docs: clarify namespace cycle prevention

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

@@ -17,11 +17,6 @@ Use this skill for Parallels guest workflows and smoke interpretation. Do not lo
 - Per-phase logs land under `/tmp/openclaw-parallels-*`.
 - Do not run local and gateway agent turns in parallel on the same fresh workspace or session.
 - For `prlctl exec`, pass the VM name before `--current-user` (`prlctl exec "$VM" --current-user ...`), not the other way around.
-- If the workflow installs OpenClaw from a repo checkout instead of the site installer/npm release, finish by installing a real guest CLI shim and verifying it in a fresh guest shell. `pnpm openclaw ...` inside the repo is not enough for handoff parity.
-- On macOS guests, prefer a user-global install plus a stable PATH-visible shim:
-  - install with `NPM_CONFIG_PREFIX="$HOME/.npm-global" npm install -g .`
-  - make sure `~/.local/bin/openclaw` exists or `~/.npm-global/bin` is on PATH
-  - verify from a brand-new guest shell with `which openclaw` and `openclaw --version`
 
 ## npm install then update
 
@@ -59,7 +54,6 @@ Use this skill for Parallels guest workflows and smoke interpretation. Do not lo
 - Multi-word `openclaw agent --message ...` checks should call `& $openclaw ...` inside PowerShell, not `Start-Process ... -ArgumentList` against `openclaw.cmd`, or Commander can see split argv and throw `too many arguments for 'agent'`.
 - Windows installer/tgz phases now retry once after guest-ready recheck; keep new Windows smoke steps idempotent so a transport-flake retry is safe.
 - Windows global `npm install -g` phases can stay quiet for a minute or more even when healthy; inspect the phase log before calling it hung, and only treat it as a regression once the retry wrapper or timeout trips.
-- Fresh Windows ref-mode onboard should use the same background PowerShell runner plus done-file/log-drain pattern as the npm-update helper, including startup materialization checks, host-side timeouts on short poll `prlctl exec` calls, and retry-on-poll-failure behavior for transient transport flakes.
 - Keep onboarding and status output ASCII-clean in logs; fancy punctuation becomes mojibake in current capture paths.
 - If you hit an older run with `rc=255` plus an empty `fresh.install-main.log` or `upgrade.install-main.log`, treat it as a likely `prlctl exec` transport drop after guest start-up, not immediate proof of an npm/package failure.
 

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -9,8 +9,6 @@ body:
       value: |
         Thanks for filing this report. Keep every answer concise, reproducible, and grounded in observed evidence.
         Do not speculate or infer beyond the evidence. If a narrative section cannot be answered from the available evidence, respond with exactly `NOT_ENOUGH_INFO`.
-
-        If this is a plugin beta-release blocker, rename the issue title to `Beta blocker: <plugin-name> - <summary>` and apply the `beta-blocker` label after filing.
   - type: dropdown
     id: bug_type
     attributes:
@@ -22,19 +20,6 @@ body:
         - Behavior bug (incorrect output/state without crash)
     validations:
       required: true
-  - type: dropdown
-    id: beta_blocker
-    attributes:
-      label: Beta release blocker
-      description: >
-        Choose `Yes` only if this blocks plugin compatibility during the current beta release window.
-        Selecting `Yes` does not apply the label automatically. You must also rename the issue title
-        to `Beta blocker: <plugin-name> - <summary>` for the automation to apply the `beta-blocker` label.
-      options:
-        - "No"
-        - "Yes"
-    validations:
-      required: true
   - type: textarea
     id: summary
     attributes:

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

@@ -1,7 +1,7 @@
 name: Setup Node environment
 description: >
-  Install Node 24 by default, pnpm, optionally Bun, and optionally run pnpm
-  install. Requires actions/checkout to run first.
+  Initialize submodules with retry, install Node 24 by default, pnpm, optionally Bun,
+  and optionally run pnpm install. Requires actions/checkout to run first.
 inputs:
   node-version:
     description: Node.js version to install.
@@ -34,6 +34,20 @@ inputs:
 runs:
   using: composite
   steps:
+    - name: Checkout submodules (retry)
+      shell: bash
+      run: |
+        set -euo pipefail
+        git submodule sync --recursive
+        for attempt in 1 2 3 4 5; do
+          if git -c protocol.version=2 submodule update --init --force --depth=1 --recursive; then
+            exit 0
+          fi
+          echo "Submodule update failed (attempt $attempt/5). Retrying…"
+          sleep $((attempt * 10))
+        done
+        exit 1
+
     - name: Setup Node.js
       uses: actions/setup-node@v6
       with:

.github/labeler.yml

@@ -221,6 +221,10 @@
   - changed-files:
       - any-glob-to-any-file:
           - "extensions/open-prose/**"
+"extensions: qwen-portal-auth":
+  - changed-files:
+      - any-glob-to-any-file:
+          - "extensions/qwen-portal-auth/**"
 "extensions: device-pair":
   - changed-files:
       - any-glob-to-any-file:

.github/pull_request_template.md

@@ -2,8 +2,6 @@
 
 Describe the problem and fix in 2–5 bullets:
 
-If this PR fixes a plugin beta-release blocker, title it `fix(<plugin-id>): beta blocker - <summary>` and link the matching `Beta blocker: <plugin-name> - <summary>` issue labeled `beta-blocker`. Contributors cannot label PRs, so the title is the PR-side signal for maintainers and automation.
-
 - Problem:
 - Why it matters:
 - What changed:
@@ -65,18 +63,6 @@ For bug fixes or regressions, name the smallest reliable test coverage that shou
 List user-visible changes (including defaults/config).  
 If none, write `None`.
 
-## Diagram (if applicable)
-
-For UI changes or non-trivial logic flows, include a small ASCII diagram reviewers can scan quickly. Otherwise write `N/A`.
-
-```text
-Before:
-[user action] -> [old state]
-
-After:
-[user action] -> [new state] -> [result]
-```
-
 ## Security Impact (required)
 
 - New permissions/capabilities? (`Yes/No`)
@@ -141,6 +127,12 @@ If a bot review conversation is addressed by this PR, resolve that conversation
 - Migration needed? (`Yes/No`)
 - If yes, exact upgrade steps:
 
+## Failure Recovery (if this breaks)
+
+- How to disable/revert this change quickly:
+- Files/config to restore:
+- Known bad symptoms reviewers should watch for:
+
 ## Risks and Mitigations
 
 List only real risks for this PR. Add/remove entries as needed. If none, write `None`.

.github/workflows/ci-bun.yml

@@ -12,42 +12,7 @@ env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
 
 jobs:
-  preflight:
-    runs-on: blacksmith-16vcpu-ubuntu-2404
-    timeout-minutes: 20
-    outputs:
-      run_bun_checks: ${{ steps.manifest.outputs.run_bun_checks }}
-      bun_checks_matrix: ${{ steps.manifest.outputs.bun_checks_matrix }}
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v6
-        with:
-          submodules: false
-
-      - name: Setup Node environment
-        uses: ./.github/actions/setup-node-env
-        with:
-          install-bun: "false"
-          install-deps: "false"
-          use-sticky-disk: "false"
-
-      - name: Build Bun CI manifest
-        id: manifest
-        env:
-          OPENCLAW_CI_DOCS_ONLY: "false"
-          OPENCLAW_CI_DOCS_CHANGED: "false"
-          OPENCLAW_CI_RUN_NODE: "true"
-          OPENCLAW_CI_RUN_MACOS: "false"
-          OPENCLAW_CI_RUN_ANDROID: "false"
-          OPENCLAW_CI_RUN_WINDOWS: "false"
-          OPENCLAW_CI_RUN_SKILLS_PYTHON: "false"
-          OPENCLAW_CI_HAS_CHANGED_EXTENSIONS: "false"
-          OPENCLAW_CI_CHANGED_EXTENSIONS_MATRIX: '{"include":[]}'
-        run: node scripts/ci-write-manifest-outputs.mjs --workflow ci-bun
-
   build-bun-artifacts:
-    needs: [preflight]
-    if: needs.preflight.outputs.run_bun_checks == 'true'
     runs-on: blacksmith-16vcpu-ubuntu-2404
     timeout-minutes: 20
     steps:
@@ -66,22 +31,25 @@ jobs:
         run: pnpm canvas:a2ui:bundle
 
       - name: Upload A2UI bundle artifact
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v4
         with:
           name: canvas-a2ui-bundle
           path: src/canvas-host/a2ui/
-          include-hidden-files: true
-          retention-days: 1
 
   bun-checks:
-    name: ${{ matrix.check_name }}
-    needs: [preflight, build-bun-artifacts]
-    if: needs.preflight.outputs.run_bun_checks == 'true'
+    needs: [build-bun-artifacts]
     runs-on: blacksmith-16vcpu-ubuntu-2404
     timeout-minutes: 20
     strategy:
       fail-fast: false
-      matrix: ${{ fromJson(needs.preflight.outputs.bun_checks_matrix) }}
+      matrix:
+        include:
+          - shard_index: 1
+            shard_count: 2
+            command: OPENCLAW_TEST_ISOLATE=1 bunx vitest run --config vitest.unit.config.ts --shard 1/2
+          - shard_index: 2
+            shard_count: 2
+            command: OPENCLAW_TEST_ISOLATE=1 bunx vitest run --config vitest.unit.config.ts --shard 2/2
     steps:
       - name: Checkout
         uses: actions/checkout@v6
@@ -101,10 +69,4 @@ jobs:
           path: src/canvas-host/a2ui/
 
       - name: Run Bun test shard
-        env:
-          SHARD_COUNT: ${{ matrix.shard_count }}
-          SHARD_INDEX: ${{ matrix.shard_index }}
-        shell: bash
-        run: |
-          set -euo pipefail
-          OPENCLAW_TEST_ISOLATE=1 bunx vitest run --config vitest.unit.config.ts --shard "$SHARD_INDEX/$SHARD_COUNT"
+        run: ${{ matrix.command }}

.github/workflows/ci.yml

@@ -17,41 +17,26 @@ env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
 
 jobs:
-  # Preflight: establish routing truth and planner-owned matrices once, then let
-  # real work fan out from a single source of truth.
-  preflight:
+  # Scope: establish the fast global truth for this revision before the
+  # expensive platform and platform-specific lanes fan out.
+  # Detect docs-only changes to skip heavy jobs (test, build, Windows, macOS, Android).
+  # Keep this job focused on routing decisions so the rest of CI can fan out sooner.
+  # Fail-safe: if detection steps are skipped, downstream outputs fall back to
+  # conservative defaults that keep heavy lanes enabled.
+  scope:
     if: github.event_name != 'pull_request' || !github.event.pull_request.draft
     runs-on: blacksmith-16vcpu-ubuntu-2404
     timeout-minutes: 20
     outputs:
-      docs_only: ${{ steps.manifest.outputs.docs_only }}
-      docs_changed: ${{ steps.manifest.outputs.docs_changed }}
-      run_node: ${{ steps.manifest.outputs.run_node }}
-      run_macos: ${{ steps.manifest.outputs.run_macos }}
-      run_android: ${{ steps.manifest.outputs.run_android }}
-      run_skills_python: ${{ steps.manifest.outputs.run_skills_python }}
-      run_skills_python_job: ${{ steps.manifest.outputs.run_skills_python_job }}
-      run_windows: ${{ steps.manifest.outputs.run_windows }}
-      has_changed_extensions: ${{ steps.manifest.outputs.has_changed_extensions }}
-      changed_extensions_matrix: ${{ steps.manifest.outputs.changed_extensions_matrix }}
-      run_build_artifacts: ${{ steps.manifest.outputs.run_build_artifacts }}
-      run_checks_fast: ${{ steps.manifest.outputs.run_checks_fast }}
-      checks_fast_matrix: ${{ steps.manifest.outputs.checks_fast_matrix }}
-      run_checks: ${{ steps.manifest.outputs.run_checks }}
-      checks_matrix: ${{ steps.manifest.outputs.checks_matrix }}
-      run_extension_fast: ${{ steps.manifest.outputs.run_extension_fast }}
-      extension_fast_matrix: ${{ steps.manifest.outputs.extension_fast_matrix }}
-      run_check: ${{ steps.manifest.outputs.run_check }}
-      run_check_additional: ${{ steps.manifest.outputs.run_check_additional }}
-      run_build_smoke: ${{ steps.manifest.outputs.run_build_smoke }}
-      run_check_docs: ${{ steps.manifest.outputs.run_check_docs }}
-      run_checks_windows: ${{ steps.manifest.outputs.run_checks_windows }}
-      checks_windows_matrix: ${{ steps.manifest.outputs.checks_windows_matrix }}
-      run_macos_node: ${{ steps.manifest.outputs.run_macos_node }}
-      macos_node_matrix: ${{ steps.manifest.outputs.macos_node_matrix }}
-      run_macos_swift: ${{ steps.manifest.outputs.run_macos_swift }}
-      run_android_job: ${{ steps.manifest.outputs.run_android_job }}
-      android_matrix: ${{ steps.manifest.outputs.android_matrix }}
+      docs_only: ${{ steps.docs_scope.outputs.docs_only }}
+      docs_changed: ${{ steps.docs_scope.outputs.docs_changed }}
+      run_node: ${{ steps.changed_scope.outputs.run_node || 'false' }}
+      run_macos: ${{ steps.changed_scope.outputs.run_macos || 'false' }}
+      run_android: ${{ steps.changed_scope.outputs.run_android || 'false' }}
+      run_skills_python: ${{ steps.changed_scope.outputs.run_skills_python || 'false' }}
+      run_windows: ${{ steps.changed_scope.outputs.run_windows || 'false' }}
+      has_changed_extensions: ${{ steps.changed_extensions.outputs.has_changed_extensions || 'false' }}
+      changed_extensions_matrix: ${{ steps.changed_extensions.outputs.changed_extensions_matrix || '{"include":[]}' }}
     steps:
       - name: Checkout
         uses: actions/checkout@v6
@@ -71,6 +56,8 @@ jobs:
         id: docs_scope
         uses: ./.github/actions/detect-docs-changes
 
+      # Detect which heavy areas are touched so CI can skip unrelated expensive jobs.
+      # Fail-safe: if skipped, downstream lanes run.
       - name: Detect changed scopes
         id: changed_scope
         if: steps.docs_scope.outputs.docs_only != 'true'
@@ -117,20 +104,6 @@ jobs:
           appendFileSync(process.env.GITHUB_OUTPUT, `changed_extensions_matrix=${matrix}\n`, "utf8");
           EOF
 
-      - name: Build CI manifest
-        id: manifest
-        env:
-          OPENCLAW_CI_DOCS_ONLY: ${{ steps.docs_scope.outputs.docs_only }}
-          OPENCLAW_CI_DOCS_CHANGED: ${{ steps.docs_scope.outputs.docs_changed }}
-          OPENCLAW_CI_RUN_NODE: ${{ steps.changed_scope.outputs.run_node || 'false' }}
-          OPENCLAW_CI_RUN_MACOS: ${{ steps.changed_scope.outputs.run_macos || 'false' }}
-          OPENCLAW_CI_RUN_ANDROID: ${{ steps.changed_scope.outputs.run_android || 'false' }}
-          OPENCLAW_CI_RUN_WINDOWS: ${{ steps.changed_scope.outputs.run_windows || 'false' }}
-          OPENCLAW_CI_RUN_SKILLS_PYTHON: ${{ steps.changed_scope.outputs.run_skills_python || 'false' }}
-          OPENCLAW_CI_HAS_CHANGED_EXTENSIONS: ${{ steps.changed_extensions.outputs.has_changed_extensions || 'false' }}
-          OPENCLAW_CI_CHANGED_EXTENSIONS_MATRIX: ${{ steps.changed_extensions.outputs.changed_extensions_matrix || '{"include":[]}' }}
-        run: node scripts/ci-write-manifest-outputs.mjs --workflow ci
-
   # Run the fast security/SCM checks in parallel with scope detection so the
   # main Node jobs do not have to wait for Python/pre-commit setup.
   security-fast:
@@ -228,12 +201,12 @@ jobs:
       - name: Audit production dependencies
         run: pre-commit run --config "${PRE_COMMIT_CONFIG_PATH:-.pre-commit-config.yaml}" --all-files pnpm-audit-prod
 
+  # Fanout: downstream lanes branch from preflight outputs instead of waiting
+  # on unrelated Linux checks.
   # Build dist once for Node-relevant changes and share it with downstream jobs.
-  # Keep this overlapping with the fast correctness lanes so green PRs get heavy
-  # test/build feedback sooner instead of waiting behind a full `check` pass.
   build-artifacts:
-    needs: [preflight]
-    if: needs.preflight.outputs.run_build_artifacts == 'true'
+    needs: [scope]
+    if: needs.scope.outputs.docs_only != 'true' && needs.scope.outputs.run_node == 'true'
     runs-on: blacksmith-16vcpu-ubuntu-2404
     timeout-minutes: 20
     steps:
@@ -277,15 +250,51 @@ jobs:
           include-hidden-files: true
           retention-days: 1
 
+  # Validate npm pack contents after build (only on push to main, not PRs).
+  release-check:
+    needs: [scope, build-artifacts]
+    if: github.event_name == 'push' && needs.scope.outputs.docs_only != 'true'
+    runs-on: blacksmith-16vcpu-ubuntu-2404
+    timeout-minutes: 20
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+        with:
+          persist-credentials: false
+          submodules: false
+
+      - name: Setup Node environment
+        uses: ./.github/actions/setup-node-env
+        with:
+          install-bun: "false"
+          use-sticky-disk: "false"
+
+      - name: Download dist artifact
+        uses: actions/download-artifact@v8
+        with:
+          name: dist-build
+          path: dist/
+
+      - name: Check release contents
+        run: pnpm release:check
+
   checks-fast:
-    name: ${{ matrix.check_name }}
-    needs: [preflight]
-    if: needs.preflight.outputs.run_checks_fast == 'true'
+    needs: [scope]
+    if: always() && needs.scope.outputs.docs_only != 'true' && needs.scope.outputs.run_node == 'true'
     runs-on: blacksmith-16vcpu-ubuntu-2404
     timeout-minutes: 20
     strategy:
       fail-fast: false
-      matrix: ${{ fromJson(needs.preflight.outputs.checks_fast_matrix) }}
+      matrix:
+        include:
+          - runtime: node
+            task: extensions
+            command: pnpm test:extensions
+          - runtime: node
+            task: contracts-protocol
+            command: |
+              pnpm test:contracts
+              pnpm protocol:check
     steps:
       - name: Checkout
         uses: actions/checkout@v6
@@ -300,35 +309,64 @@ jobs:
           use-sticky-disk: "false"
 
       - name: Run ${{ matrix.task }} (${{ matrix.runtime }})
-        env:
-          TASK: ${{ matrix.task }}
-        shell: bash
-        run: |
-          set -euo pipefail
-          case "$TASK" in
-            extensions)
-              pnpm test:extensions
-              ;;
-            contracts|contracts-protocol)
-              pnpm build
-              pnpm test:contracts
-              pnpm protocol:check
-              ;;
-            *)
-              echo "Unsupported checks-fast task: $TASK" >&2
-              exit 1
-              ;;
-          esac
+        run: ${{ matrix.command }}
 
   checks:
-    name: ${{ matrix.check_name }}
-    needs: [preflight, build-artifacts]
-    if: always() && needs.preflight.outputs.run_checks == 'true' && needs.build-artifacts.result == 'success'
+    needs: [scope, build-artifacts]
+    if: always() && needs.scope.outputs.docs_only != 'true' && needs.scope.outputs.run_node == 'true' && needs.build-artifacts.result == 'success'
     runs-on: blacksmith-16vcpu-ubuntu-2404
     timeout-minutes: 20
     strategy:
       fail-fast: false
-      matrix: ${{ fromJson(needs.preflight.outputs.checks_matrix) }}
+      matrix:
+        include:
+          - runtime: node
+            task: test
+            shard_index: 1
+            shard_count: 4
+            command: pnpm test
+          - runtime: node
+            task: test
+            shard_index: 2
+            shard_count: 4
+            command: pnpm test
+          - runtime: node
+            task: test
+            shard_index: 3
+            shard_count: 4
+            command: pnpm test
+          - runtime: node
+            task: test
+            shard_index: 4
+            shard_count: 4
+            command: pnpm test
+          - runtime: node
+            task: channels
+            shard_index: 1
+            shard_count: 3
+            command: pnpm test:channels
+          - runtime: node
+            task: channels
+            shard_index: 2
+            shard_count: 3
+            command: pnpm test:channels
+          - runtime: node
+            task: channels
+            shard_index: 3
+            shard_count: 3
+            command: pnpm test:channels
+          - runtime: node
+            task: compat-node22
+            node_version: "22.x"
+            cache_key_suffix: "node22"
+            command: |
+              pnpm build
+              pnpm ui:build
+              node openclaw.mjs --help
+              node openclaw.mjs status --json --timeout 1
+              pnpm test:build:singleton
+              node scripts/stage-bundled-plugin-runtime-deps.mjs
+              node --import tsx scripts/release-check.ts
     steps:
       - name: Skip compatibility lanes on pull requests
         if: github.event_name == 'pull_request' && matrix.task == 'compat-node22'
@@ -353,7 +391,6 @@ jobs:
       - name: Configure Node test resources
         if: (github.event_name != 'pull_request' || matrix.task != 'compat-node22') && matrix.runtime == 'node' && (matrix.task == 'test' || matrix.task == 'channels' || matrix.task == 'compat-node22')
         env:
-          TASK: ${{ matrix.task }}
           SHARD_COUNT: ${{ matrix.shard_count || '' }}
           SHARD_INDEX: ${{ matrix.shard_index || '' }}
         run: |
@@ -361,7 +398,7 @@ jobs:
           # Default heap limits have been too low on Linux CI (V8 OOM near 4GB).
           echo "OPENCLAW_TEST_WORKERS=2" >> "$GITHUB_ENV"
           echo "OPENCLAW_TEST_MAX_OLD_SPACE_SIZE_MB=6144" >> "$GITHUB_ENV"
-          if [ "$TASK" = "channels" ]; then
+          if [ "${{ matrix.task }}" = "channels" ]; then
             echo "OPENCLAW_TEST_WORKERS=1" >> "$GITHUB_ENV"
             echo "OPENCLAW_TEST_ISOLATE=1" >> "$GITHUB_ENV"
           fi
@@ -386,40 +423,17 @@ jobs:
 
       - name: Run ${{ matrix.task }} (${{ matrix.runtime }})
         if: github.event_name != 'pull_request' || matrix.task != 'compat-node22'
-        env:
-          TASK: ${{ matrix.task }}
-        shell: bash
-        run: |
-          set -euo pipefail
-          case "$TASK" in
-            test)
-              pnpm test
-              ;;
-            channels)
-              pnpm test:channels
-              ;;
-            compat-node22)
-              pnpm build
-              pnpm ui:build
-              node openclaw.mjs --help
-              node openclaw.mjs status --json --timeout 1
-              pnpm test:build:singleton
-              ;;
-            *)
-              echo "Unsupported checks task: $TASK" >&2
-              exit 1
-              ;;
-          esac
+        run: ${{ matrix.command }}
 
   extension-fast:
     name: "extension-fast"
-    needs: [preflight]
-    if: needs.preflight.outputs.run_extension_fast == 'true'
+    needs: [scope]
+    if: needs.scope.outputs.docs_only != 'true' && needs.scope.outputs.run_node == 'true' && needs.scope.outputs.has_changed_extensions == 'true'
     runs-on: blacksmith-16vcpu-ubuntu-2404
     timeout-minutes: 20
     strategy:
       fail-fast: false
-      matrix: ${{ fromJson(needs.preflight.outputs.extension_fast_matrix) }}
+      matrix: ${{ fromJson(needs.scope.outputs.changed_extensions_matrix) }}
     steps:
       - name: Checkout
         uses: actions/checkout@v6
@@ -441,8 +455,8 @@ jobs:
   # Types, lint, and format check.
   check:
     name: "check"
-    needs: [preflight]
-    if: always() && needs.preflight.outputs.run_check == 'true'
+    needs: [scope]
+    if: always() && (github.event_name != 'pull_request' || !github.event.pull_request.draft) && needs.scope.outputs.docs_only != 'true'
     runs-on: blacksmith-16vcpu-ubuntu-2404
     timeout-minutes: 20
     steps:
@@ -466,8 +480,8 @@ jobs:
 
   check-additional:
     name: "check-additional"
-    needs: [preflight]
-    if: always() && needs.preflight.outputs.run_check_additional == 'true'
+    needs: [scope]
+    if: always() && (github.event_name != 'pull_request' || !github.event.pull_request.draft) && needs.scope.outputs.docs_only != 'true'
     runs-on: blacksmith-16vcpu-ubuntu-2404
     timeout-minutes: 20
     steps:
@@ -488,51 +502,6 @@ jobs:
         continue-on-error: true
         run: pnpm run lint:plugins:no-extension-imports
 
-      - name: Run no-random-messaging guard
-        id: no_random_messaging
-        continue-on-error: true
-        run: pnpm run lint:tmp:no-random-messaging
-
-      - name: Run channel-agnostic boundary guard
-        id: channel_agnostic_boundaries
-        continue-on-error: true
-        run: pnpm run lint:tmp:channel-agnostic-boundaries
-
-      - name: Run no-raw-channel-fetch guard
-        id: no_raw_channel_fetch
-        continue-on-error: true
-        run: pnpm run lint:tmp:no-raw-channel-fetch
-
-      - name: Run ingress owner guard
-        id: ingress_owner
-        continue-on-error: true
-        run: pnpm run lint:agent:ingress-owner
-
-      - name: Run no-register-http-handler guard
-        id: no_register_http_handler
-        continue-on-error: true
-        run: pnpm run lint:plugins:no-register-http-handler
-
-      - name: Run no-monolithic plugin-sdk entry import guard
-        id: no_monolithic_plugin_sdk_entry_imports
-        continue-on-error: true
-        run: pnpm run lint:plugins:no-monolithic-plugin-sdk-entry-imports
-
-      - name: Run no-extension-src-imports guard
-        id: no_extension_src_imports
-        continue-on-error: true
-        run: pnpm run lint:plugins:no-extension-src-imports
-
-      - name: Run no-extension-test-core-imports guard
-        id: no_extension_test_core_imports
-        continue-on-error: true
-        run: pnpm run lint:plugins:no-extension-test-core-imports
-
-      - name: Run plugin-sdk subpaths exported guard
-        id: plugin_sdk_subpaths_exported
-        continue-on-error: true
-        run: pnpm run lint:plugins:plugin-sdk-subpaths-exported
-
       - name: Run web search provider boundary guard
         id: web_search_provider_boundary
         continue-on-error: true
@@ -548,11 +517,6 @@ jobs:
         continue-on-error: true
         run: pnpm run lint:extensions:no-plugin-sdk-internal
 
-      - name: Run extension relative-outside-package guard
-        id: extension_relative_outside_package_boundary
-        continue-on-error: true
-        run: pnpm run lint:extensions:no-relative-outside-package
-
       - name: Enforce safe external URL opening policy
         id: no_raw_window_open
         continue-on-error: true
@@ -563,6 +527,16 @@ jobs:
         continue-on-error: true
         run: pnpm test:gateway:watch-regression
 
+      - name: Check config docs drift statefile
+        id: config_docs_drift
+        continue-on-error: true
+        run: pnpm config:docs:check
+
+      - name: Check plugin SDK API baseline drift
+        id: plugin_sdk_api_drift
+        continue-on-error: true
+        run: pnpm plugin-sdk:api:check
+
       - name: Upload gateway watch regression artifacts
         if: always()
         uses: actions/upload-artifact@v7
@@ -575,40 +549,24 @@ jobs:
         if: always()
         env:
           PLUGIN_EXTENSION_BOUNDARY_OUTCOME: ${{ steps.plugin_extension_boundary.outcome }}
-          NO_RANDOM_MESSAGING_OUTCOME: ${{ steps.no_random_messaging.outcome }}
-          CHANNEL_AGNOSTIC_BOUNDARIES_OUTCOME: ${{ steps.channel_agnostic_boundaries.outcome }}
-          NO_RAW_CHANNEL_FETCH_OUTCOME: ${{ steps.no_raw_channel_fetch.outcome }}
-          INGRESS_OWNER_OUTCOME: ${{ steps.ingress_owner.outcome }}
-          NO_REGISTER_HTTP_HANDLER_OUTCOME: ${{ steps.no_register_http_handler.outcome }}
-          NO_MONOLITHIC_PLUGIN_SDK_ENTRY_IMPORTS_OUTCOME: ${{ steps.no_monolithic_plugin_sdk_entry_imports.outcome }}
-          NO_EXTENSION_SRC_IMPORTS_OUTCOME: ${{ steps.no_extension_src_imports.outcome }}
-          NO_EXTENSION_TEST_CORE_IMPORTS_OUTCOME: ${{ steps.no_extension_test_core_imports.outcome }}
-          PLUGIN_SDK_SUBPATHS_EXPORTED_OUTCOME: ${{ steps.plugin_sdk_subpaths_exported.outcome }}
           WEB_SEARCH_PROVIDER_BOUNDARY_OUTCOME: ${{ steps.web_search_provider_boundary.outcome }}
           EXTENSION_SRC_OUTSIDE_PLUGIN_SDK_BOUNDARY_OUTCOME: ${{ steps.extension_src_outside_plugin_sdk_boundary.outcome }}
           EXTENSION_PLUGIN_SDK_INTERNAL_BOUNDARY_OUTCOME: ${{ steps.extension_plugin_sdk_internal_boundary.outcome }}
-          EXTENSION_RELATIVE_OUTSIDE_PACKAGE_BOUNDARY_OUTCOME: ${{ steps.extension_relative_outside_package_boundary.outcome }}
           NO_RAW_WINDOW_OPEN_OUTCOME: ${{ steps.no_raw_window_open.outcome }}
           GATEWAY_WATCH_REGRESSION_OUTCOME: ${{ steps.gateway_watch_regression.outcome }}
+          CONFIG_DOCS_DRIFT_OUTCOME: ${{ steps.config_docs_drift.outcome }}
+          PLUGIN_SDK_API_DRIFT_OUTCOME: ${{ steps.plugin_sdk_api_drift.outcome }}
         run: |
           failures=0
           for result in \
             "plugin-extension-boundary|$PLUGIN_EXTENSION_BOUNDARY_OUTCOME" \
-            "lint:tmp:no-random-messaging|$NO_RANDOM_MESSAGING_OUTCOME" \
-            "lint:tmp:channel-agnostic-boundaries|$CHANNEL_AGNOSTIC_BOUNDARIES_OUTCOME" \
-            "lint:tmp:no-raw-channel-fetch|$NO_RAW_CHANNEL_FETCH_OUTCOME" \
-            "lint:agent:ingress-owner|$INGRESS_OWNER_OUTCOME" \
-            "lint:plugins:no-register-http-handler|$NO_REGISTER_HTTP_HANDLER_OUTCOME" \
-            "lint:plugins:no-monolithic-plugin-sdk-entry-imports|$NO_MONOLITHIC_PLUGIN_SDK_ENTRY_IMPORTS_OUTCOME" \
-            "lint:plugins:no-extension-src-imports|$NO_EXTENSION_SRC_IMPORTS_OUTCOME" \
-            "lint:plugins:no-extension-test-core-imports|$NO_EXTENSION_TEST_CORE_IMPORTS_OUTCOME" \
-            "lint:plugins:plugin-sdk-subpaths-exported|$PLUGIN_SDK_SUBPATHS_EXPORTED_OUTCOME" \
             "web-search-provider-boundary|$WEB_SEARCH_PROVIDER_BOUNDARY_OUTCOME" \
             "extension-src-outside-plugin-sdk-boundary|$EXTENSION_SRC_OUTSIDE_PLUGIN_SDK_BOUNDARY_OUTCOME" \
             "extension-plugin-sdk-internal-boundary|$EXTENSION_PLUGIN_SDK_INTERNAL_BOUNDARY_OUTCOME" \
-            "extension-relative-outside-package-boundary|$EXTENSION_RELATIVE_OUTSIDE_PACKAGE_BOUNDARY_OUTCOME" \
             "lint:ui:no-raw-window-open|$NO_RAW_WINDOW_OPEN_OUTCOME" \
-            "gateway-watch-regression|$GATEWAY_WATCH_REGRESSION_OUTCOME"; do
+            "gateway-watch-regression|$GATEWAY_WATCH_REGRESSION_OUTCOME" \
+            "config-docs-drift|$CONFIG_DOCS_DRIFT_OUTCOME" \
+            "plugin-sdk-api-drift|$PLUGIN_SDK_API_DRIFT_OUTCOME"; do
             name="${result%%|*}"
             outcome="${result#*|}"
             if [ "$outcome" != "success" ]; then
@@ -621,8 +579,8 @@ jobs:
 
   build-smoke:
     name: "build-smoke"
-    needs: [preflight, build-artifacts]
-    if: always() && needs.preflight.outputs.run_build_smoke == 'true' && (github.event_name != 'push' || needs.build-artifacts.result == 'success')
+    needs: [scope, build-artifacts]
+    if: always() && needs.scope.outputs.docs_only != 'true' && needs.scope.outputs.run_node == 'true' && (github.event_name != 'push' || needs.build-artifacts.result == 'success')
     runs-on: blacksmith-16vcpu-ubuntu-2404
     timeout-minutes: 20
     steps:
@@ -663,8 +621,8 @@ jobs:
 
   # Validate docs (format, lint, broken links) only when docs files changed.
   check-docs:
-    needs: [preflight]
-    if: needs.preflight.outputs.run_check_docs == 'true'
+    needs: [scope]
+    if: needs.scope.outputs.docs_changed == 'true'
     runs-on: blacksmith-16vcpu-ubuntu-2404
     timeout-minutes: 20
     steps:
@@ -684,8 +642,8 @@ jobs:
         run: pnpm check:docs
 
   skills-python:
-    needs: [preflight]
-    if: needs.preflight.outputs.run_skills_python_job == 'true'
+    needs: [scope]
+    if: needs.scope.outputs.docs_only != 'true' && (github.event_name == 'push' || needs.scope.outputs.run_skills_python == 'true')
     runs-on: blacksmith-16vcpu-ubuntu-2404
     timeout-minutes: 20
     steps:
@@ -712,9 +670,8 @@ jobs:
         run: python -m pytest -q skills
 
   checks-windows:
-    name: ${{ matrix.check_name }}
-    needs: [preflight, build-artifacts]
-    if: always() && needs.preflight.outputs.run_checks_windows == 'true' && needs.build-artifacts.result == 'success'
+    needs: [scope, build-artifacts]
+    if: always() && needs.scope.outputs.docs_only != 'true' && needs.scope.outputs.run_windows == 'true' && needs.build-artifacts.result == 'success'
     runs-on: blacksmith-32vcpu-windows-2025
     timeout-minutes: 20
     env:
@@ -727,7 +684,53 @@ jobs:
         shell: bash
     strategy:
       fail-fast: false
-      matrix: ${{ fromJson(needs.preflight.outputs.checks_windows_matrix) }}
+      matrix:
+        include:
+          - runtime: node
+            task: test
+            shard_index: 1
+            shard_count: 9
+            command: pnpm test
+          - runtime: node
+            task: test
+            shard_index: 2
+            shard_count: 9
+            command: pnpm test
+          - runtime: node
+            task: test
+            shard_index: 3
+            shard_count: 9
+            command: pnpm test
+          - runtime: node
+            task: test
+            shard_index: 4
+            shard_count: 9
+            command: pnpm test
+          - runtime: node
+            task: test
+            shard_index: 5
+            shard_count: 9
+            command: pnpm test
+          - runtime: node
+            task: test
+            shard_index: 6
+            shard_count: 9
+            command: pnpm test
+          - runtime: node
+            task: test
+            shard_index: 7
+            shard_count: 9
+            command: pnpm test
+          - runtime: node
+            task: test
+            shard_index: 8
+            shard_count: 9
+            command: pnpm test
+          - runtime: node
+            task: test
+            shard_index: 9
+            shard_count: 9
+            command: pnpm test
     steps:
       - name: Checkout
         uses: actions/checkout@v6
@@ -796,12 +799,9 @@ jobs:
 
       - name: Configure test shard (Windows)
         if: matrix.task == 'test'
-        env:
-          SHARD_COUNT: ${{ matrix.shard_count }}
-          SHARD_INDEX: ${{ matrix.shard_index }}
         run: |
-          echo "OPENCLAW_TEST_SHARDS=$SHARD_COUNT" >> "$GITHUB_ENV"
-          echo "OPENCLAW_TEST_SHARD_INDEX=$SHARD_INDEX" >> "$GITHUB_ENV"
+          echo "OPENCLAW_TEST_SHARDS=${{ matrix.shard_count }}" >> "$GITHUB_ENV"
+          echo "OPENCLAW_TEST_SHARD_INDEX=${{ matrix.shard_index }}" >> "$GITHUB_ENV"
 
       - name: Download dist artifact
         if: matrix.task == 'test'
@@ -818,30 +818,17 @@ jobs:
           path: src/canvas-host/a2ui/
 
       - name: Run ${{ matrix.task }} (${{ matrix.runtime }})
-        env:
-          TASK: ${{ matrix.task }}
-        shell: bash
-        run: |
-          set -euo pipefail
-          case "$TASK" in
-            test)
-              pnpm test
-              ;;
-            *)
-              echo "Unsupported Windows checks task: $TASK" >&2
-              exit 1
-              ;;
-          esac
+        run: ${{ matrix.command }}
 
-  macos-node:
-    name: ${{ matrix.check_name }}
-    needs: [preflight, build-artifacts]
-    if: always() && needs.preflight.outputs.run_macos_node == 'true' && needs.build-artifacts.result == 'success'
+  # Consolidated macOS job: runs TS tests + Swift lint/build/test sequentially
+  # on a single runner. GitHub limits macOS concurrent jobs to 5 per org;
+  # running 4 separate jobs per PR (as before) starved the queue. One job
+  # per PR allows 5 PRs to run macOS checks simultaneously.
+  macos:
+    needs: [scope]
+    if: github.event_name == 'pull_request' && needs.scope.outputs.docs_only != 'true' && needs.scope.outputs.run_macos == 'true'
     runs-on: macos-latest
     timeout-minutes: 20
-    strategy:
-      fail-fast: false
-      matrix: ${{ fromJson(needs.preflight.outputs.macos_node_matrix) }}
     steps:
       - name: Checkout
         uses: actions/checkout@v6
@@ -854,56 +841,16 @@ jobs:
         with:
           install-bun: "false"
 
-      - name: Download dist artifact
-        uses: actions/download-artifact@v8
-        with:
-          name: dist-build
-          path: dist/
-
-      - name: Download A2UI bundle artifact
-        uses: actions/download-artifact@v8
-        with:
-          name: canvas-a2ui-bundle
-          path: src/canvas-host/a2ui/
-
-      - name: Configure test shard (macOS)
-        env:
-          SHARD_COUNT: ${{ matrix.shard_count }}
-          SHARD_INDEX: ${{ matrix.shard_index }}
-        run: |
-          echo "OPENCLAW_TEST_SHARDS=$SHARD_COUNT" >> "$GITHUB_ENV"
-          echo "OPENCLAW_TEST_SHARD_INDEX=$SHARD_INDEX" >> "$GITHUB_ENV"
+      - name: Build dist (macOS)
+        run: pnpm build
 
+      # --- Run all checks sequentially (fast gates first) ---
       - name: TS tests (macOS)
         env:
           NODE_OPTIONS: --max-old-space-size=4096
-          TASK: ${{ matrix.task }}
-        shell: bash
-        run: |
-          set -euo pipefail
-          case "$TASK" in
-            test)
-              pnpm test
-              ;;
-            *)
-              echo "Unsupported macOS node task: $TASK" >&2
-              exit 1
-              ;;
-          esac
-
-  macos-swift:
-    name: "macos-swift"
-    needs: [preflight]
-    if: needs.preflight.outputs.run_macos_swift == 'true'
-    runs-on: macos-latest
-    timeout-minutes: 20
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v6
-        with:
-          persist-credentials: false
-          submodules: false
+        run: pnpm test
 
+      # --- Xcode/Swift setup ---
       - name: Select Xcode 26.1
         run: |
           sudo xcode-select -s /Applications/Xcode_26.1.app
@@ -912,14 +859,6 @@ jobs:
       - name: Install XcodeGen / SwiftLint / SwiftFormat
         run: brew install xcodegen swiftlint swiftformat
 
-      - name: Cache SwiftPM
-        uses: actions/cache@v5
-        with:
-          path: ~/Library/Caches/org.swift.swiftpm
-          key: ${{ runner.os }}-swiftpm-${{ hashFiles('apps/macos/Package.resolved') }}
-          restore-keys: |
-            ${{ runner.os }}-swiftpm-
-
       - name: Show toolchain
         run: |
           sw_vers
@@ -931,6 +870,14 @@ jobs:
           swiftlint --config .swiftlint.yml
           swiftformat --lint apps/macos/Sources --config .swiftformat
 
+      - name: Cache SwiftPM
+        uses: actions/cache@v5
+        with:
+          path: ~/Library/Caches/org.swift.swiftpm
+          key: ${{ runner.os }}-swiftpm-${{ hashFiles('apps/macos/Package.resolved') }}
+          restore-keys: |
+            ${{ runner.os }}-swiftpm-
+
       - name: Swift build (release)
         run: |
           set -euo pipefail
@@ -956,14 +903,22 @@ jobs:
           exit 1
 
   android:
-    name: ${{ matrix.check_name }}
-    needs: [preflight]
-    if: needs.preflight.outputs.run_android_job == 'true'
+    needs: [scope]
+    if: needs.scope.outputs.docs_only != 'true' && needs.scope.outputs.run_android == 'true'
     runs-on: blacksmith-16vcpu-ubuntu-2404
     timeout-minutes: 20
     strategy:
       fail-fast: false
-      matrix: ${{ fromJson(needs.preflight.outputs.android_matrix) }}
+      matrix:
+        include:
+          - task: test-play
+            command: ./gradlew --no-daemon :app:testPlayDebugUnitTest
+          - task: test-third-party
+            command: ./gradlew --no-daemon :app:testThirdPartyDebugUnitTest
+          - task: build-play
+            command: ./gradlew --no-daemon :app:assemblePlayDebug
+          - task: build-third-party
+            command: ./gradlew --no-daemon :app:assembleThirdPartyDebug
     steps:
       - name: Checkout
         uses: actions/checkout@v6
@@ -1012,26 +967,4 @@ jobs:
 
       - name: Run Android ${{ matrix.task }}
         working-directory: apps/android
-        env:
-          TASK: ${{ matrix.task }}
-        shell: bash
-        run: |
-          set -euo pipefail
-          case "$TASK" in
-            test-play)
-              ./gradlew --no-daemon :app:testPlayDebugUnitTest
-              ;;
-            test-third-party)
-              ./gradlew --no-daemon :app:testThirdPartyDebugUnitTest
-              ;;
-            build-play)
-              ./gradlew --no-daemon :app:assemblePlayDebug
-              ;;
-            build-third-party)
-              ./gradlew --no-daemon :app:assembleThirdPartyDebug
-              ;;
-            *)
-              echo "Unsupported Android task: $TASK" >&2
-              exit 1
-              ;;
-          esac
+        run: ${{ matrix.command }}

.github/workflows/docker-release.yml

@@ -2,6 +2,8 @@ name: Docker Release
 
 on:
   push:
+    branches:
+      - main
     tags:
       - "v*"
     paths-ignore:

.github/workflows/install-smoke.yml

@@ -15,34 +15,49 @@ env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
 
 jobs:
-  preflight:
+  docs-scope:
     if: github.event_name != 'pull_request' || !github.event.pull_request.draft
     runs-on: blacksmith-16vcpu-ubuntu-2404
     outputs:
-      docs_only: ${{ steps.manifest.outputs.docs_only }}
-      run_install_smoke: ${{ steps.manifest.outputs.run_install_smoke }}
+      docs_only: ${{ steps.check.outputs.docs_only }}
     steps:
       - name: Checkout
         uses: actions/checkout@v6
         with:
           fetch-depth: 1
           fetch-tags: false
-          persist-credentials: false
-          submodules: false
 
-      - name: Ensure preflight base commit
+      - name: Ensure docs-scope base commit
         uses: ./.github/actions/ensure-base-commit
         with:
           base-sha: ${{ github.event_name == 'push' && github.event.before || github.event.pull_request.base.sha }}
           fetch-ref: ${{ github.event_name == 'push' && github.ref_name || github.event.pull_request.base.ref }}
 
       - name: Detect docs-only changes
-        id: docs_scope
+        id: check
         uses: ./.github/actions/detect-docs-changes
 
+  changed-smoke:
+    needs: [docs-scope]
+    if: needs.docs-scope.outputs.docs_only != 'true'
+    runs-on: blacksmith-16vcpu-ubuntu-2404
+    outputs:
+      run_changed_smoke: ${{ steps.scope.outputs.run_changed_smoke }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+        with:
+          fetch-depth: 1
+          fetch-tags: false
+
+      - name: Ensure changed-smoke base commit
+        uses: ./.github/actions/ensure-base-commit
+        with:
+          base-sha: ${{ github.event_name == 'push' && github.event.before || github.event.pull_request.base.sha }}
+          fetch-ref: ${{ github.event_name == 'push' && github.ref_name || github.event.pull_request.base.ref }}
+
       - name: Detect changed smoke scope
-        id: changed_scope
-        if: steps.docs_scope.outputs.docs_only != 'true'
+        id: scope
         shell: bash
         run: |
           set -euo pipefail
@@ -55,32 +70,9 @@ jobs:
 
           node scripts/ci-changed-scope.mjs --base "$BASE" --head HEAD
 
-      - name: Setup Node environment
-        if: steps.docs_scope.outputs.docs_only != 'true'
-        uses: ./.github/actions/setup-node-env
-        with:
-          install-bun: "false"
-          install-deps: "false"
-          use-sticky-disk: "false"
-
-      - name: Build install-smoke CI manifest
-        id: manifest
-        env:
-          OPENCLAW_CI_DOCS_ONLY: ${{ steps.docs_scope.outputs.docs_only }}
-          OPENCLAW_CI_DOCS_CHANGED: "false"
-          OPENCLAW_CI_RUN_NODE: "false"
-          OPENCLAW_CI_RUN_MACOS: "false"
-          OPENCLAW_CI_RUN_ANDROID: "false"
-          OPENCLAW_CI_RUN_WINDOWS: "false"
-          OPENCLAW_CI_RUN_SKILLS_PYTHON: "false"
-          OPENCLAW_CI_HAS_CHANGED_EXTENSIONS: "false"
-          OPENCLAW_CI_CHANGED_EXTENSIONS_MATRIX: '{"include":[]}'
-          OPENCLAW_CI_RUN_CHANGED_SMOKE: ${{ steps.changed_scope.outputs.run_changed_smoke || 'false' }}
-        run: node scripts/ci-write-manifest-outputs.mjs --workflow install-smoke
-
   install-smoke:
-    needs: [preflight]
-    if: needs.preflight.outputs.run_install_smoke == 'true'
+    needs: [docs-scope, changed-smoke]
+    if: (github.event_name != 'pull_request' || !github.event.pull_request.draft) && needs.docs-scope.outputs.docs_only != 'true' && needs.changed-smoke.outputs.run_changed_smoke == 'true'
     runs-on: blacksmith-16vcpu-ubuntu-2404
     env:
       DOCKER_BUILD_SUMMARY: "false"

.github/workflows/labeler.yml

@@ -2,9 +2,9 @@ name: Labeler
 
 on:
   pull_request_target: # zizmor: ignore[dangerous-triggers] maintainer-owned triage workflow; no untrusted checkout or PR code execution
-    types: [opened, synchronize, reopened, edited]
+    types: [opened, synchronize, reopened]
   issues:
-    types: [opened, edited]
+    types: [opened]
   workflow_dispatch:
     inputs:
       max_prs:
@@ -209,59 +209,6 @@ jobs:
             //     labels: [trustedLabel],
             //   });
             // }
-      - name: Apply beta-blocker title label
-        uses: actions/github-script@v8
-        with:
-          github-token: ${{ steps.app-token.outputs.token || steps.app-token-fallback.outputs.token }}
-          script: |
-            const pullRequest = context.payload.pull_request;
-            if (!pullRequest) {
-              return;
-            }
-
-            const labelName = "beta-blocker";
-            const matchesBetaBlocker = /\bbeta blocker\b/i.test(pullRequest.title ?? "");
-
-            try {
-              await github.rest.issues.getLabel({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                name: labelName,
-              });
-            } catch (error) {
-              if (error?.status !== 404) {
-                throw error;
-              }
-              core.info(`Skipping ${labelName} labeling because the label does not exist in the repository.`);
-              return;
-            }
-
-            const currentLabels = await github.paginate(github.rest.issues.listLabelsOnIssue, {
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              issue_number: pullRequest.number,
-              per_page: 100,
-            });
-            const hasLabel = currentLabels.some((label) => label.name === labelName);
-
-            if (matchesBetaBlocker && !hasLabel) {
-              await github.rest.issues.addLabels({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                issue_number: pullRequest.number,
-                labels: [labelName],
-              });
-              return;
-            }
-
-            if (!matchesBetaBlocker && hasLabel) {
-              await github.rest.issues.removeLabel({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                issue_number: pullRequest.number,
-                name: labelName,
-              });
-            }
       - name: Apply too-many-prs label
         uses: actions/github-script@v8
         with:
@@ -472,7 +419,6 @@ jobs:
             const maxCount = processAll ? Number.POSITIVE_INFINITY : Math.max(1, maxPrs);
 
             const sizeLabels = ["size: XS", "size: S", "size: M", "size: L", "size: XL"];
-            const betaBlockerLabel = "beta-blocker";
             const labelColor = "b76e79";
             // const trustedLabel = "trusted-contributor";
             // const experiencedLabel = "experienced-contributor";
@@ -503,22 +449,6 @@ jobs:
               }
             }
 
-            async function hasBetaBlockerLabel() {
-              try {
-                await github.rest.issues.getLabel({
-                  owner,
-                  repo,
-                  name: betaBlockerLabel,
-                });
-                return true;
-              } catch (error) {
-                if (error?.status !== 404) {
-                  throw error;
-                }
-                return false;
-              }
-            }
-
             async function resolveContributorLabel(login) {
               if (contributorCache.has(login)) {
                 return contributorCache.get(login);
@@ -650,37 +580,7 @@ jobs:
               labelNames.add(label);
             }
 
-            async function applyBetaBlockerTitleLabel(pullRequest, labelNames) {
-              const matchesBetaBlocker = /\bbeta blocker\b/i.test(pullRequest.title ?? "");
-
-              if (matchesBetaBlocker) {
-                if (!labelNames.has(betaBlockerLabel)) {
-                  await github.rest.issues.addLabels({
-                    owner,
-                    repo,
-                    issue_number: pullRequest.number,
-                    labels: [betaBlockerLabel],
-                  });
-                  labelNames.add(betaBlockerLabel);
-                }
-                return;
-              }
-
-              if (!labelNames.has(betaBlockerLabel)) {
-                return;
-              }
-
-              await github.rest.issues.removeLabel({
-                owner,
-                repo,
-                issue_number: pullRequest.number,
-                name: betaBlockerLabel,
-              });
-              labelNames.delete(betaBlockerLabel);
-            }
-
             await ensureSizeLabels();
-            const betaBlockerLabelExists = await hasBetaBlockerLabel();
 
             let page = 1;
             let processed = 0;
@@ -718,9 +618,6 @@ jobs:
 
                 await applySizeLabel(pullRequest, currentLabels, labelNames);
                 await applyContributorLabel(pullRequest, labelNames);
-                if (betaBlockerLabelExists) {
-                  await applyBetaBlockerTitleLabel(pullRequest, labelNames);
-                }
 
                 processed += 1;
               }
@@ -822,56 +719,3 @@ jobs:
             //     labels: [trustedLabel],
             //   });
             // }
-      - name: Apply beta-blocker title label
-        uses: actions/github-script@v8
-        with:
-          github-token: ${{ steps.app-token.outputs.token || steps.app-token-fallback.outputs.token }}
-          script: |
-            const issue = context.payload.issue;
-            if (!issue || issue.pull_request) {
-              return;
-            }
-
-            const labelName = "beta-blocker";
-            const matchesBetaBlocker = /^beta blocker:/i.test(issue.title ?? "");
-
-            try {
-              await github.rest.issues.getLabel({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                name: labelName,
-              });
-            } catch (error) {
-              if (error?.status !== 404) {
-                throw error;
-              }
-              core.info(`Skipping ${labelName} labeling because the label does not exist in the repository.`);
-              return;
-            }
-
-            const currentLabels = await github.paginate(github.rest.issues.listLabelsOnIssue, {
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              issue_number: issue.number,
-              per_page: 100,
-            });
-            const hasLabel = currentLabels.some((label) => label.name === labelName);
-
-            if (matchesBetaBlocker && !hasLabel) {
-              await github.rest.issues.addLabels({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                issue_number: issue.number,
-                labels: [labelName],
-              });
-              return;
-            }
-
-            if (!matchesBetaBlocker && hasLabel) {
-              await github.rest.issues.removeLabel({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                issue_number: issue.number,
-                name: labelName,
-              });
-            }

AGENTS.md

@@ -60,8 +60,7 @@
 - Runtime baseline: Node **22+** (keep Node + Bun paths working).
 - Install deps: `pnpm install`
 - If deps are missing (for example `node_modules` missing, `vitest not found`, or `command not found`), run the repo’s package-manager install command (prefer lockfile/README-defined PM), then rerun the exact requested command once. Apply this to test/build/lint/typecheck/dev commands; if retry still fails, report the command and first actionable error.
-- Pre-commit hooks: `prek install`. The hook runs the repo verification flow, including `pnpm check`.
-- `FAST_COMMIT=1` skips the repo-wide `pnpm format` and `pnpm check` inside the pre-commit hook only. Use it when you intentionally want a faster commit path and are running equivalent targeted verification manually. It does not change CI and does not change what `pnpm check` itself does.
+- Pre-commit hooks: `prek install` (runs same checks as CI)
 - Also supported: `bun install` (keep `pnpm-lock.yaml` + Bun patching in sync when touching deps/patches).
 - Prefer Bun for TypeScript execution (scripts, dev, tests): `bun <file.ts>` / `bunx <tool>`.
 - Run CLI in dev: `pnpm openclaw ...` (bun) or `pnpm dev`.
@@ -72,28 +71,16 @@
 - Lint/format: `pnpm check`
 - Format check: `pnpm format` (oxfmt --check)
 - Format fix: `pnpm format:fix` (oxfmt --write)
-- Terminology:
-  - "gate" means a verification command or command set that must be green for the decision you are making.
-  - A local dev gate is the fast default loop, usually `pnpm check` plus any scoped test you actually need.
-  - A landing gate is the broader bar before pushing `main`, usually `pnpm check`, `pnpm test`, and `pnpm build` when the touched surface can affect build output, packaging, lazy-loading/module boundaries, or published surfaces.
-  - A CI gate is whatever the relevant workflow enforces for that lane (for example `check`, `check-additional`, `build-smoke`, or release validation).
-- Local dev gate: prefer `pnpm check` for the normal edit loop. It keeps the repo-architecture policy guards out of the default local loop.
-- CI architecture gate: `check-additional` enforces architecture and boundary policy guards that are intentionally kept out of the default local loop.
-- Formatting gate: the pre-commit hook runs `pnpm format` before `pnpm check`. If you want a formatting-only preflight locally, run `pnpm format` explicitly.
-- If you need a fast commit loop, `FAST_COMMIT=1 git commit ...` skips the hook’s repo-wide `pnpm format` and `pnpm check`; use that only when you are deliberately covering the touched surface some other way.
 - Tests: `pnpm test` (vitest); coverage: `pnpm test:coverage`
 - Generated baseline artifacts live together under `docs/.generated/`.
 - Config schema drift uses `pnpm config:docs:gen` / `pnpm config:docs:check`.
 - Plugin SDK API drift uses `pnpm plugin-sdk:api:gen` / `pnpm plugin-sdk:api:check`.
 - If you change config schema/help or the public Plugin SDK surface, update the matching baseline artifact and keep the two drift-check flows adjacent in scripts/workflows/docs guidance rather than inventing a third pattern.
 - For narrowly scoped changes, prefer narrowly scoped tests that directly validate the touched behavior. If no meaningful scoped test exists, say so explicitly and use the next most direct validation available.
-- Verification modes for work on `main`:
-  - Default mode: `main` is relatively stable. Count pre-commit hook coverage when it already verified the current tree, avoid rerunning the exact same checks just for ceremony, and prefer keeping CI/main green before landing.
-  - Fast-commit mode: `main` is moving fast and you intentionally optimize for shorter commit loops. Prefer explicit local verification close to the final landing point, and it is acceptable to use `--no-verify` for intermediate or catch-up commits after equivalent checks have already run locally.
-- Preferred landing bar for pushes to `main`: in Default mode, favor `pnpm check` and `pnpm test` near the final rebase/push point when feasible. In fast-commit mode, verify the touched surface locally near landing without insisting every intermediate commit replay the full hook.
+- Preferred landing bar for pushes to `main`: `pnpm check` and `pnpm test`, with a green result when feasible.
 - Scoped tests prove the change itself. `pnpm test` remains the default `main` landing bar; scoped tests do not replace full-suite gates by default.
 - Hard gate: if the change can affect build output, packaging, lazy-loading/module boundaries, or published surfaces, `pnpm build` MUST be run and MUST pass before pushing `main`.
-- Default rule: do not land changes with failing format, lint, type, build, or required test checks when those failures are caused by the change or plausibly related to the touched surface. Fast-commit mode changes how verification is sequenced; it does not lower the requirement to validate and clean up the touched surface before final landing.
+- Default rule: do not commit or push with failing format, lint, type, build, or required test checks when those failures are caused by the change or plausibly related to the touched surface.
 - For narrowly scoped changes, if unrelated failures already exist on latest `origin/main`, state that clearly, report the scoped tests you ran, and ask before broadening scope into unrelated fixes or landing despite those failures.
 - Do not use scoped tests as permission to ignore plausibly related failures.
 
@@ -101,8 +88,7 @@
 
 - Language: TypeScript (ESM). Prefer strict typing; avoid `any`.
 - Formatting/linting via Oxlint and Oxfmt.
-- Never add `@ts-nocheck` and do not add inline lint suppressions by default. Fix root causes first; only keep a suppression when the code is intentionally correct, the rule cannot express that safely, and the comment explains why.
-- Do not disable `no-explicit-any`; prefer real types, `unknown`, or a narrow adapter/helper instead. Update Oxlint/Oxfmt config only when required.
+- 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.
 - Extension SDK self-import guardrail: inside an extension package, do not import that same extension via `openclaw/plugin-sdk/<extension>` from production files. Route internal imports through a local barrel such as `./api.ts` or `./runtime-api.ts`, and keep the `plugin-sdk/<extension>` path as the external contract only.
@@ -133,8 +119,8 @@
 - Agents MUST NOT modify baseline, inventory, ignore, snapshot, or expected-failure files to silence failing checks without explicit approval in this chat.
 - For targeted/local debugging, keep using the wrapper: `pnpm test -- <path-or-filter> [vitest args...]` (for example `pnpm test -- src/commands/onboard-search.test.ts -t "shows registered plugin providers"`); do not default to raw `pnpm vitest run ...` because it bypasses wrapper config/profile/pool routing.
 - Do not set test workers above 16; tried already.
-- Keep Vitest on `forks` only. Do not introduce or reintroduce any non-`forks` Vitest pool or alternate execution mode in configs, wrapper scripts, or default test commands without explicit approval in this chat. This includes `threads`, `vmThreads`, `vmForks`, and any future/nonstandard pool variant.
-- If local Vitest runs cause memory pressure, the wrapper now derives budgets from host capabilities (CPU, memory band, current load). For a conservative explicit override during land/gate runs, use `OPENCLAW_TEST_PROFILE=serial OPENCLAW_TEST_SERIAL_GATEWAY=1 pnpm test`.
+- Do not reintroduce Vitest VM pools by default without fresh green evidence on current `main`; keep CI on `forks`.
+- If local Vitest runs cause memory pressure (common on non-Mac-Studio hosts), use `OPENCLAW_TEST_PROFILE=low OPENCLAW_TEST_SERIAL_GATEWAY=1 pnpm test` for land/gate runs.
 - Live tests (real keys): `OPENCLAW_LIVE_TEST=1 pnpm test:live` (OpenClaw-only) or `LIVE=1 pnpm test:live` (includes provider live tests). Docker: `pnpm test:docker:live-models`, `pnpm test:docker:live-gateway`. Onboarding Docker E2E: `pnpm test:docker:onboard`.
 - Full kit + what’s covered: `docs/help/testing.md`.
 - Changelog: user-facing changes only; no internal/meta notes (version alignment, appcast reminders, release process).

CHANGELOG.md

@@ -6,150 +6,10 @@ Docs: https://docs.openclaw.ai
 
 ### Breaking
 
-- Providers/Qwen: remove the deprecated `qwen-portal-auth` OAuth integration for `portal.qwen.ai`; migrate to Model Studio with `openclaw onboard --auth-choice modelstudio-api-key`. (#52709) Thanks @pomelo-nwu.
-- Config/Doctor: drop automatic config migrations older than two months; very old legacy keys now fail validation instead of being rewritten on load or by `openclaw doctor`.
-
-### Changes
-
-- MiniMax: add image generation provider for `image-01` model, supporting generate and image-to-image editing with aspect ratio control. (#54487) Thanks @liyuan97.
-- Podman: simplify the container setup around the current rootless user, install the launch helper under `~/.local/bin`, and document the host-CLI `openclaw --container <name> ...` workflow instead of a dedicated `openclaw` service user.
-- Slack/tool actions: add an explicit `upload-file` Slack action that routes file uploads through the existing Slack upload transport, with optional filename/title/comment overrides for channels and DMs.
-- Message actions/files: start unifying file-first sends on the canonical `upload-file` action by adding explicit support for Microsoft Teams and Google Chat, and by exposing BlueBubbles file sends through `upload-file` while keeping the legacy `sendAttachment` alias.
-- Plugins/Matrix TTS: send auto-TTS replies as native Matrix voice bubbles instead of generic audio attachments. (#37080) thanks @Matthew19990919.
-- Memory/plugins: move the pre-compaction memory flush plan behind the active memory plugin contract so `memory-core` owns flush prompts and target-path policy instead of hardcoded core logic.
-- MiniMax: trim model catalog to M2.7 only, removing legacy M2, M2.1, M2.5, and VL-01 models. (#54487) Thanks @liyuan97.
-- CLI: add `openclaw config schema` to print the generated JSON schema for `openclaw.json`. (#54523) Thanks @kvokka.
-- Plugins/runtime: expose `runHeartbeatOnce` in the plugin runtime `system` namespace so plugins can trigger a single heartbeat cycle with an explicit delivery target override (e.g. `heartbeat: { target: "last" }`). (#40299) Thanks @loveyana.
-- Agents/compaction: preserve the post-compaction AGENTS refresh on stale-usage preflight compaction for both immediate replies and queued followups. (#49479) Thanks @jared596.
-- Agents/compaction: surface safeguard-specific cancel reasons and relabel benign manual `/compact` no-op cases as skipped instead of failed. (#51072) Thanks @afurm.
-- Plugins/CLI backends: move bundled Claude CLI, Codex CLI, and Gemini CLI inference defaults onto the plugin surface, add bundled Gemini CLI backend support, and replace `gateway run --claude-cli-logs` with generic `--cli-backend-logs` while keeping the old flag as a compatibility alias.
-- Plugins/startup: auto-load bundled provider and CLI-backend plugins from explicit config refs, so bundled Claude CLI, Codex CLI, and Gemini CLI message-provider setups no longer need manual `plugins.allow` entries.
-- Config/TTS: auto-migrate legacy speech config on normal reads and secret resolution, keep legacy diagnostics for Doctor, and remove regular-mode runtime fallback for old bundled `tts.<provider>` API-key shapes.
-- OpenAI/apply_patch: enable `apply_patch` by default for OpenAI and OpenAI Codex models, and align its sandbox policy access with `write` permissions.
-- Docs: add `pnpm docs:check-links:anchors` for Mintlify anchor validation while keeping `scripts/docs-link-audit.mjs` as the stable link-audit entrypoint. (#55912) Thanks @velvet-shark.
-- Plugins/hooks: add async `requireApproval` to `before_tool_call` hooks, letting plugins pause tool execution and prompt the user for approval via the exec approval overlay, Telegram buttons, Discord interactions, or the `/approve` command on any channel. The `/approve` command now handles both exec and plugin approvals with automatic fallback. (#55339) Thanks @vaclavbelak and @joshavant.
-
-### Fixes
-
-- ACP/ACPX agent registry: align OpenClaw's ACPX built-in agent mirror with the latest `openclaw/acpx` command defaults and built-in aliases, pin versioned `npx` built-ins to exact versions, and stop unknown ACP agent ids from falling through to raw `--agent` command execution on the MCP-proxy path. (#28321) Thanks @m0nkmaster and @vincentkoc.
-- Control UI/config: keep sensitive raw config hidden by default, replace the blank blocked editor with an explicit reveal-to-edit state, and restore raw JSON editing without auto-exposing secrets. Fixes #55322.
-- WhatsApp: fix infinite echo loop in self-chat DM mode where the bot's own outbound replies were re-processed as new inbound user messages. (#54570) Thanks @joelnishanth
-- OpenAI Codex/image tools: register Codex for media understanding and route image prompts through Codex instructions so image analysis no longer fails on missing provider registration or missing `instructions`. (#54829) Thanks @neeravmakwana.
-- Agents/image tool: restore the generic image-runtime fallback when no provider-specific media-understanding provider is registered, so image analysis works again for providers like `openrouter` and `minimax-portal`. (#54858) Thanks @MonkeyLeeT.
-- Telegram: deliver verbose tool summaries inside forum topic sessions again, so threaded topic chats now match DM verbose behavior. (#43236) Thanks @frankbuild.
-- BlueBubbles/CLI agents: restore inbound prompt image refs for CLI routed turns, reapply embedded runner image size guardrails, and cover both CLI image transport paths with regression tests. (#51373)
-- BlueBubbles/groups: optionally enrich unnamed participant lists with local macOS Contacts names after group gating passes, so group member context can show names instead of only raw phone numbers.
-- Discord/reconnect: drain stale gateway sockets, clear cached resume state before forced fresh reconnects, and fail closed when old sockets refuse to die so Discord recovery stops looping on poisoned resume state. (#54697) Thanks @ngutman.
-- iMessage: stop leaking inline `[[reply_to:...]]` tags into delivered text by sending `reply_to` as RPC metadata and stripping stray directive tags from outbound messages. (#39512) Thanks @mvanhorn.
-- CLI/plugins: make routed commands use the same auto-enabled bundled-channel snapshot as gateway startup, so configured bundled channels like Slack load without requiring a prior config rewrite. (#54809) Thanks @neeravmakwana.
-- CLI/message send: write manual `openclaw message send` deliveries into the resolved agent session transcript again by always threading the default CLI agent through outbound mirroring. (#54187) Thanks @KevInTheCloud5617.
-- CLI/onboarding: show the Kimi Code API key option again in the Moonshot setup menu so the interactive picker includes all Kimi setup paths together. Fixes #54412 Thanks @sparkyrider
-- Agents/status: use provider-aware context window lookup for fresh Anthropic 4.6 model overrides so `/status` shows the correct 1.0m window instead of an underreported shared-cache minimum. (#54796) Thanks @neeravmakwana.
-- OpenAI/WebSocket: preserve reasoning replay metadata and tool-call item ids on WebSocket tool turns, and start a fresh response chain when full-context resend is required. (#53856) Thanks @xujingchen1996.
-- OpenAI/WS: restore reasoning blocks for Responses WebSocket runs and keep reasoning/tool-call replay metadata intact so resumed sessions do not lose or break follow-up reasoning-capable turns. (#53856) Thanks @xujingchen1996.
-- Agents/errors: surface provider quota/reset details when available, but keep HTML/Cloudflare rate-limit pages on the generic fallback so raw error pages are not shown to users. (#54512) Thanks @bugkill3r.
-- Claude CLI: switch the bundled Claude CLI backend to `stream-json` output so watchdogs see progress on long runs, and keep session/usage metadata even when Claude finishes with an empty result line. (#49698) Thanks @felear2022.
-- Claude CLI/MCP: always pass a strict generated `--mcp-config` overlay for background Claude CLI runs, including the empty-server case, so Claude does not inherit ambient user/global MCP servers. (#54961) Thanks @markojak.
-- Agents/embedded replies: surface mid-turn 429 and overload failures when embedded runs end without a user-visible reply, while preserving successful media-only replies that still use legacy `mediaUrl`. (#50930) Thanks @infichen.
-- Chat/UI: move the chat send button onto the shared ghost-button theme styling, while keeping the stop button icon readable on the danger state. (#55075) Thanks @bottenbenny.
-- WhatsApp/allowFrom: show a specific allowFrom policy error for valid blocked targets instead of the misleading `<E.164|group JID>` format hint. Thanks @mcaxtr.
-- Agents/cooldowns: scope rate-limit cooldowns per model so one 429 no longer blocks every model on the same auth profile, replace the exponential 1 min -> 1 h escalation with a stepped 30 s / 1 min / 5 min ladder, and surface a user-facing countdown message when all models are rate-limited. (#49834) Thanks @kiranvk-2011.
-- Agents/embedded transport errors: distinguish common network failures like connection refused, DNS lookup failure, and interrupted sockets from true timeouts in embedded-run user messaging and lifecycle diagnostics. (#51419) Thanks @scoootscooob.
-- Telegram/pairing: ignore self-authored DM `message` updates so bot-pinned status cards and similar service updates do not trigger bogus pairing requests or re-enter inbound dispatch. (#54530) thanks @huntharo
-- Mattermost/replies: keep pairing replies, slash-command fallback replies, and model-picker messages on the resolved config path so `exec:` SecretRef bot tokens work across all outbound reply branches. (#48347) thanks @mathiasnagler.
-- Microsoft Teams/config: accept the existing `welcomeCard`, `groupWelcomeCard`, `promptStarters`, and feedback/reflection keys in strict config validation so already-supported Teams runtime settings stop failing schema checks. (#54679) Thanks @gumclaw.
-- Plugins/SDK: thread `moduleUrl` through plugin-sdk alias resolution so user-installed plugins outside the openclaw directory (e.g. `~/.openclaw/extensions/`) correctly resolve `openclaw/plugin-sdk/*` subpath imports, and gate `plugin-sdk:check-exports` in `release:check`. (#54283) Thanks @xieyongliang.
-- Config/web fetch: allow the documented `tools.web.fetch.maxResponseBytes` setting in runtime schema validation so valid configs no longer fail with unrecognized-key errors. (#53401) Thanks @erhhung.
-- Message tool/buttons: keep the shared `buttons` schema optional in merged tool definitions so plain `action=send` calls stop failing validation when no buttons are provided. (#54418) Thanks @adzendo.
-- Agents/openai-compatible tool calls: deduplicate repeated tool call ids across live assistant messages and replayed history so OpenAI-compatible backends no longer reject duplicate `tool_call_id` values with HTTP 400. (#40996) Thanks @xaeon2026.
-- Models/openai-completions: default non-native OpenAI-compatible providers to omit tool-definition `strict` fields unless users explicitly opt back in, so tool calling keeps working on providers that reject that option. (#45497) Thanks @sahancava.
-- Plugins/context engines: retry strict legacy `assemble()` calls without the new `prompt` field when older engines reject it, preserving prompt-aware retrieval compatibility for pre-prompt plugins. (#50848) thanks @danhdoan.
-- CLI/update status: explicitly say `up to date` when the local version already matches npm latest, while keeping the availability logic unchanged. (#51409) Thanks @dongzhenye.
-- Daemon/Linux: stop flagging non-gateway systemd services as duplicate gateways just because their unit files mention OpenClaw, reducing false-positive doctor/log noise. (#45328) Thanks @gregretkowski.
-- Feishu: close WebSocket connections on monitor stop/abort so ghost connections no longer persist, preventing duplicate event processing and resource leaks across restart cycles. (#52844) Thanks @schumilin.
-- Feishu: use the original message `create_time` instead of `Date.now()` for inbound timestamps so offline-retried messages carry the correct authoring time, preventing mis-targeted agent actions on stale instructions. (#52809) Thanks @schumilin.
-- Agents/sandbox: honor `tools.sandbox.tools.alsoAllow`, let explicit sandbox re-allows remove matching built-in default-deny tools, and keep sandbox explain/error guidance aligned with the effective sandbox tool policy. (#54492) Thanks @ngutman.
-- Agents/sandbox: make blocked-tool guidance glob-aware again, redact/sanitize session-specific explain hints for safer copy-paste, and avoid leaking control-character session keys in those hints. (#54684) Thanks @ngutman.
-- Agents/compaction: trigger timeout recovery compaction before retrying high-context LLM timeouts so embedded runs stop repeating oversized requests. (#46417) thanks @joeykrug.
-- Agents/compaction: reconcile `sessions.json.compactionCount` after a late embedded auto-compaction success so persisted session counts catch up once the handler reports completion. (#45493) Thanks @jackal092927.
-- Agents/failover: classify Codex accountId token extraction failures as auth errors so model fallback continues to the next configured candidate. (#55206) Thanks @cosmicnet.
-- Talk/macOS: stop direct system-voice failures from replaying system speech, use app-locale fallback for shared watchdog timing, and add regression coverage for the macOS fallback route and language-aware timeout policy. (#53511) thanks @hongsw.
-- Discord/gateway cleanup: keep late Carbon reconnect-exhausted errors suppressed through startup/dispose cleanup so Discord monitor shutdown no longer crashes on late gateway close events. (#55373) Thanks @Takhoffman.
-- Discord/gateway shutdown: treat expected reconnect-exhausted events during intentional lifecycle stop as clean shutdowns so startup-abort cleanup no longer surfaces false gateway failures. (#55324) Thanks @joelnishanth.
-- Discord/gateway shutdown: suppress reconnect-exhausted events that were already buffered before teardown flips `lifecycleStopping`, so stale-socket Discord restarts no longer crash the whole gateway. Fixes #55403 and #55421. Thanks @lml2468 and @vincentkoc.
-- GitHub Copilot/auth refresh: treat large `expires_at` values as seconds epochs and clamp far-future runtime auth refresh timers so Copilot token refresh cannot fall into a `setTimeout` overflow hot loop. (#55360) Thanks @michael-abdo.
-- Agents/status: use the persisted runtime session model in `session_status` when no explicit override exists, and honor per-agent `thinkingDefault` in both `session_status` and `/status`. (#55425) Thanks @scoootscooob, @xaeon2026, and @ysfbsf.
-- Heartbeat/runner: guarantee the interval timer is re-armed after heartbeat runs and unexpected runner errors so scheduled heartbeats do not silently stop after an interrupted cycle. (#52270) Thanks @MiloStack.
-- Config/Doctor: rewrite stale bundled plugin load paths from legacy `extensions/*` locations to the packaged bundled path, including directory-name mismatches and slash-suffixed config entries. (#55054) Thanks @SnowSky1.
-- WhatsApp/mentions: stop treating mentions embedded in quoted messages as direct mentions so replying to a message that @mentioned the bot no longer falsely triggers mention gating. (#52711) Thanks @lurebat.
-- Agents/ollama fallback: surface non-2xx Ollama HTTP errors with a leading status code so HTTP 503 responses trigger model fallback again. (#55214) Thanks @bugkill3r.
-- Feishu/tools: stop synthetic agent ids like `agent-spawner` from being treated as Feishu account ids during tool execution, so tools fall back to the configured/default Feishu account unless the contextual id is a real enabled Feishu account. (#55627) Thanks @MonkeyLeeT.
-- Google/tools: strip empty `required: []` arrays from Gemini tool schemas so optional-only tool parameters no longer trigger Google validator 400s. (#52106) Thanks @oliviareid-svg.
-- Onboarding/TUI/local gateways: show the resolved gateway port in setup output, clarify no-daemon local health/dashboard messaging, and preserve loopback Control UI auth on reruns and explicit local gateway URLs so local quickstart flows recover cleanly. (#55730) Thanks @shakkernerd.
-- TUI/chat log: keep system messages as single logical entries and prune overflow at whole-message boundaries so wrapped system spacing stays intact. (#55732) Thanks @shakkernerd.
-- TUI/activation: validate `/activation` arguments in the TUI and reject invalid values instead of silently coercing them to `mention`. (#55733) Thanks @shakkernerd.
-- Agents/model switching: apply `/model` changes to active embedded runs at the next safe retry boundary, so overloaded or retrying turns switch to the newly selected model instead of staying pinned to the old provider.
-- Agents/Codex fallback: classify Codex `server_error` payloads as failoverable, sanitize `Codex error:` payloads before they reach chat, preserve context-overflow guidance for prefixed `invalid_request_error` payloads, and omit provider `request_id` values from user-facing UI copy. (#42892) Thanks @xaeon2026.
-- Memory/search: share memory embedding provider registrations across split plugin runtimes so memory search no longer fails with unknown provider errors after memory-core registers built-in adapters. (#55945) Thanks @glitch418x.
-- Discord/Carbon beta: update `@buape/carbon` to the latest beta and pass the new `RateLimitError` request argument so Discord stays compatible with the upstream beta constructor change. (#55980) Thanks @ngutman.
-- Plugins/inbound claims: pass full inbound attachment arrays through `inbound_claim` hook metadata while keeping the legacy singular media attachment fields for compatibility. (#55452) Thanks @huntharo.
-
-## 2026.3.24
-
-### Breaking
-
-### Changes
-
-- Gateway/OpenAI compatibility: add `/v1/models` and `/v1/embeddings`, and forward explicit model overrides through `/v1/chat/completions` and `/v1/responses` for broader client and RAG compatibility. Thanks @vincentkoc.
-- Agents/tools: make `/tools` show the tools the current agent can actually use right now, add a compact default view with an optional detailed mode, and add a live "Available Right Now" section in the Control UI so it is easier to see what will work before you ask.
-- Microsoft Teams: migrate to the official Teams SDK and add AI-agent UX best practices including streaming 1:1 replies, welcome cards with prompt starters, feedback/reflection, informative status updates, typing indicators, and native AI labeling. (#51808)
-- Microsoft Teams: add message edit and delete support for sent messages, including in-thread fallbacks when no explicit target is provided. (#49925)
-- Skills/install metadata: add one-click install recipes to bundled skills (coding-agent, gh-issues, openai-whisper-api, session-logs, tmux, trello, weather) so the CLI and Control UI can offer dependency installation when requirements are missing. (#53411) Thanks @BunsDev.
-- Control UI/skills: add status-filter tabs (All / Ready / Needs Setup / Disabled) with counts, replace inline skill cards with a click-to-detail dialog showing requirements, toggle switch, install action, API key entry, source metadata, and homepage link. (#53411) Thanks @BunsDev.
-- Slack/interactive replies: restore rich reply parity for direct deliveries, auto-render simple trailing `Options:` lines as buttons/selects, improve Slack interactive setup defaults, and isolate reply controls from plugin interactive handlers. (#53389) Thanks @vincentkoc.
-- CLI/containers: add `--container` and `OPENCLAW_CONTAINER` to run `openclaw` commands inside a running Docker or Podman OpenClaw container. (#52651) Thanks @sallyom.
-- Discord/auto threads: add optional `autoThreadName: "generated"` naming so new auto-created threads can be renamed asynchronously with concise LLM-generated titles while keeping the existing message-based naming as the default. (#43366) Thanks @davidguttman.
-- Plugins/hooks: add `before_dispatch` with canonical inbound metadata and route handled replies through the normal final-delivery path, preserving TTS and routed delivery semantics. (#50444) Thanks @gfzhx.
-- Control UI/agents: convert agent workspace file rows to expandable `<details>` with lazy-loaded inline markdown preview, and add comprehensive `.sidebar-markdown` styles for headings, lists, code blocks, tables, blockquotes, and details/summary elements. (#53411) Thanks @BunsDev.
-- Control UI/markdown preview: restyle the agent workspace file preview dialog with a frosted backdrop, sized panel, and styled header, and integrate `@create-markdown/preview` v2 system theme for rich markdown rendering (headings, tables, code blocks, callouts, blockquotes) that auto-adapts to the app's light/dark design tokens. (#53411) Thanks @BunsDev.
-- macOS app/config: replace horizontal pill-based subsection navigation with a collapsible tree sidebar using disclosure chevrons and indented subsection rows. (#53411) Thanks @BunsDev.
-- CLI/skills: soften missing-requirements label from "missing" to "needs setup" and surface API key setup guidance (where to get a key, CLI save command, storage path) in `openclaw skills info` output. (#53411) Thanks @BunsDev.
-- macOS app/skills: add "Get your key" homepage link and storage-path hint to the API key editor dialog, and show the config path in save confirmation messages. (#53411) Thanks @BunsDev.
-- Control UI/agents: add a "Not set" placeholder to the default agent model selector dropdown. (#53411) Thanks @BunsDev.
-- Runtime/install: lower the supported Node 22 floor to `22.14+` while continuing to recommend Node 24, so npm installs and self-updates do not strand Node 22.14 users on older releases.
-- CLI/update: preflight the target npm package `engines.node` before `openclaw update` runs a global package install, so outdated Node runtimes fail with a clear upgrade message instead of attempting an unsupported latest release.
-
-### Fixes
-
-- Outbound media/local files: align outbound media access with the configured fs policy so host-local files and inbound-media paths keep sending when `workspaceOnly` is off, while strict workspace-only agents remain sandboxed.
-- Security/sandbox media dispatch: close the `mediaUrl`/`fileUrl` alias bypass so outbound tool and message actions cannot escape media-root restrictions. (#54034)
-- Gateway/restart sentinel: wake the interrupted agent session via heartbeat after restart instead of only sending a best-effort restart note, retry outbound delivery once on transient failure, and preserve explicit thread/topic routing through the wake path so replies land in the correct Telegram topic or Slack thread. (#53940) Thanks @VACInc.
-- Docker/setup: avoid the pre-start `openclaw-cli` shared-network namespace loop by routing setup-time onboard/config writes through `openclaw-gateway`, so fresh Docker installs stop failing before the gateway comes up. (#53385) Thanks @amsminn.
-- Gateway/channels: keep channel startup sequential while isolating per-channel boot failures, so one broken channel no longer blocks later channels from starting. (#54215) Thanks @JonathanJing.
-- Embedded runs/secrets: stop unresolved `SecretRef` config from crashing embedded agent runs by falling back to the resolved runtime snapshot when needed. Fixes #45838.
-- WhatsApp/groups: track recent gateway-sent message IDs and suppress only matching group echoes, preserving owner `/status`, `/new`, and `/activation` commands from linked-account `fromMe` traffic. (#53624) Thanks @w-sss.
-- WhatsApp/reply-to-bot detection: restore implicit group reply detection by unwrapping `botInvokeMessage` payloads and reading `selfLid` from `creds.json`, so reply-based mentions reach the bot again in linked-account group chats.
-- Telegram/forum topics: recover `#General` topic `1` routing when Telegram omits forum metadata, including native commands, interactive callbacks, inbound message context, and fallback error replies. (#53699) thanks @huntharo
-- Discord/gateway supervision: centralize gateway error handling behind a lifetime-owned supervisor so early, active, and late-teardown Carbon gateway errors stay classified consistently and stop surfacing as process-killing teardown crashes.
-- Discord/timeouts: send a visible timeout reply when the inbound Discord worker times out before a final reply starts, including created auto-thread targets and queued-run ordering. (#53823) Thanks @Kimbo7870.
-- ACP/direct chats: always deliver a terminal ACP result when final TTS does not yield audio, even if block text already streamed earlier, and skip redundant empty-text final synthesis. (#53692) Thanks @w-sss.
-- Telegram/outbound errors: preserve actionable 403 membership/block/kick details and treat `bot not a member` as a permanent delivery failure so Telegram sends stop retrying doomed chats. (#53635) Thanks @w-sss.
-- Telegram/photos: preflight Telegram photo dimension and aspect-ratio rules, and fall back to document sends when image metadata is invalid or unavailable so photo uploads stop failing with `PHOTO_INVALID_DIMENSIONS`. (#52545) Thanks @hnshah.
-- Slack/runtime defaults: trim Slack DM reply overhead, restore Codex auto transport, and tighten Slack/web-search runtime defaults around DM preview threading, cache scoping, warning dedupe, and explicit web-search opt-in. (#53957) Thanks @vincentkoc.
-
-## 2026.3.24-beta.2
-
-### Breaking
-
 ### Changes
 
 ### Fixes
 
-- Outbound media/local files: align outbound media access with the configured fs policy so host-local files and inbound-media paths keep sending when `workspaceOnly` is off, while strict workspace-only agents remain sandboxed.
-- Runtime/install: lower the supported Node 22 floor to `22.14+` while continuing to recommend Node 24, so npm installs and self-updates do not strand Node 22.14 users on older releases.
-- CLI/update: preflight the target npm package `engines.node` before `openclaw update` runs a global package install, so outdated Node runtimes fail with a clear upgrade message instead of attempting an unsupported latest release.
-- Tests/security audit: isolate audit-test home and personal skill resolution so local `~/.agents/skills` installs no longer make maintainer prep runs fail nondeterministically. (#54473) thanks @huntharo
-
 ## 2026.3.24-beta.1
 
 ### Breaking
@@ -214,8 +74,6 @@ Docs: https://docs.openclaw.ai
 - Marketplace/agents: correct the ClawHub skill URL in agent docs and stream marketplace archive downloads to disk so installs avoid excess memory use and fail cleanly on empty responses. (#54160) Thanks @QuinnH496.
 - Discord/config types: add missing `autoArchiveDuration` to `DiscordGuildChannelConfig` so TypeScript config definitions match the existing schema and runtime support. (#43427) Thanks @davidguttman.
 - Docs/IRC: fix five `json55` code-fence typos in the IRC channel examples so Mintlify applies JSON5 syntax highlighting correctly. (#50842) Thanks @Hollychou924.
-- Discord/commands: trim overlong slash-command descriptions to Discord's 100-character limit and map rejected deploy indexes from Discord validation payloads back to command names/descriptions, so deploys stop failing on long descriptions and startup logs identify the rejected commands. (#54118) thanks @huntharo
-- Media/store: enforce the intended media file mode after writes and redirect downloads so restrictive umasks do not silently narrow saved media permissions.
 
 ## 2026.3.23
 
@@ -465,16 +323,6 @@ Docs: https://docs.openclaw.ai
 - Security/network: harden explicit-proxy SSRF pinning by translating target-hop transport hints onto HTTPS proxy tunnels and failing closed for plain HTTP guarded fetches that cannot preserve pinned DNS.
 - Security/Synology Chat: require explicit per-account webhook paths for multi-account setups by default, reject duplicate exact webhook paths fail-closed, and keep inherited-path behavior behind an explicit dangerous opt-in so shared routes can no longer collapse DM policy contexts across accounts. Thanks @tdjackey for reporting.
 - Browser/remote CDP: honor strict browser SSRF policy during remote CDP reachability and `/json/version` discovery checks, redact sensitive `cdpUrl` tokens from status output, and warn when remote CDP targets private/internal hosts.
-- Telegram/replies: set `allow_sending_without_reply` on reply-targeted sends and media-error notices so deleted parent messages no longer drop otherwise valid replies. (#52524) Thanks @moltbot886.
-- Gateway/status: resolve env-backed `gateway.auth.*` SecretRefs before read-only probe auth checks so status no longer reports false probe failures when auth is configured through SecretRef. (#52513) Thanks @CodeForgeNet.
-- Agents/exec: return plain-text failed tool output for timeouts and other non-success exec outcomes so models no longer parrot raw JSON error payloads back to users. (#52508) Thanks @martingarramon.
-- CLI/startup: lazy-load channel add and root help startup paths to trim avoidable RSS and help latency on constrained hosts. (#46784) Thanks @vincentkoc.
-- CLI/onboarding: import static provider definitions directly for onboarding model/config helpers so those paths no longer pull provider discovery just for built-in defaults. (#47467) Thanks @vincentkoc.
-- CLI/configure: clarify fresh-setup memory-search warnings so they say semantic recall needs at least one embedding provider, and scope the initial model allowlist picker to the provider selected in configure. Thanks @vincentkoc.
-- CLI/auth choice: lazy-load plugin/provider fallback resolution so mapped auth choices stay on the static path and only unknown choices pay the heavy provider load. (#47495) Thanks @vincentkoc.
-- CLI: avoid loading provider discovery during startup model normalization. (#46522) Thanks @ItsAditya-xyz and @vincentkoc.
-- CLI/status: keep `status --json` stdout clean by skipping plugin compatibility scans that were not rendered in the JSON payload. (#52449) Thanks @cgdusek.
-- Agents/Telegram: avoid rebuilding the full model catalog on ordinary inbound replies so Telegram message handling no longer pays multi-second core startup latency before reply generation. Thanks @vincentkoc.
 - Media/security: bound remote-media error-body snippets with the same streaming caps and idle timeouts as successful downloads, so malicious HTTP error responses cannot force unbounded buffering before OpenClaw throws.
 - Gateway/auth: ignore spoofed loopback hops in trusted forwarding chains and block device approvals that request scopes above the caller session. (#46800) Thanks @vincentkoc.
 - Gateway/auth: clear self-declared scopes for device-less trusted-proxy Control UI sessions so proxy-authenticated connects cannot claim admin or secrets scopes without a bound device identity.

CONTRIBUTING.md

@@ -94,7 +94,6 @@ Welcome to the lobster tank! 🦞
   - `pnpm test:extension --list` to see valid extension ids
   - If you changed shared plugin or channel surfaces, run `pnpm test:contracts`
   - For targeted shared-surface work, use `pnpm test:contracts:channels` or `pnpm test:contracts:plugins`
-  - These commands also cover the shared seam/smoke files that the default unit lane skips
   - If you changed broader runtime behavior, still run the relevant wider lanes (`pnpm test:extensions`, `pnpm test:channels`, or `pnpm test`) before asking for review
 - If you have access to Codex, run `codex review --base origin/main` locally before opening or updating your PR. Treat this as the current highest standard of AI review, even if GitHub Codex review also runs.
 - Do not submit refactor-only PRs unless a maintainer explicitly requested that refactor for an active fix or deliverable.

README.md

@@ -19,7 +19,7 @@
 </p>
 
 **OpenClaw** is a _personal AI assistant_ you run on your own devices.
-It answers you on the channels you already use (WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, BlueBubbles, IRC, Microsoft Teams, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch, Zalo, Zalo Personal, WeChat, WebChat). It can speak and listen on macOS/iOS/Android, and can render a live Canvas you control. The Gateway is just the control plane — the product is the assistant.
+It answers you on the channels you already use (WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, BlueBubbles, IRC, Microsoft Teams, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch, Zalo, Zalo Personal, WebChat). It can speak and listen on macOS/iOS/Android, and can render a live Canvas you control. The Gateway is just the control plane — the product is the assistant.
 
 If you want a personal, single-user assistant that feels local, fast, and always-on, this is it.
 
@@ -74,7 +74,7 @@ openclaw gateway --port 18789 --verbose
 # Send a message
 openclaw message send --to +1234567890 --message "Hello from OpenClaw"
 
-# Talk to the assistant (optionally deliver back to any connected channel: WhatsApp/Telegram/Slack/Discord/Google Chat/Signal/iMessage/BlueBubbles/IRC/Microsoft Teams/Matrix/Feishu/LINE/Mattermost/Nextcloud Talk/Nostr/Synology Chat/Tlon/Twitch/Zalo/Zalo Personal/WeChat/WebChat)
+# Talk to the assistant (optionally deliver back to any connected channel: WhatsApp/Telegram/Slack/Discord/Google Chat/Signal/iMessage/BlueBubbles/IRC/Microsoft Teams/Matrix/Feishu/LINE/Mattermost/Nextcloud Talk/Nostr/Synology Chat/Tlon/Twitch/Zalo/Zalo Personal/WebChat)
 openclaw agent --message "Ship checklist" --thinking high
 ```
 
@@ -126,7 +126,7 @@ Run `openclaw doctor` to surface risky/misconfigured DM policies.
 ## Highlights
 
 - **[Local-first Gateway](https://docs.openclaw.ai/gateway)** — single control plane for sessions, channels, tools, and events.
-- **[Multi-channel inbox](https://docs.openclaw.ai/channels)** — WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, BlueBubbles (iMessage), iMessage (legacy), IRC, Microsoft Teams, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch, Zalo, Zalo Personal, WeChat, WebChat, macOS, iOS/Android.
+- **[Multi-channel inbox](https://docs.openclaw.ai/channels)** — WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, BlueBubbles (iMessage), iMessage (legacy), IRC, Microsoft Teams, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch, Zalo, Zalo Personal, WebChat, macOS, iOS/Android.
 - **[Multi-agent routing](https://docs.openclaw.ai/gateway/configuration)** — route inbound channels/accounts/peers to isolated agents (workspaces + per-agent sessions).
 - **[Voice Wake](https://docs.openclaw.ai/nodes/voicewake) + [Talk Mode](https://docs.openclaw.ai/nodes/talk)** — wake words on macOS/iOS and continuous voice on Android (ElevenLabs + system TTS fallback).
 - **[Live Canvas](https://docs.openclaw.ai/platforms/mac/canvas)** — agent-driven visual workspace with [A2UI](https://docs.openclaw.ai/platforms/mac/canvas#canvas-a2ui).
@@ -150,7 +150,7 @@ Run `openclaw doctor` to surface risky/misconfigured DM policies.
 
 ### Channels
 
-- [Channels](https://docs.openclaw.ai/channels): [WhatsApp](https://docs.openclaw.ai/channels/whatsapp) (Baileys), [Telegram](https://docs.openclaw.ai/channels/telegram) (grammY), [Slack](https://docs.openclaw.ai/channels/slack) (Bolt), [Discord](https://docs.openclaw.ai/channels/discord) (discord.js), [Google Chat](https://docs.openclaw.ai/channels/googlechat) (Chat API), [Signal](https://docs.openclaw.ai/channels/signal) (signal-cli), [BlueBubbles](https://docs.openclaw.ai/channels/bluebubbles) (iMessage, recommended), [iMessage](https://docs.openclaw.ai/channels/imessage) (legacy imsg), [IRC](https://docs.openclaw.ai/channels/irc), [Microsoft Teams](https://docs.openclaw.ai/channels/msteams), [Matrix](https://docs.openclaw.ai/channels/matrix), [Feishu](https://docs.openclaw.ai/channels/feishu), [LINE](https://docs.openclaw.ai/channels/line), [Mattermost](https://docs.openclaw.ai/channels/mattermost), [Nextcloud Talk](https://docs.openclaw.ai/channels/nextcloud-talk), [Nostr](https://docs.openclaw.ai/channels/nostr), [Synology Chat](https://docs.openclaw.ai/channels/synology-chat), [Tlon](https://docs.openclaw.ai/channels/tlon), [Twitch](https://docs.openclaw.ai/channels/twitch), [Zalo](https://docs.openclaw.ai/channels/zalo), [Zalo Personal](https://docs.openclaw.ai/channels/zalouser), WeChat (`@tencent-weixin/openclaw-weixin`), [WebChat](https://docs.openclaw.ai/web/webchat).
+- [Channels](https://docs.openclaw.ai/channels): [WhatsApp](https://docs.openclaw.ai/channels/whatsapp) (Baileys), [Telegram](https://docs.openclaw.ai/channels/telegram) (grammY), [Slack](https://docs.openclaw.ai/channels/slack) (Bolt), [Discord](https://docs.openclaw.ai/channels/discord) (discord.js), [Google Chat](https://docs.openclaw.ai/channels/googlechat) (Chat API), [Signal](https://docs.openclaw.ai/channels/signal) (signal-cli), [BlueBubbles](https://docs.openclaw.ai/channels/bluebubbles) (iMessage, recommended), [iMessage](https://docs.openclaw.ai/channels/imessage) (legacy imsg), [IRC](https://docs.openclaw.ai/channels/irc), [Microsoft Teams](https://docs.openclaw.ai/channels/msteams), [Matrix](https://docs.openclaw.ai/channels/matrix), [Feishu](https://docs.openclaw.ai/channels/feishu), [LINE](https://docs.openclaw.ai/channels/line), [Mattermost](https://docs.openclaw.ai/channels/mattermost), [Nextcloud Talk](https://docs.openclaw.ai/channels/nextcloud-talk), [Nostr](https://docs.openclaw.ai/channels/nostr), [Synology Chat](https://docs.openclaw.ai/channels/synology-chat), [Tlon](https://docs.openclaw.ai/channels/tlon), [Twitch](https://docs.openclaw.ai/channels/twitch), [Zalo](https://docs.openclaw.ai/channels/zalo), [Zalo Personal](https://docs.openclaw.ai/channels/zalouser), [WebChat](https://docs.openclaw.ai/web/webchat).
 - [Group routing](https://docs.openclaw.ai/channels/group-messages): mention gating, reply tags, per-channel chunking and routing. Channel rules: [Channels](https://docs.openclaw.ai/channels).
 
 ### Apps + nodes
@@ -185,7 +185,7 @@ Run `openclaw doctor` to surface risky/misconfigured DM policies.
 ## How it works (short)
 
 ```
-WhatsApp / Telegram / Slack / Discord / Google Chat / Signal / iMessage / BlueBubbles / IRC / Microsoft Teams / Matrix / Feishu / LINE / Mattermost / Nextcloud Talk / Nostr / Synology Chat / Tlon / Twitch / Zalo / Zalo Personal / WeChat / WebChat
+WhatsApp / Telegram / Slack / Discord / Google Chat / Signal / iMessage / BlueBubbles / IRC / Microsoft Teams / Matrix / Feishu / LINE / Mattermost / Nextcloud Talk / Nostr / Synology Chat / Tlon / Twitch / Zalo / Zalo Personal / WebChat
                │
                ▼
 ┌───────────────────────────────┐
@@ -397,12 +397,6 @@ Details: [Security guide](https://docs.openclaw.ai/gateway/security) · [Docker
 - Configure a Teams app + Bot Framework, then add a `msteams` config section.
 - Allowlist who can talk via `msteams.allowFrom`; group access via `msteams.groupAllowFrom` or `msteams.groupPolicy: "open"`.
 
-### WeChat
-
-- Official Tencent plugin via [`@tencent-weixin/openclaw-weixin`](https://www.npmjs.com/package/@tencent-weixin/openclaw-weixin) (iLink Bot API). Private chats only; v2.x requires OpenClaw `>=2026.3.22`.
-- Install: `openclaw plugins install "@tencent-weixin/openclaw-weixin"`, then `openclaw channels login --channel openclaw-weixin` to scan the QR code.
-- Requires the WeChat ClawBot plugin (WeChat > Me > Settings > Plugins); gradual rollout by Tencent.
-
 ### [WebChat](https://docs.openclaw.ai/web/webchat)
 
 - Uses the Gateway WebSocket; no separate WebChat port/config.

appcast.xml

@@ -2,58 +2,6 @@
 <rss xmlns:sparkle="http://www.andymatuschak.org/xml-namespaces/sparkle" version="2.0">
     <channel>
         <title>OpenClaw</title>
-        <item>
-            <title>2026.3.24</title>
-            <pubDate>Wed, 25 Mar 2026 17:06:31 +0000</pubDate>
-            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
-            <sparkle:version>2026032490</sparkle:version>
-            <sparkle:shortVersionString>2026.3.24</sparkle:shortVersionString>
-            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
-            <description><![CDATA[<h2>OpenClaw 2026.3.24</h2>
-<h3>Breaking</h3>
-<h3>Changes</h3>
-<ul>
-<li>Gateway/OpenAI compatibility: add <code>/v1/models</code> and <code>/v1/embeddings</code>, and forward explicit model overrides through <code>/v1/chat/completions</code> and <code>/v1/responses</code> for broader client and RAG compatibility. Thanks @vincentkoc.</li>
-<li>Agents/tools: make <code>/tools</code> show the tools the current agent can actually use right now, add a compact default view with an optional detailed mode, and add a live "Available Right Now" section in the Control UI so it is easier to see what will work before you ask.</li>
-<li>Microsoft Teams: migrate to the official Teams SDK and add AI-agent UX best practices including streaming 1:1 replies, welcome cards with prompt starters, feedback/reflection, informative status updates, typing indicators, and native AI labeling. (#51808)</li>
-<li>Microsoft Teams: add message edit and delete support for sent messages, including in-thread fallbacks when no explicit target is provided. (#49925)</li>
-<li>Skills/install metadata: add one-click install recipes to bundled skills (coding-agent, gh-issues, openai-whisper-api, session-logs, tmux, trello, weather) so the CLI and Control UI can offer dependency installation when requirements are missing. (#53411) Thanks @BunsDev.</li>
-<li>Control UI/skills: add status-filter tabs (All / Ready / Needs Setup / Disabled) with counts, replace inline skill cards with a click-to-detail dialog showing requirements, toggle switch, install action, API key entry, source metadata, and homepage link. (#53411) Thanks @BunsDev.</li>
-<li>Slack/interactive replies: restore rich reply parity for direct deliveries, auto-render simple trailing <code>Options:</code> lines as buttons/selects, improve Slack interactive setup defaults, and isolate reply controls from plugin interactive handlers. (#53389) Thanks @vincentkoc.</li>
-<li>CLI/containers: add <code>--container</code> and <code>OPENCLAW_CONTAINER</code> to run <code>openclaw</code> commands inside a running Docker or Podman OpenClaw container. (#52651) Thanks @sallyom.</li>
-<li>Discord/auto threads: add optional <code>autoThreadName: "generated"</code> naming so new auto-created threads can be renamed asynchronously with concise LLM-generated titles while keeping the existing message-based naming as the default. (#43366) Thanks @davidguttman.</li>
-<li>Plugins/hooks: add <code>before_dispatch</code> with canonical inbound metadata and route handled replies through the normal final-delivery path, preserving TTS and routed delivery semantics. (#50444) Thanks @gfzhx.</li>
-<li>Control UI/agents: convert agent workspace file rows to expandable <code><details></code> with lazy-loaded inline markdown preview, and add comprehensive <code>.sidebar-markdown</code> styles for headings, lists, code blocks, tables, blockquotes, and details/summary elements. (#53411) Thanks @BunsDev.</li>
-<li>Control UI/markdown preview: restyle the agent workspace file preview dialog with a frosted backdrop, sized panel, and styled header, and integrate <code>@create-markdown/preview</code> v2 system theme for rich markdown rendering (headings, tables, code blocks, callouts, blockquotes) that auto-adapts to the app's light/dark design tokens. (#53411) Thanks @BunsDev.</li>
-<li>macOS app/config: replace horizontal pill-based subsection navigation with a collapsible tree sidebar using disclosure chevrons and indented subsection rows. (#53411) Thanks @BunsDev.</li>
-<li>CLI/skills: soften missing-requirements label from "missing" to "needs setup" and surface API key setup guidance (where to get a key, CLI save command, storage path) in <code>openclaw skills info</code> output. (#53411) Thanks @BunsDev.</li>
-<li>macOS app/skills: add "Get your key" homepage link and storage-path hint to the API key editor dialog, and show the config path in save confirmation messages. (#53411) Thanks @BunsDev.</li>
-<li>Control UI/agents: add a "Not set" placeholder to the default agent model selector dropdown. (#53411) Thanks @BunsDev.</li>
-<li>Runtime/install: lower the supported Node 22 floor to <code>22.14+</code> while continuing to recommend Node 24, so npm installs and self-updates do not strand Node 22.14 users on older releases.</li>
-<li>CLI/update: preflight the target npm package <code>engines.node</code> before <code>openclaw update</code> runs a global package install, so outdated Node runtimes fail with a clear upgrade message instead of attempting an unsupported latest release.</li>
-</ul>
-<h3>Fixes</h3>
-<ul>
-<li>Outbound media/local files: align outbound media access with the configured fs policy so host-local files and inbound-media paths keep sending when <code>workspaceOnly</code> is off, while strict workspace-only agents remain sandboxed.</li>
-<li>Security/sandbox media dispatch: close the <code>mediaUrl</code>/<code>fileUrl</code> alias bypass so outbound tool and message actions cannot escape media-root restrictions. (#54034)</li>
-<li>Gateway/restart sentinel: wake the interrupted agent session via heartbeat after restart instead of only sending a best-effort restart note, retry outbound delivery once on transient failure, and preserve explicit thread/topic routing through the wake path so replies land in the correct Telegram topic or Slack thread. (#53940) Thanks @VACInc.</li>
-<li>Docker/setup: avoid the pre-start <code>openclaw-cli</code> shared-network namespace loop by routing setup-time onboard/config writes through <code>openclaw-gateway</code>, so fresh Docker installs stop failing before the gateway comes up. (#53385) Thanks @amsminn.</li>
-<li>Gateway/channels: keep channel startup sequential while isolating per-channel boot failures, so one broken channel no longer blocks later channels from starting. (#54215) Thanks @JonathanJing.</li>
-<li>Embedded runs/secrets: stop unresolved <code>SecretRef</code> config from crashing embedded agent runs by falling back to the resolved runtime snapshot when needed. Fixes #45838.</li>
-<li>WhatsApp/groups: track recent gateway-sent message IDs and suppress only matching group echoes, preserving owner <code>/status</code>, <code>/new</code>, and <code>/activation</code> commands from linked-account <code>fromMe</code> traffic. (#53624) Thanks @w-sss.</li>
-<li>WhatsApp/reply-to-bot detection: restore implicit group reply detection by unwrapping <code>botInvokeMessage</code> payloads and reading <code>selfLid</code> from <code>creds.json</code>, so reply-based mentions reach the bot again in linked-account group chats.</li>
-<li>Telegram/forum topics: recover <code>#General</code> topic <code>1</code> routing when Telegram omits forum metadata, including native commands, interactive callbacks, inbound message context, and fallback error replies. (#53699) thanks @huntharo</li>
-<li>Discord/gateway supervision: centralize gateway error handling behind a lifetime-owned supervisor so early, active, and late-teardown Carbon gateway errors stay classified consistently and stop surfacing as process-killing teardown crashes.</li>
-<li>Discord/timeouts: send a visible timeout reply when the inbound Discord worker times out before a final reply starts, including created auto-thread targets and queued-run ordering. (#53823) Thanks @Kimbo7870.</li>
-<li>ACP/direct chats: always deliver a terminal ACP result when final TTS does not yield audio, even if block text already streamed earlier, and skip redundant empty-text final synthesis. (#53692) Thanks @w-sss.</li>
-<li>Telegram/outbound errors: preserve actionable 403 membership/block/kick details and treat <code>bot not a member</code> as a permanent delivery failure so Telegram sends stop retrying doomed chats. (#53635) Thanks @w-sss.</li>
-<li>Telegram/photos: preflight Telegram photo dimension and aspect-ratio rules, and fall back to document sends when image metadata is invalid or unavailable so photo uploads stop failing with <code>PHOTO_INVALID_DIMENSIONS</code>. (#52545) Thanks @hnshah.</li>
-<li>Slack/runtime defaults: trim Slack DM reply overhead, restore Codex auto transport, and tighten Slack/web-search runtime defaults around DM preview threading, cache scoping, warning dedupe, and explicit web-search opt-in. (#53957) Thanks @vincentkoc.</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/v2026.3.24/OpenClaw-2026.3.24.zip" length="24749233" type="application/octet-stream" sparkle:edSignature="gLm2VvI+PPEnNy4klYSs9WmZLkJTF5BcfFparrtPdnmeE4xgc8kFfICg445I039ev9/A6xGav7pm08reUHDcAg=="/>
-        </item>
         <item>
             <title>2026.3.23</title>
             <pubDate>Mon, 23 Mar 2026 16:59:51 -0700</pubDate>
@@ -171,5 +119,97 @@
 ]]></description>
             <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.3.13/OpenClaw-2026.3.13.zip" length="23640917" type="application/octet-stream" sparkle:edSignature="Me63UHSpFLocTo5Lt7Iqsl0Hq61y3jTcZ9DUkiFl9xQvTE0+ORuqRMFWqPgYwfaKMgcgQmUbrV/uFzEoTIRHBA=="/>
         </item>
+        <item>
+            <title>2026.3.12</title>
+            <pubDate>Fri, 13 Mar 2026 04:25:50 +0000</pubDate>
+            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
+            <sparkle:version>2026031290</sparkle:version>
+            <sparkle:shortVersionString>2026.3.12</sparkle:shortVersionString>
+            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
+            <description><![CDATA[<h2>OpenClaw 2026.3.12</h2>
+<h3>Changes</h3>
+<ul>
+<li>Control UI/dashboard-v2: refresh the gateway dashboard with modular overview, chat, config, agent, and session views, plus a command palette, mobile bottom tabs, and richer chat tools like slash commands, search, export, and pinned messages. (#41503) Thanks @BunsDev.</li>
+<li>OpenAI/GPT-5.4 fast mode: add configurable session-level fast toggles across <code>/fast</code>, TUI, Control UI, and ACP, with per-model config defaults and OpenAI/Codex request shaping.</li>
+<li>Anthropic/Claude fast mode: map the shared <code>/fast</code> toggle and <code>params.fastMode</code> to direct Anthropic API-key <code>service_tier</code> requests, with live verification for both Anthropic and OpenAI fast-mode tiers.</li>
+<li>Models/plugins: move Ollama, vLLM, and SGLang onto the provider-plugin architecture, with provider-owned onboarding, discovery, model-picker setup, and post-selection hooks so core provider wiring is more modular.</li>
+<li>Docs/Kubernetes: Add a starter K8s install path with raw manifests, Kind setup, and deployment docs. Thanks @sallyom @dzianisv @egkristi</li>
+<li>Agents/subagents: add <code>sessions_yield</code> so orchestrators can end the current turn immediately, skip queued tool work, and carry a hidden follow-up payload into the next session turn. (#36537) thanks @jriff</li>
+<li>Slack/agent replies: support <code>channelData.slack.blocks</code> in the shared reply delivery path so agents can send Block Kit messages through standard Slack outbound delivery. (#44592) Thanks @vincentkoc.</li>
+</ul>
+<h3>Fixes</h3>
+<ul>
+<li>Security/device pairing: switch <code>/pair</code> and <code>openclaw qr</code> setup codes to short-lived bootstrap tokens so the next release no longer embeds shared gateway credentials in chat or QR pairing payloads. Thanks @lintsinghua.</li>
+<li>Security/plugins: disable implicit workspace plugin auto-load so cloned repositories cannot execute workspace plugin code without an explicit trust decision. (<code>GHSA-99qw-6mr3-36qr</code>)(#44174) Thanks @lintsinghua and @vincentkoc.</li>
+<li>Models/Kimi Coding: send <code>anthropic-messages</code> tools in native Anthropic format again so <code>kimi-coding</code> stops degrading tool calls into XML/plain-text pseudo invocations instead of real <code>tool_use</code> blocks. (#38669, #39907, #40552) Thanks @opriz.</li>
+<li>TUI/chat log: reuse the active assistant message component for the same streaming run so <code>openclaw tui</code> no longer renders duplicate assistant replies. (#35364) Thanks @lisitan.</li>
+<li>Telegram/model picker: make inline model button selections persist the chosen session model correctly, clear overrides when selecting the configured default, and include effective fallback models in <code>/models</code> button validation. (#40105) Thanks @avirweb.</li>
+<li>Cron/proactive delivery: keep isolated direct cron sends out of the write-ahead resend queue so transient-send retries do not replay duplicate proactive messages after restart. (#40646) Thanks @openperf and @vincentkoc.</li>
+<li>Models/Kimi Coding: send the built-in <code>User-Agent: claude-code/0.1.0</code> header by default for <code>kimi-coding</code> while still allowing explicit provider headers to override it, so Kimi Code subscription auth can work without a local header-injection proxy. (#30099) Thanks @Amineelfarssi and @vincentkoc.</li>
+<li>Models/OpenAI Codex Spark: keep <code>gpt-5.3-codex-spark</code> working on the <code>openai-codex/*</code> path via resolver fallbacks and clearer Codex-only handling, while continuing to suppress the stale direct <code>openai/*</code> Spark row that OpenAI rejects live.</li>
+<li>Ollama/Kimi Cloud: apply the Moonshot Kimi payload compatibility wrapper to Ollama-hosted Kimi models like <code>kimi-k2.5:cloud</code>, so tool routing no longer breaks when thinking is enabled. (#41519) Thanks @vincentkoc.</li>
+<li>Moonshot CN API: respect explicit <code>baseUrl</code> (api.moonshot.cn) in implicit provider resolution so platform.moonshot.cn API keys authenticate correctly instead of returning HTTP 401. (#33637) Thanks @chengzhichao-xydt.</li>
+<li>Kimi Coding/provider config: respect explicit <code>models.providers["kimi-coding"].baseUrl</code> when resolving the implicit provider so custom Kimi Coding endpoints no longer get overwritten by the built-in default. (#36353) Thanks @2233admin.</li>
+<li>Gateway/main-session routing: keep TUI and other <code>mode:UI</code> main-session sends on the internal surface when <code>deliver</code> is enabled, so replies no longer inherit the session's persisted Telegram/WhatsApp route. (#43918) Thanks @obviyus.</li>
+<li>BlueBubbles/self-chat echo dedupe: drop reflected duplicate webhook copies only when a matching <code>fromMe</code> event was just seen for the same chat, body, and timestamp, preventing self-chat loops without broad webhook suppression. Related to #32166. (#38442) Thanks @vincentkoc.</li>
+<li>iMessage/self-chat echo dedupe: drop reflected duplicate copies only when a matching <code>is_from_me</code> event was just seen for the same chat, text, and <code>created_at</code>, preventing self-chat loops without broad text-only suppression. Related to #32166. (#38440) Thanks @vincentkoc.</li>
+<li>Subagents/completion announce retries: raise the default announce timeout to 90 seconds and stop retrying gateway-timeout failures for externally delivered completion announces, preventing duplicate user-facing completion messages after slow gateway responses. Fixes #41235. Thanks @vasujain00 and @vincentkoc.</li>
+<li>Mattermost/block streaming: fix duplicate message delivery (one threaded, one top-level) when block streaming is active by excluding <code>replyToId</code> from the block reply dedup key and adding an explicit <code>threading</code> dock to the Mattermost plugin. (#41362) Thanks @mathiasnagler and @vincentkoc.</li>
+<li>Mattermost/reply media delivery: pass agent-scoped <code>mediaLocalRoots</code> through shared reply delivery so allowed local files upload correctly from button, slash-command, and model-picker replies. (#44021) Thanks @LyleLiu666.</li>
+<li>macOS/Reminders: add the missing <code>NSRemindersUsageDescription</code> to the bundled app so <code>apple-reminders</code> can trigger the system permission prompt from OpenClaw.app. (#8559) Thanks @dinakars777.</li>
+<li>Gateway/session discovery: discover disk-only and retired ACP session stores under custom templated <code>session.store</code> roots so ACP reconciliation, session-id/session-label targeting, and run-id fallback keep working after restart. (#44176) thanks @gumadeiras.</li>
+<li>Plugins/env-scoped roots: fix plugin discovery/load caches and provenance tracking so same-process <code>HOME</code>/<code>OPENCLAW_HOME</code> changes no longer reuse stale plugin state or misreport <code>~/...</code> plugins as untracked. (#44046) thanks @gumadeiras.</li>
+<li>Models/OpenRouter native ids: canonicalize native OpenRouter model keys across config writes, runtime lookups, fallback management, and <code>models list --plain</code>, and migrate legacy duplicated <code>openrouter/openrouter/...</code> config entries forward on write.</li>
+<li>Windows/native update: make package installs use the npm update path instead of the git path, carry portable Git into native Windows updates, and mirror the installer's Windows npm env so <code>openclaw update</code> no longer dies early on missing <code>git</code> or <code>node-llama-cpp</code> download setup.</li>
+<li>Sandbox/write: preserve pinned mutation-helper payload stdin so sandboxed <code>write</code> no longer reports success while creating empty files. (#43876) Thanks @glitch418x.</li>
+<li>Security/exec approvals: escape invisible Unicode format characters in approval prompts so zero-width command text renders as visible <code>\u{...}</code> escapes instead of spoofing the reviewed command. (<code>GHSA-pcqg-f7rg-xfvv</code>)(#43687) Thanks @EkiXu and @vincentkoc.</li>
+<li>Hooks/loader: fail closed when workspace hook paths cannot be resolved with <code>realpath</code>, so unreadable or broken internal hook paths are skipped instead of falling back to unresolved imports. (#44437) Thanks @vincentkoc.</li>
+<li>Hooks/agent deliveries: dedupe repeated hook requests by optional idempotency key so webhook retries can reuse the first run instead of launching duplicate agent executions. (#44438) Thanks @vincentkoc.</li>
+<li>Security/exec detection: normalize compatibility Unicode and strip invisible formatting code points before obfuscation checks so zero-width and fullwidth command tricks no longer suppress heuristic detection. (<code>GHSA-9r3v-37xh-2cf6</code>)(#44091) Thanks @wooluo and @vincentkoc.</li>
+<li>Security/exec allowlist: preserve POSIX case sensitivity and keep <code>?</code> within a single path segment so exact-looking allowlist patterns no longer overmatch executables across case or directory boundaries. (<code>GHSA-f8r2-vg7x-gh8m</code>)(#43798) Thanks @zpbrent and @vincentkoc.</li>
+<li>Security/commands: require sender ownership for <code>/config</code> and <code>/debug</code> so authorized non-owner senders can no longer reach owner-only config and runtime debug surfaces. (<code>GHSA-r7vr-gr74-94p8</code>)(#44305) Thanks @tdjackey and @vincentkoc.</li>
+<li>Security/gateway auth: clear unbound client-declared scopes on shared-token WebSocket connects so device-less shared-token operators cannot self-declare elevated scopes. (<code>GHSA-rqpp-rjj8-7wv8</code>)(#44306) Thanks @LUOYEcode and @vincentkoc.</li>
+<li>Security/browser.request: block persistent browser profile create/delete routes from write-scoped <code>browser.request</code> so callers can no longer persist admin-only browser profile changes through the browser control surface. (<code>GHSA-vmhq-cqm9-6p7q</code>)(#43800) Thanks @tdjackey and @vincentkoc.</li>
+<li>Security/agent: reject public spawned-run lineage fields and keep workspace inheritance on the internal spawned-session path so external <code>agent</code> callers can no longer override the gateway workspace boundary. (<code>GHSA-2rqg-gjgv-84jm</code>)(#43801) Thanks @tdjackey and @vincentkoc.</li>
+<li>Security/session_status: enforce sandbox session-tree visibility and shared agent-to-agent access guards before reading or mutating target session state, so sandboxed subagents can no longer inspect parent session metadata or write parent model overrides via <code>session_status</code>. (<code>GHSA-wcxr-59v9-rxr8</code>)(#43754) Thanks @tdjackey and @vincentkoc.</li>
+<li>Security/agent tools: mark <code>nodes</code> as explicitly owner-only and document/test that <code>canvas</code> remains a shared trusted-operator surface unless a real boundary bypass exists.</li>
+<li>Security/exec approvals: fail closed for Ruby approval flows that use <code>-r</code>, <code>--require</code>, or <code>-I</code> so approval-backed commands no longer bind only the main script while extra local code-loading flags remain outside the reviewed file snapshot.</li>
+<li>Security/device pairing: cap issued and verified device-token scopes to each paired device's approved scope baseline so stale or overbroad tokens cannot exceed approved access. (<code>GHSA-2pwv-x786-56f8</code>)(#43686) Thanks @tdjackey and @vincentkoc.</li>
+<li>Docs/onboarding: align the legacy wizard reference and <code>openclaw onboard</code> command docs with the Ollama onboarding flow so all onboarding reference paths now document <code>--auth-choice ollama</code>, Cloud + Local mode, and non-interactive usage. (#43473) Thanks @BruceMacD.</li>
+<li>Models/secrets: enforce source-managed SecretRef markers in generated <code>models.json</code> so runtime-resolved provider secrets are not persisted when runtime projection is skipped. (#43759) Thanks @joshavant.</li>
+<li>Security/WebSocket preauth: shorten unauthenticated handshake retention and reject oversized pre-auth frames before application-layer parsing to reduce pre-pairing exposure on unsupported public deployments. (<code>GHSA-jv4g-m82p-2j93</code>)(#44089) (<code>GHSA-xwx2-ppv2-wx98</code>)(#44089) Thanks @ez-lbz and @vincentkoc.</li>
+<li>Security/proxy attachments: restore the shared media-store size cap for persisted browser proxy files so oversized payloads are rejected instead of overriding the intended 5 MB limit. (<code>GHSA-6rph-mmhp-h7h9</code>)(#43684) Thanks @tdjackey and @vincentkoc.</li>
+<li>Security/host env: block inherited <code>GIT_EXEC_PATH</code> from sanitized host exec environments so Git helper resolution cannot be steered by host environment state. (<code>GHSA-jf5v-pqgw-gm5m</code>)(#43685) Thanks @zpbrent and @vincentkoc.</li>
+<li>Security/Feishu webhook: require <code>encryptKey</code> alongside <code>verificationToken</code> in webhook mode so unsigned forged events are rejected instead of being processed with token-only configuration. (<code>GHSA-g353-mgv3-8pcj</code>)(#44087) Thanks @lintsinghua and @vincentkoc.</li>
+<li>Security/Feishu reactions: preserve looked-up group chat typing and fail closed on ambiguous reaction context so group authorization and mention gating cannot be bypassed through synthetic <code>p2p</code> reactions. (<code>GHSA-m69h-jm2f-2pv8</code>)(#44088) Thanks @zpbrent and @vincentkoc.</li>
+<li>Security/LINE webhook: require signatures for empty-event POST probes too so unsigned requests no longer confirm webhook reachability with a <code>200</code> response. (<code>GHSA-mhxh-9pjm-w7q5</code>)(#44090) Thanks @TerminalsandCoffee and @vincentkoc.</li>
+<li>Security/Zalo webhook: rate limit invalid secret guesses before auth so weak webhook secrets cannot be brute-forced through unauthenticated churned requests without pre-auth <code>429</code> responses. (<code>GHSA-5m9r-p9g7-679c</code>)(#44173) Thanks @zpbrent and @vincentkoc.</li>
+<li>Security/Zalouser groups: require stable group IDs for allowlist auth by default and gate mutable group-name matching behind <code>channels.zalouser.dangerouslyAllowNameMatching</code>. Thanks @zpbrent.</li>
+<li>Security/Slack and Teams routing: require stable channel and team IDs for allowlist routing by default, with mutable name matching only via each channel's <code>dangerouslyAllowNameMatching</code> break-glass flag.</li>
+<li>Security/exec approvals: fail closed for ambiguous inline loader and shell-payload script execution, bind the real script after POSIX shell value-taking flags, and unwrap <code>pnpm</code>/<code>npm exec</code>/<code>npx</code> script runners before approval binding. (<code>GHSA-57jw-9722-6rf2</code>)(<code>GHSA-jvqh-rfmh-jh27</code>)(<code>GHSA-x7pp-23xv-mmr4</code>)(<code>GHSA-jc5j-vg4r-j5jx</code>)(#44247) Thanks @tdjackey and @vincentkoc.</li>
+<li>Doctor/gateway service audit: canonicalize service entrypoint paths before comparing them so symlink-vs-realpath installs no longer trigger false "entrypoint does not match the current install" repair prompts. (#43882) Thanks @ngutman.</li>
+<li>Doctor/gateway service audit: earlier groundwork for this fix landed in the superseded #28338 branch. Thanks @realriphub.</li>
+<li>Gateway/session stores: regenerate the Swift push-test protocol models and align Windows native session-store realpath handling so protocol checks and sync session discovery stop drifting on Windows. (#44266) thanks @jalehman.</li>
+<li>Context engine/session routing: forward optional <code>sessionKey</code> through context-engine lifecycle calls so plugins can see structured routing metadata during bootstrap, assembly, post-turn ingestion, and compaction. (#44157) thanks @jalehman.</li>
+<li>Agents/failover: classify z.ai <code>network_error</code> stop reasons as retryable timeouts so provider connectivity failures trigger fallback instead of surfacing raw unhandled-stop-reason errors. (#43884) Thanks @hougangdev.</li>
+<li>Memory/session sync: add mode-aware post-compaction session reindexing with <code>agents.defaults.compaction.postIndexSync</code> plus <code>agents.defaults.memorySearch.sync.sessions.postCompactionForce</code>, so compacted session memory can refresh immediately without forcing every deployment into synchronous reindexing. (#25561) thanks @rodrigouroz.</li>
+<li>Telegram/model picker: make inline model button selections persist the chosen session model correctly, clear overrides when selecting the configured default, and include effective fallback models in <code>/models</code> button validation. (#40105) Thanks @avirweb.</li>
+<li>Telegram/native command sync: suppress expected <code>BOT_COMMANDS_TOO_MUCH</code> retry error noise, add a final fallback summary log, and document the difference between command-menu overflow and real Telegram network failures.</li>
+<li>Mattermost/reply media delivery: pass agent-scoped <code>mediaLocalRoots</code> through shared reply delivery so allowed local files upload correctly from button, slash-command, and model-picker replies. (#44021) Thanks @LyleLiu666.</li>
+<li>Plugins/env-scoped roots: fix plugin discovery/load caches and provenance tracking so same-process <code>HOME</code>/<code>OPENCLAW_HOME</code> changes no longer reuse stale plugin state or misreport <code>~/...</code> plugins as untracked. (#44046) thanks @gumadeiras.</li>
+<li>Gateway/session discovery: discover disk-only and retired ACP session stores under custom templated <code>session.store</code> roots so ACP reconciliation, session-id/session-label targeting, and run-id fallback keep working after restart. (#44176) thanks @gumadeiras.</li>
+<li>Models/OpenRouter native ids: canonicalize native OpenRouter model keys across config writes, runtime lookups, fallback management, and <code>models list --plain</code>, and migrate legacy duplicated <code>openrouter/openrouter/...</code> config entries forward on write.</li>
+<li>Gateway/hooks: bucket hook auth failures by forwarded client IP behind trusted proxies and warn when <code>hooks.allowedAgentIds</code> leaves hook routing unrestricted.</li>
+<li>Agents/compaction: skip the post-compaction <code>cache-ttl</code> marker write when a compaction completed in the same attempt, preventing the next turn from immediately triggering a second tiny compaction. (#28548) thanks @MoerAI.</li>
+<li>Native chat/macOS: add <code>/new</code>, <code>/reset</code>, and <code>/clear</code> reset triggers, keep shared main-session aliases aligned, and ignore stale model-selection completions so native chat state stays in sync across reset and fast model changes. (#10898) Thanks @Nachx639.</li>
+<li>Agents/compaction safeguard: route missing-model and missing-API-key cancellation warnings through the shared subsystem logger so they land in structured and file logs. (#9974) Thanks @dinakars777.</li>
+<li>Cron/doctor: stop flagging canonical <code>agentTurn</code> and <code>systemEvent</code> payload kinds as legacy cron storage, while still normalizing whitespace-padded and non-canonical variants. (#44012) Thanks @shuicici.</li>
+<li>ACP/client final-message delivery: preserve terminal assistant text snapshots before resolving <code>end_turn</code>, so ACP clients no longer drop the last visible reply when the gateway sends the final message body on the terminal chat event. (#17615) Thanks @pjeby.</li>
+<li>Telegram/Discord status reactions: show a temporary compacting reaction during auto-compaction pauses and restore thinking afterward so the bot no longer appears frozen while context is being compacted. (#35474) thanks @Cypherm.</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/v2026.3.12/OpenClaw-2026.3.12.zip" length="23628700" type="application/octet-stream" sparkle:edSignature="o6Zdcw36l3I0jUg14H+RBqNwrhuuSsq1WMDi4tBRa1+5TC3VCVdFKZ2hzmH2Xjru9lDEzVMP8v2A6RexSbOCBQ=="/>
+        </item>
     </channel>
-</rss>
+</rss>

apps/android/app/build.gradle.kts

@@ -65,8 +65,8 @@ android {
         applicationId = "ai.openclaw.app"
         minSdk = 31
         targetSdk = 36
-        versionCode = 2026032600
-        versionName = "2026.3.26"
+        versionCode = 2026032400
+        versionName = "2026.3.24"
         ndk {
             // Support all major ABIs — native libs are tiny (~47 KB per ABI)
             abiFilters += listOf("armeabi-v7a", "arm64-v8a", "x86", "x86_64")

apps/ios/Config/Version.xcconfig

@@ -1,8 +1,8 @@
 // Shared iOS version defaults.
 // Generated overrides live in build/Version.xcconfig (git-ignored).
 
-OPENCLAW_GATEWAY_VERSION = 2026.3.26
-OPENCLAW_MARKETING_VERSION = 2026.3.26
-OPENCLAW_BUILD_VERSION = 202603260
+OPENCLAW_GATEWAY_VERSION = 2026.3.24-beta.1
+OPENCLAW_MARKETING_VERSION = 2026.3.24
+OPENCLAW_BUILD_VERSION = 202603240
 
 #include? "../build/Version.xcconfig"

apps/ios/README.md

@@ -65,9 +65,9 @@ Release behavior:
 - Beta release also switches the app to `OpenClawPushTransport=relay`, `OpenClawPushDistribution=official`, and `OpenClawPushAPNsEnvironment=production`.
 - The beta flow does not modify `apps/ios/.local-signing.xcconfig` or `apps/ios/LocalSigning.xcconfig`.
 - Root `package.json.version` is the only version source for iOS.
-- A root version like `2026.3.26-beta.1` becomes:
-  - `CFBundleShortVersionString = 2026.3.26`
-  - `CFBundleVersion = next TestFlight build number for 2026.3.26`
+- A root version like `2026.3.22-beta.1` becomes:
+  - `CFBundleShortVersionString = 2026.3.22`
+  - `CFBundleVersion = next TestFlight build number for 2026.3.22`
 
 Required env for beta builds:
 

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

@@ -18,7 +18,6 @@ enum HostEnvSecurityPolicy {
         "ENV",
         "GIT_EXTERNAL_DIFF",
         "GIT_EXEC_PATH",
-        "GIT_TEMPLATE_DIR",
         "SHELL",
         "SHELLOPTS",
         "PS4",
@@ -80,8 +79,7 @@ enum HostEnvSecurityPolicy {
         "GEM_PATH",
         "BUNDLE_GEMFILE",
         "COMPOSER_HOME",
-        "XDG_CONFIG_HOME",
-        "AWS_CONFIG_FILE"
+        "XDG_CONFIG_HOME"
     ]
 
     static let blockedOverridePrefixes: [String] = [

apps/macos/Sources/OpenClaw/OpenClawConfigFile.swift

@@ -493,12 +493,8 @@ enum OpenClawConfigFile {
             return
         }
 
-        let backup = self.readConfigFingerprint(
-            at: configURL.deletingLastPathComponent().appendingPathComponent("\(configURL.lastPathComponent).bak"))
-        let clobberedPath = self.persistClobberedSnapshot(
-            data: data,
-            configURL: configURL,
-            observedAt: observedAt)
+        let backup = self.readConfigFingerprint(at: configURL.deletingLastPathComponent().appendingPathComponent("\(configURL.lastPathComponent).bak"))
+        let clobberedPath = self.persistClobberedSnapshot(data: data, configURL: configURL, observedAt: observedAt)
         self.logger.warning("config observe anomaly (\(suspicious.joined(separator: ", "))) at \(configURL.path)")
         self.appendConfigObserveAudit([
             "phase": "read",

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

@@ -15,9 +15,9 @@
     <key>CFBundlePackageType</key>
     <string>APPL</string>
     <key>CFBundleShortVersionString</key>
-    <string>2026.3.26</string>
+    <string>2026.3.24</string>
     <key>CFBundleVersion</key>
-    <string>202603260</string>
+    <string>202603240</string>
     <key>CFBundleIconFile</key>
     <string>OpenClaw</string>
     <key>CFBundleURLTypes</key>

apps/macos/Sources/OpenClaw/SkillsSettings.swift

@@ -259,12 +259,9 @@ private struct SkillRow: View {
         guard let raw = self.skill.homepage?.trimmingCharacters(in: .whitespacesAndNewlines) else {
             return nil
         }
-        guard
-            !raw.isEmpty,
-            let url = URL(string: raw),
-            let scheme = url.scheme?.lowercased(),
-            scheme == "http" || scheme == "https"
-        else {
+        guard !raw.isEmpty, let url = URL(string: raw),
+              let scheme = url.scheme?.lowercased(),
+              scheme == "http" || scheme == "https" else {
             return nil
         }
         return url
@@ -484,12 +481,9 @@ private struct EnvEditorView: View {
         guard let raw = self.editor.homepage?.trimmingCharacters(in: .whitespacesAndNewlines) else {
             return nil
         }
-        guard
-            !raw.isEmpty,
-            let url = URL(string: raw),
-            let scheme = url.scheme?.lowercased(),
-            scheme == "http" || scheme == "https"
-        else {
+        guard !raw.isEmpty, let url = URL(string: raw),
+              let scheme = url.scheme?.lowercased(),
+              scheme == "http" || scheme == "https" else {
             return nil
         }
         return url

apps/macos/Sources/OpenClaw/TalkModeRuntime.swift

@@ -8,11 +8,6 @@ import Speech
 actor TalkModeRuntime {
     static let shared = TalkModeRuntime()
 
-    enum PlaybackPlan: Equatable {
-        case elevenLabsThenSystemVoice(apiKey: String, voiceId: String)
-        case systemVoiceOnly
-    }
-
     private let logger = Logger(subsystem: "ai.openclaw", category: "talk.runtime")
     private let ttsLogger = Logger(subsystem: "ai.openclaw", category: "talk.tts")
     private static let defaultModelIdFallback = "eleven_v3"
@@ -456,22 +451,17 @@ actor TalkModeRuntime {
 
     private func playAssistant(text: String) async {
         guard let input = await self.preparePlaybackInput(text: text) else { return }
-        switch Self.playbackPlan(apiKey: input.apiKey, voiceId: input.voiceId) {
-        case let .elevenLabsThenSystemVoice(apiKey, voiceId):
-            do {
+        do {
+            if let apiKey = input.apiKey, !apiKey.isEmpty, let voiceId = input.voiceId {
                 try await self.playElevenLabs(input: input, apiKey: apiKey, voiceId: voiceId)
-            } catch {
-                self.ttsLogger
-                    .error(
-                        "talk TTS failed: \(error.localizedDescription, privacy: .public); " +
-                            "falling back to system voice")
-                do {
-                    try await self.playSystemVoice(input: input)
-                } catch {
-                    self.ttsLogger.error("talk system voice failed: \(error.localizedDescription, privacy: .public)")
-                }
+            } else {
+                try await self.playSystemVoice(input: input)
             }
-        case .systemVoiceOnly:
+        } catch {
+            self.ttsLogger
+                .error(
+                    "talk TTS failed: \(error.localizedDescription, privacy: .public); " +
+                        "falling back to system voice")
             do {
                 try await self.playSystemVoice(input: input)
             } catch {
@@ -485,13 +475,6 @@ actor TalkModeRuntime {
         }
     }
 
-    static func playbackPlan(apiKey: String?, voiceId: String?) -> PlaybackPlan {
-        guard let apiKey, !apiKey.isEmpty, let voiceId else {
-            return .systemVoiceOnly
-        }
-        return .elevenLabsThenSystemVoice(apiKey: apiKey, voiceId: voiceId)
-    }
-
     private struct TalkPlaybackInput {
         let generation: Int
         let cleanedText: String
@@ -681,12 +664,9 @@ actor TalkModeRuntime {
         await MainActor.run { TalkModeController.shared.updatePhase(.speaking) }
         self.phase = .speaking
         await TalkSystemSpeechSynthesizer.shared.stop()
-        // Use app locale as fallback when no explicit language is set (e.g. system voice without ElevenLabs directive).
-        let appLocale = await MainActor.run { AppStateStore.shared.voiceWakeLocaleID }
-        let ttsLanguage = input.language ?? appLocale
         try await TalkSystemSpeechSynthesizer.shared.speak(
             text: input.cleanedText,
-            language: ttsLanguage)
+            language: input.language)
         self.ttsLogger.info("talk system voice done")
     }
 

apps/macos/Sources/OpenClawProtocol/GatewayModels.swift

@@ -9,7 +9,6 @@ public enum ErrorCode: String, Codable, Sendable {
     case notPaired = "NOT_PAIRED"
     case agentTimeout = "AGENT_TIMEOUT"
     case invalidRequest = "INVALID_REQUEST"
-    case approvalNotFound = "APPROVAL_NOT_FOUND"
     case unavailable = "UNAVAILABLE"
 }
 
@@ -3435,90 +3434,6 @@ public struct ExecApprovalResolveParams: Codable, Sendable {
     }
 }
 
-public struct PluginApprovalRequestParams: Codable, Sendable {
-    public let pluginid: String?
-    public let title: String
-    public let description: String
-    public let severity: String?
-    public let toolname: String?
-    public let toolcallid: String?
-    public let agentid: String?
-    public let sessionkey: String?
-    public let turnsourcechannel: String?
-    public let turnsourceto: String?
-    public let turnsourceaccountid: String?
-    public let turnsourcethreadid: AnyCodable?
-    public let timeoutms: Int?
-    public let twophase: Bool?
-
-    public init(
-        pluginid: String?,
-        title: String,
-        description: String,
-        severity: String?,
-        toolname: String?,
-        toolcallid: String?,
-        agentid: String?,
-        sessionkey: String?,
-        turnsourcechannel: String?,
-        turnsourceto: String?,
-        turnsourceaccountid: String?,
-        turnsourcethreadid: AnyCodable?,
-        timeoutms: Int?,
-        twophase: Bool?)
-    {
-        self.pluginid = pluginid
-        self.title = title
-        self.description = description
-        self.severity = severity
-        self.toolname = toolname
-        self.toolcallid = toolcallid
-        self.agentid = agentid
-        self.sessionkey = sessionkey
-        self.turnsourcechannel = turnsourcechannel
-        self.turnsourceto = turnsourceto
-        self.turnsourceaccountid = turnsourceaccountid
-        self.turnsourcethreadid = turnsourcethreadid
-        self.timeoutms = timeoutms
-        self.twophase = twophase
-    }
-
-    private enum CodingKeys: String, CodingKey {
-        case pluginid = "pluginId"
-        case title
-        case description
-        case severity
-        case toolname = "toolName"
-        case toolcallid = "toolCallId"
-        case agentid = "agentId"
-        case sessionkey = "sessionKey"
-        case turnsourcechannel = "turnSourceChannel"
-        case turnsourceto = "turnSourceTo"
-        case turnsourceaccountid = "turnSourceAccountId"
-        case turnsourcethreadid = "turnSourceThreadId"
-        case timeoutms = "timeoutMs"
-        case twophase = "twoPhase"
-    }
-}
-
-public struct PluginApprovalResolveParams: Codable, Sendable {
-    public let id: String
-    public let decision: String
-
-    public init(
-        id: String,
-        decision: String)
-    {
-        self.id = id
-        self.decision = decision
-    }
-
-    private enum CodingKeys: String, CodingKey {
-        case id
-        case decision
-    }
-}
-
 public struct DevicePairListParams: Codable, Sendable {}
 
 public struct DevicePairApproveParams: Codable, Sendable {

apps/macos/Tests/OpenClawIPCTests/TalkModeRuntimeSpeechTests.swift

@@ -11,13 +11,4 @@ struct TalkModeRuntimeSpeechTests {
         #expect(request.shouldReportPartialResults)
         #expect(request.taskHint == .dictation)
     }
-
-    @Test func `playback plan falls back only from elevenlabs`() {
-        #expect(
-            TalkModeRuntime.playbackPlan(apiKey: "key", voiceId: "voice")
-                == .elevenLabsThenSystemVoice(apiKey: "key", voiceId: "voice"))
-        #expect(TalkModeRuntime.playbackPlan(apiKey: nil, voiceId: "voice") == .systemVoiceOnly)
-        #expect(TalkModeRuntime.playbackPlan(apiKey: "key", voiceId: nil) == .systemVoiceOnly)
-        #expect(TalkModeRuntime.playbackPlan(apiKey: "", voiceId: "voice") == .systemVoiceOnly)
-    }
 }

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

@@ -51,11 +51,11 @@ public final class TalkSystemSpeechSynthesizer: NSObject {
         }
         self.currentUtterance = utterance
 
-        let watchdogTimeout = Self.watchdogTimeoutSeconds(text: trimmed, language: language ?? utterance.voice?.language)
+        let estimatedSeconds = max(3.0, min(180.0, Double(trimmed.count) * 0.08))
         self.watchdog?.cancel()
         self.watchdog = Task { @MainActor [weak self] in
             guard let self else { return }
-            try? await Task.sleep(nanoseconds: UInt64(watchdogTimeout * 1_000_000_000))
+            try? await Task.sleep(nanoseconds: UInt64(estimatedSeconds * 1_000_000_000))
             if Task.isCancelled { return }
             guard self.currentToken == token else { return }
             if self.synth.isSpeaking {
@@ -63,7 +63,7 @@ public final class TalkSystemSpeechSynthesizer: NSObject {
             }
             self.finishCurrent(
                 with: NSError(domain: "TalkSystemSpeechSynthesizer", code: 408, userInfo: [
-                    NSLocalizedDescriptionKey: "system TTS timed out after \(watchdogTimeout)s",
+                    NSLocalizedDescriptionKey: "system TTS timed out after \(estimatedSeconds)s",
                 ]))
         }
 
@@ -83,37 +83,6 @@ public final class TalkSystemSpeechSynthesizer: NSObject {
         }
     }
 
-    static func watchdogTimeoutSeconds(text: String, language: String?) -> Double {
-        // Estimate speech duration per language, then apply 3x safety margin.
-        // The watchdog is a hang guard — normal completion relies on didFinish.
-        //
-        // Speech rates based on Pellegrino et al. (2019) syllable-per-second data,
-        // adjusted for TTS synthesis (slower than natural speech):
-        // https://www.science.org/doi/10.1126/sciadv.aaw2594
-        //   Japanese: 7.84 SPS -> ~0.20s/char (mixed kana/kanji avg ~1.5 mora/char)
-        //   Korean:   5.96 SPS -> ~0.25s/char (1 char = 1 syllable)
-        //   Chinese:  5.18 SPS -> ~0.28s/char (1 char = 1 syllable)
-        //   English:  6.19 SPS -> ~0.08s/char (avg ~5 chars/syllable)
-        let normalizedLanguage = language?.lowercased() ?? "en"
-        let perCharSeconds: Double
-        let minSeconds: Double
-        if normalizedLanguage.hasPrefix("ko") {
-            perCharSeconds = 0.25
-            minSeconds = 10.0
-        } else if normalizedLanguage.hasPrefix("zh") {
-            perCharSeconds = 0.28
-            minSeconds = 10.0
-        } else if normalizedLanguage.hasPrefix("ja") {
-            perCharSeconds = 0.20
-            minSeconds = 10.0
-        } else {
-            perCharSeconds = 0.08
-            minSeconds = 3.0
-        }
-        let estimatedSeconds = max(minSeconds, min(300.0, Double(text.count) * perCharSeconds))
-        return estimatedSeconds * 3.0
-    }
-
     private func matchesCurrentUtterance(_ utteranceID: ObjectIdentifier) -> Bool {
         guard let currentUtterance = self.currentUtterance else { return false }
         return ObjectIdentifier(currentUtterance) == utteranceID

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

@@ -9,7 +9,6 @@ public enum ErrorCode: String, Codable, Sendable {
     case notPaired = "NOT_PAIRED"
     case agentTimeout = "AGENT_TIMEOUT"
     case invalidRequest = "INVALID_REQUEST"
-    case approvalNotFound = "APPROVAL_NOT_FOUND"
     case unavailable = "UNAVAILABLE"
 }
 
@@ -3435,90 +3434,6 @@ public struct ExecApprovalResolveParams: Codable, Sendable {
     }
 }
 
-public struct PluginApprovalRequestParams: Codable, Sendable {
-    public let pluginid: String?
-    public let title: String
-    public let description: String
-    public let severity: String?
-    public let toolname: String?
-    public let toolcallid: String?
-    public let agentid: String?
-    public let sessionkey: String?
-    public let turnsourcechannel: String?
-    public let turnsourceto: String?
-    public let turnsourceaccountid: String?
-    public let turnsourcethreadid: AnyCodable?
-    public let timeoutms: Int?
-    public let twophase: Bool?
-
-    public init(
-        pluginid: String?,
-        title: String,
-        description: String,
-        severity: String?,
-        toolname: String?,
-        toolcallid: String?,
-        agentid: String?,
-        sessionkey: String?,
-        turnsourcechannel: String?,
-        turnsourceto: String?,
-        turnsourceaccountid: String?,
-        turnsourcethreadid: AnyCodable?,
-        timeoutms: Int?,
-        twophase: Bool?)
-    {
-        self.pluginid = pluginid
-        self.title = title
-        self.description = description
-        self.severity = severity
-        self.toolname = toolname
-        self.toolcallid = toolcallid
-        self.agentid = agentid
-        self.sessionkey = sessionkey
-        self.turnsourcechannel = turnsourcechannel
-        self.turnsourceto = turnsourceto
-        self.turnsourceaccountid = turnsourceaccountid
-        self.turnsourcethreadid = turnsourcethreadid
-        self.timeoutms = timeoutms
-        self.twophase = twophase
-    }
-
-    private enum CodingKeys: String, CodingKey {
-        case pluginid = "pluginId"
-        case title
-        case description
-        case severity
-        case toolname = "toolName"
-        case toolcallid = "toolCallId"
-        case agentid = "agentId"
-        case sessionkey = "sessionKey"
-        case turnsourcechannel = "turnSourceChannel"
-        case turnsourceto = "turnSourceTo"
-        case turnsourceaccountid = "turnSourceAccountId"
-        case turnsourcethreadid = "turnSourceThreadId"
-        case timeoutms = "timeoutMs"
-        case twophase = "twoPhase"
-    }
-}
-
-public struct PluginApprovalResolveParams: Codable, Sendable {
-    public let id: String
-    public let decision: String
-
-    public init(
-        id: String,
-        decision: String)
-    {
-        self.id = id
-        self.decision = decision
-    }
-
-    private enum CodingKeys: String, CodingKey {
-        case id
-        case decision
-    }
-}
-
 public struct DevicePairListParams: Codable, Sendable {}
 
 public struct DevicePairApproveParams: Codable, Sendable {

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

@@ -1,44 +0,0 @@
-import XCTest
-@testable import OpenClawKit
-
-final class TalkSystemSpeechSynthesizerTests: XCTestCase {
-    func testWatchdogTimeoutDefaultsToLatinProfile() {
-        let timeout = TalkSystemSpeechSynthesizer.watchdogTimeoutSeconds(
-            text: String(repeating: "a", count: 100),
-            language: nil)
-
-        XCTAssertEqual(timeout, 24.0, accuracy: 0.001)
-    }
-
-    func testWatchdogTimeoutUsesKoreanProfile() {
-        let timeout = TalkSystemSpeechSynthesizer.watchdogTimeoutSeconds(
-            text: String(repeating: "가", count: 100),
-            language: "ko-KR")
-
-        XCTAssertEqual(timeout, 75.0, accuracy: 0.001)
-    }
-
-    func testWatchdogTimeoutUsesChineseProfile() {
-        let timeout = TalkSystemSpeechSynthesizer.watchdogTimeoutSeconds(
-            text: String(repeating: "你", count: 100),
-            language: "zh-CN")
-
-        XCTAssertEqual(timeout, 84.0, accuracy: 0.001)
-    }
-
-    func testWatchdogTimeoutUsesJapaneseProfile() {
-        let timeout = TalkSystemSpeechSynthesizer.watchdogTimeoutSeconds(
-            text: String(repeating: "あ", count: 100),
-            language: "ja-JP")
-
-        XCTAssertEqual(timeout, 60.0, accuracy: 0.001)
-    }
-
-    func testWatchdogTimeoutClampsVeryLongUtterances() {
-        let timeout = TalkSystemSpeechSynthesizer.watchdogTimeoutSeconds(
-            text: String(repeating: "a", count: 10_000),
-            language: "en-US")
-
-        XCTAssertEqual(timeout, 900.0, accuracy: 0.001)
-    }
-}

docs/.generated/config-baseline.jsonl

@@ -1,4 +1,4 @@
-{"generatedBy":"scripts/generate-config-doc-baseline.ts","recordType":"meta","totalPaths":5554}
+{"generatedBy":"scripts/generate-config-doc-baseline.ts","recordType":"meta","totalPaths":5631}
 {"recordType":"path","path":"acp","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"ACP","help":"ACP runtime controls for enabling dispatch, selecting backends, constraining allowed agent targets, and tuning streamed turn projection behavior.","hasChildren":true}
 {"recordType":"path","path":"acp.allowedAgents","kind":"core","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"ACP Allowed Agents","help":"Allowlist of ACP target agent ids permitted for ACP runtime sessions. Empty means no additional allowlist restriction.","hasChildren":true}
 {"recordType":"path","path":"acp.allowedAgents.*","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -467,7 +467,7 @@
 {"recordType":"path","path":"agents.list.*.reasoningDefault","kind":"core","type":"string","required":false,"enumValues":["on","off","stream"],"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Agent Reasoning Default","help":"Optional per-agent default reasoning visibility (on|off|stream). Applies when no per-message or session reasoning override is set.","hasChildren":false}
 {"recordType":"path","path":"agents.list.*.runtime","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Agent Runtime","help":"Optional runtime descriptor for this agent. Use embedded for default OpenClaw execution or acp for external ACP harness defaults.","hasChildren":true}
 {"recordType":"path","path":"agents.list.*.runtime.acp","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Agent ACP Runtime","help":"ACP runtime defaults for this agent when runtime.type=acp. Binding-level ACP overrides still take precedence per conversation.","hasChildren":true}
-{"recordType":"path","path":"agents.list.*.runtime.acp.agent","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Agent ACP Harness Agent","help":"Optional ACP harness agent id to use for this OpenClaw agent (for example codex, claude, cursor, gemini, openclaw).","hasChildren":false}
+{"recordType":"path","path":"agents.list.*.runtime.acp.agent","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Agent ACP Harness Agent","help":"Optional ACP harness agent id to use for this OpenClaw agent (for example codex, claude).","hasChildren":false}
 {"recordType":"path","path":"agents.list.*.runtime.acp.backend","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Agent ACP Backend","help":"Optional ACP backend override for this agent's ACP sessions (falls back to global acp.backend).","hasChildren":false}
 {"recordType":"path","path":"agents.list.*.runtime.acp.cwd","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Agent ACP Working Directory","help":"Optional default working directory for this agent's ACP sessions.","hasChildren":false}
 {"recordType":"path","path":"agents.list.*.runtime.acp.mode","kind":"core","type":"string","required":false,"enumValues":["persistent","oneshot"],"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Agent ACP Mode","help":"Optional ACP session mode default for this agent (persistent or oneshot).","hasChildren":false}
@@ -638,7 +638,7 @@
 {"recordType":"path","path":"agents.list.*.tools.sandbox.tools.deny","kind":"core","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"agents.list.*.tools.sandbox.tools.deny.*","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"agents.list.*.workspace","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"approvals","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Approvals","help":"Approval routing controls for forwarding exec and plugin approval requests to chat destinations outside the originating session. Keep these disabled unless operators need explicit out-of-band approval visibility.","hasChildren":true}
+{"recordType":"path","path":"approvals","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Approvals","help":"Approval routing controls for forwarding exec approval requests to chat destinations outside the originating session. Keep this disabled unless operators need explicit out-of-band approval visibility.","hasChildren":true}
 {"recordType":"path","path":"approvals.exec","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Exec Approval Forwarding","help":"Groups exec-approval forwarding behavior including enablement, routing mode, filters, and explicit targets. Configure here when approval prompts must reach operational channels instead of only the origin thread.","hasChildren":true}
 {"recordType":"path","path":"approvals.exec.agentFilter","kind":"core","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Approval Agent Filter","help":"Optional allowlist of agent IDs eligible for forwarded approvals, for example `[\"primary\", \"ops-agent\"]`. Use this to limit forwarding blast radius and avoid notifying channels for unrelated agents.","hasChildren":true}
 {"recordType":"path","path":"approvals.exec.agentFilter.*","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -652,19 +652,6 @@
 {"recordType":"path","path":"approvals.exec.targets.*.channel","kind":"core","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Approval Target Channel","help":"Channel/provider ID used for forwarded approval delivery, such as discord, slack, or a plugin channel id. Use valid channel IDs only so approvals do not silently fail due to unknown routes.","hasChildren":false}
 {"recordType":"path","path":"approvals.exec.targets.*.threadId","kind":"core","type":["number","string"],"required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Approval Target Thread ID","help":"Optional thread/topic target for channels that support threaded delivery of forwarded approvals. Use this to keep approval traffic contained in operational threads instead of main channels.","hasChildren":false}
 {"recordType":"path","path":"approvals.exec.targets.*.to","kind":"core","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Approval Target Destination","help":"Destination identifier inside the target channel (channel ID, user ID, or thread root depending on provider). Verify semantics per provider because destination format differs across channel integrations.","hasChildren":false}
-{"recordType":"path","path":"approvals.plugin","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Plugin Approval Forwarding","help":"Groups plugin-approval forwarding behavior including enablement, routing mode, filters, and explicit targets. Independent of exec approval forwarding. Configure here when plugin approval prompts must reach operational channels.","hasChildren":true}
-{"recordType":"path","path":"approvals.plugin.agentFilter","kind":"core","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Plugin Approval Agent Filter","help":"Optional allowlist of agent IDs eligible for forwarded plugin approvals, for example `[\"primary\", \"ops-agent\"]`. Use this to limit forwarding blast radius.","hasChildren":true}
-{"recordType":"path","path":"approvals.plugin.agentFilter.*","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"approvals.plugin.enabled","kind":"core","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Forward Plugin Approvals","help":"Enables forwarding of plugin approval requests to configured delivery destinations (default: false). Independent of approvals.exec.enabled.","hasChildren":false}
-{"recordType":"path","path":"approvals.plugin.mode","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Plugin Approval Forwarding Mode","help":"Controls where plugin approval prompts are sent: \"session\" uses origin chat, \"targets\" uses configured targets, and \"both\" sends to both paths.","hasChildren":false}
-{"recordType":"path","path":"approvals.plugin.sessionFilter","kind":"core","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":["storage"],"label":"Plugin Approval Session Filter","help":"Optional session-key filters matched as substring or regex-style patterns, for example `[\"discord:\", \"^agent:ops:\"]`. Use narrow patterns so only intended approval contexts are forwarded.","hasChildren":true}
-{"recordType":"path","path":"approvals.plugin.sessionFilter.*","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"approvals.plugin.targets","kind":"core","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Plugin Approval Forwarding Targets","help":"Explicit delivery targets used when plugin approval forwarding mode includes targets, each with channel and destination details.","hasChildren":true}
-{"recordType":"path","path":"approvals.plugin.targets.*","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
-{"recordType":"path","path":"approvals.plugin.targets.*.accountId","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Plugin Approval Target Account ID","help":"Optional account selector for multi-account channel setups when plugin approvals must route through a specific account context.","hasChildren":false}
-{"recordType":"path","path":"approvals.plugin.targets.*.channel","kind":"core","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Plugin Approval Target Channel","help":"Channel/provider ID used for forwarded plugin approval delivery, such as discord, slack, or a plugin channel id.","hasChildren":false}
-{"recordType":"path","path":"approvals.plugin.targets.*.threadId","kind":"core","type":["number","string"],"required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Plugin Approval Target Thread ID","help":"Optional thread/topic target for channels that support threaded delivery of forwarded plugin approvals.","hasChildren":false}
-{"recordType":"path","path":"approvals.plugin.targets.*.to","kind":"core","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Plugin Approval Target Destination","help":"Destination identifier inside the target channel (channel ID, user ID, or thread root depending on provider).","hasChildren":false}
 {"recordType":"path","path":"audio","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Audio","help":"Global audio ingestion settings used before higher-level tools process speech or media content. Configure this when you need deterministic transcription behavior for voice notes and clips.","hasChildren":true}
 {"recordType":"path","path":"audio.transcription","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["media"],"label":"Audio Transcription","help":"Command-based transcription settings for converting audio files into text before agent handling. Keep a simple, deterministic command path here so failures are easy to diagnose in logs.","hasChildren":true}
 {"recordType":"path","path":"audio.transcription.command","kind":"core","type":"array","required":true,"deprecated":false,"sensitive":false,"tags":["media"],"label":"Audio Transcription Command","help":"Executable + args used to transcribe audio (first token must be a safe binary/path), for example `[\"whisper-cli\", \"--model\", \"small\", \"{input}\"]`. Prefer a pinned command so runtime environments behave consistently.","hasChildren":true}
@@ -747,7 +734,7 @@
 {"recordType":"path","path":"canvasHost.liveReload","kind":"core","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["reliability"],"label":"Canvas Host Live Reload","help":"Enables automatic live-reload behavior for canvas assets during development workflows. Keep disabled in production-like environments where deterministic output is preferred.","hasChildren":false}
 {"recordType":"path","path":"canvasHost.port","kind":"core","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Canvas Host Port","help":"TCP port used by the canvas host HTTP server when canvas hosting is enabled. Choose a non-conflicting port and align firewall/proxy policy accordingly.","hasChildren":false}
 {"recordType":"path","path":"canvasHost.root","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Canvas Host Root Directory","help":"Filesystem root directory served by canvas host for canvas content and static assets. Use a dedicated directory and avoid broad repo roots for least-privilege file exposure.","hasChildren":false}
-{"recordType":"path","path":"channels","kind":"core","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Channels","help":"Channel provider configurations plus shared defaults that control access policies, heartbeat visibility, and per-surface behavior. Keep defaults centralized and override per provider only where required.","hasChildren":true}
+{"recordType":"path","path":"channels","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Channels","help":"Channel provider configurations plus shared defaults that control access policies, heartbeat visibility, and per-surface behavior. Keep defaults centralized and override per provider only where required.","hasChildren":true}
 {"recordType":"path","path":"channels.bluebubbles","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["channels","network"],"label":"BlueBubbles","help":"iMessage via the BlueBubbles mac app + REST API.","hasChildren":true}
 {"recordType":"path","path":"channels.bluebubbles.accounts","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.bluebubbles.accounts.*","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
@@ -759,7 +746,6 @@
 {"recordType":"path","path":"channels.bluebubbles.accounts.*.dmHistoryLimit","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.bluebubbles.accounts.*.dmPolicy","kind":"channel","type":"string","required":false,"enumValues":["pairing","allowlist","open","disabled"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.bluebubbles.accounts.*.enabled","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.bluebubbles.accounts.*.enrichGroupParticipantsFromContacts","kind":"channel","type":"boolean","required":true,"defaultValue":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.bluebubbles.accounts.*.groupAllowFrom","kind":"channel","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.bluebubbles.accounts.*.groupAllowFrom.*","kind":"channel","type":["number","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.bluebubbles.accounts.*.groupPolicy","kind":"channel","type":"string","required":false,"enumValues":["open","disabled","allowlist"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -809,7 +795,6 @@
 {"recordType":"path","path":"channels.bluebubbles.dmHistoryLimit","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.bluebubbles.dmPolicy","kind":"channel","type":"string","required":false,"enumValues":["pairing","allowlist","open","disabled"],"deprecated":false,"sensitive":false,"tags":["access","channels","network"],"label":"BlueBubbles DM Policy","help":"Direct message access control (\"pairing\" recommended). \"open\" requires channels.bluebubbles.allowFrom=[\"*\"].","hasChildren":false}
 {"recordType":"path","path":"channels.bluebubbles.enabled","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.bluebubbles.enrichGroupParticipantsFromContacts","kind":"channel","type":"boolean","required":true,"defaultValue":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.bluebubbles.groupAllowFrom","kind":"channel","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.bluebubbles.groupAllowFrom.*","kind":"channel","type":["number","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.bluebubbles.groupPolicy","kind":"channel","type":"string","required":false,"enumValues":["open","disabled","allowlist"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -1042,8 +1027,47 @@
 {"recordType":"path","path":"channels.discord.accounts.*.voice.enabled","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.accounts.*.voice.tts","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.discord.accounts.*.voice.tts.auto","kind":"channel","type":"string","required":false,"enumValues":["off","always","inbound","tagged"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.edge","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.edge.enabled","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.edge.lang","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.edge.outputFormat","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.edge.pitch","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.edge.proxy","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.edge.rate","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.edge.saveSubtitles","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.edge.timeoutMs","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.edge.voice","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.edge.volume","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.elevenlabs","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.elevenlabs.apiKey","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","media","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.elevenlabs.apiKey.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.elevenlabs.apiKey.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.elevenlabs.apiKey.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.elevenlabs.applyTextNormalization","kind":"channel","type":"string","required":false,"enumValues":["auto","on","off"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.elevenlabs.baseUrl","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.elevenlabs.languageCode","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.elevenlabs.modelId","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.elevenlabs.seed","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.elevenlabs.voiceId","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.elevenlabs.voiceSettings","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.elevenlabs.voiceSettings.similarityBoost","kind":"channel","type":"number","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.elevenlabs.voiceSettings.speed","kind":"channel","type":"number","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.elevenlabs.voiceSettings.stability","kind":"channel","type":"number","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.elevenlabs.voiceSettings.style","kind":"channel","type":"number","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.elevenlabs.voiceSettings.useSpeakerBoost","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.accounts.*.voice.tts.enabled","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.accounts.*.voice.tts.maxTextLength","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.microsoft","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.microsoft.enabled","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.microsoft.lang","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.microsoft.outputFormat","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.microsoft.pitch","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.microsoft.proxy","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.microsoft.rate","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.microsoft.saveSubtitles","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.microsoft.timeoutMs","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.microsoft.voice","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.microsoft.volume","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.accounts.*.voice.tts.mode","kind":"channel","type":"string","required":false,"enumValues":["final","all"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.accounts.*.voice.tts.modelOverrides","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.discord.accounts.*.voice.tts.modelOverrides.allowModelId","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -1054,16 +1078,18 @@
 {"recordType":"path","path":"channels.discord.accounts.*.voice.tts.modelOverrides.allowVoice","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.accounts.*.voice.tts.modelOverrides.allowVoiceSettings","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.accounts.*.voice.tts.modelOverrides.enabled","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.openai","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.openai.apiKey","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","media","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.openai.apiKey.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.openai.apiKey.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.openai.apiKey.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.openai.baseUrl","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.openai.instructions","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.openai.model","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.openai.speed","kind":"channel","type":"number","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.openai.voice","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.accounts.*.voice.tts.prefsPath","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.accounts.*.voice.tts.provider","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.providers","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
-{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.providers.*","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
-{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.providers.*.*","kind":"channel","type":["array","boolean","null","number","object","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
-{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.providers.*.*.*","kind":"channel","type":[],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.providers.*.apiKey","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","media","network","security"],"hasChildren":true}
-{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.providers.*.apiKey.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.providers.*.apiKey.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.discord.accounts.*.voice.tts.providers.*.apiKey.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.accounts.*.voice.tts.summaryModel","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.accounts.*.voice.tts.timeoutMs","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.ackReaction","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -1268,8 +1294,47 @@
 {"recordType":"path","path":"channels.discord.voice.enabled","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["channels","network"],"label":"Discord Voice Enabled","help":"Enable Discord voice channel conversations (default: true). Omit channels.discord.voice to keep voice support disabled for the account.","hasChildren":false}
 {"recordType":"path","path":"channels.discord.voice.tts","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["channels","media","network"],"label":"Discord Voice Text-to-Speech","help":"Optional TTS overrides for Discord voice playback (merged with messages.tts).","hasChildren":true}
 {"recordType":"path","path":"channels.discord.voice.tts.auto","kind":"channel","type":"string","required":false,"enumValues":["off","always","inbound","tagged"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.edge","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
+{"recordType":"path","path":"channels.discord.voice.tts.edge.enabled","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.edge.lang","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.edge.outputFormat","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.edge.pitch","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.edge.proxy","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.edge.rate","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.edge.saveSubtitles","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.edge.timeoutMs","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.edge.voice","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.edge.volume","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.elevenlabs","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
+{"recordType":"path","path":"channels.discord.voice.tts.elevenlabs.apiKey","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","media","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.discord.voice.tts.elevenlabs.apiKey.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.elevenlabs.apiKey.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.elevenlabs.apiKey.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.elevenlabs.applyTextNormalization","kind":"channel","type":"string","required":false,"enumValues":["auto","on","off"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.elevenlabs.baseUrl","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.elevenlabs.languageCode","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.elevenlabs.modelId","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.elevenlabs.seed","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.elevenlabs.voiceId","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.elevenlabs.voiceSettings","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
+{"recordType":"path","path":"channels.discord.voice.tts.elevenlabs.voiceSettings.similarityBoost","kind":"channel","type":"number","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.elevenlabs.voiceSettings.speed","kind":"channel","type":"number","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.elevenlabs.voiceSettings.stability","kind":"channel","type":"number","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.elevenlabs.voiceSettings.style","kind":"channel","type":"number","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.elevenlabs.voiceSettings.useSpeakerBoost","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.voice.tts.enabled","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.voice.tts.maxTextLength","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.microsoft","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
+{"recordType":"path","path":"channels.discord.voice.tts.microsoft.enabled","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.microsoft.lang","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.microsoft.outputFormat","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.microsoft.pitch","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.microsoft.proxy","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.microsoft.rate","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.microsoft.saveSubtitles","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.microsoft.timeoutMs","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.microsoft.voice","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.microsoft.volume","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.voice.tts.mode","kind":"channel","type":"string","required":false,"enumValues":["final","all"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.voice.tts.modelOverrides","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.discord.voice.tts.modelOverrides.allowModelId","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -1280,16 +1345,18 @@
 {"recordType":"path","path":"channels.discord.voice.tts.modelOverrides.allowVoice","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.voice.tts.modelOverrides.allowVoiceSettings","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.voice.tts.modelOverrides.enabled","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.openai","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
+{"recordType":"path","path":"channels.discord.voice.tts.openai.apiKey","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","media","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.discord.voice.tts.openai.apiKey.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.openai.apiKey.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.openai.apiKey.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.openai.baseUrl","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.openai.instructions","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.openai.model","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.openai.speed","kind":"channel","type":"number","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.discord.voice.tts.openai.voice","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.voice.tts.prefsPath","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.voice.tts.provider","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.discord.voice.tts.providers","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
-{"recordType":"path","path":"channels.discord.voice.tts.providers.*","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
-{"recordType":"path","path":"channels.discord.voice.tts.providers.*.*","kind":"channel","type":["array","boolean","null","number","object","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
-{"recordType":"path","path":"channels.discord.voice.tts.providers.*.*.*","kind":"channel","type":[],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.discord.voice.tts.providers.*.apiKey","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","media","network","security"],"hasChildren":true}
-{"recordType":"path","path":"channels.discord.voice.tts.providers.*.apiKey.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.discord.voice.tts.providers.*.apiKey.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.discord.voice.tts.providers.*.apiKey.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.voice.tts.summaryModel","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.discord.voice.tts.timeoutMs","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["channels","network"],"label":"Feishu","help":"飞书/Lark enterprise messaging with doc/wiki/drive tools.","hasChildren":true}
@@ -1300,7 +1367,7 @@
 {"recordType":"path","path":"channels.feishu.accounts.*.allowFrom","kind":"channel","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.feishu.accounts.*.allowFrom.*","kind":"channel","type":["number","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.accounts.*.appId","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.feishu.accounts.*.appSecret","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.feishu.accounts.*.appSecret","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.feishu.accounts.*.appSecret.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.accounts.*.appSecret.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.accounts.*.appSecret.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -1321,7 +1388,7 @@
 {"recordType":"path","path":"channels.feishu.accounts.*.dms.*.systemPrompt","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.accounts.*.domain","kind":"channel","type":"string","required":false,"enumValues":["feishu","lark"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.accounts.*.enabled","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.feishu.accounts.*.encryptKey","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["channels","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.feishu.accounts.*.encryptKey","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.feishu.accounts.*.encryptKey.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.accounts.*.encryptKey.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.accounts.*.encryptKey.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -1374,7 +1441,7 @@
 {"recordType":"path","path":"channels.feishu.accounts.*.tools.wiki","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.accounts.*.topicSessionMode","kind":"channel","type":"string","required":false,"enumValues":["disabled","enabled"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.accounts.*.typingIndicator","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.feishu.accounts.*.verificationToken","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.feishu.accounts.*.verificationToken","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.feishu.accounts.*.verificationToken.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.accounts.*.verificationToken.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.accounts.*.verificationToken.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -1386,7 +1453,7 @@
 {"recordType":"path","path":"channels.feishu.allowFrom","kind":"channel","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.feishu.allowFrom.*","kind":"channel","type":["number","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.appId","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.feishu.appSecret","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.feishu.appSecret","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.feishu.appSecret.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.appSecret.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.appSecret.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -1413,7 +1480,7 @@
 {"recordType":"path","path":"channels.feishu.dynamicAgentCreation.maxAgents","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.dynamicAgentCreation.workspaceTemplate","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.enabled","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.feishu.encryptKey","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["channels","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.feishu.encryptKey","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.feishu.encryptKey.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.encryptKey.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.encryptKey.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -1465,7 +1532,7 @@
 {"recordType":"path","path":"channels.feishu.tools.wiki","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.topicSessionMode","kind":"channel","type":"string","required":false,"enumValues":["disabled","enabled"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.typingIndicator","kind":"channel","type":"boolean","required":true,"defaultValue":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.feishu.verificationToken","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.feishu.verificationToken","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.feishu.verificationToken.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.verificationToken.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.feishu.verificationToken.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -1873,8 +1940,8 @@
 {"recordType":"path","path":"channels.line.accounts.*","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.line.accounts.*.allowFrom","kind":"channel","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.line.accounts.*.allowFrom.*","kind":"channel","type":["number","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.line.accounts.*.channelAccessToken","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":true,"tags":["access","auth","channels","network","security"],"hasChildren":false}
-{"recordType":"path","path":"channels.line.accounts.*.channelSecret","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security"],"hasChildren":false}
+{"recordType":"path","path":"channels.line.accounts.*.channelAccessToken","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.line.accounts.*.channelSecret","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.line.accounts.*.dmPolicy","kind":"channel","type":"string","required":true,"enumValues":["open","allowlist","pairing","disabled"],"defaultValue":"pairing","deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.line.accounts.*.enabled","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.line.accounts.*.groupAllowFrom","kind":"channel","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
@@ -1892,13 +1959,13 @@
 {"recordType":"path","path":"channels.line.accounts.*.mediaMaxMb","kind":"channel","type":"number","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.line.accounts.*.name","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.line.accounts.*.responsePrefix","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.line.accounts.*.secretFile","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security","storage"],"hasChildren":false}
+{"recordType":"path","path":"channels.line.accounts.*.secretFile","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.line.accounts.*.tokenFile","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.line.accounts.*.webhookPath","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.line.allowFrom","kind":"channel","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.line.allowFrom.*","kind":"channel","type":["number","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.line.channelAccessToken","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":true,"tags":["access","auth","channels","network","security"],"hasChildren":false}
-{"recordType":"path","path":"channels.line.channelSecret","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security"],"hasChildren":false}
+{"recordType":"path","path":"channels.line.channelAccessToken","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.line.channelSecret","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.line.defaultAccount","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.line.dmPolicy","kind":"channel","type":"string","required":true,"enumValues":["open","allowlist","pairing","disabled"],"defaultValue":"pairing","deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.line.enabled","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -1917,11 +1984,11 @@
 {"recordType":"path","path":"channels.line.mediaMaxMb","kind":"channel","type":"number","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.line.name","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.line.responsePrefix","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.line.secretFile","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security","storage"],"hasChildren":false}
+{"recordType":"path","path":"channels.line.secretFile","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.line.tokenFile","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.line.webhookPath","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.matrix","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["channels","network"],"label":"Matrix","help":"open protocol; install the plugin to enable.","hasChildren":true}
-{"recordType":"path","path":"channels.matrix.accessToken","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":true,"tags":["access","auth","channels","network","security"],"hasChildren":false}
+{"recordType":"path","path":"channels.matrix.accessToken","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.matrix.accounts","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.matrix.accounts.*","kind":"channel","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.matrix.ackReaction","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -1934,7 +2001,7 @@
 {"recordType":"path","path":"channels.matrix.actions.profile","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.matrix.actions.reactions","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.matrix.actions.verification","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.matrix.allowBots","kind":"channel","type":["boolean","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.matrix.allowBots","kind":"channel","type":["boolean","string"],"required":false,"deprecated":false,"sensitive":false,"tags":["access","channels","network"],"label":"Matrix Allow Bot Messages","help":"Allow messages from other configured Matrix bot accounts to trigger replies (default: false). Set \"mentions\" to only accept bot messages that visibly mention this bot.","hasChildren":false}
 {"recordType":"path","path":"channels.matrix.allowlistOnly","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.matrix.allowPrivateNetwork","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.matrix.autoJoin","kind":"channel","type":"string","required":false,"enumValues":["always","allowlist","off"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -1980,7 +2047,7 @@
 {"recordType":"path","path":"channels.matrix.markdown.tables","kind":"channel","type":"string","required":false,"enumValues":["off","bullets","code"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.matrix.mediaMaxMb","kind":"channel","type":"number","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.matrix.name","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.matrix.password","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.matrix.password","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.matrix.password.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.matrix.password.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.matrix.password.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -2024,14 +2091,13 @@
 {"recordType":"path","path":"channels.mattermost.accounts.*.actions.reactions","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.accounts.*.allowFrom","kind":"channel","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.mattermost.accounts.*.allowFrom.*","kind":"channel","type":["number","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.mattermost.accounts.*.allowPrivateNetwork","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.accounts.*.baseUrl","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.accounts.*.blockStreaming","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.accounts.*.blockStreamingCoalesce","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.mattermost.accounts.*.blockStreamingCoalesce.idleMs","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.accounts.*.blockStreamingCoalesce.maxChars","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.accounts.*.blockStreamingCoalesce.minChars","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.mattermost.accounts.*.botToken","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.mattermost.accounts.*.botToken","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.mattermost.accounts.*.botToken.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.accounts.*.botToken.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.accounts.*.botToken.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -2073,27 +2139,26 @@
 {"recordType":"path","path":"channels.mattermost.actions.reactions","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.allowFrom","kind":"channel","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.mattermost.allowFrom.*","kind":"channel","type":["number","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.mattermost.allowPrivateNetwork","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.mattermost.baseUrl","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.mattermost.baseUrl","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":["channels","network"],"label":"Mattermost Base URL","help":"Base URL for your Mattermost server (e.g., https://chat.example.com).","hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.blockStreaming","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.blockStreamingCoalesce","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.mattermost.blockStreamingCoalesce.idleMs","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.blockStreamingCoalesce.maxChars","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.blockStreamingCoalesce.minChars","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.mattermost.botToken","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.mattermost.botToken","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security"],"label":"Mattermost Bot Token","help":"Bot token from Mattermost System Console -> Integrations -> Bot Accounts.","hasChildren":true}
 {"recordType":"path","path":"channels.mattermost.botToken.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.botToken.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.botToken.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.capabilities","kind":"channel","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.mattermost.capabilities.*","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.mattermost.chatmode","kind":"channel","type":"string","required":false,"enumValues":["oncall","onmessage","onchar"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.mattermost.chatmode","kind":"channel","type":"string","required":false,"enumValues":["oncall","onmessage","onchar"],"deprecated":false,"sensitive":false,"tags":["channels","network"],"label":"Mattermost Chat Mode","help":"Reply to channel messages on mention (\"oncall\"), on trigger chars (\">\" or \"!\") (\"onchar\"), or on every message (\"onmessage\").","hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.chunkMode","kind":"channel","type":"string","required":false,"enumValues":["length","newline"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.commands","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.mattermost.commands.callbackPath","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.commands.callbackUrl","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.commands.native","kind":"channel","type":["boolean","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.commands.nativeSkills","kind":"channel","type":["boolean","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.mattermost.configWrites","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.mattermost.configWrites","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["channels","network"],"label":"Mattermost Config Writes","help":"Allow Mattermost to write config in response to channel events/commands (default: true).","hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.dangerouslyAllowNameMatching","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.defaultAccount","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.dmChannelRetry","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
@@ -2113,10 +2178,10 @@
 {"recordType":"path","path":"channels.mattermost.markdown","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.mattermost.markdown.tables","kind":"channel","type":"string","required":false,"enumValues":["off","bullets","code"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.name","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.mattermost.oncharPrefixes","kind":"channel","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
+{"recordType":"path","path":"channels.mattermost.oncharPrefixes","kind":"channel","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":["channels","network"],"label":"Mattermost Onchar Prefixes","help":"Trigger prefixes for onchar mode (default: [\">\", \"!\"]).","hasChildren":true}
 {"recordType":"path","path":"channels.mattermost.oncharPrefixes.*","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.replyToMode","kind":"channel","type":"string","required":false,"enumValues":["off","first","all"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.mattermost.requireMention","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"channels.mattermost.requireMention","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["channels","network"],"label":"Mattermost Require Mention","help":"Require @mention in channels before responding (default: true).","hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.responsePrefix","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.mattermost.textChunkLimit","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.msteams","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["channels","network"],"label":"Microsoft Teams","help":"Teams SDK; enterprise support.","hasChildren":true}
@@ -2143,13 +2208,9 @@
 {"recordType":"path","path":"channels.msteams.dms.*","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.msteams.dms.*.historyLimit","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.msteams.enabled","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.msteams.feedbackEnabled","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.msteams.feedbackReflection","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.msteams.feedbackReflectionCooldownMs","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.msteams.groupAllowFrom","kind":"channel","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.msteams.groupAllowFrom.*","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.msteams.groupPolicy","kind":"channel","type":"string","required":true,"enumValues":["open","disabled","allowlist"],"defaultValue":"allowlist","deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.msteams.groupWelcomeCard","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.msteams.healthMonitor","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.msteams.healthMonitor.enabled","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.msteams.heartbeat","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
@@ -2164,8 +2225,6 @@
 {"recordType":"path","path":"channels.msteams.mediaAuthAllowHosts","kind":"channel","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.msteams.mediaAuthAllowHosts.*","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.msteams.mediaMaxMb","kind":"channel","type":"number","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.msteams.promptStarters","kind":"channel","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
-{"recordType":"path","path":"channels.msteams.promptStarters.*","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.msteams.replyStyle","kind":"channel","type":"string","required":false,"enumValues":["thread","top-level"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.msteams.requireMention","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.msteams.responsePrefix","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -2213,14 +2272,12 @@
 {"recordType":"path","path":"channels.msteams.webhook","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.msteams.webhook.path","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.msteams.webhook.port","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.msteams.welcomeCard","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["channels","network"],"label":"Nextcloud Talk","help":"Self-hosted chat via Nextcloud Talk webhook bots.","hasChildren":true}
 {"recordType":"path","path":"channels.nextcloud-talk.accounts","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.nextcloud-talk.accounts.*","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.nextcloud-talk.accounts.*.allowFrom","kind":"channel","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.nextcloud-talk.accounts.*.allowFrom.*","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.nextcloud-talk.accounts.*.allowPrivateNetwork","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.nextcloud-talk.accounts.*.apiPassword","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.nextcloud-talk.accounts.*.apiPassword","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.nextcloud-talk.accounts.*.apiPassword.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk.accounts.*.apiPassword.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk.accounts.*.apiPassword.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -2232,11 +2289,11 @@
 {"recordType":"path","path":"channels.nextcloud-talk.accounts.*.blockStreamingCoalesce.idleMs","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk.accounts.*.blockStreamingCoalesce.maxChars","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk.accounts.*.blockStreamingCoalesce.minChars","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.nextcloud-talk.accounts.*.botSecret","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.nextcloud-talk.accounts.*.botSecret","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.nextcloud-talk.accounts.*.botSecret.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk.accounts.*.botSecret.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk.accounts.*.botSecret.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.nextcloud-talk.accounts.*.botSecretFile","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security","storage"],"hasChildren":false}
+{"recordType":"path","path":"channels.nextcloud-talk.accounts.*.botSecretFile","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk.accounts.*.chunkMode","kind":"channel","type":"string","required":false,"enumValues":["length","newline"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk.accounts.*.dmHistoryLimit","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk.accounts.*.dmPolicy","kind":"channel","type":"string","required":true,"enumValues":["pairing","allowlist","open","disabled"],"defaultValue":"pairing","deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -2276,8 +2333,7 @@
 {"recordType":"path","path":"channels.nextcloud-talk.accounts.*.webhookPublicUrl","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk.allowFrom","kind":"channel","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.nextcloud-talk.allowFrom.*","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.nextcloud-talk.allowPrivateNetwork","kind":"channel","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.nextcloud-talk.apiPassword","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.nextcloud-talk.apiPassword","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.nextcloud-talk.apiPassword.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk.apiPassword.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk.apiPassword.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -2289,11 +2345,11 @@
 {"recordType":"path","path":"channels.nextcloud-talk.blockStreamingCoalesce.idleMs","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk.blockStreamingCoalesce.maxChars","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk.blockStreamingCoalesce.minChars","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.nextcloud-talk.botSecret","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.nextcloud-talk.botSecret","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.nextcloud-talk.botSecret.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk.botSecret.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk.botSecret.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.nextcloud-talk.botSecretFile","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security","storage"],"hasChildren":false}
+{"recordType":"path","path":"channels.nextcloud-talk.botSecretFile","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk.chunkMode","kind":"channel","type":"string","required":false,"enumValues":["length","newline"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk.defaultAccount","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.nextcloud-talk.dmHistoryLimit","kind":"channel","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -3337,7 +3393,7 @@
 {"recordType":"path","path":"channels.zalo.accounts.*","kind":"channel","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.zalo.accounts.*.allowFrom","kind":"channel","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.zalo.accounts.*.allowFrom.*","kind":"channel","type":["number","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.zalo.accounts.*.botToken","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.zalo.accounts.*.botToken","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.zalo.accounts.*.botToken.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.zalo.accounts.*.botToken.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.zalo.accounts.*.botToken.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -3354,14 +3410,14 @@
 {"recordType":"path","path":"channels.zalo.accounts.*.responsePrefix","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.zalo.accounts.*.tokenFile","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.zalo.accounts.*.webhookPath","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.zalo.accounts.*.webhookSecret","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.zalo.accounts.*.webhookSecret","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.zalo.accounts.*.webhookSecret.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.zalo.accounts.*.webhookSecret.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.zalo.accounts.*.webhookSecret.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.zalo.accounts.*.webhookUrl","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.zalo.allowFrom","kind":"channel","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.zalo.allowFrom.*","kind":"channel","type":["number","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.zalo.botToken","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.zalo.botToken","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.zalo.botToken.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.zalo.botToken.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.zalo.botToken.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -3379,7 +3435,7 @@
 {"recordType":"path","path":"channels.zalo.responsePrefix","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.zalo.tokenFile","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.zalo.webhookPath","kind":"channel","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"channels.zalo.webhookSecret","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","channels","network","security"],"hasChildren":true}
+{"recordType":"path","path":"channels.zalo.webhookSecret","kind":"channel","type":["object","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"channels.zalo.webhookSecret.id","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.zalo.webhookSecret.provider","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"channels.zalo.webhookSecret.source","kind":"channel","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -3877,8 +3933,47 @@
 {"recordType":"path","path":"messages.suppressToolErrors","kind":"core","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Suppress Tool Error Warnings","help":"When true, suppress ⚠️ tool-error warnings from being shown to the user. The agent already sees errors in context and can retry. Default: false.","hasChildren":false}
 {"recordType":"path","path":"messages.tts","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["media"],"label":"Message Text-to-Speech","help":"Text-to-speech policy for reading agent replies aloud on supported voice or audio surfaces. Keep disabled unless voice playback is part of your operator/user workflow.","hasChildren":true}
 {"recordType":"path","path":"messages.tts.auto","kind":"core","type":"string","required":false,"enumValues":["off","always","inbound","tagged"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.edge","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
+{"recordType":"path","path":"messages.tts.edge.enabled","kind":"core","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.edge.lang","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.edge.outputFormat","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.edge.pitch","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.edge.proxy","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.edge.rate","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.edge.saveSubtitles","kind":"core","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.edge.timeoutMs","kind":"core","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.edge.voice","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.edge.volume","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.elevenlabs","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
+{"recordType":"path","path":"messages.tts.elevenlabs.apiKey","kind":"core","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","media","security"],"hasChildren":true}
+{"recordType":"path","path":"messages.tts.elevenlabs.apiKey.id","kind":"core","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.elevenlabs.apiKey.provider","kind":"core","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.elevenlabs.apiKey.source","kind":"core","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.elevenlabs.applyTextNormalization","kind":"core","type":"string","required":false,"enumValues":["auto","on","off"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.elevenlabs.baseUrl","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.elevenlabs.languageCode","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.elevenlabs.modelId","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.elevenlabs.seed","kind":"core","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.elevenlabs.voiceId","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.elevenlabs.voiceSettings","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
+{"recordType":"path","path":"messages.tts.elevenlabs.voiceSettings.similarityBoost","kind":"core","type":"number","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.elevenlabs.voiceSettings.speed","kind":"core","type":"number","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.elevenlabs.voiceSettings.stability","kind":"core","type":"number","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.elevenlabs.voiceSettings.style","kind":"core","type":"number","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.elevenlabs.voiceSettings.useSpeakerBoost","kind":"core","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"messages.tts.enabled","kind":"core","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"messages.tts.maxTextLength","kind":"core","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.microsoft","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
+{"recordType":"path","path":"messages.tts.microsoft.enabled","kind":"core","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.microsoft.lang","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.microsoft.outputFormat","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.microsoft.pitch","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.microsoft.proxy","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.microsoft.rate","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.microsoft.saveSubtitles","kind":"core","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.microsoft.timeoutMs","kind":"core","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.microsoft.voice","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.microsoft.volume","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"messages.tts.mode","kind":"core","type":"string","required":false,"enumValues":["final","all"],"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"messages.tts.modelOverrides","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"messages.tts.modelOverrides.allowModelId","kind":"core","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -3889,16 +3984,18 @@
 {"recordType":"path","path":"messages.tts.modelOverrides.allowVoice","kind":"core","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"messages.tts.modelOverrides.allowVoiceSettings","kind":"core","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"messages.tts.modelOverrides.enabled","kind":"core","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.openai","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
+{"recordType":"path","path":"messages.tts.openai.apiKey","kind":"core","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","media","security"],"hasChildren":true}
+{"recordType":"path","path":"messages.tts.openai.apiKey.id","kind":"core","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.openai.apiKey.provider","kind":"core","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.openai.apiKey.source","kind":"core","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.openai.baseUrl","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.openai.instructions","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.openai.model","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.openai.speed","kind":"core","type":"number","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"messages.tts.openai.voice","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"messages.tts.prefsPath","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"messages.tts.provider","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"messages.tts.providers","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["media"],"label":"TTS Provider Settings","help":"Provider-specific TTS settings keyed by speech provider id. Use this instead of bundled provider-specific top-level keys so speech plugins stay decoupled from core config schema.","hasChildren":true}
-{"recordType":"path","path":"messages.tts.providers.*","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["media"],"label":"TTS Provider Config","help":"Provider-specific TTS configuration for one speech provider id. Keep fields scoped to the plugin that owns that provider.","hasChildren":true}
-{"recordType":"path","path":"messages.tts.providers.*.*","kind":"core","type":["array","boolean","null","number","object","string"],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
-{"recordType":"path","path":"messages.tts.providers.*.*.*","kind":"core","type":[],"required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"messages.tts.providers.*.apiKey","kind":"core","type":["object","string"],"required":false,"deprecated":false,"sensitive":true,"tags":["auth","media","security"],"label":"TTS Provider API Key","help":"Provider API key used by that speech provider when its plugin requires authenticated TTS access.","hasChildren":true}
-{"recordType":"path","path":"messages.tts.providers.*.apiKey.id","kind":"core","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"messages.tts.providers.*.apiKey.provider","kind":"core","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"messages.tts.providers.*.apiKey.source","kind":"core","type":"string","required":true,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"messages.tts.summaryModel","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"messages.tts.timeoutMs","kind":"core","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"meta","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Metadata","help":"Metadata fields automatically maintained by OpenClaw to record write/version history for this config file. Keep these values system-managed and avoid manual edits unless debugging migration history.","hasChildren":true}
@@ -4049,15 +4146,6 @@
 {"recordType":"path","path":"plugins.entries.brave.subagent.allowedModels","kind":"plugin","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Plugin Subagent Allowed Models","help":"Allowed override targets for trusted plugin subagent runs as canonical \"provider/model\" refs. Use \"*\" only when you intentionally allow any model.","hasChildren":true}
 {"recordType":"path","path":"plugins.entries.brave.subagent.allowedModels.*","kind":"plugin","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"plugins.entries.brave.subagent.allowModelOverride","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Allow Plugin Subagent Model Override","help":"Explicitly allows this plugin to request provider/model overrides in background subagent runs. Keep false unless the plugin is trusted to steer model selection.","hasChildren":false}
-{"recordType":"path","path":"plugins.entries.browser","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"@openclaw/browser-plugin","help":"OpenClaw browser tool plugin (plugin: browser)","hasChildren":true}
-{"recordType":"path","path":"plugins.entries.browser.config","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"@openclaw/browser-plugin Config","help":"Plugin-defined config payload for browser.","hasChildren":false}
-{"recordType":"path","path":"plugins.entries.browser.enabled","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Enable @openclaw/browser-plugin","hasChildren":false}
-{"recordType":"path","path":"plugins.entries.browser.hooks","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Plugin Hook Policy","help":"Per-plugin typed hook policy controls for core-enforced safety gates. Use this to constrain high-impact hook categories without disabling the entire plugin.","hasChildren":true}
-{"recordType":"path","path":"plugins.entries.browser.hooks.allowPromptInjection","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Allow Prompt Injection Hooks","help":"Controls whether this plugin may mutate prompts through typed hooks. Set false to block `before_prompt_build` and ignore prompt-mutating fields from legacy `before_agent_start`, while preserving legacy `modelOverride` and `providerOverride` behavior.","hasChildren":false}
-{"recordType":"path","path":"plugins.entries.browser.subagent","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Plugin Subagent Policy","help":"Per-plugin subagent runtime controls for model override trust and allowlists. Keep this unset unless a plugin must explicitly steer subagent model selection.","hasChildren":true}
-{"recordType":"path","path":"plugins.entries.browser.subagent.allowedModels","kind":"plugin","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Plugin Subagent Allowed Models","help":"Allowed override targets for trusted plugin subagent runs as canonical \"provider/model\" refs. Use \"*\" only when you intentionally allow any model.","hasChildren":true}
-{"recordType":"path","path":"plugins.entries.browser.subagent.allowedModels.*","kind":"plugin","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"plugins.entries.browser.subagent.allowModelOverride","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Allow Plugin Subagent Model Override","help":"Explicitly allows this plugin to request provider/model overrides in background subagent runs. Keep false unless the plugin is trusted to steer model selection.","hasChildren":false}
 {"recordType":"path","path":"plugins.entries.byteplus","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"@openclaw/byteplus-provider","help":"OpenClaw BytePlus provider plugin (plugin: byteplus)","hasChildren":true}
 {"recordType":"path","path":"plugins.entries.byteplus.config","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"@openclaw/byteplus-provider Config","help":"Plugin-defined config payload for byteplus.","hasChildren":false}
 {"recordType":"path","path":"plugins.entries.byteplus.enabled","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Enable @openclaw/byteplus-provider","hasChildren":false}
@@ -4326,15 +4414,6 @@
 {"recordType":"path","path":"plugins.entries.line.subagent.allowedModels","kind":"plugin","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Plugin Subagent Allowed Models","help":"Allowed override targets for trusted plugin subagent runs as canonical \"provider/model\" refs. Use \"*\" only when you intentionally allow any model.","hasChildren":true}
 {"recordType":"path","path":"plugins.entries.line.subagent.allowedModels.*","kind":"plugin","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"plugins.entries.line.subagent.allowModelOverride","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Allow Plugin Subagent Model Override","help":"Explicitly allows this plugin to request provider/model overrides in background subagent runs. Keep false unless the plugin is trusted to steer model selection.","hasChildren":false}
-{"recordType":"path","path":"plugins.entries.litellm","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"@openclaw/litellm-provider","help":"OpenClaw LiteLLM provider plugin (plugin: litellm)","hasChildren":true}
-{"recordType":"path","path":"plugins.entries.litellm.config","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"@openclaw/litellm-provider Config","help":"Plugin-defined config payload for litellm.","hasChildren":false}
-{"recordType":"path","path":"plugins.entries.litellm.enabled","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Enable @openclaw/litellm-provider","hasChildren":false}
-{"recordType":"path","path":"plugins.entries.litellm.hooks","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Plugin Hook Policy","help":"Per-plugin typed hook policy controls for core-enforced safety gates. Use this to constrain high-impact hook categories without disabling the entire plugin.","hasChildren":true}
-{"recordType":"path","path":"plugins.entries.litellm.hooks.allowPromptInjection","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Allow Prompt Injection Hooks","help":"Controls whether this plugin may mutate prompts through typed hooks. Set false to block `before_prompt_build` and ignore prompt-mutating fields from legacy `before_agent_start`, while preserving legacy `modelOverride` and `providerOverride` behavior.","hasChildren":false}
-{"recordType":"path","path":"plugins.entries.litellm.subagent","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Plugin Subagent Policy","help":"Per-plugin subagent runtime controls for model override trust and allowlists. Keep this unset unless a plugin must explicitly steer subagent model selection.","hasChildren":true}
-{"recordType":"path","path":"plugins.entries.litellm.subagent.allowedModels","kind":"plugin","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Plugin Subagent Allowed Models","help":"Allowed override targets for trusted plugin subagent runs as canonical \"provider/model\" refs. Use \"*\" only when you intentionally allow any model.","hasChildren":true}
-{"recordType":"path","path":"plugins.entries.litellm.subagent.allowedModels.*","kind":"plugin","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"plugins.entries.litellm.subagent.allowModelOverride","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Allow Plugin Subagent Model Override","help":"Explicitly allows this plugin to request provider/model overrides in background subagent runs. Keep false unless the plugin is trusted to steer model selection.","hasChildren":false}
 {"recordType":"path","path":"plugins.entries.llm-task","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"LLM Task","help":"Generic JSON-only LLM tool for structured tasks callable from workflows. (plugin: llm-task)","hasChildren":true}
 {"recordType":"path","path":"plugins.entries.llm-task.config","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"LLM Task Config","help":"Plugin-defined config payload for llm-task.","hasChildren":true}
 {"recordType":"path","path":"plugins.entries.llm-task.config.allowedModels","kind":"plugin","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
@@ -4406,15 +4485,6 @@
 {"recordType":"path","path":"plugins.entries.memory-lancedb.subagent.allowedModels.*","kind":"plugin","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"plugins.entries.memory-lancedb.subagent.allowModelOverride","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Allow Plugin Subagent Model Override","help":"Explicitly allows this plugin to request provider/model overrides in background subagent runs. Keep false unless the plugin is trusted to steer model selection.","hasChildren":false}
 {"recordType":"path","path":"plugins.entries.microsoft","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"@openclaw/microsoft-speech","help":"OpenClaw Microsoft speech plugin (plugin: microsoft)","hasChildren":true}
-{"recordType":"path","path":"plugins.entries.microsoft-foundry","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"@openclaw/microsoft-foundry","help":"OpenClaw Microsoft Foundry provider plugin (plugin: microsoft-foundry)","hasChildren":true}
-{"recordType":"path","path":"plugins.entries.microsoft-foundry.config","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"@openclaw/microsoft-foundry Config","help":"Plugin-defined config payload for microsoft-foundry.","hasChildren":false}
-{"recordType":"path","path":"plugins.entries.microsoft-foundry.enabled","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Enable @openclaw/microsoft-foundry","hasChildren":false}
-{"recordType":"path","path":"plugins.entries.microsoft-foundry.hooks","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Plugin Hook Policy","help":"Per-plugin typed hook policy controls for core-enforced safety gates. Use this to constrain high-impact hook categories without disabling the entire plugin.","hasChildren":true}
-{"recordType":"path","path":"plugins.entries.microsoft-foundry.hooks.allowPromptInjection","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Allow Prompt Injection Hooks","help":"Controls whether this plugin may mutate prompts through typed hooks. Set false to block `before_prompt_build` and ignore prompt-mutating fields from legacy `before_agent_start`, while preserving legacy `modelOverride` and `providerOverride` behavior.","hasChildren":false}
-{"recordType":"path","path":"plugins.entries.microsoft-foundry.subagent","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Plugin Subagent Policy","help":"Per-plugin subagent runtime controls for model override trust and allowlists. Keep this unset unless a plugin must explicitly steer subagent model selection.","hasChildren":true}
-{"recordType":"path","path":"plugins.entries.microsoft-foundry.subagent.allowedModels","kind":"plugin","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Plugin Subagent Allowed Models","help":"Allowed override targets for trusted plugin subagent runs as canonical \"provider/model\" refs. Use \"*\" only when you intentionally allow any model.","hasChildren":true}
-{"recordType":"path","path":"plugins.entries.microsoft-foundry.subagent.allowedModels.*","kind":"plugin","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"plugins.entries.microsoft-foundry.subagent.allowModelOverride","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Allow Plugin Subagent Model Override","help":"Explicitly allows this plugin to request provider/model overrides in background subagent runs. Keep false unless the plugin is trusted to steer model selection.","hasChildren":false}
 {"recordType":"path","path":"plugins.entries.microsoft.config","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"@openclaw/microsoft-speech Config","help":"Plugin-defined config payload for microsoft.","hasChildren":false}
 {"recordType":"path","path":"plugins.entries.microsoft.enabled","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Enable @openclaw/microsoft-speech","hasChildren":false}
 {"recordType":"path","path":"plugins.entries.microsoft.hooks","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Plugin Hook Policy","help":"Per-plugin typed hook policy controls for core-enforced safety gates. Use this to constrain high-impact hook categories without disabling the entire plugin.","hasChildren":true}
@@ -4561,7 +4631,6 @@
 {"recordType":"path","path":"plugins.entries.openshell.config.gateway","kind":"plugin","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Gateway Name","help":"Optional OpenShell gateway name passed as --gateway.","hasChildren":false}
 {"recordType":"path","path":"plugins.entries.openshell.config.gatewayEndpoint","kind":"plugin","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Gateway Endpoint","help":"Optional OpenShell gateway endpoint passed as --gateway-endpoint.","hasChildren":false}
 {"recordType":"path","path":"plugins.entries.openshell.config.gpu","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"GPU","help":"Request GPU resources when creating the sandbox.","hasChildren":false}
-{"recordType":"path","path":"plugins.entries.openshell.config.mode","kind":"plugin","type":"string","required":false,"enumValues":["mirror","remote"],"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Mode","help":"Sandbox mode. Use mirror for the default local-workspace flow or remote for a fully remote workspace.","hasChildren":false}
 {"recordType":"path","path":"plugins.entries.openshell.config.policy","kind":"plugin","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Policy File","help":"Optional path to a custom OpenShell sandbox policy YAML.","hasChildren":false}
 {"recordType":"path","path":"plugins.entries.openshell.config.providers","kind":"plugin","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Providers","help":"Provider names to attach when a sandbox is created.","hasChildren":true}
 {"recordType":"path","path":"plugins.entries.openshell.config.providers.*","kind":"plugin","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -4606,6 +4675,15 @@
 {"recordType":"path","path":"plugins.entries.qianfan.subagent.allowedModels","kind":"plugin","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Plugin Subagent Allowed Models","help":"Allowed override targets for trusted plugin subagent runs as canonical \"provider/model\" refs. Use \"*\" only when you intentionally allow any model.","hasChildren":true}
 {"recordType":"path","path":"plugins.entries.qianfan.subagent.allowedModels.*","kind":"plugin","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"plugins.entries.qianfan.subagent.allowModelOverride","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Allow Plugin Subagent Model Override","help":"Explicitly allows this plugin to request provider/model overrides in background subagent runs. Keep false unless the plugin is trusted to steer model selection.","hasChildren":false}
+{"recordType":"path","path":"plugins.entries.qwen-portal-auth","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"qwen-portal-auth","help":"Plugin entry for qwen-portal-auth.","hasChildren":true}
+{"recordType":"path","path":"plugins.entries.qwen-portal-auth.config","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"qwen-portal-auth Config","help":"Plugin-defined config payload for qwen-portal-auth.","hasChildren":false}
+{"recordType":"path","path":"plugins.entries.qwen-portal-auth.enabled","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Enable qwen-portal-auth","hasChildren":false}
+{"recordType":"path","path":"plugins.entries.qwen-portal-auth.hooks","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Plugin Hook Policy","help":"Per-plugin typed hook policy controls for core-enforced safety gates. Use this to constrain high-impact hook categories without disabling the entire plugin.","hasChildren":true}
+{"recordType":"path","path":"plugins.entries.qwen-portal-auth.hooks.allowPromptInjection","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Allow Prompt Injection Hooks","help":"Controls whether this plugin may mutate prompts through typed hooks. Set false to block `before_prompt_build` and ignore prompt-mutating fields from legacy `before_agent_start`, while preserving legacy `modelOverride` and `providerOverride` behavior.","hasChildren":false}
+{"recordType":"path","path":"plugins.entries.qwen-portal-auth.subagent","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Plugin Subagent Policy","help":"Per-plugin subagent runtime controls for model override trust and allowlists. Keep this unset unless a plugin must explicitly steer subagent model selection.","hasChildren":true}
+{"recordType":"path","path":"plugins.entries.qwen-portal-auth.subagent.allowedModels","kind":"plugin","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Plugin Subagent Allowed Models","help":"Allowed override targets for trusted plugin subagent runs as canonical \"provider/model\" refs. Use \"*\" only when you intentionally allow any model.","hasChildren":true}
+{"recordType":"path","path":"plugins.entries.qwen-portal-auth.subagent.allowedModels.*","kind":"plugin","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
+{"recordType":"path","path":"plugins.entries.qwen-portal-auth.subagent.allowModelOverride","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["access"],"label":"Allow Plugin Subagent Model Override","help":"Explicitly allows this plugin to request provider/model overrides in background subagent runs. Keep false unless the plugin is trusted to steer model selection.","hasChildren":false}
 {"recordType":"path","path":"plugins.entries.sglang","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"@openclaw/sglang-provider","help":"OpenClaw SGLang provider plugin (plugin: sglang)","hasChildren":true}
 {"recordType":"path","path":"plugins.entries.sglang.config","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"@openclaw/sglang-provider Config","help":"Plugin-defined config payload for sglang.","hasChildren":false}
 {"recordType":"path","path":"plugins.entries.sglang.enabled","kind":"plugin","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Enable @openclaw/sglang-provider","hasChildren":false}
@@ -4762,7 +4840,7 @@
 {"recordType":"path","path":"plugins.entries.voice-call.config.outbound.notifyHangupDelaySec","kind":"plugin","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Notify Hangup Delay (sec)","hasChildren":false}
 {"recordType":"path","path":"plugins.entries.voice-call.config.plivo","kind":"plugin","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"plugins.entries.voice-call.config.plivo.authId","kind":"plugin","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"plugins.entries.voice-call.config.plivo.authToken","kind":"plugin","type":"string","required":false,"deprecated":false,"sensitive":true,"tags":["auth","security"],"hasChildren":false}
+{"recordType":"path","path":"plugins.entries.voice-call.config.plivo.authToken","kind":"plugin","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
 {"recordType":"path","path":"plugins.entries.voice-call.config.provider","kind":"plugin","type":"string","required":false,"enumValues":["telnyx","twilio","plivo","mock"],"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Provider","help":"Use twilio, telnyx, or mock for dev/no-network.","hasChildren":false}
 {"recordType":"path","path":"plugins.entries.voice-call.config.publicUrl","kind":"plugin","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Public Webhook URL","hasChildren":false}
 {"recordType":"path","path":"plugins.entries.voice-call.config.responseModel","kind":"plugin","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":["advanced"],"label":"Response Model","hasChildren":false}
@@ -5145,7 +5223,7 @@
 {"recordType":"path","path":"tools.exec.applyPatch","kind":"core","type":"object","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":true}
 {"recordType":"path","path":"tools.exec.applyPatch.allowModels","kind":"core","type":"array","required":false,"deprecated":false,"sensitive":false,"tags":["access","tools"],"label":"apply_patch Model Allowlist","help":"Optional allowlist of model ids (e.g. \"gpt-5.2\" or \"openai/gpt-5.2\").","hasChildren":true}
 {"recordType":"path","path":"tools.exec.applyPatch.allowModels.*","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
-{"recordType":"path","path":"tools.exec.applyPatch.enabled","kind":"core","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["tools"],"label":"Enable apply_patch","help":"Enable or disable apply_patch for OpenAI and OpenAI Codex models when allowed by tool policy (default: true).","hasChildren":false}
+{"recordType":"path","path":"tools.exec.applyPatch.enabled","kind":"core","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["tools"],"label":"Enable apply_patch","help":"Experimental. Enables apply_patch for OpenAI models when allowed by tool policy.","hasChildren":false}
 {"recordType":"path","path":"tools.exec.applyPatch.workspaceOnly","kind":"core","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["access","advanced","security","tools"],"label":"apply_patch Workspace-Only","help":"Restrict apply_patch paths to the workspace directory (default: true). Set false to allow writing outside the workspace (dangerous).","hasChildren":false}
 {"recordType":"path","path":"tools.exec.ask","kind":"core","type":"string","required":false,"enumValues":["off","on-miss","always"],"deprecated":false,"sensitive":false,"tags":["tools"],"label":"Exec Ask","help":"Approval strategy for when exec commands require human confirmation before running. Use stricter ask behavior in shared channels and lower-friction settings in private operator contexts.","hasChildren":false}
 {"recordType":"path","path":"tools.exec.backgroundMs","kind":"core","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":[],"hasChildren":false}
@@ -5467,7 +5545,6 @@
 {"recordType":"path","path":"tools.web.fetch.maxChars","kind":"core","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":["performance","tools"],"label":"Web Fetch Max Chars","help":"Max characters returned by web_fetch (truncated).","hasChildren":false}
 {"recordType":"path","path":"tools.web.fetch.maxCharsCap","kind":"core","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":["performance","tools"],"label":"Web Fetch Hard Max Chars","help":"Hard cap for web_fetch maxChars (applies to config and tool calls).","hasChildren":false}
 {"recordType":"path","path":"tools.web.fetch.maxRedirects","kind":"core","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":["performance","storage","tools"],"label":"Web Fetch Max Redirects","help":"Maximum redirects allowed for web_fetch (default: 3).","hasChildren":false}
-{"recordType":"path","path":"tools.web.fetch.maxResponseBytes","kind":"core","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":["performance","tools"],"label":"Web Fetch Max Download Size (bytes)","help":"Max download size before truncation.","hasChildren":false}
 {"recordType":"path","path":"tools.web.fetch.readability","kind":"core","type":"boolean","required":false,"deprecated":false,"sensitive":false,"tags":["tools"],"label":"Web Fetch Readability Extraction","help":"Use Readability to extract main content from HTML (fallbacks to basic HTML cleanup).","hasChildren":false}
 {"recordType":"path","path":"tools.web.fetch.timeoutSeconds","kind":"core","type":"integer","required":false,"deprecated":false,"sensitive":false,"tags":["performance","tools"],"label":"Web Fetch Timeout (sec)","help":"Timeout in seconds for web_fetch requests.","hasChildren":false}
 {"recordType":"path","path":"tools.web.fetch.userAgent","kind":"core","type":"string","required":false,"deprecated":false,"sensitive":false,"tags":["tools"],"label":"Web Fetch User-Agent","help":"Override User-Agent header for web_fetch requests.","hasChildren":false}

docs/automation/hooks.md

@@ -459,68 +459,6 @@ These hooks are not event-stream listeners; they let plugins synchronously adjus
 
 ### Plugin Hook Events
 
-#### before_tool_call
-
-Runs before each tool call. Plugins can modify parameters, block the call, or request user approval.
-
-Return fields:
-
-- **`params`**: Override tool parameters (merged with original params)
-- **`block`**: Set to `true` to block the tool call
-- **`blockReason`**: Reason shown to the agent when blocked
-- **`requireApproval`**: Pause execution and wait for user approval via channels
-
-The `requireApproval` field triggers native platform approval (Telegram buttons, Discord components, `/approve` command) instead of relying on the agent to cooperate:
-
-```typescript
-{
-  requireApproval: {
-    title: "Sensitive operation",
-    description: "This tool call modifies production data",
-    severity: "warning",       // "info" | "warning" | "critical"
-    timeoutMs: 120000,         // default: 120s
-    timeoutBehavior: "deny",   // "allow" | "deny" (default)
-    onResolution: async (decision) => {
-      // Called after the user resolves: "allow-once", "allow-always", "deny", "timeout", or "cancelled"
-    },
-  }
-}
-```
-
-The `onResolution` callback is invoked with the final decision string after the approval resolves, times out, or is cancelled. It runs in-process within the plugin (not sent to the gateway). Use it to persist decisions, update caches, or perform cleanup.
-
-The `pluginId` field is stamped automatically by the hook runner from the plugin registration. When multiple plugins return `requireApproval`, the first one (highest priority) wins.
-
-`block` takes precedence over `requireApproval`: if the merged hook result has both `block: true` and a `requireApproval` field, the tool call is blocked immediately without triggering the approval flow. This ensures a higher-priority plugin's block cannot be overridden by a lower-priority plugin's approval request.
-
-If the gateway is unavailable or does not support plugin approvals, the tool call falls back to a soft block using the `description` as the block reason.
-
-#### before_skill_install
-
-Runs after the built-in install security scan and before installation continues. OpenClaw fires this hook for interactive skill installs as well as plugin bundle/package installs.
-
-Return fields:
-
-- **`findings`**: Additional scan findings to surface as warnings
-- **`block`**: Set to `true` to block the install
-- **`blockReason`**: Human-readable reason shown when blocked
-
-Event fields:
-
-- **`skillName`**: Human-readable skill name or plugin id for the install target
-- **`sourceDir`**: Absolute path to the source directory being scanned
-- **`source`**: Skill origin when available (for example `openclaw-bundled` or `openclaw-workspace`)
-- **`builtinFindings`**: Findings already produced by the built-in scanner
-
-Decision semantics:
-
-- `before_skill_install`: `{ block: true }` is terminal and stops lower-priority handlers.
-- `before_skill_install`: `{ block: false }` is treated as no decision.
-
-Use this hook for external security scanners, policy engines, or enterprise approval gates that need to audit install sources before they are installed.
-
-#### Compaction lifecycle
-
 Compaction lifecycle hooks exposed through the plugin hook runner:
 
 - **`before_compaction`**: Runs before compaction with count/token metadata

docs/channels/bluebubbles.md

@@ -162,25 +162,6 @@ Groups:
 - `channels.bluebubbles.groupPolicy = open | allowlist | disabled` (default: `allowlist`).
 - `channels.bluebubbles.groupAllowFrom` controls who can trigger in groups when `allowlist` is set.
 
-### Contact name enrichment (macOS, optional)
-
-BlueBubbles group webhooks often only include raw participant addresses. If you want `GroupMembers` context to show local contact names instead, you can opt in to local Contacts enrichment on macOS:
-
-- `channels.bluebubbles.enrichGroupParticipantsFromContacts = true` enables the lookup. Default: `false`.
-- Lookups run only after group access, command authorization, and mention gating have allowed the message through.
-- Only unnamed phone participants are enriched.
-- Raw phone numbers remain as the fallback when no local match is found.
-
-```json5
-{
-  channels: {
-    bluebubbles: {
-      enrichGroupParticipantsFromContacts: true,
-    },
-  },
-}
-```
-
 ### Mention gating (groups)
 
 BlueBubbles supports mention gating for group chats, matching iMessage/WhatsApp behavior:
@@ -266,9 +247,8 @@ Available actions:
 - **addParticipant**: Add someone to a group (`chatGuid`, `address`)
 - **removeParticipant**: Remove someone from a group (`chatGuid`, `address`)
 - **leaveGroup**: Leave a group chat (`chatGuid`)
-- **upload-file**: Send media/files (`to`, `buffer`, `filename`, `asVoice`)
+- **sendAttachment**: Send media/files (`to`, `buffer`, `filename`, `asVoice`)
   - Voice memos: set `asVoice: true` with **MP3** or **CAF** audio to send as an iMessage voice message. BlueBubbles converts MP3 → CAF when sending voice memos.
-- Legacy alias: `sendAttachment` still works, but `upload-file` is the canonical action name.
 
 ### Message IDs (short vs full)
 
@@ -320,7 +300,6 @@ Provider options:
 - `channels.bluebubbles.allowFrom`: DM allowlist (handles, emails, E.164 numbers, `chat_id:*`, `chat_guid:*`).
 - `channels.bluebubbles.groupPolicy`: `open | allowlist | disabled` (default: `allowlist`).
 - `channels.bluebubbles.groupAllowFrom`: Group sender allowlist.
-- `channels.bluebubbles.enrichGroupParticipantsFromContacts`: On macOS, optionally enrich unnamed group participants from local Contacts after gating passes. Default: `false`.
 - `channels.bluebubbles.groups`: Per-group config (`requireMention`, etc.).
 - `channels.bluebubbles.sendReadReceipts`: Send read receipts (default: `true`).
 - `channels.bluebubbles.blockStreaming`: Enable block streaming (default: `false`; required for streaming replies).

docs/channels/googlechat.md

@@ -201,7 +201,6 @@ Notes:
 - Default webhook path is `/googlechat` if `webhookPath` isn’t set.
 - `dangerouslyAllowNameMatching` re-enables mutable email principal matching for allowlists (break-glass compatibility mode).
 - Reactions are available via the `reactions` tool and `channels action` when `actions.reactions` is enabled.
-- Message actions expose `send` for text and `upload-file` for explicit attachment sends. `upload-file` accepts `media` / `filePath` / `path` plus optional `message`, `filename`, and thread targeting.
 - `typingIndicator` supports `none`, `message` (default), and `reaction` (reaction requires user OAuth).
 - Attachments are downloaded through the Chat API and stored in the media pipeline (size capped by `mediaMaxMb`).
 

docs/channels/groups.md

@@ -366,10 +366,6 @@ Group inbound payloads set:
 - `WasMentioned` (mention gating result)
 - Telegram forum topics also include `MessageThreadId` and `IsForum`.
 
-Channel specific notes:
-
-- BlueBubbles can optionally enrich unnamed macOS group participants from the local Contacts database before populating `GroupMembers`. This is off by default and only runs after normal group gating passes.
-
 The agent system prompt includes a group intro on the first turn of a new group session. It reminds the model to respond like a human, avoid Markdown tables, and avoid typing literal `\n` sequences.
 
 ## iMessage specifics

docs/channels/index.md

@@ -33,7 +33,6 @@ Text is supported everywhere; media and reactions vary by channel.
 - [Twitch](/channels/twitch) — Twitch chat via IRC connection (plugin, installed separately).
 - [Voice Call](/plugins/voice-call) — Telephony via Plivo or Twilio (plugin, installed separately).
 - [WebChat](/web/webchat) — Gateway WebChat UI over WebSocket.
-- [WeChat](https://www.npmjs.com/package/@tencent-weixin/openclaw-weixin) — Tencent iLink Bot plugin via QR login; private chats only.
 - [WhatsApp](/channels/whatsapp) — Most popular; uses Baileys and requires QR pairing.
 - [Zalo](/channels/zalo) — Zalo Bot API; Vietnam's popular messenger (plugin, installed separately).
 - [Zalo Personal](/channels/zalouser) — Zalo personal account via QR login (plugin, installed separately).

docs/channels/msteams.md

@@ -11,7 +11,7 @@ title: "Microsoft Teams"
 
 Updated: 2026-01-21
 
-Status: text + DM attachments are supported; channel/group file sending requires `sharePointSiteId` + Graph permissions (see [Sending files in group chats](#sending-files-in-group-chats)). Polls are sent via Adaptive Cards. Message actions expose explicit `upload-file` for file-first sends.
+Status: text + DM attachments are supported; channel/group file sending requires `sharePointSiteId` + Graph permissions (see [Sending files in group chats](#sending-files-in-group-chats)). Polls are sent via Adaptive Cards.
 
 ## Plugin required
 
@@ -527,7 +527,6 @@ Teams recently introduced two channel UI styles over the same underlying data mo
 
 - **DMs:** Images and file attachments work via Teams bot file APIs.
 - **Channels/groups:** Attachments live in M365 storage (SharePoint/OneDrive). The webhook payload only includes an HTML stub, not the actual file bytes. **Graph API permissions are required** to download channel attachments.
-- For explicit file-first sends, use `action=upload-file` with `media` / `filePath` / `path`; optional `message` becomes the accompanying text/comment, and `filename` overrides the uploaded name.
 
 Without Graph permissions, channel messages with images will be received as text-only (the image content is not accessible to the bot).
 By default, OpenClaw only downloads media from Microsoft/Teams hostnames. Override with `channels.msteams.mediaAllowHosts` (use `["*"]` to allow any host).

docs/channels/pairing.md

@@ -36,7 +36,7 @@ openclaw pairing list telegram
 openclaw pairing approve telegram <CODE>
 ```
 
-Supported channels: `bluebubbles`, `discord`, `feishu`, `googlechat`, `imessage`, `irc`, `line`, `matrix`, `mattermost`, `msteams`, `nextcloud-talk`, `nostr`, `openclaw-weixin`, `signal`, `slack`, `synology-chat`, `telegram`, `twitch`, `whatsapp`, `zalo`, `zalouser`.
+Supported channels: `bluebubbles`, `discord`, `feishu`, `googlechat`, `imessage`, `irc`, `line`, `matrix`, `mattermost`, `msteams`, `nextcloud-talk`, `nostr`, `signal`, `slack`, `synology-chat`, `telegram`, `twitch`, `whatsapp`, `zalo`, `zalouser`.
 
 ### Where the state lives
 

docs/channels/slack.md

@@ -344,8 +344,6 @@ Available action groups in current Slack tooling:
 | memberInfo | enabled |
 | emojiList  | enabled |
 
-Current Slack message actions include `send`, `upload-file`, `download-file`, `read`, `edit`, `delete`, `pin`, `unpin`, `list-pins`, `member-info`, and `emoji-list`.
-
 ## Events and operational behavior
 
 - Message edits/deletes/thread broadcasts are mapped into system events.

docs/cli/config.md

@@ -1,5 +1,5 @@
 ---
-summary: "CLI reference for `openclaw config` (get/set/unset/file/schema/validate)"
+summary: "CLI reference for `openclaw config` (get/set/unset/file/validate)"
 read_when:
   - You want to read or edit config non-interactively
 title: "config"
@@ -7,7 +7,7 @@ title: "config"
 
 # `openclaw config`
 
-Config helpers for non-interactive edits in `openclaw.json`: get/set/unset/file/schema/validate
+Config helpers for non-interactive edits in `openclaw.json`: get/set/unset/validate
 values by path and print the active config file. Run without a subcommand to
 open the configure wizard (same as `openclaw configure`).
 
@@ -15,7 +15,6 @@ open the configure wizard (same as `openclaw configure`).
 
 ```bash
 openclaw config file
-openclaw config schema
 openclaw config get browser.executablePath
 openclaw config set browser.executablePath "/usr/bin/google-chrome"
 openclaw config set agents.defaults.heartbeat.every "2h"
@@ -28,21 +27,7 @@ openclaw config validate
 openclaw config validate --json
 ```
 
-### `config schema`
-
-Print the generated JSON schema for `openclaw.json` to stdout as plain text.
-
-```bash
-openclaw config schema
-```
-
-Pipe it into a file when you want to inspect or validate it with other tools:
-
-```bash
-openclaw config schema > openclaw.schema.json
-```
-
-### Paths
+## Paths
 
 Paths use dot or bracket notation:
 

docs/cli/gateway.md

@@ -55,8 +55,7 @@ Notes:
 - `--reset`: reset dev config + credentials + sessions + workspace (requires `--dev`).
 - `--force`: kill any existing listener on the selected port before starting.
 - `--verbose`: verbose logs.
-- `--cli-backend-logs`: only show CLI backend logs in the console (and enable stdout/stderr).
-- `--claude-cli-logs`: deprecated alias for `--cli-backend-logs`.
+- `--claude-cli-logs`: only show claude-cli logs in the console (and enable its stdout/stderr).
 - `--ws-log <auto|full|compact>`: websocket log style (default `auto`).
 - `--compact`: alias for `--ws-log compact`.
 - `--raw-stream`: log raw model stream events to jsonl.

docs/cli/index.md

@@ -396,7 +396,7 @@ Interactive configuration wizard (models, channels, skills, gateway).
 
 ### `config`
 
-Non-interactive config helpers (get/set/unset/file/schema/validate). Running `openclaw config` with no
+Non-interactive config helpers (get/set/unset/file/validate). Running `openclaw config` with no
 subcommand launches the wizard.
 
 Subcommands:
@@ -413,7 +413,6 @@ Subcommands:
 - `config set --strict-json`: require JSON5 parsing for path/value input. `--json` remains a legacy alias for strict parsing outside dry-run output mode.
 - `config unset <path>`: remove a value.
 - `config file`: print the active config file path.
-- `config schema`: print the generated JSON schema for `openclaw.json`.
 - `config validate`: validate the current config against the schema without starting the gateway.
 - `config validate --json`: emit machine-readable JSON output.
 
@@ -780,8 +779,7 @@ Options:
 - `--reset` (reset dev config + credentials + sessions + workspace)
 - `--force` (kill existing listener on port)
 - `--verbose`
-- `--cli-backend-logs`
-- `--claude-cli-logs` (deprecated alias)
+- `--claude-cli-logs`
 - `--ws-log <auto|full|compact>`
 - `--compact` (alias for `--ws-log compact`)
 - `--raw-stream`
@@ -872,13 +870,6 @@ 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.
 
-Anthropic Claude CLI migration:
-
-```bash
-openclaw models auth login --provider anthropic --method cli --set-default
-openclaw onboard --auth-choice anthropic-cli
-```
-
 ### `models` (root)
 
 `openclaw models` is an alias for `models status`.

docs/cli/models.md

@@ -38,7 +38,7 @@ Notes:
 - `models set <model-or-alias>` accepts `provider/model` or an alias.
 - Model refs are parsed by splitting on the **first** `/`. If the model ID includes `/` (OpenRouter-style), include the provider prefix (example: `openrouter/moonshotai/kimi-k2`).
 - If you omit the provider, OpenClaw treats the input as an alias or a model for the **default provider** (only works when there is no `/` in the model ID).
-- `models status` may show `marker(<value>)` in auth output for non-secret placeholders (for example `OPENAI_API_KEY`, `secretref-managed`, `minimax-oauth`, `oauth:chutes`, `ollama-local`) instead of masking them as secrets.
+- `models status` may show `marker(<value>)` in auth output for non-secret placeholders (for example `OPENAI_API_KEY`, `secretref-managed`, `minimax-oauth`, `qwen-oauth`, `ollama-local`) instead of masking them as secrets.
 
 ### `models status`
 
@@ -74,17 +74,8 @@ openclaw models auth paste-token
 `models auth login` runs a provider plugin’s auth flow (OAuth/API key). Use
 `openclaw plugins list` to see which providers are installed.
 
-Examples:
-
-```bash
-openclaw models auth login --provider anthropic --method cli --set-default
-openclaw models auth login --provider openai-codex --set-default
-```
-
 Notes:
 
-- `login --provider anthropic --method cli --set-default` reuses a local Claude
-  CLI login and rewrites the main Anthropic default-model path to `claude-cli/...`.
 - `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/concepts/agent-loop.md

@@ -87,7 +87,6 @@ These run inside the agent loop or gateway pipeline:
 - **`agent_end`**: inspect the final message list and run metadata after completion.
 - **`before_compaction` / `after_compaction`**: observe or annotate compaction cycles.
 - **`before_tool_call` / `after_tool_call`**: intercept tool params/results.
-- **`before_skill_install`**: inspect built-in scan findings and optionally block skill or plugin installs.
 - **`tool_result_persist`**: synchronously transform tool results before they are written to the session transcript.
 - **`message_received` / `message_sending` / `message_sent`**: inbound + outbound message hooks.
 - **`session_start` / `session_end`**: session lifecycle boundaries.
@@ -97,8 +96,6 @@ Hook decision rules for outbound/tool guards:
 
 - `before_tool_call`: `{ block: true }` is terminal and stops lower-priority handlers.
 - `before_tool_call`: `{ block: false }` is a no-op and does not clear a prior block.
-- `before_skill_install`: `{ block: true }` is terminal and stops lower-priority handlers.
-- `before_skill_install`: `{ block: false }` is a no-op and does not clear a prior block.
 - `message_sending`: `{ cancel: true }` is terminal and stops lower-priority handlers.
 - `message_sending`: `{ cancel: false }` is a no-op and does not clear a prior cancel.
 
@@ -148,7 +145,7 @@ See [Plugin hooks](/plugins/architecture#provider-runtime-hooks) for the hook AP
 ## Timeouts
 
 - `agent.wait` default: 30s (just the wait). `timeoutMs` param overrides.
-- Agent runtime: `agents.defaults.timeoutSeconds` default 172800s (48 hours); enforced in `runEmbeddedPiAgent` abort timer.
+- Agent runtime: `agents.defaults.timeoutSeconds` default 600s; enforced in `runEmbeddedPiAgent` abort timer.
 
 ## Where things can end early
 

docs/concepts/memory.md

@@ -56,9 +56,6 @@ When a session is **close to auto-compaction**, OpenClaw triggers a **silent,
 agentic turn** that reminds the model to write durable memory **before** the
 context is compacted. The default prompts explicitly say the model _may reply_,
 but usually `NO_REPLY` is the correct response so the user never sees this turn.
-The active memory plugin owns the prompt/path policy for that flush; the
-default `memory-core` plugin writes to the canonical daily file under
-`memory/YYYY-MM-DD.md`.
 
 This is controlled by `agents.defaults.compaction.memoryFlush`:
 
@@ -100,10 +97,9 @@ semantic queries can find related notes even when wording differs. Hybrid search
 (BM25 + vector) is available for combining semantic matching with exact keyword
 lookups.
 
-Memory search adapter ids come from the active memory plugin. The default
-`memory-core` plugin ships built-ins for OpenAI, Gemini, Voyage, Mistral,
-Ollama, and local GGUF models, plus an optional QMD sidecar backend for
-advanced retrieval and post-processing features like MMR diversity re-ranking
+Memory search supports multiple embedding providers (OpenAI, Gemini, Voyage,
+Mistral, Ollama, and local GGUF models), an optional QMD sidecar backend for
+advanced retrieval, and post-processing features like MMR diversity re-ranking
 and temporal decay.
 
 For the full configuration reference -- including embedding provider setup, QMD

docs/concepts/model-providers.md

@@ -108,6 +108,7 @@ Current bundled examples:
 - `byteplus`, `cloudflare-ai-gateway`, `huggingface`, `kimi-coding`,
   `modelstudio`, `nvidia`, `qianfan`, `synthetic`, `together`, `venice`,
   `vercel-ai-gateway`, and `volcengine`: plugin-owned catalogs only
+- `qwen-portal`: plugin-owned catalog, OAuth login, and OAuth refresh
 - `minimax` and `xiaomi`: plugin-owned catalogs plus usage auth/snapshot logic
 
 The bundled `openai` plugin now owns both provider ids: `openai` and
@@ -347,6 +348,22 @@ Kimi Coding uses Moonshot AI's Anthropic-compatible endpoint:
 }
 ```
 
+### Qwen OAuth (free tier)
+
+Qwen provides OAuth access to Qwen Coder + Vision via a device-code flow.
+The bundled provider plugin is enabled by default, so just log in:
+
+```bash
+openclaw models auth login --provider qwen-portal --set-default
+```
+
+Model refs:
+
+- `qwen-portal/coder-model`
+- `qwen-portal/vision-model`
+
+See [/providers/qwen](/providers/qwen) for setup details and notes.
+
 ### Volcano Engine (Doubao)
 
 Volcano Engine (火山引擎) provides access to Doubao and other models in China.

docs/concepts/oauth.md

@@ -10,7 +10,7 @@ title: "OAuth"
 
 # OAuth
 
-OpenClaw supports “subscription auth” via OAuth for providers that offer it (notably **OpenAI Codex (ChatGPT OAuth)**). For Anthropic subscriptions, you can either use the **setup-token** flow or reuse a local **Claude CLI** login on the gateway host. 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:
+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.
 
@@ -80,48 +80,19 @@ Verify:
 openclaw models status
 ```
 
-## Anthropic Claude CLI migration
-
-If Claude CLI is already installed and signed in on the gateway host, you can
-switch Anthropic model selection over to the local CLI backend:
-
-```bash
-openclaw models auth login --provider anthropic --method cli --set-default
-```
-
-Onboarding shortcut:
-
-```bash
-openclaw onboard --auth-choice anthropic-cli
-```
-
-This keeps existing Anthropic auth profiles for rollback, but rewrites the main
-default-model path from `anthropic/...` to `claude-cli/...`.
-
 ## OAuth exchange (how login works)
 
 OpenClaw’s interactive login flows are implemented in `@mariozechner/pi-ai` and wired into the wizards/commands.
 
-### Anthropic setup-token / Claude CLI
+### Anthropic setup-token
 
 Flow shape:
 
-Setup-token path:
-
 1. run `claude setup-token`
 2. paste the token into OpenClaw
 3. store as a token auth profile (no refresh)
 
-Claude CLI path:
-
-1. sign in with `claude auth login` on the gateway host
-2. run `openclaw models auth login --provider anthropic --method cli --set-default`
-3. store no new auth profile; switch model selection to `claude-cli/...`
-
-Wizard paths:
-
-- `openclaw onboard` → auth choice `anthropic-cli`
-- `openclaw onboard` → auth choice `setup-token` (Anthropic)
+The wizard path is `openclaw onboard` → auth choice `setup-token` (Anthropic).
 
 ### OpenAI Codex (ChatGPT OAuth)
 

docs/docs.json

@@ -52,10 +52,6 @@
     ]
   },
   "redirects": [
-    {
-      "source": "/providers/modelstudio",
-      "destination": "/providers/qwen_modelstudio"
-    },
     {
       "source": "/platforms/oracle",
       "destination": "/install/oracle"
@@ -1198,6 +1194,7 @@
                   "providers/litellm",
                   "providers/minimax",
                   "providers/mistral",
+                  "providers/modelstudio",
                   "providers/moonshot",
                   "providers/nvidia",
                   "providers/ollama",
@@ -1207,7 +1204,6 @@
                   "providers/openrouter",
                   "providers/perplexity-provider",
                   "providers/qianfan",
-                  "providers/qwen_modelstudio",
                   "providers/qwen",
                   "providers/sglang",
                   "providers/synthetic",

docs/gateway/authentication.md

@@ -113,26 +113,6 @@ Optional ops scripts (systemd/Termux) are documented here:
 
 > `claude setup-token` requires an interactive TTY.
 
-## Anthropic: Claude CLI migration
-
-If Claude CLI is already installed and signed in on the gateway host, you can
-switch an existing Anthropic setup over to the CLI backend instead of pasting a
-setup-token:
-
-```bash
-openclaw models auth login --provider anthropic --method cli --set-default
-```
-
-This keeps your existing Anthropic auth profiles for rollback, but changes the
-default model selection to `claude-cli/...` and adds matching Claude CLI
-allowlist entries under `agents.defaults.models`.
-
-Onboarding shortcut:
-
-```bash
-openclaw onboard --auth-choice anthropic-cli
-```
-
 ## Checking model auth status
 
 ```bash

docs/gateway/cli-backends.md

@@ -22,14 +22,13 @@ want “always works” text responses without relying on external APIs.
 
 ## Beginner-friendly quick start
 
-You can use Claude Code CLI **without any config** (the bundled Anthropic plugin
-registers a default backend):
+You can use Claude Code CLI **without any config** (OpenClaw ships a built-in default):
 
 ```bash
 openclaw agent --message "hi" --model claude-cli/opus-4.6
 ```
 
-Codex CLI also works out of the box (via the bundled OpenAI plugin):
+Codex CLI also works out of the box:
 
 ```bash
 openclaw agent --message "hi" --model codex-cli/gpt-5.4
@@ -54,11 +53,6 @@ command path:
 
 That’s it. No keys, no extra auth config needed beyond the CLI itself.
 
-If you use a bundled CLI backend as the **primary message provider** on a
-gateway host, OpenClaw now auto-loads the owning bundled plugin when your config
-explicitly references that backend in a model ref or under
-`agents.defaults.cliBackends`.
-
 ## Using it as a fallback
 
 Add a CLI backend to your fallback list so it only runs when primary models fail:
@@ -186,9 +180,9 @@ Input modes:
 - `input: "stdin"` sends the prompt via stdin.
 - If the prompt is very long and `maxPromptArgChars` is set, stdin is used.
 
-## Defaults (plugin-owned)
+## Defaults (built-in)
 
-The bundled Anthropic plugin registers a default for `claude-cli`:
+OpenClaw ships a default for `claude-cli`:
 
 - `command: "claude"`
 - `args: ["-p", "--output-format", "json", "--permission-mode", "bypassPermissions"]`
@@ -199,38 +193,19 @@ The bundled Anthropic plugin registers a default for `claude-cli`:
 - `systemPromptWhen: "first"`
 - `sessionMode: "always"`
 
-The bundled OpenAI plugin also registers a default for `codex-cli`:
+OpenClaw also ships a default for `codex-cli`:
 
 - `command: "codex"`
-- `args: ["exec","--json","--color","never","--sandbox","workspace-write","--skip-git-repo-check"]`
-- `resumeArgs: ["exec","resume","{sessionId}","--color","never","--sandbox","workspace-write","--skip-git-repo-check"]`
+- `args: ["exec","--json","--color","never","--sandbox","read-only","--skip-git-repo-check"]`
+- `resumeArgs: ["exec","resume","{sessionId}","--color","never","--sandbox","read-only","--skip-git-repo-check"]`
 - `output: "jsonl"`
 - `resumeOutput: "text"`
 - `modelArg: "--model"`
 - `imageArg: "--image"`
 - `sessionMode: "existing"`
 
-The bundled Google plugin also registers a default for `google-gemini-cli`:
-
-- `command: "gemini"`
-- `args: ["--prompt", "--output-format", "json"]`
-- `resumeArgs: ["--resume", "{sessionId}", "--prompt", "--output-format", "json"]`
-- `modelArg: "--model"`
-- `sessionMode: "existing"`
-- `sessionIdFields: ["session_id", "sessionId"]`
-
 Override only if needed (common: absolute `command` path).
 
-## Plugin-owned defaults
-
-CLI backend defaults are now part of the plugin surface:
-
-- Plugins register them with `api.registerCliBackend(...)`.
-- The backend `id` becomes the provider prefix in model refs.
-- User config in `agents.defaults.cliBackends.<id>` still overrides the plugin default.
-- Backend-specific config cleanup stays plugin-owned through the optional
-  `normalizeConfig` hook.
-
 ## Limitations
 
 - **No OpenClaw tools** (the CLI backend never receives tool calls). Some CLIs

docs/gateway/openai-http-api.md

@@ -165,30 +165,6 @@ Set `stream: true` to receive Server-Sent Events (SSE):
 - Each event line is `data: <json>`
 - Stream ends with `data: [DONE]`
 
-## Open WebUI quick setup
-
-For a basic Open WebUI connection:
-
-- Base URL: `http://127.0.0.1:18789/v1`
-- Docker on macOS base URL: `http://host.docker.internal:18789/v1`
-- API key: your Gateway bearer token
-- Model: `openclaw/default`
-
-Expected behavior:
-
-- `GET /v1/models` should list `openclaw/default`
-- Open WebUI should use `openclaw/default` as the chat model id
-- If you want a specific backend provider/model for that agent, set the agent's normal default model or send `x-openclaw-model`
-
-Quick smoke:
-
-```bash
-curl -sS http://127.0.0.1:18789/v1/models \
-  -H 'Authorization: Bearer YOUR_TOKEN'
-```
-
-If that returns `openclaw/default`, most Open WebUI setups can connect with the same base URL and token.
-
 ## Examples
 
 Non-streaming:

docs/gateway/sandboxing.md

@@ -402,7 +402,7 @@ Docker installs and the containerized gateway live here:
 For Docker gateway deployments, `scripts/docker/setup.sh` can bootstrap sandbox config.
 Set `OPENCLAW_SANDBOX=1` (or `true`/`yes`/`on`) to enable that path. You can
 override socket location with `OPENCLAW_DOCKER_SOCKET`. Full setup and env
-reference: [Docker](/install/docker#agent-sandbox).
+reference: [Docker](/install/docker#enable-agent-sandbox-for-docker-gateway).
 
 ## setupCommand (one-time container setup)
 

docs/gateway/troubleshooting.md

@@ -169,7 +169,7 @@ Look for:
 
 Common signatures:
 
-- `Gateway start blocked: set gateway.mode=local` → local gateway mode is not enabled. Fix: set `gateway.mode="local"` in your config (or run `openclaw configure`). If you are running OpenClaw via Podman, the default config path is `~/.openclaw/openclaw.json`.
+- `Gateway start blocked: set gateway.mode=local` → local gateway mode is not enabled. Fix: set `gateway.mode="local"` in your config (or run `openclaw configure`). If you are running OpenClaw via Podman using the dedicated `openclaw` user, the config lives at `~openclaw/.openclaw/openclaw.json`.
 - `refusing to bind gateway ... without auth` → non-loopback bind without token/password.
 - `another gateway instance is already listening` / `EADDRINUSE` → port conflict.
 

docs/help/faq.md

@@ -546,8 +546,8 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
   </Accordion>
 
   <Accordion title="Can I use Claude Max subscription without an API key?">
-    Yes. You can either use a **setup-token** or reuse a local **Claude CLI**
-    login on the gateway host.
+    Yes. You can authenticate with a **setup-token**
+    instead of an API key. This is the subscription path.
 
     Claude Pro/Max subscriptions **do not include an API key**, so this is the
     technical path for subscription accounts. But this is your decision: Anthropic
@@ -572,12 +572,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
   </Accordion>
 
   <Accordion title="Do you support Claude subscription auth (Claude Pro or Max)?">
-    Yes. You can either:
-
-    - use a **setup-token**
-    - reuse a local **Claude CLI** login on the gateway host with `openclaw models auth login --provider anthropic --method cli --set-default`
-
-    Setup-token is still supported. Claude CLI migration is simpler when the gateway host already runs Claude Code. See [Anthropic](/providers/anthropic) and [OAuth](/concepts/oauth).
+    Yes - via **setup-token**. OpenClaw no longer reuses Claude Code CLI OAuth tokens; use a setup-token or an Anthropic API key. Generate the token anywhere and paste it on the gateway host. See [Anthropic](/providers/anthropic) and [OAuth](/concepts/oauth).
 
     Important: this is technical compatibility, not a policy guarantee. Anthropic
     has blocked some subscription usage outside Claude Code in the past.
@@ -2158,8 +2153,9 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     1. Upgrade to a current OpenClaw release (or run from source `main`), then restart the gateway.
     2. Make sure MiniMax is configured (wizard or JSON), or that a MiniMax API key
        exists in env/auth profiles so the provider can be injected.
-    3. Use the exact model id (case-sensitive): `minimax/MiniMax-M2.7` or
-       `minimax/MiniMax-M2.7-highspeed`.
+    3. Use the exact model id (case-sensitive): `minimax/MiniMax-M2.7`,
+       `minimax/MiniMax-M2.7-highspeed`, `minimax/MiniMax-M2.5`, or
+       `minimax/MiniMax-M2.5-highspeed`.
     4. Run:
 
        ```bash

docs/help/testing.md

@@ -23,7 +23,6 @@ This doc is a “how we test” guide:
 Most days:
 
 - Full gate (expected before push): `pnpm build && pnpm check && pnpm test`
-- Faster local full-suite run on a roomy machine: `pnpm test:max`
 
 When you touch tests or want extra confidence:
 
@@ -55,19 +54,11 @@ Think of the suites as “increasing realism” (and increasing flakiness/cost):
   - Should be fast and stable
 - Scheduler note:
   - `pnpm test` now keeps a small checked-in behavioral manifest for true pool/isolation overrides and a separate timing snapshot for the slowest unit files.
-  - Extension-only local runs now also use a checked-in extensions timing snapshot plus a slightly coarser shared batch target on high-memory hosts, so the shared extensions lane avoids spawning an extra batch when two measured shared runs are enough.
-  - High-memory local extension shared batches also run with a slightly higher worker cap than before, which shortened the two remaining shared extension batches without changing the isolated extension lanes.
-  - High-memory local channel runs now reuse the checked-in channel timing snapshot to split the shared channels lane into a few measured batches instead of one long shared worker.
-  - High-memory local channel shared batches also run with a slightly lower worker cap than shared unit batches, which helped targeted channel reruns avoid CPU oversubscription once isolated channel lanes are already in flight.
-  - Targeted local channel reruns now start splitting shared channel work a bit earlier, which keeps medium-sized targeted reruns from leaving one oversized shared channel batch on the critical path.
-  - Targeted local unit reruns also split medium-sized shared unit selections into measured batches, which helps large focused reruns overlap instead of waiting behind one long shared unit lane.
-  - High-memory local multi-surface runs also use slightly coarser shared `unit-fast` batches so the mixed planner spends less time spinning up extra shared unit workers before the later surfaces can overlap.
-  - Shared unit, extension, channel, and gateway runs all stay on Vitest `forks`.
-  - The wrapper keeps measured fork-isolated exceptions and heavy singleton lanes explicit in `test/fixtures/test-parallel.behavior.json`.
+  - Shared unit coverage now defaults to `threads`, while the manifest keeps the measured fork-only exceptions and heavy singleton lanes explicit.
+  - The shared extension lane still defaults to `threads`; the wrapper keeps explicit fork-only exceptions in `test/fixtures/test-parallel.behavior.json` when a file cannot safely share a non-isolated worker.
+  - The channel suite (`vitest.channels.config.ts`) now also defaults to `threads`; the March 22, 2026 direct full-suite control run passed clean without channel-specific fork exceptions.
   - The wrapper peels the heaviest measured files into dedicated lanes instead of relying on a growing hand-maintained exclusion list.
-  - For surface-only local runs, unit, extension, and channel shared lanes can overlap their isolated hotspots instead of waiting behind one serial prefix.
-  - For multi-surface local runs, the wrapper keeps the shared surface phases ordered, but batches inside the same shared phase now fan out together, deferred isolated work can overlap the next shared phase, and spare `unit-fast` headroom now starts that deferred work earlier instead of leaving those slots idle.
-  - Refresh the timing snapshots with `pnpm test:perf:update-timings` and `pnpm test:perf:update-timings:extensions` after major suite shape changes.
+  - Refresh the timing snapshot with `pnpm test:perf:update-timings` after major suite shape changes.
 - Embedded runner note:
   - When you change message-tool discovery inputs or compaction runtime context,
     keep both levels of coverage.
@@ -81,19 +72,18 @@ Think of the suites as “increasing realism” (and increasing flakiness/cost):
     sufficient substitute for those integration paths.
 - Pool note:
   - Base Vitest config still defaults to `forks`.
-  - Unit, channel, extension, and gateway wrapper lanes all default to `forks`.
+  - Unit wrapper lanes default to `threads`, with explicit manifest fork-only exceptions.
+  - Extension scoped config defaults to `threads`.
+  - Channel scoped config defaults to `threads`.
   - Unit, channel, and extension configs default to `isolate: false` for faster file startup.
   - `pnpm test` also passes `--isolate=false` at the wrapper level.
   - Opt back into Vitest file isolation with `OPENCLAW_TEST_ISOLATE=1 pnpm test`.
   - `OPENCLAW_TEST_NO_ISOLATE=0` or `OPENCLAW_TEST_NO_ISOLATE=false` also force isolated runs.
 - Fast-local iteration note:
   - `pnpm test:changed` runs the wrapper with `--changed origin/main`.
-  - `pnpm test:changed:max` keeps the same changed-file filter but uses the wrapper's aggressive local planner profile.
-  - `pnpm test:max` exposes that same planner profile for a full local run.
-  - On supported local Node versions, including Node 25, the normal profile can use top-level lane parallelism. `pnpm test:max` still pushes the planner harder when you want a more aggressive local run.
   - The base Vitest config marks the wrapper manifests/config files as `forceRerunTriggers` so changed-mode reruns stay correct when scheduler inputs change.
-  - The wrapper keeps `OPENCLAW_VITEST_FS_MODULE_CACHE` enabled on supported hosts, but assigns a lane-local `OPENCLAW_VITEST_FS_MODULE_CACHE_PATH` so concurrent Vitest processes do not race on one shared experimental cache directory.
-  - Set `OPENCLAW_VITEST_FS_MODULE_CACHE_PATH=/abs/path` if you want one explicit cache location for direct single-run profiling.
+  - Vitest's filesystem module cache is now enabled by default for Node-side test reruns.
+  - Opt out with `OPENCLAW_VITEST_FS_MODULE_CACHE=0` or `OPENCLAW_VITEST_FS_MODULE_CACHE=false` if you suspect stale transform cache behavior.
 - Perf-debug note:
   - `pnpm test:perf:imports` enables Vitest import-duration reporting plus import-breakdown output.
   - `pnpm test:perf:imports:changed` scopes the same profiling view to files changed since `origin/main`.
@@ -305,19 +295,6 @@ OPENCLAW_LIVE_CLI_BACKEND=1 \
   pnpm test:live src/gateway/gateway-cli-backend.live.test.ts
 ```
 
-Docker recipe:
-
-```bash
-pnpm test:docker:live-cli-backend
-```
-
-Notes:
-
-- The Docker runner lives at `scripts/test-live-cli-backend-docker.sh`.
-- It runs the live CLI-backend smoke inside the repo Docker image as the non-root `node` user, because Claude CLI rejects `bypassPermissions` when invoked as root.
-- For `claude-cli`, it installs the Linux `@anthropic-ai/claude-code` package into a cached writable prefix at `OPENCLAW_DOCKER_CLI_TOOLS_DIR` (default: `~/.cache/openclaw/docker-cli-tools`).
-- It copies `~/.claude` into the container when available, but on machines where Claude auth is backed by `ANTHROPIC_API_KEY`, it also preserves `ANTHROPIC_API_KEY` / `ANTHROPIC_API_KEY_OLD` for the child Claude CLI via `OPENCLAW_LIVE_CLI_BACKEND_PRESERVE_ENV`.
-
 ### Recommended live recipes
 
 Narrow, explicit allowlists are fastest and least flaky:
@@ -447,17 +424,10 @@ If you want to rely on env keys (e.g. exported in your `~/.profile`), run local
 
 ## Docker runners (optional "works in Linux" checks)
 
-These Docker runners split into two buckets:
-
-- Live-model runners: `test:docker:live-models` and `test:docker:live-gateway` run `pnpm test:live` inside the repo Docker image, mounting your local config dir and workspace (and sourcing `~/.profile` if mounted).
-- Container smoke runners: `test:docker:openwebui`, `test:docker:onboard`, `test:docker:gateway-network`, and `test:docker:plugins` boot one or more real containers and verify higher-level integration paths.
-
-The live-model Docker runners also bind-mount only the needed CLI auth homes (or all supported ones when the run is not narrowed), then copy them into the container home before the run so external-CLI OAuth can refresh tokens without mutating the host auth store:
+These run `pnpm test:live` inside the repo Docker image, mounting your local config dir and workspace (and sourcing `~/.profile` if mounted). They also bind-mount only the needed CLI auth homes (or all supported ones when the run is not narrowed), then copy them into the container home before the run so external-CLI OAuth can refresh tokens without mutating the host auth store:
 
 - Direct models: `pnpm test:docker:live-models` (script: `scripts/test-live-models-docker.sh`)
-- CLI backend smoke: `pnpm test:docker:live-cli-backend` (script: `scripts/test-live-cli-backend-docker.sh`)
 - Gateway + dev agent: `pnpm test:docker:live-gateway` (script: `scripts/test-live-gateway-models-docker.sh`)
-- Open WebUI live smoke: `pnpm test:docker:openwebui` (script: `scripts/e2e/openwebui-docker.sh`)
 - Onboarding wizard (TTY, full scaffolding): `pnpm test:docker:onboard` (script: `scripts/e2e/onboard-docker.sh`)
 - Gateway networking (two containers, WS auth + health): `pnpm test:docker:gateway-network` (script: `scripts/e2e/gateway-network-docker.sh`)
 - Plugins (install smoke + `/plugin` alias + Claude-bundle restart semantics): `pnpm test:docker:plugins` (script: `scripts/e2e/plugins-docker.sh`)
@@ -470,17 +440,6 @@ real Telegram/Discord/etc. channel workers inside the container.
 `test:docker:live-models` still runs `pnpm test:live`, so pass through
 `OPENCLAW_LIVE_GATEWAY_*` as well when you need to narrow or exclude gateway
 live coverage from that Docker lane.
-`test:docker:openwebui` is a higher-level compatibility smoke: it starts an
-OpenClaw gateway container with the OpenAI-compatible HTTP endpoints enabled,
-starts a pinned Open WebUI container against that gateway, signs in through
-Open WebUI, verifies `/api/models` exposes `openclaw/default`, then sends a
-real chat request through Open WebUI's `/api/chat/completions` proxy.
-The first run can be noticeably slower because Docker may need to pull the
-Open WebUI image and Open WebUI may need to finish its own cold-start setup.
-This lane expects a usable live model key, and `OPENCLAW_PROFILE_FILE`
-(`~/.profile` by default) is the primary way to provide it in Dockerized runs.
-Successful runs print a small JSON payload like `{ "ok": true, "model":
-"openclaw/default", ... }`.
 
 Manual ACP plain-language thread smoke (not CI):
 
@@ -492,22 +451,17 @@ Useful env vars:
 - `OPENCLAW_CONFIG_DIR=...` (default: `~/.openclaw`) mounted to `/home/node/.openclaw`
 - `OPENCLAW_WORKSPACE_DIR=...` (default: `~/.openclaw/workspace`) mounted to `/home/node/.openclaw/workspace`
 - `OPENCLAW_PROFILE_FILE=...` (default: `~/.profile`) mounted to `/home/node/.profile` and sourced before running tests
-- `OPENCLAW_DOCKER_CLI_TOOLS_DIR=...` (default: `~/.cache/openclaw/docker-cli-tools`) mounted to `/home/node/.npm-global` for cached CLI installs inside Docker
 - External CLI auth dirs under `$HOME` are mounted read-only under `/host-auth/...`, then copied into `/home/node/...` before tests start
-  - Default: mount all supported dirs (`.codex`, `.claude`, `.minimax`)
+  - Default: mount all supported dirs (`.codex`, `.claude`, `.qwen`, `.minimax`)
   - Narrowed provider runs mount only the needed dirs inferred from `OPENCLAW_LIVE_PROVIDERS` / `OPENCLAW_LIVE_GATEWAY_PROVIDERS`
   - Override manually with `OPENCLAW_DOCKER_AUTH_DIRS=all`, `OPENCLAW_DOCKER_AUTH_DIRS=none`, or a comma list like `OPENCLAW_DOCKER_AUTH_DIRS=.claude,.codex`
 - `OPENCLAW_LIVE_GATEWAY_MODELS=...` / `OPENCLAW_LIVE_MODELS=...` to narrow the run
 - `OPENCLAW_LIVE_GATEWAY_PROVIDERS=...` / `OPENCLAW_LIVE_PROVIDERS=...` to filter providers in-container
 - `OPENCLAW_LIVE_REQUIRE_PROFILE_KEYS=1` to ensure creds come from the profile store (not env)
-- `OPENCLAW_OPENWEBUI_MODEL=...` to choose the model exposed by the gateway for the Open WebUI smoke
-- `OPENCLAW_OPENWEBUI_PROMPT=...` to override the nonce-check prompt used by the Open WebUI smoke
-- `OPENWEBUI_IMAGE=...` to override the pinned Open WebUI image tag
 
 ## Docs sanity
 
-Run docs checks after doc edits: `pnpm check:docs`.
-Run full Mintlify anchor validation when you need in-page heading checks too: `pnpm docs:check-links:anchors`.
+Run docs checks after doc edits: `pnpm docs:list`.
 
 ## Offline regression (CI-safe)
 
@@ -539,9 +493,7 @@ Future evals should stay deterministic first:
 
 Contract tests verify that every registered plugin and channel conforms to its
 interface contract. They iterate over all discovered plugins and run a suite of
-shape and behavior assertions. The default `pnpm test` unit lane intentionally
-skips these shared seam and smoke files; run the contract commands explicitly
-when you touch shared channel or provider surfaces.
+shape and behavior assertions.
 
 ### Commands
 
@@ -562,11 +514,6 @@ Located in `src/channels/plugins/contracts/*.contract.test.ts`:
 - **threading** - Thread ID handling
 - **directory** - Directory/roster API
 - **group-policy** - Group policy enforcement
-
-### Provider status contracts
-
-Located in `src/plugins/contracts/*.contract.test.ts`.
-
 - **status** - Channel status probes
 - **registry** - Plugin registry shape
 

docs/index.md

@@ -54,7 +54,7 @@ OpenClaw is a **self-hosted gateway** that connects your favorite chat apps —
 - **Agent-native**: built for coding agents with tool use, sessions, memory, and multi-agent routing
 - **Open source**: MIT licensed, community-driven
 
-**What do you need?** Node 24 (recommended), or Node 22 LTS (`22.14+`) for compatibility, an API key from your chosen provider, and 5 minutes. For best quality and security, use the strongest latest-generation model available.
+**What do you need?** Node 24 (recommended), or Node 22 LTS (`22.16+`) for compatibility, an API key from your chosen provider, and 5 minutes. For best quality and security, use the strongest latest-generation model available.
 
 ## How it works
 

docs/install/ansible.md

@@ -48,7 +48,7 @@ The Ansible playbook installs and configures:
 1. **Tailscale** -- mesh VPN for secure remote access
 2. **UFW firewall** -- SSH + Tailscale ports only
 3. **Docker CE + Compose V2** -- for agent sandboxes
-4. **Node.js 24 + pnpm** -- runtime dependencies (Node 22 LTS, currently `22.14+`, remains supported)
+4. **Node.js 24 + pnpm** -- runtime dependencies (Node 22 LTS, currently `22.16+`, remains supported)
 5. **OpenClaw** -- host-based, not containerized
 6. **Systemd service** -- auto-start with security hardening
 

docs/install/bun.md

@@ -41,7 +41,7 @@ Bun is an optional local runtime for running TypeScript directly (`bun run ...`,
 
 Bun blocks dependency lifecycle scripts unless explicitly trusted. For this repo, the commonly blocked scripts are not required:
 
-- `@whiskeysockets/baileys` `preinstall` -- checks Node major >= 20 (OpenClaw defaults to Node 24 and still supports Node 22 LTS, currently `22.14+`)
+- `@whiskeysockets/baileys` `preinstall` -- checks Node major >= 20 (OpenClaw defaults to Node 24 and still supports Node 22 LTS, currently `22.16+`)
 - `protobufjs` `postinstall` -- emits warnings about incompatible version schemes (no build artifacts)
 
 If you hit a runtime issue that requires these scripts, trust them explicitly:

docs/install/development-channels.md

@@ -48,7 +48,7 @@ update **without** changing your persisted channel:
 
 ```bash
 # Install a specific version
-openclaw update --tag 2026.3.26
+openclaw update --tag 2026.3.22
 
 # Install from the beta dist-tag (one-off, does not persist)
 openclaw update --tag beta
@@ -57,7 +57,7 @@ openclaw update --tag beta
 openclaw update --tag main
 
 # Install a specific npm package spec
-openclaw update --tag openclaw@2026.3.26
+openclaw update --tag openclaw@2026.3.22
 ```
 
 Notes:
@@ -75,7 +75,7 @@ Preview what `openclaw update` would do without making changes:
 ```bash
 openclaw update --dry-run
 openclaw update --channel beta --dry-run
-openclaw update --tag 2026.3.26 --dry-run
+openclaw update --tag 2026.3.22 --dry-run
 openclaw update --dry-run --json
 ```
 

docs/install/index.md

@@ -45,7 +45,7 @@ For all flags and CI/automation options, see [Installer internals](/install/inst
 
 ## System requirements
 
-- **Node 24** (recommended) or Node 22.14+ — the installer script handles this automatically
+- **Node 24** (recommended) or Node 22.16+ — the installer script handles this automatically
 - **macOS, Linux, or Windows** — both native Windows and WSL2 are supported; WSL2 is more stable. See [Windows](/platforms/windows).
 - `pnpm` is only needed if you build from source
 

docs/install/installer.md

@@ -71,7 +71,7 @@ Recommended for most interactive installs on macOS/Linux/WSL.
     Supports macOS and Linux (including WSL). If macOS is detected, installs Homebrew if missing.
   </Step>
   <Step title="Ensure Node.js 24 by default">
-    Checks Node version and installs Node 24 if needed (Homebrew on macOS, NodeSource setup scripts on Linux apt/dnf/yum). OpenClaw still supports Node 22 LTS, currently `22.14+`, for compatibility.
+    Checks Node version and installs Node 24 if needed (Homebrew on macOS, NodeSource setup scripts on Linux apt/dnf/yum). OpenClaw still supports Node 22 LTS, currently `22.16+`, for compatibility.
   </Step>
   <Step title="Ensure Git">
     Installs Git if missing.
@@ -257,7 +257,7 @@ Designed for environments where you want everything under a local prefix (defaul
     Requires PowerShell 5+.
   </Step>
   <Step title="Ensure Node.js 24 by default">
-    If missing, attempts install via winget, then Chocolatey, then Scoop. Node 22 LTS, currently `22.14+`, remains supported for compatibility.
+    If missing, attempts install via winget, then Chocolatey, then Scoop. Node 22 LTS, currently `22.16+`, remains supported for compatibility.
   </Step>
   <Step title="Install OpenClaw">
     - `npm` method (default): global npm install using selected `-Tag`

docs/install/migrating.md

@@ -91,7 +91,7 @@ Custom profiles use `~/.openclaw-<profile>/` or a path set via `OPENCLAW_STATE_D
 
   <Accordion title="Remote mode">
     If your UI points at a **remote** gateway, the remote host owns sessions and workspace.
-    Migrate the gateway host itself, not your local laptop. See [FAQ](/help/faq#where-things-live-on-disk).
+    Migrate the gateway host itself, not your local laptop. See [FAQ](/help/faq#where-does-openclaw-store-its-data).
   </Accordion>
 
   <Accordion title="Secrets in backups">

docs/install/node.md

@@ -9,7 +9,7 @@ read_when:
 
 # Node.js
 
-OpenClaw requires **Node 22.14 or newer**. **Node 24 is the default and recommended runtime** for installs, CI, and release workflows. Node 22 remains supported via the active LTS line. The [installer script](/install#alternative-install-methods) will detect and install Node automatically — this page is for when you want to set up Node yourself and make sure everything is wired up correctly (versions, PATH, global installs).
+OpenClaw requires **Node 22.16 or newer**. **Node 24 is the default and recommended runtime** for installs, CI, and release workflows. Node 22 remains supported via the active LTS line. The [installer script](/install#alternative-install-methods) will detect and install Node automatically — this page is for when you want to set up Node yourself and make sure everything is wired up correctly (versions, PATH, global installs).
 
 ## Check your version
 
@@ -17,7 +17,7 @@ OpenClaw requires **Node 22.14 or newer**. **Node 24 is the default and recommen
 node -v
 ```
 
-If this prints `v24.x.x` or higher, you're on the recommended default. If it prints `v22.14.x` or higher, you're on the supported Node 22 LTS path, but we still recommend upgrading to Node 24 when convenient. If Node isn't installed or the version is too old, pick an install method below.
+If this prints `v24.x.x` or higher, you're on the recommended default. If it prints `v22.16.x` or higher, you're on the supported Node 22 LTS path, but we still recommend upgrading to Node 24 when convenient. If Node isn't installed or the version is too old, pick an install method below.
 
 ## Install Node
 

docs/install/podman.md

@@ -7,261 +7,127 @@ title: "Podman"
 
 # Podman
 
-Run the OpenClaw Gateway in a rootless Podman container, managed by your current non-root user.
-
-The intended model is:
-
-- Podman runs the gateway container.
-- Your host `openclaw` CLI is the control plane.
-- Persistent state lives on the host under `~/.openclaw` by default.
-- Day-to-day management uses `openclaw --container <name> ...` instead of `sudo -u openclaw`, `podman exec`, or a separate service user.
+Run the OpenClaw Gateway in a **rootless** Podman container. Uses the same image as Docker (built from the repo [Dockerfile](https://github.com/openclaw/openclaw/blob/main/Dockerfile)).
 
 ## Prerequisites
 
-- **Podman** in rootless mode
-- **OpenClaw CLI** installed on the host
-- **Optional:** `systemd --user` if you want Quadlet-managed auto-start
-- **Optional:** `sudo` only if you want `loginctl enable-linger "$(whoami)"` for boot persistence on a headless host
+- **Podman** (rootless mode)
+- **sudo** access for one-time setup (creating the dedicated user and building the image)
 
 ## Quick start
 
 <Steps>
   <Step title="One-time setup">
-    From the repo root, run `./scripts/podman/setup.sh`.
+    From the repo root, run the setup script. It creates a dedicated `openclaw` user, builds the container image, and installs the launch script:
+
+    ```bash
+    ./scripts/podman/setup.sh
+    ```
+
+    This also creates a minimal config at `~openclaw/.openclaw/openclaw.json` (sets `gateway.mode` to `"local"`) so the Gateway can start without running the wizard.
+
+    By default the container is **not** installed as a systemd service -- you start it manually in the next step. For a production-style setup with auto-start and restarts, pass `--quadlet` instead:
+
+    ```bash
+    ./scripts/podman/setup.sh --quadlet
+    ```
+
+    (Or set `OPENCLAW_PODMAN_QUADLET=1`. Use `--container` to install only the container and launch script.)
+
+    **Optional build-time env vars** (set before running `scripts/podman/setup.sh`):
+
+    - `OPENCLAW_DOCKER_APT_PACKAGES` -- install extra apt packages during image build.
+    - `OPENCLAW_EXTENSIONS` -- pre-install extension dependencies (space-separated names, e.g. `diagnostics-otel matrix`).
+
   </Step>
 
-  <Step title="Start the Gateway container">
-    Start the container with `./scripts/run-openclaw-podman.sh launch`.
+  <Step title="Start the Gateway">
+    For a quick manual launch:
+
+    ```bash
+    ./scripts/run-openclaw-podman.sh launch
+    ```
+
   </Step>
 
-  <Step title="Run onboarding inside the container">
-    Run `./scripts/run-openclaw-podman.sh launch setup`, then open `http://127.0.0.1:18789/`.
-  </Step>
+  <Step title="Run the onboarding wizard">
+    To add channels or providers interactively:
+
+    ```bash
+    ./scripts/run-openclaw-podman.sh launch setup
+    ```
+
+    Then open `http://127.0.0.1:18789/` and use the token from `~openclaw/.openclaw/.env` (or the value printed by setup).
 
-  <Step title="Manage the running container from the host CLI">
-    Set `OPENCLAW_CONTAINER=openclaw`, then use normal `openclaw` commands from the host.
   </Step>
 </Steps>
 
-Setup details:
-
-- `./scripts/podman/setup.sh` builds `openclaw:local` in your rootless Podman store by default, or uses `OPENCLAW_IMAGE` / `OPENCLAW_PODMAN_IMAGE` if you set one.
-- It creates `~/.openclaw/openclaw.json` with `gateway.mode: "local"` if missing.
-- It creates `~/.openclaw/.env` with `OPENCLAW_GATEWAY_TOKEN` if missing.
-- For manual launches, the helper reads only a small allowlist of Podman-related keys from `~/.openclaw/.env` and passes explicit runtime env vars to the container; it does not hand the full env file to Podman.
-
-Quadlet-managed setup:
-
-```bash
-./scripts/podman/setup.sh --quadlet
-```
-
-Quadlet is a Linux-only option because it depends on systemd user services.
-
-You can also set `OPENCLAW_PODMAN_QUADLET=1`.
-
-Optional build/setup env vars:
-
-- `OPENCLAW_IMAGE` or `OPENCLAW_PODMAN_IMAGE` -- use an existing/pulled image instead of building `openclaw:local`
-- `OPENCLAW_DOCKER_APT_PACKAGES` -- install extra apt packages during image build
-- `OPENCLAW_EXTENSIONS` -- pre-install extension dependencies at build time
-
-Container start:
-
-```bash
-./scripts/run-openclaw-podman.sh launch
-```
-
-The script starts the container as your current uid/gid with `--userns=keep-id` and bind-mounts your OpenClaw state into the container.
-
-Onboarding:
-
-```bash
-./scripts/run-openclaw-podman.sh launch setup
-```
-
-Then open `http://127.0.0.1:18789/` and use the token from `~/.openclaw/.env`.
-
-Host CLI default:
-
-```bash
-export OPENCLAW_CONTAINER=openclaw
-```
-
-Then commands such as these will run inside that container automatically:
-
-```bash
-openclaw dashboard --no-open
-openclaw gateway status --deep
-openclaw doctor
-openclaw channels login
-```
-
-On macOS, Podman machine may make the browser appear non-local to the gateway.
-If the Control UI reports device-auth errors after launch, prefer the SSH
-tunnel flow in [macOS Podman SSH tunnel](#macos-podman-ssh-tunnel). For
-remote HTTPS access, use the Tailscale guidance in
-[Podman + Tailscale](#podman--tailscale).
-
-## macOS Podman SSH tunnel
-
-On macOS, Podman machine can make the browser appear non-local to the gateway even when the published port is only on `127.0.0.1`.
-
-For local browser access, use an SSH tunnel into the Podman VM and open the tunneled localhost port instead.
-
-Recommended local tunnel port:
-
-- `28889` on the Mac host
-- forwarded to `127.0.0.1:18789` inside the Podman VM
-
-Start the tunnel in a separate terminal:
-
-```bash
-ssh -N \
-  -i ~/.local/share/containers/podman/machine/machine \
-  -p <podman-vm-ssh-port> \
-  -L 28889:127.0.0.1:18789 \
-  core@127.0.0.1
-```
-
-In that command, `<podman-vm-ssh-port>` is the Podman VM's SSH port on the Mac host. Check your current value with:
-
-```bash
-podman system connection list
-```
-
-Allow the tunneled browser origin once. This is required the first time you use the tunnel because the launcher can auto-seed the Podman-published port, but it cannot infer your chosen browser tunnel port:
-
-```bash
-OPENCLAW_CONTAINER=openclaw openclaw config set gateway.controlUi.allowedOrigins \
-  '["http://127.0.0.1:18789","http://localhost:18789","http://127.0.0.1:28889","http://localhost:28889"]' \
-  --strict-json
-podman restart openclaw
-```
-
-That is a one-time step for the default `28889` tunnel.
-
-Then open:
-
-```text
-http://127.0.0.1:28889/
-```
-
-Notes:
-
-- `18789` is usually already occupied on the Mac host by the Podman-published gateway port, so the tunnel uses `28889` as the local browser port.
-- If the UI asks for pairing approval, prefer explicit container-targeted or explicit-URL commands so the host CLI does not fall back to local pairing files:
-
-```bash
-openclaw --container openclaw devices list
-openclaw --container openclaw devices approve --latest
-```
-
-- Equivalent explicit-URL form:
-
-```bash
-openclaw devices list \
-  --url ws://127.0.0.1:28889 \
-  --token "$(sed -n 's/^OPENCLAW_GATEWAY_TOKEN=//p' ~/.openclaw/.env | head -n1)"
-```
-
-## Podman + Tailscale
-
-For HTTPS or remote browser access, follow the main Tailscale docs.
-
-Podman-specific note:
-
-- Keep the Podman publish host at `127.0.0.1`.
-- Prefer host-managed `tailscale serve` over `openclaw gateway --tailscale serve`.
-- For local macOS browser access without HTTPS, prefer the SSH tunnel section above.
-
-See:
-
-- [Tailscale](/gateway/tailscale)
-- [Control UI](/web/control-ui)
-
 ## Systemd (Quadlet, optional)
 
-If you ran `./scripts/podman/setup.sh --quadlet`, setup installs a Quadlet file at:
+If you ran `./scripts/podman/setup.sh --quadlet` (or `OPENCLAW_PODMAN_QUADLET=1`), a [Podman Quadlet](https://docs.podman.io/en/latest/markdown/podman-systemd.unit.5.html) unit is installed so the gateway runs as a systemd user service for the openclaw user. The service is enabled and started at the end of setup.
 
-```bash
-~/.config/containers/systemd/openclaw.container
-```
+- **Start:** `sudo systemctl --machine openclaw@ --user start openclaw.service`
+- **Stop:** `sudo systemctl --machine openclaw@ --user stop openclaw.service`
+- **Status:** `sudo systemctl --machine openclaw@ --user status openclaw.service`
+- **Logs:** `sudo journalctl --machine openclaw@ --user -u openclaw.service -f`
 
-Useful commands:
+The quadlet file lives at `~openclaw/.config/containers/systemd/openclaw.container`. To change ports or env, edit that file (or the `.env` it sources), then `sudo systemctl --machine openclaw@ --user daemon-reload` and restart the service. On boot, the service starts automatically if lingering is enabled for openclaw (setup does this when loginctl is available).
 
-- **Start:** `systemctl --user start openclaw.service`
-- **Stop:** `systemctl --user stop openclaw.service`
-- **Status:** `systemctl --user status openclaw.service`
-- **Logs:** `journalctl --user -u openclaw.service -f`
+To add quadlet **after** an initial setup that did not use it, re-run: `./scripts/podman/setup.sh --quadlet`.
 
-After editing the Quadlet file:
+## The openclaw user (non-login)
 
-```bash
-systemctl --user daemon-reload
-systemctl --user restart openclaw.service
-```
+`scripts/podman/setup.sh` creates a dedicated system user `openclaw`:
 
-For boot persistence on SSH/headless hosts, enable lingering for your current user:
+- **Shell:** `nologin` — no interactive login; reduces attack surface.
+- **Home:** e.g. `/home/openclaw` — holds `~/.openclaw` (config, workspace) and the launch script `run-openclaw-podman.sh`.
+- **Rootless Podman:** The user must have a **subuid** and **subgid** range. Many distros assign these automatically when the user is created. If setup prints a warning, add lines to `/etc/subuid` and `/etc/subgid`:
 
-```bash
-sudo loginctl enable-linger "$(whoami)"
-```
+  ```text
+  openclaw:100000:65536
+  ```
 
-## Config, env, and storage
+  Then start the gateway as that user (e.g. from cron or systemd):
 
-- **Config dir:** `~/.openclaw`
-- **Workspace dir:** `~/.openclaw/workspace`
-- **Token file:** `~/.openclaw/.env`
-- **Launch helper:** `./scripts/run-openclaw-podman.sh`
+  ```bash
+  sudo -u openclaw /home/openclaw/run-openclaw-podman.sh
+  sudo -u openclaw /home/openclaw/run-openclaw-podman.sh setup
+  ```
 
-The launch script and Quadlet bind-mount host state into the container:
+- **Config:** Only `openclaw` and root can access `/home/openclaw/.openclaw`. To edit config: use the Control UI once the gateway is running, or `sudo -u openclaw $EDITOR /home/openclaw/.openclaw/openclaw.json`.
 
-- `OPENCLAW_CONFIG_DIR` -> `/home/node/.openclaw`
-- `OPENCLAW_WORKSPACE_DIR` -> `/home/node/.openclaw/workspace`
+## Environment and config
 
-By default those are host directories, not anonymous container state, so config and workspace survive container replacement.
-The Podman setup also seeds `gateway.controlUi.allowedOrigins` for `127.0.0.1` and `localhost` on the published gateway port so the local dashboard works with the container's non-loopback bind.
+- **Token:** Stored in `~openclaw/.openclaw/.env` as `OPENCLAW_GATEWAY_TOKEN`. `scripts/podman/setup.sh` and `run-openclaw-podman.sh` generate it if missing (uses `openssl`, `python3`, or `od`).
+- **Optional:** In that `.env` you can set provider keys (e.g. `GROQ_API_KEY`, `OLLAMA_API_KEY`) and other OpenClaw env vars.
+- **Host ports:** By default the script maps `18789` (gateway) and `18790` (bridge). Override the **host** port mapping with `OPENCLAW_PODMAN_GATEWAY_HOST_PORT` and `OPENCLAW_PODMAN_BRIDGE_HOST_PORT` when launching.
+- **Gateway bind:** By default, `run-openclaw-podman.sh` starts the gateway with `--bind loopback` for safe local access. To expose on LAN, set `OPENCLAW_GATEWAY_BIND=lan` and configure `gateway.controlUi.allowedOrigins` (or explicitly enable host-header fallback) in `openclaw.json`.
+- **Paths:** Host config and workspace default to `~openclaw/.openclaw` and `~openclaw/.openclaw/workspace`. Override the host paths used by the launch script with `OPENCLAW_CONFIG_DIR` and `OPENCLAW_WORKSPACE_DIR`.
 
-Useful env vars for the manual launcher:
+## Storage model
 
-- `OPENCLAW_PODMAN_CONTAINER` -- container name (`openclaw` by default)
-- `OPENCLAW_PODMAN_IMAGE` / `OPENCLAW_IMAGE` -- image to run
-- `OPENCLAW_PODMAN_GATEWAY_HOST_PORT` -- host port mapped to container `18789`
-- `OPENCLAW_PODMAN_BRIDGE_HOST_PORT` -- host port mapped to container `18790`
-- `OPENCLAW_PODMAN_PUBLISH_HOST` -- host interface for published ports; default is `127.0.0.1`
-- `OPENCLAW_GATEWAY_BIND` -- gateway bind mode inside the container; default is `lan`
-- `OPENCLAW_PODMAN_USERNS` -- `keep-id` (default), `auto`, or `host`
+- **Persistent host data:** `OPENCLAW_CONFIG_DIR` and `OPENCLAW_WORKSPACE_DIR` are bind-mounted into the container and retain state on the host.
+- **Ephemeral sandbox tmpfs:** if you enable `agents.defaults.sandbox`, the tool sandbox containers mount `tmpfs` at `/tmp`, `/var/tmp`, and `/run`. Those paths are memory-backed and disappear with the sandbox container; the top-level Podman container setup does not add its own tmpfs mounts.
+- **Disk growth hotspots:** the main paths to watch are `media/`, `agents/<agentId>/sessions/sessions.json`, transcript JSONL files, `cron/runs/*.jsonl`, and rolling file logs under `/tmp/openclaw/` (or your configured `logging.file`).
 
-The manual launcher reads `~/.openclaw/.env` before finalizing container/image defaults, so you can persist these there.
-
-If you use a non-default `OPENCLAW_CONFIG_DIR` or `OPENCLAW_WORKSPACE_DIR`, set the same variables for both `./scripts/podman/setup.sh` and later `./scripts/run-openclaw-podman.sh launch` commands. The repo-local launcher does not persist custom path overrides across shells.
-
-Quadlet note:
-
-- The generated Quadlet service intentionally keeps a fixed, hardened default shape: `127.0.0.1` published ports, `--bind lan` inside the container, and `keep-id` user namespace.
-- It still reads `~/.openclaw/.env` for gateway runtime env such as `OPENCLAW_GATEWAY_TOKEN`, but it does not consume the manual launcher's Podman-specific override allowlist.
-- If you need custom publish ports, publish host, or other container-run flags, use the manual launcher or edit `~/.config/containers/systemd/openclaw.container` directly, then reload and restart the service.
+`scripts/podman/setup.sh` now stages the image tar in a private temp directory and prints the chosen base dir during setup. For non-root runs it accepts `TMPDIR` only when that base is safe to use; otherwise it falls back to `/var/tmp`, then `/tmp`. The saved tar stays owner-only and is streamed into the target user’s `podman load`, so private caller temp dirs do not block setup.
 
 ## Useful commands
 
-- **Container logs:** `podman logs -f openclaw`
-- **Stop container:** `podman stop openclaw`
-- **Remove container:** `podman rm -f openclaw`
-- **Open dashboard URL from host CLI:** `openclaw dashboard --no-open`
-- **Health/status via host CLI:** `openclaw gateway status --deep`
+- **Logs:** With quadlet: `sudo journalctl --machine openclaw@ --user -u openclaw.service -f`. With script: `sudo -u openclaw podman logs -f openclaw`
+- **Stop:** With quadlet: `sudo systemctl --machine openclaw@ --user stop openclaw.service`. With script: `sudo -u openclaw podman stop openclaw`
+- **Start again:** With quadlet: `sudo systemctl --machine openclaw@ --user start openclaw.service`. With script: re-run the launch script or `podman start openclaw`
+- **Remove container:** `sudo -u openclaw podman rm -f openclaw` — config and workspace on the host are kept
 
 ## Troubleshooting
 
-- **Permission denied (EACCES) on config or workspace:** The container runs with `--userns=keep-id` and `--user <your uid>:<your gid>` by default. Ensure the host config/workspace paths are owned by your current user.
-- **Gateway start blocked (missing `gateway.mode=local`):** Ensure `~/.openclaw/openclaw.json` exists and sets `gateway.mode="local"`. `scripts/podman/setup.sh` creates this if missing.
-- **Container CLI commands hit the wrong target:** Use `openclaw --container <name> ...` explicitly, or export `OPENCLAW_CONTAINER=<name>` in your shell.
-- **`openclaw update` fails with `--container`:** Expected. Rebuild/pull the image, then restart the container or the Quadlet service.
-- **Quadlet service does not start:** Run `systemctl --user daemon-reload`, then `systemctl --user start openclaw.service`. On headless systems you may also need `sudo loginctl enable-linger "$(whoami)"`.
-- **SELinux blocks bind mounts:** Leave the default mount behavior alone; the launcher auto-adds `:Z` on Linux when SELinux is enforcing or permissive.
+- **Permission denied (EACCES) on config or auth-profiles:** The container defaults to `--userns=keep-id` and runs as the same uid/gid as the host user running the script. Ensure your host `OPENCLAW_CONFIG_DIR` and `OPENCLAW_WORKSPACE_DIR` are owned by that user.
+- **Gateway start blocked (missing `gateway.mode=local`):** Ensure `~openclaw/.openclaw/openclaw.json` exists and sets `gateway.mode="local"`. `scripts/podman/setup.sh` creates this file if missing.
+- **Rootless Podman fails for user openclaw:** Check `/etc/subuid` and `/etc/subgid` contain a line for `openclaw` (e.g. `openclaw:100000:65536`). Add it if missing and restart.
+- **Container name in use:** The launch script uses `podman run --replace`, so the existing container is replaced when you start again. To clean up manually: `podman rm -f openclaw`.
+- **Script not found when running as openclaw:** Ensure `scripts/podman/setup.sh` was run so that `run-openclaw-podman.sh` is copied to openclaw’s home (e.g. `/home/openclaw/run-openclaw-podman.sh`).
+- **Quadlet service not found or fails to start:** Run `sudo systemctl --machine openclaw@ --user daemon-reload` after editing the `.container` file. Quadlet requires cgroups v2: `podman info --format '{{.Host.CgroupsVersion}}'` should show `2`.
 
-## Related
+## Optional: run as your own user
 
-- [Docker](/install/docker)
-- [Gateway background process](/gateway/background-process)
-- [Gateway troubleshooting](/gateway/troubleshooting)
+To run the gateway as your normal user (no dedicated openclaw user): build the image, create `~/.openclaw/.env` with `OPENCLAW_GATEWAY_TOKEN`, and run the container with `--userns=keep-id` and mounts to your `~/.openclaw`. The launch script is designed for the openclaw-user flow; for a single-user setup you can instead run the `podman run` command from the script manually, pointing config and workspace to your home. Recommended for most users: use `scripts/podman/setup.sh` and run as the openclaw user so config and process are isolated.

docs/platforms/linux.md

@@ -15,7 +15,7 @@ Native Linux companion apps are planned. Contributions are welcome if you want t
 
 ## Beginner quick path (VPS)
 
-1. Install Node 24 (recommended; Node 22 LTS, currently `22.14+`, still works for compatibility)
+1. Install Node 24 (recommended; Node 22 LTS, currently `22.16+`, still works for compatibility)
 2. `npm i -g openclaw@latest`
 3. `openclaw onboard --install-daemon`
 4. From your laptop: `ssh -N -L 18789:127.0.0.1:18789 <user>@<host>`

docs/platforms/mac/bundled-gateway.md

@@ -16,7 +16,7 @@ running (or attaches to an existing local Gateway if one is already running).
 
 ## Install the CLI (required for local mode)
 
-Node 24 is the default runtime on the Mac. Node 22 LTS, currently `22.14+`, still works for compatibility. Then install `openclaw` globally:
+Node 24 is the default runtime on the Mac. Node 22 LTS, currently `22.16+`, still works for compatibility. Then install `openclaw` globally:
 
 ```bash
 npm install -g openclaw@<version>

docs/platforms/mac/dev-setup.md

@@ -14,7 +14,7 @@ This guide covers the necessary steps to build and run the OpenClaw macOS applic
 Before building the app, ensure you have the following installed:
 
 1. **Xcode 26.2+**: Required for Swift development.
-2. **Node.js 24 & pnpm**: Recommended for the gateway, CLI, and packaging scripts. Node 22 LTS, currently `22.14+`, remains supported for compatibility.
+2. **Node.js 24 & pnpm**: Recommended for the gateway, CLI, and packaging scripts. Node 22 LTS, currently `22.16+`, remains supported for compatibility.
 
 ## 1. Install Dependencies
 

docs/platforms/mac/signing.md

@@ -14,7 +14,7 @@ This app is usually built from [`scripts/package-mac-app.sh`](https://github.com
 - calls [`scripts/codesign-mac-app.sh`](https://github.com/openclaw/openclaw/blob/main/scripts/codesign-mac-app.sh) to sign the main binary and app bundle so macOS treats each rebuild as the same signed bundle and keeps TCC permissions (notifications, accessibility, screen recording, mic, speech). For stable permissions, use a real signing identity; ad-hoc is opt-in and fragile (see [macOS permissions](/platforms/mac/permissions)).
 - uses `CODESIGN_TIMESTAMP=auto` by default; it enables trusted timestamps for Developer ID signatures. Set `CODESIGN_TIMESTAMP=off` to skip timestamping (offline debug builds).
 - inject build metadata into Info.plist: `OpenClawBuildTimestamp` (UTC) and `OpenClawGitCommit` (short hash) so the About pane can show build, git, and debug/release channel.
-- **Packaging defaults to Node 24**: the script runs TS builds and the Control UI build. Node 22 LTS, currently `22.14+`, remains supported for compatibility.
+- **Packaging defaults to Node 24**: the script runs TS builds and the Control UI build. Node 22 LTS, currently `22.16+`, remains supported for compatibility.
 - reads `SIGN_IDENTITY` from the environment. Add `export SIGN_IDENTITY="Apple Development: Your Name (TEAMID)"` (or your Developer ID Application cert) to your shell rc to always sign with your cert. Ad-hoc signing requires explicit opt-in via `ALLOW_ADHOC_SIGNING=1` or `SIGN_IDENTITY="-"` (not recommended for permission testing).
 - runs a Team ID audit after signing and fails if any Mach-O inside the app bundle is signed by a different Team ID. Set `SKIP_TEAM_ID_CHECK=1` to bypass.
 

docs/plugins/architecture.md

@@ -27,15 +27,14 @@ This page covers the internal architecture of the OpenClaw plugin system.
 Capabilities are the public **native plugin** model inside OpenClaw. Every
 native OpenClaw plugin registers against one or more capability types:
 
-| Capability            | Registration method                           | Example plugins           |
-| --------------------- | --------------------------------------------- | ------------------------- |
-| Text inference        | `api.registerProvider(...)`                   | `openai`, `anthropic`     |
-| CLI inference backend | `api.registerCliBackend(...)`                 | `openai`, `anthropic`     |
-| Speech                | `api.registerSpeechProvider(...)`             | `elevenlabs`, `microsoft` |
-| Media understanding   | `api.registerMediaUnderstandingProvider(...)` | `openai`, `google`        |
-| Image generation      | `api.registerImageGenerationProvider(...)`    | `openai`, `google`        |
-| Web search            | `api.registerWebSearchProvider(...)`          | `google`                  |
-| Channel / messaging   | `api.registerChannel(...)`                    | `msteams`, `matrix`       |
+| Capability          | Registration method                           | Example plugins           |
+| ------------------- | --------------------------------------------- | ------------------------- |
+| Text inference      | `api.registerProvider(...)`                   | `openai`, `anthropic`     |
+| Speech              | `api.registerSpeechProvider(...)`             | `elevenlabs`, `microsoft` |
+| Media understanding | `api.registerMediaUnderstandingProvider(...)` | `openai`, `google`        |
+| Image generation    | `api.registerImageGenerationProvider(...)`    | `openai`, `google`        |
+| Web search          | `api.registerWebSearchProvider(...)`          | `google`                  |
+| Channel / messaging | `api.registerChannel(...)`                    | `msteams`, `matrix`       |
 
 A plugin that registers zero capabilities but provides hooks, tools, or
 services is a **legacy hook-only** plugin. That pattern is still fully supported.

docs/plugins/building-plugins.md

@@ -128,20 +128,19 @@ and provider plugins have dedicated guides linked above.
 
 A single plugin can register any number of capabilities via the `api` object:
 
-| Capability            | Registration method                           | Detailed guide                                                                  |
-| --------------------- | --------------------------------------------- | ------------------------------------------------------------------------------- |
-| Text inference (LLM)  | `api.registerProvider(...)`                   | [Provider Plugins](/plugins/sdk-provider-plugins)                               |
-| CLI inference backend | `api.registerCliBackend(...)`                 | [CLI Backends](/gateway/cli-backends)                                           |
-| Channel / messaging   | `api.registerChannel(...)`                    | [Channel Plugins](/plugins/sdk-channel-plugins)                                 |
-| Speech (TTS/STT)      | `api.registerSpeechProvider(...)`             | [Provider Plugins](/plugins/sdk-provider-plugins#step-5-add-extra-capabilities) |
-| Media understanding   | `api.registerMediaUnderstandingProvider(...)` | [Provider Plugins](/plugins/sdk-provider-plugins#step-5-add-extra-capabilities) |
-| Image generation      | `api.registerImageGenerationProvider(...)`    | [Provider Plugins](/plugins/sdk-provider-plugins#step-5-add-extra-capabilities) |
-| Web search            | `api.registerWebSearchProvider(...)`          | [Provider Plugins](/plugins/sdk-provider-plugins#step-5-add-extra-capabilities) |
-| Agent tools           | `api.registerTool(...)`                       | Below                                                                           |
-| Custom commands       | `api.registerCommand(...)`                    | [Entry Points](/plugins/sdk-entrypoints)                                        |
-| Event hooks           | `api.registerHook(...)`                       | [Entry Points](/plugins/sdk-entrypoints)                                        |
-| HTTP routes           | `api.registerHttpRoute(...)`                  | [Internals](/plugins/architecture#gateway-http-routes)                          |
-| CLI subcommands       | `api.registerCli(...)`                        | [Entry Points](/plugins/sdk-entrypoints)                                        |
+| Capability           | Registration method                           | Detailed guide                                                                  |
+| -------------------- | --------------------------------------------- | ------------------------------------------------------------------------------- |
+| Text inference (LLM) | `api.registerProvider(...)`                   | [Provider Plugins](/plugins/sdk-provider-plugins)                               |
+| Channel / messaging  | `api.registerChannel(...)`                    | [Channel Plugins](/plugins/sdk-channel-plugins)                                 |
+| Speech (TTS/STT)     | `api.registerSpeechProvider(...)`             | [Provider Plugins](/plugins/sdk-provider-plugins#step-5-add-extra-capabilities) |
+| Media understanding  | `api.registerMediaUnderstandingProvider(...)` | [Provider Plugins](/plugins/sdk-provider-plugins#step-5-add-extra-capabilities) |
+| Image generation     | `api.registerImageGenerationProvider(...)`    | [Provider Plugins](/plugins/sdk-provider-plugins#step-5-add-extra-capabilities) |
+| Web search           | `api.registerWebSearchProvider(...)`          | [Provider Plugins](/plugins/sdk-provider-plugins#step-5-add-extra-capabilities) |
+| Agent tools          | `api.registerTool(...)`                       | Below                                                                           |
+| Custom commands      | `api.registerCommand(...)`                    | [Entry Points](/plugins/sdk-entrypoints)                                        |
+| Event hooks          | `api.registerHook(...)`                       | [Entry Points](/plugins/sdk-entrypoints)                                        |
+| HTTP routes          | `api.registerHttpRoute(...)`                  | [Internals](/plugins/architecture#gateway-http-routes)                          |
+| CLI subcommands      | `api.registerCli(...)`                        | [Entry Points](/plugins/sdk-entrypoints)                                        |
 
 For the full registration API, see [SDK Overview](/plugins/sdk-overview#registration-api).
 
@@ -149,8 +148,6 @@ Hook guard semantics to keep in mind:
 
 - `before_tool_call`: `{ block: true }` is terminal and stops lower-priority handlers.
 - `before_tool_call`: `{ block: false }` is treated as no decision.
-- `before_skill_install`: `{ block: true }` is terminal and stops lower-priority handlers.
-- `before_skill_install`: `{ block: false }` is treated as no decision.
 - `message_sending`: `{ cancel: true }` is terminal and stops lower-priority handlers.
 - `message_sending`: `{ cancel: false }` is treated as no decision.
 
@@ -227,15 +224,6 @@ internal imports — never import your own plugin through its SDK path.
 <Check>Tests pass (`pnpm test -- extensions/my-plugin/`)</Check>
 <Check>`pnpm check` passes (in-repo plugins)</Check>
 
-## Beta Release Testing
-
-1. Watch for GitHub release tags on [openclaw/openclaw](https://github.com/openclaw/openclaw/releases) and subscribe via `Watch` > `Releases`. Beta tags look like `v2026.3.N-beta.1`. You can also turn on notifications for the official OpenClaw X account [@openclaw](https://x.com/openclaw) for release announcements.
-2. Test your plugin against the beta tag as soon as it appears. The window before stable is typically only a few hours.
-3. Post in your plugin's thread in the `plugin-forum` Discord channel after testing with either `all good` or what broke. If you do not have a thread yet, create one.
-4. If something breaks, open or update an issue titled `Beta blocker: <plugin-name> - <summary>` and apply the `beta-blocker` label. Put the issue link in your thread.
-5. Open a PR to `main` titled `fix(<plugin-id>): beta blocker - <summary>` and link the issue in both the PR and your Discord thread. Contributors cannot label PRs, so the title is the PR-side signal for maintainers and automation. Blockers with a PR get merged; blockers without one might ship anyway. Maintainers watch these threads during beta testing.
-6. Silence means green. If you miss the window, your fix likely lands in the next cycle.
-
 ## Next steps
 
 <CardGroup cols={2}>

docs/plugins/manifest.md

@@ -46,8 +46,6 @@ Use it for:
 - config validation
 - auth and onboarding metadata that should be available without booting plugin
   runtime
-- static capability ownership snapshots used for bundled compat wiring and
-  contract coverage
 - config UI hints
 
 Do not use it for:
@@ -80,7 +78,6 @@ Those belong in your plugin code and `package.json`.
   "description": "OpenRouter provider plugin",
   "version": "1.0.0",
   "providers": ["openrouter"],
-  "cliBackends": ["openrouter-cli"],
   "providerAuthEnvVars": {
     "openrouter": ["OPENROUTER_API_KEY"]
   },
@@ -128,10 +125,8 @@ Those belong in your plugin code and `package.json`.
 | `kind`                | No       | `"memory"` \| `"context-engine"` | Declares an exclusive plugin kind used by `plugins.slots.*`.                                                                 |
 | `channels`            | No       | `string[]`                       | Channel ids owned by this plugin. Used for discovery and config validation.                                                  |
 | `providers`           | No       | `string[]`                       | Provider ids owned by this plugin.                                                                                           |
-| `cliBackends`         | No       | `string[]`                       | CLI inference backend ids owned by this plugin. Used for startup auto-activation from explicit config refs.                  |
 | `providerAuthEnvVars` | No       | `Record<string, string[]>`       | Cheap provider-auth env metadata that OpenClaw can inspect without loading plugin code.                                      |
 | `providerAuthChoices` | No       | `object[]`                       | Cheap auth-choice metadata for onboarding pickers, preferred-provider resolution, and simple CLI flag wiring.                |
-| `contracts`           | No       | `object`                         | Static bundled capability snapshot for speech, media-understanding, image-generation, web search, and tool ownership.        |
 | `skills`              | No       | `string[]`                       | Skill directories to load, relative to the plugin root.                                                                      |
 | `name`                | No       | `string`                         | Human-readable plugin name.                                                                                                  |
 | `description`         | No       | `string`                         | Short summary shown in plugin surfaces.                                                                                      |
@@ -187,38 +182,6 @@ Each field hint can include:
 | `sensitive`   | `boolean`  | Marks the field as secret or sensitive. |
 | `placeholder` | `string`   | Placeholder text for form inputs.       |
 
-## contracts reference
-
-Use `contracts` only for static capability ownership metadata that OpenClaw can
-read without importing the plugin runtime.
-
-```json
-{
-  "contracts": {
-    "speechProviders": ["openai"],
-    "mediaUnderstandingProviders": ["openai", "openai-codex"],
-    "imageGenerationProviders": ["openai"],
-    "webSearchProviders": ["gemini"],
-    "tools": ["firecrawl_search", "firecrawl_scrape"]
-  }
-}
-```
-
-Each list is optional:
-
-| Field                         | Type       | What it means                                                  |
-| ----------------------------- | ---------- | -------------------------------------------------------------- |
-| `speechProviders`             | `string[]` | Speech provider ids this plugin owns.                          |
-| `mediaUnderstandingProviders` | `string[]` | Media-understanding provider ids this plugin owns.             |
-| `imageGenerationProviders`    | `string[]` | Image-generation provider ids this plugin owns.                |
-| `webSearchProviders`          | `string[]` | Web-search provider ids this plugin owns.                      |
-| `tools`                       | `string[]` | Agent tool names this plugin owns for bundled contract checks. |
-
-Legacy top-level `speechProviders`, `mediaUnderstandingProviders`, and
-`imageGenerationProviders` are deprecated. Use `openclaw doctor --fix` to move
-them under `contracts`; normal manifest loading no longer treats them as
-capability ownership.
-
 ## Manifest versus package.json
 
 The two files serve different jobs:
@@ -271,8 +234,8 @@ See [Configuration reference](/gateway/configuration) for the full `plugins.*` s
   - `kind: "memory"` is selected by `plugins.slots.memory`.
   - `kind: "context-engine"` is selected by `plugins.slots.contextEngine`
     (default: built-in `legacy`).
-- `channels`, `providers`, `cliBackends`, and `skills` can be omitted when a
-  plugin does not need them.
+- `channels`, `providers`, and `skills` can be omitted when a plugin does not
+  need them.
 - If your plugin depends on native modules, document the build steps and any
   package-manager allowlist requirements (for example, pnpm `allow-build-scripts`
   - `pnpm rebuild <package>`).

docs/plugins/sdk-overview.md

@@ -66,7 +66,6 @@ subpaths is in `scripts/lib/plugin-sdk-entrypoints.json`.
   <Accordion title="Provider subpaths">
     | Subpath | Key exports |
     | --- | --- |
-    | `plugin-sdk/cli-backend` | CLI backend defaults + watchdog constants |
     | `plugin-sdk/provider-auth` | `createProviderApiKeyAuthMethod`, `ensureApiKeyFromOptionEnvOrPrompt`, `upsertAuthProfile` |
     | `plugin-sdk/provider-models` | `normalizeModelCompat` |
     | `plugin-sdk/provider-catalog` | Catalog type re-exports |
@@ -115,7 +114,6 @@ methods:
 | Method                                        | What it registers              |
 | --------------------------------------------- | ------------------------------ |
 | `api.registerProvider(...)`                   | Text inference (LLM)           |
-| `api.registerCliBackend(...)`                 | Local CLI inference backend    |
 | `api.registerChannel(...)`                    | Messaging channel              |
 | `api.registerSpeechProvider(...)`             | Text-to-speech / STT synthesis |
 | `api.registerMediaUnderstandingProvider(...)` | Image/audio/video analysis     |
@@ -140,41 +138,12 @@ methods:
 | `api.registerService(service)`                 | Background service    |
 | `api.registerInteractiveHandler(registration)` | Interactive handler   |
 
-### CLI backend registration
-
-`api.registerCliBackend(...)` lets a plugin own the default config for a local
-AI CLI backend such as `claude-cli` or `codex-cli`.
-
-- The backend `id` becomes the provider prefix in model refs like `claude-cli/opus`.
-- The backend `config` uses the same shape as `agents.defaults.cliBackends.<id>`.
-- User config still wins. OpenClaw merges `agents.defaults.cliBackends.<id>` over the
-  plugin default before running the CLI.
-- Use `normalizeConfig` when a backend needs compatibility rewrites after merge
-  (for example normalizing old flag shapes).
-
 ### Exclusive slots
 
 | Method                                     | What it registers                     |
 | ------------------------------------------ | ------------------------------------- |
 | `api.registerContextEngine(id, factory)`   | Context engine (one active at a time) |
 | `api.registerMemoryPromptSection(builder)` | Memory prompt section builder         |
-| `api.registerMemoryFlushPlan(resolver)`    | Memory flush plan resolver            |
-| `api.registerMemoryRuntime(runtime)`       | Memory runtime adapter                |
-
-### Memory embedding adapters
-
-| Method                                         | What it registers                              |
-| ---------------------------------------------- | ---------------------------------------------- |
-| `api.registerMemoryEmbeddingProvider(adapter)` | Memory embedding adapter for the active plugin |
-
-- `registerMemoryPromptSection`, `registerMemoryFlushPlan`, and
-  `registerMemoryRuntime` are exclusive to memory plugins.
-- `registerMemoryEmbeddingProvider` lets the active memory plugin register one
-  or more embedding adapter ids (for example `openai`, `gemini`, or a custom
-  plugin-defined id).
-- User config such as `agents.defaults.memorySearch.provider` and
-  `agents.defaults.memorySearch.fallback` resolves against those registered
-  adapter ids.
 
 ### Events and lifecycle
 
@@ -187,8 +156,6 @@ AI CLI backend such as `claude-cli` or `codex-cli`.
 
 - `before_tool_call`: returning `{ block: true }` is terminal. Once any handler sets it, lower-priority handlers are skipped.
 - `before_tool_call`: returning `{ block: false }` is treated as no decision (same as omitting `block`), not as an override.
-- `before_skill_install`: returning `{ block: true }` is terminal. Once any handler sets it, lower-priority handlers are skipped.
-- `before_skill_install`: returning `{ block: false }` is treated as no decision (same as omitting `block`), not as an override.
 - `message_sending`: returning `{ cancel: true }` is terminal. Once any handler sets it, lower-priority handlers are skipped.
 - `message_sending`: returning `{ cancel: false }` is treated as no decision (same as omitting `cancel`), not as an override.
 

docs/providers/anthropic.md

@@ -1,9 +1,8 @@
 ---
-summary: "Use Anthropic Claude via API keys, setup-token, or Claude CLI in OpenClaw"
+summary: "Use Anthropic Claude via API keys or setup-token in OpenClaw"
 read_when:
   - You want to use Anthropic models in OpenClaw
   - You want setup-token instead of API keys
-  - You want to reuse Claude CLI subscription auth on the gateway host
 title: "Anthropic"
 ---
 
@@ -27,7 +26,7 @@ openclaw onboard
 openclaw onboard --anthropic-api-key "$ANTHROPIC_API_KEY"
 ```
 
-### Claude CLI config snippet
+### Config snippet
 
 ```json5
 {
@@ -187,122 +186,7 @@ Note: Anthropic currently rejects `context-1m-*` beta requests when using
 OAuth/subscription tokens (`sk-ant-oat-*`). OpenClaw automatically skips the
 context1m beta header for OAuth auth and keeps the required OAuth betas.
 
-## Option B: Claude CLI as the message provider
-
-**Best for:** a single-user gateway host that already has Claude CLI installed
-and signed in with a Claude subscription.
-
-This path uses the local `claude` binary for model inference instead of calling
-the Anthropic API directly. OpenClaw treats it as a **CLI backend provider**
-with model refs like:
-
-- `claude-cli/claude-sonnet-4-6`
-- `claude-cli/claude-opus-4-6`
-
-How it works:
-
-1. OpenClaw launches `claude -p --output-format json ...` on the **gateway
-   host**.
-2. The first turn sends `--session-id <uuid>`.
-3. Follow-up turns reuse the stored Claude session via `--resume <sessionId>`.
-4. Your chat messages still go through the normal OpenClaw message pipeline, but
-   the actual model reply is produced by Claude CLI.
-
-### Requirements
-
-- Claude CLI installed on the gateway host and available on PATH, or configured
-  with an absolute command path.
-- Claude CLI already authenticated on that same host:
-
-```bash
-claude auth status
-```
-
-- OpenClaw auto-loads the bundled Anthropic plugin at gateway startup when your
-  config explicitly references `claude-cli/...` or `claude-cli` backend config.
-
-### Config snippet
-
-```json5
-{
-  agents: {
-    defaults: {
-      model: {
-        primary: "claude-cli/claude-sonnet-4-6",
-      },
-      models: {
-        "claude-cli/claude-sonnet-4-6": {},
-      },
-      sandbox: { mode: "off" },
-    },
-  },
-}
-```
-
-If the `claude` binary is not on the gateway host PATH:
-
-```json5
-{
-  agents: {
-    defaults: {
-      cliBackends: {
-        "claude-cli": {
-          command: "/opt/homebrew/bin/claude",
-        },
-      },
-    },
-  },
-}
-```
-
-### What you get
-
-- Claude subscription auth reused from the local CLI
-- Normal OpenClaw message/session routing
-- Claude CLI session continuity across turns
-
-### Migrate from Anthropic auth to Claude CLI
-
-If you currently use `anthropic/...` with a setup-token or API key and want to
-switch the same gateway host to Claude CLI:
-
-```bash
-openclaw models auth login --provider anthropic --method cli --set-default
-```
-
-Or in onboarding:
-
-```bash
-openclaw onboard --auth-choice anthropic-cli
-```
-
-What this does:
-
-- verifies Claude CLI is already signed in on the gateway host
-- switches the default model to `claude-cli/...`
-- rewrites Anthropic default-model fallbacks like `anthropic/claude-opus-4-6`
-  to `claude-cli/claude-opus-4-6`
-- adds matching `claude-cli/...` entries to `agents.defaults.models`
-
-What it does **not** do:
-
-- delete your existing Anthropic auth profiles
-- remove every old `anthropic/...` config reference outside the main default
-  model/allowlist path
-
-That makes rollback simple: change the default model back to `anthropic/...` if
-you need to.
-
-### Important limits
-
-- This is **not** the Anthropic API provider. It is the local CLI runtime.
-- Tools are disabled on the OpenClaw side for CLI backend runs.
-- Text in, text out. No OpenClaw streaming handoff.
-- Best fit for a personal gateway host, not shared multi-user billing setups.
-
-More details: [/gateway/cli-backends](/gateway/cli-backends)
-
-## Option C: Claude setup-token
+## Option B: Claude setup-token
 
 **Best for:** using your Claude subscription.
 

docs/providers/index.md

@@ -39,6 +39,7 @@ Looking for chat channel docs (WhatsApp/Telegram/Discord/Slack/Mattermost (plugi
 - [LiteLLM (unified gateway)](/providers/litellm)
 - [MiniMax](/providers/minimax)
 - [Mistral](/providers/mistral)
+- [Model Studio (Alibaba Cloud)](/providers/modelstudio)
 - [Moonshot AI (Kimi + Kimi Coding)](/providers/moonshot)
 - [NVIDIA](/providers/nvidia)
 - [Ollama (cloud + local models)](/providers/ollama)
@@ -48,7 +49,7 @@ Looking for chat channel docs (WhatsApp/Telegram/Discord/Slack/Mattermost (plugi
 - [OpenRouter](/providers/openrouter)
 - [Perplexity (web search)](/providers/perplexity-provider)
 - [Qianfan](/providers/qianfan)
-- [Qwen / Model Studio (Alibaba Cloud)](/providers/qwen_modelstudio)
+- [Qwen (OAuth)](/providers/qwen)
 - [SGLang (local models)](/providers/sglang)
 - [Synthetic](/providers/synthetic)
 - [Together AI](/providers/together)

docs/providers/minimax.md

@@ -8,12 +8,16 @@ title: "MiniMax"
 
 # MiniMax
 
-OpenClaw's MiniMax provider defaults to **MiniMax M2.7**.
+OpenClaw's MiniMax provider defaults to **MiniMax M2.7** and keeps
+**MiniMax M2.5** in the catalog for compatibility.
 
 ## Model lineup
 
 - `MiniMax-M2.7`: default hosted text model.
 - `MiniMax-M2.7-highspeed`: faster M2.7 text tier.
+- `MiniMax-M2.5`: previous text model, still available in the MiniMax catalog.
+- `MiniMax-M2.5-highspeed`: faster M2.5 text tier.
+- `MiniMax-VL-01`: vision model for text + image inputs.
 
 ## Choose a setup
 
@@ -76,6 +80,24 @@ Configure via CLI:
             contextWindow: 200000,
             maxTokens: 8192,
           },
+          {
+            id: "MiniMax-M2.5",
+            name: "MiniMax M2.5",
+            reasoning: true,
+            input: ["text"],
+            cost: { input: 0.3, output: 1.2, cacheRead: 0.03, cacheWrite: 0.12 },
+            contextWindow: 200000,
+            maxTokens: 8192,
+          },
+          {
+            id: "MiniMax-M2.5-highspeed",
+            name: "MiniMax M2.5 Highspeed",
+            reasoning: true,
+            input: ["text"],
+            cost: { input: 0.3, output: 1.2, cacheRead: 0.03, cacheWrite: 0.12 },
+            contextWindow: 200000,
+            maxTokens: 8192,
+          },
         ],
       },
     },
@@ -106,6 +128,46 @@ Example below uses Opus as a concrete primary; swap to your preferred latest-gen
 }
 ```
 
+### Optional: Local via LM Studio (manual)
+
+**Best for:** local inference with LM Studio.
+We have seen strong results with MiniMax M2.5 on powerful hardware (e.g. a
+desktop/server) using LM Studio's local server.
+
+Configure manually via `openclaw.json`:
+
+```json5
+{
+  agents: {
+    defaults: {
+      model: { primary: "lmstudio/minimax-m2.5-gs32" },
+      models: { "lmstudio/minimax-m2.5-gs32": { alias: "Minimax" } },
+    },
+  },
+  models: {
+    mode: "merge",
+    providers: {
+      lmstudio: {
+        baseUrl: "http://127.0.0.1:1234/v1",
+        apiKey: "lmstudio",
+        api: "openai-responses",
+        models: [
+          {
+            id: "minimax-m2.5-gs32",
+            name: "MiniMax M2.5 GS32",
+            reasoning: true,
+            input: ["text"],
+            cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+            contextWindow: 196608,
+            maxTokens: 8192,
+          },
+        ],
+      },
+    },
+  },
+}
+```
+
 ## Configure via `openclaw configure`
 
 Use the interactive config wizard to set MiniMax without editing JSON:
@@ -128,7 +190,7 @@ Use the interactive config wizard to set MiniMax without editing JSON:
 
 - Model refs are `minimax/<model>`.
 - Default text model: `MiniMax-M2.7`.
-- Alternate text model: `MiniMax-M2.7-highspeed`.
+- Alternate text models: `MiniMax-M2.7-highspeed`, `MiniMax-M2.5`, `MiniMax-M2.5-highspeed`.
 - Coding Plan usage API: `https://api.minimaxi.com/v1/api/openplatform/coding_plan/remains` (requires a coding plan key).
 - Update pricing values in `models.json` if you need exact cost tracking.
 - Referral link for MiniMax Coding Plan (10% off): [https://platform.minimax.io/subscribe/coding-plan?code=DbXJTRClnb&source=link](https://platform.minimax.io/subscribe/coding-plan?code=DbXJTRClnb&source=link)
@@ -152,6 +214,8 @@ Make sure the model id is **case‑sensitive**:
 
 - `minimax/MiniMax-M2.7`
 - `minimax/MiniMax-M2.7-highspeed`
+- `minimax/MiniMax-M2.5`
+- `minimax/MiniMax-M2.5-highspeed`
 
 Then recheck with:
 

docs/providers/modelstudio.md

@@ -0,0 +1,66 @@
+---
+title: "Model Studio"
+summary: "Alibaba Cloud Model Studio setup (Coding Plan, dual region endpoints)"
+read_when:
+  - You want to use Alibaba Cloud Model Studio with OpenClaw
+  - You need the API key env var for Model Studio
+---
+
+# Model Studio (Alibaba Cloud)
+
+The Model Studio provider gives access to Alibaba Cloud Coding Plan models,
+including Qwen and third-party models hosted on the platform.
+
+- Provider: `modelstudio`
+- Auth: `MODELSTUDIO_API_KEY`
+- API: OpenAI-compatible
+
+## Quick start
+
+1. Set the API key:
+
+```bash
+openclaw onboard --auth-choice modelstudio-api-key
+```
+
+2. Set a default model:
+
+```json5
+{
+  agents: {
+    defaults: {
+      model: { primary: "modelstudio/qwen3.5-plus" },
+    },
+  },
+}
+```
+
+## Region endpoints
+
+Model Studio has two endpoints based on region:
+
+| Region     | Endpoint                             |
+| ---------- | ------------------------------------ |
+| China (CN) | `coding.dashscope.aliyuncs.com`      |
+| Global     | `coding-intl.dashscope.aliyuncs.com` |
+
+The provider auto-selects based on the auth choice (`modelstudio-api-key` for
+global, `modelstudio-api-key-cn` for China). You can override with a custom
+`baseUrl` in config.
+
+## Available models
+
+- **qwen3.5-plus** (default) - Qwen 3.5 Plus
+- **qwen3-max** - Qwen 3 Max
+- **qwen3-coder** series - Qwen coding models
+- **GLM-5**, **GLM-4.7** - GLM models via Alibaba
+- **Kimi K2.5** - Moonshot AI via Alibaba
+- **MiniMax-M2.5** - MiniMax via Alibaba
+
+Most models support image input. Context windows range from 200K to 1M tokens.
+
+## Environment note
+
+If the Gateway runs as a daemon (launchd/systemd), make sure
+`MODELSTUDIO_API_KEY` is available to that process (for example, in
+`~/.openclaw/.env` or via `env.shellEnv`).

docs/providers/qwen.md

@@ -1,33 +1,53 @@
 ---
-summary: "Use Qwen models via Alibaba Cloud Model Studio"
+summary: "Use Qwen OAuth (free tier) in OpenClaw"
 read_when:
   - You want to use Qwen with OpenClaw
-  - You previously used Qwen OAuth
+  - You want free-tier OAuth access to Qwen Coder
 title: "Qwen"
 ---
 
 # Qwen
 
-<Warning>
+Qwen provides a free-tier OAuth flow for Qwen Coder and Qwen Vision models
+(2,000 requests/day, subject to Qwen rate limits).
 
-**Qwen OAuth has been removed.** The free-tier OAuth integration
-(`qwen-portal`) that used `portal.qwen.ai` endpoints is no longer available.
-See [Issue #49557](https://github.com/openclaw/openclaw/issues/49557) for
-background.
-
-</Warning>
-
-## Recommended: Model Studio (Alibaba Cloud Coding Plan)
-
-Use [Model Studio](/providers/modelstudio) for officially supported access to
-Qwen models (Qwen 3.5 Plus, GLM-4.7, Kimi K2.5, MiniMax M2.5, and more).
+## Enable the plugin
 
 ```bash
-# Global endpoint
-openclaw onboard --auth-choice modelstudio-api-key
-
-# China endpoint
-openclaw onboard --auth-choice modelstudio-api-key-cn
+openclaw plugins enable qwen-portal-auth
 ```
 
-See [Model Studio](/providers/modelstudio) for full setup details.
+Restart the Gateway after enabling.
+
+## Authenticate
+
+```bash
+openclaw models auth login --provider qwen-portal --set-default
+```
+
+This runs the Qwen device-code OAuth flow and writes a provider entry to your
+`models.json` (plus a `qwen` alias for quick switching).
+
+## Model IDs
+
+- `qwen-portal/coder-model`
+- `qwen-portal/vision-model`
+
+Switch models with:
+
+```bash
+openclaw models set qwen-portal/coder-model
+```
+
+## Reuse Qwen Code CLI login
+
+If you already logged in with the Qwen Code CLI, OpenClaw will sync credentials
+from `~/.qwen/oauth_creds.json` when it loads the auth store. You still need a
+`models.providers.qwen-portal` entry (use the login command above to create one).
+
+## Notes
+
+- Tokens auto-refresh; re-run the login command if refresh fails or access is revoked.
+- Default base URL: `https://portal.qwen.ai/v1` (override with
+  `models.providers.qwen-portal.baseUrl` if Qwen provides a different endpoint).
+- See [Model providers](/concepts/model-providers) for provider-wide rules.

docs/providers/qwen_modelstudio.md

@@ -1,85 +0,0 @@
----
-title: "Qwen / Model Studio"
-summary: "Alibaba Cloud Model Studio setup (Standard pay-as-you-go and Coding Plan, dual region endpoints)"
-read_when:
-  - You want to use Qwen (Alibaba Cloud Model Studio) with OpenClaw
-  - You need the API key env var for Model Studio
-  - You want to use the Standard (pay-as-you-go) or Coding Plan endpoint
----
-
-# Qwen / Model Studio (Alibaba Cloud)
-
-The Model Studio provider gives access to Alibaba Cloud models including Qwen
-and third-party models hosted on the platform. Two billing plans are supported:
-**Standard** (pay-as-you-go) and **Coding Plan** (subscription).
-
-- Provider: `modelstudio`
-- Auth: `MODELSTUDIO_API_KEY`
-- API: OpenAI-compatible
-
-## Quick start
-
-### Standard (pay-as-you-go)
-
-```bash
-# China endpoint
-openclaw onboard --auth-choice modelstudio-standard-api-key-cn
-
-# Global/Intl endpoint
-openclaw onboard --auth-choice modelstudio-standard-api-key
-```
-
-### Coding Plan (subscription)
-
-```bash
-# China endpoint
-openclaw onboard --auth-choice modelstudio-api-key-cn
-
-# Global/Intl endpoint
-openclaw onboard --auth-choice modelstudio-api-key
-```
-
-After onboarding, set a default model:
-
-```json5
-{
-  agents: {
-    defaults: {
-      model: { primary: "modelstudio/qwen3.5-plus" },
-    },
-  },
-}
-```
-
-## Plan types and endpoints
-
-| Plan                       | Region | Auth choice                       | Endpoint                                         |
-| -------------------------- | ------ | --------------------------------- | ------------------------------------------------ |
-| Standard (pay-as-you-go)   | China  | `modelstudio-standard-api-key-cn` | `dashscope.aliyuncs.com/compatible-mode/v1`      |
-| Standard (pay-as-you-go)   | Global | `modelstudio-standard-api-key`    | `dashscope-intl.aliyuncs.com/compatible-mode/v1` |
-| Coding Plan (subscription) | China  | `modelstudio-api-key-cn`          | `coding.dashscope.aliyuncs.com/v1`               |
-| Coding Plan (subscription) | Global | `modelstudio-api-key`             | `coding-intl.dashscope.aliyuncs.com/v1`          |
-
-The provider auto-selects the endpoint based on your auth choice. You can
-override with a custom `baseUrl` in config.
-
-## Get your API key
-
-- **China**: [bailian.console.aliyun.com](https://bailian.console.aliyun.com/)
-- **Global/Intl**: [modelstudio.console.alibabacloud.com](https://modelstudio.console.alibabacloud.com/)
-
-## Available models
-
-- **qwen3.5-plus** (default) — Qwen 3.5 Plus
-- **qwen3-coder-plus**, **qwen3-coder-next** — Qwen coding models
-- **GLM-5** — GLM models via Alibaba
-- **Kimi K2.5** — Moonshot AI via Alibaba
-- **MiniMax-M2.5** — MiniMax via Alibaba
-
-Some models (qwen3.5-plus, kimi-k2.5) support image input. Context windows range from 200K to 1M tokens.
-
-## Environment note
-
-If the Gateway runs as a daemon (launchd/systemd), make sure
-`MODELSTUDIO_API_KEY` is available to that process (for example, in
-`~/.openclaw/.env` or via `env.shellEnv`).

docs/reference/memory-config.md

@@ -20,12 +20,7 @@ automatic flush), see [Memory](/concepts/memory).
 - Watches memory files for changes (debounced).
 - Configure memory search under `agents.defaults.memorySearch` (not top-level
   `memorySearch`).
-- `memorySearch.provider` and `memorySearch.fallback` accept **adapter ids**
-  registered by the active memory plugin.
-- The default `memory-core` plugin registers these built-in adapter ids:
-  `local`, `openai`, `gemini`, `voyage`, `mistral`, and `ollama`.
-- With the default `memory-core` plugin, if `memorySearch.provider` is not set,
-  OpenClaw auto-selects:
+- Uses remote embeddings by default. If `memorySearch.provider` is not set, OpenClaw auto-selects:
   1. `local` if a `memorySearch.local.modelPath` is configured and the file exists.
   2. `openai` if an OpenAI key can be resolved.
   3. `gemini` if a Gemini key can be resolved.
@@ -34,9 +29,8 @@ automatic flush), see [Memory](/concepts/memory).
   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.
-- With the default `memory-core` plugin, `memorySearch.provider = "ollama"` is
-  also supported for local/self-hosted Ollama embeddings (`/api/embeddings`),
-  but it is not auto-selected.
+- `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
@@ -323,16 +317,15 @@ If you don't want to set an API key, use `memorySearch.provider = "local"` or se
 
 ### Fallbacks
 
-- `memorySearch.fallback` can be any registered memory embedding adapter id, or `none`.
-- With the default `memory-core` plugin, valid built-in fallback ids are `openai`, `gemini`, `voyage`, `mistral`, `ollama`, and `local`.
+- `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
+### Batch indexing (OpenAI + Gemini + Voyage)
 
-- Disabled by default. Set `agents.defaults.memorySearch.remote.batch.enabled = true` to enable batch indexing for providers whose adapter exposes batch support.
+- Disabled by default. Set `agents.defaults.memorySearch.remote.batch.enabled = true` to enable for large-corpus indexing (OpenAI, Gemini, and Voyage).
 - Default behavior waits for batch completion; tune `remote.batch.wait`, `remote.batch.pollIntervalMs`, and `remote.batch.timeoutMinutes` if needed.
 - Set `remote.batch.concurrency` to control how many batch jobs we submit in parallel (default: 2).
-- With the default `memory-core` plugin, batch indexing is available for `openai`, `gemini`, and `voyage`.
+- Batch mode applies when `memorySearch.provider = "openai"` or `"gemini"` and uses the corresponding API key.
 - Gemini batch jobs use the async embeddings batch endpoint and require Gemini Batch API availability.
 
 Why OpenAI batch is fast and cheap:

docs/reference/secretref-credential-surface.md

@@ -29,7 +29,8 @@ Scope intent:
 - `agents.list[].memorySearch.remote.apiKey`
 - `talk.apiKey`
 - `talk.providers.*.apiKey`
-- `messages.tts.providers.*.apiKey`
+- `messages.tts.elevenlabs.apiKey`
+- `messages.tts.openai.apiKey`
 - `tools.web.fetch.firecrawl.apiKey`
 - `plugins.entries.brave.config.webSearch.apiKey`
 - `plugins.entries.google.config.webSearch.apiKey`
@@ -62,10 +63,12 @@ Scope intent:
 - `channels.slack.accounts.*.signingSecret`
 - `channels.discord.token`
 - `channels.discord.pluralkit.token`
-- `channels.discord.voice.tts.providers.*.apiKey`
+- `channels.discord.voice.tts.elevenlabs.apiKey`
+- `channels.discord.voice.tts.openai.apiKey`
 - `channels.discord.accounts.*.token`
 - `channels.discord.accounts.*.pluralkit.token`
-- `channels.discord.accounts.*.voice.tts.providers.*.apiKey`
+- `channels.discord.accounts.*.voice.tts.elevenlabs.apiKey`
+- `channels.discord.accounts.*.voice.tts.openai.apiKey`
 - `channels.irc.password`
 - `channels.irc.nickserv.password`
 - `channels.irc.accounts.*.password`

docs/reference/secretref-user-supplied-credentials-matrix.json

@@ -80,9 +80,16 @@
       "optIn": true
     },
     {
-      "id": "channels.discord.accounts.*.voice.tts.providers.*.apiKey",
+      "id": "channels.discord.accounts.*.voice.tts.elevenlabs.apiKey",
       "configFile": "openclaw.json",
-      "path": "channels.discord.accounts.*.voice.tts.providers.*.apiKey",
+      "path": "channels.discord.accounts.*.voice.tts.elevenlabs.apiKey",
+      "secretShape": "secret_input",
+      "optIn": true
+    },
+    {
+      "id": "channels.discord.accounts.*.voice.tts.openai.apiKey",
+      "configFile": "openclaw.json",
+      "path": "channels.discord.accounts.*.voice.tts.openai.apiKey",
       "secretShape": "secret_input",
       "optIn": true
     },
@@ -101,9 +108,16 @@
       "optIn": true
     },
     {
-      "id": "channels.discord.voice.tts.providers.*.apiKey",
+      "id": "channels.discord.voice.tts.elevenlabs.apiKey",
       "configFile": "openclaw.json",
-      "path": "channels.discord.voice.tts.providers.*.apiKey",
+      "path": "channels.discord.voice.tts.elevenlabs.apiKey",
+      "secretShape": "secret_input",
+      "optIn": true
+    },
+    {
+      "id": "channels.discord.voice.tts.openai.apiKey",
+      "configFile": "openclaw.json",
+      "path": "channels.discord.voice.tts.openai.apiKey",
       "secretShape": "secret_input",
       "optIn": true
     },
@@ -406,9 +420,16 @@
       "optIn": true
     },
     {
-      "id": "messages.tts.providers.*.apiKey",
+      "id": "messages.tts.elevenlabs.apiKey",
       "configFile": "openclaw.json",
-      "path": "messages.tts.providers.*.apiKey",
+      "path": "messages.tts.elevenlabs.apiKey",
+      "secretShape": "secret_input",
+      "optIn": true
+    },
+    {
+      "id": "messages.tts.openai.apiKey",
+      "configFile": "openclaw.json",
+      "path": "messages.tts.openai.apiKey",
       "secretShape": "secret_input",
       "optIn": true
     },

docs/reference/test.md

@@ -26,7 +26,6 @@ title: "Tests"
 - Gateway integration: opt-in via `OPENCLAW_TEST_INCLUDE_GATEWAY=1 pnpm test` or `pnpm test:gateway`.
 - `pnpm test:e2e`: Runs gateway end-to-end smoke tests (multi-instance WS/HTTP/node pairing). Defaults to `forks` + adaptive workers in `vitest.e2e.config.ts`; tune with `OPENCLAW_E2E_WORKERS=<n>` and set `OPENCLAW_E2E_VERBOSE=1` for verbose logs.
 - `pnpm test:live`: Runs provider live tests (minimax/zai). Requires API keys and `LIVE=1` (or provider-specific `*_LIVE_TEST=1`) to unskip.
-- `pnpm test:docker:openwebui`: Starts Dockerized OpenClaw + Open WebUI, signs in through Open WebUI, checks `/api/models`, then runs a real proxied chat through `/api/chat/completions`. Requires a usable live model key (for example OpenAI in `~/.profile`), pulls an external Open WebUI image, and is not expected to be CI-stable like the normal unit/e2e suites.
 
 ## Local PR gate
 
@@ -40,7 +39,7 @@ For local PR land/gate checks, run:
 If `pnpm test` flakes on a loaded host, rerun once before treating it as a regression, then isolate with `pnpm vitest run <path/to/test>`. For memory-constrained hosts, use:
 
 - `OPENCLAW_TEST_PROFILE=low OPENCLAW_TEST_SERIAL_GATEWAY=1 pnpm test`
-- `OPENCLAW_VITEST_FS_MODULE_CACHE_PATH=/tmp/openclaw-vitest-cache pnpm test:changed`
+- `OPENCLAW_VITEST_FS_MODULE_CACHE=0 pnpm test:changed`
 
 ## Model latency bench (local keys)
 

docs/reference/wizard.md

@@ -31,7 +31,7 @@ For a high-level overview, see [Onboarding (CLI)](/start/wizard).
   </Step>
   <Step title="Model/Auth">
     - **Anthropic API key**: uses `ANTHROPIC_API_KEY` if present or prompts for a key, then saves it for daemon use.
-    - **Anthropic Claude CLI**: on macOS onboarding checks Keychain item "Claude Code-credentials" (choose "Always Allow" so launchd starts don't block); on Linux/Windows it reuses `~/.claude/.credentials.json` if present and switches model selection to `claude-cli/...`.
+    - **Anthropic OAuth (Claude Code CLI)**: on macOS onboarding checks Keychain item "Claude Code-credentials" (choose "Always Allow" so launchd starts don't block); on Linux/Windows it reuses `~/.claude/.credentials.json` if present.
     - **Anthropic token (paste setup-token)**: run `claude setup-token` on any machine, then paste the token (you can name it; blank = default).
     - **OpenAI Code (Codex) subscription (Codex CLI)**: if `~/.codex/auth.json` exists, onboarding can reuse it.
     - **OpenAI Code (Codex) subscription (OAuth)**: browser flow; paste the `code#state`.

docs/start/getting-started.md

@@ -14,7 +14,7 @@ and a working chat session.
 
 ## What you need
 
-- **Node.js** — Node 24 recommended (Node 22.14+ also supported)
+- **Node.js** — Node 24 recommended (Node 22.16+ also supported)
 - **An API key** from a model provider (Anthropic, OpenAI, Google, etc.) — onboarding will prompt you
 
 <Tip>

docs/start/setup.md

@@ -21,7 +21,7 @@ For onboarding details, see [Onboarding (CLI)](/start/wizard).
 
 ## Prereqs (from source)
 
-- Node 24 recommended (Node 22 LTS, currently `22.14+`, still supported)
+- Node 24 recommended (Node 22 LTS, currently `22.16+`, still supported)
 - `pnpm`
 - Docker (optional; only for containerized setup/e2e — see [Docker](/install/docker))
 

docs/start/wizard-cli-reference.md

@@ -126,10 +126,7 @@ What you set:
   <Accordion title="Anthropic API key">
     Uses `ANTHROPIC_API_KEY` if present or prompts for a key, then saves it for daemon use.
   </Accordion>
-  <Accordion title="Anthropic Claude CLI">
-    Reuses a local Claude CLI login on the gateway host and switches model
-    selection to `claude-cli/...`.
-
+  <Accordion title="Anthropic OAuth (Claude Code CLI)">
     - macOS: checks Keychain item "Claude Code-credentials"
     - Linux and Windows: reuses `~/.claude/.credentials.json` if present
 

docs/tools/acp-agents.md

@@ -1,5 +1,5 @@
 ---
-summary: "Use ACP runtime sessions for Codex, Claude Code, Cursor, Gemini CLI, OpenClaw ACP, and other harness agents"
+summary: "Use ACP runtime sessions for Pi, Claude Code, Codex, OpenCode, Gemini CLI, and other harness agents"
 read_when:
   - Running coding harnesses through ACP
   - Setting up thread-bound ACP sessions on thread-capable channels
@@ -11,7 +11,7 @@ title: "ACP Agents"
 
 # ACP agents
 
-[Agent Client Protocol (ACP)](https://agentclientprotocol.com/) sessions let OpenClaw run external coding harnesses (for example Pi, Claude Code, Codex, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, and other supported ACPX harnesses) through an ACP backend plugin.
+[Agent Client Protocol (ACP)](https://agentclientprotocol.com/) sessions let OpenClaw run external coding harnesses (for example Pi, Claude Code, Codex, OpenCode, and Gemini CLI) through an ACP backend plugin.
 
 If you ask OpenClaw in plain language to "run this in Codex" or "start Claude Code in a thread", OpenClaw should route that request to the ACP runtime (not the native sub-agent runtime).
 
@@ -441,23 +441,14 @@ Equivalent operations:
 
 Current acpx built-in harness aliases:
 
+- `pi`
 - `claude`
 - `codex`
-- `copilot`
-- `cursor` (Cursor CLI: `cursor-agent acp`)
-- `droid`
-- `gemini`
-- `iflow`
-- `kilocode`
-- `kimi`
-- `kiro`
-- `openclaw`
 - `opencode`
-- `pi`
-- `qwen`
+- `gemini`
+- `kimi`
 
 When OpenClaw uses the acpx backend, prefer these values for `agentId` unless your acpx config defines custom agent aliases.
-If your local Cursor install still exposes ACP as `agent acp`, override the `cursor` agent command in your acpx config instead of changing the built-in default.
 
 Direct acpx CLI usage can also target arbitrary adapters via `--agent <command>`, but that raw escape hatch is an acpx CLI feature (not the normal OpenClaw `agentId` path).
 
@@ -473,22 +464,7 @@ Core ACP baseline:
     dispatch: { enabled: true },
     backend: "acpx",
     defaultAgent: "codex",
-    allowedAgents: [
-      "claude",
-      "codex",
-      "copilot",
-      "cursor",
-      "droid",
-      "gemini",
-      "iflow",
-      "kilocode",
-      "kimi",
-      "kiro",
-      "openclaw",
-      "opencode",
-      "pi",
-      "qwen",
-    ],
+    allowedAgents: ["pi", "claude", "codex", "opencode", "gemini", "kimi"],
     maxConcurrentSessions: 8,
     stream: {
       coalesceIdleMs: 300,

docs/tools/apply-patch.md

@@ -36,9 +36,8 @@ The tool accepts a single `input` string that wraps one or more file operations:
 - `tools.exec.applyPatch.workspaceOnly` defaults to `true` (workspace-contained). Set it to `false` only if you intentionally want `apply_patch` to write/delete outside the workspace directory.
 - Use `*** Move to:` within an `*** Update File:` hunk to rename files.
 - `*** End of File` marks an EOF-only insert when needed.
-- Available by default for OpenAI and OpenAI Codex models. Set
-  `tools.exec.applyPatch.enabled: false` to disable it.
-- Optionally gate by model via
+- Experimental and disabled by default. Enable with `tools.exec.applyPatch.enabled`.
+- OpenAI-only (including OpenAI Codex). Optionally gate by model via
   `tools.exec.applyPatch.allowModels`.
 - Config is only under `tools.exec`.
 

docs/tools/browser.md

@@ -42,44 +42,6 @@ openclaw browser --browser-profile openclaw snapshot
 If you get “Browser disabled”, enable it in config (see below) and restart the
 Gateway.
 
-## Plugin control
-
-The default `browser` tool is now a bundled plugin that ships enabled by
-default. That means you can disable or replace it without removing the rest of
-OpenClaw's plugin system:
-
-```json5
-{
-  plugins: {
-    entries: {
-      browser: {
-        enabled: false,
-      },
-    },
-  },
-}
-```
-
-Disable the bundled plugin before installing another plugin that provides the
-same `browser` tool name. The default browser experience needs both:
-
-- `plugins.entries.browser.enabled` not disabled
-- `browser.enabled=true`
-
-If you turn off only the plugin, the bundled browser CLI (`openclaw browser`),
-gateway method (`browser.request`), agent tool, and default browser control
-service all disappear together. Your `browser.*` config stays intact for a
-replacement plugin to reuse.
-
-The bundled browser plugin also owns the browser runtime implementation now.
-Core keeps only shared Plugin SDK helpers plus compatibility re-exports for
-older internal import paths. In practice, removing or replacing
-`extensions/browser` removes the browser feature set instead of leaving a
-second core-owned runtime behind.
-
-Browser config changes still require a Gateway restart so the bundled plugin
-can re-register its browser service with the new settings.
-
 ## Profiles: `openclaw` vs `user`
 
 - `openclaw`: managed, isolated browser (no extension required).
@@ -231,9 +193,8 @@ Notes:
 ## Browserless (hosted remote CDP)
 
 [Browserless](https://browserless.io) is a hosted Chromium service that exposes
-CDP connection URLs over HTTPS and WebSocket. OpenClaw can use either form, but
-for a remote browser profile the simplest option is the direct WebSocket URL
-from Browserless' connection docs.
+CDP endpoints over HTTPS. You can point an OpenClaw browser profile at a
+Browserless region endpoint and authenticate with your API key.
 
 Example:
 
@@ -246,7 +207,7 @@ Example:
     remoteCdpHandshakeTimeoutMs: 4000,
     profiles: {
       browserless: {
-        cdpUrl: "wss://production-sfo.browserless.io?token=<BROWSERLESS_API_KEY>",
+        cdpUrl: "https://production-sfo.browserless.io?token=<BROWSERLESS_API_KEY>",
         color: "#00AA00",
       },
     },
@@ -258,21 +219,17 @@ Notes:
 
 - Replace `<BROWSERLESS_API_KEY>` with your real Browserless token.
 - Choose the region endpoint that matches your Browserless account (see their docs).
-- If Browserless gives you an HTTPS base URL, you can either convert it to
-  `wss://` for a direct CDP connection or keep the HTTPS URL and let OpenClaw
-  discover `/json/version`.
 
 ## Direct WebSocket CDP providers
 
 Some hosted browser services expose a **direct WebSocket** endpoint rather than
 the standard HTTP-based CDP discovery (`/json/version`). OpenClaw supports both:
 
-- **HTTP(S) endpoints** — OpenClaw calls `/json/version` to discover the
-  WebSocket debugger URL, then connects.
+- **HTTP(S) endpoints** (e.g. Browserless) — OpenClaw calls `/json/version` to
+  discover the WebSocket debugger URL, then connects.
 - **WebSocket endpoints** (`ws://` / `wss://`) — OpenClaw connects directly,
   skipping `/json/version`. Use this for services like
-  [Browserless](https://browserless.io),
-  [Browserbase](https://www.browserbase.com), or any provider that hands you a
+  [Browserbase](https://www.browserbase.com) or any provider that hands you a
   WebSocket URL.
 
 ### Browserbase

docs/tools/exec-approvals.md

@@ -361,35 +361,6 @@ Reply in chat:
 /approve <id> deny
 ```
 
-The `/approve` command handles both exec approvals and plugin approvals. If the ID does not match a pending exec approval, it automatically checks plugin approvals.
-
-### Plugin approval forwarding
-
-Plugin approval forwarding uses the same delivery pipeline as exec approvals but has its own
-independent config under `approvals.plugin`. Enabling or disabling one does not affect the other.
-
-```json5
-{
-  approvals: {
-    plugin: {
-      enabled: true,
-      mode: "targets",
-      agentFilter: ["main"],
-      targets: [
-        { channel: "slack", to: "U12345678" },
-        { channel: "telegram", to: "123456789" },
-      ],
-    },
-  },
-}
-```
-
-The config shape is identical to `approvals.exec`: `enabled`, `mode`, `agentFilter`,
-`sessionFilter`, and `targets` work the same way.
-
-Channels that support interactive exec approval buttons (such as Telegram) also render buttons for
-plugin approvals. Channels without adapter support fall back to plain text with `/approve` instructions.
-
 ### Built-in chat approval clients
 
 Discord and Telegram can also act as explicit exec approval clients with channel-specific config.
@@ -413,8 +384,8 @@ topics, OpenClaw preserves the topic for the approval prompt and the post-approv
 
 See:
 
-- [Discord](/channels/discord)
-- [Telegram](/channels/telegram)
+- [Discord](/channels/discord#exec-approvals-in-discord)
+- [Telegram](/channels/telegram#exec-approvals-in-telegram)
 
 ### macOS IPC flow
 

docs/tools/exec.md

@@ -184,17 +184,16 @@ Paste (bracketed by default):
 { "tool": "process", "action": "paste", "sessionId": "<id>", "text": "line1\nline2\n" }
 ```
 
-## apply_patch
+## apply_patch (experimental)
 
 `apply_patch` is a subtool of `exec` for structured multi-file edits.
-It is enabled by default for OpenAI and OpenAI Codex models. Use config only
-when you want to disable it or restrict it to specific models:
+Enable it explicitly:
 
 ```json5
 {
   tools: {
     exec: {
-      applyPatch: { workspaceOnly: true, allowModels: ["gpt-5.2"] },
+      applyPatch: { enabled: true, workspaceOnly: true, allowModels: ["gpt-5.2"] },
     },
   },
 }
@@ -203,7 +202,6 @@ when you want to disable it or restrict it to specific models:
 Notes:
 
 - Only available for OpenAI/OpenAI Codex models.
-- Tool policy still applies; `allow: ["write"]` implicitly allows `apply_patch`.
+- Tool policy still applies; `allow: ["exec"]` implicitly allows `apply_patch`.
 - Config lives under `tools.exec.applyPatch`.
-- `tools.exec.applyPatch.enabled` defaults to `true`; set it to `false` to disable the tool for OpenAI models.
 - `tools.exec.applyPatch.workspaceOnly` defaults to `true` (workspace-contained). Set it to `false` only if you intentionally want `apply_patch` to write/delete outside the workspace directory.

docs/tools/plugin.md

@@ -90,7 +90,7 @@ and the [Plugin SDK Overview](/plugins/sdk-overview).
     `anthropic`, `byteplus`, `cloudflare-ai-gateway`, `github-copilot`, `google`,
     `huggingface`, `kilocode`, `kimi-coding`, `minimax`, `mistral`, `modelstudio`,
     `moonshot`, `nvidia`, `openai`, `opencode`, `opencode-go`, `openrouter`,
-    `qianfan`, `synthetic`, `together`, `venice`,
+    `qianfan`, `qwen-portal-auth`, `synthetic`, `together`, `venice`,
     `vercel-ai-gateway`, `volcengine`, `xiaomi`, `zai`
   </Accordion>
 
@@ -104,7 +104,6 @@ and the [Plugin SDK Overview](/plugins/sdk-overview).
   </Accordion>
 
   <Accordion title="Other">
-    - `browser` — bundled browser plugin for the browser tool, `openclaw browser` CLI, `browser.request` gateway method, browser runtime, and default browser control service (enabled by default; disable before replacing it)
     - `copilot-proxy` — VS Code Copilot Proxy bridge (disabled by default)
   </Accordion>
 </AccordionGroup>
@@ -263,8 +262,6 @@ Hook guard behavior for typed lifecycle hooks:
 
 - `before_tool_call`: `{ block: true }` is terminal; lower-priority handlers are skipped.
 - `before_tool_call`: `{ block: false }` is a no-op and does not clear an earlier block.
-- `before_skill_install`: `{ block: true }` is terminal; lower-priority handlers are skipped.
-- `before_skill_install`: `{ block: false }` is a no-op and does not clear an earlier block.
 - `message_sending`: `{ cancel: true }` is terminal; lower-priority handlers are skipped.
 - `message_sending`: `{ cancel: false }` is a no-op and does not clear an earlier cancel.
 

docs/tools/tts.md

@@ -15,7 +15,7 @@ It works anywhere OpenClaw can send audio.
 ## Supported services
 
 - **ElevenLabs** (primary or fallback provider)
-- **Microsoft** (primary or fallback provider; current bundled implementation uses `node-edge-tts`)
+- **Microsoft** (primary or fallback provider; current bundled implementation uses `node-edge-tts`, default when no API keys)
 - **OpenAI** (primary or fallback provider; also used for summaries)
 
 ### Microsoft speech notes
@@ -38,7 +38,9 @@ If you want OpenAI or ElevenLabs:
 - `ELEVENLABS_API_KEY` (or `XI_API_KEY`)
 - `OPENAI_API_KEY`
 
-Microsoft speech does **not** require an API key.
+Microsoft speech does **not** require an API key. If no API keys are found,
+OpenClaw defaults to Microsoft (unless disabled via
+`messages.tts.microsoft.enabled=false` or `messages.tts.edge.enabled=false`).
 
 If multiple providers are configured, the selected provider is used first and the others are fallback options.
 Auto-summary uses the configured `summaryModel` (or `agents.defaults.model.primary`),
@@ -58,8 +60,8 @@ so that provider must also be authenticated if you enable summaries.
 No. Auto‑TTS is **off** by default. Enable it in config with
 `messages.tts.auto` or per session with `/tts always` (alias: `/tts on`).
 
-When `messages.tts.provider` is unset, OpenClaw picks the first configured
-speech provider in registry auto-select order.
+Microsoft speech **is** enabled by default once TTS is on, and is used automatically
+when no OpenAI or ElevenLabs API keys are available.
 
 ## Config
 
@@ -91,28 +93,26 @@ Full schema is in [Gateway configuration](/gateway/configuration).
       modelOverrides: {
         enabled: true,
       },
-      providers: {
-        openai: {
-          apiKey: "openai_api_key",
-          baseUrl: "https://api.openai.com/v1",
-          model: "gpt-4o-mini-tts",
-          voice: "alloy",
-        },
-        elevenlabs: {
-          apiKey: "elevenlabs_api_key",
-          baseUrl: "https://api.elevenlabs.io",
-          voiceId: "voice_id",
-          modelId: "eleven_multilingual_v2",
-          seed: 42,
-          applyTextNormalization: "auto",
-          languageCode: "en",
-          voiceSettings: {
-            stability: 0.5,
-            similarityBoost: 0.75,
-            style: 0.0,
-            useSpeakerBoost: true,
-            speed: 1.0,
-          },
+      openai: {
+        apiKey: "openai_api_key",
+        baseUrl: "https://api.openai.com/v1",
+        model: "gpt-4o-mini-tts",
+        voice: "alloy",
+      },
+      elevenlabs: {
+        apiKey: "elevenlabs_api_key",
+        baseUrl: "https://api.elevenlabs.io",
+        voiceId: "voice_id",
+        modelId: "eleven_multilingual_v2",
+        seed: 42,
+        applyTextNormalization: "auto",
+        languageCode: "en",
+        voiceSettings: {
+          stability: 0.5,
+          similarityBoost: 0.75,
+          style: 0.0,
+          useSpeakerBoost: true,
+          speed: 1.0,
         },
       },
     },
@@ -128,15 +128,13 @@ Full schema is in [Gateway configuration](/gateway/configuration).
     tts: {
       auto: "always",
       provider: "microsoft",
-      providers: {
-        microsoft: {
-          enabled: true,
-          voice: "en-US-MichelleNeural",
-          lang: "en-US",
-          outputFormat: "audio-24khz-48kbitrate-mono-mp3",
-          rate: "+10%",
-          pitch: "-5%",
-        },
+      microsoft: {
+        enabled: true,
+        voice: "en-US-MichelleNeural",
+        lang: "en-US",
+        outputFormat: "audio-24khz-48kbitrate-mono-mp3",
+        rate: "+10%",
+        pitch: "-5%",
       },
     },
   },
@@ -149,10 +147,8 @@ Full schema is in [Gateway configuration](/gateway/configuration).
 {
   messages: {
     tts: {
-      providers: {
-        microsoft: {
-          enabled: false,
-        },
+      microsoft: {
+        enabled: false,
       },
     },
   },
@@ -212,37 +208,37 @@ Then run:
 - `enabled`: legacy toggle (doctor migrates this to `auto`).
 - `mode`: `"final"` (default) or `"all"` (includes tool/block replies).
 - `provider`: speech provider id such as `"elevenlabs"`, `"microsoft"`, or `"openai"` (fallback is automatic).
-- If `provider` is **unset**, OpenClaw uses the first configured speech provider in registry auto-select order.
+- If `provider` is **unset**, OpenClaw prefers `openai` (if key), then `elevenlabs` (if key),
+  otherwise `microsoft`.
 - Legacy `provider: "edge"` still works and is normalized to `microsoft`.
 - `summaryModel`: optional cheap model for auto-summary; defaults to `agents.defaults.model.primary`.
   - Accepts `provider/model` or a configured model alias.
 - `modelOverrides`: allow the model to emit TTS directives (on by default).
   - `allowProvider` defaults to `false` (provider switching is opt-in).
-- `providers.<id>`: provider-owned settings keyed by speech provider id.
 - `maxTextLength`: hard cap for TTS input (chars). `/tts audio` fails if exceeded.
 - `timeoutMs`: request timeout (ms).
 - `prefsPath`: override the local prefs JSON path (provider/limit/summary).
 - `apiKey` values fall back to env vars (`ELEVENLABS_API_KEY`/`XI_API_KEY`, `OPENAI_API_KEY`).
-- `providers.elevenlabs.baseUrl`: override ElevenLabs API base URL.
-- `providers.openai.baseUrl`: override the OpenAI TTS endpoint.
-  - Resolution order: `messages.tts.providers.openai.baseUrl` -> `OPENAI_TTS_BASE_URL` -> `https://api.openai.com/v1`
+- `elevenlabs.baseUrl`: override ElevenLabs API base URL.
+- `openai.baseUrl`: override the OpenAI TTS endpoint.
+  - Resolution order: `messages.tts.openai.baseUrl` -> `OPENAI_TTS_BASE_URL` -> `https://api.openai.com/v1`
   - Non-default values are treated as OpenAI-compatible TTS endpoints, so custom model and voice names are accepted.
-- `providers.elevenlabs.voiceSettings`:
+- `elevenlabs.voiceSettings`:
   - `stability`, `similarityBoost`, `style`: `0..1`
   - `useSpeakerBoost`: `true|false`
   - `speed`: `0.5..2.0` (1.0 = normal)
-- `providers.elevenlabs.applyTextNormalization`: `auto|on|off`
-- `providers.elevenlabs.languageCode`: 2-letter ISO 639-1 (e.g. `en`, `de`)
-- `providers.elevenlabs.seed`: integer `0..4294967295` (best-effort determinism)
-- `providers.microsoft.enabled`: allow Microsoft speech usage (default `true`; no API key).
-- `providers.microsoft.voice`: Microsoft neural voice name (e.g. `en-US-MichelleNeural`).
-- `providers.microsoft.lang`: language code (e.g. `en-US`).
-- `providers.microsoft.outputFormat`: Microsoft output format (e.g. `audio-24khz-48kbitrate-mono-mp3`).
+- `elevenlabs.applyTextNormalization`: `auto|on|off`
+- `elevenlabs.languageCode`: 2-letter ISO 639-1 (e.g. `en`, `de`)
+- `elevenlabs.seed`: integer `0..4294967295` (best-effort determinism)
+- `microsoft.enabled`: allow Microsoft speech usage (default `true`; no API key).
+- `microsoft.voice`: Microsoft neural voice name (e.g. `en-US-MichelleNeural`).
+- `microsoft.lang`: language code (e.g. `en-US`).
+- `microsoft.outputFormat`: Microsoft output format (e.g. `audio-24khz-48kbitrate-mono-mp3`).
   - See Microsoft Speech output formats for valid values; not all formats are supported by the bundled Edge-backed transport.
-- `providers.microsoft.rate` / `providers.microsoft.pitch` / `providers.microsoft.volume`: percent strings (e.g. `+10%`, `-5%`).
-- `providers.microsoft.saveSubtitles`: write JSON subtitles alongside the audio file.
-- `providers.microsoft.proxy`: proxy URL for Microsoft speech requests.
-- `providers.microsoft.timeoutMs`: request timeout override (ms).
+- `microsoft.rate` / `microsoft.pitch` / `microsoft.volume`: percent strings (e.g. `+10%`, `-5%`).
+- `microsoft.saveSubtitles`: write JSON subtitles alongside the audio file.
+- `microsoft.proxy`: proxy URL for Microsoft speech requests.
+- `microsoft.timeoutMs`: request timeout override (ms).
 - `edge.*`: legacy alias for the same Microsoft settings.
 
 ## Model-driven overrides (default on)

docs/tts.md

@@ -15,7 +15,7 @@ It works anywhere OpenClaw can send audio.
 ## Supported services
 
 - **ElevenLabs** (primary or fallback provider)
-- **Microsoft** (primary or fallback provider; current bundled implementation uses `node-edge-tts`)
+- **Microsoft** (primary or fallback provider; current bundled implementation uses `node-edge-tts`, default when no API keys)
 - **OpenAI** (primary or fallback provider; also used for summaries)
 
 ### Microsoft speech notes
@@ -38,7 +38,9 @@ If you want OpenAI or ElevenLabs:
 - `ELEVENLABS_API_KEY` (or `XI_API_KEY`)
 - `OPENAI_API_KEY`
 
-Microsoft speech does **not** require an API key.
+Microsoft speech does **not** require an API key. If no API keys are found,
+OpenClaw defaults to Microsoft (unless disabled via
+`messages.tts.microsoft.enabled=false` or `messages.tts.edge.enabled=false`).
 
 If multiple providers are configured, the selected provider is used first and the others are fallback options.
 Auto-summary uses the configured `summaryModel` (or `agents.defaults.model.primary`),
@@ -58,8 +60,8 @@ so that provider must also be authenticated if you enable summaries.
 No. Auto‑TTS is **off** by default. Enable it in config with
 `messages.tts.auto` or per session with `/tts always` (alias: `/tts on`).
 
-When `messages.tts.provider` is unset, OpenClaw picks the first configured
-speech provider in registry auto-select order.
+Microsoft speech **is** enabled by default once TTS is on, and is used automatically
+when no OpenAI or ElevenLabs API keys are available.
 
 ## Config
 
@@ -91,28 +93,26 @@ Full schema is in [Gateway configuration](/gateway/configuration).
       modelOverrides: {
         enabled: true,
       },
-      providers: {
-        openai: {
-          apiKey: "openai_api_key",
-          baseUrl: "https://api.openai.com/v1",
-          model: "gpt-4o-mini-tts",
-          voice: "alloy",
-        },
-        elevenlabs: {
-          apiKey: "elevenlabs_api_key",
-          baseUrl: "https://api.elevenlabs.io",
-          voiceId: "voice_id",
-          modelId: "eleven_multilingual_v2",
-          seed: 42,
-          applyTextNormalization: "auto",
-          languageCode: "en",
-          voiceSettings: {
-            stability: 0.5,
-            similarityBoost: 0.75,
-            style: 0.0,
-            useSpeakerBoost: true,
-            speed: 1.0,
-          },
+      openai: {
+        apiKey: "openai_api_key",
+        baseUrl: "https://api.openai.com/v1",
+        model: "gpt-4o-mini-tts",
+        voice: "alloy",
+      },
+      elevenlabs: {
+        apiKey: "elevenlabs_api_key",
+        baseUrl: "https://api.elevenlabs.io",
+        voiceId: "voice_id",
+        modelId: "eleven_multilingual_v2",
+        seed: 42,
+        applyTextNormalization: "auto",
+        languageCode: "en",
+        voiceSettings: {
+          stability: 0.5,
+          similarityBoost: 0.75,
+          style: 0.0,
+          useSpeakerBoost: true,
+          speed: 1.0,
         },
       },
     },
@@ -128,15 +128,13 @@ Full schema is in [Gateway configuration](/gateway/configuration).
     tts: {
       auto: "always",
       provider: "microsoft",
-      providers: {
-        microsoft: {
-          enabled: true,
-          voice: "en-US-MichelleNeural",
-          lang: "en-US",
-          outputFormat: "audio-24khz-48kbitrate-mono-mp3",
-          rate: "+10%",
-          pitch: "-5%",
-        },
+      microsoft: {
+        enabled: true,
+        voice: "en-US-MichelleNeural",
+        lang: "en-US",
+        outputFormat: "audio-24khz-48kbitrate-mono-mp3",
+        rate: "+10%",
+        pitch: "-5%",
       },
     },
   },
@@ -149,10 +147,8 @@ Full schema is in [Gateway configuration](/gateway/configuration).
 {
   messages: {
     tts: {
-      providers: {
-        microsoft: {
-          enabled: false,
-        },
+      microsoft: {
+        enabled: false,
       },
     },
   },
@@ -212,37 +208,37 @@ Then run:
 - `enabled`: legacy toggle (doctor migrates this to `auto`).
 - `mode`: `"final"` (default) or `"all"` (includes tool/block replies).
 - `provider`: speech provider id such as `"elevenlabs"`, `"microsoft"`, or `"openai"` (fallback is automatic).
-- If `provider` is **unset**, OpenClaw uses the first configured speech provider in registry auto-select order.
+- If `provider` is **unset**, OpenClaw prefers `openai` (if key), then `elevenlabs` (if key),
+  otherwise `microsoft`.
 - Legacy `provider: "edge"` still works and is normalized to `microsoft`.
 - `summaryModel`: optional cheap model for auto-summary; defaults to `agents.defaults.model.primary`.
   - Accepts `provider/model` or a configured model alias.
 - `modelOverrides`: allow the model to emit TTS directives (on by default).
   - `allowProvider` defaults to `false` (provider switching is opt-in).
-- `providers.<id>`: provider-owned settings keyed by speech provider id.
 - `maxTextLength`: hard cap for TTS input (chars). `/tts audio` fails if exceeded.
 - `timeoutMs`: request timeout (ms).
 - `prefsPath`: override the local prefs JSON path (provider/limit/summary).
 - `apiKey` values fall back to env vars (`ELEVENLABS_API_KEY`/`XI_API_KEY`, `OPENAI_API_KEY`).
-- `providers.elevenlabs.baseUrl`: override ElevenLabs API base URL.
-- `providers.openai.baseUrl`: override the OpenAI TTS endpoint.
-  - Resolution order: `messages.tts.providers.openai.baseUrl` -> `OPENAI_TTS_BASE_URL` -> `https://api.openai.com/v1`
+- `elevenlabs.baseUrl`: override ElevenLabs API base URL.
+- `openai.baseUrl`: override the OpenAI TTS endpoint.
+  - Resolution order: `messages.tts.openai.baseUrl` -> `OPENAI_TTS_BASE_URL` -> `https://api.openai.com/v1`
   - Non-default values are treated as OpenAI-compatible TTS endpoints, so custom model and voice names are accepted.
-- `providers.elevenlabs.voiceSettings`:
+- `elevenlabs.voiceSettings`:
   - `stability`, `similarityBoost`, `style`: `0..1`
   - `useSpeakerBoost`: `true|false`
   - `speed`: `0.5..2.0` (1.0 = normal)
-- `providers.elevenlabs.applyTextNormalization`: `auto|on|off`
-- `providers.elevenlabs.languageCode`: 2-letter ISO 639-1 (e.g. `en`, `de`)
-- `providers.elevenlabs.seed`: integer `0..4294967295` (best-effort determinism)
-- `providers.microsoft.enabled`: allow Microsoft speech usage (default `true`; no API key).
-- `providers.microsoft.voice`: Microsoft neural voice name (e.g. `en-US-MichelleNeural`).
-- `providers.microsoft.lang`: language code (e.g. `en-US`).
-- `providers.microsoft.outputFormat`: Microsoft output format (e.g. `audio-24khz-48kbitrate-mono-mp3`).
+- `elevenlabs.applyTextNormalization`: `auto|on|off`
+- `elevenlabs.languageCode`: 2-letter ISO 639-1 (e.g. `en`, `de`)
+- `elevenlabs.seed`: integer `0..4294967295` (best-effort determinism)
+- `microsoft.enabled`: allow Microsoft speech usage (default `true`; no API key).
+- `microsoft.voice`: Microsoft neural voice name (e.g. `en-US-MichelleNeural`).
+- `microsoft.lang`: language code (e.g. `en-US`).
+- `microsoft.outputFormat`: Microsoft output format (e.g. `audio-24khz-48kbitrate-mono-mp3`).
   - See Microsoft Speech output formats for valid values; not all formats are supported by the bundled Edge-backed transport.
-- `providers.microsoft.rate` / `providers.microsoft.pitch` / `providers.microsoft.volume`: percent strings (e.g. `+10%`, `-5%`).
-- `providers.microsoft.saveSubtitles`: write JSON subtitles alongside the audio file.
-- `providers.microsoft.proxy`: proxy URL for Microsoft speech requests.
-- `providers.microsoft.timeoutMs`: request timeout override (ms).
+- `microsoft.rate` / `microsoft.pitch` / `microsoft.volume`: percent strings (e.g. `+10%`, `-5%`).
+- `microsoft.saveSubtitles`: write JSON subtitles alongside the audio file.
+- `microsoft.proxy`: proxy URL for Microsoft speech requests.
+- `microsoft.timeoutMs`: request timeout override (ms).
 - `edge.*`: legacy alias for the same Microsoft settings.
 
 ## Model-driven overrides (default on)

docs/zh-CN/concepts/agent-loop.md

@@ -136,7 +136,7 @@ OpenClaw 有两个钩子系统：
 ## 超时
 
 - `agent.wait` 默认：30 秒（仅等待）。`timeoutMs` 参数可覆盖。
-- 智能体运行时：`agents.defaults.timeoutSeconds` 默认 172800 秒（48 小时）；在 `runEmbeddedPiAgent` 中止计时器中强制执行。使用 `0` 可完全禁用超时。
+- 智能体运行时：`agents.defaults.timeoutSeconds` 默认 600 秒；在 `runEmbeddedPiAgent` 中止计时器中强制执行。
 
 ## 可能提前结束的情况
 

docs/zh-CN/concepts/model-providers.md

@@ -109,6 +109,7 @@ x-i18n:
 - `byteplus`、`cloudflare-ai-gateway`、`huggingface`、`kimi-coding`、
   `modelstudio`、`nvidia`、`qianfan`、`synthetic`、`together`、`venice`、
   `vercel-ai-gateway` 和 `volcengine`：仅插件接管的目录
+- `qwen-portal`：插件接管的目录、OAuth 登录和 OAuth 刷新
 - `minimax` 和 `xiaomi`：插件接管的目录，以及使用量身份验证/快照逻辑
 
 内置的 `openai` 插件现在接管两个提供商 ID：`openai` 和
@@ -347,6 +348,22 @@ Kimi Coding 使用 Moonshot AI 的 Anthropic 兼容端点：
 }
 ```
 
+### Qwen OAuth（免费层）
+
+Qwen 通过设备代码流程提供对 Qwen Coder + Vision 的 OAuth 访问。
+内置提供商插件默认启用，因此只需登录：
+
+```bash
+openclaw models auth login --provider qwen-portal --set-default
+```
+
+模型引用：
+
+- `qwen-portal/coder-model`
+- `qwen-portal/vision-model`
+
+设置详情和说明请参见 [/providers/qwen](/providers/qwen)。
+
 ### Volcano Engine（Doubao）
 
 Volcano Engine（火山引擎）为中国用户提供对 Doubao 和其他模型的访问。

docs/zh-CN/providers/qwen.md

@@ -1,36 +1,55 @@
 ---
 read_when:
   - 你想在 OpenClaw 中使用 Qwen
-  - 你之前使用过 Qwen OAuth
-summary: 通过阿里云 Model Studio 使用 Qwen 模型
+  - 你想要免费层 OAuth 访问 Qwen Coder
+summary: 在 OpenClaw 中使用 Qwen OAuth（免费层）
 title: Qwen
 x-i18n:
-  generated_at: "2026-03-23T00:00:00Z"
+  generated_at: "2026-02-03T07:53:34Z"
   model: claude-opus-4-5
   provider: pi
-  source_hash: ""
+  source_hash: 88b88e224e2fecbb1ca26e24fbccdbe25609be40b38335d0451343a5da53fdd4
   source_path: providers/qwen.md
   workflow: 15
 ---
 
 # Qwen
 
-<Warning>
+Qwen 为 Qwen Coder 和 Qwen Vision 模型提供免费层 OAuth 流程（每天 2,000 次请求，受 Qwen 速率限制约束）。
 
-**Qwen OAuth 已移除。** 使用 `portal.qwen.ai` 端点的免费层 OAuth 集成（`qwen-portal`）已不再可用。详情请参见 [Issue #49557](https://github.com/openclaw/openclaw/issues/49557)。
-
-</Warning>
-
-## 推荐方案：Model Studio（阿里云 Coding Plan）
-
-使用 [Model Studio](/providers/modelstudio) 获取官方支持的 Qwen 模型访问（Qwen 3.5 Plus、GLM-4.7、Kimi K2.5、MiniMax M2.5 等）。
+## 启用插件
 
 ```bash
-# 全球端点
-openclaw onboard --auth-choice modelstudio-api-key
-
-# 中国端点
-openclaw onboard --auth-choice modelstudio-api-key-cn
+openclaw plugins enable qwen-portal-auth
 ```
 
-完整设置详情请参见 [Model Studio](/providers/modelstudio)。
+启用后重启 Gateway 网关。
+
+## 认证
+
+```bash
+openclaw models auth login --provider qwen-portal --set-default
+```
+
+这会运行 Qwen 设备码 OAuth 流程并将提供商条目写入你的 `models.json`（加上一个 `qwen` 别名以便快速切换）。
+
+## 模型 ID
+
+- `qwen-portal/coder-model`
+- `qwen-portal/vision-model`
+
+切换模型：
+
+```bash
+openclaw models set qwen-portal/coder-model
+```
+
+## 复用 Qwen Code CLI 登录
+
+如果你已经使用 Qwen Code CLI 登录，OpenClaw 会在加载认证存储时从 `~/.qwen/oauth_creds.json` 同步凭证。你仍然需要一个 `models.providers.qwen-portal` 条目（使用上面的登录命令创建一个）。
+
+## 注意
+
+- 令牌自动刷新；如果刷新失败或访问被撤销，请重新运行登录命令。
+- 默认基础 URL：`https://portal.qwen.ai/v1`（如果 Qwen 提供不同的端点，使用 `models.providers.qwen-portal.baseUrl` 覆盖）。
+- 参阅[模型提供商](/concepts/model-providers)了解提供商级别的规则。

docs/zh-CN/tools/plugin.md

@@ -155,6 +155,7 @@ Bundle hook 支持仅限于常规 OpenClaw hook 目录格式（在声明的 hook
 - OpenCode Zen provider 能力 — 以 `opencode` 形式捆绑（默认启用）
 - OpenRouter provider 运行时 — 以 `openrouter` 形式捆绑（默认启用）
 - Qianfan provider catalog — 以 `qianfan` 形式捆绑（默认启用）
+- Qwen OAuth（provider 身份验证 + catalog）— 以 `qwen-portal-auth` 形式捆绑（默认启用）
 - Synthetic provider catalog — 以 `synthetic` 形式捆绑（默认启用）
 - Together provider catalog — 以 `together` 形式捆绑（默认启用）
 - Venice provider catalog — 以 `venice` 形式捆绑（默认启用）
@@ -496,7 +497,7 @@ api.registerHttpRoute({
   `openclaw/plugin-sdk/minimax-portal-auth`、
   `openclaw/plugin-sdk/nextcloud-talk`、`openclaw/plugin-sdk/nostr`、
   `openclaw/plugin-sdk/open-prose`、`openclaw/plugin-sdk/phone-control`、
-  `openclaw/plugin-sdk/synology-chat`、
+  `openclaw/plugin-sdk/qwen-portal-auth`、`openclaw/plugin-sdk/synology-chat`、
   `openclaw/plugin-sdk/talk-voice`、`openclaw/plugin-sdk/test-utils`、
   `openclaw/plugin-sdk/thread-ownership`、`openclaw/plugin-sdk/tlon`、
   `openclaw/plugin-sdk/twitch`、`openclaw/plugin-sdk/voice-call`、
@@ -612,6 +613,7 @@ OpenClaw 按以下顺序扫描：
 - `openrouter`
 - `phone-control`
 - `qianfan`
+- `qwen-portal-auth`
 - `sglang`
 - `synthetic`
 - `talk-voice`

experiments/plugin-sdk-namespaces-plan.md

@@ -0,0 +1,557 @@
+# Plugin SDK Namespaces Plan
+
+## TL;DR
+
+OpenClaw should introduce a few clear SDK namespaces like `plugin`, `channel`,
+and `provider`, instead of keeping so much of the public surface flat.
+
+The safe way to do that is:
+
+- add thin ESM facade entrypoints, not TypeScript `namespace`
+- keep the root `openclaw/plugin-sdk` surface small
+- replace flat registration methods on `OpenClawPluginApi` with namespace groups
+- ship the cutover in one coordinated release instead of dragging old flat APIs
+  along
+- forbid leaf modules from importing back through namespace facades
+
+That gives plugin authors a cleaner SDK that feels closer to VS Code, without
+turning the SDK into a giant barrel or creating circular import problems.
+
+## Goal
+
+Introduce public namespaces to the OpenClaw Plugin SDK so the surface feels
+closer to the VS Code extension API, while keeping the implementation tight,
+isolated, and resistant to circular imports.
+
+This plan is about the public SDK shape. It is not a proposal to merge
+everything into one giant barrel.
+
+## Why This Is Worth Doing
+
+Today the Plugin SDK has three visible problems:
+
+- The public package export surface is large and mostly flat.
+- `src/plugin-sdk/core.ts` and `src/plugin-sdk/index.ts` carry too many
+  unrelated meanings.
+- `OpenClawPluginApi` is still a flat registration API even though
+  `api.runtime` already proves grouped namespaces work well.
+
+The result is harder docs, harder discovery, and too many helper names that
+look equally important even when they are not.
+
+## Current Facts In The Repo
+
+- Package exports are generated from a flat entrypoint list in
+  `src/plugin-sdk/entrypoints.ts` and `scripts/lib/plugin-sdk-entrypoints.json`.
+- The root `openclaw/plugin-sdk` entry is intentionally tiny in
+  `src/plugin-sdk/index.ts`.
+- `api.runtime` is already a successful namespace model. It groups behavior as
+  `agent`, `subagent`, `media`, `imageGeneration`, `webSearch`, `tools`,
+  `channel`, `events`, `logging`, `state`, `tts`, `mediaUnderstanding`, and
+  `modelAuth` in `src/plugins/runtime/index.ts`.
+- The main plugin registration API is still flat in `OpenClawPluginApi` in
+  `src/plugins/types.ts`.
+- The concrete API object is assembled in `src/plugins/registry.ts`, and a
+  second partial copy exists in `src/plugins/captured-registration.ts`.
+
+Those facts suggest a path that is low-risk:
+
+- keep leaf modules as the source of truth
+- add namespace facades on top
+- cut docs, examples, and templates over in the same release as the namespace
+  model
+
+## Design Principles
+
+### 1. Do Not Use TypeScript `namespace`
+
+Use normal ESM modules and package exports.
+
+The SDK already ships as package export subpaths. The namespace model should be
+implemented as public facade modules, not TypeScript `namespace` syntax.
+
+### 2. Keep The Root Tiny
+
+Do not turn `openclaw/plugin-sdk` into a giant VS Code-style monolith.
+
+The closest safe equivalent is:
+
+- a tiny root for shared types and a few universal values
+- a small number of explicit namespace entrypoints
+- optional ergonomic aggregation only after the namespace surfaces settle
+
+### 3. Namespace Facades Must Be Thin
+
+Namespace entrypoints should contain no real business logic.
+
+They should only:
+
+- re-export stable leaves
+- assemble small namespace objects
+
+That keeps cycles and accidental coupling down.
+
+### 4. Types Stay Direct And Easy To Import
+
+Like VS Code, namespaces should mostly group behavior. Common types should stay
+directly importable from the root or the owning domain surface.
+
+Examples:
+
+- `ChannelPlugin`
+- `ProviderPlugin`
+- `OpenClawPluginApi`
+- `PluginRuntime`
+
+### 5. Do Not Namespace Everything At Once
+
+Only namespace areas that already have a clear public identity.
+
+Phase 1 should focus on:
+
+- `plugin`
+- `channel`
+- `provider`
+
+`runtime` already has a good public namespace shape on `api.runtime` and should
+not be reopened as a giant package-export family in the first pass.
+
+## Proposed Public Model
+
+### Namespace Entry Points
+
+Canonical public entrypoints:
+
+- `openclaw/plugin-sdk/plugin`
+- `openclaw/plugin-sdk/channel`
+- `openclaw/plugin-sdk/provider`
+- `openclaw/plugin-sdk/runtime`
+- `openclaw/plugin-sdk/testing`
+
+What each should mean:
+
+- `plugin`
+  - plugin entry helpers
+  - shared plugin definition helpers
+  - plugin-facing config schema helpers that are truly universal
+- `channel`
+  - channel entry helpers
+  - chat-channel builders
+  - stable channel-facing contracts and helpers
+- `provider`
+  - provider entry helpers
+  - auth, catalog, models, onboard, stream, usage, and provider registration helpers
+- `runtime`
+  - the existing `api.runtime` story and runtime-related public helpers that are
+    truly stable
+- `testing`
+  - plugin author testing helpers
+
+### Nested Leaves
+
+Under those namespaces, the long-term canonical leaves should become nested:
+
+- `openclaw/plugin-sdk/channel/setup`
+- `openclaw/plugin-sdk/channel/pairing`
+- `openclaw/plugin-sdk/channel/reply-pipeline`
+- `openclaw/plugin-sdk/channel/contract`
+- `openclaw/plugin-sdk/channel/targets`
+- `openclaw/plugin-sdk/channel/actions`
+- `openclaw/plugin-sdk/channel/inbound`
+- `openclaw/plugin-sdk/channel/lifecycle`
+- `openclaw/plugin-sdk/channel/policy`
+- `openclaw/plugin-sdk/channel/feedback`
+- `openclaw/plugin-sdk/channel/config-schema`
+- `openclaw/plugin-sdk/channel/config-helpers`
+
+- `openclaw/plugin-sdk/provider/auth`
+- `openclaw/plugin-sdk/provider/catalog`
+- `openclaw/plugin-sdk/provider/models`
+- `openclaw/plugin-sdk/provider/onboard`
+- `openclaw/plugin-sdk/provider/stream`
+- `openclaw/plugin-sdk/provider/usage`
+- `openclaw/plugin-sdk/provider/web-search`
+
+Not every current flat subpath needs a namespaced replacement. The goal is to
+promote the stable public domains, not to preserve every current export forever.
+
+## What Happens To `core`
+
+`core` is overloaded today. In a namespace model it should shrink, not grow.
+
+Target split:
+
+- plugin-wide entry helpers move toward `plugin`
+- channel builders and channel-oriented shared helpers move toward `channel`
+- `core` stops being a first-class public destination and shrinks to the
+  smallest possible remaining shared surface
+
+Rule: no new public API should be added to `core` once namespace entrypoints
+exist.
+
+## Proposed `OpenClawPluginApi` Shape
+
+Keep context fields flat:
+
+- `id`
+- `name`
+- `version`
+- `description`
+- `source`
+- `rootDir`
+- `registrationMode`
+- `config`
+- `pluginConfig`
+- `runtime`
+- `logger`
+- `resolvePath`
+
+Move registration behavior behind namespaces:
+
+| Current flat method                  | Proposed namespace location               |
+| ------------------------------------ | ----------------------------------------- |
+| `registerTool`                       | `api.tool.register`                       |
+| `registerHook`                       | `api.hook.register`                       |
+| `on`                                 | `api.hook.on`                             |
+| `registerHttpRoute`                  | `api.http.registerRoute`                  |
+| `registerChannel`                    | `api.channel.register`                    |
+| `registerProvider`                   | `api.provider.register`                   |
+| `registerSpeechProvider`             | `api.provider.registerSpeech`             |
+| `registerMediaUnderstandingProvider` | `api.provider.registerMediaUnderstanding` |
+| `registerImageGenerationProvider`    | `api.provider.registerImageGeneration`    |
+| `registerWebSearchProvider`          | `api.provider.registerWebSearch`          |
+| `registerGatewayMethod`              | `api.gateway.registerMethod`              |
+| `registerCli`                        | `api.cli.register`                        |
+| `registerService`                    | `api.service.register`                    |
+| `registerInteractiveHandler`         | `api.interactive.register`                |
+| `registerCommand`                    | `api.command.register`                    |
+| `registerContextEngine`              | `api.contextEngine.register`              |
+| `registerMemoryPromptSection`        | `api.memory.registerPromptSection`        |
+
+The cutover should replace the flat methods in one coordinated change.
+
+That gives plugin authors a clearer public shape and avoids carrying two public
+registration models at the same time.
+
+## Example Public Usage
+
+Proposed style:
+
+```ts
+import { definePluginEntry } from "openclaw/plugin-sdk/plugin";
+import { channel } from "openclaw/plugin-sdk/channel";
+import { provider } from "openclaw/plugin-sdk/provider";
+import type { ChannelPlugin, OpenClawPluginApi } from "openclaw/plugin-sdk";
+
+const chatPlugin: ChannelPlugin = channel.createChatPlugin({
+  id: "demo",
+  /* ... */
+});
+
+export default definePluginEntry({
+  id: "demo",
+  register(api: OpenClawPluginApi) {
+    api.channel.register(chatPlugin);
+    api.command.register({
+      name: "status",
+      description: "Show plugin status",
+      run: async () => ({ text: "ok" }),
+    });
+  },
+});
+```
+
+This is close to the VS Code mental model:
+
+- grouped behavior
+- direct types
+- obvious public areas
+
+without requiring a single monolithic root import.
+
+## Optional Ergonomic Surface
+
+If the project later wants the closest possible VS Code feel, add a dedicated
+opt-in facade such as `openclaw/plugin-sdk/sdk`.
+
+That facade can assemble:
+
+- `plugin`
+- `channel`
+- `provider`
+- `runtime`
+- `testing`
+
+It should not be phase 1.
+
+Why:
+
+- it is the highest-risk barrel from a cycle and weight perspective
+- it is easier to add once the namespace surfaces already exist
+- it preserves the root `openclaw/plugin-sdk` entry as a small type-oriented
+  surface
+
+## Internal Implementation Rules
+
+These rules are the important part. Without them, namespaces will rot into
+barrels and cycles.
+
+### Rule 1: Namespace Facades Are One-Way
+
+Namespace entrypoints may import leaf modules.
+
+Leaf modules may not import their namespace entrypoint.
+
+Examples:
+
+- allowed: `src/plugin-sdk/channel.ts` importing `./channel-setup.ts`
+- forbidden: `src/plugin-sdk/channel-setup.ts` importing `./channel.ts`
+
+### Rule 1A: Allowed Dependency Directions Must Be Explicit
+
+The allowed directions should be:
+
+- namespace facade -> leaves in the same namespace
+- leaf -> local implementation helpers
+- leaf -> dedicated shared internal leaf
+- leaf -> another leaf in the same namespace only by direct relative import,
+  never through the namespace facade
+
+The forbidden directions should be:
+
+- leaf -> its own namespace facade
+- leaf -> another namespace facade
+- namespace facade -> another namespace facade
+- channel leaf -> provider leaf, or provider leaf -> channel leaf, unless the
+  dependency is first extracted into a shared internal leaf
+
+Short version:
+
+- facades point downward
+- leaves never point back upward
+- cross-namespace sharing must go sideways through a shared internal leaf, not
+  directly through another public namespace
+
+### Rule 1B: If Two Namespaces Need Each Other, Extract A Shared Leaf
+
+If `channel` and `provider` start needing each other directly, that is the sign
+that the seam is wrong.
+
+Do not allow:
+
+- `src/plugin-sdk/channel/*` importing from `src/plugin-sdk/provider/*`
+- `src/plugin-sdk/provider/*` importing from `src/plugin-sdk/channel/*`
+
+Instead:
+
+- extract the shared logic into a dedicated internal leaf
+- let both sides depend on that leaf
+- keep the public namespaces separate
+
+This is the main cycle-prevention rule. Shared logic moves to a lower layer
+before it creates a back-edge.
+
+### Rule 2: No Public-Specifier Self-Imports Inside The SDK
+
+Files inside `src/plugin-sdk/**` should never import from
+`openclaw/plugin-sdk/...`.
+
+They should import local source files directly.
+
+### Rule 3: Shared Code Lives In Shared Leaves
+
+If `channel` and `provider` need the same implementation detail, move that code
+to a shared leaf instead of importing one namespace from the other.
+
+Good shared homes:
+
+- a dedicated internal shared leaf
+- a very small shared core leaf only if it has a precise, stable reason to
+  exist
+- existing domain-neutral helpers
+
+Bad pattern:
+
+- `provider/*` importing from `channel/index`
+- `channel/*` importing from `provider/index`
+
+### Rule 4: Assemble The API Surface Once
+
+`OpenClawPluginApi` should be built by one canonical factory.
+
+`src/plugins/registry.ts` and `src/plugins/captured-registration.ts` should stop
+hand-building separate versions of the API object.
+
+That factory can expose:
+
+- the namespaced shape only
+
+from the same underlying implementation.
+
+### Rule 5: Namespace Entry Files Stay Small
+
+Namespace facades should stay close to pure exports. If a namespace file grows
+real orchestration logic, split that logic back into leaf modules.
+
+### Dependency Shape
+
+The intended import graph is:
+
+```text
+public facade
+  -> same-namespace leaves
+    -> local helpers
+    -> shared internal leaves
+```
+
+Not this:
+
+```text
+channel facade -> provider facade
+channel leaf -> channel facade
+provider leaf -> channel leaf
+```
+
+Concrete examples:
+
+- allowed: `src/plugin-sdk/channel.ts` -> `./channel/setup.ts`
+- allowed: `src/plugin-sdk/channel/setup.ts` -> `./_internal/channel-shared.ts`
+- allowed: `src/plugin-sdk/provider/auth.ts` -> `../_internal/provider-shared.ts`
+- forbidden: `src/plugin-sdk/channel/setup.ts` -> `./channel.ts`
+- forbidden: `src/plugin-sdk/channel/setup.ts` -> `../provider/index.ts`
+- forbidden: `src/plugin-sdk/channel.ts` -> `./provider.ts`
+
+## Migration Strategy
+
+This should be a cutover, not a long overlap period.
+
+That means:
+
+- one coordinated release
+- one migration guide
+- one docs/templates/test update
+- one public SDK shape after the release
+
+## Phase 1: Extract The Canonical API Builder
+
+Do this first, before changing the public surface.
+
+Why:
+
+- it removes duplicated API assembly
+- it gives one place to switch the public shape
+- it reduces cutover risk
+
+Implementation:
+
+- extract one canonical API builder from `src/plugins/registry.ts` and
+  `src/plugins/captured-registration.ts`
+- make that builder assemble the new namespaced registration API
+
+## Phase 2: Add Canonical Namespace Entrypoints
+
+Add:
+
+- `plugin`
+- `channel`
+- `provider`
+
+as thin public facades over existing flat leaves.
+
+Implementation detail:
+
+- the first pass can re-export current flat files
+- do not move source layout and package exports in the same commit if it can be
+  avoided
+
+Examples:
+
+- `src/plugin-sdk/channel/setup.ts` can initially re-export from
+  `../channel-setup.js`
+- `src/plugin-sdk/provider/auth.ts` can initially re-export from
+  `../provider-auth.js`
+
+This lets the public namespace story land before the internal source move,
+without forcing all implementation files to move in the same commit.
+
+## Phase 3: Cut Public API, Docs, And Templates Together
+
+In the same release:
+
+- docs prefer namespaced entrypoints
+- templates prefer namespaced imports
+- tests and examples switch to the namespaced shape
+- `OpenClawPluginApi` changes to the namespaced registration model
+- flat registration methods are removed instead of carried as aliases
+
+## Phase 4: Remove The Old Public Story
+
+After the cutover release lands:
+
+- stop documenting superseded flat leaves as public API
+- keep only the namespace model in author-facing docs
+- remove any leftover flat registration surface that survived only as
+  transitional scaffolding during implementation
+
+## What Should Not Be Namespaced In Phase 1
+
+To keep the refactor tight, do not force these into the first milestone:
+
+- every `*-runtime` helper subpath
+- extension-branded public subpaths
+- one-off utilities that do not yet have a stable domain home
+- the root `openclaw/plugin-sdk` barrel
+
+If a subpath is only public because history leaked it, namespace work should not
+promote it.
+
+## Guardrails And Validation
+
+The namespace rollout should ship with explicit checks.
+
+### Existing Checks To Reuse
+
+- `src/plugin-sdk/subpaths.test.ts`
+- `src/plugin-sdk/runtime-api-guardrails.test.ts`
+- `pnpm build` for `[CIRCULAR_REEXPORT]` warnings
+- `pnpm plugin-sdk:api:check`
+
+### New Checks To Add
+
+- namespace facade files may only re-export or compose approved leaves
+- leaf files under a namespace may not import their parent `index` facade
+- leaf files under one namespace may not import another namespace facade
+- cross-namespace leaf imports should fail unless the target is an approved
+  shared internal leaf
+- namespace facades may not import other namespace facades
+- no new API should be added to `core` once namespace facades exist
+- `OpenClawPluginApi` must not expose both flat and namespaced registration
+  methods after cutover
+
+## Recommended End State
+
+The elegant end state is:
+
+- a tiny root
+- a few first-class namespaces
+- direct types
+- a grouped `api` registration surface
+- stable leaves under each namespace
+- no reverse imports from leaves back into namespace facades
+
+That gives OpenClaw a VS Code-like feel where the public SDK has clear domains,
+but still respects the repo's existing build, lazy-loading, and package-boundary
+constraints.
+
+## Short Recommendation
+
+If this work starts soon, the first implementation step should be:
+
+1. extract one canonical `OpenClawPluginApi` builder
+2. switch that builder to the namespaced registration shape
+3. add `plugin`, `channel`, and `provider` facade entrypoints
+4. cut docs, templates, and examples over in the same release
+5. remove the old flat registration story instead of maintaining dual public APIs
+
+That sequence keeps the refactor elegant and minimizes the chance that
+namespaces become another layer of accidental coupling.