.channels` and `message.groups` event registrations so Slack providers no longer crash on startup with Bolt 4.6+; channel/group traffic continues through the unified `message` handler (`channel_type`). (#32033) Thanks @mahopan.
+- Slack/socket auth failure handling: fail fast on non-recoverable auth errors (`account_inactive`, `invalid_auth`, etc.) during startup and reconnect instead of retry-looping indefinitely, including `unable_to_socket_mode_start` error payload propagation. (#32377) Thanks @scoootscooob.
+- Gateway/macOS LaunchAgent hardening: write `Umask=077` in generated gateway LaunchAgent plists so npm upgrades preserve owner-only default file permissions for gateway-created state files. (#31919) Fixes #31905. Thanks @liuxiaopai-ai.
+- macOS/LaunchAgent security defaults: write `Umask=63` (octal `077`) into generated gateway launchd plists so post-update service reinstalls keep owner-only file permissions by default instead of falling back to system `022`. (#32022) Fixes #31905. Thanks @liuxiaopai-ai.
+- Media understanding/provider HTTP proxy routing: pass a proxy-aware fetch function from `HTTPS_PROXY`/`HTTP_PROXY` env vars into audio/video provider calls (with graceful malformed-proxy fallback) so transcription/video requests honor configured outbound proxies. (#27093) Thanks @mcaxtr.
+- Sandbox/workspace mount permissions: make primary `/workspace` bind mounts read-only whenever `workspaceAccess` is not `rw` (including `none`) across both core sandbox container and sandbox browser create flows. (#32227) Thanks @guanyu-zhang.
+- Tools/fsPolicy propagation: honor `tools.fs.workspaceOnly` for image/pdf local-root allowlists so non-sandbox media paths outside workspace are rejected when workspace-only mode is enabled. (#31882) Thanks @justinhuangcode.
+- Daemon/Homebrew runtime pinning: resolve Homebrew Cellar Node paths to stable Homebrew-managed symlinks (including versioned formulas like `node@22`) so gateway installs keep the intended runtime across brew upgrades. (#32185) Thanks @scoootscooob.
+- Browser/Security output boundary hardening: replace check-then-rename output commits with root-bound fd-verified writes, unify install/skills canonical path-boundary checks, and add regression coverage for symlink-rebind race paths across browser output and shared fs-safe write flows. Thanks @tdjackey for reporting.
+- Gateway/Security canonicalization hardening: decode plugin route path variants to canonical fixpoint (with bounded depth), fail closed on canonicalization anomalies, and enforce gateway auth for deeply encoded `/api/channels/*` variants to prevent alternate-path auth bypass through plugin handlers. Thanks @tdjackey for reporting.
+- Browser/Gateway hardening: preserve env credentials for `OPENCLAW_GATEWAY_URL` / `CLAWDBOT_GATEWAY_URL` while treating explicit `--url` as override-only auth, and make container browser hardening flags optional with safer defaults for Docker/LXC stability. (#31504) Thanks @vincentkoc.
+- Gateway/Control UI basePath webhook passthrough: let non-read methods under configured `controlUiBasePath` fall through to plugin routes (instead of returning Control UI 405), restoring webhook handlers behind basePath mounts. (#32311) Thanks @ademczuk.
+- Gateway/Webchat streaming finalization: flush throttled trailing assistant text before `final` chat events so streaming consumers do not miss tail content, while preserving duplicate suppression and heartbeat/silent lead-fragment guards. (#24856) Thanks @visionik and @vincentkoc.
+- Control UI/Legacy browser compatibility: replace `toSorted`-dependent cron suggestion sorting in `app-render` with a compatibility helper so older browsers without `Array.prototype.toSorted` no longer white-screen. (#31775) Thanks @liuxiaopai-ai.
+- macOS/PeekabooBridge: add compatibility socket symlinks for legacy `clawdbot`, `clawdis`, and `moltbot` Application Support socket paths so pre-rename clients can still connect. (#6033) Thanks @lumpinif and @vincentkoc.
+- Gateway/message tool reliability: avoid false `Unknown channel` failures when `message.*` actions receive platform-specific channel ids by falling back to `toolContext.currentChannelProvider`, and prevent health-monitor restart thrash for channels that just (re)started by adding a per-channel startup-connect grace window. (from #32367) Thanks @MunemHashmi.
+- Windows/Spawn canonicalization: unify non-core Windows spawn handling across ACP client, QMD/mcporter memory paths, and sandbox Docker execution using the shared wrapper-resolution policy, with targeted regression coverage for `.cmd` shim unwrapping and shell fallback behavior. (#31750) Thanks @Takhoffman.
+- Security/ACP sandbox inheritance: enforce fail-closed runtime guardrails for `sessions_spawn` with `runtime="acp"` by rejecting ACP spawns from sandboxed requester sessions and rejecting `sandbox="require"` for ACP runtime, preventing sandbox-boundary bypass via host-side ACP initialization. (#32254) Thanks @tdjackey for reporting, and @dutifulbob for the fix.
+- Security/Web tools SSRF guard: keep DNS pinning for untrusted `web_fetch` and citation-redirect URL checks when proxy env vars are set, and require explicit dangerous opt-in before env-proxy routing can bypass pinned dispatch for trusted/operator-controlled endpoints. Thanks @tdjackey for reporting.
+- Gemini schema sanitization: coerce malformed JSON Schema `properties` values (`null`, arrays, primitives) to `{}` before provider validation, preventing downstream strict-validator crashes on invalid plugin/tool schemas. (#32332) Thanks @webdevtodayjason.
+- Media understanding/malformed attachment guards: harden attachment selection and decision summary formatting against non-array or malformed attachment payloads to prevent runtime crashes on invalid inbound metadata shapes. (#28024) Thanks @claw9267.
+- Browser/Extension navigation reattach: preserve debugger re-attachment when relay is temporarily disconnected by deferring relay attach events until reconnect/re-announce, reducing post-navigation tab loss. (#28725) Thanks @stone-jin.
+- Browser/Extension relay stale tabs: evict stale cached targets from `/json/list` when extension targets are destroyed/crashed or commands fail with missing target/session errors. (#6175) Thanks @vincentkoc.
+- Browser/CDP startup readiness: wait for CDP websocket readiness after launching Chrome and cleanly stop/reset when readiness never arrives, reducing follow-up `PortInUseError` races after `browser start`/`open`. (#29538) Thanks @AaronWander.
+- OpenAI/Responses WebSocket tool-call id hygiene: normalize blank/whitespace streamed tool-call ids before persistence, and block empty `function_call_output.call_id` payloads in the WS conversion path to avoid OpenAI 400 errors (`Invalid 'input[n].call_id': empty string`), with regression coverage for both inbound stream normalization and outbound payload guards.
+- Security/Nodes camera URL downloads: bind node `camera.snap`/`camera.clip` URL payload downloads to the resolved node host, enforce fail-closed behavior when node `remoteIp` is unavailable, and use SSRF-guarded fetch with redirect host/protocol checks to prevent off-node fetch pivots. Thanks @tdjackey for reporting.
+- Config/backups hardening: enforce owner-only (`0600`) permissions on rotated config backups and clean orphan `.bak.*` files outside the managed backup ring, reducing credential leakage risk from stale or permissive backup artifacts. (#31718) Thanks @YUJIE2002.
+- Telegram/inbound media filenames: preserve original `file_name` metadata for document/audio/video/animation downloads (with fetch/path fallbacks), so saved inbound attachments keep sender-provided names instead of opaque Telegram file paths. (#31837) Thanks @Kay-051.
+- Gateway/OpenAI chat completions: honor `x-openclaw-message-channel` when building `agentCommand` input for `/v1/chat/completions`, preserving caller channel identity instead of forcing `webchat`. (#30462) Thanks @bmendonca3.
+- Plugin SDK/runtime hardening: add package export verification in CI/release checks to catch missing runtime exports before publish-time regressions. (#28575) Thanks @bmendonca3.
+- Media/MIME normalization: normalize parameterized/case-variant MIME strings in `kindFromMime` (for example `Audio/Ogg; codecs=opus`) so WhatsApp voice notes are classified as audio and routed through transcription correctly. (#32280) Thanks @Lucenx9.
+- Discord/audio preflight mentions: detect audio attachments via Discord `content_type` and gate preflight transcription on typed text (not media placeholders), so guild voice-note mentions are transcribed and matched correctly. (#32136) Thanks @jnMetaCode.
+- Discord/acp inline actions: prefer autocomplete for `/acp` action inline values and ignore bound-thread bot system messages to prevent ACP loops. (#33136) Thanks @thewilloftheshadow.
+- Feishu/topic session routing: use `thread_id` as topic session scope fallback when `root_id` is absent, keep first-turn topic keys stable across thread creation, and force thread replies when inbound events already carry topic/thread context. (#29788) Thanks @songyaolun.
+- Gateway/Webchat NO_REPLY streaming: suppress assistant lead-fragment deltas that are prefixes of `NO_REPLY` and keep final-message buffering in sync, preventing partial `NO` leaks on silent-response runs while preserving legitimate short replies. (#32073) Thanks @liuxiaopai-ai.
+- Telegram/models picker callbacks: keep long model buttons selectable by falling back to compact callback payloads and resolving provider ids on selection (with provider re-prompt on ambiguity), avoiding Telegram 64-byte callback truncation failures. (#31857) Thanks @bmendonca3.
+- Context-window metadata warmup: add exponential config-load retry backoff (1s -> 2s -> 4s, capped at 60s) so transient startup failures recover automatically without hot-loop retries.
+- Voice-call/Twilio external outbound: auto-register webhook-first `outbound-api` calls (initiated outside OpenClaw) so media streams are accepted and call direction metadata stays accurate. (#31181) Thanks @scoootscooob.
+- Feishu/topic root replies: prefer `root_id` as outbound `replyTargetMessageId` when present, and parse millisecond `message_create_time` values correctly so topic replies anchor to the root message in grouped thread flows. (#29968) Thanks @bmendonca3.
+- Feishu/DM pairing reply target: send pairing challenge replies to `chat:<chat_id>` instead of `user:<sender_open_id>` so Lark/Feishu private chats with user-id-only sender payloads receive pairing messages reliably. (#31403) Thanks @stakeswky.
+- Feishu/Lark private DM routing: treat inbound `chat_type: "private"` as direct-message context for pairing/mention-forward/reaction synthetic handling so Lark private chats behave like Feishu p2p DMs. (#31400) Thanks @stakeswky.
+- Signal/message actions: allow `react` to fall back to `toolContext.currentMessageId` when `messageId` is omitted, matching Telegram behavior and unblocking agent-initiated reactions on inbound turns. (#32217) Thanks @dunamismax.
+- Discord/message actions: allow `react` to fall back to `toolContext.currentMessageId` when `messageId` is omitted, matching Telegram/Signal reaction ergonomics in inbound turns.
+- Synology Chat/reply delivery: resolve webhook usernames to Chat API `user_id` values for outbound chatbot replies, avoiding mismatches between webhook user IDs and `method=chatbot` recipient IDs in multi-account setups. (#23709) Thanks @druide67.
+- Slack/thread context payloads: only inject thread starter/history text on first thread turn for new sessions while preserving thread metadata, reducing repeated context-token bloat on long-lived thread sessions. (#32133) Thanks @sourman.
+- Slack/session routing: keep top-level channel messages in one shared session when `replyToMode=off`, while preserving thread-scoped keys for true thread replies and non-off modes. (#32193) Thanks @bmendonca3.
+- Voice-call/webhook routing: require exact webhook path matches (instead of prefix matches) so lookalike paths cannot reach provider verification/dispatch logic. (#31930) Thanks @afurm.
+- Zalo/Pairing auth tests: add webhook regression coverage asserting DM pairing-store reads/writes remain account-scoped, preventing cross-account authorization bleed in multi-account setups. (#26121) Thanks @bmendonca3.
+- Zalouser/Pairing auth tests: add account-scoped DM pairing-store regression coverage (`monitor.account-scope.test.ts`) to prevent cross-account allowlist bleed in multi-account setups. (#26672) Thanks @bmendonca3.
+- Feishu/Send target prefixes: normalize explicit `group:`/`dm:` send targets and preserve explicit receive-id routing hints when resolving outbound Feishu targets. (#31594) Thanks @liuxiaopai-ai.
+- Webchat/Feishu session continuation: preserve routable `OriginatingChannel`/`OriginatingTo` metadata from session delivery context in `chat.send`, and prefer provider-normalized channel when deciding cross-channel route dispatch so Webchat replies continue on the selected Feishu session instead of falling back to main/internal session routing. (#31573)
+- Telegram/implicit mention forum handling: exclude Telegram forum system service messages (`forum_topic_*`, `general_forum_topic_*`) from reply-chain implicit mention detection so `requireMention` does not get bypassed inside bot-created topic lifecycle events. (#32262) Thanks @scoootscooob.
+- Slack/inbound debounce routing: isolate top-level non-DM message debounce keys by message timestamp to avoid cross-thread collisions, preserve DM batching, and flush pending top-level buffers before immediate non-debounce follow-ups to keep ordering stable. (#31951) Thanks @scoootscooob.
+- Feishu/Duplicate replies: suppress same-target reply dispatch when message-tool sends use generic provider metadata (`provider: "message"`) and normalize `lark`/`feishu` provider aliases during duplicate-target checks, preventing double-delivery in Feishu sessions. (#31526)
+- Webchat/silent token leak: filter assistant `NO_REPLY`-only transcript entries from `chat.history` responses and add client-side defense-in-depth guards in the chat controller so internal silent tokens never render as visible chat bubbles. (#32015) Consolidates overlap from #32183, #32082, #32045, #32052, #32172, and #32112. Thanks @ademczuk, @liuxiaopai-ai, @ningding97, @bmendonca3, and @x4v13r1120.
+- Doctor/local memory provider checks: stop false-positive local-provider warnings when `provider=local` and no explicit `modelPath` is set by honoring default local model fallback while still warning when gateway probe reports local embeddings not ready. (#32014) Fixes #31998. Thanks @adhishthite.
+- Media understanding/parakeet CLI output parsing: read `parakeet-mlx` transcripts from `--output-dir/<media-basename>.txt` when txt output is requested (or default), with stdout fallback for non-txt formats. (#9177) Thanks @mac-110.
+- Media understanding/audio transcription guard: skip tiny/empty audio files (<1024 bytes) before provider/CLI transcription to avoid noisy invalid-audio failures and preserve clean fallback behavior. (#8388) Thanks @Glucksberg.
+- Gateway/Plugin HTTP route precedence: run explicit plugin HTTP routes before the Control UI SPA catch-all so registered plugin webhook/custom paths remain reachable, while unmatched paths still fall through to Control UI handling. (#31885) Thanks @Sid-Qin.
+- Gateway/Node browser proxy routing: honor `profile` from `browser.request` JSON body when query params omit it, while preserving query-profile precedence when both are present. (#28852) Thanks @Sid-Qin.
+- Gateway/Control UI basePath POST handling: return 405 for `POST` on exact basePath routes (for example `/openclaw`) instead of redirecting, and add end-to-end regression coverage that root-mounted webhook POST paths still pass through to plugin handlers. (#31349) Thanks @Sid-Qin.
+- Browser/default profile selection: default `browser.defaultProfile` behavior now prefers `openclaw` (managed standalone CDP) when no explicit default is configured, while still auto-provisioning the `chrome` relay profile for explicit opt-in use. (#32031) Fixes #31907. Thanks @liuxiaopai-ai.
+- Sandbox/mkdirp boundary checks: allow existing in-boundary directories to pass mkdirp boundary validation when directory open probes return platform-specific I/O errors, with regression coverage for directory-safe fallback behavior. (#31547) Thanks @stakeswky.
+- Models/config env propagation: apply `config.env.vars` before implicit provider discovery in models bootstrap so config-scoped credentials are visible to implicit provider resolution paths. (#32295) Thanks @hsiaoa.
+- Models/Codex usage labels: infer weekly secondary usage windows from reset cadence when API window seconds are ambiguously reported as 24h, so `openclaw models status` no longer mislabels weekly limits as daily. (#31938) Thanks @bmendonca3.
+- Gateway/Heartbeat model reload: treat `models.*` and `agents.defaults.model` config updates as heartbeat hot-reload triggers so heartbeat picks up model changes without a full gateway restart. (#32046) Thanks @stakeswky.
+- Memory/LanceDB embeddings: forward configured `embedding.dimensions` into OpenAI embeddings requests so vector size and API output dimensions stay aligned when dimensions are explicitly configured. (#32036) Thanks @scotthuang.
+- Gateway/Control UI method guard: allow POST requests to non-UI routes to fall through when no base path is configured, and add POST regression coverage for fallthrough and base-path 405 behavior. (#23970) Thanks @tyler6204.
+- Browser/CDP status accuracy: require a successful `Browser.getVersion` response over the CDP websocket (not just socket-open) before reporting `cdpReady`, so stale idle command channels are surfaced as unhealthy. (#23427) Thanks @vincentkoc.
+- Daemon/systemd checks in containers: treat missing `systemctl` invocations (including `spawn systemctl ENOENT`/`EACCES`) as unavailable service state during `is-enabled` checks, preventing container flows from failing with `Gateway service check failed` before install/status handling can continue. (#26089) Thanks @sahilsatralkar and @vincentkoc.
+- Security/Node exec approvals: revalidate approval-bound `cwd` identity immediately before execution/forwarding and fail closed with an explicit denial when `cwd` drifts after approval hardening.
+- Security audit/skills workspace hardening: add `skills.workspace.symlink_escape` warning in `openclaw security audit` when workspace `skills/**/SKILL.md` resolves outside the workspace root (for example symlink-chain drift), plus docs coverage in the security glossary.
+- Security/Node exec approvals: preserve shell/dispatch-wrapper argv semantics during approval hardening so approved wrapper commands (for example `env sh -c ...`) cannot drift into a different runtime command shape, and add regression coverage for both approval-plan generation and approved runtime execution paths. Thanks @tdjackey for reporting.
+- Security/fs-safe write hardening: make `writeFileWithinRoot` use same-directory temp writes plus atomic rename, add post-write inode/hardlink revalidation with security warnings on boundary drift, and avoid truncating existing targets when final rename fails.
+- Security/Skills archive extraction: unify tar extraction safety checks across tar.gz and tar.bz2 install flows, enforce tar compressed-size limits, and fail closed if tar.bz2 archives change between preflight and extraction to prevent bypasses of entry-type/size guardrails. Thanks @GCXWLP for reporting.
+- Security/Prompt spoofing hardening: stop injecting queued runtime events into user-role prompt text, route them through trusted system-prompt context, and neutralize inbound spoof markers like `[System Message]` and line-leading `System:` in untrusted message content. (#30448)
+- Sandbox/Docker setup command parsing: accept `agents.*.sandbox.docker.setupCommand` as either a string or a string array, and normalize arrays to newline-delimited shell scripts so multi-step setup commands no longer concatenate without separators. (#31953) Thanks @liuxiaopai-ai.
+- Sandbox/Bootstrap context boundary hardening: reject symlink/hardlink alias bootstrap seed files that resolve outside the source workspace and switch post-compaction `AGENTS.md` context reads to boundary-verified file opens, preventing host file content from being injected via workspace aliasing. Thanks @tdjackey for reporting.
+- Agents/Sandbox workdir mapping: map container workdir paths (for example `/workspace`) back to the host workspace before sandbox path validation so exec requests keep the intended directory in containerized runs instead of falling back to an unavailable host path. (#31841) Thanks @liuxiaopai-ai.
+- Docker/Sandbox bootstrap hardening: make `OPENCLAW_SANDBOX` opt-in parsing explicit (`1|true|yes|on`), support custom Docker socket paths via `OPENCLAW_DOCKER_SOCKET`, defer docker.sock exposure until sandbox prerequisites pass, and reset/roll back persisted sandbox mode to `off` when setup is skipped or partially fails to avoid stale broken sandbox state. (#29974) Thanks @jamtujest and @vincentkoc.
+- Hooks/webhook ACK compatibility: return `200` (instead of `202`) for successful `/hooks/agent` requests so providers that require `200` (for example Forward Email) accept dispatched agent hook deliveries. (#28204) Thanks @AIflow-Labs.
+- Feishu/Run channel fallback: prefer `Provider` over `Surface` when inferring queued run `messageProvider` fallback (when `OriginatingChannel` is missing), preventing Feishu turns from being mislabeled as `webchat` in mixed relay metadata contexts. (#31880) Fixes #31859. Thanks @liuxiaopai-ai.
+- Skills/sherpa-onnx-tts: run the `sherpa-onnx-tts` bin under ESM (replace CommonJS `require` imports) and add regression coverage to prevent `require is not defined in ES module scope` startup crashes. (#31965) Thanks @bmendonca3.
+- Inbound metadata/direct relay context: restore direct-channel conversation metadata blocks for external channels (for example WhatsApp) while preserving webchat-direct suppression, so relay agents recover sender/message identifiers without reintroducing internal webchat metadata noise. (#31969) Fixes #29972. Thanks @Lucenx9.
+- Slack/Channel message subscriptions: register explicit `message.channels` and `message.groups` monitor handlers (alongside generic `message`) so channel/group event subscriptions are consumed even when Slack dispatches typed message event names. Fixes #31674.
+- Hooks/session-scoped memory context: expose ephemeral `sessionId` in embedded plugin tool contexts and `before_tool_call`/`after_tool_call` hook contexts (including compaction and client-tool wiring) so plugins can isolate per-conversation state across `/new` and `/reset`. Related #31253 and #31304. Thanks @Sid-Qin and @Servo-AIpex.
+- Voice-call/Twilio inbound greeting: run answered-call initial notify greeting for Twilio instead of skipping the manager speak path, with regression coverage for both Twilio and Plivo notify flows. (#29121) Thanks @xinhuagu.
+- Voice-call/stale call hydration: verify active calls with the provider before loading persisted in-progress calls so stale locally persisted records do not block or misroute new call handling after restarts. (#4325) Thanks @garnetlyx.
+- Feishu/File upload filenames: percent-encode non-ASCII/special-character `file_name` values in Feishu multipart uploads so Chinese/symbol-heavy filenames are sent as proper attachments instead of plain text links. (#31179) Thanks @Kay-051.
+- Media/MIME channel parity: route Telegram/Signal/iMessage media-kind checks through normalized `kindFromMime` so mixed-case/parameterized MIME values classify consistently across message channels.
+- WhatsApp/inbound self-message context: propagate inbound `fromMe` through the web inbox pipeline and annotate direct self messages as `(self)` in envelopes so agents can distinguish owner-authored turns from contact turns. (#32167) Thanks @scoootscooob.
+- Webchat/stream finalization: persist streamed assistant text when final events omit `message`, while keeping final payload precedence and skipping empty stream buffers to prevent disappearing replies after tool turns. (#31920) Thanks @Sid-Qin.
+- Feishu/Inbound ordering: serialize message handling per chat while preserving cross-chat concurrency to avoid same-chat race drops under bursty inbound traffic. (#31807)
+- Feishu/Typing notification suppression: skip typing keepalive reaction re-adds when the indicator is already active, preventing duplicate notification pings from repeated identical emoji adds. (#31580)
+- Feishu/Probe failure backoff: cache API and timeout probe failures for one minute per account key while preserving abort-aware probe timeouts, reducing repeated health-check retries during transient credential/network outages. (#29970)
+- Feishu/Streaming block fallback: preserve markdown block stream text as final streaming-card content when final payload text is missing, while still suppressing non-card internal block chunk delivery. (#30663)
+- Feishu/Bitable API errors: unify Feishu Bitable tool error handling with structured `LarkApiError` responses and consistent API/context attribution across wiki/base metadata, field, and record operations. (#31450)
+- Feishu/Missing-scope grant URL fix: rewrite known invalid scope aliases (`contact:contact.base:readonly`) to valid scope names in permission grant links, so remediation URLs open with correct Feishu consent scopes. (#31943)
+- BlueBubbles/Message metadata: harden send response ID extraction, include sender identity in DM context, and normalize inbound `message_id` selection to avoid duplicate ID metadata. (#23970) Thanks @tyler6204.
+- WebChat/markdown tables: ensure GitHub-flavored markdown table parsing is explicitly enabled at render time and add horizontal overflow handling for wide tables, with regression coverage for table-only and mixed text+table content. (#32365) Thanks @BlueBirdBack.
+- Feishu/default account resolution: always honor explicit `channels.feishu.defaultAccount` during outbound account selection (including top-level-credential setups where the preferred id is not present in `accounts`), instead of silently falling back to another account id. (#32253) Thanks @bmendonca3.
+- Feishu/Sender lookup permissions: suppress user-facing grant prompts for stale non-existent scope errors (`contact:contact.base:readonly`) during best-effort sender-name resolution so inbound messages continue without repeated false permission notices. (#31761)
+- Discord/dispatch + Slack formatting: restore parallel outbound dispatch across Discord channels with per-channel queues while preserving in-channel ordering, and run Slack preview/stream update text through mrkdwn normalization for consistent formatting. (#31927) Thanks @Sid-Qin.
+- Feishu/Inbound debounce: debounce rapid same-chat sender bursts into one ordered dispatch turn, skip already-processed retries when composing merged text, and preserve bot-mention intent across merged entries to reduce duplicate or late inbound handling. (#31548)
+- Tests/Sandbox + archive portability: use junction-compatible directory-link setup on Windows and explicit file-symlink platform guards in symlink escape tests where unprivileged file symlinks are unavailable, reducing false Windows CI failures while preserving traversal checks on supported paths. (#28747) Thanks @arosstale.
+- Browser/Extension re-announce reliability: keep relay state in `connecting` when re-announce forwarding fails and extend debugger re-attach retries after navigation to reduce false attached states and post-nav disconnect loops. (#27630) Thanks @markmusson.
+- Browser/Act request compatibility: accept legacy flattened `action="act"` params (`kind/ref/text/...`) in addition to `request={...}` so browser act calls no longer fail with `request required`. (#15120) Thanks @vincentkoc.
+- OpenRouter/x-ai compatibility: skip `reasoning.effort` injection for `x-ai/*` models (for example Grok) so OpenRouter requests no longer fail with invalid-arguments errors on unsupported reasoning params. (#32054) Thanks @scoootscooob.
+- Models/openai-completions developer-role compatibility: force `supportsDeveloperRole=false` for non-native endpoints, treat unparseable `baseUrl` values as non-native, and add regression coverage for empty/malformed baseUrl plus explicit-true override behavior. (#29479) thanks @akramcodez.
+- Browser/Profile attach-only override: support `browser.profiles.<name>.attachOnly` (fallback to global `browser.attachOnly`) so loopback proxy profiles can skip local launch/port-ownership checks without forcing attach-only mode for every profile. (#20595) Thanks @unblockedgamesstudio and @vincentkoc.
+- Sessions/Lock recovery: detect recycled Linux PIDs by comparing lock-file `starttime` with `/proc/<pid>/stat` starttime, so stale `.jsonl.lock` files are reclaimed immediately in containerized PID-reuse scenarios while preserving compatibility for older lock files. (#26443) Fixes #27252. Thanks @HirokiKobayashi-R and @vincentkoc.
+- Cron/isolated delivery target fallback: remove early unresolved-target return so cron delivery can flow through shared outbound target resolution (including per-channel `resolveDefaultTo` fallback) when `delivery.to` is omitted. (#32364) Thanks @hclsys.
+- OpenAI media capabilities: include `audio` in the OpenAI provider capability list so audio transcription models are eligible in media-understanding provider selection. (#12717) Thanks @openjay.
+- Browser/Managed tab cap: limit loopback managed `openclaw` page tabs to 8 via best-effort cleanup after tab opens to reduce long-running renderer buildup while preserving attach-only and remote profile behavior. (#29724) Thanks @pandego.
+- Docker/Image health checks: add Dockerfile `HEALTHCHECK` that probes gateway `GET /healthz` so container runtimes can mark unhealthy instances without requiring auth credentials in the probe command. (#11478) Thanks @U-C4N and @vincentkoc.
+- Gateway/Node dangerous-command parity: include `sms.send` in default onboarding node `denyCommands`, share onboarding deny defaults with the gateway dangerous-command source of truth, and include `sms.send` in phone-control `/phone arm writes` handling so SMS follows the same break-glass flow as other dangerous node commands. Thanks @zpbrent.
+- Pairing/AllowFrom account fallback: handle omitted `accountId` values in `readChannelAllowFromStore` and `readChannelAllowFromStoreSync` as `default`, while preserving legacy unscoped allowFrom merges for default-account flows. Thanks @Sid-Qin and @vincentkoc.
+- Browser/Remote CDP ownership checks: skip local-process ownership errors for non-loopback remote CDP profiles when HTTP is reachable but the websocket handshake fails, and surface the remote websocket attach/retry path instead. (#15582) Landed from contributor (#28780) Thanks @stubbi, @bsormagec, @unblockedgamesstudio and @vincentkoc.
+- Browser/CDP proxy bypass: force direct loopback agent paths and scoped `NO_PROXY` expansion for localhost CDP HTTP/WS connections when proxy env vars are set, so browser relay/control still works behind global proxy settings. (#31469) Thanks @widingmarcus-cyber.
+- Sessions/idle reset correctness: preserve existing `updatedAt` during inbound metadata-only writes so idle-reset boundaries are not unintentionally refreshed before actual user turns. (#32379) Thanks @romeodiaz.
+- Sessions/lock recovery: reclaim orphan legacy same-PID lock files missing `starttime` when no in-process lock ownership exists, avoiding false lock timeouts after PID reuse while preserving active lock safety checks. (#32081) Thanks @bmendonca3.
+- Sessions/store cache invalidation: reload cached session stores when file size changes within the same mtime tick by keying cache validation on a single file-stat snapshot (`mtimeMs` + `sizeBytes`), with regression coverage for same-tick rewrites. (#32191) Thanks @jalehman.
+- Agents/Subagents `sessions_spawn`: reject malformed `agentId` inputs before normalization (for example error-message/path-like strings) to prevent unintended synthetic agent IDs and ghost workspace/session paths; includes strict validation regression coverage. (#31381) Thanks @openperf.
+- CLI/installer Node preflight: enforce Node.js `v22.12+` consistently in both `openclaw.mjs` runtime bootstrap and installer active-shell checks, with actionable nvm recovery guidance for mismatched shell PATH/defaults. (#32356) Thanks @jasonhargrove.
+- Web UI/config form: support SecretInput string-or-secret-ref unions in map `additionalProperties`, so provider API key fields stay editable instead of being marked unsupported. (#31866) Thanks @ningding97.
+- Auto-reply/inline command cleanup: preserve newline structure when stripping inline `/status` and extracting inline slash commands by collapsing only horizontal whitespace, preventing paragraph flattening in multi-line replies. (#32224) Thanks @scoootscooob.
+- Config/raw redaction safety: preserve non-sensitive literals during raw redaction round-trips, scope SecretRef redaction to secret IDs (not structural fields like `source`/`provider`), and fall back to structured raw redaction when text replacement cannot restore the original config shape. (#32174) Thanks @bmendonca3.
+- Hooks/runtime stability: keep the internal hook handler registry on a `globalThis` singleton so hook registration/dispatch remains consistent when bundling emits duplicate module copies. (#32292) Thanks @Drickon.
+- Hooks/after_tool_call: include embedded session context (`sessionKey`, `agentId`) and fire the hook exactly once per tool execution by removing duplicate adapter-path dispatch in embedded runs. (#32201) Thanks @jbeno, @scoootscooob, @vincentkoc.
+- Hooks/tool-call correlation: include `runId` and `toolCallId` in plugin tool hook payloads/context and scope tool start/adjusted-param tracking by run to prevent cross-run collisions in `before_tool_call` and `after_tool_call`. (#32360) Thanks @vincentkoc.
+- Plugins/install diagnostics: reject legacy plugin package shapes without `openclaw.extensions` and return an explicit upgrade hint with troubleshooting docs for repackaging. (#32055) Thanks @liuxiaopai-ai.
+- Hooks/plugin context parity: ensure `llm_input` hooks in embedded attempts receive the same `trigger` and `channelId`-aware `hookCtx` used by the other hook phases, preserving channel/trigger-scoped plugin behavior. (#28623) Thanks @davidrudduck and @vincentkoc.
+- Plugins/hardlink install compatibility: allow bundled plugin manifests and entry files to load when installed via hardlink-based package managers (`pnpm`, `bun`) while keeping hardlink rejection enabled for non-bundled plugin sources. (#32119) Fixes #28175, #28404, #29455. Thanks @markfietje.
+- Cron/session reaper reliability: move cron session reaper sweeps into `onTimer` `finally` and keep pruning active even when timer ticks fail early (for example cron store parse failures), preventing stale isolated run sessions from accumulating indefinitely. (#31996) Fixes #31946. Thanks @scoootscooob.
+- Cron/HEARTBEAT_OK summary leak: suppress fallback main-session enqueue for heartbeat/internal ack summaries in isolated announce mode so `HEARTBEAT_OK` noise never appears in user chat while real summaries still forward. (#32093) Thanks @scoootscooob.
+- Authentication: classify `permission_error` as `auth_permanent` for profile fallback. (#31324) Thanks @Sid-Qin.
+- Agents/host edit reliability: treat host edit-tool throws as success only when on-disk post-check confirms replacement likely happened (`newText` present and `oldText` absent), preventing false failure reports while avoiding pre-write false positives. (#32383) Thanks @polooooo.
+- Plugins/install fallback safety: resolve bare install specs to bundled plugin ids before npm lookup (for example `diffs` -> bundled `@openclaw/diffs`), keep npm fallback limited to true package-not-found errors, and continue rejecting non-plugin npm packages that fail manifest validation. (#32096) Thanks @scoootscooob.
+- Web UI/inline code copy fidelity: disable forced mid-token wraps on inline `<code>` spans so copied UUID/hash/token strings preserve exact content instead of inserting line-break spaces. (#32346) Thanks @hclsys.
+- Restart sentinel formatting: avoid duplicate `Reason:` lines when restart message text already matches `stats.reason`, keeping restart notifications concise for users and downstream parsers. (#32083) Thanks @velamints2.
+- Auto-reply/followup queue: avoid stale callback reuse across idle-window restarts by caching the followup runner only when a drain actually starts, preserving enqueue ordering after empty-finalize paths. (#31902) Thanks @Lanfei.
+- Agents/tool-result guard: always clear pending tool-call state on interruptions even when synthetic tool results are disabled, preventing orphaned tool-use transcripts that cause follow-up provider request failures. (#32120) Thanks @jnMetaCode.
+- Failover/error classification: treat HTTP `529` (provider overloaded, common with Anthropic-compatible APIs) as `rate_limit` so model failover can engage instead of misclassifying the error path. (#31854) Thanks @bugkill3r.
+- Logging: use local time for logged timestamps instead of UTC, aligning log output with documented local timezone behavior and avoiding confusion during local diagnostics. (#28434) Thanks @liuy.
+- Agents/Subagent announce cleanup: keep completion-message runs pending while descendants settle, add a 30 minute hard-expiry backstop to avoid indefinite pending state, and keep retry bookkeeping resumable across deferred wakes. (#23970) Thanks @tyler6204.
+- Secrets/exec resolver timeout defaults: use provider `timeoutMs` as the default inactivity (`noOutputTimeoutMs`) watchdog for exec secret providers, preventing premature no-output kills for resolvers that start producing output after 2s. (#32235) Thanks @bmendonca3.
+- Auto-reply/reminder guard note suppression: when a turn makes reminder-like commitments but schedules no new cron jobs, suppress the unscheduled-reminder warning note only if an enabled cron already exists for the same session; keep warnings for unrelated sessions, disabled jobs, or unreadable cron store paths. (#32255) Thanks @scoootscooob.
+- Cron/isolated announce heartbeat suppression: treat multi-payload runs as skippable when any payload is a heartbeat ack token and no payload has media, preventing internal narration + trailing `HEARTBEAT_OK` from being delivered to users. (#32131) Thanks @adhishthite.
+- Cron/store migration: normalize legacy cron jobs with string `schedule` and top-level `command`/`timeout` fields into canonical schedule/payload/session-target shape on load, preventing schedule-error loops on old persisted stores. (#31926) Thanks @bmendonca3.
+- Tests/Windows backup rotation: skip chmod-only backup permission assertions on Windows while retaining compose/rotation/prune coverage across platforms to avoid false CI failures from Windows non-POSIX mode semantics. (#32286) Thanks @jalehman.
+- Tests/Subagent announce: set `OPENCLAW_TEST_FAST=1` before importing `subagent-announce` format suites so module-level fast-mode constants are captured deterministically on Windows CI, preventing timeout flakes in nested completion announce coverage. (#31370) Thanks @zwffff.
+
+## 2026.3.1
+
+### Changes
+
+- OpenAI/Streaming transport: make `openai` Responses WebSocket-first by default (`transport: "auto"` with SSE fallback), add shared OpenAI WS stream/connection runtime wiring with per-session cleanup, and preserve server-side compaction payload mutation (`store` + `context_management`) on the WS path.
 - Gateway/Container probes: add built-in HTTP liveness/readiness endpoints (`/health`, `/healthz`, `/ready`, `/readyz`) for Docker/Kubernetes health checks, with fallback routing so existing handlers on those paths are not shadowed. (#31272) Thanks @vincentkoc.
-- README/Contributors: rank contributor avatars by composite score (commits + merged PRs + code LOC), excluding docs-only LOC to prevent bulk-generated files from inflating rankings. (#23970) Thanks @tyler6204.
 - Android/Nodes: add `camera.list`, `device.permissions`, `device.health`, and `notifications.actions` (`open`/`dismiss`/`reply`) on Android nodes, plus first-class node-tool actions for the new device/notification commands. (#28260) Thanks @obviyus.
 - Discord/Thread bindings: replace fixed TTL lifecycle with inactivity (`idleHours`, default 24h) plus optional hard `maxAgeHours` lifecycle controls, and add `/session idle` + `/session max-age` commands for focused thread-bound sessions. (#27845) Thanks @osolmaz.
 - Telegram/DM topics: add per-DM `direct` + topic config (allowlists, `dmPolicy`, `skills`, `systemPrompt`, `requireTopic`), route DM topics as distinct inbound/outbound sessions, and enforce topic-aware authorization/debounce for messages, callbacks, commands, and reactions. Landed from contributor PR #30579 by @kesor. Thanks @kesor.
-- Telegram/DM streaming: use `sendMessageDraft` for private preview streaming, keep reasoning/answer preview lanes separated in DM reasoning-stream mode. (#31824) Thanks @obviyus.
-- Web UI/Cron i18n: localize cron page labels, filters, form help text, and validation/error messaging in English and zh-CN. (#29315) Thanks @BUGKillerKing.
-- OpenAI/Streaming transport: make `openai` Responses WebSocket-first by default (`transport: "auto"` with SSE fallback), add shared OpenAI WS stream/connection runtime wiring with per-session cleanup, and preserve server-side compaction payload mutation (`store` + `context_management`) on the WS path.
 - Android/Gateway capability refresh: add live Android capability integration coverage and node canvas capability refresh wiring, plus runtime hardening for A2UI readiness retries, scoped canvas URL normalization, debug diagnostics JSON, and JavaScript MIME delivery. (#28388) Thanks @obviyus.
 - Android/Nodes parity: add `system.notify`, `photos.latest`, `contacts.search`/`contacts.add`, `calendar.events`/`calendar.add`, and `motion.activity`/`motion.pedometer`, with motion sensor-aware command gating and improved activity sampling reliability. (#29398) Thanks @obviyus.
+- Agents/Thinking defaults: set `adaptive` as the default thinking level for Anthropic Claude 4.6 models (including Bedrock Claude 4.6 refs) while keeping other reasoning-capable models at `low` unless explicitly configured.
+- Web UI/Cron i18n: localize cron page labels, filters, form help text, and validation/error messaging in English and zh-CN. (#29315) Thanks @BUGKillerKing.
 - CLI/Config: add `openclaw config file` to print the active config file path resolved from `OPENCLAW_CONFIG_PATH` or the default location. (#26256) thanks @cyb1278588254.
 - Feishu/Docx tables + uploads: add `feishu_doc` actions for Docx table creation/cell writing (`create_table`, `write_table_cells`, `create_table_with_values`) and image/file uploads (`upload_image`, `upload_file`) with stricter create/upload error handling for missing `document_id` and placeholder cleanup failures. (#20304) Thanks @xuhao1.
 - Feishu/Reactions: add inbound `im.message.reaction.created_v1` handling, route verified reactions through synthetic inbound turns, and harden verification with timeout + fail-closed filtering so non-bot or unverified reactions are dropped. (#16716) Thanks @schumilin.
@@ -29,7 +340,6 @@ Docs: https://docs.openclaw.ai
 - Feishu/Doc permissions: support optional owner permission grant fields on `feishu_doc` create and report permission metadata only when the grant call succeeds, with regression coverage for success/failure/omitted-owner paths. (#28295) Thanks @zhoulongchao77.
 - Web UI/i18n: add German (`de`) locale support and auto-render language options from supported locale constants in Overview settings. (#28495) thanks @dsantoreis.
 - Tools/Diffs: add a new optional `diffs` plugin tool for read-only diff rendering from before/after text or unified patches, with gateway viewer URLs for canvas and PNG image output. Thanks @gumadeiras.
-- Tools/Diffs: add PDF file output support and rendering quality customization controls (`fileQuality`, `fileScale`, `fileMaxWidth`) for generated diff artifacts, and document PDF as the preferred option when messaging channels compress images. (#31342) Thanks @gumadeiras.
 - Memory/LanceDB: support custom OpenAI `baseUrl` and embedding dimensions for LanceDB memory. (#17874) Thanks @rish2jain and @vincentkoc.
 - ACP/ACPX streaming: pin ACPX plugin support to `0.1.15`, add configurable ACPX command/version probing, and streamline ACP stream delivery (`final_only` default + reduced tool-event noise) with matching runtime and test updates. (#30036) Thanks @osolmaz.
 - Shell env markers: set `OPENCLAW_SHELL` across shell-like runtimes (`exec`, `acp`, `acp-client`, `tui-local`) so shell startup/config rules can target OpenClaw contexts consistently, and document the markers in env/exec/acp/TUI docs. Thanks @vincentkoc.
@@ -39,81 +349,54 @@ Docs: https://docs.openclaw.ai
 
 ### Breaking
 
-- **BREAKING:** Zalo Personal plugin (`@openclaw/zalouser`) no longer depends on external `zca`-compatible CLI binaries (`openzca`, `zca-cli`) for runtime send/listen/login; operators should use `openclaw channels login --channel zalouser` after upgrade to refresh sessions in the new JS-native path.
 - **BREAKING:** Node exec approval payloads now require `systemRunPlan`. `host=node` approval requests without that plan are rejected.
 - **BREAKING:** Node `system.run` execution now pins path-token commands to the canonical executable path (`realpath`) in both allowlist and approval execution flows. Integrations/tests that asserted token-form argv (for example `tr`) must now accept canonical paths (for example `/usr/bin/tr`).
-- **BREAKING:** Plugin SDK removed `api.registerHttpHandler(...)`. Plugins must register explicit HTTP routes via `api.registerHttpRoute({ path, auth, match, handler })`, and dynamic webhook lifecycles should use `registerPluginHttpRoute(...)`.
 
 ### Fixes
 
-- Sandbox/Docker setup command parsing: accept `agents.*.sandbox.docker.setupCommand` as either a string or a string array, and normalize arrays to newline-delimited shell scripts so multi-step setup commands no longer concatenate without separators. (#31953) Thanks @liuxiaopai-ai.
-- Security/Node exec approvals: preserve shell/dispatch-wrapper argv semantics during approval hardening so approved wrapper commands (for example `env sh -c ...`) cannot drift into a different runtime command shape, and add regression coverage for both approval-plan generation and approved runtime execution paths. Thanks @tdjackey for reporting.
-- Sandbox/Bootstrap context boundary hardening: reject symlink/hardlink alias bootstrap seed files that resolve outside the source workspace and switch post-compaction `AGENTS.md` context reads to boundary-verified file opens, preventing host file content from being injected via workspace aliasing. Thanks @tdjackey for reporting.
-- Browser/Security output boundary hardening: replace check-then-rename output commits with root-bound fd-verified writes, unify install/skills canonical path-boundary checks, and add regression coverage for symlink-rebind race paths across browser output and shared fs-safe write flows. Thanks @tdjackey for reporting.
-- Security/Webhook request hardening: enforce auth-before-body parsing for BlueBubbles and Google Chat webhook handlers, add strict pre-auth body/time budgets for webhook auth paths (including LINE signature verification), and add shared in-flight/request guardrails plus regression tests/lint checks to prevent reintroducing unauthenticated slow-body DoS patterns. Thanks @GCXWLP for reporting.
-- Gateway/Security hardening: tie loopback-origin dev allowance to actual local socket clients (not Host header claims), add explicit warnings/metrics when `gateway.controlUi.dangerouslyAllowHostHeaderOriginFallback` accepts websocket origins, harden safe-regex detection for quantified ambiguous alternation patterns (for example `(a|aa)+`), and bound large regex-evaluation inputs for session-filter and log-redaction paths.
-- Tests/Sandbox + archive portability: use junction-compatible directory-link setup on Windows and explicit file-symlink platform guards in symlink escape tests where unprivileged file symlinks are unavailable, reducing false Windows CI failures while preserving traversal checks on supported paths. (#28747) Thanks @arosstale.
-- Security/Skills archive extraction: unify tar extraction safety checks across tar.gz and tar.bz2 install flows, enforce tar compressed-size limits, and fail closed if tar.bz2 archives change between preflight and extraction to prevent bypasses of entry-type/size guardrails. Thanks @GCXWLP for reporting.
-- Tests/Subagent announce: set `OPENCLAW_TEST_FAST=1` before importing `subagent-announce` format suites so module-level fast-mode constants are captured deterministically on Windows CI, preventing timeout flakes in nested completion announce coverage. (#31370) Thanks @zwffff.
-- Gateway/Node dangerous-command parity: include `sms.send` in default onboarding node `denyCommands`, share onboarding deny defaults with the gateway dangerous-command source of truth, and include `sms.send` in phone-control `/phone arm writes` handling so SMS follows the same break-glass flow as other dangerous node commands. Thanks @zpbrent.
-- Zalo/Pairing auth tests: add webhook regression coverage asserting DM pairing-store reads/writes remain account-scoped, preventing cross-account authorization bleed in multi-account setups. (#26121) Thanks @bmendonca3.
-- Logging: use local time for logged timestamps instead of UTC, aligning log output with documented local timezone behavior and avoiding confusion during local diagnostics. (#28434) Thanks @liuy.
-- Zalouser/Pairing auth tests: add account-scoped DM pairing-store regression coverage (`monitor.account-scope.test.ts`) to prevent cross-account allowlist bleed in multi-account setups. (#26672) Thanks @bmendonca3.
-- Security/Web tools SSRF guard: keep DNS pinning for untrusted `web_fetch` and citation-redirect URL checks when proxy env vars are set, and require explicit dangerous opt-in before env-proxy routing can bypass pinned dispatch for trusted/operator-controlled endpoints. Thanks @tdjackey for reporting.
-- Gateway/Security canonicalization hardening: decode plugin route path variants to canonical fixpoint (with bounded depth), fail closed on canonicalization anomalies, and enforce gateway auth for deeply encoded `/api/channels/*` variants to prevent alternate-path auth bypass through plugin handlers. Thanks @tdjackey for reporting.
-- Gateway/Plugin HTTP hardening: require explicit `auth` for plugin route registration, add route ownership guards for duplicate `path+match` registrations, centralize plugin path matching/auth logic into dedicated modules, and share webhook target-route lifecycle wiring across channel monitors to avoid stale or conflicting registrations. Thanks @tdjackey for reporting.
-- Agents/Sessions list transcript paths: handle missing/non-string/relative `sessions.list.path` values and per-agent `{agentId}` templates when deriving `transcriptPath`, so cross-agent session listings resolve to concrete agent session files instead of workspace-relative paths. (#24775) Thanks @martinfrancois.
-- Agents/Subagents `sessions_spawn`: reject malformed `agentId` inputs before normalization (for example error-message/path-like strings) to prevent unintended synthetic agent IDs and ghost workspace/session paths; includes strict validation regression coverage. (#31381) Thanks @openperf.
-- macOS/PeekabooBridge: add compatibility socket symlinks for legacy `clawdbot`, `clawdis`, and `moltbot` Application Support socket paths so pre-rename clients can still connect. (#6033) Thanks @lumpinif and @vincentkoc.
-- Webchat/Feishu session continuation: preserve routable `OriginatingChannel`/`OriginatingTo` metadata from session delivery context in `chat.send`, and prefer provider-normalized channel when deciding cross-channel route dispatch so Webchat replies continue on the selected Feishu session instead of falling back to main/internal session routing. (#31573)
-- Feishu/Duplicate replies: suppress same-target reply dispatch when message-tool sends use generic provider metadata (`provider: "message"`) and normalize `lark`/`feishu` provider aliases during duplicate-target checks, preventing double-delivery in Feishu sessions. (#31526)
-- Feishu/Plugin sdk compatibility: add safe webhook default fallbacks when loading Feishu monitor state so mixed-version installs no longer crash if older `openclaw/plugin-sdk` builds omit webhook default constants. (#31606)
-- Pairing/AllowFrom account fallback: handle omitted `accountId` values in `readChannelAllowFromStore` and `readChannelAllowFromStoreSync` as `default`, while preserving legacy unscoped allowFrom merges for default-account flows. Thanks @Sid-Qin and @vincentkoc.
-- Agents/Subagent announce cleanup: keep completion-message runs pending while descendants settle, add a 30 minute hard-expiry backstop to avoid indefinite pending state, and keep retry bookkeeping resumable across deferred wakes. (#23970) Thanks @tyler6204.
-- BlueBubbles/Message metadata: harden send response ID extraction, include sender identity in DM context, and normalize inbound `message_id` selection to avoid duplicate ID metadata. (#23970) Thanks @tyler6204.
-- Gateway/Control UI method guard: allow POST requests to non-UI routes to fall through when no base path is configured, and add POST regression coverage for fallthrough and base-path 405 behavior. (#23970) Thanks @tyler6204.
-- Gateway/Control UI basePath POST handling: return 405 for `POST` on exact basePath routes (for example `/openclaw`) instead of redirecting, and add end-to-end regression coverage that root-mounted webhook POST paths still pass through to plugin handlers. (#31349) Thanks @Sid-Qin.
-- Authentication: classify `permission_error` as `auth_permanent` for profile fallback. (#31324) Thanks @Sid-Qin.
-- Security/Prompt spoofing hardening: stop injecting queued runtime events into user-role prompt text, route them through trusted system-prompt context, and neutralize inbound spoof markers like `[System Message]` and line-leading `System:` in untrusted message content. (#30448)
-- Gateway/Node browser proxy routing: honor `profile` from `browser.request` JSON body when query params omit it, while preserving query-profile precedence when both are present. (#28852) Thanks @Sid-Qin.
-- Browser/Extension relay reconnect tolerance: keep `/json/version` and `/cdp` reachable during short MV3 worker disconnects when attached targets still exist, and retain clients across reconnect grace windows. (#30232) Thanks @Sid-Qin.
-- Browser/Extension re-announce reliability: keep relay state in `connecting` when re-announce forwarding fails and extend debugger re-attach retries after navigation to reduce false attached states and post-nav disconnect loops. (#27630) Thanks @markmusson.
-- Browser/Extension navigation reattach: preserve debugger re-attachment when relay is temporarily disconnected by deferring relay attach events until reconnect/re-announce, reducing post-navigation tab loss. (#28725) Thanks @stone-jin.
-- Browser/Profile defaults: prefer `openclaw` profile over `chrome` in headless/no-sandbox environments unless an explicit `defaultProfile` is configured. (#14944) Thanks @BenediktSchackenberg.
-- Browser/Remote CDP ownership checks: skip local-process ownership errors for non-loopback remote CDP profiles when HTTP is reachable but the websocket handshake fails, and surface the remote websocket attach/retry path instead. (#15582) Landed from contributor (#28780) Thanks @stubbi, @bsormagec, @unblockedgamesstudio and @vincentkoc.
-- Browser/Profile attach-only override: support `browser.profiles.<name>.attachOnly` (fallback to global `browser.attachOnly`) so loopback proxy profiles can skip local launch/port-ownership checks without forcing attach-only mode for every profile. (#20595) Thanks @unblockedgamesstudio and @vincentkoc.
-- Browser/Act request compatibility: accept legacy flattened `action="act"` params (`kind/ref/text/...`) in addition to `request={...}` so browser act calls no longer fail with `request required`. (#15120) Thanks @vincentkoc.
-- Browser/Extension relay stale tabs: evict stale cached targets from `/json/list` when extension targets are destroyed/crashed or commands fail with missing target/session errors. (#6175) Thanks @vincentkoc.
-- CLI/Browser start timeout: honor `openclaw browser --timeout <ms> start` and stop by removing the fixed 15000ms override so slower Chrome startups can use caller-provided timeouts. (#22412, #23427) Thanks @vincentkoc.
-- Browser/CDP startup diagnostics: include Chrome stderr output and a Linux no-sandbox hint in startup timeout errors so failed launches are easier to diagnose. (#29312) Thanks @veast.
-- Browser/CDP startup readiness: wait for CDP websocket readiness after launching Chrome and cleanly stop/reset when readiness never arrives, reducing follow-up `PortInUseError` races after `browser start`/`open`. (#29538) Thanks @AaronWander.
-- Browser/Managed tab cap: limit loopback managed `openclaw` page tabs to 8 via best-effort cleanup after tab opens to reduce long-running renderer buildup while preserving attach-only and remote profile behavior. (#29724) Thanks @pandego.
-- Browser/CDP proxy bypass: force direct loopback agent paths and scoped `NO_PROXY` expansion for localhost CDP HTTP/WS connections when proxy env vars are set, so browser relay/control still works behind global proxy settings. (#31469) Thanks @widingmarcus-cyber.
-- Docker/Image health checks: add Dockerfile `HEALTHCHECK` that probes gateway `GET /healthz` so container runtimes can mark unhealthy instances without requiring auth credentials in the probe command. (#11478) Thanks @U-C4N and @vincentkoc.
-- Docker/Sandbox bootstrap hardening: make `OPENCLAW_SANDBOX` opt-in parsing explicit (`1|true|yes|on`), support custom Docker socket paths via `OPENCLAW_DOCKER_SOCKET`, defer docker.sock exposure until sandbox prerequisites pass, and reset/roll back persisted sandbox mode to `off` when setup is skipped or partially fails to avoid stale broken sandbox state. (#29974) Thanks @jamtujest and @vincentkoc.
-- Daemon/systemd checks in containers: treat missing `systemctl` invocations (including `spawn systemctl ENOENT`/`EACCES`) as unavailable service state during `is-enabled` checks, preventing container flows from failing with `Gateway service check failed` before install/status handling can continue. (#26089) Thanks @sahilsatralkar and @vincentkoc.
-- Android/Nodes reliability: reject `facing=both` when `deviceId` is set to avoid mislabeled duplicate captures, allow notification `open`/`reply` on non-clearable entries while still gating dismiss, trigger listener rebind before notification actions, and scale invoke-result ack timeout to invoke budget for large clip payloads. (#28260) Thanks @obviyus.
+- Feishu/Streaming card text fidelity: merge throttled/fragmented partial updates without dropping content and avoid newline injection when stitching chunk-style deltas so card-stream output matches final reply text. (#29616) Thanks @HaoHuaqing.
+- Security/Feishu webhook ingress: bound unauthenticated webhook rate-limit state with stale-window pruning and a hard key cap to prevent unbounded pre-auth memory growth from rotating source keys. (#26050) Thanks @bmendonca3.
+- Security/Compaction audit: remove the post-compaction audit injection message. (#28507) Thanks @fuller-stack-dev and @vincentkoc.
+- Web tools/RFC2544 fake-IP compatibility: allow RFC2544 benchmark range (`198.18.0.0/15`) for trusted web-tool fetch endpoints so proxy fake-IP networking modes do not trigger false SSRF blocks. Landed from contributor PR #31176 by @sunkinux. Thanks @sunkinux.
+- Feishu/Sessions announce group targets: normalize `group:` and `channel:` Feishu targets to `chat_id` routing so `sessions_send` announce delivery no longer sends group chat IDs via `user_id` API params. Fixes #31426.
 - Windows/Plugin install: avoid `spawn EINVAL` on Windows npm/npx invocations by resolving to `node` + npm CLI scripts instead of spawning `.cmd` directly. Landed from contributor PR #31147 by @codertony. Thanks @codertony.
-- Windows/Spawn canonicalization: unify non-core Windows spawn handling across ACP client, QMD/mcporter memory paths, and sandbox Docker execution using the shared wrapper-resolution policy, with targeted regression coverage for `.cmd` shim unwrapping and shell fallback behavior. (#31750) Thanks @Takhoffman.
-- Sandbox/mkdirp boundary checks: allow existing in-boundary directories to pass mkdirp boundary validation when directory open probes return platform-specific I/O errors, with regression coverage for directory-safe fallback behavior. (#31547) Thanks @stakeswky.
+- Web UI/Cron: include configured agent model defaults/fallbacks in cron model suggestions so scheduled-job model autocomplete reflects configured models. (#29709) Thanks @Sid-Qin.
+- Cron/Delivery: disable the agent messaging tool when `delivery.mode` is `"none"` so cron output is not sent to Telegram or other channels. (#21808) Thanks @lailoo.
+- CLI/Cron: clarify `cron list` output by renaming `Agent` to `Agent ID` and adding a `Model` column for isolated agent-turn jobs. (#26259) Thanks @openperf.
+- Gateway/Control UI origins: honor `gateway.controlUi.allowedOrigins: ["*"]` wildcard entries (including trimmed values) and lock behavior with regression tests. Landed from contributor PR #31058 by @byungsker. Thanks @byungsker.
+- Agents/Sessions list transcript paths: handle missing/non-string/relative `sessions.list.path` values and per-agent `{agentId}` templates when deriving `transcriptPath`, so cross-agent session listings resolve to concrete agent session files instead of workspace-relative paths. (#24775) Thanks @martinfrancois.
+- Gateway/Control UI CSP: allow required Google Fonts origins in Control UI CSP. (#29279) Thanks @vincentkoc.
+- CLI/Install: add an npm-link fallback to fix CLI startup `Permission denied` failures (`exit 127`) on affected installs. (#17151) Thanks @sskyu and @vincentkoc.
+- Plugins/NPM spec install: fix npm-spec plugin installs when `npm pack` output is empty by detecting newly created `.tgz` archives in the pack directory. (#21039) Thanks @graysurf and @vincentkoc.
+- Plugins/Install: clear stale install errors when an npm package is not found so follow-up install attempts report current state correctly. (#25073) Thanks @dalefrieswthat.
+- Gateway/macOS supervised restart: actively `launchctl kickstart -k` during intentional supervised restarts to bypass LaunchAgent `ThrottleInterval` delays, and fall back to in-process restart when kickstart fails. Landed from contributor PR #29078 by @cathrynlavery. Thanks @cathrynlavery.
+- Sessions/Internal routing: preserve established external `lastTo`/`lastChannel` routes for internal/non-deliverable turns, with added coverage for no-fallback internal routing behavior. Landed from contributor PR #30941 by @graysurf. Thanks @graysurf.
+- Auto-reply/NO_REPLY: strip `NO_REPLY` token from mixed-content messages instead of leaking raw control text to end users. Landed from contributor PR #31080 by @scoootscooob. Thanks @scoootscooob.
+- Inbound metadata/Multi-account routing: include `account_id` in trusted inbound metadata so multi-account channel sessions can reliably disambiguate the receiving account in prompt context. Landed from contributor PR #30984 by @Stxle2. Thanks @Stxle2.
+- Cron/Delivery mode none: send explicit `delivery: { mode: "none" }` from cron editor for both add and update flows so previous announce delivery is actually cleared. Landed from contributor PR #31145 by @byungsker. Thanks @byungsker.
+- Cron editor viewport: make the sticky cron edit form independently scrollable with viewport-bounded height so lower fields/actions are reachable on shorter screens. Landed from contributor PR #31133 by @Sid-Qin. Thanks @Sid-Qin.
+- Agents/Thinking fallback: when providers reject unsupported thinking levels without enumerating alternatives, retry with `think=off` to avoid hard failure during model/provider fallback chains. Landed from contributor PR #31002 by @yfge. Thanks @yfge.
+- Agents/Failover reason classification: avoid false rate-limit classification from incidental `tpm` substrings by matching TPM as a standalone token/phrase and keeping auth-context errors on the auth path. Landed from contributor PR #31007 by @HOYALIM. Thanks @HOYALIM.
+- Gateway/WS: close repeated post-handshake `unauthorized role:*` request floods per connection and sample duplicate rejection logs, preventing a single misbehaving client from degrading gateway responsiveness. (#20168) Thanks @acy103, @vibecodooor, and @vincentkoc.
+- Gateway/Auth: improve device-auth v2 migration diagnostics so operators get clearer guidance when legacy clients connect. (#28305) Thanks @vincentkoc.
+- CLI/Ollama config: allow `config set` for Ollama `apiKey` without predeclared provider config. (#29299) Thanks @vincentkoc.
+- Agents/Ollama: demote empty-discovery logging from `warn` to `debug` to reduce noisy warnings in normal edge-case discovery flows. (#26379) Thanks @byungsker.
+- Sandbox/Browser Docker: pass `OPENCLAW_BROWSER_NO_SANDBOX=1` to sandbox browser containers and bump sandbox browser security hash epoch so existing containers are recreated and pick up the env on upgrade. (#29879) Thanks @Lukavyi.
+- Tools/Edit workspace boundary errors: preserve the real `Path escapes workspace root` failure path instead of surfacing a misleading access/file-not-found error when editing outside workspace roots. Landed from contributor PR #31015 by @haosenwang1018. Thanks @haosenwang1018.
+- Browser/Open & navigate: accept `url` as an alias parameter for `open` and `navigate`. (#29260) Thanks @vincentkoc.
+- Sandbox/mkdirp boundary checks: allow directory-safe boundary validation for existing in-boundary subdirectories, preventing false `cannot create directories` failures in sandbox write mode. (#30610) Thanks @glitch418x.
+- Android/Nodes reliability: reject `facing=both` when `deviceId` is set to avoid mislabeled duplicate captures, allow notification `open`/`reply` on non-clearable entries while still gating dismiss, trigger listener rebind before notification actions, and scale invoke-result ack timeout to invoke budget for large clip payloads. (#28260) Thanks @obviyus.
 - LINE/Voice transcription: classify M4A voice media as `audio/mp4` (not `video/mp4`) by checking the MPEG-4 `ftyp` major brand (`M4A ` / `M4B `), restoring voice transcription for LINE voice messages. Landed from contributor PR #31151 by @scoootscooob. Thanks @scoootscooob.
 - Slack/Announce target account routing: enable session-backed announce-target lookup for Slack so multi-account announces resolve the correct `accountId` instead of defaulting to bot-token context. Landed from contributor PR #31028 by @taw0002. Thanks @taw0002.
 - Android/Voice screen TTS: stream assistant speech via ElevenLabs WebSocket in Talk Mode, stop cleanly on speaker mute/barge-in, and ignore stale out-of-order stream events. (#29521) Thanks @gregmousseau.
 - Android/Photos permissions: declare Android 14+ selected-photo access permission (`READ_MEDIA_VISUAL_USER_SELECTED`) and align Android permission/settings paths with current minSdk behavior for more reliable permission state handling.
-- Web UI/Cron: include configured agent model defaults/fallbacks in cron model suggestions so scheduled-job model autocomplete reflects configured models. (#29709) Thanks @Sid-Qin.
-- Cron/Delivery: disable the agent messaging tool when `delivery.mode` is `"none"` so cron output is not sent to Telegram or other channels. (#21808) Thanks @lailoo.
-- CLI/Cron: clarify `cron list` output by renaming `Agent` to `Agent ID` and adding a `Model` column for isolated agent-turn jobs. (#26259) Thanks @openperf.
 - Feishu/Reply media attachments: send Feishu reply `mediaUrl`/`mediaUrls` payloads as attachments alongside text/streamed replies in the reply dispatcher, including legacy fallback when `mediaUrls` is empty. (#28959) Thanks @icesword0760.
-- Feishu/Send target prefixes: normalize explicit `group:`/`dm:` send targets and preserve explicit receive-id routing hints when resolving outbound Feishu targets. (#31594) Thanks @liuxiaopai-ai.
-- Slack/User-token resolution: normalize Slack account user-token sourcing through resolved account metadata (`SLACK_USER_TOKEN` env + config) so monitor reads, Slack actions, directory lookups, onboarding allow-from resolution, and capabilities probing consistently use the effective user token. (#28103) Thanks @Glucksberg.
-- Slack/Channel message subscriptions: register explicit `message.channels` and `message.groups` monitor handlers (alongside generic `message`) so channel/group event subscriptions are consumed even when Slack dispatches typed message event names. Fixes #31674.
+- Slack/User-token resolution: normalize Slack account user-token sourcing through resolved account metadata (`SLACK_USER_TOKEN` env + config) so monitor reads, Slack actions, directory lookups, onboarding allow-from resolution, and capabilities probing consistently use the effective user token. (#28103) Thanks @chilu18.
 - Feishu/Outbound session routing: stop assuming bare `oc_` identifiers are always group chats, honor explicit `dm:`/`group:` prefixes for `oc_` chat IDs, and default ambiguous bare `oc_` targets to direct routing to avoid DM session misclassification. (#10407) Thanks @Bermudarat.
 - Feishu/Group session routing: add configurable group session scopes (`group`, `group_sender`, `group_topic`, `group_topic_sender`) with legacy `topicSessionMode=enabled` compatibility so Feishu group conversations can isolate sessions by sender/topic as configured. (#17798) Thanks @yfge.
 - Feishu/Reply-in-thread routing: add `replyInThread` config (`disabled|enabled`) for group replies, propagate `reply_in_thread` across text/card/media/streaming sends, and align topic-scoped session routing so newly created reply threads stay on the same session root. (#27325) Thanks @kcinzgg.
-- Feishu/Probe status caching: cache successful `probeFeishu()` bot-info results for 10 minutes (bounded cache with per-account keying) to reduce repeated status/onboarding probe API calls, while bypassing cache for failures and exceptions. (#28907) Thanks @Glucksberg.
-- Feishu/Opus media send type: send `.opus` attachments with `msg_type: "audio"` (instead of `"media"`) so Feishu voice messages deliver correctly while `.mp4` remains `msg_type: "media"` and documents remain `msg_type: "file"`. (#28269) Thanks @Glucksberg.
-- Gateway/WS security: keep plaintext `ws://` loopback-only by default, with explicit break-glass private-network opt-in via `OPENCLAW_ALLOW_INSECURE_PRIVATE_WS=1`; align onboarding/client/call validation and tests to this strict-default policy. (#28670) Thanks @dashed, @vincentkoc.
-- Gateway/Subagent TLS pairing: allow authenticated local `gateway-client` backend self-connections to skip device pairing while still requiring pairing for non-local/direct-host paths, restoring `sessions_spawn` with `gateway.tls.enabled=true` in Docker/LAN setups. Fixes #30740. Thanks @Sid-Qin and @vincentkoc.
+- Feishu/Probe status caching: cache successful `probeFeishu()` bot-info results for 10 minutes (bounded cache with per-account keying) to reduce repeated status/onboarding probe API calls, while bypassing cache for failures and exceptions. (#28907) Thanks @hou-rong.
+- Feishu/Opus media send type: send `.opus` attachments with `msg_type: "audio"` (instead of `"media"`) so Feishu voice messages deliver correctly while `.mp4` remains `msg_type: "media"` and documents remain `msg_type: "file"`. (#28269) Thanks @PinoHouse.
 - Feishu/Mobile video media type: treat inbound `message_type: "media"` as video-equivalent for media key extraction, placeholder inference, and media download resolution so mobile-app video sends ingest correctly. (#25502) Thanks @4ier.
 - Feishu/Inbound sender fallback: fall back to `sender_id.user_id` when `sender_id.open_id` is missing on inbound events, and use ID-type-aware sender lookup so mobile-delivered messages keep stable sender identity/routing. (#26703) Thanks @NewdlDewdl.
 - Feishu/Reply context metadata: include inbound `parent_id` and `root_id` as `ReplyToId`/`RootMessageId` in inbound context, and parse interactive-card quote bodies into readable text when fetching replied messages. (#18529) Thanks @qiangu.
@@ -132,17 +415,10 @@ Docs: https://docs.openclaw.ai
 - Slack/Native commands: register Slack native status as `/agentstatus` (Slack-reserved `/status`) so manifest slash command registration stays valid while text `/status` still works. Landed from contributor PR #29032 by @maloqab. Thanks @maloqab.
 - Android/Camera clip: remove `camera.clip` HTTP-upload fallback to base64 so clip transport is deterministic and fail-loud, and reject non-positive `maxWidth` values so invalid inputs fall back to the safe resize default. (#28229) Thanks @obviyus.
 - Android/Gateway canvas capability refresh: send `node.canvas.capability.refresh` with object `params` (`{}`) from Android node runtime so gateway object-schema validation accepts refresh retries and A2UI host recovery works after scoped capability expiry. (#28413) Thanks @obviyus.
-- Gateway/Control UI origins: honor `gateway.controlUi.allowedOrigins: ["*"]` wildcard entries (including trimmed values) and lock behavior with regression tests. Landed from contributor PR #31058 by @byungsker. Thanks @byungsker.
-- Agents/Sessions list transcript paths: handle missing/non-string/relative `sessions.list.path` values and per-agent `{agentId}` templates when deriving `transcriptPath`, so cross-agent session listings resolve to concrete agent session files instead of workspace-relative paths. (#24775) Thanks @martinfrancois.
-- Sessions/Lock recovery: detect recycled Linux PIDs by comparing lock-file `starttime` with `/proc/<pid>/stat` starttime, so stale `.jsonl.lock` files are reclaimed immediately in containerized PID-reuse scenarios while preserving compatibility for older lock files. (#26443) Fixes #27252. Thanks @HirokiKobayashi-R and @vincentkoc.
-- Gateway/Control UI CSP: allow required Google Fonts origins in Control UI CSP. (#29279) Thanks @Glucksberg and @vincentkoc.
-- CLI/Install: add an npm-link fallback to fix CLI startup `Permission denied` failures (`exit 127`) on affected installs. (#17151) Thanks @sskyu and @vincentkoc.
 - Onboarding/Custom providers: improve verification reliability for slower local endpoints (for example Ollama) during setup. (#27380) Thanks @Sid-Qin.
-- Plugins/NPM spec install: fix npm-spec plugin installs when `npm pack` output is empty by detecting newly created `.tgz` archives in the pack directory. (#21039) Thanks @graysurf and @vincentkoc.
-- Plugins/Install: clear stale install errors when an npm package is not found so follow-up install attempts report current state correctly. (#25073) Thanks @dalefrieswthat.
-- Security/Feishu webhook ingress: bound unauthenticated webhook rate-limit state with stale-window pruning and a hard key cap to prevent unbounded pre-auth memory growth from rotating source keys. (#26050) Thanks @bmendonca3.
-- Gateway/macOS supervised restart: actively `launchctl kickstart -k` during intentional supervised restarts to bypass LaunchAgent `ThrottleInterval` delays, and fall back to in-process restart when kickstart fails. Landed from contributor PR #29078 by @cathrynlavery. Thanks @cathrynlavery.
 - Daemon/macOS TLS certs: default LaunchAgent service env `NODE_EXTRA_CA_CERTS` to `/etc/ssl/cert.pem` (while preserving explicit overrides) so HTTPS clients no longer fail with local-issuer errors under launchd. (#27915) Thanks @Lukavyi.
+- Daemon/Linux systemd user-bus fallback: when `systemctl --user` cannot reach the user bus due missing session env, fall back to `systemctl --machine <user>@ --user` so daemon checks/install continue in headless SSH/server sessions. (#34884) Thanks @vincentkoc.
+- Gateway/Linux restart health: reduce false `openclaw gateway restart` timeouts by falling back to `ss -ltnp` when `lsof` is missing, confirming ambiguous busy-port cases via local gateway probe, and targeting the original `SUDO_USER` systemd user scope for restart commands. (#34874) Thanks @vincentkoc.
 - Discord/Components wildcard handlers: use distinct internal registration sentinel IDs and parse those sentinels as wildcard keys so select/user/role/channel/mentionable/modal interactions are not dropped by raw customId dedupe paths. Landed from contributor PR #29459 by @Sid-Qin. Thanks @Sid-Qin.
 - Feishu/Reaction notifications: add `channels.feishu.reactionNotifications` (`off | own | all`, default `own`) so operators can disable reaction ingress or allow all verified reaction events (not only bot-authored message reactions). (#28529) Thanks @cowboy129.
 - Feishu/Typing backoff: re-throw Feishu typing add/remove rate-limit and quota errors (`429`, `99991400`, `99991403`) and detect SDK non-throwing backoff responses so the typing keepalive circuit breaker can stop retries instead of looping indefinitely. (#28494) Thanks @guoqunabc.
@@ -153,56 +429,32 @@ Docs: https://docs.openclaw.ai
 - Feishu/API quota controls: add `typingIndicator` and `resolveSenderNames` config flags (top-level and per-account) so operators can disable typing reactions and sender-name lookup requests while keeping default behavior unchanged. (#10513) Thanks @BigUncle.
 - Feishu/System preview prompt leakage: stop enqueuing inbound Feishu message previews as system events so user preview text is not injected into later turns as trusted `System:` context. Landed from contributor PR #31209 by @stakeswky. Thanks @stakeswky.
 - Feishu/Typing replay suppression: skip typing indicators for stale replayed inbound messages after compaction using message-age checks with second/millisecond timestamp normalization, preventing old-message reaction floods while preserving typing for fresh messages. Landed from contributor PR #30709 by @arkyu2077. Thanks @arkyu2077.
-- Sessions/Internal routing: preserve established external `lastTo`/`lastChannel` routes for internal/non-deliverable turns, with added coverage for no-fallback internal routing behavior. Landed from contributor PR #30941 by @graysurf. Thanks @graysurf.
 - Control UI/Debug log layout: render Debug Event Log payloads at full width to prevent payload JSON from being squeezed into a narrow side column. Landed from contributor PR #30978 by @stozo04. Thanks @stozo04.
-- Auto-reply/NO_REPLY: strip `NO_REPLY` token from mixed-content messages instead of leaking raw control text to end users. Landed from contributor PR #31080 by @scoootscooob. Thanks @scoootscooob.
 - Install/npm: fix npm global install deprecation warnings. (#28318) Thanks @vincentkoc.
 - Update/Global npm: fallback to `--omit=optional` when global `npm update` fails so optional dependency install failures no longer abort update flows. (#24896) Thanks @xinhuagu and @vincentkoc.
-- Inbound metadata/Multi-account routing: include `account_id` in trusted inbound metadata so multi-account channel sessions can reliably disambiguate the receiving account in prompt context. Landed from contributor PR #30984 by @Stxle2. Thanks @Stxle2.
 - Model directives/Auth profiles: split `/model` profile suffixes at the first `@` after the last slash so email-based auth profile IDs (for example OAuth profile IDs) resolve correctly. Landed from contributor PR #30932 by @haosenwang1018. Thanks @haosenwang1018.
-- Cron/Delivery mode none: send explicit `delivery: { mode: "none" }` from cron editor for both add and update flows so previous announce delivery is actually cleared. Landed from contributor PR #31145 by @byungsker. Thanks @byungsker.
-- Cron editor viewport: make the sticky cron edit form independently scrollable with viewport-bounded height so lower fields/actions are reachable on shorter screens. Landed from contributor PR #31133 by @Sid-Qin. Thanks @Sid-Qin.
-- Agents/Thinking fallback: when providers reject unsupported thinking levels without enumerating alternatives, retry with `think=off` to avoid hard failure during model/provider fallback chains. Landed from contributor PR #31002 by @yfge. Thanks @yfge.
 - Ollama/Embedded runner base URL precedence: prioritize configured provider `baseUrl` over model defaults for embedded Ollama runs so Docker and remote-host setups avoid localhost fetch failures. (#30964) Thanks @stakeswky.
-- Agents/Failover reason classification: avoid false rate-limit classification from incidental `tpm` substrings by matching TPM as a standalone token/phrase and keeping auth-context errors on the auth path. Landed from contributor PR #31007 by @HOYALIM. Thanks @HOYALIM.
-- Gateway/WS: close repeated post-handshake `unauthorized role:*` request floods per connection and sample duplicate rejection logs, preventing a single misbehaving client from degrading gateway responsiveness. (#20168) Thanks @acy103, @vibecodooor, and @vincentkoc.
-- Gateway/Auth: improve device-auth v2 migration diagnostics so operators get clearer guidance when legacy clients connect. (#28305) Thanks @vincentkoc.
-- CLI/Ollama config: allow `config set` for Ollama `apiKey` without predeclared provider config. (#29299) Thanks @vincentkoc.
 - Ollama/Autodiscovery: harden autodiscovery and warning behavior. (#29201) Thanks @marcodelpin and @vincentkoc.
 - Ollama/Context window: unify context window handling across discovery, merge, and OpenAI-compatible transport paths. (#29205) Thanks @Sid-Qin, @jimmielightner, and @vincentkoc.
-- Agents/Ollama: demote empty-discovery logging from `warn` to `debug` to reduce noisy warnings in normal edge-case discovery flows. (#26379) Thanks @byungsker.
 - fix(model): preserve reasoning in provider fallback resolution. (#29285) Fixes #25636. Thanks @vincentkoc.
 - Docker/Image permissions: normalize `/app/extensions`, `/app/.agent`, and `/app/.agents` to directory mode `755` and file mode `644` during image build so plugin discovery does not block inherited world-writable paths. (#30191) Fixes #30139. Thanks @edincampara.
 - OpenAI Responses/Compaction: rewrite and unify the OpenAI Responses store patches to treat empty `baseUrl` as non-direct, honor `compat.supportsStore=false`, and auto-inject server-side compaction `context_management` for compatible direct OpenAI models (with per-model opt-out/threshold overrides). Landed from contributor PRs #16930 (@OiPunk), #22441 (@EdwardWu7), and #25088 (@MoerAI). Thanks @OiPunk, @EdwardWu7, and @MoerAI.
-- Sandbox/Browser Docker: pass `OPENCLAW_BROWSER_NO_SANDBOX=1` to sandbox browser containers and bump sandbox browser security hash epoch so existing containers are recreated and pick up the env on upgrade. (#29879) Thanks @Lukavyi.
+- Agents/Compaction safeguard: preserve recent turns verbatim with stable user/assistant pairing, keep multimodal and tool-result hints in preserved tails, and avoid empty-history fallback text in compacted output. (#25554) thanks @rodrigouroz.
 - Usage normalization: clamp negative prompt/input token values to zero (including `prompt_tokens` alias inputs) so `/usage` and TUI usage displays cannot show nonsensical negative counts. Landed from contributor PR #31211 by @scoootscooob. Thanks @scoootscooob.
 - Secrets/Auth profiles: normalize inline SecretRef `token`/`key` values to canonical `tokenRef`/`keyRef` before persistence, and keep explicit `keyRef` precedence when inline refs are also present. Landed from contributor PR #31047 by @minupla. Thanks @minupla.
-- Tools/Edit workspace boundary errors: preserve the real `Path escapes workspace root` failure path instead of surfacing a misleading access/file-not-found error when editing outside workspace roots. Landed from contributor PR #31015 by @haosenwang1018. Thanks @haosenwang1018.
-- Browser/Open & navigate: accept `url` as an alias parameter for `open` and `navigate`. (#29260) Thanks @vincentkoc.
 - Codex/Usage window: label weekly usage window as `Week` instead of `Day`. (#26267) Thanks @Sid-Qin.
 - Signal/Sync message null-handling: treat `syncMessage` presence (including `null`) as sync envelope traffic so replayed sentTranscript payloads cannot bypass loop guards after daemon restart. Landed from contributor PR #31138 by @Sid-Qin. Thanks @Sid-Qin.
 - Infra/fs-safe: sanitize directory-read failures so raw `EISDIR` text never leaks to messaging surfaces, with regression tests for both root-scoped and direct safe reads. Landed from contributor PR #31205 by @polooooo. Thanks @polooooo.
-- Sandbox/mkdirp boundary checks: allow directory-safe boundary validation for existing in-boundary subdirectories, preventing false `cannot create directories` failures in sandbox write mode. (#30610) Thanks @glitch418x.
-- Security/Compaction audit: remove the post-compaction audit injection message. (#28507) Thanks @fuller-stack-dev and @vincentkoc.
-- Web tools/RFC2544 fake-IP compatibility: allow RFC2544 benchmark range (`198.18.0.0/15`) for trusted web-tool fetch endpoints so proxy fake-IP networking modes do not trigger false SSRF blocks. Landed from contributor PR #31176 by @sunkinux. Thanks @sunkinux.
 
 ## Unreleased
 
 ### Changes
 
-- ACP/ACPX streaming: pin ACPX plugin support to `0.1.15`, add configurable ACPX command/version probing, and streamline ACP stream delivery (`final_only` default + reduced tool-event noise) with matching runtime and test updates. (#30036) Thanks @osolmaz.
-- Cron/Heartbeat light bootstrap context: add opt-in lightweight bootstrap mode for automation runs (`--light-context` for cron agent turns and `agents.*.heartbeat.lightContext` for heartbeat), keeping only `HEARTBEAT.md` for heartbeat runs and skipping bootstrap-file injection for cron lightweight runs. (#26064) Thanks @jose-velez.
-- OpenAI/Streaming transport: make `openai` Responses WebSocket-first by default (`transport: "auto"` with SSE fallback), add shared OpenAI WS stream/connection runtime wiring with per-session cleanup, and preserve server-side compaction payload mutation (`store` + `context_management`) on the WS path.
-- OpenAI/WebSocket warm-up: add optional OpenAI Responses WebSocket warm-up (`response.create` with `generate:false`), enable it by default for `openai/*`, and expose `params.openaiWsWarmup` for per-model enable/disable control.
-- Agents/Subagents runtime events: replace ad-hoc subagent completion system-message handoff with typed internal completion events (`task_completion`) that are rendered consistently across direct and queued announce paths, with gateway/CLI plumbing for structured `internalEvents`.
-
-### Breaking
-
-- **BREAKING:** Node exec approval payloads now require `systemRunPlan`. `host=node` approval requests without that plan are rejected.
-- **BREAKING:** Node `system.run` execution now pins path-token commands to the canonical executable path (`realpath`) in both allowlist and approval execution flows. Integrations/tests that asserted token-form argv (for example `tr`) must now accept canonical paths (for example `/usr/bin/tr`).
+- Docs/Contributing: require before/after screenshots for UI or visual PRs in the pre-PR checklist. (#32206) Thanks @hydro13.
 
 ### Fixes
 
+- Logging/Subsystem console timestamps: route subsystem console timestamp rendering through `formatConsoleTimestamp(...)` so `pretty` and timestamp-prefix output use local timezone formatting consistently instead of inline UTC `toISOString()` paths. (#25970) Thanks @openperf.
 - Feishu/Multi-account + reply reliability: add `channels.feishu.defaultAccount` outbound routing support with schema validation, prevent inbound preview text from leaking into prompt system events, keep quoted-message extraction text-first (post/interactive/file placeholders instead of raw JSON), route Feishu video sends as `msg_type: "file"`, and avoid websocket event blocking by using non-blocking event handling in monitor dispatch. Landed from contributor PRs #31209, #29610, #30432, #30331, and #29501. Thanks @stakeswky, @hclsys, @bmendonca3, @patrick-yingxi-pan, and @zwffff.
 - Feishu/Target routing + replies + dedupe: normalize provider-prefixed targets (`feishu:`/`lark:`), prefer configured `channels.feishu.defaultAccount` for tool execution, honor Feishu outbound `renderMode` in adapter text/caption sends, fall back to normal send when reply targets are withdrawn/deleted, and add synchronous in-memory dedupe guard for concurrent duplicate inbound events. Landed from contributor PRs #30428, #30438, #29958, #30444, and #29463. Thanks @bmendonca3 and @Yaxuan42.
 - Channels/Multi-account default routing: add optional `channels.<channel>.defaultAccount` default-selection support across message channels so omitted `accountId` routes to an explicit configured account instead of relying on implicit first-entry ordering (fallback behavior unchanged when unset).
@@ -213,7 +465,7 @@ Docs: https://docs.openclaw.ai
 - Matrix/Directory room IDs: preserve original room-ID casing for direct `!roomId` group lookups (without `:server`) so allowlist checks do not fail on case-sensitive IDs. Landed from contributor PR #31201 by @williamos-dev. Thanks @williamos-dev.
 - Discord/Inbound media fallback: preserve attachment and sticker metadata when Discord CDN fetch/save fails by keeping URL-based media entries in context, with regression coverage for save failures and mixed success/failure ordering. Landed from contributor PR #28906 by @Sid-Qin. Thanks @Sid-Qin.
 - Auto-reply/Block reply timeout path: normalize `onBlockReply(...)` execution through `Promise.resolve(...)` before timeout wrapping so mixed sync/async callbacks keep deterministic timeout behavior across strict TypeScript build paths. (#19779) Thanks @dalefrieswthat and @vincentkoc.
-- Cron/One-shot reschedule re-arm: allow completed `at` jobs to run again when rescheduled to a later time than `lastRunAtMs`, while keeping completed non-rescheduled one-shot jobs inactive. (#28915) Thanks @Glucksberg.
+- Cron/One-shot reschedule re-arm: allow completed `at` jobs to run again when rescheduled to a later time than `lastRunAtMs`, while keeping completed non-rescheduled one-shot jobs inactive. (#28915) Thanks @arosstale.
 - Docs/Docker images: clarify the official GHCR image source and tag guidance (`main`, `latest`, `<version>`), and document that `OPENCLAW_IMAGE` skips local image builds but still uses the repo-local compose/setup flow. (#27214, #31180) Fixes #15655. Thanks @ipl31.
 - Docs/Gateway Docker bind guidance: clarify bridge-network loopback behavior and require bind mode values (`auto`/`loopback`/`lan`/`tailnet`/`custom`) instead of host aliases in `gateway.bind`. (#28001) Thanks @Anandesh-Sharma and @vincentkoc.
 - Docker/Image base annotations: add OCI labels for base image plus source/documentation/license metadata, include revision/version/created labels in Docker release builds, and document annotation keys/release context in install docs. Fixes #27945. Thanks @vincentkoc.
@@ -225,7 +477,7 @@ Docs: https://docs.openclaw.ai
 - Discord/Ack reactions: add Discord-account-level `ackReactionScope` override and support explicit `off`/`none` values in shared config schemas to disable ack reactions per account. Landed from contributor PR #30400 by @BlueBirdBack. Thanks @BlueBirdBack.
 - Discord/Forum thread tags: support `appliedTags` on Discord thread-create actions and map to `applied_tags` for forum/media starter posts, with targeted thread-creation regression coverage. Landed from contributor PR #30358 by @pushkarsingh32. Thanks @pushkarsingh32.
 - Discord/Application ID fallback: parse bot application IDs from token prefixes without numeric precision loss and use token fallback only on transport/timeout failures when probing `/oauth2/applications/@me`. Landed from contributor PR #29695 by @dhananjai1729. Thanks @dhananjai1729.
-- Discord/EventQueue timeout config: expose per-account `channels.discord.accounts.<id>.eventQueue.listenerTimeout` (and related queue options) so long-running handlers can avoid Carbon listener timeout drops. Landed from contributor PR #28945 by @Glucksberg. Thanks @Glucksberg.
+- Discord/EventQueue timeout config: expose per-account `channels.discord.accounts.<id>.eventQueue.listenerTimeout` (and related queue options) so long-running handlers can avoid Carbon listener timeout drops. Landed from contributor PR #24270 by @pdd-cli. Thanks @pdd-cli.
 - CLI/Cron run exit code: return exit code `0` only when `cron run` reports `{ ok: true, ran: true }`, and `1` for non-run/error outcomes so scripting/debugging reflects actual execution status. Landed from contributor PR #31121 by @Sid-Qin. Thanks @Sid-Qin.
 - Cron/Failure delivery routing: add `failureAlert.mode` (`announce|webhook`) and `failureAlert.accountId` support, plus `cron.failureDestination` and per-job `delivery.failureDestination` routing with duplicate-target suppression, best-effort skip behavior, and global+job merge semantics. Landed from contributor PR #31059 by @kesor. Thanks @kesor.
 - CLI/JSON preflight output: keep `--json` command stdout machine-readable by suppressing doctor preflight note output while still running legacy migration/config doctor flow. (#24368) Thanks @altaywtf.
@@ -307,7 +559,7 @@ Docs: https://docs.openclaw.ai
 - Gateway/Control UI API routing: when `gateway.controlUi.basePath` is unset (default), stop serving Control UI SPA HTML for `/api` and `/api/*` so API paths fall through to normal gateway handlers/404 responses instead of `index.html`. (#30333) Fixes #30295. thanks @Sid-Qin.
 - Cron/One-shot reliability: retry transient one-shot failures with bounded backoff and configurable retry policy before disabling. (#24435) Thanks @hugenshen.
 - Gateway/Cron auditability: add gateway info logs for successful cron create, update, and remove operations. (#25090) Thanks @MoerAI.
-- Gateway/Tailscale onboarding origin allowlist: auto-add the detected Tailnet HTTPS origin during interactive configure/onboarding flows (including IPv6-safe origin formatting and binary-path reuse), so Tailscale serve/funnel Control UI access works without manual `allowedOrigins` edits. Landed from contributor PR #28960 by @Glucksberg. Thanks @Glucksberg.
+- Gateway/Tailscale onboarding origin allowlist: auto-add the detected Tailnet HTTPS origin during interactive configure/onboarding flows (including IPv6-safe origin formatting and binary-path reuse), so Tailscale serve/funnel Control UI access works without manual `allowedOrigins` edits. Landed from contributor PR #26157 by @stakeswky. Thanks @stakeswky.
 - Gateway/Upgrade migration for Control UI origins: seed `gateway.controlUi.allowedOrigins` on startup for legacy non-loopback configs (`lan`/`tailnet`/`custom`) when origins are missing or blank, preventing post-upgrade crash loops while preserving explicit existing policy. Landed from contributor PR #29394 by @synchronic1. Thanks @synchronic1.
 - Gateway/Plugin HTTP auth hardening: require gateway auth for protected plugin paths and explicit `registerHttpRoute` paths (while preserving wildcard-handler behavior for signature-auth webhooks), and run plugin handlers after built-in handlers for deterministic route precedence. Landed from contributor PR #29198 by @Mariana-Codebase. Thanks @Mariana-Codebase.
 - Gateway/Config patch guard: reject `config.patch` updates that set non-loopback `gateway.bind` while `gateway.tailscale.mode` is `serve`/`funnel`, preventing restart crash loops from invalid bind/tailscale combinations. Landed from contributor PR #30910 by @liuxiaopai-ai. Thanks @liuxiaopai-ai.
@@ -318,10 +570,11 @@ Docs: https://docs.openclaw.ai
 - Slack/Transient request errors: classify Slack request-error messages like `Client network socket disconnected before secure TLS connection was established` as transient in unhandled-rejection fatal detection, preventing temporary network drops from crash-looping the gateway. (#23169) Thanks @graysurf.
 - Slack/Usage footer formatting: wrap session keys in inline code in full response-usage footers so Slack does not parse colon-delimited session segments as emoji shortcodes. (#30258) Thanks @pushkarsingh32.
 - Slack/Thread session isolation: route channel/group top-level messages into thread-scoped sessions (`:thread:<ts>`) and read inbound `previousTimestamp` from the resolved thread session key, preventing cross-thread context bleed and stale timestamp lookups. (#10686) Thanks @pablohrcarvalho.
-- Slack/Socket Mode slash startup: treat `app.options()` registration as best-effort and fall back to static arg menus when listener registration fails, preventing Slack monitor startup crash loops on receiver init edge cases. (#21715) Thanks @Glucksberg.
+- Slack/Socket Mode slash startup: treat `app.options()` registration as best-effort and fall back to static arg menus when listener registration fails, preventing Slack monitor startup crash loops on receiver init edge cases. (#21715) Thanks @AIflow-Labs.
 - Slack/Legacy streaming config: map boolean `channels.slack.streaming=false` to unified streaming mode `off` (with `nativeStreaming=false`) so legacy configs correctly disable draft preview/native streaming instead of defaulting to `partial`. (#25990) Thanks @chilu18.
 - Slack/Socket reconnect reliability: reconnect Socket Mode after disconnect/start failures using bounded exponential backoff with abort-aware waits, while preserving clean shutdown behavior and adding disconnect/error helper tests. (#27232) Thanks @pandego.
-- Memory/QMD update+embed output cap: discard captured stdout for `qmd update` and `qmd embed` runs (while keeping stderr diagnostics) so large index progress output no longer fails sync with `produced too much output` during boot/refresh. (#28900) Thanks @Glucksberg.
+- Memory/QMD update+embed output cap: discard captured stdout for `qmd update` and `qmd embed` runs (while keeping stderr diagnostics) so large index progress output no longer fails sync with `produced too much output` during boot/refresh. (#28900; landed from contributor PR #23311 by @haitao-sjsu) Thanks @haitao-sjsu.
+- Feishu/Onboarding SecretRef guards: avoid direct `.trim()` calls on object-form `appId`/`appSecret` in onboarding credential checks, keep status semantics strict when an account explicitly sets empty `appId` (no fallback to top-level `appId`), recognize env SecretRef `appId`/`appSecret` as configured so readiness is accurate, and preserve unresolved SecretRef errors in default account resolution for actionable diagnostics. (#30903) Thanks @LiaoyuanNing.
 - Onboarding/Custom providers: raise default custom-provider model context window to the runtime hard minimum (16k) and auto-heal existing custom model entries below that threshold during reconfiguration, preventing immediate `Model context window too small (4096 tokens)` failures. (#21653) Thanks @r4jiv007.
 - Web UI/Assistant text: strip internal `<relevant-memories>...</relevant-memories>` scaffolding from rendered assistant messages (while preserving code-fence literals), preventing memory-context leakage in chat output for models that echo internal blocks. (#29851) Thanks @Valkster70.
 - Dashboard/Sessions: allow authenticated Control UI clients to delete and patch sessions while still blocking regular webchat clients from session mutation RPCs, fixing Dashboard session delete failures. (#21264) Thanks @jskoiz.
@@ -563,7 +816,7 @@ Docs: https://docs.openclaw.ai
 - WhatsApp/Web reconnect: treat close status `440` as non-retryable (including string-form status values), stop reconnect loops immediately, and emit operator guidance to relink after resolving session conflicts. (#25858) Thanks @markmusson.
 - WhatsApp/Reasoning safety: suppress outbound payloads marked as reasoning and hard-drop text payloads that begin with `Reasoning:` before WhatsApp delivery, preventing hidden thinking blocks from leaking to end users through final-message paths. (#25804, #25214, #24328)
 - Matrix/Read receipts: send read receipts as soon as Matrix messages arrive (before handler pipeline work), so clients no longer show long-lived unread/sent states while replies are processing. (#25841, #25840) Thanks @joshjhall.
-- Telegram/Replies: when markdown formatting renders to empty HTML (for example syntax-only chunks in threaded replies), retry delivery with plain text, and fail loud when both formatted and plain payloads are empty to avoid false delivered states. (#25096, #25091) Thanks @Glucksberg.
+- Telegram/Replies: when markdown formatting renders to empty HTML (for example syntax-only chunks in threaded replies), retry delivery with plain text, and fail loud when both formatted and plain payloads are empty to avoid false delivered states. (#25096, #25091) Thanks @ArsalanShakil.
 - Telegram/Media fetch: prioritize IPv4 before IPv6 in SSRF pinned DNS address ordering so media downloads still work on hosts with broken IPv6 routing. (#24295, #23975) Thanks @Glucksberg.
 - Telegram/Outbound API: replace Node 22's global undici dispatcher when applying Telegram `autoSelectFamily` decisions so outbound `fetch` calls inherit IPv4 fallback instead of staying pinned to stale dispatcher settings. (#25682, #25676) Thanks @lairtonlelis.
 - Onboarding/Telegram: keep core-channel onboarding available when plugin registry population is missing by falling back to built-in adapters and continuing wizard setup with actionable recovery guidance. (#25803) Thanks @Suko.
@@ -618,28 +871,8 @@ Docs: https://docs.openclaw.ai
 - Security/Exec companion host: forward canonical `system.run` display text (not payload-only shell snippets) to the macOS exec host, and enforce rawCommand/argv consistency there for shell-wrapper positional-argv carriers and env-modifier preludes, preventing companion-side approval/display drift. Thanks @tdjackey for reporting.
 - Security/Exec approvals: fail closed when transparent dispatch-wrapper unwrapping exceeds the depth cap, so nested `/usr/bin/env` chains cannot bypass shell-wrapper approval gating in `allowlist` + `ask=on-miss` mode. Thanks @tdjackey for reporting.
 - Security/Exec: limit default safe-bin trusted directories to immutable system paths (`/bin`, `/usr/bin`) and require explicit opt-in (`tools.exec.safeBinTrustedDirs`) for package-manager/user bin paths (for example Homebrew), add security-audit findings for risky trusted-dir choices, warn at runtime when explicitly trusted dirs are group/world writable, and add doctor hints when configured `safeBins` resolve outside trusted dirs. Thanks @tdjackey for reporting.
-- Telegram/Media fetch: prioritize IPv4 before IPv6 in SSRF pinned DNS address ordering so media downloads still work on hosts with broken IPv6 routing. (#24295, #23975) Thanks @Glucksberg.
-- Telegram/Outbound API: replace Node 22's global undici dispatcher when applying Telegram `autoSelectFamily` decisions so outbound `fetch` calls inherit IPv4 fallback instead of staying pinned to stale dispatcher settings. (#25682, #25676) Thanks @lairtonlelis.
-- Agents/Billing classification: prevent long assistant/user-facing text from being rewritten as billing failures while preserving explicit `status/code/http 402` detection for oversized structured error payloads. (#25680, #25661) Thanks @lairtonlelis.
-- Telegram/Replies: when markdown formatting renders to empty HTML (for example syntax-only chunks in threaded replies), retry delivery with plain text, and fail loud when both formatted and plain payloads are empty to avoid false delivered states. (#25096, #25091) Thanks @Glucksberg.
-- Sessions/Tool-result guard: avoid generating synthetic `toolResult` entries for assistant turns that ended with `stopReason: "aborted"` or `"error"`, preventing orphaned tool-use IDs from triggering downstream API validation errors. (#25429) Thanks @mikaeldiakhate-cell.
 - Gateway/Sessions: preserve `modelProvider` on `sessions.reset` and avoid incorrect provider prefixes for legacy session models. (#25874) Thanks @lbo728.
-- Usage accounting: parse Moonshot/Kimi `cached_tokens` fields (including `prompt_tokens_details.cached_tokens`) into normalized cache-read usage metrics. (#25436) Thanks @Elarwei001.
-- Doctor/Sandbox: when sandbox mode is enabled but Docker is unavailable, surface a clear actionable warning (including failure impact and remediation) instead of a mild “skip checks” note. (#25438) Thanks @mcaxtr.
-- Config/Meta: accept numeric `meta.lastTouchedAt` timestamps and coerce them to ISO strings, preserving compatibility with agent edits that write `Date.now()` values. (#25491) Thanks @mcaxtr.
-- Auto-reply/Reset hooks: guarantee native `/new` and `/reset` flows emit command/reset hooks even on early-return command paths, with dedupe protection to avoid double hook emission. (#25459) Thanks @chilu18.
-- Hooks/Slug generator: resolve session slug model from the agent’s effective model (including defaults/fallback resolution) instead of raw agent-primary config only. (#25485) Thanks @SudeepMalipeddi.
-- Slack/DM routing: treat `D*` channel IDs as direct messages even when Slack sends an incorrect `channel_type`, preventing DM traffic from being misclassified as channel/group chats. (#25479) Thanks @mcaxtr.
-- Models/Providers: preserve explicit user `reasoning` overrides when merging provider model config with built-in catalog metadata, so `reasoning: false` is no longer overwritten by catalog defaults. (#25314) Thanks @lbo728.
-- Exec approvals: treat bare allowlist `*` as a true wildcard for parsed executables, including unresolved PATH lookups, so global opt-in allowlists work as configured. (#25250) Thanks @widingmarcus-cyber.
-- Gateway/Auth: allow trusted-proxy authenticated Control UI websocket sessions to skip device pairing when device identity is absent, preventing false `pairing required` failures behind trusted reverse proxies. (#25428) Thanks @SidQin-cyber.
-- Agents/Tool dispatch: await block-reply flush before tool execution starts so buffered block replies preserve message ordering around tool calls. (#25427) Thanks @SidQin-cyber.
 - Agents/Compaction: harden summarization prompts to preserve opaque identifiers verbatim (UUIDs, IDs, tokens, host/IP/port, URLs), reducing post-compaction identifier drift and hallucinated identifier reconstruction.
-- iOS/Signing: improve `scripts/ios-team-id.sh` for Xcode 16+ by falling back to Xcode-managed provisioning profiles, add actionable guidance when an Apple account exists but no Team ID can be resolved, and ignore Xcode `xcodebuild` output directories (`apps/ios/build`, `apps/shared/OpenClawKit/build`, `Swabble/build`). (#22773) Thanks @brianleach.
-- macOS/Menu bar: stop reusing the injector delegate for the "Usage cost (30 days)" submenu to prevent recursive submenu injection loops when opening cost history. (#25341) Thanks @yingchunbai.
-- Control UI/Chat images: route image-click opens through a shared safe-open helper (allowing only safe URL schemes) and open new tabs with opener isolation to block tabnabbing. (#18685, #25444, #25847) Thanks @Mariana-Codebase and @shakkernerd.
-- CLI/Doctor: correct stale recovery hints to use valid commands (`openclaw gateway status --deep` and `openclaw configure --section model`). (#24485) Thanks @chilu18.
-- CLI/Memory search: accept `--query <text>` for `openclaw memory search` (while keeping positional query support), and emit a clear error when neither form is provided. (#25904, #25857) Thanks @niceysam and @stakeswky.
 - Security/Sandbox: canonicalize bind-mount source paths via existing-ancestor realpath so symlink-parent + non-existent-leaf paths cannot bypass allowed-source-roots or blocked-path checks. Thanks @tdjackey.
 
 ## 2026.2.23
@@ -674,11 +907,11 @@ Docs: https://docs.openclaw.ai
 - Agents/Reasoning: when model-default thinking is active (for example `thinking=low`), keep auto-reasoning disabled unless explicitly enabled, preventing `Reasoning:` thinking-block leakage in channel replies. (#24335, #24290) thanks @Kay-051.
 - Agents/Reasoning: avoid classifying provider reasoning-required errors as context overflows so these failures no longer trigger compaction-style overflow recovery. (#24593) Thanks @vincentkoc.
 - Agents/Models: codify `agents.defaults.model` / `agents.defaults.imageModel` config-boundary input as `string | {primary,fallbacks}`, split explicit vs effective model resolution, and fix `models status --agent` source attribution so defaults-inherited agents are labeled as `defaults` while runtime selection still honors defaults fallback. (#24210) thanks @bianbiandashen.
-- Agents/Compaction: pass `agentDir` into manual `/compact` command runs so compaction auth/profile resolution stays scoped to the active agent. (#24133) thanks @Glucksberg.
+- Agents/Compaction: pass `agentDir` into manual `/compact` command runs so compaction auth/profile resolution stays scoped to the active agent. (#24133) thanks @miloudbelarebia.
 - Agents/Compaction: pass model metadata through the embedded runtime so safeguard summarization can run when `ctx.model` is unavailable, avoiding repeated `"Summary unavailable due to context limits"` fallback summaries. (#3479) Thanks @battman21, @hanxiao and @vincentkoc.
 - Agents/Compaction: cancel safeguard compaction when summary generation cannot run (missing model/API key or summarization failure), preserving history instead of truncating to fallback `"Summary unavailable"` text. (#10711) Thanks @DukeDeSouth and @vincentkoc.
 - Agents/Tools: make `session_status` read transcript-derived usage mid-turn and tail-read session logs for cache-aware context reporting without full-log scans. (#22387) Thanks @1ucian.
-- Agents/Overflow: detect additional provider context-overflow error shapes (including `input length` + `max_tokens` exceed-context variants) so failures route through compaction/recovery paths instead of leaking raw provider errors to users. (#9951) Thanks @echoVic and @Glucksberg.
+- Agents/Overflow: detect additional provider context-overflow error shapes (including `input length` + `max_tokens` exceed-context variants) so failures route through compaction/recovery paths instead of leaking raw provider errors to users. (#9951) Thanks @echoVic.
 - Agents/Overflow: add Chinese context-overflow pattern detection in `isContextOverflowError` so localized provider errors route through overflow recovery paths. (#22855) Thanks @Clawborn.
 - Agents/Failover: treat HTTP 502/503/504 errors as failover-eligible transient timeouts so fallback chains can switch providers/models during upstream outages instead of retrying the same failing target. (#20999) Thanks @taw0002 and @vincentkoc.
 - Auto-reply/Inbound metadata: hide direct-chat `message_id`/`message_id_full` and sender metadata only from normalized chat type (not sender-id sentinels), preserving group metadata visibility and preventing sender-id spoofed direct-mode classification. (#24373) thanks @jd316.
@@ -693,7 +926,6 @@ Docs: https://docs.openclaw.ai
 - Plugins/Install: when npm install returns 404 for bundled channel npm specs, fallback to bundled channel sources and complete install/enable persistence instead of failing plugin install. (#12849) Thanks @vincentkoc.
 - Gemini OAuth/Auth: resolve npm global shim install layouts while discovering Gemini CLI credentials, preventing false "Gemini CLI not found" onboarding/auth failures when shim paths are on `PATH`. (#27585) Thanks @ehgamemo and @vincentkoc.
 - Providers/Groq: avoid classifying Groq TPM limit errors as context overflow so throttling paths no longer trigger overflow recovery logic. (#16176) Thanks @dddabtc.
-- Gateway/WS: close repeated post-handshake `unauthorized role:*` request floods per connection and sample duplicate rejection logs, preventing a single misbehaving client from degrading gateway responsiveness. (#20168) Thanks @acy103, @vibecodooor, and @vincentkoc.
 - Gateway/Restart: treat child listener PIDs as owned by the service runtime PID during restart health checks to avoid false stale-process kills and restart timeouts on launchd/systemd. (#24696) Thanks @gumadeiras.
 - Config/Write: apply `unsetPaths` with immutable path-copy updates so config writes never mutate caller-provided objects, and harden `openclaw config get/set/unset` path traversal by rejecting prototype-key segments and inherited-property traversal. (#24134) thanks @frankekn.
 - Channels/WhatsApp: accept `channels.whatsapp.enabled` in config validation to match built-in channel auto-enable behavior, preventing `Unrecognized key: "enabled"` failures during channel setup. (#24263) Thanks @steipete.
@@ -748,7 +980,7 @@ Docs: https://docs.openclaw.ai
 - Agents/Kimi: classify Moonshot `Your request exceeded model token limit` failures as context overflows so auto-compaction and user-facing overflow recovery trigger correctly instead of surfacing raw invalid-request errors. (#9562) Thanks @danilofalcao.
 - Providers/Moonshot: mark Kimi K2.5 as image-capable in implicit + onboarding model definitions, and refresh stale explicit provider capability fields (`input`/`reasoning`/context limits) from implicit catalogs so existing configs pick up Moonshot vision support without manual model rewrites. (#13135, #4459) Thanks @manikv12.
 - Agents/Transcript: enable consecutive-user turn merging for strict non-OpenAI `openai-completions` providers (for example Moonshot/Kimi), reducing `roles must alternate` ordering failures on OpenAI-compatible endpoints while preserving current OpenRouter/Opencode behavior. (#7693) Thanks @steipete.
-- Install/Discord Voice: make `@discordjs/opus` an optional dependency so `openclaw` install/update no longer hard-fails when native Opus builds fail, while keeping `opusscript` as the runtime fallback decoder for Discord voice flows. (#23737, #23733, #23703) Thanks @jeadland, @Sheetaa, and @Breakyman.
+- Install/Discord Voice: make the native Opus decoder optional so `openclaw` install/update no longer hard-fails when native builds fail, while keeping `opusscript` as the runtime fallback decoder for Discord voice flows. (#23737, #23733, #23703) Thanks @jeadland, @Sheetaa, and @Breakyman.
 - Docker/Setup: precreate `$OPENCLAW_CONFIG_DIR/identity` during `docker-setup.sh` so CLI commands that need device identity (for example `devices list`) avoid `EACCES ... /home/node/.openclaw/identity` failures on restrictive bind mounts. (#23948) Thanks @ackson-beep.
 - Exec/Background: stop applying the default exec timeout to background sessions (`background: true` or explicit `yieldMs`) when no explicit timeout is set, so long-running background jobs are no longer terminated at the default timeout boundary. (#23303) Thanks @steipete.
 - Slack/Threading: sessions: keep parent-session forking and thread-history context active beyond first turn by removing first-turn-only gates in session init, thread-history fetch, and reply prompt context injection. (#23843, #23090) Thanks @vincentkoc and @Taskle.
@@ -825,7 +1057,7 @@ Docs: https://docs.openclaw.ai
 - Config/Memory: allow `"mistral"` in `agents.defaults.memorySearch.provider` and `agents.defaults.memorySearch.fallback` schema validation. (#14934) Thanks @ThomsenDrake.
 - Feishu/Commands: in group chats, command authorization now falls back to top-level `channels.feishu.allowFrom` when per-group `allowFrom` is not set, so `/command` no longer gets blocked by an unintended empty allowlist. (#23756) Thanks @steipete.
 - Dev tooling: prevent `CLAUDE.md` symlink target regressions by excluding CLAUDE symlink sentinels from `oxfmt` and marking them `-text` in `.gitattributes`, so formatter/EOL normalization cannot reintroduce trailing-newline targets. Thanks @vincentkoc.
-- Agents/Compaction: restore embedded compaction safeguard/context-pruning extension loading in production by wiring bundled extension factories into the resource loader instead of runtime file-path resolution. (#22349) Thanks @Glucksberg.
+- Agents/Compaction: restore embedded compaction safeguard/context-pruning extension loading in production by wiring bundled extension factories into the resource loader instead of runtime file-path resolution. (#22349; landed from contributor PR #5005 by @Diaspar4u) Thanks @Diaspar4u.
 - Feishu/Media: for inbound video messages that include both `file_key` (video) and `image_key` (thumbnail), prefer `file_key` when downloading media so video attachments are saved instead of silently failing on thumbnail keys. (#23633) Thanks @steipete.
 - Hooks/Loader: avoid redundant hook-module recompilation on gateway restart by skipping cache-busting for bundled hooks and using stable file metadata keys (`mtime+size`) for mutable workspace/managed/plugin hook imports. (#16953) Thanks @mudrii.
 - Hooks/Cron: suppress duplicate main-session events for delivered hook turns and mark `SILENT_REPLY_TOKEN` (`NO_REPLY`) early exits as delivered to prevent hook context pollution. (#20678) Thanks @JonathanWorks.
@@ -950,6 +1182,8 @@ Docs: https://docs.openclaw.ai
 - Security/Control UI avatars: harden `/avatar/:agentId` local avatar serving by rejecting symlink paths and requiring fd-level file identity + size checks before reads. Thanks @tdjackey for reporting.
 - Security/MSTeams media: enforce allowlist checks for SharePoint reference attachment URLs and redirect targets during Graph-backed media fetches so redirect chains cannot escape configured media host boundaries. Thanks @tdjackey for reporting.
 - Security/MSTeams media: route attachment auth-retry and Graph SharePoint download redirects through shared `safeFetch` so each hop is validated with allowlist + DNS/IP checks across the full redirect chain. (#23598) Thanks @Asm3r96 and @lewiswigmore.
+- Security/MSTeams auth redirect scoping: strip bearer auth on redirect hops outside `authAllowHosts` and gate SharePoint Graph auth-header injection by auth allowlist to prevent token bleed across redirect targets. (#25045) Thanks @bmendonca3.
+- MSTeams/reply reliability: when Bot Framework revokes thread turn-context proxies (for example debounced flush paths), fall back to proactive messaging/typing and continue pending sends without duplicating already delivered messages. (#27224) Thanks @openperf.
 - Security/macOS discovery: fail closed for unresolved discovery endpoints by clearing stale remote selection values, use resolved service host only for SSH target derivation, and keep remote URL config aligned with resolved endpoint availability. (#21618) Thanks @bmendonca3.
 - Chat/Usage/TUI: strip synthetic inbound metadata blocks (including `Conversation info` and trailing `Untrusted context` channel metadata wrappers) from displayed conversation history so internal prompt context no longer leaks into user-visible logs.
 - CI/Tests: fix TypeScript case-table typing and lint assertion regressions so `pnpm check` passes again after Synology Chat landing. (#23012) Thanks @druide67.
@@ -1055,8 +1289,6 @@ Docs: https://docs.openclaw.ai
 - Gateway/Config: allow `gateway.customBindHost` in strict config validation when `gateway.bind="custom"` so valid custom bind-host configurations no longer fail startup. (#20318, fixes #20289) Thanks @MisterGuy420.
 - Gateway/Pairing: tolerate legacy paired devices missing `roles`/`scopes` metadata in websocket upgrade checks and backfill metadata on reconnect. (#21447, fixes #21236) Thanks @joshavant.
 - Gateway/Pairing/CLI: align read-scope compatibility in pairing/device-token checks and add local `openclaw devices` fallback recovery for loopback `pairing required` deadlocks, with explicit fallback notice to unblock approval bootstrap flows. (#21616) Thanks @shakkernerd.
-- Cron: honor `cron.maxConcurrentRuns` in the timer loop so due jobs can execute up to the configured parallelism instead of always running serially. (#11595) Thanks @Takhoffman.
-- Agents/Compaction: restore embedded compaction safeguard/context-pruning extension loading in production by wiring bundled extension factories into the resource loader instead of runtime file-path resolution. (#22349) Thanks @Glucksberg.
 - Agents/Subagents: restore announce-chain delivery to agent injection, defer nested announce output until descendant follow-up content is ready, and prevent descendant deferrals from consuming announce retry budget so deep chains do not drop final completions. (#22223) Thanks @tyler6204.
 - Agents/System Prompt: label allowlisted senders as authorized senders to avoid implying ownership. Thanks @thewilloftheshadow.
 - Agents/Tool display: fix exec cwd suffix inference so `pushd ... && popd ... && <command>` does not keep stale `(in <dir>)` context in summaries. (#21925) Thanks @Lukavyi.
@@ -1116,6 +1348,8 @@ Docs: https://docs.openclaw.ai
 - iOS/Watch: add an Apple Watch companion MVP with watch inbox UI, watch notification relay handling, and gateway command surfaces for watch status/send flows. (#20054) Thanks @mbelinky.
 - iOS/Gateway: wake disconnected iOS nodes via APNs before `nodes.invoke` and auto-reconnect gateway sessions on silent push wake to reduce invoke failures while the app is backgrounded. (#20332) Thanks @mbelinky.
 - Gateway/CLI: add paired-device hygiene flows with `device.pair.remove`, plus `openclaw devices remove` and guarded `openclaw devices clear --yes [--pending]` commands for removing paired entries and optionally rejecting pending requests. (#20057) Thanks @mbelinky.
+- Mattermost: add opt-in native slash command support with registration lifecycle, callback route/token validation, multi-account token routing, and callback URL/path configuration (`channels.mattermost.commands.*`). (#16515) Thanks @echo931.
+- Mattermost: harden native slash callback auth-bypass behavior for configurable callback paths, add callback validation coverage, and clarify callback reachability/allowlist docs. (#32467) Thanks @mukhtharcm and @echo931.
 - iOS/APNs: add push registration and notification-signing configuration for node delivery. (#20308) Thanks @mbelinky.
 - Gateway/APNs: add a push-test pipeline for APNs delivery validation in gateway flows. (#20307) Thanks @mbelinky.
 - Security/Audit: add `gateway.http.no_auth` findings when `gateway.auth.mode="none"` leaves Gateway HTTP APIs reachable, with loopback warning and remote-exposure critical severity, plus regression coverage and docs updates.
@@ -1429,7 +1663,6 @@ Docs: https://docs.openclaw.ai
 - Browser/Agents: when browser control service is unavailable, return explicit non-retry guidance (instead of "try again") so models do not loop on repeated browser tool calls until timeout. (#17673) Thanks @austenstone.
 - Subagents: use child-run-based deterministic announce idempotency keys across direct and queued delivery paths (with legacy queued-item fallback) to prevent duplicate announce retries without collapsing distinct same-millisecond announces. (#17150) Thanks @widingmarcus-cyber.
 - Subagents/Models: preserve `agents.defaults.model.fallbacks` when subagent sessions carry a model override, so subagent runs fail over to configured fallback models instead of retrying only the overridden primary model.
-- Agents/Tools: scope the `message` tool schema to the active channel so Telegram uses `buttons` and Discord uses `components`. (#18215) Thanks @obviyus.
 - Telegram: omit `message_thread_id` for DM sends/draft previews and keep forum-topic handling (`id=1` general omitted, non-general kept), preventing DM failures with `400 Bad Request: message thread not found`. (#10942) Thanks @garnetlyx.
 - Telegram: replace inbound `<media:audio>` placeholder with successful preflight voice transcript in message body context, preventing placeholder-only prompt bodies for mention-gated voice messages. (#16789) Thanks @Limitless2023.
 - Telegram: retry inbound media `getFile` calls (3 attempts with backoff) and gracefully fall back to placeholder-only processing when retries fail, preventing dropped voice/media messages on transient Telegram network errors. (#16154) Thanks @yinghaosang.
@@ -1439,7 +1672,6 @@ Docs: https://docs.openclaw.ai
 - Discord: ensure role allowlist matching uses raw role IDs for message routing authorization. Thanks @xinhuagu.
 - Discord: skip text-based exec approval forwarding in favor of Discord's component-based approval UI. Thanks @thewilloftheshadow.
 - Web UI/Agents: hide `BOOTSTRAP.md` in the Agents Files list after onboarding is completed, avoiding confusing missing-file warnings for completed workspaces. (#17491) Thanks @gumadeiras.
-- Memory/QMD: scope managed collection names per agent and precreate glob-backed collection directories before registration, preventing cross-agent collection clobbering and startup ENOENT failures in fresh workspaces. (#17194) Thanks @jonathanadams96.
 - Gateway/Memory: initialize QMD startup sync for every configured agent (not just the default agent), so `memory.qmd.update.onBoot` is effective across multi-agent setups. (#17663) Thanks @HenryLoenwind.
 - Auto-reply/WhatsApp/TUI/Web: when a final assistant message is `NO_REPLY` and a messaging tool send succeeded, mirror the delivered messaging-tool text into session-visible assistant output so TUI/Web no longer show `NO_REPLY` placeholders. (#7010) Thanks @Morrowind-Xie.
 - Cron: infer `payload.kind="agentTurn"` for model-only `cron.update` payload patches, so partial agent-turn updates do not fail validation when `kind` is omitted. (#15664) Thanks @rodrigouroz.
@@ -1517,7 +1749,7 @@ Docs: https://docs.openclaw.ai
 - Agents: treat `read` tool `file_path` arguments as valid in tool-start diagnostics to avoid false “read tool called without path” warnings when alias parameters are used. (#16717) Thanks @Stache73.
 - Agents/Transcript: drop malformed tool-call blocks with blank required fields (`id`/`name` or missing `input`/`arguments`) during session transcript repair to prevent persistent tool-call corruption on future turns. (#15485) Thanks @mike-zachariades.
 - Tools/Write/Edit: normalize structured text-block arguments for `content`/`oldText`/`newText` before filesystem edits, preventing JSON-like file corruption and false “exact text not found” misses from block-form params. (#16778) Thanks @danielpipernz.
-- Ollama/Agents: avoid forcing `<final>` tag enforcement for Ollama models, which could suppress all output as `(no output)`. (#16191) Thanks @Glucksberg.
+- Ollama/Agents: avoid forcing `<final>` tag enforcement for Ollama models, which could suppress all output as `(no output)`. (#16191) Thanks @briancolinger.
 - Plugins: suppress false duplicate plugin id warnings when the same extension is discovered via multiple paths (config/workspace/global vs bundled), while still warning on genuine duplicates. (#16222) Thanks @shadril238.
 - Agents/Process: supervise PTY/child process lifecycles with explicit ownership, cancellation, timeouts, and deterministic cleanup, preventing Codex/Pi PTY sessions from dying or stalling on resume. (#14257) Thanks @onutc.
 - Skills: watch `SKILL.md` only when refreshing skills snapshot to avoid file-descriptor exhaustion in large data trees. (#11325) Thanks @household-bard.
@@ -1840,7 +2072,7 @@ Docs: https://docs.openclaw.ai
 
 - Cron: prevent one-shot `at` jobs from re-firing on gateway restart when previously skipped or errored. (#13845)
 - Discord: add exec approval cleanup option to delete DMs after approval/denial/timeout. (#13205) Thanks @thewilloftheshadow.
-- Sessions: prune stale entries, cap session store size, rotate large stores, accept duration/size thresholds, default to warn-only maintenance, and prune cron run sessions after retention windows. (#13083) Thanks @skyfallsin, @Glucksberg, @gumadeiras.
+- Sessions: prune stale entries, cap session store size, rotate large stores, accept duration/size thresholds, default to warn-only maintenance, and prune cron run sessions after retention windows. (#13083) Thanks @skyfallsin, @gumadeiras.
 - CI: Implement pipeline and workflow order. Thanks @quotentiroler.
 - WhatsApp: preserve original filenames for inbound documents. (#12691) Thanks @akramcodez.
 - Telegram: harden quote parsing; preserve quote context; avoid QUOTE_TEXT_INVALID; avoid nested reply quote misclassification. (#12156) Thanks @rybnikov.
@@ -1930,9 +2162,6 @@ Docs: https://docs.openclaw.ai
 - TTS: add missing OpenAI voices (ballad, cedar, juniper, marin, verse) to the allowlist so they are recognized instead of silently falling back to Edge TTS. (#2393)
 - Cron: scheduler reliability (timer drift, restart catch-up, lock contention, stale running markers). (#10776) Thanks @tyler6204.
 - Cron: store migration hardening (legacy field migration, parse error handling, explicit delivery mode persistence). (#10776) Thanks @tyler6204.
-- Memory: set Voyage embeddings `input_type` for improved retrieval. (#10818) Thanks @mcinteerj.
-- Memory/QMD: run boot refresh in background by default, add configurable QMD maintenance timeouts, retry QMD after fallback failures, and scope QMD queries to OpenClaw-managed collections. (#9690, #9705, #10042) Thanks @vignesh07.
-- Media understanding: recognize `.caf` audio attachments for transcription. (#10982) Thanks @succ985.
 - Telegram: auto-inject DM topic threadId in message tool + subagent announce. (#7235) Thanks @Lukavyi.
 - Security: require auth for Gateway canvas host and A2UI assets. (#9518) Thanks @coygeek.
 - Cron: fix scheduling and reminder delivery regressions; harden next-run recompute + timer re-arming + legacy schedule fields. (#9733, #9823, #9948, #9932) Thanks @tyler6204, @pycckuu, @j2h4u, @fujiwara-tofu-shop.
@@ -1993,7 +2222,7 @@ Docs: https://docs.openclaw.ai
 - Cron: accept epoch timestamps and 0ms durations in CLI `--at` parsing.
 - Cron: reload store data when the store file is recreated or mtime changes.
 - Cron: deliver announce runs directly, honor delivery mode, and respect wakeMode for summaries. (#8540) Thanks @tyler6204.
-- Telegram: include forward_from_chat metadata in forwarded messages and harden cron delivery target checks. (#8392) Thanks @Glucksberg.
+- Telegram: include forward_from_chat metadata in forwarded messages and harden cron delivery target checks. (#8392) Thanks @sleontenko.
 - macOS: fix cron payload summary rendering and ISO 8601 formatter concurrency safety.
 - Discord: enforce DM allowlists for agent components (buttons/select menus), honoring pairing store approvals and tag matches. (#11254) Thanks @thedudeabidesai.
 
@@ -2050,7 +2279,6 @@ Docs: https://docs.openclaw.ai
 - Security: guard skill installer downloads with SSRF checks (block private/localhost URLs).
 - Security/Gateway: require `operator.approvals` for in-chat `/approve` when invoked from gateway clients. Thanks @yueyueL.
 - Security: harden Windows exec allowlist; block cmd.exe bypass via single &. Thanks @simecek.
-- Discord: route autoThread replies to existing threads instead of the root channel. (#8302) Thanks @gavinbmoore, @thewilloftheshadow.
 - Media understanding: apply SSRF guardrails to provider fetches; allow private baseUrl overrides explicitly.
 - fix(voice-call): harden inbound allowlist; reject anonymous callers; require Telnyx publicKey for allowlist; token-gate Twilio media streams; cap webhook body size (thanks @simecek)
 - Onboarding: keep TUI flow exclusive (skip completion prompt + background Web UI seed); completion prompt now handled by install/update.
@@ -2120,62 +2348,10 @@ Docs: https://docs.openclaw.ai
 
 ## 2026.1.31
 
-### Changes
-
-- Docs: onboarding/install/i18n/exec-approvals/Control UI/exe.dev/cacheRetention updates + misc nav/typos. (#3050, #3461, #4064, #4675, #4729, #4763, #5003, #5402, #5446, #5474, #5663, #5689, #5694, #5967, #6270, #6300, #6311, #6416, #6487, #6550, #6789)
-- Telegram: use shared pairing store. (#6127) Thanks @obviyus.
-- Agents: add OpenRouter app attribution headers. Thanks @alexanderatallah.
-- Agents: add system prompt safety guardrails. (#5445) Thanks @joshp123.
-- Agents: update pi-ai to 0.50.9 and rename cacheControlTtl -> cacheRetention (with back-compat mapping).
-- Agents: extend CreateAgentSessionOptions with systemPrompt/skills/contextFiles.
-- Agents: add tool policy conformance snapshot (no runtime behavior change). (#6011)
-- Auth: update MiniMax OAuth hint + portal auth note copy.
-- Discord: inherit thread parent bindings for routing. (#3892) Thanks @aerolalit.
-- Gateway: inject timestamps into agent and chat.send messages. (#3705) Thanks @conroywhitney, @CashWilliams.
-- Gateway: require TLS 1.3 minimum for TLS listeners. (#5970) Thanks @loganaden.
-- Web UI: refine chat layout + extend session active duration.
-- CI: add formal conformance + alias consistency checks. (#5723, #5807)
-
 ### Fixes
 
-- Security: guard remote media fetches with SSRF protections (block private/localhost, DNS pinning).
-- Updates: clean stale global install rename dirs and extend gateway update timeouts to avoid npm ENOTEMPTY failures.
 - Plugins: validate plugin/hook install paths and reject traversal-like names.
-- Telegram: add download timeouts for file fetches. (#6914) Thanks @hclsys.
-- Telegram: enforce thread specs for DM vs forum sends. (#6833) Thanks @obviyus.
-- Streaming: flush block streaming on paragraph boundaries for newline chunking. (#7014)
-- Streaming: stabilize partial streaming filters.
-- Auto-reply: avoid referencing workspace files in /new greeting prompt. (#5706) Thanks @bravostation.
-- Tools: align tool execute adapters/signatures (legacy + parameter order + arg normalization).
 - Tools: treat `"*"` tool allowlist entries as valid to avoid spurious unknown-entry warnings.
-- Skills: update session-logs paths from .clawdbot to .openclaw. (#4502)
-- Slack: harden media fetch limits and Slack file URL validation. (#6639) Thanks @davidiach.
-- Lint: satisfy curly rule after import sorting. (#6310)
-- Process: resolve Windows `spawn()` failures for npm-family CLIs by appending `.cmd` when needed. (#5815) Thanks @thejhinvirtuoso.
-- Discord: resolve PluralKit proxied senders for allowlists and labels. (#5838) Thanks @thewilloftheshadow.
-- Tlon: add timeout to SSE client fetch calls (CWE-400). (#5926)
-- Memory search: L2-normalize local embedding vectors to fix semantic search. (#5332)
-- Agents: align embedded runner + typings with pi-coding-agent API updates (pi 0.51.0).
-- Agents: ensure OpenRouter attribution headers apply in the embedded runner.
-- Agents: cap context window resolution for compaction safeguard. (#6187) Thanks @iamEvanYT.
-- System prompt: resolve overrides and hint using session_status for current date/time. (#1897, #1928, #2108, #3677)
-- Agents: fix Pi prompt template argument syntax. (#6543)
-- Subagents: fix announce failover race (always emit lifecycle end; timeout=0 means no-timeout). (#6621)
-- Teams: gate media auth retries.
-- Telegram: restore draft streaming partials. (#5543) Thanks @obviyus.
-- Onboarding: friendlier Windows onboarding message. (#6242) Thanks @shanselman.
-- TUI: prevent crash when searching with digits in the model selector.
-- Agents: wire before_tool_call plugin hook into tool execution. (#6570, #6660) Thanks @ryancnelson.
-- Browser: secure Chrome extension relay CDP sessions.
-- Docker: use container port for gateway command instead of host port. (#5110) Thanks @mise42.
-- Docker: start gateway CMD by default for container deployments. (#6635) Thanks @kaizen403.
-- fix(lobster): block arbitrary exec via lobsterPath/cwd injection (GHSA-4mhr-g7xj-cg8j). (#5335) Thanks @vignesh07.
-- Security: sanitize WhatsApp accountId to prevent path traversal. (#4610)
-- Security: restrict MEDIA path extraction to prevent LFI. (#4930)
-- Security: validate message-tool filePath/path against sandbox root. (#6398)
-- Security: block LD*/DYLD* env overrides for host exec. (#4896) Thanks @HassanFleyah.
-- Security: harden web tool content wrapping + file parsing safeguards. (#4058) Thanks @VACInc.
-- Security: enforce Twitch `allowFrom` allowlist gating (deny non-allowlisted senders). Thanks @MegaManSec.
 
 ## 2026.1.30
 
@@ -2376,7 +2552,7 @@ Docs: https://docs.openclaw.ai
 - Web search: add Brave freshness filter parameter for time-scoped results. (#1688) Thanks @JonUleis. https://docs.openclaw.ai/tools/web
 - UI: refresh Control UI dashboard design system (colors, icons, typography). (#1745, #1786) Thanks @EnzeD, @mousberg.
 - Exec approvals: forward approval prompts to chat with `/approve` for all channels (including plugins). (#1621) Thanks @czekaj. https://docs.openclaw.ai/tools/exec-approvals https://docs.openclaw.ai/tools/slash-commands
-- Gateway: expose config.patch in the gateway tool with safe partial updates + restart sentinel. (#1653) Thanks @Glucksberg.
+- Gateway: expose config.patch in the gateway tool with safe partial updates + restart sentinel. (#1653) Thanks @steipete.
 - Diagnostics: add diagnostic flags for targeted debug logs (config + env override). https://docs.openclaw.ai/diagnostics/flags
 - Docs: expand FAQ (migration, scheduling, concurrency, model recommendations, OpenAI subscription auth, Pi sizing, hackable install, docs SSL workaround).
 - Docs: add verbose installer troubleshooting guidance.
@@ -2389,7 +2565,7 @@ Docs: https://docs.openclaw.ai
 
 - Web UI: fix config/debug layout overflow, scrolling, and code block sizing. (#1715) Thanks @saipreetham589.
 - Web UI: show Stop button during active runs, swap back to New session when idle. (#1664) Thanks @ndbroadbent.
-- Web UI: clear stale disconnect banners on reconnect; allow form saves with unsupported schema paths but block missing schema. (#1707) Thanks @Glucksberg.
+- Web UI: clear stale disconnect banners on reconnect; allow form saves with unsupported schema paths but block missing schema. (#1707) Thanks @steipete.
 - Web UI: hide internal `message_id` hints in chat bubbles.
 - Gateway: allow Control UI token-only auth to skip device pairing even when device identity is present (`gateway.controlUi.allowInsecureAuth`). (#1679) Thanks @steipete.
 - Matrix: decrypt E2EE media attachments with preflight size guard. (#1744) Thanks @araa47.
@@ -2906,7 +3082,6 @@ Thanks @AlexMikhalev, @CoreyH, @John-Rood, @KrauseFx, @MaudeBot, @Nachx639, @Nic
 
 - **BREAKING:** iOS minimum version is now 18.0 to support Textual markdown rendering in native chat. (#702)
 - **BREAKING:** Microsoft Teams is now a plugin; install `@openclaw/msteams` via `openclaw plugins install @openclaw/msteams`.
-- **BREAKING:** Channel auth now prefers config over env for Discord/Telegram/Matrix (env is fallback only). (#1040) — thanks @thewilloftheshadow.
 
 ### Changes
 
@@ -2915,7 +3090,6 @@ Thanks @AlexMikhalev, @CoreyH, @John-Rood, @KrauseFx, @MaudeBot, @Nachx639, @Nic
 - CLI/macOS: sync remote SSH target/identity to config and let `gateway status` auto-infer SSH targets (ssh-config aware).
 - Telegram: scope inline buttons with allowlist default + callback gating in DMs/groups.
 - Telegram: default reaction notifications to own.
-- Tools: improve `web_fetch` extraction using Readability (with fallback).
 - Heartbeat: tighten prompt guidance + suppress duplicate alerts for 24h. (#980) — thanks @voidserf.
 - Repo: ignore local identity files to avoid accidental commits. (#1001) — thanks @gerardward2007.
 - Sessions/Security: add `session.dmScope` for multi-user DM isolation and audit warnings. (#948) — thanks @Alphonse-arianee.
@@ -2955,7 +3129,6 @@ Thanks @AlexMikhalev, @CoreyH, @John-Rood, @KrauseFx, @MaudeBot, @Nachx639, @Nic
 - Sessions: keep per-session overrides when `/new` resets compaction counters. (#1050) — thanks @YuriNachos.
 - Skills: allow OpenAI image-gen helper to handle URL or base64 responses. (#1050) — thanks @YuriNachos.
 - WhatsApp: default response prefix only for self-chat, using identity name when set.
-- Signal/iMessage: bound transport readiness waits to 30s with periodic logging. (#1014) — thanks @Szpadel.
 - iMessage: treat missing `imsg rpc` support as fatal to avoid restart loops.
 - Auth: merge main auth profiles into per-agent stores for sub-agents and document inheritance. (#1013) — thanks @marcmarg.
 - Agents: avoid JSON Schema `format` collisions in tool params by renaming snapshot format fields. (#1013) — thanks @marcmarg.
@@ -3052,13 +3225,7 @@ Thanks @AlexMikhalev, @CoreyH, @John-Rood, @KrauseFx, @MaudeBot, @Nachx639, @Nic
 - Agents: make user time zone and 24-hour time explicit in the system prompt. (#859) — thanks @CashWilliams.
 - Agents: strip downgraded tool call text without eating adjacent replies and filter thinking-tag leaks. (#905) — thanks @erikpr1994.
 - Agents: cap tool call IDs for OpenAI/OpenRouter to avoid request rejections. (#875) — thanks @j1philli.
-- Agents: scrub tuple `items` schemas for Gemini tool calls. (#926, fixes #746) — thanks @grp06.
-- Agents: stabilize sub-agent announce status from runtime outcomes and normalize Result/Notes. (#835) — thanks @roshanasingh4.
-- Auth: normalize Claude Code CLI profile mode to oauth and auto-migrate config. (#855) — thanks @sebslight.
-- Embedded runner: suppress raw API error payloads from replies. (#924) — thanks @grp06.
-- Logging: tolerate `EIO` from console writes to avoid gateway crashes. (#925, fixes #878) — thanks @grp06.
 - Sandbox: restore `docker.binds` config validation and preserve configured PATH for `docker exec`. (#873) — thanks @akonyer.
-- Google: downgrade unsigned thinking blocks before send to avoid missing signature errors.
 
 #### macOS / Apps
 

CONTRIBUTING.md

@@ -74,6 +74,7 @@ Welcome to the lobster tank! 🦞
 - Ensure CI checks pass
 - Keep PRs focused (one thing per PR; do not mix unrelated concerns)
 - Describe what & why
+- **Include screenshots** — one showing the problem/before, one showing the fix/after (for UI or visual changes)
 
 ## Control UI Decorators
 

Dockerfile

@@ -72,7 +72,7 @@ RUN if [ -n "$OPENCLAW_INSTALL_DOCKER_CLI" ]; then \
       # Update OPENCLAW_DOCKER_GPG_FINGERPRINT when Docker rotates release keys.
       curl -fsSL https://download.docker.com/linux/debian/gpg -o /tmp/docker.gpg.asc && \
       expected_fingerprint="$(printf '%s' "$OPENCLAW_DOCKER_GPG_FINGERPRINT" | tr '[:lower:]' '[:upper:]' | tr -d '[:space:]')" && \
-      actual_fingerprint="$(gpg --batch --show-keys --with-colons /tmp/docker.gpg.asc | awk -F: '$1 == \"fpr\" { print toupper($10); exit }')" && \
+      actual_fingerprint="$(gpg --batch --show-keys --with-colons /tmp/docker.gpg.asc | awk -F: '$1 == "fpr" { print toupper($10); exit }')" && \
       if [ -z "$actual_fingerprint" ] || [ "$actual_fingerprint" != "$expected_fingerprint" ]; then \
         echo "ERROR: Docker apt key fingerprint mismatch (expected $expected_fingerprint, got ${actual_fingerprint:-<empty>})" >&2; \
         exit 1; \

README.md

@@ -40,7 +40,7 @@ New install? Start here: [Getting started](https://docs.openclaw.ai/start/gettin
 
 - **[OpenAI](https://openai.com/)** (ChatGPT/Codex)
 
-Model note: while any model is supported, I strongly recommend **Anthropic Pro/Max (100/200) + Opus 4.6** for long‑context strength and better prompt‑injection resistance. See [Onboarding](https://docs.openclaw.ai/start/onboarding).
+Model note: while many providers/models are supported, for the best experience and lower prompt-injection risk use the strongest latest-generation model available to you. See [Onboarding](https://docs.openclaw.ai/start/onboarding).
 
 ## Models (selection + auth)
 

SECURITY.md

@@ -57,6 +57,8 @@ These are frequently reported but are typically closed with no code change:
 - Reports that only show differences in heuristic detection/parity (for example obfuscation-pattern detection on one exec path but not another, such as `node.invoke -> system.run` parity gaps) without demonstrating bypass of auth, approvals, allowlist enforcement, sandboxing, or other documented trust boundaries.
 - ReDoS/DoS claims that require trusted operator configuration input (for example catastrophic regex in `sessionFilter` or `logging.redactPatterns`) without a trust-boundary bypass.
 - Archive/install extraction claims that require pre-existing local filesystem priming in trusted state (for example planting symlink/hardlink aliases under destination directories such as skills/tools paths) without showing an untrusted path that can create/control that primitive.
+- Reports that depend on replacing or rewriting an already-approved executable path on a trusted host (same-path inode/content swap) without showing an untrusted path to perform that write.
+- Reports that depend on pre-existing symlinked skill/workspace filesystem state (for example symlink chains involving `skills/*/SKILL.md`) without showing an untrusted path that can create/control that state.
 - Missing HSTS findings on default local/loopback deployments.
 - Slack webhook signature findings when HTTP mode already uses signing-secret verification.
 - Discord inbound webhook signature findings for paths not used by this repo's Discord integration.
@@ -114,6 +116,8 @@ Plugins/extensions are part of OpenClaw's trusted computing base for a gateway.
 - Prompt-injection-only attacks (without a policy/auth/sandbox boundary bypass)
 - Reports that require write access to trusted local state (`~/.openclaw`, workspace files like `MEMORY.md` / `memory/*.md`)
 - Reports where exploitability depends on attacker-controlled pre-existing symlink/hardlink filesystem state in trusted local paths (for example extraction/install target trees) unless a separate untrusted boundary bypass is shown that creates that state.
+- Reports whose only claim is sandbox/workspace read expansion through trusted local skill/workspace symlink state (for example `skills/*/SKILL.md` symlink chains) unless a separate untrusted boundary bypass is shown that creates/controls that state.
+- Reports whose only claim is post-approval executable identity drift on a trusted host via same-path file replacement/rewrite unless a separate untrusted boundary bypass is shown for that host write primitive.
 - Reports where the only demonstrated impact is an already-authorized sender intentionally invoking a local-action command (for example `/export-session` writing to an absolute host path) without bypassing auth, sandbox, or another documented boundary
 - Reports where the only claim is that a trusted-installed/enabled plugin can execute with gateway/host privileges (documented trust model behavior).
 - Any report whose only claim is that an operator-enabled `dangerous*`/`dangerously*` config option weakens defaults (these are explicit break-glass tradeoffs by design)
@@ -149,6 +153,8 @@ OpenClaw's security model is "personal assistant" (one trusted operator, potenti
 - The model/agent is **not** a trusted principal. Assume prompt/content injection can manipulate behavior.
 - Security boundaries come from host/config trust, auth, tool policy, sandboxing, and exec approvals.
 - Prompt injection by itself is not a vulnerability report unless it crosses one of those boundaries.
+- Hook/webhook-driven payloads should be treated as untrusted content; keep unsafe bypass flags disabled unless doing tightly scoped debugging (`hooks.gmail.allowUnsafeExternalContent`, `hooks.mappings[].allowUnsafeExternalContent`).
+- Weak model tiers are generally easier to prompt-inject. For tool-enabled or hook-driven agents, prefer strong modern model tiers and strict tool policy (for example `tools.profile: "messaging"` or stricter), plus sandboxing where possible.
 
 ## Gateway and Node trust concept
 

appcast.xml

@@ -2,6 +2,225 @@
 <rss xmlns:sparkle="http://www.andymatuschak.org/xml-namespaces/sparkle" version="2.0">
     <channel>
         <title>OpenClaw</title>
+        <item>
+            <title>2026.3.2</title>
+            <pubDate>Tue, 03 Mar 2026 04:30:29 +0000</pubDate>
+            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
+            <sparkle:version>2026030290</sparkle:version>
+            <sparkle:shortVersionString>2026.3.2</sparkle:shortVersionString>
+            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
+            <description><![CDATA[<h2>OpenClaw 2026.3.2</h2>
+<h3>Changes</h3>
+<ul>
+<li>Secrets/SecretRef coverage: expand SecretRef support across the full supported user-supplied credential surface (64 targets total), including runtime collectors, <code>openclaw secrets</code> planning/apply/audit flows, onboarding SecretInput UX, and related docs; unresolved refs now fail fast on active surfaces while inactive surfaces report non-blocking diagnostics. (#29580) Thanks @joshavant.</li>
+<li>Tools/PDF analysis: add a first-class <code>pdf</code> tool with native Anthropic and Google PDF provider support, extraction fallback for non-native models, configurable defaults (<code>agents.defaults.pdfModel</code>, <code>pdfMaxBytesMb</code>, <code>pdfMaxPages</code>), and docs/tests covering routing, validation, and registration. (#31319) Thanks @tyler6204.</li>
+<li>Outbound adapters/plugins: add shared <code>sendPayload</code> support across direct-text-media, Discord, Slack, WhatsApp, Zalo, and Zalouser with multi-media iteration and chunk-aware text fallback. (#30144) Thanks @nohat.</li>
+<li>Models/MiniMax: add first-class <code>MiniMax-M2.5-highspeed</code> support across built-in provider catalogs, onboarding flows, and MiniMax OAuth plugin defaults, while keeping legacy <code>MiniMax-M2.5-Lightning</code> compatibility for existing configs.</li>
+<li>Sessions/Attachments: add inline file attachment support for <code>sessions_spawn</code> (subagent runtime only) with base64/utf8 encoding, transcript content redaction, lifecycle cleanup, and configurable limits via <code>tools.sessions_spawn.attachments</code>. (#16761) Thanks @napetrov.</li>
+<li>Telegram/Streaming defaults: default <code>channels.telegram.streaming</code> to <code>partial</code> (from <code>off</code>) so new Telegram setups get live preview streaming out of the box, with runtime fallback to message-edit preview when native drafts are unavailable.</li>
+<li>Telegram/DM streaming: use <code>sendMessageDraft</code> for private preview streaming, keep reasoning/answer preview lanes separated in DM reasoning-stream mode. (#31824) Thanks @obviyus.</li>
+<li>Telegram/voice mention gating: add optional <code>disableAudioPreflight</code> on group/topic config to skip mention-detection preflight transcription for inbound voice notes where operators want text-only mention checks. (#23067) Thanks @yangnim21029.</li>
+<li>CLI/Config validation: add <code>openclaw config validate</code> (with <code>--json</code>) to validate config files before gateway startup, and include detailed invalid-key paths in startup invalid-config errors. (#31220) thanks @Sid-Qin.</li>
+<li>Tools/Diffs: add PDF file output support and rendering quality customization controls (<code>fileQuality</code>, <code>fileScale</code>, <code>fileMaxWidth</code>) for generated diff artifacts, and document PDF as the preferred option when messaging channels compress images. (#31342) Thanks @gumadeiras.</li>
+<li>Memory/Ollama embeddings: add <code>memorySearch.provider = "ollama"</code> and <code>memorySearch.fallback = "ollama"</code> support, honor <code>models.providers.ollama</code> settings for memory embedding requests, and document Ollama embedding usage. (#26349) Thanks @nico-hoff.</li>
+<li>Zalo Personal plugin (<code>@openclaw/zalouser</code>): rebuilt channel runtime to use native <code>zca-js</code> integration in-process, removing external CLI transport usage and keeping QR/login + send/listen flows fully inside OpenClaw.</li>
+<li>Plugin SDK/channel extensibility: expose <code>channelRuntime</code> on <code>ChannelGatewayContext</code> so external channel plugins can access shared runtime helpers (reply/routing/session/text/media/commands) without internal imports. (#25462) Thanks @guxiaobo.</li>
+<li>Plugin runtime/STT: add <code>api.runtime.stt.transcribeAudioFile(...)</code> so extensions can transcribe local audio files through OpenClaw's configured media-understanding audio providers. (#22402) Thanks @benthecarman.</li>
+<li>Plugin hooks/session lifecycle: include <code>sessionKey</code> in <code>session_start</code>/<code>session_end</code> hook events and contexts so plugins can correlate lifecycle callbacks with routing identity. (#26394) Thanks @tempeste.</li>
+<li>Hooks/message lifecycle: add internal hook events <code>message:transcribed</code> and <code>message:preprocessed</code>, plus richer outbound <code>message:sent</code> context (<code>isGroup</code>, <code>groupId</code>) for group-conversation correlation and post-transcription automations. (#9859) Thanks @Drickon.</li>
+<li>Media understanding/audio echo: add optional <code>tools.media.audio.echoTranscript</code> + <code>echoFormat</code> to send a pre-agent transcript confirmation message to the originating chat, with echo disabled by default. (#32150) Thanks @AytuncYildizli.</li>
+<li>Plugin runtime/system: expose <code>runtime.system.requestHeartbeatNow(...)</code> so extensions can wake targeted sessions immediately after enqueueing system events. (#19464) Thanks @AustinEral.</li>
+<li>Plugin runtime/events: expose <code>runtime.events.onAgentEvent</code> and <code>runtime.events.onSessionTranscriptUpdate</code> for extension-side subscriptions, and isolate transcript-listener failures so one faulty listener cannot break the entire update fanout. (#16044) Thanks @scifantastic.</li>
+<li>CLI/Banner taglines: add <code>cli.banner.taglineMode</code> (<code>random</code> | <code>default</code> | <code>off</code>) to control funny tagline behavior in startup output, with docs + FAQ guidance and regression tests for config override behavior.</li>
+</ul>
+<h3>Breaking</h3>
+<ul>
+<li><strong>BREAKING:</strong> Onboarding now defaults <code>tools.profile</code> to <code>messaging</code> for new local installs (interactive + non-interactive). New setups no longer start with broad coding/system tools unless explicitly configured.</li>
+<li><strong>BREAKING:</strong> ACP dispatch now defaults to enabled unless explicitly disabled (<code>acp.dispatch.enabled=false</code>). If you need to pause ACP turn routing while keeping <code>/acp</code> controls, set <code>acp.dispatch.enabled=false</code>. Docs: https://docs.openclaw.ai/tools/acp-agents</li>
+<li><strong>BREAKING:</strong> Plugin SDK removed <code>api.registerHttpHandler(...)</code>. Plugins must register explicit HTTP routes via <code>api.registerHttpRoute({ path, auth, match, handler })</code>, and dynamic webhook lifecycles should use <code>registerPluginHttpRoute(...)</code>.</li>
+<li><strong>BREAKING:</strong> Zalo Personal plugin (<code>@openclaw/zalouser</code>) no longer depends on external <code>zca</code>-compatible CLI binaries (<code>openzca</code>, <code>zca-cli</code>) for runtime send/listen/login; operators should use <code>openclaw channels login --channel zalouser</code> after upgrade to refresh sessions in the new JS-native path.</li>
+</ul>
+<h3>Fixes</h3>
+<ul>
+<li>Plugin command/runtime hardening: validate and normalize plugin command name/description at registration boundaries, and guard Telegram native menu normalization paths so malformed plugin command specs cannot crash startup (<code>trim</code> on undefined). (#31997) Fixes #31944. Thanks @liuxiaopai-ai.</li>
+<li>Telegram: guard duplicate-token checks and gateway startup token normalization when account tokens are missing, preventing <code>token.trim()</code> crashes during status/start flows. (#31973) Thanks @ningding97.</li>
+<li>Discord/lifecycle startup status: push an immediate <code>connected</code> status snapshot when the gateway is already connected before lifecycle debug listeners attach, with abort-guarding to avoid contradictory status flips during pre-aborted startup. (#32336) Thanks @mitchmcalister.</li>
+<li>Feishu/LINE group system prompts: forward per-group <code>systemPrompt</code> config into inbound context <code>GroupSystemPrompt</code> for Feishu and LINE group/room events so configured group-specific behavior actually applies at dispatch time. (#31713) Thanks @whiskyboy.</li>
+<li>Mentions/Slack formatting hardening: add null-safe guards for runtime text normalization paths so malformed/undefined text payloads do not crash mention stripping or mrkdwn conversion. (#31865) Thanks @stone-jin.</li>
+<li>Feishu/Plugin sdk compatibility: add safe webhook default fallbacks when loading Feishu monitor state so mixed-version installs no longer crash if older <code>openclaw/plugin-sdk</code> builds omit webhook default constants. (#31606)</li>
+<li>Feishu/group broadcast dispatch: add configurable multi-agent group broadcast dispatch with observer-session isolation, cross-account dedupe safeguards, and non-mention history buffering rules that avoid duplicate replay in broadcast/topic workflows. (#29575) Thanks @ohmyskyhigh.</li>
+<li>Gateway/Subagent TLS pairing: allow authenticated local <code>gateway-client</code> backend self-connections to skip device pairing while still requiring pairing for non-local/direct-host paths, restoring <code>sessions_spawn</code> with <code>gateway.tls.enabled=true</code> in Docker/LAN setups. Fixes #30740. Thanks @Sid-Qin and @vincentkoc.</li>
+<li>Browser/CDP startup diagnostics: include Chrome stderr output and a Linux no-sandbox hint in startup timeout errors so failed launches are easier to diagnose. (#29312) Thanks @veast.</li>
+<li>Synology Chat/webhook ingress hardening: enforce bounded body reads (size + timeout) via shared request-body guards to prevent unauthenticated slow-body hangs before token validation. (#25831) Thanks @bmendonca3.</li>
+<li>Feishu/Dedup restart resilience: warm persistent dedup state into memory on monitor startup so retry events after gateway restart stay suppressed without requiring initial on-disk probe misses. (#31605)</li>
+<li>Voice-call/runtime lifecycle: prevent <code>EADDRINUSE</code> loops by resetting failed runtime promises, making webhook <code>start()</code> idempotent with the actual bound port, and fully cleaning up webhook/tunnel/tailscale resources after startup failures. (#32395) Thanks @scoootscooob.</li>
+<li>Gateway/Security hardening: tie loopback-origin dev allowance to actual local socket clients (not Host header claims), add explicit warnings/metrics when <code>gateway.controlUi.dangerouslyAllowHostHeaderOriginFallback</code> accepts websocket origins, harden safe-regex detection for quantified ambiguous alternation patterns (for example <code>(a|aa)+</code>), and bound large regex-evaluation inputs for session-filter and log-redaction paths.</li>
+<li>Gateway/Plugin HTTP hardening: require explicit <code>auth</code> for plugin route registration, add route ownership guards for duplicate <code>path+match</code> registrations, centralize plugin path matching/auth logic into dedicated modules, and share webhook target-route lifecycle wiring across channel monitors to avoid stale or conflicting registrations. Thanks @tdjackey for reporting.</li>
+<li>Browser/Profile defaults: prefer <code>openclaw</code> profile over <code>chrome</code> in headless/no-sandbox environments unless an explicit <code>defaultProfile</code> is configured. (#14944) Thanks @BenediktSchackenberg.</li>
+<li>Gateway/WS security: keep plaintext <code>ws://</code> loopback-only by default, with explicit break-glass private-network opt-in via <code>OPENCLAW_ALLOW_INSECURE_PRIVATE_WS=1</code>; align onboarding/client/call validation and tests to this strict-default policy. (#28670) Thanks @dashed, @vincentkoc.</li>
+<li>OpenAI Codex OAuth/TLS prerequisites: add an OAuth TLS cert-chain preflight with actionable remediation for cert trust failures, and gate doctor TLS prerequisite probing to OpenAI Codex OAuth-configured installs (or explicit <code>doctor --deep</code>) to avoid unconditional outbound probe latency. (#32051) Thanks @alexfilatov.</li>
+<li>Security/Webhook request hardening: enforce auth-before-body parsing for BlueBubbles and Google Chat webhook handlers, add strict pre-auth body/time budgets for webhook auth paths (including LINE signature verification), and add shared in-flight/request guardrails plus regression tests/lint checks to prevent reintroducing unauthenticated slow-body DoS patterns. Thanks @GCXWLP for reporting.</li>
+<li>CLI/Config validation and routing hardening: dedupe <code>openclaw config validate</code> failures to a single authoritative report, expose allowed-values metadata/hints across core Zod and plugin AJV validation (including <code>--json</code> fields), sanitize terminal-rendered validation text, and make command-path parsing root-option-aware across preaction/route/lazy registration (including routed <code>config get/unset</code> with split root options). Thanks @gumadeiras.</li>
+<li>Browser/Extension relay reconnect tolerance: keep <code>/json/version</code> and <code>/cdp</code> reachable during short MV3 worker disconnects when attached targets still exist, and retain clients across reconnect grace windows. (#30232) Thanks @Sid-Qin.</li>
+<li>CLI/Browser start timeout: honor <code>openclaw browser --timeout <ms> start</code> and stop by removing the fixed 15000ms override so slower Chrome startups can use caller-provided timeouts. (#22412, #23427) Thanks @vincentkoc.</li>
+<li>Synology Chat/gateway lifecycle: keep <code>startAccount</code> pending until abort for inactive and active account paths to prevent webhook route restart loops under gateway supervision. (#23074) Thanks @druide67.</li>
+<li>Exec approvals/allowlist matching: escape regex metacharacters in path-pattern literals (while preserving glob wildcards), preventing crashes on allowlisted executables like <code>/usr/bin/g++</code> and correctly matching mixed wildcard/literal token paths. (#32162) Thanks @stakeswky.</li>
+<li>Synology Chat/webhook compatibility: accept JSON and alias payload fields, allow token resolution from body/query/header sources, and ACK webhook requests with <code>204</code> to avoid persistent <code>Processing...</code> states in Synology Chat clients. (#26635) Thanks @memphislee09-source.</li>
+<li>Voice-call/Twilio signature verification: retry signature validation across deterministic URL port variants (with/without port) to handle mixed Twilio signing behavior behind reverse proxies and non-standard ports. (#25140) Thanks @drvoss.</li>
+<li>Slack/Bolt startup compatibility: remove invalid <code>message.channels</code> and <code>message.groups</code> event registrations so Slack providers no longer crash on startup with Bolt 4.6+; channel/group traffic continues through the unified <code>message</code> handler (<code>channel_type</code>). (#32033) Thanks @mahopan.</li>
+<li>Slack/socket auth failure handling: fail fast on non-recoverable auth errors (<code>account_inactive</code>, <code>invalid_auth</code>, etc.) during startup and reconnect instead of retry-looping indefinitely, including <code>unable_to_socket_mode_start</code> error payload propagation. (#32377) Thanks @scoootscooob.</li>
+<li>Gateway/macOS LaunchAgent hardening: write <code>Umask=077</code> in generated gateway LaunchAgent plists so npm upgrades preserve owner-only default file permissions for gateway-created state files. (#31919) Fixes #31905. Thanks @liuxiaopai-ai.</li>
+<li>macOS/LaunchAgent security defaults: write <code>Umask=63</code> (octal <code>077</code>) into generated gateway launchd plists so post-update service reinstalls keep owner-only file permissions by default instead of falling back to system <code>022</code>. (#32022) Fixes #31905. Thanks @liuxiaopai-ai.</li>
+<li>Media understanding/provider HTTP proxy routing: pass a proxy-aware fetch function from <code>HTTPS_PROXY</code>/<code>HTTP_PROXY</code> env vars into audio/video provider calls (with graceful malformed-proxy fallback) so transcription/video requests honor configured outbound proxies. (#27093) Thanks @mcaxtr.</li>
+<li>Sandbox/workspace mount permissions: make primary <code>/workspace</code> bind mounts read-only whenever <code>workspaceAccess</code> is not <code>rw</code> (including <code>none</code>) across both core sandbox container and sandbox browser create flows. (#32227) Thanks @guanyu-zhang.</li>
+<li>Tools/fsPolicy propagation: honor <code>tools.fs.workspaceOnly</code> for image/pdf local-root allowlists so non-sandbox media paths outside workspace are rejected when workspace-only mode is enabled. (#31882) Thanks @justinhuangcode.</li>
+<li>Daemon/Homebrew runtime pinning: resolve Homebrew Cellar Node paths to stable Homebrew-managed symlinks (including versioned formulas like <code>node@22</code>) so gateway installs keep the intended runtime across brew upgrades. (#32185) Thanks @scoootscooob.</li>
+<li>Browser/Security output boundary hardening: replace check-then-rename output commits with root-bound fd-verified writes, unify install/skills canonical path-boundary checks, and add regression coverage for symlink-rebind race paths across browser output and shared fs-safe write flows. Thanks @tdjackey for reporting.</li>
+<li>Gateway/Security canonicalization hardening: decode plugin route path variants to canonical fixpoint (with bounded depth), fail closed on canonicalization anomalies, and enforce gateway auth for deeply encoded <code>/api/channels/*</code> variants to prevent alternate-path auth bypass through plugin handlers. Thanks @tdjackey for reporting.</li>
+<li>Browser/Gateway hardening: preserve env credentials for <code>OPENCLAW_GATEWAY_URL</code> / <code>CLAWDBOT_GATEWAY_URL</code> while treating explicit <code>--url</code> as override-only auth, and make container browser hardening flags optional with safer defaults for Docker/LXC stability. (#31504) Thanks @vincentkoc.</li>
+<li>Gateway/Control UI basePath webhook passthrough: let non-read methods under configured <code>controlUiBasePath</code> fall through to plugin routes (instead of returning Control UI 405), restoring webhook handlers behind basePath mounts. (#32311) Thanks @ademczuk.</li>
+<li>Control UI/Legacy browser compatibility: replace <code>toSorted</code>-dependent cron suggestion sorting in <code>app-render</code> with a compatibility helper so older browsers without <code>Array.prototype.toSorted</code> no longer white-screen. (#31775) Thanks @liuxiaopai-ai.</li>
+<li>macOS/PeekabooBridge: add compatibility socket symlinks for legacy <code>clawdbot</code>, <code>clawdis</code>, and <code>moltbot</code> Application Support socket paths so pre-rename clients can still connect. (#6033) Thanks @lumpinif and @vincentkoc.</li>
+<li>Gateway/message tool reliability: avoid false <code>Unknown channel</code> failures when <code>message.*</code> actions receive platform-specific channel ids by falling back to <code>toolContext.currentChannelProvider</code>, and prevent health-monitor restart thrash for channels that just (re)started by adding a per-channel startup-connect grace window. (from #32367) Thanks @MunemHashmi.</li>
+<li>Windows/Spawn canonicalization: unify non-core Windows spawn handling across ACP client, QMD/mcporter memory paths, and sandbox Docker execution using the shared wrapper-resolution policy, with targeted regression coverage for <code>.cmd</code> shim unwrapping and shell fallback behavior. (#31750) Thanks @Takhoffman.</li>
+<li>Security/ACP sandbox inheritance: enforce fail-closed runtime guardrails for <code>sessions_spawn</code> with <code>runtime="acp"</code> by rejecting ACP spawns from sandboxed requester sessions and rejecting <code>sandbox="require"</code> for ACP runtime, preventing sandbox-boundary bypass via host-side ACP initialization. (#32254) Thanks @tdjackey for reporting, and @dutifulbob for the fix.</li>
+<li>Security/Web tools SSRF guard: keep DNS pinning for untrusted <code>web_fetch</code> and citation-redirect URL checks when proxy env vars are set, and require explicit dangerous opt-in before env-proxy routing can bypass pinned dispatch for trusted/operator-controlled endpoints. Thanks @tdjackey for reporting.</li>
+<li>Gemini schema sanitization: coerce malformed JSON Schema <code>properties</code> values (<code>null</code>, arrays, primitives) to <code>{}</code> before provider validation, preventing downstream strict-validator crashes on invalid plugin/tool schemas. (#32332) Thanks @webdevtodayjason.</li>
+<li>Media understanding/malformed attachment guards: harden attachment selection and decision summary formatting against non-array or malformed attachment payloads to prevent runtime crashes on invalid inbound metadata shapes. (#28024) Thanks @claw9267.</li>
+<li>Browser/Extension navigation reattach: preserve debugger re-attachment when relay is temporarily disconnected by deferring relay attach events until reconnect/re-announce, reducing post-navigation tab loss. (#28725) Thanks @stone-jin.</li>
+<li>Browser/Extension relay stale tabs: evict stale cached targets from <code>/json/list</code> when extension targets are destroyed/crashed or commands fail with missing target/session errors. (#6175) Thanks @vincentkoc.</li>
+<li>Browser/CDP startup readiness: wait for CDP websocket readiness after launching Chrome and cleanly stop/reset when readiness never arrives, reducing follow-up <code>PortInUseError</code> races after <code>browser start</code>/<code>open</code>. (#29538) Thanks @AaronWander.</li>
+<li>OpenAI/Responses WebSocket tool-call id hygiene: normalize blank/whitespace streamed tool-call ids before persistence, and block empty <code>function_call_output.call_id</code> payloads in the WS conversion path to avoid OpenAI 400 errors (<code>Invalid 'input[n].call_id': empty string</code>), with regression coverage for both inbound stream normalization and outbound payload guards.</li>
+<li>Security/Nodes camera URL downloads: bind node <code>camera.snap</code>/<code>camera.clip</code> URL payload downloads to the resolved node host, enforce fail-closed behavior when node <code>remoteIp</code> is unavailable, and use SSRF-guarded fetch with redirect host/protocol checks to prevent off-node fetch pivots. Thanks @tdjackey for reporting.</li>
+<li>Config/backups hardening: enforce owner-only (<code>0600</code>) permissions on rotated config backups and clean orphan <code>.bak.*</code> files outside the managed backup ring, reducing credential leakage risk from stale or permissive backup artifacts. (#31718) Thanks @YUJIE2002.</li>
+<li>Telegram/inbound media filenames: preserve original <code>file_name</code> metadata for document/audio/video/animation downloads (with fetch/path fallbacks), so saved inbound attachments keep sender-provided names instead of opaque Telegram file paths. (#31837) Thanks @Kay-051.</li>
+<li>Gateway/OpenAI chat completions: honor <code>x-openclaw-message-channel</code> when building <code>agentCommand</code> input for <code>/v1/chat/completions</code>, preserving caller channel identity instead of forcing <code>webchat</code>. (#30462) Thanks @bmendonca3.</li>
+<li>Plugin SDK/runtime hardening: add package export verification in CI/release checks to catch missing runtime exports before publish-time regressions. (#28575) Thanks @Glucksberg.</li>
+<li>Media/MIME normalization: normalize parameterized/case-variant MIME strings in <code>kindFromMime</code> (for example <code>Audio/Ogg; codecs=opus</code>) so WhatsApp voice notes are classified as audio and routed through transcription correctly. (#32280) Thanks @Lucenx9.</li>
+<li>Discord/audio preflight mentions: detect audio attachments via Discord <code>content_type</code> and gate preflight transcription on typed text (not media placeholders), so guild voice-note mentions are transcribed and matched correctly. (#32136) Thanks @jnMetaCode.</li>
+<li>Feishu/topic session routing: use <code>thread_id</code> as topic session scope fallback when <code>root_id</code> is absent, keep first-turn topic keys stable across thread creation, and force thread replies when inbound events already carry topic/thread context. (#29788) Thanks @songyaolun.</li>
+<li>Gateway/Webchat NO_REPLY streaming: suppress assistant lead-fragment deltas that are prefixes of <code>NO_REPLY</code> and keep final-message buffering in sync, preventing partial <code>NO</code> leaks on silent-response runs while preserving legitimate short replies. (#32073) Thanks @liuxiaopai-ai.</li>
+<li>Telegram/models picker callbacks: keep long model buttons selectable by falling back to compact callback payloads and resolving provider ids on selection (with provider re-prompt on ambiguity), avoiding Telegram 64-byte callback truncation failures. (#31857) Thanks @bmendonca3.</li>
+<li>Context-window metadata warmup: add exponential config-load retry backoff (1s -> 2s -> 4s, capped at 60s) so transient startup failures recover automatically without hot-loop retries.</li>
+<li>Voice-call/Twilio external outbound: auto-register webhook-first <code>outbound-api</code> calls (initiated outside OpenClaw) so media streams are accepted and call direction metadata stays accurate. (#31181) Thanks @scoootscooob.</li>
+<li>Feishu/topic root replies: prefer <code>root_id</code> as outbound <code>replyTargetMessageId</code> when present, and parse millisecond <code>message_create_time</code> values correctly so topic replies anchor to the root message in grouped thread flows. (#29968) Thanks @bmendonca3.</li>
+<li>Feishu/DM pairing reply target: send pairing challenge replies to <code>chat:<chat_id></code> instead of <code>user:<sender_open_id></code> so Lark/Feishu private chats with user-id-only sender payloads receive pairing messages reliably. (#31403) Thanks @stakeswky.</li>
+<li>Feishu/Lark private DM routing: treat inbound <code>chat_type: "private"</code> as direct-message context for pairing/mention-forward/reaction synthetic handling so Lark private chats behave like Feishu p2p DMs. (#31400) Thanks @stakeswky.</li>
+<li>Signal/message actions: allow <code>react</code> to fall back to <code>toolContext.currentMessageId</code> when <code>messageId</code> is omitted, matching Telegram behavior and unblocking agent-initiated reactions on inbound turns. (#32217) Thanks @dunamismax.</li>
+<li>Discord/message actions: allow <code>react</code> to fall back to <code>toolContext.currentMessageId</code> when <code>messageId</code> is omitted, matching Telegram/Signal reaction ergonomics in inbound turns.</li>
+<li>Synology Chat/reply delivery: resolve webhook usernames to Chat API <code>user_id</code> values for outbound chatbot replies, avoiding mismatches between webhook user IDs and <code>method=chatbot</code> recipient IDs in multi-account setups. (#23709) Thanks @druide67.</li>
+<li>Slack/thread context payloads: only inject thread starter/history text on first thread turn for new sessions while preserving thread metadata, reducing repeated context-token bloat on long-lived thread sessions. (#32133) Thanks @sourman.</li>
+<li>Slack/session routing: keep top-level channel messages in one shared session when <code>replyToMode=off</code>, while preserving thread-scoped keys for true thread replies and non-off modes. (#32193) Thanks @bmendonca3.</li>
+<li>Voice-call/webhook routing: require exact webhook path matches (instead of prefix matches) so lookalike paths cannot reach provider verification/dispatch logic. (#31930) Thanks @afurm.</li>
+<li>Zalo/Pairing auth tests: add webhook regression coverage asserting DM pairing-store reads/writes remain account-scoped, preventing cross-account authorization bleed in multi-account setups. (#26121) Thanks @bmendonca3.</li>
+<li>Zalouser/Pairing auth tests: add account-scoped DM pairing-store regression coverage (<code>monitor.account-scope.test.ts</code>) to prevent cross-account allowlist bleed in multi-account setups. (#26672) Thanks @bmendonca3.</li>
+<li>Feishu/Send target prefixes: normalize explicit <code>group:</code>/<code>dm:</code> send targets and preserve explicit receive-id routing hints when resolving outbound Feishu targets. (#31594) Thanks @liuxiaopai-ai.</li>
+<li>Webchat/Feishu session continuation: preserve routable <code>OriginatingChannel</code>/<code>OriginatingTo</code> metadata from session delivery context in <code>chat.send</code>, and prefer provider-normalized channel when deciding cross-channel route dispatch so Webchat replies continue on the selected Feishu session instead of falling back to main/internal session routing. (#31573)</li>
+<li>Telegram/implicit mention forum handling: exclude Telegram forum system service messages (<code>forum_topic_*</code>, <code>general_forum_topic_*</code>) from reply-chain implicit mention detection so <code>requireMention</code> does not get bypassed inside bot-created topic lifecycle events. (#32262) Thanks @scoootscooob.</li>
+<li>Slack/inbound debounce routing: isolate top-level non-DM message debounce keys by message timestamp to avoid cross-thread collisions, preserve DM batching, and flush pending top-level buffers before immediate non-debounce follow-ups to keep ordering stable. (#31951) Thanks @scoootscooob.</li>
+<li>Feishu/Duplicate replies: suppress same-target reply dispatch when message-tool sends use generic provider metadata (<code>provider: "message"</code>) and normalize <code>lark</code>/<code>feishu</code> provider aliases during duplicate-target checks, preventing double-delivery in Feishu sessions. (#31526)</li>
+<li>Webchat/silent token leak: filter assistant <code>NO_REPLY</code>-only transcript entries from <code>chat.history</code> responses and add client-side defense-in-depth guards in the chat controller so internal silent tokens never render as visible chat bubbles. (#32015) Consolidates overlap from #32183, #32082, #32045, #32052, #32172, and #32112. Thanks @ademczuk, @liuxiaopai-ai, @ningding97, @bmendonca3, and @x4v13r1120.</li>
+<li>Doctor/local memory provider checks: stop false-positive local-provider warnings when <code>provider=local</code> and no explicit <code>modelPath</code> is set by honoring default local model fallback while still warning when gateway probe reports local embeddings not ready. (#32014) Fixes #31998. Thanks @adhishthite.</li>
+<li>Media understanding/parakeet CLI output parsing: read <code>parakeet-mlx</code> transcripts from <code>--output-dir/<media-basename>.txt</code> when txt output is requested (or default), with stdout fallback for non-txt formats. (#9177) Thanks @mac-110.</li>
+<li>Media understanding/audio transcription guard: skip tiny/empty audio files (<1024 bytes) before provider/CLI transcription to avoid noisy invalid-audio failures and preserve clean fallback behavior. (#8388) Thanks @Glucksberg.</li>
+<li>Gateway/Plugin HTTP route precedence: run explicit plugin HTTP routes before the Control UI SPA catch-all so registered plugin webhook/custom paths remain reachable, while unmatched paths still fall through to Control UI handling. (#31885) Thanks @Sid-Qin.</li>
+<li>Gateway/Node browser proxy routing: honor <code>profile</code> from <code>browser.request</code> JSON body when query params omit it, while preserving query-profile precedence when both are present. (#28852) Thanks @Sid-Qin.</li>
+<li>Gateway/Control UI basePath POST handling: return 405 for <code>POST</code> on exact basePath routes (for example <code>/openclaw</code>) instead of redirecting, and add end-to-end regression coverage that root-mounted webhook POST paths still pass through to plugin handlers. (#31349) Thanks @Sid-Qin.</li>
+<li>Browser/default profile selection: default <code>browser.defaultProfile</code> behavior now prefers <code>openclaw</code> (managed standalone CDP) when no explicit default is configured, while still auto-provisioning the <code>chrome</code> relay profile for explicit opt-in use. (#32031) Fixes #31907. Thanks @liuxiaopai-ai.</li>
+<li>Sandbox/mkdirp boundary checks: allow existing in-boundary directories to pass mkdirp boundary validation when directory open probes return platform-specific I/O errors, with regression coverage for directory-safe fallback behavior. (#31547) Thanks @stakeswky.</li>
+<li>Models/config env propagation: apply <code>config.env.vars</code> before implicit provider discovery in models bootstrap so config-scoped credentials are visible to implicit provider resolution paths. (#32295) Thanks @hsiaoa.</li>
+<li>Models/Codex usage labels: infer weekly secondary usage windows from reset cadence when API window seconds are ambiguously reported as 24h, so <code>openclaw models status</code> no longer mislabels weekly limits as daily. (#31938) Thanks @bmendonca3.</li>
+<li>Gateway/Heartbeat model reload: treat <code>models.*</code> and <code>agents.defaults.model</code> config updates as heartbeat hot-reload triggers so heartbeat picks up model changes without a full gateway restart. (#32046) Thanks @stakeswky.</li>
+<li>Memory/LanceDB embeddings: forward configured <code>embedding.dimensions</code> into OpenAI embeddings requests so vector size and API output dimensions stay aligned when dimensions are explicitly configured. (#32036) Thanks @scotthuang.</li>
+<li>Gateway/Control UI method guard: allow POST requests to non-UI routes to fall through when no base path is configured, and add POST regression coverage for fallthrough and base-path 405 behavior. (#23970) Thanks @tyler6204.</li>
+<li>Browser/CDP status accuracy: require a successful <code>Browser.getVersion</code> response over the CDP websocket (not just socket-open) before reporting <code>cdpReady</code>, so stale idle command channels are surfaced as unhealthy. (#23427) Thanks @vincentkoc.</li>
+<li>Daemon/systemd checks in containers: treat missing <code>systemctl</code> invocations (including <code>spawn systemctl ENOENT</code>/<code>EACCES</code>) as unavailable service state during <code>is-enabled</code> checks, preventing container flows from failing with <code>Gateway service check failed</code> before install/status handling can continue. (#26089) Thanks @sahilsatralkar and @vincentkoc.</li>
+<li>Security/Node exec approvals: revalidate approval-bound <code>cwd</code> identity immediately before execution/forwarding and fail closed with an explicit denial when <code>cwd</code> drifts after approval hardening.</li>
+<li>Security audit/skills workspace hardening: add <code>skills.workspace.symlink_escape</code> warning in <code>openclaw security audit</code> when workspace <code>skills/**/SKILL.md</code> resolves outside the workspace root (for example symlink-chain drift), plus docs coverage in the security glossary.</li>
+<li>Security/Node exec approvals: preserve shell/dispatch-wrapper argv semantics during approval hardening so approved wrapper commands (for example <code>env sh -c ...</code>) cannot drift into a different runtime command shape, and add regression coverage for both approval-plan generation and approved runtime execution paths. Thanks @tdjackey for reporting.</li>
+<li>Security/fs-safe write hardening: make <code>writeFileWithinRoot</code> use same-directory temp writes plus atomic rename, add post-write inode/hardlink revalidation with security warnings on boundary drift, and avoid truncating existing targets when final rename fails.</li>
+<li>Security/Skills archive extraction: unify tar extraction safety checks across tar.gz and tar.bz2 install flows, enforce tar compressed-size limits, and fail closed if tar.bz2 archives change between preflight and extraction to prevent bypasses of entry-type/size guardrails. Thanks @GCXWLP for reporting.</li>
+<li>Security/Prompt spoofing hardening: stop injecting queued runtime events into user-role prompt text, route them through trusted system-prompt context, and neutralize inbound spoof markers like <code>[System Message]</code> and line-leading <code>System:</code> in untrusted message content. (#30448)</li>
+<li>Sandbox/Docker setup command parsing: accept <code>agents.*.sandbox.docker.setupCommand</code> as either a string or a string array, and normalize arrays to newline-delimited shell scripts so multi-step setup commands no longer concatenate without separators. (#31953) Thanks @liuxiaopai-ai.</li>
+<li>Sandbox/Bootstrap context boundary hardening: reject symlink/hardlink alias bootstrap seed files that resolve outside the source workspace and switch post-compaction <code>AGENTS.md</code> context reads to boundary-verified file opens, preventing host file content from being injected via workspace aliasing. Thanks @tdjackey for reporting.</li>
+<li>Agents/Sandbox workdir mapping: map container workdir paths (for example <code>/workspace</code>) back to the host workspace before sandbox path validation so exec requests keep the intended directory in containerized runs instead of falling back to an unavailable host path. (#31841) Thanks @liuxiaopai-ai.</li>
+<li>Docker/Sandbox bootstrap hardening: make <code>OPENCLAW_SANDBOX</code> opt-in parsing explicit (<code>1|true|yes|on</code>), support custom Docker socket paths via <code>OPENCLAW_DOCKER_SOCKET</code>, defer docker.sock exposure until sandbox prerequisites pass, and reset/roll back persisted sandbox mode to <code>off</code> when setup is skipped or partially fails to avoid stale broken sandbox state. (#29974) Thanks @jamtujest and @vincentkoc.</li>
+<li>Hooks/webhook ACK compatibility: return <code>200</code> (instead of <code>202</code>) for successful <code>/hooks/agent</code> requests so providers that require <code>200</code> (for example Forward Email) accept dispatched agent hook deliveries. (#28204) Thanks @Glucksberg.</li>
+<li>Feishu/Run channel fallback: prefer <code>Provider</code> over <code>Surface</code> when inferring queued run <code>messageProvider</code> fallback (when <code>OriginatingChannel</code> is missing), preventing Feishu turns from being mislabeled as <code>webchat</code> in mixed relay metadata contexts. (#31880) Fixes #31859. Thanks @liuxiaopai-ai.</li>
+<li>Skills/sherpa-onnx-tts: run the <code>sherpa-onnx-tts</code> bin under ESM (replace CommonJS <code>require</code> imports) and add regression coverage to prevent <code>require is not defined in ES module scope</code> startup crashes. (#31965) Thanks @bmendonca3.</li>
+<li>Inbound metadata/direct relay context: restore direct-channel conversation metadata blocks for external channels (for example WhatsApp) while preserving webchat-direct suppression, so relay agents recover sender/message identifiers without reintroducing internal webchat metadata noise. (#31969) Fixes #29972. Thanks @Lucenx9.</li>
+<li>Slack/Channel message subscriptions: register explicit <code>message.channels</code> and <code>message.groups</code> monitor handlers (alongside generic <code>message</code>) so channel/group event subscriptions are consumed even when Slack dispatches typed message event names. Fixes #31674.</li>
+<li>Hooks/session-scoped memory context: expose ephemeral <code>sessionId</code> in embedded plugin tool contexts and <code>before_tool_call</code>/<code>after_tool_call</code> hook contexts (including compaction and client-tool wiring) so plugins can isolate per-conversation state across <code>/new</code> and <code>/reset</code>. Related #31253 and #31304. Thanks @Sid-Qin and @Servo-AIpex.</li>
+<li>Voice-call/Twilio inbound greeting: run answered-call initial notify greeting for Twilio instead of skipping the manager speak path, with regression coverage for both Twilio and Plivo notify flows. (#29121) Thanks @xinhuagu.</li>
+<li>Voice-call/stale call hydration: verify active calls with the provider before loading persisted in-progress calls so stale locally persisted records do not block or misroute new call handling after restarts. (#4325) Thanks @garnetlyx.</li>
+<li>Feishu/File upload filenames: percent-encode non-ASCII/special-character <code>file_name</code> values in Feishu multipart uploads so Chinese/symbol-heavy filenames are sent as proper attachments instead of plain text links. (#31179) Thanks @Kay-051.</li>
+<li>Media/MIME channel parity: route Telegram/Signal/iMessage media-kind checks through normalized <code>kindFromMime</code> so mixed-case/parameterized MIME values classify consistently across message channels.</li>
+<li>WhatsApp/inbound self-message context: propagate inbound <code>fromMe</code> through the web inbox pipeline and annotate direct self messages as <code>(self)</code> in envelopes so agents can distinguish owner-authored turns from contact turns. (#32167) Thanks @scoootscooob.</li>
+<li>Webchat/stream finalization: persist streamed assistant text when final events omit <code>message</code>, while keeping final payload precedence and skipping empty stream buffers to prevent disappearing replies after tool turns. (#31920) Thanks @Sid-Qin.</li>
+<li>Feishu/Inbound ordering: serialize message handling per chat while preserving cross-chat concurrency to avoid same-chat race drops under bursty inbound traffic. (#31807)</li>
+<li>Feishu/Typing notification suppression: skip typing keepalive reaction re-adds when the indicator is already active, preventing duplicate notification pings from repeated identical emoji adds. (#31580)</li>
+<li>Feishu/Probe failure backoff: cache API and timeout probe failures for one minute per account key while preserving abort-aware probe timeouts, reducing repeated health-check retries during transient credential/network outages. (#29970)</li>
+<li>Feishu/Streaming block fallback: preserve markdown block stream text as final streaming-card content when final payload text is missing, while still suppressing non-card internal block chunk delivery. (#30663)</li>
+<li>Feishu/Bitable API errors: unify Feishu Bitable tool error handling with structured <code>LarkApiError</code> responses and consistent API/context attribution across wiki/base metadata, field, and record operations. (#31450)</li>
+<li>Feishu/Missing-scope grant URL fix: rewrite known invalid scope aliases (<code>contact:contact.base:readonly</code>) to valid scope names in permission grant links, so remediation URLs open with correct Feishu consent scopes. (#31943)</li>
+<li>BlueBubbles/Message metadata: harden send response ID extraction, include sender identity in DM context, and normalize inbound <code>message_id</code> selection to avoid duplicate ID metadata. (#23970) Thanks @tyler6204.</li>
+<li>WebChat/markdown tables: ensure GitHub-flavored markdown table parsing is explicitly enabled at render time and add horizontal overflow handling for wide tables, with regression coverage for table-only and mixed text+table content. (#32365) Thanks @BlueBirdBack.</li>
+<li>Feishu/default account resolution: always honor explicit <code>channels.feishu.defaultAccount</code> during outbound account selection (including top-level-credential setups where the preferred id is not present in <code>accounts</code>), instead of silently falling back to another account id. (#32253) Thanks @bmendonca3.</li>
+<li>Feishu/Sender lookup permissions: suppress user-facing grant prompts for stale non-existent scope errors (<code>contact:contact.base:readonly</code>) during best-effort sender-name resolution so inbound messages continue without repeated false permission notices. (#31761)</li>
+<li>Discord/dispatch + Slack formatting: restore parallel outbound dispatch across Discord channels with per-channel queues while preserving in-channel ordering, and run Slack preview/stream update text through mrkdwn normalization for consistent formatting. (#31927) Thanks @Sid-Qin.</li>
+<li>Feishu/Inbound debounce: debounce rapid same-chat sender bursts into one ordered dispatch turn, skip already-processed retries when composing merged text, and preserve bot-mention intent across merged entries to reduce duplicate or late inbound handling. (#31548)</li>
+<li>Tests/Sandbox + archive portability: use junction-compatible directory-link setup on Windows and explicit file-symlink platform guards in symlink escape tests where unprivileged file symlinks are unavailable, reducing false Windows CI failures while preserving traversal checks on supported paths. (#28747) Thanks @arosstale.</li>
+<li>Browser/Extension re-announce reliability: keep relay state in <code>connecting</code> when re-announce forwarding fails and extend debugger re-attach retries after navigation to reduce false attached states and post-nav disconnect loops. (#27630) Thanks @markmusson.</li>
+<li>Browser/Act request compatibility: accept legacy flattened <code>action="act"</code> params (<code>kind/ref/text/...</code>) in addition to <code>request={...}</code> so browser act calls no longer fail with <code>request required</code>. (#15120) Thanks @vincentkoc.</li>
+<li>OpenRouter/x-ai compatibility: skip <code>reasoning.effort</code> injection for <code>x-ai/*</code> models (for example Grok) so OpenRouter requests no longer fail with invalid-arguments errors on unsupported reasoning params. (#32054) Thanks @scoootscooob.</li>
+<li>Models/openai-completions developer-role compatibility: force <code>supportsDeveloperRole=false</code> for non-native endpoints, treat unparseable <code>baseUrl</code> values as non-native, and add regression coverage for empty/malformed baseUrl plus explicit-true override behavior. (#29479) thanks @akramcodez.</li>
+<li>Browser/Profile attach-only override: support <code>browser.profiles.<name>.attachOnly</code> (fallback to global <code>browser.attachOnly</code>) so loopback proxy profiles can skip local launch/port-ownership checks without forcing attach-only mode for every profile. (#20595) Thanks @unblockedgamesstudio and @vincentkoc.</li>
+<li>Sessions/Lock recovery: detect recycled Linux PIDs by comparing lock-file <code>starttime</code> with <code>/proc/<pid>/stat</code> starttime, so stale <code>.jsonl.lock</code> files are reclaimed immediately in containerized PID-reuse scenarios while preserving compatibility for older lock files. (#26443) Fixes #27252. Thanks @HirokiKobayashi-R and @vincentkoc.</li>
+<li>Cron/isolated delivery target fallback: remove early unresolved-target return so cron delivery can flow through shared outbound target resolution (including per-channel <code>resolveDefaultTo</code> fallback) when <code>delivery.to</code> is omitted. (#32364) Thanks @hclsys.</li>
+<li>OpenAI media capabilities: include <code>audio</code> in the OpenAI provider capability list so audio transcription models are eligible in media-understanding provider selection. (#12717) Thanks @openjay.</li>
+<li>Browser/Managed tab cap: limit loopback managed <code>openclaw</code> page tabs to 8 via best-effort cleanup after tab opens to reduce long-running renderer buildup while preserving attach-only and remote profile behavior. (#29724) Thanks @pandego.</li>
+<li>Docker/Image health checks: add Dockerfile <code>HEALTHCHECK</code> that probes gateway <code>GET /healthz</code> so container runtimes can mark unhealthy instances without requiring auth credentials in the probe command. (#11478) Thanks @U-C4N and @vincentkoc.</li>
+<li>Gateway/Node dangerous-command parity: include <code>sms.send</code> in default onboarding node <code>denyCommands</code>, share onboarding deny defaults with the gateway dangerous-command source of truth, and include <code>sms.send</code> in phone-control <code>/phone arm writes</code> handling so SMS follows the same break-glass flow as other dangerous node commands. Thanks @zpbrent.</li>
+<li>Pairing/AllowFrom account fallback: handle omitted <code>accountId</code> values in <code>readChannelAllowFromStore</code> and <code>readChannelAllowFromStoreSync</code> as <code>default</code>, while preserving legacy unscoped allowFrom merges for default-account flows. Thanks @Sid-Qin and @vincentkoc.</li>
+<li>Browser/Remote CDP ownership checks: skip local-process ownership errors for non-loopback remote CDP profiles when HTTP is reachable but the websocket handshake fails, and surface the remote websocket attach/retry path instead. (#15582) Landed from contributor (#28780) Thanks @stubbi, @bsormagec, @unblockedgamesstudio and @vincentkoc.</li>
+<li>Browser/CDP proxy bypass: force direct loopback agent paths and scoped <code>NO_PROXY</code> expansion for localhost CDP HTTP/WS connections when proxy env vars are set, so browser relay/control still works behind global proxy settings. (#31469) Thanks @widingmarcus-cyber.</li>
+<li>Sessions/idle reset correctness: preserve existing <code>updatedAt</code> during inbound metadata-only writes so idle-reset boundaries are not unintentionally refreshed before actual user turns. (#32379) Thanks @romeodiaz.</li>
+<li>Sessions/lock recovery: reclaim orphan legacy same-PID lock files missing <code>starttime</code> when no in-process lock ownership exists, avoiding false lock timeouts after PID reuse while preserving active lock safety checks. (#32081) Thanks @bmendonca3.</li>
+<li>Sessions/store cache invalidation: reload cached session stores when file size changes within the same mtime tick by keying cache validation on a single file-stat snapshot (<code>mtimeMs</code> + <code>sizeBytes</code>), with regression coverage for same-tick rewrites. (#32191) Thanks @jalehman.</li>
+<li>Agents/Subagents <code>sessions_spawn</code>: reject malformed <code>agentId</code> inputs before normalization (for example error-message/path-like strings) to prevent unintended synthetic agent IDs and ghost workspace/session paths; includes strict validation regression coverage. (#31381) Thanks @openperf.</li>
+<li>CLI/installer Node preflight: enforce Node.js <code>v22.12+</code> consistently in both <code>openclaw.mjs</code> runtime bootstrap and installer active-shell checks, with actionable nvm recovery guidance for mismatched shell PATH/defaults. (#32356) Thanks @jasonhargrove.</li>
+<li>Web UI/config form: support SecretInput string-or-secret-ref unions in map <code>additionalProperties</code>, so provider API key fields stay editable instead of being marked unsupported. (#31866) Thanks @ningding97.</li>
+<li>Auto-reply/inline command cleanup: preserve newline structure when stripping inline <code>/status</code> and extracting inline slash commands by collapsing only horizontal whitespace, preventing paragraph flattening in multi-line replies. (#32224) Thanks @scoootscooob.</li>
+<li>Config/raw redaction safety: preserve non-sensitive literals during raw redaction round-trips, scope SecretRef redaction to secret IDs (not structural fields like <code>source</code>/<code>provider</code>), and fall back to structured raw redaction when text replacement cannot restore the original config shape. (#32174) Thanks @bmendonca3.</li>
+<li>Hooks/runtime stability: keep the internal hook handler registry on a <code>globalThis</code> singleton so hook registration/dispatch remains consistent when bundling emits duplicate module copies. (#32292) Thanks @Drickon.</li>
+<li>Hooks/after_tool_call: include embedded session context (<code>sessionKey</code>, <code>agentId</code>) and fire the hook exactly once per tool execution by removing duplicate adapter-path dispatch in embedded runs. (#32201) Thanks @jbeno, @scoootscooob, @vincentkoc.</li>
+<li>Hooks/tool-call correlation: include <code>runId</code> and <code>toolCallId</code> in plugin tool hook payloads/context and scope tool start/adjusted-param tracking by run to prevent cross-run collisions in <code>before_tool_call</code> and <code>after_tool_call</code>. (#32360) Thanks @vincentkoc.</li>
+<li>Plugins/install diagnostics: reject legacy plugin package shapes without <code>openclaw.extensions</code> and return an explicit upgrade hint with troubleshooting docs for repackaging. (#32055) Thanks @liuxiaopai-ai.</li>
+<li>Hooks/plugin context parity: ensure <code>llm_input</code> hooks in embedded attempts receive the same <code>trigger</code> and <code>channelId</code>-aware <code>hookCtx</code> used by the other hook phases, preserving channel/trigger-scoped plugin behavior. (#28623) Thanks @davidrudduck and @vincentkoc.</li>
+<li>Plugins/hardlink install compatibility: allow bundled plugin manifests and entry files to load when installed via hardlink-based package managers (<code>pnpm</code>, <code>bun</code>) while keeping hardlink rejection enabled for non-bundled plugin sources. (#32119) Fixes #28175, #28404, #29455. Thanks @markfietje.</li>
+<li>Cron/session reaper reliability: move cron session reaper sweeps into <code>onTimer</code> <code>finally</code> and keep pruning active even when timer ticks fail early (for example cron store parse failures), preventing stale isolated run sessions from accumulating indefinitely. (#31996) Fixes #31946. Thanks @scoootscooob.</li>
+<li>Cron/HEARTBEAT_OK summary leak: suppress fallback main-session enqueue for heartbeat/internal ack summaries in isolated announce mode so <code>HEARTBEAT_OK</code> noise never appears in user chat while real summaries still forward. (#32093) Thanks @scoootscooob.</li>
+<li>Authentication: classify <code>permission_error</code> as <code>auth_permanent</code> for profile fallback. (#31324) Thanks @Sid-Qin.</li>
+<li>Agents/host edit reliability: treat host edit-tool throws as success only when on-disk post-check confirms replacement likely happened (<code>newText</code> present and <code>oldText</code> absent), preventing false failure reports while avoiding pre-write false positives. (#32383) Thanks @polooooo.</li>
+<li>Plugins/install fallback safety: resolve bare install specs to bundled plugin ids before npm lookup (for example <code>diffs</code> -> bundled <code>@openclaw/diffs</code>), keep npm fallback limited to true package-not-found errors, and continue rejecting non-plugin npm packages that fail manifest validation. (#32096) Thanks @scoootscooob.</li>
+<li>Web UI/inline code copy fidelity: disable forced mid-token wraps on inline <code><code></code> spans so copied UUID/hash/token strings preserve exact content instead of inserting line-break spaces. (#32346) Thanks @hclsys.</li>
+<li>Restart sentinel formatting: avoid duplicate <code>Reason:</code> lines when restart message text already matches <code>stats.reason</code>, keeping restart notifications concise for users and downstream parsers. (#32083) Thanks @velamints2.</li>
+<li>Auto-reply/followup queue: avoid stale callback reuse across idle-window restarts by caching the followup runner only when a drain actually starts, preserving enqueue ordering after empty-finalize paths. (#31902) Thanks @Lanfei.</li>
+<li>Agents/tool-result guard: always clear pending tool-call state on interruptions even when synthetic tool results are disabled, preventing orphaned tool-use transcripts that cause follow-up provider request failures. (#32120) Thanks @jnMetaCode.</li>
+<li>Failover/error classification: treat HTTP <code>529</code> (provider overloaded, common with Anthropic-compatible APIs) as <code>rate_limit</code> so model failover can engage instead of misclassifying the error path. (#31854) Thanks @bugkill3r.</li>
+<li>Logging: use local time for logged timestamps instead of UTC, aligning log output with documented local timezone behavior and avoiding confusion during local diagnostics. (#28434) Thanks @liuy.</li>
+<li>Agents/Subagent announce cleanup: keep completion-message runs pending while descendants settle, add a 30 minute hard-expiry backstop to avoid indefinite pending state, and keep retry bookkeeping resumable across deferred wakes. (#23970) Thanks @tyler6204.</li>
+<li>Secrets/exec resolver timeout defaults: use provider <code>timeoutMs</code> as the default inactivity (<code>noOutputTimeoutMs</code>) watchdog for exec secret providers, preventing premature no-output kills for resolvers that start producing output after 2s. (#32235) Thanks @bmendonca3.</li>
+<li>Auto-reply/reminder guard note suppression: when a turn makes reminder-like commitments but schedules no new cron jobs, suppress the unscheduled-reminder warning note only if an enabled cron already exists for the same session; keep warnings for unrelated sessions, disabled jobs, or unreadable cron store paths. (#32255) Thanks @scoootscooob.</li>
+<li>Cron/isolated announce heartbeat suppression: treat multi-payload runs as skippable when any payload is a heartbeat ack token and no payload has media, preventing internal narration + trailing <code>HEARTBEAT_OK</code> from being delivered to users. (#32131) Thanks @adhishthite.</li>
+<li>Cron/store migration: normalize legacy cron jobs with string <code>schedule</code> and top-level <code>command</code>/<code>timeout</code> fields into canonical schedule/payload/session-target shape on load, preventing schedule-error loops on old persisted stores. (#31926) Thanks @bmendonca3.</li>
+<li>Tests/Windows backup rotation: skip chmod-only backup permission assertions on Windows while retaining compose/rotation/prune coverage across platforms to avoid false CI failures from Windows non-POSIX mode semantics. (#32286) Thanks @jalehman.</li>
+<li>Tests/Subagent announce: set <code>OPENCLAW_TEST_FAST=1</code> before importing <code>subagent-announce</code> format suites so module-level fast-mode constants are captured deterministically on Windows CI, preventing timeout flakes in nested completion announce coverage. (#31370) Thanks @zwffff.</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/v2026.3.2/OpenClaw-2026.3.2.zip" length="23181513" type="application/octet-stream" sparkle:edSignature="THMgkcoMgz2vv5zse3Po3K7l3Or2RhBKurXZIi8iYVXN76yJy1YXAY6kXi6ovD+dbYn68JKYDIKA1Ya78bO7BQ=="/>
+        </item>
         <item>
             <title>2026.3.1</title>
             <pubDate>Mon, 02 Mar 2026 04:40:59 +0000</pubDate>
@@ -140,175 +359,5 @@
 ]]></description>
             <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.3.1/OpenClaw-2026.3.1.zip" length="12804155" type="application/octet-stream" sparkle:edSignature="TF1otD4Vk3pG0iViX7mvix5DQEgAsk4JkSFvH7opjf9aawV16f29SUa2wRmiCFU6HEgyNgnGI/078O+A27eXCA=="/>
         </item>
-        <item>
-            <title>2026.2.15</title>
-            <pubDate>Mon, 16 Feb 2026 05:04:34 +0100</pubDate>
-            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
-            <sparkle:version>202602150</sparkle:version>
-            <sparkle:shortVersionString>2026.2.15</sparkle:shortVersionString>
-            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
-            <description><![CDATA[<h2>OpenClaw 2026.2.15</h2>
-<h3>Changes</h3>
-<ul>
-<li>Discord: unlock rich interactive agent prompts with Components v2 (buttons, selects, modals, and attachment-backed file blocks) so for native interaction through Discord. Thanks @thewilloftheshadow.</li>
-<li>Discord: components v2 UI + embeds passthrough + exec approval UX refinements (CV2 containers, button layout, Discord-forwarding skip). Thanks @thewilloftheshadow.</li>
-<li>Plugins: expose <code>llm_input</code> and <code>llm_output</code> hook payloads so extensions can observe prompt/input context and model output usage details. (#16724) Thanks @SecondThread.</li>
-<li>Subagents: nested sub-agents (sub-sub-agents) with configurable depth. Set <code>agents.defaults.subagents.maxSpawnDepth: 2</code> to allow sub-agents to spawn their own children. Includes <code>maxChildrenPerAgent</code> limit (default 5), depth-aware tool policy, and proper announce chain routing. (#14447) Thanks @tyler6204.</li>
-<li>Slack/Discord/Telegram: add per-channel ack reaction overrides (account/channel-level) to support platform-specific emoji formats. (#17092) Thanks @zerone0x.</li>
-<li>Cron/Gateway: add finished-run webhook delivery toggle (<code>notify</code>) and dedicated webhook auth token support (<code>cron.webhookToken</code>) for outbound cron webhook posts. (#14535) Thanks @advaitpaliwal.</li>
-<li>Channels: deduplicate probe/token resolution base types across core + extensions while preserving per-channel error typing. (#16986) Thanks @iyoda and @thewilloftheshadow.</li>
-</ul>
-<h3>Fixes</h3>
-<ul>
-<li>Security: replace deprecated SHA-1 sandbox configuration hashing with SHA-256 for deterministic sandbox cache identity and recreation checks. Thanks @kexinoh.</li>
-<li>Security/Logging: redact Telegram bot tokens from error messages and uncaught stack traces to prevent accidental secret leakage into logs. Thanks @aether-ai-agent.</li>
-<li>Sandbox/Security: block dangerous sandbox Docker config (bind mounts, host networking, unconfined seccomp/apparmor) to prevent container escape via config injection. Thanks @aether-ai-agent.</li>
-<li>Sandbox: preserve array order in config hashing so order-sensitive Docker/browser settings trigger container recreation correctly. Thanks @kexinoh.</li>
-<li>Gateway/Security: redact sensitive session/path details from <code>status</code> responses for non-admin clients; full details remain available to <code>operator.admin</code>. (#8590) Thanks @fr33d3m0n.</li>
-<li>Gateway/Control UI: preserve requested operator scopes for Control UI bypass modes (<code>allowInsecureAuth</code> / <code>dangerouslyDisableDeviceAuth</code>) when device identity is unavailable, preventing false <code>missing scope</code> failures on authenticated LAN/HTTP operator sessions. (#17682) Thanks @leafbird.</li>
-<li>LINE/Security: fail closed on webhook startup when channel token or channel secret is missing, and treat LINE accounts as configured only when both are present. (#17587) Thanks @davidahmann.</li>
-<li>Skills/Security: restrict <code>download</code> installer <code>targetDir</code> to the per-skill tools directory to prevent arbitrary file writes. Thanks @Adam55A-code.</li>
-<li>Skills/Linux: harden go installer fallback on apt-based systems by handling root/no-sudo environments safely, doing best-effort apt index refresh, and returning actionable errors instead of failing with spawn errors. (#17687) Thanks @mcrolly.</li>
-<li>Web Fetch/Security: cap downloaded response body size before HTML parsing to prevent memory exhaustion from oversized or deeply nested pages. Thanks @xuemian168.</li>
-<li>Config/Gateway: make sensitive-key whitelist suffix matching case-insensitive while preserving <code>passwordFile</code> path exemptions, preventing accidental redaction of non-secret config values like <code>maxTokens</code> and IRC password-file paths. (#16042) Thanks @akramcodez.</li>
-<li>Dev tooling: harden git <code>pre-commit</code> hook against option injection from malicious filenames (for example <code>--force</code>), preventing accidental staging of ignored files. Thanks @mrthankyou.</li>
-<li>Gateway/Agent: reject malformed <code>agent:</code>-prefixed session keys (for example, <code>agent:main</code>) in <code>agent</code> and <code>agent.identity.get</code> instead of silently resolving them to the default agent, preventing accidental cross-session routing. (#15707) Thanks @rodrigouroz.</li>
-<li>Gateway/Chat: harden <code>chat.send</code> inbound message handling by rejecting null bytes, stripping unsafe control characters, and normalizing Unicode to NFC before dispatch. (#8593) Thanks @fr33d3m0n.</li>
-<li>Gateway/Send: return an actionable error when <code>send</code> targets internal-only <code>webchat</code>, guiding callers to use <code>chat.send</code> or a deliverable channel. (#15703) Thanks @rodrigouroz.</li>
-<li>Control UI: prevent stored XSS via assistant name/avatar by removing inline script injection, serving bootstrap config as JSON, and enforcing <code>script-src 'self'</code>. Thanks @Adam55A-code.</li>
-<li>Agents/Security: sanitize workspace paths before embedding into LLM prompts (strip Unicode control/format chars) to prevent instruction injection via malicious directory names. Thanks @aether-ai-agent.</li>
-<li>Agents/Sandbox: clarify system prompt path guidance so sandbox <code>bash/exec</code> uses container paths (for example <code>/workspace</code>) while file tools keep host-bridge mapping, avoiding first-attempt path misses from host-only absolute paths in sandbox command execution. (#17693) Thanks @app/juniordevbot.</li>
-<li>Agents/Context: apply configured model <code>contextWindow</code> overrides after provider discovery so <code>lookupContextTokens()</code> honors operator config values (including discovery-failure paths). (#17404) Thanks @michaelbship and @vignesh07.</li>
-<li>Agents/Context: derive <code>lookupContextTokens()</code> from auth-available model metadata and keep the smallest discovered context window for duplicate model ids, preventing cross-provider cache collisions from overestimating session context limits. (#17586) Thanks @githabideri and @vignesh07.</li>
-<li>Agents/OpenAI: force <code>store=true</code> for direct OpenAI Responses/Codex runs to preserve multi-turn server-side conversation state, while leaving proxy/non-OpenAI endpoints unchanged. (#16803) Thanks @mark9232 and @vignesh07.</li>
-<li>Memory/FTS: make <code>buildFtsQuery</code> Unicode-aware so non-ASCII queries (including CJK) produce keyword tokens instead of falling back to vector-only search. (#17672) Thanks @KinGP5471.</li>
-<li>Auto-reply/Compaction: resolve <code>memory/YYYY-MM-DD.md</code> placeholders with timezone-aware runtime dates and append a <code>Current time:</code> line to memory-flush turns, preventing wrong-year memory filenames without making the system prompt time-variant. (#17603, #17633) Thanks @nicholaspapadam-wq and @vignesh07.</li>
-<li>Agents: return an explicit timeout error reply when an embedded run times out before producing any payloads, preventing silent dropped turns during slow cache-refresh transitions. (#16659) Thanks @liaosvcaf and @vignesh07.</li>
-<li>Group chats: always inject group chat context (name, participants, reply guidance) into the system prompt on every turn, not just the first. Prevents the model from losing awareness of which group it's in and incorrectly using the message tool to send to the same group. (#14447) Thanks @tyler6204.</li>
-<li>Browser/Agents: when browser control service is unavailable, return explicit non-retry guidance (instead of "try again") so models do not loop on repeated browser tool calls until timeout. (#17673) Thanks @austenstone.</li>
-<li>Subagents: use child-run-based deterministic announce idempotency keys across direct and queued delivery paths (with legacy queued-item fallback) to prevent duplicate announce retries without collapsing distinct same-millisecond announces. (#17150) Thanks @widingmarcus-cyber.</li>
-<li>Subagents/Models: preserve <code>agents.defaults.model.fallbacks</code> when subagent sessions carry a model override, so subagent runs fail over to configured fallback models instead of retrying only the overridden primary model.</li>
-<li>Telegram: omit <code>message_thread_id</code> for DM sends/draft previews and keep forum-topic handling (<code>id=1</code> general omitted, non-general kept), preventing DM failures with <code>400 Bad Request: message thread not found</code>. (#10942) Thanks @garnetlyx.</li>
-<li>Telegram: replace inbound <code><media:audio></code> placeholder with successful preflight voice transcript in message body context, preventing placeholder-only prompt bodies for mention-gated voice messages. (#16789) Thanks @Limitless2023.</li>
-<li>Telegram: retry inbound media <code>getFile</code> calls (3 attempts with backoff) and gracefully fall back to placeholder-only processing when retries fail, preventing dropped voice/media messages on transient Telegram network errors. (#16154) Thanks @yinghaosang.</li>
-<li>Telegram: finalize streaming preview replies in place instead of sending a second final message, preventing duplicate Telegram assistant outputs at stream completion. (#17218) Thanks @obviyus.</li>
-<li>Discord: preserve channel session continuity when runtime payloads omit <code>message.channelId</code> by falling back to event/raw <code>channel_id</code> values for routing/session keys, so same-channel messages keep history across turns/restarts. Also align diagnostics so active Discord runs no longer appear as <code>sessionKey=unknown</code>. (#17622) Thanks @shakkernerd.</li>
-<li>Discord: dedupe native skill commands by skill name in multi-agent setups to prevent duplicated slash commands with <code>_2</code> suffixes. (#17365) Thanks @seewhyme.</li>
-<li>Discord: ensure role allowlist matching uses raw role IDs for message routing authorization. Thanks @xinhuagu.</li>
-<li>Web UI/Agents: hide <code>BOOTSTRAP.md</code> in the Agents Files list after onboarding is completed, avoiding confusing missing-file warnings for completed workspaces. (#17491) Thanks @gumadeiras.</li>
-<li>Auto-reply/WhatsApp/TUI/Web: when a final assistant message is <code>NO_REPLY</code> and a messaging tool send succeeded, mirror the delivered messaging-tool text into session-visible assistant output so TUI/Web no longer show <code>NO_REPLY</code> placeholders. (#7010) Thanks @Morrowind-Xie.</li>
-<li>Cron: infer <code>payload.kind="agentTurn"</code> for model-only <code>cron.update</code> payload patches, so partial agent-turn updates do not fail validation when <code>kind</code> is omitted. (#15664) Thanks @rodrigouroz.</li>
-<li>TUI: make searchable-select filtering and highlight rendering ANSI-aware so queries ignore hidden escape codes and no longer corrupt ANSI styling sequences during match highlighting. (#4519) Thanks @bee4come.</li>
-<li>TUI/Windows: coalesce rapid single-line submit bursts in Git Bash into one multiline message as a fallback when bracketed paste is unavailable, preventing pasted multiline text from being split into multiple sends. (#4986) Thanks @adamkane.</li>
-<li>TUI: suppress false <code>(no output)</code> placeholders for non-local empty final events during concurrent runs, preventing external-channel replies from showing empty assistant bubbles while a local run is still streaming. (#5782) Thanks @LagWizard and @vignesh07.</li>
-<li>TUI: preserve copy-sensitive long tokens (URLs/paths/file-like identifiers) during wrapping and overflow sanitization so wrapped output no longer inserts spaces that corrupt copy/paste values. (#17515, #17466, #17505) Thanks @abe238, @trevorpan, and @JasonCry.</li>
-<li>CLI/Build: make legacy daemon CLI compatibility shim generation tolerant of minimal tsdown daemon export sets, while preserving restart/register compatibility aliases and surfacing explicit errors for unavailable legacy daemon commands. Thanks @vignesh07.</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/v2026.2.15/OpenClaw-2026.2.15.zip" length="22896513" type="application/octet-stream" sparkle:edSignature="MLGsd2NeHXFRH1Or0bFQnAjqfuuJDuhl1mvKFIqTQcRvwbeyvOyyLXrqSbmaOgJR3wBQBKLs6jYQ9dQ/3R8RCg=="/>
-        </item>
-        <item>
-            <title>2026.2.26</title>
-            <pubDate>Thu, 26 Feb 2026 23:37:15 +0100</pubDate>
-            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
-            <sparkle:version>202602260</sparkle:version>
-            <sparkle:shortVersionString>2026.2.26</sparkle:shortVersionString>
-            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
-            <description><![CDATA[<h2>OpenClaw 2026.2.26</h2>
-<h3>Changes</h3>
-<ul>
-<li>Highlight: External Secrets Management introduces a full <code>openclaw secrets</code> workflow (<code>audit</code>, <code>configure</code>, <code>apply</code>, <code>reload</code>) with runtime snapshot activation, strict <code>secrets apply</code> target-path validation, safer migration scrubbing, ref-only auth-profile support, and dedicated docs. (#26155) Thanks @joshavant.</li>
-<li>ACP/Thread-bound agents: make ACP agents first-class runtimes for thread sessions with <code>acp</code> spawn/send dispatch integration, acpx backend bridging, lifecycle controls, startup reconciliation, runtime cleanup, and coalesced thread replies. (#23580) thanks @osolmaz.</li>
-<li>Agents/Routing CLI: add <code>openclaw agents bindings</code>, <code>openclaw agents bind</code>, and <code>openclaw agents unbind</code> for account-scoped route management, including channel-only to account-scoped binding upgrades, role-aware binding identity handling, plugin-resolved binding account IDs, and optional account-binding prompts in <code>openclaw channels add</code>. (#27195) thanks @gumadeiras.</li>
-<li>Codex/WebSocket transport: make <code>openai-codex</code> WebSocket-first by default (<code>transport: "auto"</code> with SSE fallback), keep explicit per-model/runtime transport overrides, and add regression coverage + docs for transport selection.</li>
-<li>Onboarding/Plugins: let channel plugins own interactive onboarding flows with optional <code>configureInteractive</code> and <code>configureWhenConfigured</code> hooks while preserving the generic fallback path. (#27191) thanks @gumadeiras.</li>
-<li>Android/Nodes: add Android <code>device</code> capability plus <code>device.status</code> and <code>device.info</code> node commands, including runtime handler wiring and protocol/registry coverage for device status/info payloads. (#27664) Thanks @obviyus.</li>
-<li>Android/Nodes: add <code>notifications.list</code> support on Android nodes and expose <code>nodes notifications_list</code> in agent tooling for listing active device notifications. (#27344) thanks @obviyus.</li>
-<li>Docs/Contributing: add Nimrod Gutman to the maintainer roster in <code>CONTRIBUTING.md</code>. (#27840) Thanks @ngutman.</li>
-</ul>
-<h3>Fixes</h3>
-<ul>
-<li>Telegram/DM allowlist runtime inheritance: enforce <code>dmPolicy: "allowlist"</code> <code>allowFrom</code> requirements using effective account-plus-parent config across account-capable channels (Telegram, Discord, Slack, Signal, iMessage, IRC, BlueBubbles, WhatsApp), and align <code>openclaw doctor</code> checks to the same inheritance logic so DM traffic is not silently dropped after upgrades. (#27936) Thanks @widingmarcus-cyber.</li>
-<li>Delivery queue/recovery backoff: prevent retry starvation by persisting <code>lastAttemptAt</code> on failed sends and deferring recovery retries until each entry's <code>lastAttemptAt + backoff</code> window is eligible, while continuing to recover ready entries behind deferred ones. Landed from contributor PR #27710 by @Jimmy-xuzimo. Thanks @Jimmy-xuzimo.</li>
-<li>Google Chat/Lifecycle: keep Google Chat <code>startAccount</code> pending until abort in webhook mode so startup is no longer interpreted as immediate exit, preventing auto-restart loops and webhook-target churn. (#27384) thanks @junsuwhy.</li>
-<li>Temp dirs/Linux umask: force <code>0700</code> permissions after temp-dir creation and self-heal existing writable temp dirs before trust checks so <code>umask 0002</code> installs no longer crash-loop on startup. Landed from contributor PR #27860 by @stakeswky. (#27853) Thanks @stakeswky.</li>
-<li>Nextcloud Talk/Lifecycle: keep <code>startAccount</code> pending until abort and stop the webhook monitor on shutdown, preventing <code>EADDRINUSE</code> restart loops when the gateway manages account lifecycle. (#27897)</li>
-<li>Microsoft Teams/File uploads: acknowledge <code>fileConsent/invoke</code> immediately (<code>invokeResponse</code> before upload + file card send) so Teams no longer shows false "Something went wrong" timeout banners while upload completion continues asynchronously; includes updated async regression coverage. Landed from contributor PR #27641 by @scz2011.</li>
-<li>Queue/Drain/Cron reliability: harden lane draining with guaranteed <code>draining</code> flag reset on synchronous pump failures, reject new queue enqueues during gateway restart drain windows (instead of silently killing accepted tasks), add <code>/stop</code> queued-backlog cutoff metadata with stale-message skipping (while avoiding cross-session native-stop cutoff bleed), and raise isolated cron <code>agentTurn</code> outer safety timeout to avoid false 10-minute timeout races against longer agent session timeouts. (#27407, #27332, #27427)</li>
-<li>Typing/Main reply pipeline: always mark dispatch idle in <code>agent-runner</code> finalization so typing cleanup runs even when dispatcher <code>onIdle</code> does not fire, preventing stuck typing indicators after run completion. (#27250) Thanks @Sid-Qin.</li>
-<li>Typing/TTL safety net: add max-duration guardrails to shared typing callbacks so stuck lifecycle edges auto-stop typing indicators even when explicit idle/cleanup signals are missed. (#27428) Thanks @Crpdim.</li>
-<li>Typing/Cross-channel leakage: unify run-scoped typing suppression for cross-channel/internal-webchat routes, preserve current inbound origin as embedded run message channel context, harden shared typing keepalive with consecutive-failure circuit breaker edge-case handling, and enforce dispatcher completion/idle waits in extension dispatcher callsites (Feishu, Matrix, Mattermost, MSTeams) so typing indicators always clean up on success/error paths. Related: #27647, #27493, #27598. Supersedes/replaces draft PRs: #27640, #27593, #27540.</li>
-<li>Telegram/sendChatAction 401 handling: add bounded exponential backoff + temporary local typing suppression after repeated unauthorized failures to stop unbounded <code>sendChatAction</code> retry loops that can trigger Telegram abuse enforcement and bot deletion. (#27415) Thanks @widingmarcus-cyber.</li>
-<li>Telegram/Webhook startup: clarify webhook config guidance, allow <code>channels.telegram.webhookPort: 0</code> for ephemeral listener binding, and log both the local listener URL and Telegram-advertised webhook URL with the bound port. (#25732) thanks @huntharo.</li>
-<li>Browser/Chrome extension handshake: bind relay WS message handling before <code>onopen</code> and add non-blocking <code>connect.challenge</code> response handling for gateway-style handshake frames, avoiding stuck <code>…</code> badge states when challenge frames arrive immediately on connect. Landed from contributor PR #22571 by @pandego. (#22553)</li>
-<li>Browser/Extension relay init: dedupe concurrent same-port relay startup with shared in-flight initialization promises so callers await one startup lifecycle and receive consistent success/failure results. Landed from contributor PR #21277 by @HOYALIM. (Related #20688)</li>
-<li>Browser/Fill relay + CLI parity: accept <code>act.fill</code> fields without explicit <code>type</code> by defaulting missing/empty <code>type</code> to <code>text</code> in both browser relay route parsing and <code>openclaw browser fill</code> CLI field parsing, so relay calls no longer fail when the model omits field type metadata. Landed from contributor PR #27662 by @Uface11. (#27296) Thanks @Uface11.</li>
-<li>Feishu/Permission error dispatch: merge sender-name permission notices into the main inbound dispatch so one user message produces one agent turn/reply (instead of a duplicate permission-notice turn), with regression coverage. (#27381) thanks @byungsker.</li>
-<li>Agents/Canvas default node resolution: when multiple connected canvas-capable nodes exist and no single <code>mac-*</code> candidate is selected, default to the first connected candidate instead of failing with <code>node required</code> for implicit-node canvas tool calls. Landed from contributor PR #27444 by @carbaj03. Thanks @carbaj03.</li>
-<li>TUI/stream assembly: preserve streamed text across real tool-boundary drops without keeping stale streamed text when non-text blocks appear only in the final payload. Landed from contributor PR #27711 by @scz2011. (#27674)</li>
-<li>Hooks/Internal <code>message:sent</code>: forward <code>sessionKey</code> on outbound sends from agent delivery, cron isolated delivery, gateway receipt acks, heartbeat sends, session-maintenance warnings, and restart-sentinel recovery so internal <code>message:sent</code> hooks consistently dispatch with session context, including <code>openclaw agent --deliver</code> runs resumed via <code>--session-id</code> (without explicit <code>--session-key</code>). Landed from contributor PR #27584 by @qualiobra. Thanks @qualiobra.</li>
-<li>Pi image-token usage: stop re-injecting history image blocks each turn, process image references from the current prompt only, and prune already-answered user-image blocks in stored history to prevent runaway token growth. (#27602)</li>
-<li>BlueBubbles/SSRF: auto-allowlist the configured <code>serverUrl</code> hostname for attachment fetches so localhost/private-IP BlueBubbles setups are no longer false-blocked by default SSRF checks. Landed from contributor PR #27648 by @lailoo. (#27599) Thanks @taylorhou for reporting.</li>
-<li>Agents/Compaction + onboarding safety: prevent destructive double-compaction by stripping stale assistant usage around compaction boundaries, skipping post-compaction custom metadata writes in the same attempt, and cancelling safeguard compaction when there are no real conversation messages to summarize; harden workspace/bootstrap detection for memory-backed workspaces; and change <code>openclaw onboard --reset</code> default scope to <code>config+creds+sessions</code> (workspace deletion now requires <code>--reset-scope full</code>). (#26458, #27314) Thanks @jaden-clovervnd, @Sid-Qin, and @widingmarcus-cyber for fix direction in #26502, #26529, and #27492.</li>
-<li>NO_REPLY suppression: suppress <code>NO_REPLY</code> before Slack API send and in sub-agent announce completion flow so sentinel text no longer leaks into user channels. Landed from contributor PRs #27529 (by @Sid-Qin) and #27535 (rewritten minimal landing by maintainers). (#27387, #27531)</li>
-<li>Matrix/Group sender identity: preserve sender labels in Matrix group inbound prompt text (<code>BodyForAgent</code>) for both channel and threaded messages, and align group envelopes with shared inbound sender-prefix formatting so first-person requests resolve against the current sender. (#27401) thanks @koushikxd.</li>
-<li>Auto-reply/Streaming: suppress only exact <code>NO_REPLY</code> final replies while still filtering streaming partial sentinel fragments (<code>NO_</code>, <code>NO_RE</code>, <code>HEARTBEAT_...</code>) so substantive replies ending with <code>NO_REPLY</code> are delivered and partial silent tokens do not leak during streaming. (#19576) Thanks @aldoeliacim.</li>
-<li>Auto-reply/Inbound metadata: add a readable <code>timestamp</code> field to conversation info and ignore invalid/out-of-range timestamp values so prompt assembly never crashes on malformed timestamp inputs. (#17017) thanks @liuy.</li>
-<li>Typing/Run completion race: prevent post-run keepalive ticks from re-triggering typing callbacks by guarding <code>triggerTyping()</code> with <code>runComplete</code>, with regression coverage for no-restart behavior during run-complete/dispatch-idle boundaries. (#27413) Thanks @widingmarcus-cyber.</li>
-<li>Typing/Dispatch idle: force typing cleanup when <code>markDispatchIdle</code> never arrives after run completion, avoiding leaked typing keepalive loops in cron/announce edges. Landed from contributor PR #27541 by @Sid-Qin. (#27493)</li>
-<li>Telegram/Inline buttons: allow callback-query button handling in groups (including <code>/models</code> follow-up buttons) when group policy authorizes the sender, by removing the redundant callback allowlist gate that blocked open-policy groups. (#27343) Thanks @GodsBoy.</li>
-<li>Telegram/Streaming preview: when finalizing without an existing preview message, prime pending preview text with final answer before stop-flush so users do not briefly see stale 1-2 word fragments (for example <code>no</code> before <code>no problem</code>). (#27449) Thanks @emanuelst for the original fix direction in #19673.</li>
-<li>Browser/Extension relay CORS: handle <code>/json*</code> <code>OPTIONS</code> preflight before auth checks, allow Chrome extension origins, and return extension-origin CORS headers on relay HTTP responses so extension token validation no longer fails cross-origin. Landed from contributor PR #23962 by @miloudbelarebia. (#23842)</li>
-<li>Browser/Extension relay auth: allow <code>?token=</code> query-param auth on relay <code>/json*</code> endpoints (consistent with relay WebSocket auth) so curl/devtools-style <code>/json/version</code> and <code>/json/list</code> probes work without requiring custom headers. Landed from contributor PR #26015 by @Sid-Qin. (#25928)</li>
-<li>Browser/Extension relay shutdown: flush pending extension-request timers/rejections during relay <code>stop()</code> before socket/server teardown so in-flight extension waits do not survive shutdown windows. Landed from contributor PR #24142 by @kevinWangSheng.</li>
-<li>Browser/Extension relay reconnect resilience: keep CDP clients alive across brief MV3 extension disconnect windows, wait briefly for extension reconnect before failing in-flight CDP commands, and only tear down relay target/client state after reconnect grace expires. Landed from contributor PR #27617 by @davidemanuelDEV.</li>
-<li>Browser/Route decode hardening: guard malformed percent-encoding in relay target action routes and browser route-param decoding so crafted <code>%</code> paths return <code>400</code> instead of crashing/unhandled URI decode failures. Landed from contributor PR #11880 by @Yida-Dev.</li>
-<li>Feishu/Inbound message metadata: include inbound <code>message_id</code> in <code>BodyForAgent</code> on a dedicated metadata line so agents can reliably correlate and act on media/message operations that require message IDs, with regression coverage. (#27253) thanks @xss925175263.</li>
-<li>Feishu/Doc tools: route <code>feishu_doc</code> and <code>feishu_app_scopes</code> through the active agent account context (with explicit <code>accountId</code> override support) so multi-account agents no longer default to the first configured app, with regression coverage for context routing and explicit override behavior. (#27338) thanks @AaronL725.</li>
-<li>LINE/Inline directives auth: gate directive parsing (<code>/model</code>, <code>/think</code>, <code>/verbose</code>, <code>/reasoning</code>, <code>/queue</code>) on resolved authorization (<code>command.isAuthorizedSender</code>) so <code>commands.allowFrom</code>-authorized LINE senders are not silently stripped when raw <code>CommandAuthorized</code> is unset. Landed from contributor PR #27248 by @kevinWangSheng. (#27240)</li>
-<li>Onboarding/Gateway: seed default Control UI <code>allowedOrigins</code> for non-loopback binds during onboarding (<code>localhost</code>/<code>127.0.0.1</code> plus custom bind host) so fresh non-loopback setups do not fail startup due to missing origin policy. (#26157) thanks @stakeswky.</li>
-<li>Docker/GCP onboarding: reduce first-build OOM risk by capping Node heap during <code>pnpm install</code>, reuse existing gateway token during <code>docker-setup.sh</code> reruns so <code>.env</code> stays aligned with config, auto-bootstrap Control UI allowed origins for non-loopback Docker binds, and add GCP docs guidance for tokenized dashboard links + pairing recovery commands. (#26253) Thanks @pandego.</li>
-<li>CLI/Gateway <code>--force</code> in non-root Docker: recover from <code>lsof</code> permission failures (<code>EACCES</code>/<code>EPERM</code>) by falling back to <code>fuser</code> kill + probe-based port checks, so <code>openclaw gateway --force</code> works for default container <code>node</code> user flows. (#27941)</li>
-<li>Gateway/Bind visibility: emit a startup warning when binding to non-loopback addresses so operators get explicit exposure guidance in runtime logs. (#25397) thanks @let5sne.</li>
-<li>Sessions cleanup/Doctor: add <code>openclaw sessions cleanup --fix-missing</code> to prune store entries whose transcript files are missing, including doctor guidance and CLI coverage. Landed from contributor PR #27508 by @Sid-Qin. (#27422)</li>
-<li>Doctor/State integrity: ignore metadata-only slash routing sessions when checking recent missing transcripts so <code>openclaw doctor</code> no longer reports false-positive transcript-missing warnings for <code>*:slash:*</code> keys. (#27375) thanks @gumadeiras.</li>
-<li>CLI/Gateway status: force local <code>gateway status</code> probe host to <code>127.0.0.1</code> for <code>bind=lan</code> so co-located probes do not trip non-loopback plaintext WebSocket checks. (#26997) thanks @chikko80.</li>
-<li>CLI/Gateway auth: align <code>gateway run --auth</code> parsing/help text with supported gateway auth modes by accepting <code>none</code> and <code>trusted-proxy</code> (in addition to <code>token</code>/<code>password</code>) for CLI overrides. (#27469) thanks @s1korrrr.</li>
-<li>CLI/Daemon status TLS probe: use <code>wss://</code> and forward local TLS certificate fingerprint for TLS-enabled gateway daemon probes so <code>openclaw daemon status</code> works with <code>gateway.bind=lan</code> + <code>gateway.tls.enabled=true</code>. (#24234) thanks @liuy.</li>
-<li>Podman/Default bind: change <code>run-openclaw-podman.sh</code> default gateway bind from <code>lan</code> to <code>loopback</code> and document explicit LAN opt-in with Control UI origin configuration. (#27491) thanks @robbyczgw-cla.</li>
-<li>Daemon/macOS launchd: forward proxy env vars into supervised service environments, keep LaunchAgent <code>KeepAlive=true</code> semantics, and harden restart sequencing to <code>print -> bootout -> wait old pid exit -> bootstrap -> kickstart</code>. (#27276) thanks @frankekn.</li>
-<li>Gateway/macOS restart-loop hardening: detect OpenClaw-managed supervisor markers during SIGUSR1 restart handoff, clean stale gateway PIDs before <code>/restart</code> launchctl/systemctl triggers, and set LaunchAgent <code>ThrottleInterval=60</code> to bound launchd retry storms during lock-release races. Landed from contributor PRs #27655 (@taw0002), #27448 (@Sid-Qin), and #27650 (@kevinWangSheng). (#27605, #27590, #26904, #26736)</li>
-<li>Models/MiniMax auth header defaults: set <code>authHeader: true</code> for both onboarding-generated MiniMax API providers and implicit built-in MiniMax (<code>minimax</code>, <code>minimax-portal</code>) provider templates so first requests no longer fail with MiniMax <code>401 authentication_error</code> due to missing <code>Authorization</code> header. Landed from contributor PRs #27622 by @riccoyuanft and #27631 by @kevinWangSheng. (#27600, #15303)</li>
-<li>Auth/Auth profiles: normalize <code>auth-profiles.json</code> alias fields (<code>mode -> type</code>, <code>apiKey -> key</code>) before credential validation so entries copied from <code>openclaw.json</code> auth examples are no longer silently dropped. (#26950) thanks @byungsker.</li>
-<li>Models/Profile suffix parsing: centralize trailing <code>@profile</code> parsing and only treat <code>@</code> as a profile separator when it appears after the final <code>/</code>, preserving model IDs like <code>openai/@cf/...</code> and <code>openrouter/@preset/...</code> across <code>/model</code> directive parsing and allowlist model resolution, with regression coverage.</li>
-<li>Models/OpenAI Codex config schema parity: accept <code>openai-codex-responses</code> in the config model API schema and TypeScript <code>ModelApi</code> union, with regression coverage for config validation. Landed from contributor PR #27501 by @AytuncYildizli. Thanks @AytuncYildizli.</li>
-<li>Agents/Models config: preserve agent-level provider <code>apiKey</code> and <code>baseUrl</code> during merge-mode <code>models.json</code> updates when agent values are present. (#27293) thanks @Sid-Qin.</li>
-<li>Azure OpenAI Responses: force <code>store=true</code> for <code>azure-openai-responses</code> direct responses API calls to avoid multi-turn 400 failures. Landed from contributor PR #27499 by @polarbear-Yang. (#27497)</li>
-<li>Security/Node exec approvals: require structured <code>commandArgv</code> approvals for <code>host=node</code>, enforce versioned <code>systemRunBindingV1</code> matching for argv/cwd/session/agent/env context with fail-closed behavior on missing/mismatched bindings, and add <code>GIT_EXTERNAL_DIFF</code> to blocked host env keys. This ships in the next npm release (<code>2026.2.26</code>). Thanks @tdjackey for reporting.</li>
-<li>Security/Plugin channel HTTP auth: normalize protected <code>/api/channels</code> path checks against canonicalized request paths (case + percent-decoding + slash normalization), resolve encoded dot-segment traversal variants, and fail closed on malformed <code>%</code>-encoded channel prefixes so alternate-path variants cannot bypass gateway auth. This ships in the next npm release (<code>2026.2.26</code>). Thanks @zpbrent for reporting.</li>
-<li>Security/Gateway node pairing: pin paired-device <code>platform</code>/<code>deviceFamily</code> metadata across reconnects and bind those fields into device-auth signatures, so reconnect metadata spoofing cannot expand node command allowlists without explicit repair pairing. This ships in the next npm release (<code>2026.2.26</code>). Thanks @76embiid21 for reporting.</li>
-<li>Security/Sandbox path alias guard: reject broken symlink targets by resolving through existing ancestors and failing closed on out-of-root targets, preventing workspace-only <code>apply_patch</code> writes from escaping sandbox/workspace boundaries via dangling symlinks. This ships in the next npm release (<code>2026.2.26</code>). Thanks @tdjackey for reporting.</li>
-<li>Security/Workspace FS boundary aliases: harden canonical boundary resolution for non-existent-leaf symlink aliases while preserving valid in-root aliases, preventing first-write workspace escapes via out-of-root symlink targets. This ships in the next npm release (<code>2026.2.26</code>). Thanks @tdjackey for reporting.</li>
-<li>Security/Config includes: harden <code>$include</code> file loading with verified-open reads, reject hardlinked include aliases, and enforce include file-size guardrails so config include resolution remains bounded to trusted in-root files. This ships in the next npm release (<code>2026.2.26</code>). Thanks @zpbrent for reporting.</li>
-<li>Security/Node exec approvals hardening: freeze immutable approval-time execution plans (<code>argv</code>/<code>cwd</code>/<code>agentId</code>/<code>sessionKey</code>) via <code>system.run.prepare</code>, enforce those canonical plan values during approval forwarding/execution, and reject mutable parent-symlink cwd paths during approval-plan building to prevent approval bypass via symlink rebind. This ships in the next npm release (<code>2026.2.26</code>). Thanks @tdjackey for reporting.</li>
-<li>Security/Microsoft Teams media fetch: route Graph message/hosted-content/attachment fetches and auth-scope fallback attachment downloads through shared SSRF-guarded fetch paths, and centralize hostname-suffix allowlist policy helpers in the plugin SDK to remove channel/plugin drift. This ships in the next npm release (<code>2026.2.26</code>). Thanks @tdjackey for reporting.</li>
-<li>Security/Voice Call (Twilio): bind webhook replay + manager dedupe identity to authenticated request material, remove unsigned <code>i-twilio-idempotency-token</code> trust from replay/dedupe keys, and thread verified request identity through provider parse flow to harden cross-provider event dedupe. This ships in the next npm release (<code>2026.2.26</code>). Thanks @tdjackey for reporting.</li>
-<li>Security/Exec approvals forwarding: prefer turn-source channel/account/thread metadata when resolving approval delivery targets so stale session routes do not misroute approval prompts.</li>
-<li>Security/Pairing multi-account isolation: enforce account-scoped pairing allowlists and pending-request storage across core + extension message channels while preserving channel-scoped defaults for the default account. This ships in the next npm release (<code>2026.2.26</code>). Thanks @tdjackey for reporting and @gumadeiras for implementation.</li>
-<li>Config/Plugins entries: treat unknown <code>plugins.entries.*</code> ids as startup warnings (ignored stale keys) instead of hard validation failures that can crash-loop gateway boot. Landed from contributor PR #27506 by @Sid-Qin. (#27455)</li>
-<li>Telegram native commands: degrade command registration on <code>BOT_COMMANDS_TOO_MUCH</code> by retrying with fewer commands instead of crash-looping startup sync. Landed from contributor PR #27512 by @Sid-Qin. (#27456)</li>
-<li>Web tools/Proxy: route <code>web_search</code> provider HTTP calls (Brave, Perplexity, xAI, Gemini, Kimi), redirect resolution, and <code>web_fetch</code> through a shared proxy-aware SSRF guard path so gateway installs behind <code>HTTP_PROXY</code>/<code>HTTPS_PROXY</code>/<code>ALL_PROXY</code> no longer fail with transport <code>fetch failed</code> errors. (#27430) thanks @kevinWangSheng.</li>
-<li>Android/Node invoke: remove native gateway WebSocket <code>Origin</code> header to avoid false origin rejections, unify invoke command registry/policy/error parsing paths, and keep command availability checks centralized to reduce dispatcher/advertisement drift. (#27257) Thanks @obviyus.</li>
-<li>Gateway shared-auth scopes: preserve requested operator scopes for shared-token clients when device identity is unavailable, instead of clearing scopes during auth handling. Landed from contributor PR #27498 by @kevinWangSheng. (#27494)</li>
-<li>Cron/Hooks isolated routing: preserve canonical <code>agent:*</code> session keys in isolated runs so already-qualified keys are not double-prefixed (for example <code>agent:main:main</code> no longer becomes <code>agent:main:agent:main:main</code>). Landed from contributor PR #27333 by @MaheshBhushan. (#27289, #27282)</li>
-<li>Channels/Multi-account config: when adding a non-default channel account to a single-account top-level channel setup, move existing account-scoped top-level single-account values into <code>channels.<channel>.accounts.default</code> before writing the new account so the original account keeps working without duplicated account values at channel root; <code>openclaw doctor --fix</code> now repairs previously mixed channel account shapes the same way. (#27334) thanks @gumadeiras.</li>
-<li>iOS/Talk mode: stop injecting the voice directive hint into iOS Talk prompts and remove the Voice Directive Hint setting, reducing model bias toward tool-style TTS directives and keeping relay responses text-first by default. (#27543) thanks @ngutman.</li>
-<li>CI/Windows: shard the Windows <code>checks-windows</code> test lane into two matrix jobs and honor explicit shard index overrides in <code>scripts/test-parallel.mjs</code> to reduce CI critical-path wall time. (#27234) Thanks @joshavant.</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/v2026.2.26/OpenClaw-2026.2.26.zip" length="12796628" type="application/octet-stream" sparkle:edSignature="qqVJfkQS9Q4LCTlGtOyXzORWZWWnOkWyiJ6DVX27oPF8aeUlUyfHrmb51sFiNjSuCJC2xmJW1Mi1CAHl/I1pCw=="/>
-        </item>
     </channel>
 </rss>

apps/ios/ActivityWidget/Assets.xcassets/Contents.json

@@ -0,0 +1,6 @@
+{
+  "info" : {
+    "author" : "xcode",
+    "version" : 1
+  }
+}

apps/ios/ActivityWidget/Info.plist

@@ -0,0 +1,31 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+	<key>CFBundleDevelopmentRegion</key>
+	<string>$(DEVELOPMENT_LANGUAGE)</string>
+	<key>CFBundleDisplayName</key>
+	<string>OpenClaw Activity</string>
+	<key>CFBundleExecutable</key>
+	<string>$(EXECUTABLE_NAME)</string>
+	<key>CFBundleIdentifier</key>
+	<string>$(PRODUCT_BUNDLE_IDENTIFIER)</string>
+	<key>CFBundleInfoDictionaryVersion</key>
+	<string>6.0</string>
+	<key>CFBundleName</key>
+	<string>$(PRODUCT_NAME)</string>
+	<key>CFBundlePackageType</key>
+	<string>XPC!</string>
+	<key>CFBundleShortVersionString</key>
+	<string>2026.3.2</string>
+	<key>CFBundleVersion</key>
+	<string>20260301</string>
+	<key>NSExtension</key>
+	<dict>
+		<key>NSExtensionPointIdentifier</key>
+		<string>com.apple.widgetkit-extension</string>
+	</dict>
+	<key>NSSupportsLiveActivities</key>
+	<true/>
+</dict>
+</plist>

apps/ios/ActivityWidget/OpenClawActivityWidgetBundle.swift

@@ -0,0 +1,9 @@
+import SwiftUI
+import WidgetKit
+
+@main
+struct OpenClawActivityWidgetBundle: WidgetBundle {
+    var body: some Widget {
+        OpenClawLiveActivity()
+    }
+}

apps/ios/ActivityWidget/OpenClawLiveActivity.swift

@@ -0,0 +1,84 @@
+import ActivityKit
+import SwiftUI
+import WidgetKit
+
+struct OpenClawLiveActivity: Widget {
+    var body: some WidgetConfiguration {
+        ActivityConfiguration(for: OpenClawActivityAttributes.self) { context in
+            lockScreenView(context: context)
+        } dynamicIsland: { context in
+            DynamicIsland {
+                DynamicIslandExpandedRegion(.leading) {
+                    statusDot(state: context.state)
+                }
+                DynamicIslandExpandedRegion(.center) {
+                    Text(context.state.statusText)
+                        .font(.subheadline)
+                        .lineLimit(1)
+                }
+                DynamicIslandExpandedRegion(.trailing) {
+                    trailingView(state: context.state)
+                }
+            } compactLeading: {
+                statusDot(state: context.state)
+            } compactTrailing: {
+                Text(context.state.statusText)
+                    .font(.caption2)
+                    .lineLimit(1)
+                    .frame(maxWidth: 64)
+            } minimal: {
+                statusDot(state: context.state)
+            }
+        }
+    }
+
+    @ViewBuilder
+    private func lockScreenView(context: ActivityViewContext<OpenClawActivityAttributes>) -> some View {
+        HStack(spacing: 8) {
+            statusDot(state: context.state)
+                .frame(width: 10, height: 10)
+            VStack(alignment: .leading, spacing: 2) {
+                Text("OpenClaw")
+                    .font(.subheadline.bold())
+                Text(context.state.statusText)
+                    .font(.caption)
+                    .foregroundStyle(.secondary)
+            }
+            Spacer()
+            trailingView(state: context.state)
+        }
+        .padding(.vertical, 4)
+    }
+
+    @ViewBuilder
+    private func trailingView(state: OpenClawActivityAttributes.ContentState) -> some View {
+        if state.isConnecting {
+            ProgressView().controlSize(.small)
+        } else if state.isDisconnected {
+            Image(systemName: "wifi.slash")
+                .foregroundStyle(.red)
+        } else if state.isIdle {
+            Image(systemName: "antenna.radiowaves.left.and.right")
+                .foregroundStyle(.green)
+        } else {
+            Text(state.startedAt, style: .timer)
+                .font(.caption)
+                .monospacedDigit()
+                .foregroundStyle(.secondary)
+        }
+    }
+
+    @ViewBuilder
+    private func statusDot(state: OpenClawActivityAttributes.ContentState) -> some View {
+        Circle()
+            .fill(dotColor(state: state))
+            .frame(width: 6, height: 6)
+    }
+
+    private func dotColor(state: OpenClawActivityAttributes.ContentState) -> Color {
+        if state.isDisconnected { return .red }
+        if state.isConnecting { return .gray }
+        if state.isIdle { return .green }
+        return .blue
+    }
+}

apps/ios/Config/Signing.xcconfig

@@ -4,6 +4,7 @@ OPENCLAW_IOS_SELECTED_TEAM = $(OPENCLAW_IOS_DEFAULT_TEAM)
 OPENCLAW_APP_BUNDLE_ID = ai.openclaw.ios
 OPENCLAW_WATCH_APP_BUNDLE_ID = ai.openclaw.ios.watchkitapp
 OPENCLAW_WATCH_EXTENSION_BUNDLE_ID = ai.openclaw.ios.watchkitapp.extension
+OPENCLAW_ACTIVITY_WIDGET_BUNDLE_ID = ai.openclaw.ios.activitywidget
 
 // Local contributors can override this by running scripts/ios-configure-signing.sh.
 // Keep include after defaults: xcconfig is evaluated top-to-bottom.

apps/ios/Sources/Camera/CameraController.swift

@@ -1,6 +1,7 @@
 import AVFoundation
 import OpenClawKit
 import Foundation
+import os
 
 actor CameraController {
     struct CameraDeviceInfo: Codable, Sendable {
@@ -120,7 +121,8 @@ actor CameraController {
                 Self.pickCamera(facing: preferFrontCamera ? .front : .back, deviceId: deviceId)
             },
             cameraUnavailableError: CameraError.cameraUnavailable,
-            mapSetupError: Self.mapMovieSetupError) { output in
+            mapSetupError: Self.mapMovieSetupError,
+            operation: { output in
                 var delegate: MovieFileDelegate?
                 let recordedURL: URL = try await withCheckedThrowingContinuation { cont in
                     let d = MovieFileDelegate(cont)
@@ -131,7 +133,7 @@ actor CameraController {
                 // Transcode .mov -> .mp4 for easier downstream handling.
                 try await Self.exportToMP4(inputURL: recordedURL, outputURL: mp4URL)
                 return try Data(contentsOf: mp4URL)
-            }
+            })
         return (
             format: format.rawValue,
             base64: data.base64EncodedString(),
@@ -259,7 +261,7 @@ actor CameraController {
 
 private final class PhotoCaptureDelegate: NSObject, AVCapturePhotoCaptureDelegate {
     private let continuation: CheckedContinuation<Data, Error>
-    private var didResume = false
+    private let resumed = OSAllocatedUnfairLock(initialState: false)
 
     init(_ continuation: CheckedContinuation<Data, Error>) {
         self.continuation = continuation
@@ -270,8 +272,12 @@ private final class PhotoCaptureDelegate: NSObject, AVCapturePhotoCaptureDelegat
         didFinishProcessingPhoto photo: AVCapturePhoto,
         error: Error?
     ) {
-        guard !self.didResume else { return }
-        self.didResume = true
+        let alreadyResumed = self.resumed.withLock { old in
+            let was = old
+            old = true
+            return was
+        }
+        guard !alreadyResumed else { return }
 
         if let error {
             self.continuation.resume(throwing: error)
@@ -300,15 +306,19 @@ private final class PhotoCaptureDelegate: NSObject, AVCapturePhotoCaptureDelegat
         error: Error?
     ) {
         guard let error else { return }
-        guard !self.didResume else { return }
-        self.didResume = true
+        let alreadyResumed = self.resumed.withLock { old in
+            let was = old
+            old = true
+            return was
+        }
+        guard !alreadyResumed else { return }
         self.continuation.resume(throwing: error)
     }
 }
 
 private final class MovieFileDelegate: NSObject, AVCaptureFileOutputRecordingDelegate {
     private let continuation: CheckedContinuation<URL, Error>
-    private var didResume = false
+    private let resumed = OSAllocatedUnfairLock(initialState: false)
 
     init(_ continuation: CheckedContinuation<URL, Error>) {
         self.continuation = continuation
@@ -320,8 +330,12 @@ private final class MovieFileDelegate: NSObject, AVCaptureFileOutputRecordingDel
         from connections: [AVCaptureConnection],
         error: Error?)
     {
-        guard !self.didResume else { return }
-        self.didResume = true
+        let alreadyResumed = self.resumed.withLock { old in
+            let was = old
+            old = true
+            return was
+        }
+        guard !alreadyResumed else { return }
 
         if let error {
             let ns = error as NSError

apps/ios/Sources/Gateway/GatewayConnectionController.swift

@@ -9,6 +9,7 @@ import Darwin
 import OpenClawKit
 import Network
 import Observation
+import os
 import Photos
 import ReplayKit
 import Security
@@ -990,12 +991,16 @@ extension GatewayConnectionController {
 #endif
 
 private final class GatewayTLSFingerprintProbe: NSObject, URLSessionDelegate, @unchecked Sendable {
+    private struct ProbeState {
+        var didFinish = false
+        var session: URLSession?
+        var task: URLSessionWebSocketTask?
+    }
+
     private let url: URL
     private let timeoutSeconds: Double
     private let onComplete: (String?) -> Void
-    private var didFinish = false
-    private var session: URLSession?
-    private var task: URLSessionWebSocketTask?
+    private let state = OSAllocatedUnfairLock(initialState: ProbeState())
 
     init(url: URL, timeoutSeconds: Double, onComplete: @escaping (String?) -> Void) {
         self.url = url
@@ -1008,9 +1013,11 @@ private final class GatewayTLSFingerprintProbe: NSObject, URLSessionDelegate, @u
         config.timeoutIntervalForRequest = self.timeoutSeconds
         config.timeoutIntervalForResource = self.timeoutSeconds
         let session = URLSession(configuration: config, delegate: self, delegateQueue: nil)
-        self.session = session
         let task = session.webSocketTask(with: self.url)
-        self.task = task
+        self.state.withLock { s in
+            s.session = session
+            s.task = task
+        }
         task.resume()
 
         DispatchQueue.global(qos: .utility).asyncAfter(deadline: .now() + self.timeoutSeconds) { [weak self] in
@@ -1036,12 +1043,18 @@ private final class GatewayTLSFingerprintProbe: NSObject, URLSessionDelegate, @u
     }
 
     private func finish(_ fingerprint: String?) {
-        objc_sync_enter(self)
-        defer { objc_sync_exit(self) }
-        guard !self.didFinish else { return }
-        self.didFinish = true
-        self.task?.cancel(with: .goingAway, reason: nil)
-        self.session?.invalidateAndCancel()
+        let (shouldComplete, taskToCancel, sessionToInvalidate) = self.state.withLock { s -> (Bool, URLSessionWebSocketTask?, URLSession?) in
+            guard !s.didFinish else { return (false, nil, nil) }
+            s.didFinish = true
+            let task = s.task
+            let session = s.session
+            s.task = nil
+            s.session = nil
+            return (true, task, session)
+        }
+        guard shouldComplete else { return }
+        taskToCancel?.cancel(with: .goingAway, reason: nil)
+        sessionToInvalidate?.invalidateAndCancel()
         self.onComplete(fingerprint)
     }
 

apps/ios/Sources/Gateway/GatewaySettingsStore.swift

@@ -25,6 +25,7 @@ enum GatewaySettingsStore {
     private static let instanceIdAccount = "instanceId"
     private static let preferredGatewayStableIDAccount = "preferredStableID"
     private static let lastDiscoveredGatewayStableIDAccount = "lastDiscoveredStableID"
+    private static let lastGatewayConnectionAccount = "lastConnection"
     private static let talkProviderApiKeyAccountPrefix = "provider.apiKey."
 
     static func bootstrapPersistence() {
@@ -140,11 +141,20 @@ enum GatewaySettingsStore {
         }
     }
 
-    private enum LastGatewayKind: String {
+    private enum LastGatewayKind: String, Codable {
         case manual
         case discovered
     }
 
+    /// JSON-serializable envelope stored as a single Keychain entry.
+    private struct LastGatewayConnectionData: Codable {
+        var kind: LastGatewayKind
+        var stableID: String
+        var useTLS: Bool
+        var host: String?
+        var port: Int?
+    }
+
     static func loadTalkProviderApiKey(provider: String) -> String? {
         guard let providerId = self.normalizedTalkProviderID(provider) else { return nil }
         let account = self.talkProviderApiKeyAccount(providerId: providerId)
@@ -168,47 +178,93 @@ enum GatewaySettingsStore {
     }
 
     static func saveLastGatewayConnectionManual(host: String, port: Int, useTLS: Bool, stableID: String) {
-        let defaults = UserDefaults.standard
-        defaults.set(LastGatewayKind.manual.rawValue, forKey: self.lastGatewayKindDefaultsKey)
-        defaults.set(host, forKey: self.lastGatewayHostDefaultsKey)
-        defaults.set(port, forKey: self.lastGatewayPortDefaultsKey)
-        defaults.set(useTLS, forKey: self.lastGatewayTlsDefaultsKey)
-        defaults.set(stableID, forKey: self.lastGatewayStableIDDefaultsKey)
+        let payload = LastGatewayConnectionData(
+            kind: .manual, stableID: stableID, useTLS: useTLS, host: host, port: port)
+        self.saveLastGatewayConnectionData(payload)
     }
 
     static func saveLastGatewayConnectionDiscovered(stableID: String, useTLS: Bool) {
-        let defaults = UserDefaults.standard
-        defaults.set(LastGatewayKind.discovered.rawValue, forKey: self.lastGatewayKindDefaultsKey)
-        defaults.removeObject(forKey: self.lastGatewayHostDefaultsKey)
-        defaults.removeObject(forKey: self.lastGatewayPortDefaultsKey)
-        defaults.set(useTLS, forKey: self.lastGatewayTlsDefaultsKey)
-        defaults.set(stableID, forKey: self.lastGatewayStableIDDefaultsKey)
+        let payload = LastGatewayConnectionData(
+            kind: .discovered, stableID: stableID, useTLS: useTLS)
+        self.saveLastGatewayConnectionData(payload)
     }
 
     static func loadLastGatewayConnection() -> LastGatewayConnection? {
+        // Migrate legacy UserDefaults entries on first access.
+        self.migrateLastGatewayFromUserDefaultsIfNeeded()
+
+        guard let json = KeychainStore.loadString(
+            service: self.gatewayService, account: self.lastGatewayConnectionAccount),
+            let data = json.data(using: .utf8),
+            let stored = try? JSONDecoder().decode(LastGatewayConnectionData.self, from: data)
+        else { return nil }
+
+        let stableID = stored.stableID.trimmingCharacters(in: .whitespacesAndNewlines)
+        guard !stableID.isEmpty else { return nil }
+
+        if stored.kind == .discovered {
+            return .discovered(stableID: stableID, useTLS: stored.useTLS)
+        }
+
+        let host = (stored.host ?? "").trimmingCharacters(in: .whitespacesAndNewlines)
+        let port = stored.port ?? 0
+        guard !host.isEmpty, port > 0, port <= 65535 else { return nil }
+        return .manual(host: host, port: port, useTLS: stored.useTLS, stableID: stableID)
+    }
+
+    static func clearLastGatewayConnection(defaults: UserDefaults = .standard) {
+        _ = KeychainStore.delete(
+            service: self.gatewayService, account: self.lastGatewayConnectionAccount)
+        // Clean up any legacy UserDefaults entries.
+        defaults.removeObject(forKey: self.lastGatewayKindDefaultsKey)
+        defaults.removeObject(forKey: self.lastGatewayHostDefaultsKey)
+        defaults.removeObject(forKey: self.lastGatewayPortDefaultsKey)
+        defaults.removeObject(forKey: self.lastGatewayTlsDefaultsKey)
+        defaults.removeObject(forKey: self.lastGatewayStableIDDefaultsKey)
+    }
+
+    @discardableResult
+    private static func saveLastGatewayConnectionData(_ payload: LastGatewayConnectionData) -> Bool {
+        guard let data = try? JSONEncoder().encode(payload),
+              let json = String(data: data, encoding: .utf8)
+        else { return false }
+        return KeychainStore.saveString(
+            json, service: self.gatewayService, account: self.lastGatewayConnectionAccount)
+    }
+
+    /// Migrate legacy UserDefaults gateway.last.* keys into a single Keychain entry.
+    private static func migrateLastGatewayFromUserDefaultsIfNeeded() {
         let defaults = UserDefaults.standard
         let stableID = defaults.string(forKey: self.lastGatewayStableIDDefaultsKey)?
             .trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
-        guard !stableID.isEmpty else { return nil }
+        guard !stableID.isEmpty else { return }
+
+        // Already migrated if Keychain entry exists.
+        if KeychainStore.loadString(
+            service: self.gatewayService, account: self.lastGatewayConnectionAccount) != nil
+        {
+            // Clean up legacy keys.
+            self.removeLastGatewayDefaults(defaults)
+            return
+        }
+
         let useTLS = defaults.bool(forKey: self.lastGatewayTlsDefaultsKey)
         let kindRaw = defaults.string(forKey: self.lastGatewayKindDefaultsKey)?
             .trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
         let kind = LastGatewayKind(rawValue: kindRaw) ?? .manual
-
-        if kind == .discovered {
-            return .discovered(stableID: stableID, useTLS: useTLS)
-        }
-
         let host = defaults.string(forKey: self.lastGatewayHostDefaultsKey)?
-            .trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
-        let port = defaults.integer(forKey: self.lastGatewayPortDefaultsKey)
+            .trimmingCharacters(in: .whitespacesAndNewlines)
+        let port = defaults.object(forKey: self.lastGatewayPortDefaultsKey) as? Int
 
-        // Back-compat: older builds persisted manual-style host/port without a kind marker.
-        guard !host.isEmpty, port > 0, port <= 65535 else { return nil }
-        return .manual(host: host, port: port, useTLS: useTLS, stableID: stableID)
+        let payload = LastGatewayConnectionData(
+            kind: kind, stableID: stableID, useTLS: useTLS,
+            host: kind == .manual ? host : nil,
+            port: kind == .manual ? port : nil)
+        guard self.saveLastGatewayConnectionData(payload) else { return }
+        self.removeLastGatewayDefaults(defaults)
     }
 
-    static func clearLastGatewayConnection(defaults: UserDefaults = .standard) {
+    private static func removeLastGatewayDefaults(_ defaults: UserDefaults) {
         defaults.removeObject(forKey: self.lastGatewayKindDefaultsKey)
         defaults.removeObject(forKey: self.lastGatewayHostDefaultsKey)
         defaults.removeObject(forKey: self.lastGatewayPortDefaultsKey)
@@ -355,9 +411,15 @@ enum GatewayDiagnostics {
     private static let maxLogBytes: Int64 = 512 * 1024
     private static let keepLogBytes: Int64 = 256 * 1024
     private static let logSizeCheckEveryWrites = 50
-    nonisolated(unsafe) private static var logWritesSinceCheck = 0
+    private static let logWritesSinceCheck = OSAllocatedUnfairLock(initialState: 0)
+    private static let isoFormatter: ISO8601DateFormatter = {
+        let f = ISO8601DateFormatter()
+        f.formatOptions = [.withInternetDateTime, .withFractionalSeconds]
+        return f
+    }()
+
     private static var fileURL: URL? {
-        FileManager.default.urls(for: .documentDirectory, in: .userDomainMask).first?
+        FileManager.default.urls(for: .cachesDirectory, in: .userDomainMask).first?
             .appendingPathComponent("openclaw-gateway.log")
     }
 
@@ -404,32 +466,41 @@ enum GatewayDiagnostics {
         }
     }
 
+    private static func applyFileProtection(url: URL) {
+        try? FileManager.default.setAttributes(
+            [.protectionKey: FileProtectionType.completeUntilFirstUserAuthentication],
+            ofItemAtPath: url.path)
+    }
+
     static func bootstrap() {
         guard let url = fileURL else { return }
         queue.async {
             self.truncateLogIfNeeded(url: url)
-            let formatter = ISO8601DateFormatter()
-            formatter.formatOptions = [.withInternetDateTime, .withFractionalSeconds]
-            let timestamp = formatter.string(from: Date())
+            let timestamp = self.isoFormatter.string(from: Date())
             let line = "[\(timestamp)] gateway diagnostics started\n"
             if let data = line.data(using: .utf8) {
                 self.appendToLog(url: url, data: data)
+                self.applyFileProtection(url: url)
             }
         }
     }
 
     static func log(_ message: String) {
-        let formatter = ISO8601DateFormatter()
-        formatter.formatOptions = [.withInternetDateTime, .withFractionalSeconds]
-        let timestamp = formatter.string(from: Date())
+        let timestamp = self.isoFormatter.string(from: Date())
         let line = "[\(timestamp)] \(message)"
         logger.info("\(line, privacy: .public)")
 
         guard let url = fileURL else { return }
         queue.async {
-            self.logWritesSinceCheck += 1
-            if self.logWritesSinceCheck >= self.logSizeCheckEveryWrites {
-                self.logWritesSinceCheck = 0
+            let shouldTruncate = self.logWritesSinceCheck.withLock { count in
+                count += 1
+                if count >= self.logSizeCheckEveryWrites {
+                    count = 0
+                    return true
+                }
+                return false
+            }
+            if shouldTruncate {
                 self.truncateLogIfNeeded(url: url)
             }
             let entry = line + "\n"

apps/ios/Sources/Gateway/KeychainStore.swift

@@ -1,48 +1,16 @@
 import Foundation
-import Security
+import OpenClawKit
 
 enum KeychainStore {
     static func loadString(service: String, account: String) -> String? {
-        let query: [String: Any] = [
-            kSecClass as String: kSecClassGenericPassword,
-            kSecAttrService as String: service,
-            kSecAttrAccount as String: account,
-            kSecReturnData as String: true,
-            kSecMatchLimit as String: kSecMatchLimitOne,
-        ]
-
-        var item: CFTypeRef?
-        let status = SecItemCopyMatching(query as CFDictionary, &item)
-        guard status == errSecSuccess, let data = item as? Data else { return nil }
-        return String(data: data, encoding: .utf8)
+        GenericPasswordKeychainStore.loadString(service: service, account: account)
     }
 
     static func saveString(_ value: String, service: String, account: String) -> Bool {
-        let data = Data(value.utf8)
-        let query: [String: Any] = [
-            kSecClass as String: kSecClassGenericPassword,
-            kSecAttrService as String: service,
-            kSecAttrAccount as String: account,
-        ]
-
-        let update: [String: Any] = [kSecValueData as String: data]
-        let status = SecItemUpdate(query as CFDictionary, update as CFDictionary)
-        if status == errSecSuccess { return true }
-        if status != errSecItemNotFound { return false }
-
-        var insert = query
-        insert[kSecValueData as String] = data
-        insert[kSecAttrAccessible as String] = kSecAttrAccessibleAfterFirstUnlockThisDeviceOnly
-        return SecItemAdd(insert as CFDictionary, nil) == errSecSuccess
+        GenericPasswordKeychainStore.saveString(value, service: service, account: account)
     }
 
     static func delete(service: String, account: String) -> Bool {
-        let query: [String: Any] = [
-            kSecClass as String: kSecClassGenericPassword,
-            kSecAttrService as String: service,
-            kSecAttrAccount as String: account,
-        ]
-        let status = SecItemDelete(query as CFDictionary)
-        return status == errSecSuccess || status == errSecItemNotFound
+        GenericPasswordKeychainStore.delete(service: service, account: account)
     }
 }

apps/ios/Sources/Info.plist

@@ -54,6 +54,8 @@
 	<string>OpenClaw needs microphone access for voice wake.</string>
 	<key>NSSpeechRecognitionUsageDescription</key>
 	<string>OpenClaw uses on-device speech recognition for voice wake.</string>
+	<key>NSSupportsLiveActivities</key>
+	<true/>
 	<key>UIApplicationSceneManifest</key>
 	<dict>
 		<key>UIApplicationSupportsMultipleScenes</key>

apps/ios/Sources/LiveActivity/LiveActivityManager.swift

@@ -0,0 +1,125 @@
+import ActivityKit
+import Foundation
+import os
+
+/// Minimal Live Activity lifecycle focused on connection health + stale cleanup.
+@MainActor
+final class LiveActivityManager {
+    static let shared = LiveActivityManager()
+
+    private let logger = Logger(subsystem: "ai.openclaw.ios", category: "LiveActivity")
+    private var currentActivity: Activity<OpenClawActivityAttributes>?
+    private var activityStartDate: Date = .now
+
+    private init() {
+        self.hydrateCurrentAndPruneDuplicates()
+    }
+
+    var isActive: Bool {
+        guard let activity = self.currentActivity else { return false }
+        guard activity.activityState == .active else {
+            self.currentActivity = nil
+            return false
+        }
+        return true
+    }
+
+    func startActivity(agentName: String, sessionKey: String) {
+        self.hydrateCurrentAndPruneDuplicates()
+
+        if self.currentActivity != nil {
+            self.handleConnecting()
+            return
+        }
+
+        let authInfo = ActivityAuthorizationInfo()
+        guard authInfo.areActivitiesEnabled else {
+            self.logger.info("Live Activities disabled; skipping start")
+            return
+        }
+
+        self.activityStartDate = .now
+        let attributes = OpenClawActivityAttributes(agentName: agentName, sessionKey: sessionKey)
+
+        do {
+            let activity = try Activity.request(
+                attributes: attributes,
+                content: ActivityContent(state: self.connectingState(), staleDate: nil),
+                pushType: nil)
+            self.currentActivity = activity
+            self.logger.info("started live activity id=\(activity.id, privacy: .public)")
+        } catch {
+            self.logger.error("failed to start live activity: \(error.localizedDescription, privacy: .public)")
+        }
+    }
+
+    func handleConnecting() {
+        self.updateCurrent(state: self.connectingState())
+    }
+
+    func handleReconnect() {
+        self.updateCurrent(state: self.idleState())
+    }
+
+    func handleDisconnect() {
+        self.updateCurrent(state: self.disconnectedState())
+    }
+
+    private func hydrateCurrentAndPruneDuplicates() {
+        let active = Activity<OpenClawActivityAttributes>.activities
+        guard !active.isEmpty else {
+            self.currentActivity = nil
+            return
+        }
+
+        let keeper = active.max { lhs, rhs in
+            lhs.content.state.startedAt < rhs.content.state.startedAt
+        } ?? active[0]
+
+        self.currentActivity = keeper
+        self.activityStartDate = keeper.content.state.startedAt
+
+        let stale = active.filter { $0.id != keeper.id }
+        for activity in stale {
+            Task {
+                await activity.end(
+                    ActivityContent(state: self.disconnectedState(), staleDate: nil),
+                    dismissalPolicy: .immediate)
+            }
+        }
+    }
+
+    private func updateCurrent(state: OpenClawActivityAttributes.ContentState) {
+        guard let activity = self.currentActivity else { return }
+        Task {
+            await activity.update(ActivityContent(state: state, staleDate: nil))
+        }
+    }
+
+    private func connectingState() -> OpenClawActivityAttributes.ContentState {
+        OpenClawActivityAttributes.ContentState(
+            statusText: "Connecting...",
+            isIdle: false,
+            isDisconnected: false,
+            isConnecting: true,
+            startedAt: self.activityStartDate)
+    }
+
+    private func idleState() -> OpenClawActivityAttributes.ContentState {
+        OpenClawActivityAttributes.ContentState(
+            statusText: "Idle",
+            isIdle: true,
+            isDisconnected: false,
+            isConnecting: false,
+            startedAt: self.activityStartDate)
+    }
+
+    private func disconnectedState() -> OpenClawActivityAttributes.ContentState {
+        OpenClawActivityAttributes.ContentState(
+            statusText: "Disconnected",
+            isIdle: false,
+            isDisconnected: true,
+            isConnecting: false,
+            startedAt: self.activityStartDate)
+    }
+}

apps/ios/Sources/LiveActivity/OpenClawActivityAttributes.swift

@@ -0,0 +1,45 @@
+import ActivityKit
+import Foundation
+
+/// Shared schema used by iOS app + Live Activity widget extension.
+struct OpenClawActivityAttributes: ActivityAttributes {
+    var agentName: String
+    var sessionKey: String
+
+    struct ContentState: Codable, Hashable {
+        var statusText: String
+        var isIdle: Bool
+        var isDisconnected: Bool
+        var isConnecting: Bool
+        var startedAt: Date
+    }
+}
+
+#if DEBUG
+extension OpenClawActivityAttributes {
+    static let preview = OpenClawActivityAttributes(agentName: "main", sessionKey: "main")
+}
+
+extension OpenClawActivityAttributes.ContentState {
+    static let connecting = OpenClawActivityAttributes.ContentState(
+        statusText: "Connecting...",
+        isIdle: false,
+        isDisconnected: false,
+        isConnecting: true,
+        startedAt: .now)
+
+    static let idle = OpenClawActivityAttributes.ContentState(
+        statusText: "Idle",
+        isIdle: true,
+        isDisconnected: false,
+        isConnecting: false,
+        startedAt: .now)
+
+    static let disconnected = OpenClawActivityAttributes.ContentState(
+        statusText: "Disconnected",
+        isIdle: false,
+        isDisconnected: true,
+        isConnecting: false,
+        startedAt: .now)
+}
+#endif

apps/ios/Sources/Location/LocationService.swift

@@ -21,7 +21,7 @@ final class LocationService: NSObject, CLLocationManagerDelegate, LocationServic
         self.manager
     }
 
-    var locationRequestContinuation: CheckedContinuation<CLLocation, Error>? {
+    var locationRequestContinuation: CheckedContinuation<CLLocation, Swift.Error>? {
         get { self.locationContinuation }
         set { self.locationContinuation = newValue }
     }
@@ -65,9 +65,10 @@ final class LocationService: NSObject, CLLocationManagerDelegate, LocationServic
             desiredAccuracy: desiredAccuracy,
             maxAgeMs: maxAgeMs,
             timeoutMs: timeoutMs,
-            request: { try await self.requestLocationOnce() }) { timeoutMs, operation in
+            request: { try await self.requestLocationOnce() },
+            withTimeout: { timeoutMs, operation in
                 try await self.withTimeout(timeoutMs: timeoutMs, operation: operation)
-        }
+            })
     }
 
     private func awaitAuthorizationChange() async -> CLAuthorizationStatus {

apps/ios/Sources/Model/NodeAppModel.swift

@@ -90,7 +90,9 @@ final class NodeAppModel {
     var lastShareEventText: String = "No share events yet."
     var openChatRequestID: Int = 0
     private(set) var pendingAgentDeepLinkPrompt: AgentDeepLinkPrompt?
+    private var queuedAgentDeepLinkPrompt: AgentDeepLinkPrompt?
     private var lastAgentDeepLinkPromptAt: Date = .distantPast
+    @ObservationIgnored private var queuedAgentDeepLinkPromptTask: Task<Void, Never>?
 
     // Primary "node" connection: used for device capabilities and node.invoke requests.
     private let nodeGateway = GatewayNodeSession()
@@ -1693,6 +1695,7 @@ extension NodeAppModel {
         self.operatorGatewayTask = nil
         self.voiceWakeSyncTask?.cancel()
         self.voiceWakeSyncTask = nil
+        LiveActivityManager.shared.handleDisconnect()
         self.gatewayHealthMonitor.stop()
         Task {
             await self.operatorGateway.disconnect()
@@ -1729,6 +1732,7 @@ private extension NodeAppModel {
         self.operatorConnected = false
         self.voiceWakeSyncTask?.cancel()
         self.voiceWakeSyncTask = nil
+        LiveActivityManager.shared.handleDisconnect()
         self.gatewayDefaultAgentId = nil
         self.gatewayAgents = []
         self.selectedAgentId = GatewaySettingsStore.loadGatewaySelectedAgentId(stableID: stableID)
@@ -1809,6 +1813,7 @@ private extension NodeAppModel {
                             await self.refreshAgentsFromGateway()
                             await self.refreshShareRouteFromGateway()
                             await self.startVoiceWakeSync()
+                            await MainActor.run { LiveActivityManager.shared.handleReconnect() }
                             await MainActor.run { self.startGatewayHealthMonitor() }
                         },
                         onDisconnected: { [weak self] reason in
@@ -1816,6 +1821,7 @@ private extension NodeAppModel {
                             await MainActor.run {
                                 self.operatorConnected = false
                                 self.talkMode.updateGatewayConnected(false)
+                                LiveActivityManager.shared.handleDisconnect()
                             }
                             GatewayDiagnostics.log("operator gateway disconnected reason=\(reason)")
                             await MainActor.run { self.stopGatewayHealthMonitor() }
@@ -1880,6 +1886,14 @@ private extension NodeAppModel {
                     self.gatewayStatusText = (attempt == 0) ? "Connecting…" : "Reconnecting…"
                     self.gatewayServerName = nil
                     self.gatewayRemoteAddress = nil
+                    let liveActivity = LiveActivityManager.shared
+                    if liveActivity.isActive {
+                        liveActivity.handleConnecting()
+                    } else {
+                        liveActivity.startActivity(
+                            agentName: self.selectedAgentId ?? "main",
+                            sessionKey: self.mainSessionKey)
+                    }
                 }
 
                 do {
@@ -2591,19 +2605,31 @@ extension NodeAppModel {
                     "agent deep link rejected: unkeyed message too long chars=\(message.count, privacy: .public)")
                 return
             }
-            if Date().timeIntervalSince(self.lastAgentDeepLinkPromptAt) < 1.0 {
-                self.deepLinkLogger.debug("agent deep link prompt throttled")
-                return
-            }
-            self.lastAgentDeepLinkPromptAt = Date()
-
             let urlText = originalURL.absoluteString
             let prompt = AgentDeepLinkPrompt(
                 id: UUID().uuidString,
                 messagePreview: message,
                 urlPreview: urlText.count > 500 ? "\(urlText.prefix(500))…" : urlText,
                 request: self.effectiveAgentDeepLinkForPrompt(link))
-            self.pendingAgentDeepLinkPrompt = prompt
+
+            let promptIntervalSeconds = 5.0
+            let elapsed = Date().timeIntervalSince(self.lastAgentDeepLinkPromptAt)
+            if elapsed < promptIntervalSeconds {
+                if self.pendingAgentDeepLinkPrompt != nil {
+                    self.pendingAgentDeepLinkPrompt = prompt
+                    self.recordShareEvent("Updated local confirmation request (\(message.count) chars).")
+                    self.deepLinkLogger.debug("agent deep link prompt coalesced into active confirmation")
+                    return
+                }
+
+                let remaining = max(0, promptIntervalSeconds - elapsed)
+                self.queueAgentDeepLinkPrompt(prompt, initialDelaySeconds: remaining)
+                self.recordShareEvent("Queued local confirmation (\(message.count) chars).")
+                self.deepLinkLogger.debug("agent deep link prompt queued due to rate limit")
+                return
+            }
+
+            self.presentAgentDeepLinkPrompt(prompt)
             self.recordShareEvent("Awaiting local confirmation (\(message.count) chars).")
             self.deepLinkLogger.info("agent deep link requires local confirmation")
             return
@@ -2672,6 +2698,60 @@ extension NodeAppModel {
         self.deepLinkLogger.info("agent deep link cancelled by local user")
     }
 
+    private func presentAgentDeepLinkPrompt(_ prompt: AgentDeepLinkPrompt) {
+        self.lastAgentDeepLinkPromptAt = Date()
+        self.pendingAgentDeepLinkPrompt = prompt
+    }
+
+    private func queueAgentDeepLinkPrompt(_ prompt: AgentDeepLinkPrompt, initialDelaySeconds: TimeInterval) {
+        self.queuedAgentDeepLinkPrompt = prompt
+        guard self.queuedAgentDeepLinkPromptTask == nil else { return }
+
+        self.queuedAgentDeepLinkPromptTask = Task { [weak self] in
+            guard let self else { return }
+            let delayNs = UInt64(max(0, initialDelaySeconds) * 1_000_000_000)
+            if delayNs > 0 {
+                do {
+                    try await Task.sleep(nanoseconds: delayNs)
+                } catch {
+                    return
+                }
+            }
+            await self.deliverQueuedAgentDeepLinkPrompt()
+        }
+    }
+
+    private func deliverQueuedAgentDeepLinkPrompt() async {
+        defer { self.queuedAgentDeepLinkPromptTask = nil }
+        let promptIntervalSeconds = 5.0
+        while let prompt = self.queuedAgentDeepLinkPrompt {
+            if self.pendingAgentDeepLinkPrompt != nil {
+                do {
+                    try await Task.sleep(nanoseconds: 200_000_000)
+                } catch {
+                    return
+                }
+                continue
+            }
+
+            let elapsed = Date().timeIntervalSince(self.lastAgentDeepLinkPromptAt)
+            if elapsed < promptIntervalSeconds {
+                let remaining = max(0, promptIntervalSeconds - elapsed)
+                do {
+                    try await Task.sleep(nanoseconds: UInt64(remaining * 1_000_000_000))
+                } catch {
+                    return
+                }
+                continue
+            }
+
+            self.queuedAgentDeepLinkPrompt = nil
+            self.presentAgentDeepLinkPrompt(prompt)
+            self.recordShareEvent("Awaiting local confirmation (\(prompt.messagePreview.count) chars).")
+            self.deepLinkLogger.info("agent deep link queued prompt delivered")
+        }
+    }
+
     private func submitAgentDeepLink(_ link: AgentDeepLink, messageCharCount: Int) async {
         do {
             try await self.sendAgentRequest(link: link)

apps/ios/Sources/Onboarding/GatewayOnboardingView.swift

@@ -302,6 +302,7 @@ private struct ManualEntryStep: View {
     // (GatewaySetupCode) decode raw setup codes.
 }
 
+@MainActor
 private func gatewayConnectionStatusLines(
     appModel: NodeAppModel,
     gatewayController: GatewayConnectionController) -> [String]
@@ -309,6 +310,7 @@ private func gatewayConnectionStatusLines(
     ConnectionStatusBox.defaultLines(appModel: appModel, gatewayController: gatewayController)
 }
 
+@MainActor
 private func resetGatewayConnectionState(
     appModel: NodeAppModel,
     connectStatusText: inout String?,
@@ -319,6 +321,7 @@ private func resetGatewayConnectionState(
     connectingGatewayID = nil
 }
 
+@MainActor
 @ViewBuilder
 private func gatewayConnectionStatusSection(
     appModel: NodeAppModel,

apps/ios/Sources/Screen/ScreenRecordService.swift

@@ -1,4 +1,5 @@
 import AVFoundation
+import OpenClawKit
 import ReplayKit
 
 final class ScreenRecordService: @unchecked Sendable {

apps/ios/Sources/Services/WatchMessagingService.swift

@@ -20,10 +20,11 @@ enum WatchMessagingError: LocalizedError {
     }
 }
 
-final class WatchMessagingService: NSObject, WatchMessagingServicing, @unchecked Sendable {
-    private static let logger = Logger(subsystem: "ai.openclaw", category: "watch.messaging")
+@MainActor
+final class WatchMessagingService: NSObject, @preconcurrency WatchMessagingServicing {
+    nonisolated private static let logger = Logger(subsystem: "ai.openclaw", category: "watch.messaging")
     private let session: WCSession?
-    private let replyHandlerLock = NSLock()
+    private var pendingActivationContinuations: [CheckedContinuation<Void, Never>] = []
     private var replyHandler: (@Sendable (WatchQuickReplyEvent) -> Void)?
 
     override init() {
@@ -39,11 +40,11 @@ final class WatchMessagingService: NSObject, WatchMessagingServicing, @unchecked
         }
     }
 
-    static func isSupportedOnDevice() -> Bool {
+    nonisolated static func isSupportedOnDevice() -> Bool {
         WCSession.isSupported()
     }
 
-    static func currentStatusSnapshot() -> WatchMessagingStatus {
+    nonisolated static func currentStatusSnapshot() -> WatchMessagingStatus {
         guard WCSession.isSupported() else {
             return WatchMessagingStatus(
                 supported: false,
@@ -70,9 +71,7 @@ final class WatchMessagingService: NSObject, WatchMessagingServicing, @unchecked
     }
 
     func setReplyHandler(_ handler: (@Sendable (WatchQuickReplyEvent) -> Void)?) {
-        self.replyHandlerLock.lock()
         self.replyHandler = handler
-        self.replyHandlerLock.unlock()
     }
 
     func sendNotification(
@@ -161,19 +160,15 @@ final class WatchMessagingService: NSObject, WatchMessagingServicing, @unchecked
     }
 
     private func emitReply(_ event: WatchQuickReplyEvent) {
-        let handler: ((WatchQuickReplyEvent) -> Void)?
-        self.replyHandlerLock.lock()
-        handler = self.replyHandler
-        self.replyHandlerLock.unlock()
-        handler?(event)
+        self.replyHandler?(event)
     }
 
-    private static func nonEmpty(_ value: String?) -> String? {
+    nonisolated private static func nonEmpty(_ value: String?) -> String? {
         let trimmed = value?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
         return trimmed.isEmpty ? nil : trimmed
     }
 
-    private static func parseQuickReplyPayload(
+    nonisolated private static func parseQuickReplyPayload(
         _ payload: [String: Any],
         transport: String) -> WatchQuickReplyEvent?
     {
@@ -205,13 +200,12 @@ final class WatchMessagingService: NSObject, WatchMessagingServicing, @unchecked
         guard let session = self.session else { return }
         if session.activationState == .activated { return }
         session.activate()
-        for _ in 0..<8 {
-            if session.activationState == .activated { return }
-            try? await Task.sleep(nanoseconds: 100_000_000)
+        await withCheckedContinuation { continuation in
+            self.pendingActivationContinuations.append(continuation)
         }
     }
 
-    private static func status(for session: WCSession) -> WatchMessagingStatus {
+    nonisolated private static func status(for session: WCSession) -> WatchMessagingStatus {
         WatchMessagingStatus(
             supported: true,
             paired: session.isPaired,
@@ -220,7 +214,7 @@ final class WatchMessagingService: NSObject, WatchMessagingServicing, @unchecked
             activationState: activationStateLabel(session.activationState))
     }
 
-    private static func activationStateLabel(_ state: WCSessionActivationState) -> String {
+    nonisolated private static func activationStateLabel(_ state: WCSessionActivationState) -> String {
         switch state {
         case .notActivated:
             "notActivated"
@@ -235,32 +229,42 @@ final class WatchMessagingService: NSObject, WatchMessagingServicing, @unchecked
 }
 
 extension WatchMessagingService: WCSessionDelegate {
-    func session(
+    nonisolated func session(
         _ session: WCSession,
         activationDidCompleteWith activationState: WCSessionActivationState,
         error: (any Error)?)
     {
         if let error {
             Self.logger.error("watch activation failed: \(error.localizedDescription, privacy: .public)")
-            return
+        } else {
+            Self.logger.debug("watch activation state=\(Self.activationStateLabel(activationState), privacy: .public)")
+        }
+        // Always resume all waiters so callers never hang, even on error.
+        Task { @MainActor in
+            let waiters = self.pendingActivationContinuations
+            self.pendingActivationContinuations.removeAll()
+            for continuation in waiters {
+                continuation.resume()
+            }
         }
-        Self.logger.debug("watch activation state=\(Self.activationStateLabel(activationState), privacy: .public)")
     }
 
-    func sessionDidBecomeInactive(_ session: WCSession) {}
+    nonisolated func sessionDidBecomeInactive(_ session: WCSession) {}
 
-    func sessionDidDeactivate(_ session: WCSession) {
+    nonisolated func sessionDidDeactivate(_ session: WCSession) {
         session.activate()
     }
 
-    func session(_: WCSession, didReceiveMessage message: [String: Any]) {
+    nonisolated func session(_: WCSession, didReceiveMessage message: [String: Any]) {
         guard let event = Self.parseQuickReplyPayload(message, transport: "sendMessage") else {
             return
         }
-        self.emitReply(event)
+        Task { @MainActor in
+            self.emitReply(event)
+        }
     }
 
-    func session(
+    nonisolated func session(
         _: WCSession,
         didReceiveMessage message: [String: Any],
         replyHandler: @escaping ([String: Any]) -> Void)
@@ -270,15 +274,19 @@ extension WatchMessagingService: WCSessionDelegate {
             return
         }
         replyHandler(["ok": true])
-        self.emitReply(event)
+        Task { @MainActor in
+            self.emitReply(event)
+        }
     }
 
-    func session(_: WCSession, didReceiveUserInfo userInfo: [String: Any]) {
+    nonisolated func session(_: WCSession, didReceiveUserInfo userInfo: [String: Any]) {
         guard let event = Self.parseQuickReplyPayload(userInfo, transport: "transferUserInfo") else {
             return
         }
-        self.emitReply(event)
+        Task { @MainActor in
+            self.emitReply(event)
+        }
     }
 
-    func sessionReachabilityDidChange(_ session: WCSession) {}
+    nonisolated func sessionReachabilityDidChange(_ session: WCSession) {}
 }

apps/ios/Sources/Voice/TalkModeManager.swift

@@ -7,6 +7,23 @@ import Observation
 import OSLog
 import Speech
 
+private final class StreamFailureBox: @unchecked Sendable {
+    private let lock = NSLock()
+    private var valueInternal: Error?
+
+    func set(_ error: Error) {
+        self.lock.lock()
+        self.valueInternal = error
+        self.lock.unlock()
+    }
+
+    var value: Error? {
+        self.lock.lock()
+        defer { self.lock.unlock() }
+        return self.valueInternal
+    }
+}
+
 // This file intentionally centralizes talk mode state + behavior.
 // It's large, and splitting would force `private` -> `fileprivate` across many members.
 // We'll refactor into smaller files when the surface stabilizes.
@@ -72,6 +89,9 @@ final class TalkModeManager: NSObject {
     private var mainSessionKey: String = "main"
     private var fallbackVoiceId: String?
     private var lastPlaybackWasPCM: Bool = false
+    /// Set when the ElevenLabs API rejects PCM format (e.g. 403 subscription_required).
+    /// Once set, all subsequent requests in this session use MP3 instead of re-trying PCM.
+    private var pcmFormatUnavailable: Bool = false
     var pcmPlayer: PCMStreamingAudioPlaying = PCMStreamingAudioPlayer.shared
     var mp3Player: StreamingAudioPlaying = StreamingAudioPlayer.shared
 
@@ -987,9 +1007,12 @@ final class TalkModeManager: NSObject {
                 self.logger.warning("unknown voice alias \(requestedVoice ?? "?", privacy: .public)")
             }
 
-            let resolvedKey =
-                (self.apiKey?.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty == false ? self.apiKey : nil) ??
-                ProcessInfo.processInfo.environment["ELEVENLABS_API_KEY"]
+            let configuredKey = self.apiKey?.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty == false ? self.apiKey : nil
+            #if DEBUG
+            let resolvedKey = configuredKey ?? ProcessInfo.processInfo.environment["ELEVENLABS_API_KEY"]
+            #else
+            let resolvedKey = configuredKey
+            #endif
             let apiKey = resolvedKey?.trimmingCharacters(in: .whitespacesAndNewlines)
             let preferredVoice = resolvedVoice ?? self.currentVoiceId ?? self.defaultVoiceId
             let voiceId: String? = if let apiKey, !apiKey.isEmpty {
@@ -1004,7 +1027,8 @@ final class TalkModeManager: NSObject {
                 let desiredOutputFormat = (directive?.outputFormat ?? self.defaultOutputFormat)?
                     .trimmingCharacters(in: .whitespacesAndNewlines)
                 let requestedOutputFormat = (desiredOutputFormat?.isEmpty == false) ? desiredOutputFormat : nil
-                let outputFormat = ElevenLabsTTSClient.validatedOutputFormat(requestedOutputFormat ?? "pcm_44100")
+                let outputFormat = ElevenLabsTTSClient.validatedOutputFormat(
+                    requestedOutputFormat ?? self.effectiveDefaultOutputFormat)
                 if outputFormat == nil, let requestedOutputFormat {
                     self.logger.warning(
                         "talk output_format unsupported for local playback: \(requestedOutputFormat, privacy: .public)")
@@ -1033,7 +1057,7 @@ final class TalkModeManager: NSObject {
                 let request = makeRequest(outputFormat: outputFormat)
 
                 let client = ElevenLabsTTSClient(apiKey: apiKey)
-                let stream = client.streamSynthesize(voiceId: voiceId, request: request)
+                let rawStream = client.streamSynthesize(voiceId: voiceId, request: request)
 
                 if self.interruptOnSpeech {
                     do {
@@ -1048,11 +1072,16 @@ final class TalkModeManager: NSObject {
                 let sampleRate = TalkTTSValidation.pcmSampleRate(from: outputFormat)
                 let result: StreamingPlaybackResult
                 if let sampleRate {
+                    let streamFailure = StreamFailureBox()
+                    let stream = Self.monitorStreamFailures(rawStream, failureBox: streamFailure)
                     self.lastPlaybackWasPCM = true
                     var playback = await self.pcmPlayer.play(stream: stream, sampleRate: sampleRate)
                     if !playback.finished, playback.interruptedAt == nil {
-                        let mp3Format = ElevenLabsTTSClient.validatedOutputFormat("mp3_44100")
+                        let mp3Format = ElevenLabsTTSClient.validatedOutputFormat("mp3_44100_128")
                         self.logger.warning("pcm playback failed; retrying mp3")
+                        if Self.isPCMFormatRejectedByAPI(streamFailure.value) {
+                            self.pcmFormatUnavailable = true
+                        }
                         self.lastPlaybackWasPCM = false
                         let mp3Stream = client.streamSynthesize(
                             voiceId: voiceId,
@@ -1062,7 +1091,7 @@ final class TalkModeManager: NSObject {
                     result = playback
                 } else {
                     self.lastPlaybackWasPCM = false
-                    result = await self.mp3Player.play(stream: stream)
+                    result = await self.mp3Player.play(stream: rawStream)
                 }
                 let duration = Date().timeIntervalSince(started)
                 self.logger.info("elevenlabs stream finished=\(result.finished, privacy: .public) dur=\(duration, privacy: .public)s")
@@ -1388,7 +1417,7 @@ final class TalkModeManager: NSObject {
 
     private func resolveIncrementalPrefetchOutputFormat(context: IncrementalSpeechContext) -> String? {
         if TalkTTSValidation.pcmSampleRate(from: context.outputFormat) != nil {
-            return ElevenLabsTTSClient.validatedOutputFormat("mp3_44100")
+            return ElevenLabsTTSClient.validatedOutputFormat("mp3_44100_128")
         }
         return context.outputFormat
     }
@@ -1477,15 +1506,19 @@ final class TalkModeManager: NSObject {
         let desiredOutputFormat = (directive?.outputFormat ?? self.defaultOutputFormat)?
             .trimmingCharacters(in: .whitespacesAndNewlines)
         let requestedOutputFormat = (desiredOutputFormat?.isEmpty == false) ? desiredOutputFormat : nil
-        let outputFormat = ElevenLabsTTSClient.validatedOutputFormat(requestedOutputFormat ?? "pcm_44100")
+        let outputFormat = ElevenLabsTTSClient.validatedOutputFormat(
+            requestedOutputFormat ?? self.effectiveDefaultOutputFormat)
         if outputFormat == nil, let requestedOutputFormat {
             self.logger.warning(
                 "talk output_format unsupported for local playback: \(requestedOutputFormat, privacy: .public)")
         }
 
-        let resolvedKey =
-            (self.apiKey?.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty == false ? self.apiKey : nil) ??
-            ProcessInfo.processInfo.environment["ELEVENLABS_API_KEY"]
+        let configuredKey = self.apiKey?.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty == false ? self.apiKey : nil
+        #if DEBUG
+        let resolvedKey = configuredKey ?? ProcessInfo.processInfo.environment["ELEVENLABS_API_KEY"]
+        #else
+        let resolvedKey = configuredKey
+        #endif
         let apiKey = resolvedKey?.trimmingCharacters(in: .whitespacesAndNewlines)
         let voiceId: String? = if let apiKey, !apiKey.isEmpty {
             await self.resolveVoiceId(preferred: preferredVoice, apiKey: apiKey)
@@ -1528,6 +1561,44 @@ final class TalkModeManager: NSObject {
             latencyTier: TalkTTSValidation.validatedLatencyTier(context.directive?.latencyTier))
     }
 
+    /// Returns `mp3_44100_128` when the API has already rejected PCM, otherwise `pcm_44100`.
+    private var effectiveDefaultOutputFormat: String {
+        self.pcmFormatUnavailable ? "mp3_44100_128" : "pcm_44100"
+    }
+
+    private static func monitorStreamFailures(
+        _ stream: AsyncThrowingStream<Data, Error>,
+        failureBox: StreamFailureBox
+    ) -> AsyncThrowingStream<Data, Error>
+    {
+        AsyncThrowingStream { continuation in
+            let task = Task {
+                do {
+                    for try await chunk in stream {
+                        continuation.yield(chunk)
+                    }
+                    continuation.finish()
+                } catch {
+                    failureBox.set(error)
+                    continuation.finish(throwing: error)
+                }
+            }
+            continuation.onTermination = { _ in
+                task.cancel()
+            }
+        }
+    }
+
+    private static func isPCMFormatRejectedByAPI(_ error: Error?) -> Bool {
+        guard let error = error as NSError? else { return false }
+        guard error.domain == "ElevenLabsTTS", error.code >= 400 else { return false }
+        let message = (error.userInfo[NSLocalizedDescriptionKey] as? String ?? error.localizedDescription).lowercased()
+        return message.contains("output_format")
+            || message.contains("pcm_")
+            || message.contains("pcm ")
+            || message.contains("subscription_required")
+    }
+
     private static func makeBufferedAudioStream(chunks: [Data]) -> AsyncThrowingStream<Data, Error> {
         AsyncThrowingStream { continuation in
             for chunk in chunks {
@@ -1569,22 +1640,27 @@ final class TalkModeManager: NSObject {
             text: text,
             context: context,
             outputFormat: context.outputFormat)
-        let stream: AsyncThrowingStream<Data, Error>
+        let rawStream: AsyncThrowingStream<Data, Error>
         if let prefetchedAudio, !prefetchedAudio.chunks.isEmpty {
-            stream = Self.makeBufferedAudioStream(chunks: prefetchedAudio.chunks)
+            rawStream = Self.makeBufferedAudioStream(chunks: prefetchedAudio.chunks)
         } else {
-            stream = client.streamSynthesize(voiceId: voiceId, request: request)
+            rawStream = client.streamSynthesize(voiceId: voiceId, request: request)
         }
         let playbackFormat = prefetchedAudio?.outputFormat ?? context.outputFormat
         let sampleRate = TalkTTSValidation.pcmSampleRate(from: playbackFormat)
         let result: StreamingPlaybackResult
         if let sampleRate {
+            let streamFailure = StreamFailureBox()
+            let stream = Self.monitorStreamFailures(rawStream, failureBox: streamFailure)
             self.lastPlaybackWasPCM = true
             var playback = await self.pcmPlayer.play(stream: stream, sampleRate: sampleRate)
             if !playback.finished, playback.interruptedAt == nil {
                 self.logger.warning("pcm playback failed; retrying mp3")
+                if Self.isPCMFormatRejectedByAPI(streamFailure.value) {
+                    self.pcmFormatUnavailable = true
+                }
                 self.lastPlaybackWasPCM = false
-                let mp3Format = ElevenLabsTTSClient.validatedOutputFormat("mp3_44100")
+                let mp3Format = ElevenLabsTTSClient.validatedOutputFormat("mp3_44100_128")
                 let mp3Stream = client.streamSynthesize(
                     voiceId: voiceId,
                     request: self.makeIncrementalTTSRequest(
@@ -1596,7 +1672,7 @@ final class TalkModeManager: NSObject {
             result = playback
         } else {
             self.lastPlaybackWasPCM = false
-            result = await self.mp3Player.play(stream: stream)
+            result = await self.mp3Player.play(stream: rawStream)
         }
         if !result.finished, let interruptedAt = result.interruptedAt {
             self.lastInterruptedAtSeconds = interruptedAt
@@ -1606,6 +1682,8 @@ final class TalkModeManager: NSObject {
 }
 
 private struct IncrementalSpeechBuffer {
+    private static let softBoundaryMinChars = 72
+
     private(set) var latestText: String = ""
     private(set) var directive: TalkDirective?
     private var spokenOffset: Int = 0
@@ -1698,8 +1776,9 @@ private struct IncrementalSpeechBuffer {
             }
 
             if !inCodeBlock {
-                buffer.append(chars[idx])
-                if Self.isBoundary(chars[idx]) {
+                let currentChar = chars[idx]
+                buffer.append(currentChar)
+                if Self.isBoundary(currentChar) || Self.isSoftBoundary(currentChar, bufferedChars: buffer.count) {
                     lastBoundary = idx + 1
                     bufferAtBoundary = buffer
                     inCodeBlockAtBoundary = inCodeBlock
@@ -1726,6 +1805,10 @@ private struct IncrementalSpeechBuffer {
     private static func isBoundary(_ ch: Character) -> Bool {
         ch == "." || ch == "!" || ch == "?" || ch == "\n"
     }
+
+    private static func isSoftBoundary(_ ch: Character, bufferedChars: Int) -> Bool {
+        bufferedChars >= Self.softBoundaryMinChars && ch.isWhitespace
+    }
 }
 
 extension TalkModeManager {
@@ -1920,6 +2003,7 @@ extension TalkModeManager {
 
     func reloadConfig() async {
         guard let gateway else { return }
+        self.pcmFormatUnavailable = false
         do {
             let res = try await gateway.request(
                 method: "talk.config",
@@ -2099,6 +2183,10 @@ private final class AudioTapDiagnostics: @unchecked Sendable {
 
 #if DEBUG
 extension TalkModeManager {
+    static func _test_isPCMFormatRejectedByAPI(_ error: Error?) -> Bool {
+        self.isPCMFormatRejectedByAPI(error)
+    }
+
     func _test_seedTranscript(_ transcript: String) {
         self.lastTranscript = transcript
         self.lastHeard = Date()

apps/ios/Sources/Voice/VoiceWakeManager.swift

@@ -441,13 +441,6 @@ final class VoiceWakeManager: NSObject {
         }
     }
 
-    private static func permissionMessage(
-        kind: String,
-        status: AVAudioSession.RecordPermission) -> String
-    {
-        self.deniedByDefaultPermissionMessage(kind: kind, isUndetermined: status == .undetermined)
-    }
-
     private static func permissionMessage(
         kind: String,
         status: SFSpeechRecognizerAuthorizationStatus) -> String
@@ -466,7 +459,7 @@ final class VoiceWakeManager: NSObject {
         }
     }
 
-    private static func deniedByDefaultPermissionMessage(kind: String, isUndetermined: Bool) -> String {
+    private nonisolated static func deniedByDefaultPermissionMessage(kind: String, isUndetermined: Bool) -> String {
         if isUndetermined {
             return "\(kind) permission not granted"
         }

apps/ios/SwiftSources.input.xcfilelist

@@ -62,3 +62,7 @@ Sources/Voice/VoiceWakePreferences.swift
 ../../Swabble/Sources/SwabbleKit/WakeWordGate.swift
 Sources/Voice/TalkModeManager.swift
 Sources/Voice/TalkOrbOverlay.swift
+Sources/LiveActivity/OpenClawActivityAttributes.swift
+Sources/LiveActivity/LiveActivityManager.swift
+ActivityWidget/OpenClawActivityWidgetBundle.swift
+ActivityWidget/OpenClawLiveActivity.swift

apps/ios/Tests/GatewayConnectionControllerTests.swift

@@ -71,18 +71,37 @@ import UIKit
     }
 
     @Test @MainActor func loadLastConnectionReadsSavedValues() {
-        withUserDefaults([:]) {
-            GatewaySettingsStore.saveLastGatewayConnectionManual(
-                host: "gateway.example.com",
-                port: 443,
-                useTLS: true,
-                stableID: "manual|gateway.example.com|443")
-            let loaded = GatewaySettingsStore.loadLastGatewayConnection()
-            #expect(loaded == .manual(host: "gateway.example.com", port: 443, useTLS: true, stableID: "manual|gateway.example.com|443"))
+        let prior = KeychainStore.loadString(service: "ai.openclaw.gateway", account: "lastConnection")
+        defer {
+            if let prior {
+                _ = KeychainStore.saveString(prior, service: "ai.openclaw.gateway", account: "lastConnection")
+            } else {
+                _ = KeychainStore.delete(service: "ai.openclaw.gateway", account: "lastConnection")
+            }
         }
+        _ = KeychainStore.delete(service: "ai.openclaw.gateway", account: "lastConnection")
+
+        GatewaySettingsStore.saveLastGatewayConnectionManual(
+            host: "gateway.example.com",
+            port: 443,
+            useTLS: true,
+            stableID: "manual|gateway.example.com|443")
+        let loaded = GatewaySettingsStore.loadLastGatewayConnection()
+        #expect(loaded == .manual(host: "gateway.example.com", port: 443, useTLS: true, stableID: "manual|gateway.example.com|443"))
     }
 
     @Test @MainActor func loadLastConnectionReturnsNilForInvalidData() {
+        let prior = KeychainStore.loadString(service: "ai.openclaw.gateway", account: "lastConnection")
+        defer {
+            if let prior {
+                _ = KeychainStore.saveString(prior, service: "ai.openclaw.gateway", account: "lastConnection")
+            } else {
+                _ = KeychainStore.delete(service: "ai.openclaw.gateway", account: "lastConnection")
+            }
+        }
+        _ = KeychainStore.delete(service: "ai.openclaw.gateway", account: "lastConnection")
+
+        // Plant legacy UserDefaults with invalid host/port to exercise migration + validation.
         withUserDefaults([
             "gateway.last.kind": "manual",
             "gateway.last.host": "",

apps/ios/Tests/GatewaySettingsStoreTests.swift

@@ -27,6 +27,7 @@ private let lastGatewayDefaultsKeys = [
     "gateway.last.tls",
     "gateway.last.stableID",
 ]
+private let lastGatewayKeychainEntry = KeychainEntry(service: gatewayService, account: "lastConnection")
 
 private func snapshotDefaults(_ keys: [String]) -> [String: Any?] {
     let defaults = UserDefaults.standard
@@ -84,9 +85,13 @@ private func withBootstrapSnapshots(_ body: () -> Void) {
     body()
 }
 
-private func withLastGatewayDefaultsSnapshot(_ body: () -> Void) {
-    let snapshot = snapshotDefaults(lastGatewayDefaultsKeys)
-    defer { restoreDefaults(snapshot) }
+private func withLastGatewaySnapshot(_ body: () -> Void) {
+    let defaultsSnapshot = snapshotDefaults(lastGatewayDefaultsKeys)
+    let keychainSnapshot = snapshotKeychain([lastGatewayKeychainEntry])
+    defer {
+        restoreDefaults(defaultsSnapshot)
+        restoreKeychain(keychainSnapshot)
+    }
     body()
 }
 
@@ -135,7 +140,7 @@ private func withLastGatewayDefaultsSnapshot(_ body: () -> Void) {
     }
 
     @Test func lastGateway_manualRoundTrip() {
-        withLastGatewayDefaultsSnapshot {
+        withLastGatewaySnapshot {
             GatewaySettingsStore.saveLastGatewayConnectionManual(
                 host: "example.com",
                 port: 443,
@@ -147,28 +152,24 @@ private func withLastGatewayDefaultsSnapshot(_ body: () -> Void) {
         }
     }
 
-    @Test func lastGateway_discoveredDoesNotPersistResolvedHostPort() {
-        withLastGatewayDefaultsSnapshot {
-            // Simulate a prior manual record that included host/port.
-            applyDefaults([
-                "gateway.last.host": "10.0.0.99",
-                "gateway.last.port": 18789,
-                "gateway.last.tls": true,
-                "gateway.last.stableID": "manual|10.0.0.99|18789",
-                "gateway.last.kind": "manual",
-            ])
+    @Test func lastGateway_discoveredOverwritesManual() {
+        withLastGatewaySnapshot {
+            GatewaySettingsStore.saveLastGatewayConnectionManual(
+                host: "10.0.0.99",
+                port: 18789,
+                useTLS: true,
+                stableID: "manual|10.0.0.99|18789")
 
             GatewaySettingsStore.saveLastGatewayConnectionDiscovered(stableID: "gw|abc", useTLS: true)
 
-            let defaults = UserDefaults.standard
-            #expect(defaults.object(forKey: "gateway.last.host") == nil)
-            #expect(defaults.object(forKey: "gateway.last.port") == nil)
             #expect(GatewaySettingsStore.loadLastGatewayConnection() == .discovered(stableID: "gw|abc", useTLS: true))
         }
     }
 
-    @Test func lastGateway_backCompat_manualLoadsWhenKindMissing() {
-        withLastGatewayDefaultsSnapshot {
+    @Test func lastGateway_migratesFromUserDefaults() {
+        withLastGatewaySnapshot {
+            // Clear Keychain entry and plant legacy UserDefaults values.
+            applyKeychain([lastGatewayKeychainEntry: nil])
             applyDefaults([
                 "gateway.last.kind": nil,
                 "gateway.last.host": "example.org",
@@ -179,6 +180,11 @@ private func withLastGatewayDefaultsSnapshot(_ body: () -> Void) {
 
             let loaded = GatewaySettingsStore.loadLastGatewayConnection()
             #expect(loaded == .manual(host: "example.org", port: 18789, useTLS: false, stableID: "manual|example.org|18789"))
+
+            // Legacy keys should be cleaned up after migration.
+            let defaults = UserDefaults.standard
+            #expect(defaults.object(forKey: "gateway.last.stableID") == nil)
+            #expect(defaults.object(forKey: "gateway.last.host") == nil)
         }
     }
 

apps/ios/Tests/NodeAppModelInvokeTests.swift

@@ -416,6 +416,20 @@ private final class MockWatchMessagingService: @preconcurrency WatchMessagingSer
         #expect(appModel.openChatRequestID == 1)
     }
 
+    @Test @MainActor func handleDeepLinkCoalescesPromptWhenRateLimited() async throws {
+        let appModel = NodeAppModel()
+        appModel._test_setGatewayConnected(true)
+
+        await appModel.handleDeepLink(url: makeAgentDeepLinkURL(message: "first prompt"))
+        let firstPrompt = try #require(appModel.pendingAgentDeepLinkPrompt)
+
+        await appModel.handleDeepLink(url: makeAgentDeepLinkURL(message: "second prompt"))
+        let coalescedPrompt = try #require(appModel.pendingAgentDeepLinkPrompt)
+
+        #expect(coalescedPrompt.id != firstPrompt.id)
+        #expect(coalescedPrompt.messagePreview.contains("second prompt"))
+    }
+
     @Test @MainActor func handleDeepLinkStripsDeliveryFieldsWhenUnkeyed() async throws {
         let appModel = NodeAppModel()
         appModel._test_setGatewayConnected(true)

apps/ios/Tests/TalkModeConfigParsingTests.swift

@@ -1,3 +1,4 @@
+import Foundation
 import Testing
 @testable import OpenClaw
 
@@ -28,4 +29,22 @@ import Testing
         let selection = TalkModeManager.selectTalkProviderConfig(talk)
         #expect(selection == nil)
     }
+
+    @Test func detectsPCMFormatRejectionFromElevenLabsError() {
+        let error = NSError(
+            domain: "ElevenLabsTTS",
+            code: 403,
+            userInfo: [
+                NSLocalizedDescriptionKey: "ElevenLabs failed: 403 subscription_required output_format=pcm_44100",
+            ])
+        #expect(TalkModeManager._test_isPCMFormatRejectedByAPI(error))
+    }
+
+    @Test func ignoresGenericPlaybackFailuresForPCMFormatRejection() {
+        let error = NSError(
+            domain: "StreamingAudio",
+            code: -1,
+            userInfo: [NSLocalizedDescriptionKey: "queue enqueue failed"])
+        #expect(TalkModeManager._test_isPCMFormatRejectedByAPI(error) == false)
+    }
 }

apps/ios/Tests/TalkModeIncrementalSpeechBufferTests.swift

@@ -0,0 +1,28 @@
+import Testing
+@testable import OpenClaw
+
+@MainActor
+@Suite struct TalkModeIncrementalSpeechBufferTests {
+    @Test func emitsSoftBoundaryBeforeTerminalPunctuation() {
+        let manager = TalkModeManager(allowSimulatorCapture: true)
+        manager._test_incrementalReset()
+
+        let partial =
+            "We start speaking earlier by splitting this long stream chunk at a whitespace boundary before punctuation arrives"
+        let segments = manager._test_incrementalIngest(partial, isFinal: false)
+
+        #expect(segments.count == 1)
+        #expect(segments[0].count >= 72)
+        #expect(segments[0].count < partial.count)
+    }
+
+    @Test func keepsShortChunkBufferedWithoutPunctuation() {
+        let manager = TalkModeManager(allowSimulatorCapture: true)
+        manager._test_incrementalReset()
+
+        let short = "short chunk without punctuation"
+        let segments = manager._test_incrementalIngest(short, isFinal: false)
+
+        #expect(segments.isEmpty)
+    }
+}

apps/ios/project.yml

@@ -38,6 +38,8 @@ targets:
     dependencies:
       - target: OpenClawShareExtension
         embed: true
+      - target: OpenClawActivityWidget
+        embed: true
       - target: OpenClawWatchApp
       - package: OpenClawKit
       - package: OpenClawKit
@@ -84,6 +86,7 @@ targets:
         TARGETED_DEVICE_FAMILY: "1"
         SWIFT_VERSION: "6.0"
         SWIFT_STRICT_CONCURRENCY: complete
+        SUPPORTS_LIVE_ACTIVITIES: YES
         ENABLE_APPINTENTS_METADATA: NO
         ENABLE_APP_INTENTS_METADATA_GENERATION: NO
     info:
@@ -115,6 +118,7 @@ targets:
         NSLocationAlwaysAndWhenInUseUsageDescription: OpenClaw can share your location in the background when you enable Always.
         NSMicrophoneUsageDescription: OpenClaw needs microphone access for voice wake.
         NSSpeechRecognitionUsageDescription: OpenClaw uses on-device speech recognition for voice wake.
+        NSSupportsLiveActivities: true
         UISupportedInterfaceOrientations:
           - UIInterfaceOrientationPortrait
           - UIInterfaceOrientationPortraitUpsideDown
@@ -164,6 +168,37 @@ targets:
               NSExtensionActivationSupportsImageWithMaxCount: 10
               NSExtensionActivationSupportsMovieWithMaxCount: 1
 
+  OpenClawActivityWidget:
+    type: app-extension
+    platform: iOS
+    configFiles:
+      Debug: Signing.xcconfig
+      Release: Signing.xcconfig
+    sources:
+      - path: ActivityWidget
+      - path: Sources/LiveActivity/OpenClawActivityAttributes.swift
+    dependencies:
+      - sdk: WidgetKit.framework
+      - sdk: ActivityKit.framework
+    settings:
+      base:
+        CODE_SIGN_IDENTITY: "Apple Development"
+        CODE_SIGN_STYLE: "$(OPENCLAW_CODE_SIGN_STYLE)"
+        DEVELOPMENT_TEAM: "$(OPENCLAW_DEVELOPMENT_TEAM)"
+        PRODUCT_BUNDLE_IDENTIFIER: "$(OPENCLAW_ACTIVITY_WIDGET_BUNDLE_ID)"
+        SWIFT_VERSION: "6.0"
+        SWIFT_STRICT_CONCURRENCY: complete
+        SUPPORTS_LIVE_ACTIVITIES: YES
+    info:
+      path: ActivityWidget/Info.plist
+      properties:
+        CFBundleDisplayName: OpenClaw Activity
+        CFBundleShortVersionString: "2026.3.2"
+        CFBundleVersion: "20260301"
+        NSSupportsLiveActivities: true
+        NSExtension:
+          NSExtensionPointIdentifier: com.apple.widgetkit-extension
+
   OpenClawWatchApp:
     type: application.watchapp2
     platform: watchOS

apps/macos/Sources/OpenClaw/CameraCaptureService.swift

@@ -164,7 +164,7 @@ actor CameraCaptureService {
     }
 
     private func ensureAccess(for mediaType: AVMediaType) async throws {
-        if !(await CameraAuthorization.isAuthorized(for: mediaType)) {
+        if await !(CameraAuthorization.isAuthorized(for: mediaType)) {
             throw CameraError.permissionDenied(kind: mediaType == .video ? "Camera" : "Microphone")
         }
     }

apps/macos/Sources/OpenClaw/CanvasFileWatcher.swift

@@ -9,5 +9,4 @@ final class CanvasFileWatcher: @unchecked Sendable, SimpleFileWatcherOwner {
             queueLabel: "ai.openclaw.canvaswatcher",
             onChange: onChange))
     }
-
 }

apps/macos/Sources/OpenClaw/CanvasWindowController+Testing.swift

@@ -25,11 +25,22 @@ extension CanvasWindowController {
     }
 
     static func _testParseIPv4(_ host: String) -> (UInt8, UInt8, UInt8, UInt8)? {
-        LoopbackHost.parseIPv4(host)
+        let parts = host.split(separator: ".", omittingEmptySubsequences: false)
+        guard parts.count == 4 else { return nil }
+        let bytes: [UInt8] = parts.compactMap { UInt8($0) }
+        guard bytes.count == 4 else { return nil }
+        return (bytes[0], bytes[1], bytes[2], bytes[3])
     }
 
     static func _testIsLocalNetworkIPv4(_ ip: (UInt8, UInt8, UInt8, UInt8)) -> Bool {
-        LoopbackHost.isLocalNetworkIPv4(ip)
+        let (a, b, _, _) = ip
+        if a == 10 { return true }
+        if a == 172, (16...31).contains(Int(b)) { return true }
+        if a == 192, b == 168 { return true }
+        if a == 127 { return true }
+        if a == 169, b == 254 { return true }
+        if a == 100, (64...127).contains(Int(b)) { return true }
+        return false
     }
 
     static func _testIsLocalNetworkCanvasURL(_ url: URL) -> Bool {

apps/macos/Sources/OpenClaw/ConfigFileWatcher.swift

@@ -30,5 +30,4 @@ final class ConfigFileWatcher: @unchecked Sendable, SimpleFileWatcherOwner {
             },
             onChange: onChange))
     }
-
 }

apps/macos/Sources/OpenClaw/ExecSystemRunCommandValidator.swift

@@ -124,12 +124,12 @@ enum ExecSystemRunCommandValidator {
 
             let lower = token.lowercased()
             let flag = lower.split(separator: "=", maxSplits: 1).first.map(String.init) ?? lower
-                if ExecEnvOptions.flagOnly.contains(flag) {
+            if ExecEnvOptions.flagOnly.contains(flag) {
                 usesModifiers = true
                 idx += 1
                 continue
             }
-                if ExecEnvOptions.withValue.contains(flag) {
+            if ExecEnvOptions.withValue.contains(flag) {
                 usesModifiers = true
                 if !lower.contains("=") {
                     expectsOptionValue = true

apps/macos/Sources/OpenClaw/NodeMode/MacNodeLocationService.swift

@@ -39,11 +39,12 @@ final class MacNodeLocationService: NSObject, CLLocationManagerDelegate, Locatio
             desiredAccuracy: desiredAccuracy,
             maxAgeMs: maxAgeMs,
             timeoutMs: timeoutMs,
-            request: { try await self.requestLocationOnce() }) { timeoutMs, operation in
+            request: { try await self.requestLocationOnce() },
+            withTimeout: { timeoutMs, operation in
                 try await self.withTimeout(timeoutMs: timeoutMs) {
                     try await operation()
                 }
-        }
+            })
     }
 
     private func withTimeout<T: Sendable>(

apps/macos/Sources/OpenClaw/NodesMenu.swift

@@ -184,9 +184,9 @@ struct NodeMenuRowView: View {
 
             VStack(alignment: .leading, spacing: 2) {
                 HStack(alignment: .firstTextBaseline, spacing: 8) {
-                        Text(NodeMenuEntryFormatter.primaryName(self.entry))
-                            .font(.callout.weight(NodeMenuEntryFormatter.isConnected(self.entry) ? .semibold : .regular))
-                            .foregroundStyle(self.palette.primary)
+                    Text(NodeMenuEntryFormatter.primaryName(self.entry))
+                        .font(.callout.weight(NodeMenuEntryFormatter.isConnected(self.entry) ? .semibold : .regular))
+                        .foregroundStyle(self.palette.primary)
                         .lineLimit(1)
                         .truncationMode(.middle)
                         .layoutPriority(1)
@@ -195,9 +195,9 @@ struct NodeMenuRowView: View {
 
                     HStack(alignment: .firstTextBaseline, spacing: 6) {
                         if let right = NodeMenuEntryFormatter.headlineRight(self.entry) {
-                                Text(right)
-                                    .font(.caption.monospacedDigit())
-                                    .foregroundStyle(self.palette.secondary)
+                            Text(right)
+                                .font(.caption.monospacedDigit())
+                                .foregroundStyle(self.palette.secondary)
                                 .lineLimit(1)
                                 .truncationMode(.middle)
                                 .layoutPriority(2)

apps/macos/Sources/OpenClaw/NotifyOverlay.swift

@@ -64,9 +64,10 @@ final class NotifyOverlayController {
         OverlayPanelFactory.present(
             window: self.window,
             isVisible: &self.model.isVisible,
-            target: target) { window in
-                self.updateWindowFrame(animate: true)
-                window.orderFrontRegardless()
+            target: target)
+        { window in
+            self.updateWindowFrame(animate: true)
+            window.orderFrontRegardless()
         }
     }
 

apps/macos/Sources/OpenClaw/OnboardingView+Pages.swift

@@ -134,10 +134,10 @@ extension OnboardingView {
             if self.gatewayDiscovery.gateways.isEmpty {
                 ProgressView().controlSize(.small)
                 Button("Refresh") {
-                    self.gatewayDiscovery.refreshWideAreaFallbackNow(timeoutSeconds: 5.0)
+                    self.gatewayDiscovery.refreshRemoteFallbackNow(timeoutSeconds: 5.0)
                 }
                 .buttonStyle(.link)
-                .help("Retry Tailscale discovery (DNS-SD).")
+                .help("Retry remote discovery (Tailscale DNS-SD + Serve probe).")
             }
             Spacer(minLength: 0)
         }
@@ -311,7 +311,7 @@ extension OnboardingView {
                             .font(.caption.monospaced())
                             .foregroundStyle(.secondary)
                             .lineLimit(1)
-                        .truncationMode(.middle)
+                            .truncationMode(.middle)
                     }
                 }
                 Spacer(minLength: 0)

apps/macos/Sources/OpenClaw/PairingAlertSupport.swift

@@ -134,7 +134,8 @@ enum PairingAlertSupport {
         messageText: String,
         informativeText: String,
         alertHostWindow: inout NSWindow?,
-        completion: @escaping (NSApplication.ModalResponse, NSWindow) -> Void) -> NSAlert {
+        completion: @escaping (NSApplication.ModalResponse, NSWindow) -> Void) -> NSAlert
+    {
         NSApp.activate(ignoringOtherApps: true)
 
         let alert = NSAlert()
@@ -164,32 +165,6 @@ enum PairingAlertSupport {
             completion: completion)
     }
 
-    static func presentPairingAlert<Request>(
-        request: Request,
-        requestId: String,
-        messageText: String,
-        informativeText: String,
-        activeAlert: inout NSAlert?,
-        activeRequestId: inout String?,
-        alertHostWindow: inout NSWindow?,
-        clearActive: @escaping @MainActor (NSWindow) -> Void,
-        onResponse: @escaping @MainActor (NSApplication.ModalResponse, Request) async -> Void)
-    {
-        self.presentPairingAlert(
-            requestId: requestId,
-            messageText: messageText,
-            informativeText: informativeText,
-            activeAlert: &activeAlert,
-            activeRequestId: &activeRequestId,
-            alertHostWindow: &alertHostWindow)
-        { response, hostWindow in
-            Task { @MainActor in
-                clearActive(hostWindow)
-                await onResponse(response, request)
-            }
-        }
-    }
-
     static func presentPairingAlert<Request>(
         request: Request,
         requestId: String,
@@ -199,19 +174,18 @@ enum PairingAlertSupport {
         onResponse: @escaping @MainActor (NSApplication.ModalResponse, Request) async -> Void)
     {
         self.presentPairingAlert(
-            request: request,
             requestId: requestId,
             messageText: messageText,
             informativeText: informativeText,
             activeAlert: &state.activeAlert,
             activeRequestId: &state.activeRequestId,
-            alertHostWindow: &state.alertHostWindow)
-        { response, hostWindow in
-            Task { @MainActor in
-                self.clearActivePairingAlert(state: state, hostWindow: hostWindow)
-                await onResponse(response, request)
-            }
-        }
+            alertHostWindow: &state.alertHostWindow,
+            completion: { response, hostWindow in
+                Task { @MainActor in
+                    self.clearActivePairingAlert(state: state, hostWindow: hostWindow)
+                    await onResponse(response, request)
+                }
+            })
     }
 
     static func clearActivePairingAlert(
@@ -231,12 +205,12 @@ enum PairingAlertSupport {
             hostWindow: hostWindow)
     }
 
-    static func stopPairingPrompter<Request>(
+    static func stopPairingPrompter(
         isStopping: inout Bool,
         activeAlert: inout NSAlert?,
         activeRequestId: inout String?,
         task: inout Task<Void, Never>?,
-        queue: inout [Request],
+        queue: inout [some Any],
         isPresenting: inout Bool,
         alertHostWindow: inout NSWindow?)
     {
@@ -252,10 +226,10 @@ enum PairingAlertSupport {
         alertHostWindow = nil
     }
 
-    static func stopPairingPrompter<Request>(
+    static func stopPairingPrompter(
         isStopping: inout Bool,
         task: inout Task<Void, Never>?,
-        queue: inout [Request],
+        queue: inout [some Any],
         isPresenting: inout Bool,
         state: PairingAlertState)
     {

apps/macos/Sources/OpenClaw/PeekabooBridgeHostCoordinator.swift

@@ -36,6 +36,7 @@ final class PeekabooBridgeHostCoordinator {
             ?? fileManager.homeDirectoryForCurrentUser.appendingPathComponent("Library/Application Support")
         return Self.legacySocketDirectoryNames.map { Self.makeSocketPath(for: $0, in: base) }
     }
+
     func setEnabled(_ enabled: Bool) async {
         if enabled {
             await self.startIfNeeded()
@@ -85,7 +86,7 @@ final class PeekabooBridgeHostCoordinator {
     }
 
     private func ensureLegacySocketSymlinks() {
-        Self.legacySocketPaths.forEach { legacyPath in
+        for legacyPath in Self.legacySocketPaths {
             self.ensureLegacySocketSymlink(at: legacyPath)
         }
     }
@@ -116,7 +117,9 @@ final class PeekabooBridgeHostCoordinator {
             }
             try fileManager.createSymbolicLink(atPath: legacyPath, withDestinationPath: Self.openclawSocketPath)
         } catch {
-            self.logger.debug("Failed to create legacy PeekabooBridge socket symlink: \(error.localizedDescription, privacy: .public)")
+            let message = "Failed to create legacy PeekabooBridge socket symlink: \(error.localizedDescription)"
+            self.logger
+                .debug("\(message, privacy: .public)")
         }
     }
 

apps/macos/Sources/OpenClaw/TalkOverlay.swift

@@ -33,9 +33,10 @@ final class TalkOverlayController {
         OverlayPanelFactory.present(
             window: self.window,
             isVisible: &self.model.isVisible,
-            target: target) { window in
-                window.setFrame(target, display: true)
-                window.orderFrontRegardless()
+            target: target)
+        { window in
+            window.setFrame(target, display: true)
+            window.orderFrontRegardless()
         }
     }
 

apps/macos/Sources/OpenClaw/UsageCostData.swift

@@ -77,14 +77,14 @@ struct GatewayCostUsageDay: Codable {
     init(from decoder: Decoder) throws {
         let c = try decoder.container(keyedBy: CodingKeys.self)
         self.date = try c.decode(String.self, forKey: .date)
-        self.totals = GatewayCostUsageTotals(
-            input: try c.decode(Int.self, forKey: .input),
-            output: try c.decode(Int.self, forKey: .output),
-            cacheRead: try c.decode(Int.self, forKey: .cacheRead),
-            cacheWrite: try c.decode(Int.self, forKey: .cacheWrite),
-            totalTokens: try c.decode(Int.self, forKey: .totalTokens),
-            totalCost: try c.decode(Double.self, forKey: .totalCost),
-            missingCostEntries: try c.decode(Int.self, forKey: .missingCostEntries))
+        self.totals = try GatewayCostUsageTotals(
+            input: c.decode(Int.self, forKey: .input),
+            output: c.decode(Int.self, forKey: .output),
+            cacheRead: c.decode(Int.self, forKey: .cacheRead),
+            cacheWrite: c.decode(Int.self, forKey: .cacheWrite),
+            totalTokens: c.decode(Int.self, forKey: .totalTokens),
+            totalCost: c.decode(Double.self, forKey: .totalCost),
+            missingCostEntries: c.decode(Int.self, forKey: .missingCostEntries))
     }
 
     func encode(to encoder: Encoder) throws {

apps/macos/Sources/OpenClaw/VoicePushToTalk.swift

@@ -172,9 +172,9 @@ actor VoicePushToTalk {
         let adoptedPrefix = self.adoptedPrefix
         let adoptedAttributed: NSAttributedString? = adoptedPrefix.isEmpty ? nil : VoiceOverlayTextFormatting
             .makeAttributed(
-            committed: adoptedPrefix,
-            volatile: "",
-            isFinal: false)
+                committed: adoptedPrefix,
+                volatile: "",
+                isFinal: false)
         self.overlayToken = await MainActor.run {
             VoiceSessionCoordinator.shared.startSession(
                 source: .pushToTalk,
@@ -406,5 +406,4 @@ actor VoicePushToTalk {
         if suffix.isEmpty { return prefix }
         return "\(prefix) \(suffix)"
     }
-
 }

apps/macos/Sources/OpenClaw/VoiceWakeOverlayController+Window.swift

@@ -23,10 +23,11 @@ extension VoiceWakeOverlayController {
                     "overlay present windowShown textLen=\(self.model.text.count, privacy: .public)")
                 // Keep the status item in “listening” mode until we explicitly dismiss the overlay.
                 AppStateStore.shared.triggerVoiceEars(ttl: nil)
-            }) { window in
+            },
+            onAlreadyVisible: { window in
                 self.updateWindowFrame(animate: true)
                 window.orderFrontRegardless()
-        }
+            })
     }
 
     private func ensureWindow() {

apps/macos/Sources/OpenClaw/VoiceWakeRuntime.swift

@@ -773,5 +773,4 @@ actor VoiceWakeRuntime {
     }
 
     #endif
-
 }

apps/macos/Sources/OpenClawDiscovery/GatewayDiscoveryModel.swift

@@ -76,6 +76,8 @@ public final class GatewayDiscoveryModel {
     private var pendingServiceResolvers: [String: GatewayServiceResolver] = [:]
     private var wideAreaFallbackTask: Task<Void, Never>?
     private var wideAreaFallbackGateways: [DiscoveredGateway] = []
+    private var tailscaleServeFallbackTask: Task<Void, Never>?
+    private var tailscaleServeFallbackGateways: [DiscoveredGateway] = []
     private let logger = Logger(subsystem: "ai.openclaw", category: "gateway-discovery")
 
     public init(
@@ -111,6 +113,7 @@ public final class GatewayDiscoveryModel {
         }
 
         self.scheduleWideAreaFallback()
+        self.scheduleTailscaleServeFallback()
     }
 
     public func refreshWideAreaFallbackNow(timeoutSeconds: TimeInterval = 5.0) {
@@ -126,6 +129,23 @@ public final class GatewayDiscoveryModel {
         }
     }
 
+    public func refreshTailscaleServeFallbackNow(timeoutSeconds: TimeInterval = 5.0) {
+        Task.detached(priority: .utility) { [weak self] in
+            guard let self else { return }
+            let beacons = await TailscaleServeGatewayDiscovery.discover(timeoutSeconds: timeoutSeconds)
+            await MainActor.run { [weak self] in
+                guard let self else { return }
+                self.tailscaleServeFallbackGateways = self.mapTailscaleServeBeacons(beacons)
+                self.recomputeGateways()
+            }
+        }
+    }
+
+    public func refreshRemoteFallbackNow(timeoutSeconds: TimeInterval = 5.0) {
+        self.refreshWideAreaFallbackNow(timeoutSeconds: timeoutSeconds)
+        self.refreshTailscaleServeFallbackNow(timeoutSeconds: timeoutSeconds)
+    }
+
     public func stop() {
         for browser in self.browsers.values {
             browser.cancel()
@@ -140,6 +160,9 @@ public final class GatewayDiscoveryModel {
         self.wideAreaFallbackTask?.cancel()
         self.wideAreaFallbackTask = nil
         self.wideAreaFallbackGateways = []
+        self.tailscaleServeFallbackTask?.cancel()
+        self.tailscaleServeFallbackTask = nil
+        self.tailscaleServeFallbackGateways = []
         self.gateways = []
         self.statusText = "Stopped"
     }
@@ -168,22 +191,45 @@ public final class GatewayDiscoveryModel {
         }
     }
 
+    private func mapTailscaleServeBeacons(
+        _ beacons: [TailscaleServeGatewayBeacon]) -> [DiscoveredGateway]
+    {
+        beacons.map { beacon in
+            let stableID = "tailscale-serve|\(beacon.tailnetDns.lowercased())"
+            let isLocal = Self.isLocalGateway(
+                lanHost: nil,
+                tailnetDns: beacon.tailnetDns,
+                displayName: beacon.displayName,
+                serviceName: nil,
+                local: self.localIdentity)
+            return DiscoveredGateway(
+                displayName: beacon.displayName,
+                serviceHost: beacon.host,
+                servicePort: beacon.port,
+                lanHost: nil,
+                tailnetDns: beacon.tailnetDns,
+                sshPort: 22,
+                gatewayPort: beacon.port,
+                cliPath: nil,
+                stableID: stableID,
+                debugID: "\(beacon.host):\(beacon.port)",
+                isLocal: isLocal)
+        }
+    }
+
     private func recomputeGateways() {
         let primary = self.sortedDeduped(gateways: self.gatewaysByDomain.values.flatMap(\.self))
         let primaryFiltered = self.filterLocalGateways ? primary.filter { !$0.isLocal } : primary
-        if !primaryFiltered.isEmpty {
-            self.gateways = primaryFiltered
-            return
-        }
 
         // Bonjour can return only "local" results for the wide-area domain (or no results at all),
-        // which makes onboarding look empty even though Tailscale DNS-SD can already see gateways.
-        guard !self.wideAreaFallbackGateways.isEmpty else {
+        // and cross-network setups may rely on Tailscale Serve without DNS-SD.
+        let fallback = self.wideAreaFallbackGateways + self.tailscaleServeFallbackGateways
+        guard !fallback.isEmpty else {
             self.gateways = primaryFiltered
             return
         }
 
-        let combined = self.sortedDeduped(gateways: primary + self.wideAreaFallbackGateways)
+        let combined = self.sortedDeduped(gateways: primary + fallback)
         self.gateways = self.filterLocalGateways ? combined.filter { !$0.isLocal } : combined
     }
 
@@ -284,6 +330,39 @@ public final class GatewayDiscoveryModel {
         }
     }
 
+    private func scheduleTailscaleServeFallback() {
+        if Self.isRunningTests { return }
+        guard self.tailscaleServeFallbackTask == nil else { return }
+        self.tailscaleServeFallbackTask = Task.detached(priority: .utility) { [weak self] in
+            guard let self else { return }
+            var attempt = 0
+            let startedAt = Date()
+            while !Task.isCancelled, Date().timeIntervalSince(startedAt) < 35.0 {
+                let hasResults = await MainActor.run {
+                    if self.filterLocalGateways {
+                        return !self.gateways.isEmpty
+                    }
+                    return self.gateways.contains(where: { !$0.isLocal })
+                }
+                if hasResults { return }
+
+                let beacons = await TailscaleServeGatewayDiscovery.discover(timeoutSeconds: 2.4)
+                if !beacons.isEmpty {
+                    await MainActor.run { [weak self] in
+                        guard let self else { return }
+                        self.tailscaleServeFallbackGateways = self.mapTailscaleServeBeacons(beacons)
+                        self.recomputeGateways()
+                    }
+                    return
+                }
+
+                attempt += 1
+                let backoff = min(8.0, 0.8 + (Double(attempt) * 0.8))
+                try? await Task.sleep(nanoseconds: UInt64(backoff * 1_000_000_000))
+            }
+        }
+    }
+
     private var hasUsableWideAreaResults: Bool {
         guard let domain = OpenClawBonjour.wideAreaGatewayServiceDomain else { return false }
         guard let gateways = self.gatewaysByDomain[domain], !gateways.isEmpty else { return false }
@@ -291,11 +370,25 @@ public final class GatewayDiscoveryModel {
         return gateways.contains(where: { !$0.isLocal })
     }
 
+    static func dedupeKey(for gateway: DiscoveredGateway) -> String {
+        if let host = gateway.serviceHost?
+            .trimmingCharacters(in: .whitespacesAndNewlines)
+            .lowercased(),
+           !host.isEmpty,
+           let port = gateway.servicePort,
+           port > 0
+        {
+            return "endpoint|\(host):\(port)"
+        }
+        return "stable|\(gateway.stableID)"
+    }
+
     private func sortedDeduped(gateways: [DiscoveredGateway]) -> [DiscoveredGateway] {
         var seen = Set<String>()
         let deduped = gateways.filter { gateway in
-            if seen.contains(gateway.stableID) { return false }
-            seen.insert(gateway.stableID)
+            let key = Self.dedupeKey(for: gateway)
+            if seen.contains(key) { return false }
+            seen.insert(key)
             return true
         }
         return deduped.sorted {

apps/macos/Sources/OpenClawDiscovery/TailscaleNetwork.swift

@@ -13,8 +13,8 @@ public enum TailscaleNetwork {
     }
 
     public static func detectTailnetIPv4() -> String? {
-        for entry in NetworkInterfaceIPv4.addresses() {
-            if self.isTailnetIPv4(entry.ip) { return entry.ip }
+        for entry in NetworkInterfaceIPv4.addresses() where self.isTailnetIPv4(entry.ip) {
+            return entry.ip
         }
         return nil
     }

apps/macos/Sources/OpenClawDiscovery/TailscaleServeGatewayDiscovery.swift

@@ -0,0 +1,315 @@
+import Foundation
+import OpenClawKit
+
+struct TailscaleServeGatewayBeacon: Sendable, Equatable {
+    var displayName: String
+    var tailnetDns: String
+    var host: String
+    var port: Int
+}
+
+enum TailscaleServeGatewayDiscovery {
+    private static let maxCandidates = 32
+    private static let probeConcurrency = 6
+    private static let defaultProbeTimeoutSeconds: TimeInterval = 1.6
+
+    struct DiscoveryContext: Sendable {
+        var tailscaleStatus: @Sendable () async -> String?
+        var probeHost: @Sendable (_ host: String, _ timeout: TimeInterval) async -> Bool
+
+        static let live = DiscoveryContext(
+            tailscaleStatus: { await readTailscaleStatus() },
+            probeHost: { host, timeout in
+                await probeHostForGatewayChallenge(host: host, timeout: timeout)
+            })
+    }
+
+    static func discover(
+        timeoutSeconds: TimeInterval = 3.0,
+        context: DiscoveryContext = .live) async -> [TailscaleServeGatewayBeacon]
+    {
+        guard timeoutSeconds > 0 else { return [] }
+        guard let statusJson = await context.tailscaleStatus(),
+              let status = parseStatus(statusJson)
+        else {
+            return []
+        }
+
+        let candidates = self.collectCandidates(status: status)
+        if candidates.isEmpty { return [] }
+
+        let deadline = Date().addingTimeInterval(timeoutSeconds)
+        let perProbeTimeout = min(self.defaultProbeTimeoutSeconds, max(0.5, timeoutSeconds * 0.45))
+
+        var byHost: [String: TailscaleServeGatewayBeacon] = [:]
+        await withTaskGroup(of: TailscaleServeGatewayBeacon?.self) { group in
+            var index = 0
+            let workerCount = min(self.probeConcurrency, candidates.count)
+
+            func submitOne() {
+                guard index < candidates.count else { return }
+                let candidate = candidates[index]
+                index += 1
+                group.addTask {
+                    let remaining = deadline.timeIntervalSinceNow
+                    if remaining <= 0 {
+                        return nil
+                    }
+                    let timeout = min(perProbeTimeout, remaining)
+                    let reachable = await context.probeHost(candidate.dnsName, timeout)
+                    if !reachable {
+                        return nil
+                    }
+                    return TailscaleServeGatewayBeacon(
+                        displayName: candidate.displayName,
+                        tailnetDns: candidate.dnsName,
+                        host: candidate.dnsName,
+                        port: 443)
+                }
+            }
+
+            for _ in 0..<workerCount {
+                submitOne()
+            }
+
+            while let beacon = await group.next() {
+                if let beacon {
+                    byHost[beacon.host.lowercased()] = beacon
+                }
+                submitOne()
+            }
+        }
+
+        return byHost.values.sorted {
+            $0.displayName.localizedCaseInsensitiveCompare($1.displayName) == .orderedAscending
+        }
+    }
+
+    private struct Candidate: Sendable {
+        var dnsName: String
+        var displayName: String
+    }
+
+    private static func collectCandidates(status: TailscaleStatus) -> [Candidate] {
+        let selfDns = normalizeDnsName(status.selfNode?.dnsName)
+        var out: [Candidate] = []
+        var seen = Set<String>()
+
+        for node in status.peer.values {
+            if node.online == false {
+                continue
+            }
+            guard let dnsName = normalizeDnsName(node.dnsName) else {
+                continue
+            }
+            if dnsName == selfDns {
+                continue
+            }
+            if seen.contains(dnsName) {
+                continue
+            }
+            seen.insert(dnsName)
+
+            out.append(Candidate(
+                dnsName: dnsName,
+                displayName: displayName(hostName: node.hostName, dnsName: dnsName)))
+
+            if out.count >= self.maxCandidates {
+                break
+            }
+        }
+
+        return out
+    }
+
+    private static func displayName(hostName: String?, dnsName: String) -> String {
+        if let hostName {
+            let trimmed = hostName.trimmingCharacters(in: .whitespacesAndNewlines)
+            if !trimmed.isEmpty {
+                return trimmed
+            }
+        }
+        return dnsName
+            .split(separator: ".")
+            .first
+            .map(String.init) ?? dnsName
+    }
+
+    private static func normalizeDnsName(_ raw: String?) -> String? {
+        guard let raw else { return nil }
+        let trimmed = raw.trimmingCharacters(in: .whitespacesAndNewlines)
+        if trimmed.isEmpty { return nil }
+        let withoutDot = trimmed.hasSuffix(".") ? String(trimmed.dropLast()) : trimmed
+        let lower = withoutDot.lowercased()
+        return lower.isEmpty ? nil : lower
+    }
+
+    private static func readTailscaleStatus() async -> String? {
+        let candidates = [
+            "/usr/local/bin/tailscale",
+            "/opt/homebrew/bin/tailscale",
+            "/Applications/Tailscale.app/Contents/MacOS/Tailscale",
+            "tailscale",
+        ]
+
+        for candidate in candidates {
+            guard let executable = self.resolveExecutablePath(candidate) else { continue }
+            if let stdout = await self.run(path: executable, args: ["status", "--json"], timeout: 1.0) {
+                return stdout
+            }
+        }
+
+        return nil
+    }
+
+    static func resolveExecutablePath(
+        _ candidate: String,
+        env: [String: String] = ProcessInfo.processInfo.environment) -> String?
+    {
+        let trimmed = candidate.trimmingCharacters(in: .whitespacesAndNewlines)
+        guard !trimmed.isEmpty else { return nil }
+
+        let fileManager = FileManager.default
+        let hasPathSeparator = trimmed.contains("/")
+        if hasPathSeparator {
+            return fileManager.isExecutableFile(atPath: trimmed) ? trimmed : nil
+        }
+
+        let pathRaw = env["PATH"] ?? ""
+        let entries = pathRaw.split(separator: ":").map(String.init)
+        for entry in entries {
+            let dir = entry.trimmingCharacters(in: .whitespacesAndNewlines)
+            if dir.isEmpty { continue }
+            let fullPath = URL(fileURLWithPath: dir)
+                .appendingPathComponent(trimmed)
+                .path
+            if fileManager.isExecutableFile(atPath: fullPath) {
+                return fullPath
+            }
+        }
+
+        return nil
+    }
+
+    private static func run(path: String, args: [String], timeout: TimeInterval) async -> String? {
+        await withCheckedContinuation { continuation in
+            DispatchQueue.global(qos: .utility).async {
+                continuation.resume(returning: self.runBlocking(path: path, args: args, timeout: timeout))
+            }
+        }
+    }
+
+    private static func runBlocking(path: String, args: [String], timeout: TimeInterval) -> String? {
+        let process = Process()
+        process.executableURL = URL(fileURLWithPath: path)
+        process.arguments = args
+        let outPipe = Pipe()
+        process.standardOutput = outPipe
+        process.standardError = FileHandle.nullDevice
+
+        do {
+            try process.run()
+        } catch {
+            return nil
+        }
+
+        let deadline = Date().addingTimeInterval(timeout)
+        while process.isRunning, Date() < deadline {
+            Thread.sleep(forTimeInterval: 0.02)
+        }
+        if process.isRunning {
+            process.terminate()
+        }
+        process.waitUntilExit()
+
+        let data = (try? outPipe.fileHandleForReading.readToEnd()) ?? Data()
+        let output = String(data: data, encoding: .utf8)?.trimmingCharacters(in: .whitespacesAndNewlines)
+        return output?.isEmpty == false ? output : nil
+    }
+
+    private static func parseStatus(_ raw: String) -> TailscaleStatus? {
+        guard let data = raw.data(using: .utf8) else { return nil }
+        return try? JSONDecoder().decode(TailscaleStatus.self, from: data)
+    }
+
+    private static func probeHostForGatewayChallenge(host: String, timeout: TimeInterval) async -> Bool {
+        var components = URLComponents()
+        components.scheme = "wss"
+        components.host = host
+        guard let url = components.url else { return false }
+
+        let config = URLSessionConfiguration.ephemeral
+        config.timeoutIntervalForRequest = max(0.5, timeout)
+        config.timeoutIntervalForResource = max(0.5, timeout)
+        let session = URLSession(configuration: config)
+        let task = session.webSocketTask(with: url)
+        task.resume()
+
+        defer {
+            task.cancel(with: .goingAway, reason: nil)
+            session.invalidateAndCancel()
+        }
+
+        do {
+            return try await AsyncTimeout.withTimeout(
+                seconds: timeout,
+                onTimeout: { NSError(domain: "TailscaleServeDiscovery", code: 1, userInfo: nil) },
+                operation: {
+                    while true {
+                        let message = try await task.receive()
+                        if isConnectChallenge(message: message) {
+                            return true
+                        }
+                    }
+                })
+        } catch {
+            return false
+        }
+    }
+
+    private static func isConnectChallenge(message: URLSessionWebSocketTask.Message) -> Bool {
+        let data: Data
+        switch message {
+        case let .data(value):
+            data = value
+        case let .string(value):
+            guard let encoded = value.data(using: .utf8) else { return false }
+            data = encoded
+        @unknown default:
+            return false
+        }
+
+        guard let object = try? JSONSerialization.jsonObject(with: data),
+              let dict = object as? [String: Any],
+              let type = dict["type"] as? String,
+              type == "event",
+              let event = dict["event"] as? String
+        else {
+            return false
+        }
+
+        return event == "connect.challenge"
+    }
+}
+
+private struct TailscaleStatus: Decodable {
+    struct Node: Decodable {
+        let dnsName: String?
+        let hostName: String?
+        let online: Bool?
+
+        private enum CodingKeys: String, CodingKey {
+            case dnsName = "DNSName"
+            case hostName = "HostName"
+            case online = "Online"
+        }
+    }
+
+    let selfNode: Node?
+    let peer: [String: Node]
+
+    private enum CodingKeys: String, CodingKey {
+        case selfNode = "Self"
+        case peer = "Peer"
+    }
+}

apps/macos/Sources/OpenClawProtocol/GatewayModels.swift

@@ -1030,6 +1030,74 @@ public struct PushTestResult: Codable, Sendable {
     }
 }
 
+public struct SecretsReloadParams: Codable, Sendable {}
+
+public struct SecretsResolveParams: Codable, Sendable {
+    public let commandname: String
+    public let targetids: [String]
+
+    public init(
+        commandname: String,
+        targetids: [String])
+    {
+        self.commandname = commandname
+        self.targetids = targetids
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case commandname = "commandName"
+        case targetids = "targetIds"
+    }
+}
+
+public struct SecretsResolveAssignment: Codable, Sendable {
+    public let path: String?
+    public let pathsegments: [String]
+    public let value: AnyCodable
+
+    public init(
+        path: String?,
+        pathsegments: [String],
+        value: AnyCodable)
+    {
+        self.path = path
+        self.pathsegments = pathsegments
+        self.value = value
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case path
+        case pathsegments = "pathSegments"
+        case value
+    }
+}
+
+public struct SecretsResolveResult: Codable, Sendable {
+    public let ok: Bool?
+    public let assignments: [SecretsResolveAssignment]?
+    public let diagnostics: [String]?
+    public let inactiverefpaths: [String]?
+
+    public init(
+        ok: Bool?,
+        assignments: [SecretsResolveAssignment]?,
+        diagnostics: [String]?,
+        inactiverefpaths: [String]?)
+    {
+        self.ok = ok
+        self.assignments = assignments
+        self.diagnostics = diagnostics
+        self.inactiverefpaths = inactiverefpaths
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case ok
+        case assignments
+        case diagnostics
+        case inactiverefpaths = "inactiveRefPaths"
+    }
+}
+
 public struct SessionsListParams: Codable, Sendable {
     public let limit: Int?
     public let activeminutes: Int?

apps/macos/Tests/OpenClawIPCTests/GatewayDiscoveryModelTests.swift

@@ -1,4 +1,4 @@
-import OpenClawDiscovery
+@testable import OpenClawDiscovery
 import Testing
 
 @Suite
@@ -121,4 +121,50 @@ struct GatewayDiscoveryModelTests {
             host: "studio.local",
             port: 2201) == "peter@studio.local:2201")
     }
+
+    @Test func dedupeKeyPrefersResolvedEndpointAcrossSources() {
+        let wideArea = GatewayDiscoveryModel.DiscoveredGateway(
+            displayName: "Gateway",
+            serviceHost: "gateway-host.tailnet-example.ts.net",
+            servicePort: 443,
+            lanHost: nil,
+            tailnetDns: "gateway-host.tailnet-example.ts.net",
+            sshPort: 22,
+            gatewayPort: 443,
+            cliPath: nil,
+            stableID: "wide-area|openclaw.internal.|gateway-host",
+            debugID: "wide-area",
+            isLocal: false)
+        let serve = GatewayDiscoveryModel.DiscoveredGateway(
+            displayName: "Gateway",
+            serviceHost: "gateway-host.tailnet-example.ts.net",
+            servicePort: 443,
+            lanHost: nil,
+            tailnetDns: "gateway-host.tailnet-example.ts.net",
+            sshPort: 22,
+            gatewayPort: 443,
+            cliPath: nil,
+            stableID: "tailscale-serve|gateway-host.tailnet-example.ts.net",
+            debugID: "serve",
+            isLocal: false)
+
+        #expect(GatewayDiscoveryModel.dedupeKey(for: wideArea) == GatewayDiscoveryModel.dedupeKey(for: serve))
+    }
+
+    @Test func dedupeKeyFallsBackToStableIDWithoutEndpoint() {
+        let unresolved = GatewayDiscoveryModel.DiscoveredGateway(
+            displayName: "Gateway",
+            serviceHost: nil,
+            servicePort: nil,
+            lanHost: nil,
+            tailnetDns: "gateway-host.tailnet-example.ts.net",
+            sshPort: 22,
+            gatewayPort: nil,
+            cliPath: nil,
+            stableID: "tailscale-serve|gateway-host.tailnet-example.ts.net",
+            debugID: "serve",
+            isLocal: false)
+
+        #expect(GatewayDiscoveryModel.dedupeKey(for: unresolved) == "stable|tailscale-serve|gateway-host.tailnet-example.ts.net")
+    }
 }

apps/macos/Tests/OpenClawIPCTests/TailscaleServeGatewayDiscoveryTests.swift

@@ -0,0 +1,77 @@
+import Foundation
+import Testing
+@testable import OpenClawDiscovery
+
+@Suite
+struct TailscaleServeGatewayDiscoveryTests {
+    @Test func discoversServeGatewayFromTailnetPeers() async {
+        let statusJson = """
+        {
+          "Self": {
+            "DNSName": "local-mac.tailnet-example.ts.net.",
+            "HostName": "local-mac",
+            "Online": true
+          },
+          "Peer": {
+            "peer-1": {
+              "DNSName": "gateway-host.tailnet-example.ts.net.",
+              "HostName": "gateway-host",
+              "Online": true
+            },
+            "peer-2": {
+              "DNSName": "offline.tailnet-example.ts.net.",
+              "HostName": "offline-box",
+              "Online": false
+            },
+            "peer-3": {
+              "DNSName": "local-mac.tailnet-example.ts.net.",
+              "HostName": "local-mac",
+              "Online": true
+            }
+          }
+        }
+        """
+
+        let context = TailscaleServeGatewayDiscovery.DiscoveryContext(
+            tailscaleStatus: { statusJson },
+            probeHost: { host, _ in
+                host == "gateway-host.tailnet-example.ts.net"
+            })
+
+        let beacons = await TailscaleServeGatewayDiscovery.discover(timeoutSeconds: 2.0, context: context)
+        #expect(beacons.count == 1)
+        #expect(beacons.first?.displayName == "gateway-host")
+        #expect(beacons.first?.tailnetDns == "gateway-host.tailnet-example.ts.net")
+        #expect(beacons.first?.host == "gateway-host.tailnet-example.ts.net")
+        #expect(beacons.first?.port == 443)
+    }
+
+    @Test func returnsEmptyWhenStatusUnavailable() async {
+        let context = TailscaleServeGatewayDiscovery.DiscoveryContext(
+            tailscaleStatus: { nil },
+            probeHost: { _, _ in true })
+
+        let beacons = await TailscaleServeGatewayDiscovery.discover(timeoutSeconds: 2.0, context: context)
+        #expect(beacons.isEmpty)
+    }
+
+    @Test func resolvesBareExecutableFromPATH() throws {
+        let tempDir = FileManager.default.temporaryDirectory
+            .appendingPathComponent(UUID().uuidString)
+        try FileManager.default.createDirectory(at: tempDir, withIntermediateDirectories: true)
+        defer { try? FileManager.default.removeItem(at: tempDir) }
+
+        let executable = tempDir.appendingPathComponent("tailscale")
+        try "#!/bin/sh\necho ok\n".write(to: executable, atomically: true, encoding: .utf8)
+        try FileManager.default.setAttributes([.posixPermissions: 0o755], ofItemAtPath: executable.path)
+
+        let env: [String: String] = ["PATH": tempDir.path]
+        let resolved = TailscaleServeGatewayDiscovery.resolveExecutablePath("tailscale", env: env)
+        #expect(resolved == executable.path)
+    }
+
+    @Test func rejectsMissingExecutableCandidate() {
+        #expect(TailscaleServeGatewayDiscovery.resolveExecutablePath("", env: [:]) == nil)
+        #expect(TailscaleServeGatewayDiscovery.resolveExecutablePath("definitely-not-here", env: ["PATH": "/tmp"]) == nil)
+    }
+}

apps/shared/OpenClawKit/Sources/OpenClawKit/GatewayTLSPinning.swift

@@ -17,23 +17,41 @@ public struct GatewayTLSParams: Sendable {
 }
 
 public enum GatewayTLSStore {
-    private static let suiteName = "ai.openclaw.shared"
-    private static let keyPrefix = "gateway.tls."
+    private static let keychainService = "ai.openclaw.tls-pinning"
 
-    private static var defaults: UserDefaults {
-        UserDefaults(suiteName: suiteName) ?? .standard
-    }
+    // Legacy UserDefaults location used before Keychain migration.
+    private static let legacySuiteName = "ai.openclaw.shared"
+    private static let legacyKeyPrefix = "gateway.tls."
 
     public static func loadFingerprint(stableID: String) -> String? {
-        let key = self.keyPrefix + stableID
-        let raw = self.defaults.string(forKey: key)?.trimmingCharacters(in: .whitespacesAndNewlines)
+        self.migrateFromUserDefaultsIfNeeded(stableID: stableID)
+        let raw = GenericPasswordKeychainStore.loadString(service: self.keychainService, account: stableID)?
+            .trimmingCharacters(in: .whitespacesAndNewlines)
         if raw?.isEmpty == false { return raw }
         return nil
     }
 
     public static func saveFingerprint(_ value: String, stableID: String) {
-        let key = self.keyPrefix + stableID
-        self.defaults.set(value, forKey: key)
+        _ = GenericPasswordKeychainStore.saveString(value, service: self.keychainService, account: stableID)
+    }
+
+    // MARK: - Migration
+
+    /// On first Keychain read for a given stableID, move any legacy UserDefaults
+    /// fingerprint into Keychain and remove the old entry.
+    private static func migrateFromUserDefaultsIfNeeded(stableID: String) {
+        guard let defaults = UserDefaults(suiteName: self.legacySuiteName) else { return }
+        let legacyKey = self.legacyKeyPrefix + stableID
+        guard let existing = defaults.string(forKey: legacyKey)?
+            .trimmingCharacters(in: .whitespacesAndNewlines),
+            !existing.isEmpty
+        else { return }
+        if GenericPasswordKeychainStore.loadString(service: self.keychainService, account: stableID) == nil {
+            guard GenericPasswordKeychainStore.saveString(existing, service: self.keychainService, account: stableID) else {
+                return
+            }
+        }
+        defaults.removeObject(forKey: legacyKey)
     }
 }
 

apps/shared/OpenClawKit/Sources/OpenClawKit/GenericPasswordKeychainStore.swift

@@ -0,0 +1,77 @@
+import Foundation
+import Security
+
+public enum GenericPasswordKeychainStore {
+    public static func loadString(service: String, account: String) -> String? {
+        guard let data = self.loadData(service: service, account: account) else { return nil }
+        return String(data: data, encoding: .utf8)
+    }
+
+    @discardableResult
+    public static func saveString(
+        _ value: String,
+        service: String,
+        account: String,
+        accessible: CFString = kSecAttrAccessibleAfterFirstUnlockThisDeviceOnly
+    ) -> Bool {
+        self.saveData(Data(value.utf8), service: service, account: account, accessible: accessible)
+    }
+
+    @discardableResult
+    public static func delete(service: String, account: String) -> Bool {
+        let query = self.baseQuery(service: service, account: account)
+        let status = SecItemDelete(query as CFDictionary)
+        return status == errSecSuccess || status == errSecItemNotFound
+    }
+
+    private static func loadData(service: String, account: String) -> Data? {
+        var query = self.baseQuery(service: service, account: account)
+        query[kSecReturnData as String] = true
+        query[kSecMatchLimit as String] = kSecMatchLimitOne
+
+        var item: CFTypeRef?
+        let status = SecItemCopyMatching(query as CFDictionary, &item)
+        guard status == errSecSuccess, let data = item as? Data else { return nil }
+        return data
+    }
+
+    @discardableResult
+    private static func saveData(
+        _ data: Data,
+        service: String,
+        account: String,
+        accessible: CFString
+    ) -> Bool {
+        let query = self.baseQuery(service: service, account: account)
+        let previousData = self.loadData(service: service, account: account)
+
+        let deleteStatus = SecItemDelete(query as CFDictionary)
+        guard deleteStatus == errSecSuccess || deleteStatus == errSecItemNotFound else {
+            return false
+        }
+
+        var insert = query
+        insert[kSecValueData as String] = data
+        insert[kSecAttrAccessible as String] = accessible
+        if SecItemAdd(insert as CFDictionary, nil) == errSecSuccess {
+            return true
+        }
+
+        // Best-effort rollback: preserve prior value if replacement fails.
+        guard let previousData else { return false }
+        var rollback = query
+        rollback[kSecValueData as String] = previousData
+        rollback[kSecAttrAccessible as String] = accessible
+        _ = SecItemDelete(query as CFDictionary)
+        _ = SecItemAdd(rollback as CFDictionary, nil)
+        return false
+    }
+
+    private static func baseQuery(service: String, account: String) -> [String: Any] {
+        [
+            kSecClass as String: kSecClassGenericPassword,
+            kSecAttrService as String: service,
+            kSecAttrAccount as String: account,
+        ]
+    }
+}

apps/shared/OpenClawKit/Sources/OpenClawKit/TalkSystemSpeechSynthesizer.swift

@@ -12,6 +12,7 @@ public final class TalkSystemSpeechSynthesizer: NSObject {
     private let synth = AVSpeechSynthesizer()
     private var speakContinuation: CheckedContinuation<Void, Error>?
     private var currentUtterance: AVSpeechUtterance?
+    private var didStartCallback: (() -> Void)?
     private var currentToken = UUID()
     private var watchdog: Task<Void, Never>?
 
@@ -26,17 +27,23 @@ public final class TalkSystemSpeechSynthesizer: NSObject {
         self.currentToken = UUID()
         self.watchdog?.cancel()
         self.watchdog = nil
+        self.didStartCallback = nil
         self.synth.stopSpeaking(at: .immediate)
         self.finishCurrent(with: SpeakError.canceled)
     }
 
-    public func speak(text: String, language: String? = nil) async throws {
+    public func speak(
+        text: String,
+        language: String? = nil,
+        onStart: (() -> Void)? = nil
+    ) async throws {
         let trimmed = text.trimmingCharacters(in: .whitespacesAndNewlines)
         guard !trimmed.isEmpty else { return }
 
         self.stop()
         let token = UUID()
         self.currentToken = token
+        self.didStartCallback = onStart
 
         let utterance = AVSpeechUtterance(string: trimmed)
         if let language, let voice = AVSpeechSynthesisVoice(language: language) {
@@ -76,8 +83,13 @@ public final class TalkSystemSpeechSynthesizer: NSObject {
         }
     }
 
-    private func handleFinish(error: Error?) {
-        guard self.currentUtterance != nil else { return }
+    private func matchesCurrentUtterance(_ utteranceID: ObjectIdentifier) -> Bool {
+        guard let currentUtterance = self.currentUtterance else { return false }
+        return ObjectIdentifier(currentUtterance) == utteranceID
+    }
+
+    private func handleFinish(utteranceID: ObjectIdentifier, error: Error?) {
+        guard self.matchesCurrentUtterance(utteranceID) else { return }
         self.watchdog?.cancel()
         self.watchdog = nil
         self.finishCurrent(with: error)
@@ -85,6 +97,7 @@ public final class TalkSystemSpeechSynthesizer: NSObject {
 
     private func finishCurrent(with error: Error?) {
         self.currentUtterance = nil
+        self.didStartCallback = nil
         let cont = self.speakContinuation
         self.speakContinuation = nil
         if let error {
@@ -96,12 +109,26 @@ public final class TalkSystemSpeechSynthesizer: NSObject {
 }
 
 extension TalkSystemSpeechSynthesizer: AVSpeechSynthesizerDelegate {
+    public nonisolated func speechSynthesizer(
+        _ synthesizer: AVSpeechSynthesizer,
+        didStart utterance: AVSpeechUtterance)
+    {
+        let utteranceID = ObjectIdentifier(utterance)
+        Task { @MainActor in
+            guard self.matchesCurrentUtterance(utteranceID) else { return }
+            let callback = self.didStartCallback
+            self.didStartCallback = nil
+            callback?()
+        }
+    }
+
     public nonisolated func speechSynthesizer(
         _ synthesizer: AVSpeechSynthesizer,
         didFinish utterance: AVSpeechUtterance)
     {
+        let utteranceID = ObjectIdentifier(utterance)
         Task { @MainActor in
-            self.handleFinish(error: nil)
+            self.handleFinish(utteranceID: utteranceID, error: nil)
         }
     }
 
@@ -109,8 +136,9 @@ extension TalkSystemSpeechSynthesizer: AVSpeechSynthesizerDelegate {
         _ synthesizer: AVSpeechSynthesizer,
         didCancel utterance: AVSpeechUtterance)
     {
+        let utteranceID = ObjectIdentifier(utterance)
         Task { @MainActor in
-            self.handleFinish(error: SpeakError.canceled)
+            self.handleFinish(utteranceID: utteranceID, error: SpeakError.canceled)
         }
     }
 }

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

@@ -1030,6 +1030,74 @@ public struct PushTestResult: Codable, Sendable {
     }
 }
 
+public struct SecretsReloadParams: Codable, Sendable {}
+
+public struct SecretsResolveParams: Codable, Sendable {
+    public let commandname: String
+    public let targetids: [String]
+
+    public init(
+        commandname: String,
+        targetids: [String])
+    {
+        self.commandname = commandname
+        self.targetids = targetids
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case commandname = "commandName"
+        case targetids = "targetIds"
+    }
+}
+
+public struct SecretsResolveAssignment: Codable, Sendable {
+    public let path: String?
+    public let pathsegments: [String]
+    public let value: AnyCodable
+
+    public init(
+        path: String?,
+        pathsegments: [String],
+        value: AnyCodable)
+    {
+        self.path = path
+        self.pathsegments = pathsegments
+        self.value = value
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case path
+        case pathsegments = "pathSegments"
+        case value
+    }
+}
+
+public struct SecretsResolveResult: Codable, Sendable {
+    public let ok: Bool?
+    public let assignments: [SecretsResolveAssignment]?
+    public let diagnostics: [String]?
+    public let inactiverefpaths: [String]?
+
+    public init(
+        ok: Bool?,
+        assignments: [SecretsResolveAssignment]?,
+        diagnostics: [String]?,
+        inactiverefpaths: [String]?)
+    {
+        self.ok = ok
+        self.assignments = assignments
+        self.diagnostics = diagnostics
+        self.inactiverefpaths = inactiverefpaths
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case ok
+        case assignments
+        case diagnostics
+        case inactiverefpaths = "inactiveRefPaths"
+    }
+}
+
 public struct SessionsListParams: Codable, Sendable {
     public let limit: Int?
     public let activeminutes: Int?

changelog/fragments/README.md

@@ -1,13 +0,0 @@
-# Changelog Fragments
-
-Use this directory when a PR should not edit `CHANGELOG.md` directly.
-
-- One fragment file per PR.
-- File name recommendation: `pr-<number>.md`.
-- Include at least one line with both `#<pr>` and `thanks @<contributor>`.
-
-Example:
-
-```md
-- Fix LINE monitor lifecycle wait ownership (#27001) (thanks @alice)
-```

changelog/fragments/pr-5080.md

@@ -1 +0,0 @@
-- Clarify block reply pipeline seen-check parameter naming for maintainability (#5080) (thanks @yassine20011)

changelog/fragments/pr-5343.md

@@ -1 +0,0 @@
-- Memory flush: fix usage-threshold gating and transcript fallback paths so flushes run reliably when expected (#5343) (thanks @jarvis-medmatic)

changelog/fragments/pr-feishu-reply-mechanism.md

@@ -0,0 +1 @@
+- Feishu reply routing now uses one canonical reply-target path across inbound and outbound flows: normal groups reply to the triggering message while topic-mode groups stay on topic roots, outbound sends preserve `replyToId`/`threadId`, withdrawn reply targets fall back to direct sends, and cron duplicate suppression normalizes Feishu/Lark target IDs consistently (#32980, #32958, #33572, #33526; #33789, #33575, #33515, #33161). Thanks @guoqunabc, @bmendonca3, @MunemHashmi, and @Jimmy-xuzimo.

docs/auth-credential-semantics.md

@@ -0,0 +1,45 @@
+# Auth Credential Semantics
+
+This document defines the canonical credential eligibility and resolution semantics used across:
+
+- `resolveAuthProfileOrder`
+- `resolveApiKeyForProfile`
+- `models status --probe`
+- `doctor-auth`
+
+The goal is to keep selection-time and runtime behavior aligned.
+
+## Stable Reason Codes
+
+- `ok`
+- `missing_credential`
+- `invalid_expires`
+- `expired`
+- `unresolved_ref`
+
+## Token Credentials
+
+Token credentials (`type: "token"`) support inline `token` and/or `tokenRef`.
+
+### Eligibility rules
+
+1. A token profile is ineligible when both `token` and `tokenRef` are absent.
+2. `expires` is optional.
+3. If `expires` is present, it must be a finite number greater than `0`.
+4. If `expires` is invalid (`NaN`, `0`, negative, non-finite, or wrong type), the profile is ineligible with `invalid_expires`.
+5. If `expires` is in the past, the profile is ineligible with `expired`.
+6. `tokenRef` does not bypass `expires` validation.
+
+### Resolution rules
+
+1. Resolver semantics match eligibility semantics for `expires`.
+2. For eligible profiles, token material may be resolved from inline value or `tokenRef`.
+3. Unresolvable refs produce `unresolved_ref` in `models status --probe` output.
+
+## Legacy-Compatible Messaging
+
+For script compatibility, probe errors keep this first line unchanged:
+
+`Auth profile credentials are missing or expired.`
+
+Human-friendly detail and stable reason codes may be added on subsequent lines.

docs/automation/hooks.md

@@ -258,7 +258,9 @@ Triggered when the gateway starts:
 Triggered when messages are received or sent:
 
 - **`message`**: All message events (general listener)
-- **`message:received`**: When an inbound message is received from any channel
+- **`message:received`**: When an inbound message is received from any channel. Fires early in processing before media understanding. Content may contain raw placeholders like `<media:audio>` for media attachments that haven't been processed yet.
+- **`message:transcribed`**: When a message has been fully processed, including audio transcription and link understanding. At this point, `transcript` contains the full transcript text for audio messages. Use this hook when you need access to transcribed audio content.
+- **`message:preprocessed`**: Fires for every message after all media + link understanding completes, giving hooks access to the fully enriched body (transcripts, image descriptions, link summaries) before the agent sees it.
 - **`message:sent`**: When an outbound message is successfully sent
 
 #### Message Event Context
@@ -297,6 +299,30 @@ Message events include rich context about the message:
   accountId?: string,     // Provider account ID
   conversationId?: string, // Chat/conversation ID
   messageId?: string,     // Message ID returned by the provider
+  isGroup?: boolean,      // Whether this outbound message belongs to a group/channel context
+  groupId?: string,       // Group/channel identifier for correlation with message:received
+}
+
+// message:transcribed context
+{
+  body?: string,          // Raw inbound body before enrichment
+  bodyForAgent?: string,  // Enriched body visible to the agent
+  transcript: string,     // Audio transcript text
+  channelId: string,      // Channel (e.g., "telegram", "whatsapp")
+  conversationId?: string,
+  messageId?: string,
+}
+
+// message:preprocessed context
+{
+  body?: string,          // Raw inbound body
+  bodyForAgent?: string,  // Final enriched body after media/link understanding
+  transcript?: string,    // Transcript when audio was present
+  channelId: string,      // Channel (e.g., "telegram", "whatsapp")
+  conversationId?: string,
+  messageId?: string,
+  isGroup?: boolean,
+  groupId?: string,
 }
 ```
 

docs/automation/webhook.md

@@ -159,7 +159,7 @@ Mapping options (summary):
 ## Responses
 
 - `200` for `/hooks/wake`
-- `202` for `/hooks/agent` (async run started)
+- `200` for `/hooks/agent` (async run accepted)
 - `401` on auth failure
 - `429` after repeated auth failures from the same client (check `Retry-After`)
 - `400` on invalid payload

docs/brave-search.md

@@ -8,7 +8,7 @@ title: "Brave Search"
 
 # Brave Search API
 
-OpenClaw uses Brave Search as the default provider for `web_search`.
+OpenClaw supports Brave Search as a web search provider for `web_search`.
 
 ## Get an API key
 
@@ -33,9 +33,48 @@ OpenClaw uses Brave Search as the default provider for `web_search`.
 }
 ```
 
+## Tool parameters
+
+| Parameter     | Description                                                         |
+| ------------- | ------------------------------------------------------------------- |
+| `query`       | Search query (required)                                             |
+| `count`       | Number of results to return (1-10, default: 5)                      |
+| `country`     | 2-letter ISO country code (e.g., "US", "DE")                        |
+| `language`    | ISO 639-1 language code for search results (e.g., "en", "de", "fr") |
+| `ui_lang`     | ISO language code for UI elements                                   |
+| `freshness`   | Time filter: `day` (24h), `week`, `month`, or `year`                |
+| `date_after`  | Only results published after this date (YYYY-MM-DD)                 |
+| `date_before` | Only results published before this date (YYYY-MM-DD)                |
+
+**Examples:**
+
+```javascript
+// Country and language-specific search
+await web_search({
+  query: "renewable energy",
+  country: "DE",
+  language: "de",
+});
+
+// Recent results (past week)
+await web_search({
+  query: "AI news",
+  freshness: "week",
+});
+
+// Date range search
+await web_search({
+  query: "AI developments",
+  date_after: "2024-01-01",
+  date_before: "2024-06-30",
+});
+```
+
 ## Notes
 
 - The Data for AI plan is **not** compatible with `web_search`.
-- Brave provides a free tier plus paid plans; check the Brave API portal for current limits.
+- Brave provides paid plans; check the Brave API portal for current limits.
+- Brave Terms include restrictions on some AI-related uses of Search Results. Review the Brave Terms of Service and confirm your intended use is compliant. For legal questions, consult your counsel.
+- Results are cached for 15 minutes by default (configurable via `cacheTtlMinutes`).
 
 See [Web tools](/tools/web) for the full web_search configuration.

docs/channels/channel-routing.md

@@ -17,6 +17,7 @@ host configuration.
 - **AccountId**: per‑channel account instance (when supported).
 - Optional channel default account: `channels.<channel>.defaultAccount` chooses
   which account is used when an outbound path does not specify `accountId`.
+  - In multi-account setups, set an explicit default (`defaultAccount` or `accounts.default`) when two or more accounts are configured. Without it, fallback routing may pick the first normalized account ID.
 - **AgentId**: an isolated workspace + session store (“brain”).
 - **SessionKey**: the bucket key used to store context and control concurrency.
 
@@ -41,6 +42,19 @@ Examples:
 - `agent:main:telegram:group:-1001234567890:topic:42`
 - `agent:main:discord:channel:123456:thread:987654`
 
+## Main DM route pinning
+
+When `session.dmScope` is `main`, direct messages may share one main session.
+To prevent the session’s `lastRoute` from being overwritten by non-owner DMs,
+OpenClaw infers a pinned owner from `allowFrom` when all of these are true:
+
+- `allowFrom` has exactly one non-wildcard entry.
+- The entry can be normalized to a concrete sender ID for that channel.
+- The inbound DM sender does not match that pinned owner.
+
+In that mismatch case, OpenClaw still records inbound session metadata, but it
+skips updating the main session `lastRoute`.
+
 ## Routing rules (how an agent is chosen)
 
 Routing picks **one agent** for each inbound message:

docs/channels/discord.md

@@ -133,6 +133,8 @@ openclaw gateway
 DISCORD_BOT_TOKEN=...
 ```
 
+        SecretRef values are also supported for `channels.discord.token` (env/file/exec providers). See [Secrets Management](/gateway/secrets).
+
       </Tab>
     </Tabs>
 
@@ -419,6 +421,7 @@ Example:
       guilds: {
         "123456789012345678": {
           requireMention: true,
+          ignoreOtherMentions: true,
           users: ["987654321098765432"],
           roles: ["123456789012345678"],
           channels: {
@@ -446,6 +449,7 @@ Example:
     - implicit reply-to-bot behavior in supported cases
 
     `requireMention` is configured per guild/channel (`channels.discord.guilds...`).
+    `ignoreOtherMentions` optionally drops messages that mention another user/role but not the bot (excluding @everyone/@here).
 
     Group DMs:
 
@@ -786,7 +790,7 @@ Default slash command settings:
   </Accordion>
 
   <Accordion title="Presence configuration">
-    Presence updates are applied only when you set a status or activity field.
+    Presence updates are applied when you set a status or activity field, or when you enable auto presence.
 
     Status only example:
 
@@ -836,6 +840,29 @@ Default slash command settings:
     - 4: Custom (uses the activity text as the status state; emoji is optional)
     - 5: Competing
 
+    Auto presence example (runtime health signal):
+
+```json5
+{
+  channels: {
+    discord: {
+      autoPresence: {
+        enabled: true,
+        intervalMs: 30000,
+        minUpdateIntervalMs: 15000,
+        exhaustedText: "token exhausted",
+      },
+    },
+  },
+}
+```
+
+    Auto presence maps runtime availability to Discord status: healthy => online, degraded or unknown => idle, exhausted or unavailable => dnd. Optional text overrides:
+
+    - `autoPresence.healthyText`
+    - `autoPresence.degradedText`
+    - `autoPresence.exhaustedText` (supports `{reason}` placeholder)
+
   </Accordion>
 
   <Accordion title="Exec approvals in Discord">
@@ -944,6 +971,7 @@ Auto-join example:
 Notes:
 
 - `voice.tts` overrides `messages.tts` for voice playback only.
+- Voice transcript turns derive owner status from Discord `allowFrom` (or `dm.allowFrom`); non-owner speakers cannot access owner-only tools (for example `gateway` and `cron`).
 - Voice is enabled by default; set `channels.discord.voice.enabled=false` to disable it.
 - `voice.daveEncryption` and `voice.decryptionFailureTolerance` pass through to `@discordjs/voice` join options.
 - `@discordjs/voice` defaults are `daveEncryption=true` and `decryptionFailureTolerance=24` if unset.
@@ -1056,6 +1084,7 @@ openclaw logs --follow
     By default bot-authored messages are ignored.
 
     If you set `channels.discord.allowBots=true`, use strict mention and allowlist rules to avoid loop behavior.
+    Prefer `channels.discord.allowBots="mentions"` to only accept bot messages that mention the bot.
 
   </Accordion>
 

docs/channels/feishu.md

@@ -197,6 +197,17 @@ Edit `~/.openclaw/openclaw.json`:
 
 If you use `connectionMode: "webhook"`, set `verificationToken`. The Feishu webhook server binds to `127.0.0.1` by default; set `webhookHost` only if you intentionally need a different bind address.
 
+#### Verification Token (webhook mode)
+
+When using webhook mode, set `channels.feishu.verificationToken` in your config. To get the value:
+
+1. In Feishu Open Platform, open your app
+2. Go to **Development** → **Events & Callbacks** (开发配置 → 事件与回调)
+3. Open the **Encryption** tab (加密策略)
+4. Copy **Verification Token**
+
+![Verification Token location](../images/feishu-verification-token.png)
+
 ### Configure via environment variables
 
 ```bash
@@ -359,9 +370,9 @@ After approval, you can chat normally.
 }
 ```
 
-### Allow specific users to run control commands in a group (e.g. /reset, /new)
+### Restrict which senders can message in a group (sender allowlist)
 
-In addition to allowing the group itself, control commands are gated by the **sender** open_id.
+In addition to allowing the group itself, **all messages** in that group are gated by the sender open_id: only users listed in `groups.<chat_id>.allowFrom` have their messages processed; messages from other members are ignored (this is full sender-level gating, not only for control commands like /reset or /new).
 
 ```json5
 {

docs/channels/mattermost.md

@@ -55,6 +55,45 @@ Minimal config:
 }
 ```
 
+## Native slash commands
+
+Native slash commands are opt-in. When enabled, OpenClaw registers `oc_*` slash commands via
+the Mattermost API and receives callback POSTs on the gateway HTTP server.
+
+```json5
+{
+  channels: {
+    mattermost: {
+      commands: {
+        native: true,
+        nativeSkills: true,
+        callbackPath: "/api/channels/mattermost/command",
+        // Use when Mattermost cannot reach the gateway directly (reverse proxy/public URL).
+        callbackUrl: "https://gateway.example.com/api/channels/mattermost/command",
+      },
+    },
+  },
+}
+```
+
+Notes:
+
+- `native: "auto"` defaults to disabled for Mattermost. Set `native: true` to enable.
+- If `callbackUrl` is omitted, OpenClaw derives one from gateway host/port + `callbackPath`.
+- For multi-account setups, `commands` can be set at the top level or under
+  `channels.mattermost.accounts.<id>.commands` (account values override top-level fields).
+- Command callbacks are validated with per-command tokens and fail closed when token checks fail.
+- Reachability requirement: the callback endpoint must be reachable from the Mattermost server.
+  - Do not set `callbackUrl` to `localhost` unless Mattermost runs on the same host/network namespace as OpenClaw.
+  - Do not set `callbackUrl` to your Mattermost base URL unless that URL reverse-proxies `/api/channels/mattermost/command` to OpenClaw.
+  - A quick check is `curl https://<gateway-host>/api/channels/mattermost/command`; a GET should return `405 Method Not Allowed` from OpenClaw, not `404`.
+- Mattermost egress allowlist requirement:
+  - If your callback targets private/tailnet/internal addresses, set Mattermost
+    `ServiceSettings.AllowedUntrustedInternalConnections` to include the callback host/domain.
+  - Use host/domain entries, not full URLs.
+    - Good: `gateway.tailnet-name.ts.net`
+    - Bad: `https://gateway.tailnet-name.ts.net`
+
 ## Environment variables (default account)
 
 Set these on the gateway host if you prefer env vars:

docs/channels/telegram.md

@@ -230,23 +230,31 @@ curl "https://api.telegram.org/bot<bot_token>/getUpdates"
 ## Feature reference
 
 <AccordionGroup>
-  <Accordion title="Live stream preview (message edits)">
-    OpenClaw can stream partial replies by sending a temporary Telegram message and editing it as text arrives.
+  <Accordion title="Live stream preview (native drafts + message edits)">
+    OpenClaw can stream partial replies in real time:
+
+    - direct chats: Telegram native draft streaming via `sendMessageDraft`
+    - groups/topics: preview message + `editMessageText`
 
     Requirement:
 
-    - `channels.telegram.streaming` is `off | partial | block | progress` (default: `off`)
+    - `channels.telegram.streaming` is `off | partial | block | progress` (default: `partial`)
     - `progress` maps to `partial` on Telegram (compat with cross-channel naming)
     - legacy `channels.telegram.streamMode` and boolean `streaming` values are auto-mapped
 
-    This works in direct chats and groups/topics.
+    Telegram enabled `sendMessageDraft` for all bots in Bot API 9.5 (March 1, 2026).
 
-    For text-only replies, OpenClaw keeps the same preview message and performs a final edit in place (no second message).
+    For text-only replies:
+
+    - DM: OpenClaw updates the draft in place (no extra preview message)
+    - group/topic: OpenClaw keeps the same preview message and performs a final edit in place (no second message)
 
     For complex replies (for example media payloads), OpenClaw falls back to normal final delivery and then cleans up the preview message.
 
     Preview streaming is separate from block streaming. When block streaming is explicitly enabled for Telegram, OpenClaw skips the preview stream to avoid double-streaming.
 
+    If native draft transport is unavailable/rejected, OpenClaw automatically falls back to `sendMessage` + `editMessageText`.
+
     Telegram-only reasoning stream:
 
     - `/reasoning stream` sends reasoning to the live preview while generating
@@ -437,6 +445,29 @@ curl "https://api.telegram.org/bot<bot_token>/getUpdates"
     - typing actions still include `message_thread_id`
 
     Topic inheritance: topic entries inherit group settings unless overridden (`requireMention`, `allowFrom`, `skills`, `systemPrompt`, `enabled`, `groupPolicy`).
+    `agentId` is topic-only and does not inherit from group defaults.
+
+    **Per-topic agent routing**: Each topic can route to a different agent by setting `agentId` in the topic config. This gives each topic its own isolated workspace, memory, and session. Example:
+
+    ```json5
+    {
+      channels: {
+        telegram: {
+          groups: {
+            "-1001234567890": {
+              topics: {
+                "1": { agentId: "main" },      // General topic → main agent
+                "3": { agentId: "zu" },        // Dev topic → zu agent
+                "5": { agentId: "coder" }      // Code review → coder agent
+              }
+            }
+          }
+        }
+      }
+    }
+    ```
+
+    Each topic then has its own session key: `agent:zu:telegram:group:-1001234567890:topic:3`
 
     Template context includes:
 
@@ -731,6 +762,8 @@ Primary reference:
 - `channels.telegram.groupPolicy`: `open | allowlist | disabled` (default: allowlist).
 - `channels.telegram.groupAllowFrom`: group sender allowlist (numeric Telegram user IDs). `openclaw doctor --fix` can resolve legacy `@username` entries to IDs. Non-numeric entries are ignored at auth time. Group auth does not use DM pairing-store fallback (`2026.2.25+`).
 - Multi-account precedence:
+  - When two or more account IDs are configured, set `channels.telegram.defaultAccount` (or include `channels.telegram.accounts.default`) to make default routing explicit.
+  - If neither is set, OpenClaw falls back to the first normalized account ID and `openclaw doctor` warns.
   - `channels.telegram.accounts.default.allowFrom` and `channels.telegram.accounts.default.groupAllowFrom` apply only to the `default` account.
   - Named accounts inherit `channels.telegram.allowFrom` and `channels.telegram.groupAllowFrom` when account-level values are unset.
   - Named accounts do not inherit `channels.telegram.accounts.default.allowFrom` / `groupAllowFrom`.
@@ -741,9 +774,11 @@ Primary reference:
   - `channels.telegram.groups.<id>.allowFrom`: per-group sender allowlist override.
   - `channels.telegram.groups.<id>.systemPrompt`: extra system prompt for the group.
   - `channels.telegram.groups.<id>.enabled`: disable the group when `false`.
-  - `channels.telegram.groups.<id>.topics.<threadId>.*`: per-topic overrides (same fields as group).
+  - `channels.telegram.groups.<id>.topics.<threadId>.*`: per-topic overrides (group fields + topic-only `agentId`).
+  - `channels.telegram.groups.<id>.topics.<threadId>.agentId`: route this topic to a specific agent (overrides group-level and binding routing).
   - `channels.telegram.groups.<id>.topics.<threadId>.groupPolicy`: per-topic override for groupPolicy (`open | allowlist | disabled`).
   - `channels.telegram.groups.<id>.topics.<threadId>.requireMention`: per-topic mention gating override.
+  - `channels.telegram.direct.<id>.topics.<threadId>.agentId`: route DM topics to a specific agent (same behavior as forum topics).
 - `channels.telegram.capabilities.inlineButtons`: `off | dm | group | all | allowlist` (default: allowlist).
 - `channels.telegram.accounts.<account>.capabilities.inlineButtons`: per-account override.
 - `channels.telegram.commands.nativeSkills`: enable/disable Telegram native skills commands.
@@ -751,7 +786,7 @@ Primary reference:
 - `channels.telegram.textChunkLimit`: outbound chunk size (chars).
 - `channels.telegram.chunkMode`: `length` (default) or `newline` to split on blank lines (paragraph boundaries) before length chunking.
 - `channels.telegram.linkPreview`: toggle link previews for outbound messages (default: true).
-- `channels.telegram.streaming`: `off | partial | block | progress` (live stream preview; default: `off`; `progress` maps to `partial`; `block` is legacy preview mode compatibility).
+- `channels.telegram.streaming`: `off | partial | block | progress` (live stream preview; default: `partial`; `progress` maps to `partial`; `block` is legacy preview mode compatibility). In DMs, `partial` uses native `sendMessageDraft` when available.
 - `channels.telegram.mediaMaxMb`: inbound Telegram media download/processing cap (MB).
 - `channels.telegram.retry`: retry policy for Telegram send helpers (CLI/tools/actions) on recoverable outbound API errors (attempts, minDelayMs, maxDelayMs, jitter).
 - `channels.telegram.network.autoSelectFamily`: override Node autoSelectFamily (true=enable, false=disable). Defaults to enabled on Node 22+, with WSL2 defaulting to disabled.

docs/channels/tlon.md

@@ -11,8 +11,8 @@ Tlon is a decentralized messenger built on Urbit. OpenClaw connects to your Urbi
 respond to DMs and group chat messages. Group replies require an @ mention by default and can
 be further restricted via allowlists.
 
-Status: supported via plugin. DMs, group mentions, thread replies, and text-only media fallback
-(URL appended to caption). Reactions, polls, and native media uploads are not supported.
+Status: supported via plugin. DMs, group mentions, thread replies, rich text formatting, and
+image uploads are supported. Reactions and polls are not yet supported.
 
 ## Plugin required
 
@@ -50,27 +50,38 @@ Minimal config (single account):
       ship: "~sampel-palnet",
       url: "https://your-ship-host",
       code: "lidlut-tabwed-pillex-ridrup",
+      ownerShip: "~your-main-ship", // recommended: your ship, always allowed
     },
   },
 }
 ```
 
-Private/LAN ship URLs (advanced):
+## Private/LAN ships
 
-By default, OpenClaw blocks private/internal hostnames and IP ranges for this plugin (SSRF hardening).
-If your ship URL is on a private network (for example `http://192.168.1.50:8080` or `http://localhost:8080`),
+By default, OpenClaw blocks private/internal hostnames and IP ranges for SSRF protection.
+If your ship is running on a private network (localhost, LAN IP, or internal hostname),
 you must explicitly opt in:
 
 ```json5
 {
   channels: {
     tlon: {
+      url: "http://localhost:8080",
       allowPrivateNetwork: true,
     },
   },
 }
 ```
 
+This applies to URLs like:
+
+- `http://localhost:8080`
+- `http://192.168.x.x:8080`
+- `http://my-ship.local:8080`
+
+⚠️ Only enable this if you trust your local network. This setting disables SSRF protections
+for requests to your ship URL.
+
 ## Group channels
 
 Auto-discovery is enabled by default. You can also pin channels manually:
@@ -99,7 +110,7 @@ Disable auto-discovery:
 
 ## Access control
 
-DM allowlist (empty = allow all):
+DM allowlist (empty = no DMs allowed, use `ownerShip` for approval flow):
 
 ```json5
 {
@@ -134,6 +145,56 @@ Group authorization (restricted by default):
 }
 ```
 
+## Owner and approval system
+
+Set an owner ship to receive approval requests when unauthorized users try to interact:
+
+```json5
+{
+  channels: {
+    tlon: {
+      ownerShip: "~your-main-ship",
+    },
+  },
+}
+```
+
+The owner ship is **automatically authorized everywhere** — DM invites are auto-accepted and
+channel messages are always allowed. You don't need to add the owner to `dmAllowlist` or
+`defaultAuthorizedShips`.
+
+When set, the owner receives DM notifications for:
+
+- DM requests from ships not in the allowlist
+- Mentions in channels without authorization
+- Group invite requests
+
+## Auto-accept settings
+
+Auto-accept DM invites (for ships in dmAllowlist):
+
+```json5
+{
+  channels: {
+    tlon: {
+      autoAcceptDmInvites: true,
+    },
+  },
+}
+```
+
+Auto-accept group invites:
+
+```json5
+{
+  channels: {
+    tlon: {
+      autoAcceptGroupInvites: true,
+    },
+  },
+}
+```
+
 ## Delivery targets (CLI/cron)
 
 Use these with `openclaw message send` or cron delivery:
@@ -141,8 +202,75 @@ Use these with `openclaw message send` or cron delivery:
 - DM: `~sampel-palnet` or `dm/~sampel-palnet`
 - Group: `chat/~host-ship/channel` or `group:~host-ship/channel`
 
+## Bundled skill
+
+The Tlon plugin includes a bundled skill ([`@tloncorp/tlon-skill`](https://github.com/tloncorp/tlon-skill))
+that provides CLI access to Tlon operations:
+
+- **Contacts**: get/update profiles, list contacts
+- **Channels**: list, create, post messages, fetch history
+- **Groups**: list, create, manage members
+- **DMs**: send messages, react to messages
+- **Reactions**: add/remove emoji reactions to posts and DMs
+- **Settings**: manage plugin permissions via slash commands
+
+The skill is automatically available when the plugin is installed.
+
+## Capabilities
+
+| Feature         | Status                                  |
+| --------------- | --------------------------------------- |
+| Direct messages | ✅ Supported                            |
+| Groups/channels | ✅ Supported (mention-gated by default) |
+| Threads         | ✅ Supported (auto-replies in thread)   |
+| Rich text       | ✅ Markdown converted to Tlon format    |
+| Images          | ✅ Uploaded to Tlon storage             |
+| Reactions       | ✅ Via [bundled skill](#bundled-skill)  |
+| Polls           | ❌ Not yet supported                    |
+| Native commands | ✅ Supported (owner-only by default)    |
+
+## Troubleshooting
+
+Run this ladder first:
+
+```bash
+openclaw status
+openclaw gateway status
+openclaw logs --follow
+openclaw doctor
+```
+
+Common failures:
+
+- **DMs ignored**: sender not in `dmAllowlist` and no `ownerShip` configured for approval flow.
+- **Group messages ignored**: channel not discovered or sender not authorized.
+- **Connection errors**: check ship URL is reachable; enable `allowPrivateNetwork` for local ships.
+- **Auth errors**: verify login code is current (codes rotate).
+
+## Configuration reference
+
+Full configuration: [Configuration](/gateway/configuration)
+
+Provider options:
+
+- `channels.tlon.enabled`: enable/disable channel startup.
+- `channels.tlon.ship`: bot's Urbit ship name (e.g. `~sampel-palnet`).
+- `channels.tlon.url`: ship URL (e.g. `https://sampel-palnet.tlon.network`).
+- `channels.tlon.code`: ship login code.
+- `channels.tlon.allowPrivateNetwork`: allow localhost/LAN URLs (SSRF bypass).
+- `channels.tlon.ownerShip`: owner ship for approval system (always authorized).
+- `channels.tlon.dmAllowlist`: ships allowed to DM (empty = none).
+- `channels.tlon.autoAcceptDmInvites`: auto-accept DMs from allowlisted ships.
+- `channels.tlon.autoAcceptGroupInvites`: auto-accept all group invites.
+- `channels.tlon.autoDiscoverChannels`: auto-discover group channels (default: true).
+- `channels.tlon.groupChannels`: manually pinned channel nests.
+- `channels.tlon.defaultAuthorizedShips`: ships authorized for all channels.
+- `channels.tlon.authorization.channelRules`: per-channel auth rules.
+- `channels.tlon.showModelSignature`: append model name to messages.
+
 ## Notes
 
 - Group replies require a mention (e.g. `~your-bot-ship`) to respond.
 - Thread replies: if the inbound message is in a thread, OpenClaw replies in-thread.
-- Media: `sendMedia` falls back to text + URL (no native upload).
+- Rich text: Markdown formatting (bold, italic, code, headers, lists) is converted to Tlon's native format.
+- Images: URLs are uploaded to Tlon storage and embedded as image blocks.

docs/channels/zalouser.md

@@ -107,6 +107,28 @@ Example:
 }
 ```
 
+### Group mention gating
+
+- `channels.zalouser.groups.<group>.requireMention` controls whether group replies require a mention.
+- Resolution order: exact group id/name -> normalized group slug -> `*` -> default (`true`).
+- This applies both to allowlisted groups and open group mode.
+
+Example:
+
+```json5
+{
+  channels: {
+    zalouser: {
+      groupPolicy: "allowlist",
+      groups: {
+        "*": { allow: true, requireMention: true },
+        "Work Chat": { allow: true, requireMention: false },
+      },
+    },
+  },
+}
+```
+
 ## Multi-account
 
 Accounts map to `zalouser` profiles in OpenClaw state. Example:
@@ -125,6 +147,14 @@ Accounts map to `zalouser` profiles in OpenClaw state. Example:
 }
 ```
 
+## Typing, reactions, and delivery acknowledgements
+
+- OpenClaw sends a typing event before dispatching a reply (best-effort).
+- Message reaction action `react` is supported for `zalouser` in channel actions.
+  - Use `remove: true` to remove a specific reaction emoji from a message.
+  - Reaction semantics: [Reactions](/tools/reactions)
+- For inbound messages that include event metadata, OpenClaw sends delivered + seen acknowledgements (best-effort).
+
 ## Troubleshooting
 
 **Login doesn't stick:**

docs/ci.md

@@ -13,20 +13,20 @@ The CI runs on every push to `main` and every pull request. It uses smart scopin
 
 ## Job Overview
 
-| Job               | Purpose                                         | When it runs              |
-| ----------------- | ----------------------------------------------- | ------------------------- |
-| `docs-scope`      | Detect docs-only changes                        | Always                    |
-| `changed-scope`   | Detect which areas changed (node/macos/android) | Non-docs PRs              |
-| `check`           | TypeScript types, lint, format                  | Non-docs changes          |
-| `check-docs`      | Markdown lint + broken link check               | Docs changed              |
-| `code-analysis`   | LOC threshold check (1000 lines)                | PRs only                  |
-| `secrets`         | Detect leaked secrets                           | Always                    |
-| `build-artifacts` | Build dist once, share with other jobs          | Non-docs, node changes    |
-| `release-check`   | Validate npm pack contents                      | After build               |
-| `checks`          | Node/Bun tests + protocol check                 | Non-docs, node changes    |
-| `checks-windows`  | Windows-specific tests                          | Non-docs, node changes    |
-| `macos`           | Swift lint/build/test + TS tests                | PRs with macos changes    |
-| `android`         | Gradle build + tests                            | Non-docs, android changes |
+| Job               | Purpose                                                 | When it runs                                      |
+| ----------------- | ------------------------------------------------------- | ------------------------------------------------- |
+| `docs-scope`      | Detect docs-only changes                                | Always                                            |
+| `changed-scope`   | Detect which areas changed (node/macos/android/windows) | Non-docs PRs                                      |
+| `check`           | TypeScript types, lint, format                          | Push to `main`, or PRs with Node-relevant changes |
+| `check-docs`      | Markdown lint + broken link check                       | Docs changed                                      |
+| `code-analysis`   | LOC threshold check (1000 lines)                        | PRs only                                          |
+| `secrets`         | Detect leaked secrets                                   | Always                                            |
+| `build-artifacts` | Build dist once, share with other jobs                  | Non-docs, node changes                            |
+| `release-check`   | Validate npm pack contents                              | After build                                       |
+| `checks`          | Node/Bun tests + protocol check                         | Non-docs, node changes                            |
+| `checks-windows`  | Windows-specific tests                                  | Non-docs, windows-relevant changes                |
+| `macos`           | Swift lint/build/test + TS tests                        | PRs with macos changes                            |
+| `android`         | Gradle build + tests                                    | Non-docs, android changes                         |
 
 ## Fail-Fast Order
 
@@ -36,12 +36,14 @@ Jobs are ordered so cheap checks fail before expensive ones run:
 2. `build-artifacts` (blocked on above)
 3. `checks`, `checks-windows`, `macos`, `android` (blocked on build)
 
+Scope logic lives in `scripts/ci-changed-scope.mjs` and is covered by unit tests in `src/scripts/ci-changed-scope.test.ts`.
+
 ## Runners
 
 | Runner                           | Jobs                                       |
 | -------------------------------- | ------------------------------------------ |
 | `blacksmith-16vcpu-ubuntu-2404`  | Most Linux jobs, including scope detection |
-| `blacksmith-16vcpu-windows-2025` | `checks-windows`                           |
+| `blacksmith-32vcpu-windows-2025` | `checks-windows`                           |
 | `macos-latest`                   | `macos`, `ios`                             |
 
 ## Local Equivalents

docs/cli/index.md

@@ -828,7 +828,7 @@ Tip: when calling `config.set`/`config.apply`/`config.patch` directly, pass `bas
 
 See [/concepts/models](/concepts/models) for fallback behavior and scanning strategy.
 
-Preferred Anthropic auth (setup-token):
+Anthropic setup-token (supported):
 
 ```bash
 claude setup-token
@@ -836,6 +836,10 @@ openclaw models auth setup-token --provider anthropic
 openclaw models status
 ```
 
+Policy note: this is technical compatibility. Anthropic has blocked some
+subscription usage outside Claude Code in the past; verify current Anthropic
+terms before relying on setup-token in production.
+
 ### `models` (root)
 
 `openclaw models` is an alias for `models status`.

docs/cli/memory.md

@@ -50,3 +50,5 @@ Notes:
 - `memory status --deep --index` runs a reindex if the store is dirty.
 - `memory index --verbose` prints per-phase details (provider, model, sources, batch activity).
 - `memory status` includes any extra paths configured via `memorySearch.extraPaths`.
+- If effectively active memory remote API key fields are configured as SecretRefs, the command resolves those values from the active gateway snapshot. If gateway is unavailable, the command fails fast.
+- Gateway version skew note: this command path requires a gateway that supports `secrets.resolve`; older gateways return an unknown-method error.

docs/cli/models.md

@@ -77,3 +77,4 @@ Notes:
 
 - `setup-token` prompts for a setup-token value (generate it with `claude setup-token` on any machine).
 - `paste-token` accepts a token string generated elsewhere or from automation.
+- Anthropic policy note: setup-token support is technical compatibility. Anthropic has blocked some subscription usage outside Claude Code in the past, so verify current terms before using it broadly.

docs/cli/plugins.md

@@ -48,6 +48,10 @@ Security note: treat plugin installs like running code. Prefer pinned versions.
 Npm specs are **registry-only** (package name + optional version/tag). Git/URL/file
 specs are rejected. Dependency installs run with `--ignore-scripts` for safety.
 
+If a bare install spec matches a bundled plugin id (for example `diffs`), OpenClaw
+installs the bundled plugin directly. To install an npm package with the same
+name, use an explicit scoped spec (for example `@scope/diffs`).
+
 Supported archives: `.zip`, `.tgz`, `.tar.gz`, `.tar`.
 
 Use `--link` to avoid copying a local directory (adds to `plugins.load.paths`):

docs/cli/qr.md

@@ -34,6 +34,9 @@ openclaw qr --url wss://gateway.example/ws --token '<token>'
 ## Notes
 
 - `--token` and `--password` are mutually exclusive.
+- With `--remote`, if effectively active remote credentials are configured as SecretRefs and you do not pass `--token` or `--password`, the command resolves them from the active gateway snapshot. If gateway is unavailable, the command fails fast.
+- Without `--remote`, local `gateway.auth.password` SecretRefs are resolved when password auth can win (explicit `gateway.auth.mode="password"` or inferred password mode with no winning token from auth/env), and no CLI auth override is passed.
+- Gateway version skew note: this command path requires a gateway that supports `secrets.resolve`; older gateways return an unknown-method error.
 - After scanning, approve device pairing with:
   - `openclaw devices list`
   - `openclaw devices approve <requestId>`

docs/cli/secrets.md

@@ -9,14 +9,14 @@ title: "secrets"
 
 # `openclaw secrets`
 
-Use `openclaw secrets` to migrate credentials from plaintext to SecretRefs and keep the active secrets runtime healthy.
+Use `openclaw secrets` to manage SecretRefs and keep the active runtime snapshot healthy.
 
 Command roles:
 
 - `reload`: gateway RPC (`secrets.reload`) that re-resolves refs and swaps runtime snapshot only on full success (no config writes).
-- `audit`: read-only scan of config + auth stores + legacy residues (`.env`, `auth.json`) for plaintext, unresolved refs, and precedence drift.
-- `configure`: interactive planner for provider setup + target mapping + preflight (TTY required).
-- `apply`: execute a saved plan (`--dry-run` for validation only), then scrub migrated plaintext residues.
+- `audit`: read-only scan of configuration/auth stores and legacy residues for plaintext, unresolved refs, and precedence drift.
+- `configure`: interactive planner for provider setup, target mapping, and preflight (TTY required).
+- `apply`: execute a saved plan (`--dry-run` for validation only), then scrub targeted plaintext residues.
 
 Recommended operator loop:
 
@@ -31,11 +31,13 @@ openclaw secrets reload
 
 Exit code note for CI/gates:
 
-- `audit --check` returns `1` on findings, `2` when refs are unresolved.
+- `audit --check` returns `1` on findings.
+- unresolved refs return `2`.
 
 Related:
 
 - Secrets guide: [Secrets Management](/gateway/secrets)
+- Credential surface: [SecretRef Credential Surface](/reference/secretref-credential-surface)
 - Security guide: [Security](/gateway/security)
 
 ## Reload runtime snapshot
@@ -59,8 +61,8 @@ Scan OpenClaw state for:
 
 - plaintext secret storage
 - unresolved refs
-- precedence drift (`auth-profiles` shadowing config refs)
-- legacy residues (`auth.json`, OAuth out-of-scope notes)
+- precedence drift (`auth-profiles.json` credentials shadowing `openclaw.json` refs)
+- legacy residues (legacy auth store entries, OAuth reminders)
 
 ```bash
 openclaw secrets audit
@@ -71,7 +73,7 @@ openclaw secrets audit --json
 Exit behavior:
 
 - `--check` exits non-zero on findings.
-- unresolved refs exit with a higher-priority non-zero code.
+- unresolved refs exit with higher-priority non-zero code.
 
 Report shape highlights:
 
@@ -85,7 +87,7 @@ Report shape highlights:
 
 ## Configure (interactive helper)
 
-Build provider + SecretRef changes interactively, run preflight, and optionally apply:
+Build provider and SecretRef changes interactively, run preflight, and optionally apply:
 
 ```bash
 openclaw secrets configure
@@ -93,6 +95,7 @@ openclaw secrets configure --plan-out /tmp/openclaw-secrets-plan.json
 openclaw secrets configure --apply --yes
 openclaw secrets configure --providers-only
 openclaw secrets configure --skip-provider-setup
+openclaw secrets configure --agent ops
 openclaw secrets configure --json
 ```
 
@@ -106,23 +109,26 @@ Flags:
 
 - `--providers-only`: configure `secrets.providers` only, skip credential mapping.
 - `--skip-provider-setup`: skip provider setup and map credentials to existing providers.
+- `--agent <id>`: scope `auth-profiles.json` target discovery and writes to one agent store.
 
 Notes:
 
 - Requires an interactive TTY.
 - You cannot combine `--providers-only` with `--skip-provider-setup`.
-- `configure` targets secret-bearing fields in `openclaw.json`.
-- Include all secret-bearing fields you intend to migrate (for example both `models.providers.*.apiKey` and `skills.entries.*.apiKey`) so audit can reach a clean state.
+- `configure` targets secret-bearing fields in `openclaw.json` plus `auth-profiles.json` for the selected agent scope.
+- `configure` supports creating new `auth-profiles.json` mappings directly in the picker flow.
+- Canonical supported surface: [SecretRef Credential Surface](/reference/secretref-credential-surface).
 - It performs preflight resolution before apply.
 - Generated plans default to scrub options (`scrubEnv`, `scrubAuthProfilesForProviderTargets`, `scrubLegacyAuthJson` all enabled).
-- Apply path is one-way for migrated plaintext values.
+- Apply path is one-way for scrubbed plaintext values.
 - Without `--apply`, CLI still prompts `Apply this plan now?` after preflight.
-- With `--apply` (and no `--yes`), CLI prompts an extra irreversible-migration confirmation.
+- With `--apply` (and no `--yes`), CLI prompts an extra irreversible confirmation.
 
 Exec provider safety note:
 
 - Homebrew installs often expose symlinked binaries under `/opt/homebrew/bin/*`.
 - Set `allowSymlinkCommand: true` only when needed for trusted package-manager paths, and pair it with `trustedDirs` (for example `["/opt/homebrew"]`).
+- On Windows, if ACL verification is unavailable for a provider path, OpenClaw fails closed. For trusted paths only, set `allowInsecurePath: true` on that provider to bypass path security checks.
 
 ## Apply a saved plan
 
@@ -154,10 +160,9 @@ Safety comes from strict preflight + atomic-ish apply with best-effort in-memory
 ## Example
 
 ```bash
-# Audit first, then configure, then confirm clean:
 openclaw secrets audit --check
 openclaw secrets configure
 openclaw secrets audit --check
 ```
 
-If `audit --check` still reports plaintext findings after a partial migration, verify you also migrated skill keys (`skills.entries.*.apiKey`) and any other reported target paths.
+If `audit --check` still reports plaintext findings, update the remaining reported target paths and rerun audit.

docs/concepts/context.md

@@ -114,6 +114,8 @@ By default, OpenClaw injects a fixed set of workspace files (if present):
 
 Large files are truncated per-file using `agents.defaults.bootstrapMaxChars` (default `20000` chars). OpenClaw also enforces a total bootstrap injection cap across files with `agents.defaults.bootstrapTotalMaxChars` (default `150000` chars). `/context` shows **raw vs injected** sizes and whether truncation happened.
 
+When truncation occurs, the runtime can inject an in-prompt warning block under Project Context. Configure this with `agents.defaults.bootstrapPromptTruncationWarning` (`off`, `once`, `always`; default `once`).
+
 ## Skills: what’s injected vs loaded on-demand
 
 The system prompt includes a compact **skills list** (name + description + location). This list has real overhead.

docs/concepts/memory.md

@@ -109,6 +109,8 @@ Defaults:
   6. Otherwise memory search stays disabled until configured.
 - Local mode uses node-llama-cpp and may require `pnpm approve-builds`.
 - Uses sqlite-vec (when available) to accelerate vector search inside SQLite.
+- `memorySearch.provider = "ollama"` is also supported for local/self-hosted
+  Ollama embeddings (`/api/embeddings`), but it is not auto-selected.
 
 Remote embeddings **require** an API key for the embedding provider. OpenClaw
 resolves keys from auth profiles, `models.providers.*.apiKey`, or environment
@@ -116,7 +118,9 @@ variables. Codex OAuth only covers chat/completions and does **not** satisfy
 embeddings for memory search. For Gemini, use `GEMINI_API_KEY` or
 `models.providers.google.apiKey`. For Voyage, use `VOYAGE_API_KEY` or
 `models.providers.voyage.apiKey`. For Mistral, use `MISTRAL_API_KEY` or
-`models.providers.mistral.apiKey`.
+`models.providers.mistral.apiKey`. Ollama typically does not require a real API
+key (a placeholder like `OLLAMA_API_KEY=ollama-local` is enough when needed by
+local policy).
 When using a custom OpenAI-compatible endpoint,
 set `memorySearch.remote.apiKey` (and optional `memorySearch.remote.headers`).
 
@@ -331,7 +335,7 @@ If you don't want to set an API key, use `memorySearch.provider = "local"` or se
 
 Fallbacks:
 
-- `memorySearch.fallback` can be `openai`, `gemini`, `voyage`, `mistral`, `local`, or `none`.
+- `memorySearch.fallback` can be `openai`, `gemini`, `voyage`, `mistral`, `ollama`, `local`, or `none`.
 - The fallback provider is only used when the primary embedding provider fails.
 
 Batch indexing (OpenAI + Gemini + Voyage):

docs/concepts/model-failover.md

@@ -83,6 +83,9 @@ When a profile fails due to auth/rate‑limit errors (or a timeout that looks
 like rate limiting), OpenClaw marks it in cooldown and moves to the next profile.
 Format/invalid‑request errors (for example Cloud Code Assist tool call ID
 validation failures) are treated as failover‑worthy and use the same cooldowns.
+OpenAI-compatible stop-reason errors such as `Unhandled stop reason: error`,
+`stop reason: error`, and `reason: error` are classified as timeout/failover
+signals.
 
 Cooldowns use exponential backoff:
 

docs/concepts/model-providers.md

@@ -60,6 +60,8 @@ OpenClaw ships with the pi‑ai catalog. These providers require **no**
 - Optional rotation: `ANTHROPIC_API_KEYS`, `ANTHROPIC_API_KEY_1`, `ANTHROPIC_API_KEY_2`, plus `OPENCLAW_LIVE_ANTHROPIC_KEY` (single override)
 - Example model: `anthropic/claude-opus-4-6`
 - CLI: `openclaw onboard --auth-choice token` (paste setup-token) or `openclaw models auth paste-token --provider anthropic`
+- Policy note: setup-token support is technical compatibility; Anthropic has blocked some subscription usage outside Claude Code in the past. Verify current Anthropic terms and decide based on your risk tolerance.
+- Recommendation: Anthropic API key auth is the safer, recommended path over subscription setup-token auth.
 
 ```json5
 {
@@ -75,6 +77,7 @@ OpenClaw ships with the pi‑ai catalog. These providers require **no**
 - CLI: `openclaw onboard --auth-choice openai-codex` or `openclaw models auth login --provider openai-codex`
 - Default transport is `auto` (WebSocket-first, SSE fallback)
 - Override per model via `agents.defaults.models["openai-codex/<model>"].params.transport` (`"sse"`, `"websocket"`, or `"auto"`)
+- Policy note: OpenAI Codex OAuth is explicitly supported for external tools/workflows like OpenClaw.
 
 ```json5
 {
@@ -121,7 +124,7 @@ OpenClaw ships with the pi‑ai catalog. These providers require **no**
 
 - Provider: `zai`
 - Auth: `ZAI_API_KEY`
-- Example model: `zai/glm-4.7`
+- Example model: `zai/glm-5`
 - CLI: `openclaw onboard --auth-choice zai-api-key`
   - Aliases: `z.ai/*` and `z-ai/*` normalize to `zai/*`
 
@@ -175,14 +178,20 @@ Moonshot uses OpenAI-compatible endpoints, so configure it as a custom provider:
 
 Kimi K2 model IDs:
 
-{/_moonshot-kimi-k2-model-refs:start_/ && null}
+<!-- markdownlint-disable MD037 -->
+
+{/_ moonshot-kimi-k2-model-refs:start _/ && null}
+
+<!-- markdownlint-enable MD037 -->
 
 - `moonshot/kimi-k2.5`
 - `moonshot/kimi-k2-0905-preview`
 - `moonshot/kimi-k2-turbo-preview`
 - `moonshot/kimi-k2-thinking`
 - `moonshot/kimi-k2-thinking-turbo`
-  {/_moonshot-kimi-k2-model-refs:end_/ && null}
+  <!-- markdownlint-disable MD037 -->
+  {/_ moonshot-kimi-k2-model-refs:end _/ && null}
+  <!-- markdownlint-enable MD037 -->
 
 ```json5
 {
@@ -307,13 +316,13 @@ Synthetic provides Anthropic-compatible models behind the `synthetic` provider:
 
 - Provider: `synthetic`
 - Auth: `SYNTHETIC_API_KEY`
-- Example model: `synthetic/hf:MiniMaxAI/MiniMax-M2.1`
+- Example model: `synthetic/hf:MiniMaxAI/MiniMax-M2.5`
 - CLI: `openclaw onboard --auth-choice synthetic-api-key`
 
 ```json5
 {
   agents: {
-    defaults: { model: { primary: "synthetic/hf:MiniMaxAI/MiniMax-M2.1" } },
+    defaults: { model: { primary: "synthetic/hf:MiniMaxAI/MiniMax-M2.5" } },
   },
   models: {
     mode: "merge",
@@ -322,7 +331,7 @@ Synthetic provides Anthropic-compatible models behind the `synthetic` provider:
         baseUrl: "https://api.synthetic.new/anthropic",
         apiKey: "${SYNTHETIC_API_KEY}",
         api: "anthropic-messages",
-        models: [{ id: "hf:MiniMaxAI/MiniMax-M2.1", name: "MiniMax M2.1" }],
+        models: [{ id: "hf:MiniMaxAI/MiniMax-M2.5", name: "MiniMax M2.5" }],
       },
     },
   },
@@ -396,8 +405,8 @@ Example (OpenAI‑compatible):
 {
   agents: {
     defaults: {
-      model: { primary: "lmstudio/minimax-m2.1-gs32" },
-      models: { "lmstudio/minimax-m2.1-gs32": { alias: "Minimax" } },
+      model: { primary: "lmstudio/minimax-m2.5-gs32" },
+      models: { "lmstudio/minimax-m2.5-gs32": { alias: "Minimax" } },
     },
   },
   models: {
@@ -408,8 +417,8 @@ Example (OpenAI‑compatible):
         api: "openai-completions",
         models: [
           {
-            id: "minimax-m2.1-gs32",
-            name: "MiniMax M2.1",
+            id: "minimax-m2.5-gs32",
+            name: "MiniMax M2.5",
             reasoning: false,
             input: ["text"],
             cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
@@ -433,6 +442,9 @@ Notes:
   - `contextWindow: 200000`
   - `maxTokens: 8192`
 - Recommended: set explicit values that match your proxy/model limits.
+- For `api: "openai-completions"` on non-native endpoints (any non-empty `baseUrl` whose host is not `api.openai.com`), OpenClaw forces `compat.supportsDeveloperRole: false` to avoid provider 400 errors for unsupported `developer` roles.
+- If `baseUrl` is empty/omitted, OpenClaw keeps the default OpenAI behavior (which resolves to `api.openai.com`).
+- For safety, an explicit `compat.supportsDeveloperRole: true` is still overridden on non-native `openai-completions` endpoints.
 
 ## CLI examples
 

docs/concepts/models.md

@@ -28,10 +28,11 @@ Related:
 - `agents.defaults.imageModel` is used **only when** the primary model can’t accept images.
 - Per-agent defaults can override `agents.defaults.model` via `agents.list[].model` plus bindings (see [/concepts/multi-agent](/concepts/multi-agent)).
 
-## Quick model picks (anecdotal)
+## Quick model policy
 
-- **GLM**: a bit better for coding/tool calling.
-- **MiniMax**: better for writing and vibes.
+- Set your primary to the strongest latest-generation model available to you.
+- Use fallbacks for cost/latency-sensitive tasks and lower-stakes chat.
+- For tool-enabled agents or untrusted inputs, avoid older/weaker model tiers.
 
 ## Setup wizard (recommended)
 
@@ -42,8 +43,7 @@ openclaw onboard
 ```
 
 It can set up model + auth for common providers, including **OpenAI Code (Codex)
-subscription** (OAuth) and **Anthropic** (API key recommended; `claude
-setup-token` also supported).
+subscription** (OAuth) and **Anthropic** (API key or `claude setup-token`).
 
 ## Config keys (overview)
 
@@ -160,7 +160,9 @@ JSON includes `auth.oauth` (warn window + profiles) and `auth.providers`
 (effective auth per provider).
 Use `--check` for automation (exit `1` when missing/expired, `2` when expiring).
 
-Preferred Anthropic auth is the Claude Code CLI setup-token (run anywhere; paste on the gateway host if needed):
+Auth choice is provider/account dependent. For always-on gateway hosts, API keys are usually the most predictable; subscription token flows are also supported.
+
+Example (Anthropic setup-token):
 
 ```bash
 claude setup-token

docs/concepts/oauth.md

@@ -10,7 +10,9 @@ title: "OAuth"
 
 # OAuth
 
-OpenClaw supports “subscription auth” via OAuth for providers that offer it (notably **OpenAI Codex (ChatGPT OAuth)**). For Anthropic subscriptions, use the **setup-token** flow. This page explains:
+OpenClaw supports “subscription auth” via OAuth for providers that offer it (notably **OpenAI Codex (ChatGPT OAuth)**). For Anthropic subscriptions, use the **setup-token** flow. Anthropic subscription use outside Claude Code has been restricted for some users in the past, so treat it as a user-choice risk and verify current Anthropic policy yourself. OpenAI Codex OAuth is explicitly supported for use in external tools like OpenClaw. This page explains:
+
+For Anthropic in production, API key auth is the safer recommended path over subscription setup-token auth.
 
 - how the OAuth **token exchange** works (PKCE)
 - where tokens are **stored** (and why)
@@ -54,6 +56,12 @@ For static secret refs and runtime snapshot activation behavior, see [Secrets Ma
 
 ## Anthropic setup-token (subscription auth)
 
+<Warning>
+Anthropic setup-token support is technical compatibility, not a policy guarantee.
+Anthropic has blocked some subscription usage outside Claude Code in the past.
+Decide for yourself whether to use subscription auth, and verify Anthropic's current terms.
+</Warning>
+
 Run `claude setup-token` on any machine, then paste it into OpenClaw:
 
 ```bash
@@ -76,7 +84,7 @@ openclaw models status
 
 OpenClaw’s interactive login flows are implemented in `@mariozechner/pi-ai` and wired into the wizards/commands.
 
-### Anthropic (Claude Pro/Max) setup-token
+### Anthropic setup-token
 
 Flow shape:
 
@@ -88,6 +96,8 @@ The wizard path is `openclaw onboard` → auth choice `setup-token` (Anthropic).
 
 ### OpenAI Codex (ChatGPT OAuth)
 
+OpenAI Codex OAuth is explicitly supported for use outside the Codex CLI, including OpenClaw workflows.
+
 Flow shape (PKCE):
 
 1. generate PKCE verifier/challenge + random `state`

docs/concepts/streaming.md

@@ -138,7 +138,7 @@ Legacy key migration:
 
 Telegram:
 
-- Uses Bot API `sendMessage` + `editMessageText`.
+- Uses Bot API `sendMessageDraft` in DMs when available, and `sendMessage` + `editMessageText` for group/topic preview updates.
 - Preview streaming is skipped when Telegram block streaming is explicitly enabled (to avoid double-streaming).
 - `/reasoning stream` can write reasoning to preview.