fix(plugins): stabilize registry package paths

.agents/skills/openclaw-pr-maintainer/SKILL.md

@@ -35,21 +35,6 @@ Use this skill for maintainer-facing GitHub workflow, not for ordinary code chan
 - If the claim is unsubstantiated or likely wrong, request evidence or changes instead of merging.
 - If the linked issue appears outdated or incorrect, correct triage first. Do not merge a speculative fix.
 
-## Close low-signal manual PRs carefully
-
-- Do not close for red CI alone. Require a clear low-signal category plus stale or failed validation.
-- Good manual-close categories:
-  - blank or mostly untouched PR template with no concrete OpenClaw problem/fix
-  - random docs-only churn such as root README translations, generic wording tweaks, or community-plugin discoverability docs that should go through ClawHub
-  - test-only coverage without a linked bug, owner request, or behavior change
-  - refactor-only cleanup, variable renames, formatting, or generated/baseline churn without maintainer request
-  - third-party channel/provider/tool/skill/plugin work that belongs on ClawHub instead of core
-  - risky ops/infra drive-bys such as new external CI services, release workflows, host upgrade scripts, Docker base migrations, or apt retry/fix-missing tweaks without owner request and green validation
-  - dirty branches where a narrow stated change includes unrelated docs/generated/runtime/extension files
-  - repeated bot-review spam or copied bot output without author-owned fixes
-- Keep or escalate plausible focused bug fixes, green PRs, active maintainer discussions, assigned work, recent author follow-up, and unique reproduction details.
-- For third-party capabilities, prefer the `r: third-party-extension` auto-response label when it applies; it points contributors to publish on ClawHub.
-
 ## Handle GitHub text safely
 
 - For issue comments and PR comments, use literal multiline strings or `-F - <<'EOF'` for real newlines. Never embed `\n`.

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

@@ -49,19 +49,6 @@ pnpm openclaw qa suite \
 5. If the user wants to watch the live UI, find the current `openclaw-qa` listen port and report `http://127.0.0.1:<port>`.
 6. If a scenario fails, fix the product or harness root cause, then rerun the full lane.
 
-## OTEL smoke
-
-For local QA-lab OpenTelemetry validation, use:
-
-```bash
-pnpm qa:otel:smoke
-```
-
-This starts a local OTLP/HTTP trace receiver, runs the `otel-trace-smoke`
-scenario through qa-channel, decodes the emitted protobuf spans, and verifies
-the exported trace names and privacy contract. It does not require Opik,
-Langfuse, or external collector credentials.
-
 ## QA credentials and 1Password
 
 - Use `op` only inside `tmux` for QA secret lookup in this repo.

.agents/skills/openclaw-release-maintainer/SKILL.md

@@ -202,16 +202,10 @@ Before tagging or publishing, run:
 pnpm check:architecture
 pnpm build
 pnpm ui:build
-pnpm qa:otel:smoke
 pnpm release:check
 pnpm test:install:smoke
 ```
 
-- Use `pnpm qa:otel:smoke` when release validation needs telemetry coverage.
-  It starts a local OTLP/HTTP trace receiver, runs QA-lab's
-  `otel-trace-smoke`, and checks span names plus content/identifier redaction
-  without external Opik or Langfuse credentials.
-
 For a non-root smoke path:
 
 ```bash

.env.example

@@ -82,5 +82,4 @@ OPENCLAW_GATEWAY_TOKEN=
 
 # ELEVENLABS_API_KEY=...
 # XI_API_KEY=...  # alias for ElevenLabs
-# INWORLD_API_KEY=...
 # DEEPGRAM_API_KEY=...

.github/codeql/codeql-javascript-typescript-extensions.yml

@@ -1,18 +0,0 @@
-name: openclaw-codeql-javascript-typescript-extensions
-
-paths:
-  - extensions
-
-paths-ignore:
-  - apps
-  - dist
-  - docs
-  - "**/node_modules"
-  - "**/coverage"
-  - "**/*.generated.ts"
-  - "**/*.bundle.js"
-  - "**/*-runtime.js"
-  - "**/*.test.ts"
-  - "**/*.test.tsx"
-  - "**/*.e2e.test.ts"
-  - "**/*.e2e.test.tsx"

.github/codeql/codeql-javascript-typescript.yml

@@ -1,7 +1,8 @@
-name: openclaw-codeql-javascript-typescript-core
+name: openclaw-codeql-javascript-typescript
 
 paths:
   - src
+  - extensions
   - ui/src
   - skills
 

.github/labeler.yml

@@ -3,12 +3,6 @@
       - any-glob-to-any-file:
           - "extensions/bluebubbles/**"
           - "docs/channels/bluebubbles.md"
-"plugin: azure-speech":
-  - changed-files:
-      - any-glob-to-any-file:
-          - "extensions/azure-speech/**"
-          - "docs/providers/azure-speech.md"
-          - "docs/tools/tts.md"
 "channel: discord":
   - changed-files:
       - any-glob-to-any-file:
@@ -313,11 +307,6 @@
   - changed-files:
       - any-glob-to-any-file:
           - "extensions/huggingface/**"
-"extensions: inworld":
-  - changed-files:
-      - any-glob-to-any-file:
-          - "extensions/inworld/**"
-          - "docs/providers/inworld.md"
 "extensions: kilocode":
   - changed-files:
       - any-glob-to-any-file:

.github/workflows/auto-response.yml

@@ -5,8 +5,8 @@ on:
     types: [opened, edited, labeled]
   issue_comment:
     types: [created]
-  pull_request_target: # zizmor: ignore[dangerous-triggers] maintainer-owned label automation; trusted base checkout only, no untrusted PR code execution
-    types: [opened, edited, synchronize, reopened, labeled]
+  pull_request_target: # zizmor: ignore[dangerous-triggers] maintainer-owned label automation; no untrusted checkout or code execution
+    types: [labeled]
 
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
@@ -20,15 +20,10 @@ permissions: {}
 jobs:
   auto-response:
     permissions:
-      contents: read
       issues: write
       pull-requests: write
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@v6
-        with:
-          ref: ${{ github.sha }}
-          persist-credentials: false
       - uses: actions/create-github-app-token@v3
         id: app-token
         continue-on-error: true
@@ -41,15 +36,499 @@ jobs:
         with:
           app-id: "2971289"
           private-key: ${{ secrets.GH_APP_PRIVATE_KEY_FALLBACK }}
-      - name: Run Barnacle auto-response
+      - name: Handle labeled items
         uses: actions/github-script@v9
         with:
           github-token: ${{ steps.app-token.outputs.token || steps.app-token-fallback.outputs.token }}
           script: |
-            const { pathToFileURL } = require("node:url");
-            const moduleUrl = pathToFileURL(
-              `${process.env.GITHUB_WORKSPACE}/scripts/github/barnacle-auto-response.mjs`,
-            );
-            const { runBarnacleAutoResponse } = await import(moduleUrl.href);
+            // Labels prefixed with "r:" are auto-response triggers.
+            const activePrLimit = 10;
+            const rules = [
+              {
+                label: "r: skill",
+                close: true,
+                message:
+                  "Thanks for the contribution! New skills should be published to [Clawhub](https://clawhub.ai) for everyone to use. We’re keeping the core lean on skills, so I’m closing this out.",
+              },
+              {
+                label: "r: support",
+                close: true,
+                message:
+                  "Please use [our support server](https://discord.gg/clawd) and ask in #help or #users-helping-users to resolve this, or follow the stuck FAQ at https://docs.openclaw.ai/help/faq#im-stuck-whats-the-fastest-way-to-get-unstuck.",
+              },
+              {
+                label: "r: no-ci-pr",
+                close: true,
+                message:
+                  "Please don't make PRs for test failures on main.\n\n" +
+                  "The team is aware of those and will handle them directly on the codebase, not only fixing the tests but also investigating what the root cause is. Having to sift through test-fix-PRs (including some that have been out of date for weeks...) on top of that doesn't help. There are already way too many PRs for humans to manage; please don't make the flood worse.\n\n" +
+                  "Thank you.",
+              },
+              {
+                label: "r: too-many-prs",
+                close: true,
+                message:
+                  `Closing this PR because the author has more than ${activePrLimit} active PRs in this repo. ` +
+                  "Please reduce the active PR queue and reopen or resubmit once it is back under the limit. You can close your own PRs to get back under the limit.",
+              },
+              {
+                label: "r: testflight",
+                close: true,
+                commentTriggers: ["testflight"],
+                message: "Not available, build from source.",
+              },
+              {
+                label: "r: third-party-extension",
+                close: true,
+                message:
+                  "Please make this as a third-party plugin that you maintain yourself in your own repo. Docs: https://docs.openclaw.ai/plugin. Feel free to open a PR after to add it to our community plugins page: https://docs.openclaw.ai/plugins/community",
+              },
+              {
+                label: "r: moltbook",
+                close: true,
+                lock: true,
+                lockReason: "off-topic",
+                commentTriggers: ["moltbook"],
+                message:
+                  "OpenClaw is not affiliated with Moltbook, and issues related to Moltbook should not be submitted here.",
+              },
+            ];
 
-            await runBarnacleAutoResponse({ github, context, core });
+            const maintainerTeam = "maintainer";
+            const pingWarningMessage =
+              "Please don’t spam-ping multiple maintainers at once. Be patient, or join our community Discord for help: https://discord.gg/clawd";
+            const mentionRegex = /@([A-Za-z0-9-]+)/g;
+            const maintainerCache = new Map();
+            const normalizeLogin = (login) => login.toLowerCase();
+            const bugSubtypeLabelSpecs = {
+              regression: {
+                color: "D93F0B",
+                description: "Behavior that previously worked and now fails",
+              },
+              "bug:crash": {
+                color: "B60205",
+                description: "Process/app exits unexpectedly or hangs",
+              },
+              "bug:behavior": {
+                color: "D73A4A",
+                description: "Incorrect behavior without a crash",
+              },
+            };
+            const bugTypeToLabel = {
+              "Regression (worked before, now fails)": "regression",
+              "Crash (process/app exits or hangs)": "bug:crash",
+              "Behavior bug (incorrect output/state without crash)": "bug:behavior",
+            };
+            const bugSubtypeLabels = Object.keys(bugSubtypeLabelSpecs);
+
+            const extractIssueFormValue = (body, field) => {
+              if (!body) {
+                return "";
+              }
+              const escapedField = field.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
+              const regex = new RegExp(
+                `(?:^|\\n)###\\s+${escapedField}\\s*\\n([\\s\\S]*?)(?=\\n###\\s+|$)`,
+                "i",
+              );
+              const match = body.match(regex);
+              if (!match) {
+                return "";
+              }
+              for (const line of match[1].split("\n")) {
+                const trimmed = line.trim();
+                if (trimmed) {
+                  return trimmed;
+                }
+              }
+              return "";
+            };
+
+            const ensureLabelExists = async (name, color, description) => {
+              try {
+                await github.rest.issues.getLabel({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  name,
+                });
+              } catch (error) {
+                if (error?.status !== 404) {
+                  throw error;
+                }
+                await github.rest.issues.createLabel({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  name,
+                  color,
+                  description,
+                });
+              }
+            };
+
+            const syncBugSubtypeLabel = async (issue, labelSet) => {
+              if (!labelSet.has("bug")) {
+                return;
+              }
+
+              const selectedBugType = extractIssueFormValue(issue.body ?? "", "Bug type");
+              const targetLabel = bugTypeToLabel[selectedBugType];
+              if (!targetLabel) {
+                return;
+              }
+
+              const targetSpec = bugSubtypeLabelSpecs[targetLabel];
+              await ensureLabelExists(targetLabel, targetSpec.color, targetSpec.description);
+
+              for (const subtypeLabel of bugSubtypeLabels) {
+                if (subtypeLabel === targetLabel) {
+                  continue;
+                }
+                if (!labelSet.has(subtypeLabel)) {
+                  continue;
+                }
+                try {
+                  await github.rest.issues.removeLabel({
+                    owner: context.repo.owner,
+                    repo: context.repo.repo,
+                    issue_number: issue.number,
+                    name: subtypeLabel,
+                  });
+                  labelSet.delete(subtypeLabel);
+                } catch (error) {
+                  if (error?.status !== 404) {
+                    throw error;
+                  }
+                }
+              }
+
+              if (!labelSet.has(targetLabel)) {
+                await github.rest.issues.addLabels({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: issue.number,
+                  labels: [targetLabel],
+                });
+                labelSet.add(targetLabel);
+              }
+            };
+
+            const isMaintainer = async (login) => {
+              if (!login) {
+                return false;
+              }
+              const normalized = normalizeLogin(login);
+              if (maintainerCache.has(normalized)) {
+                return maintainerCache.get(normalized);
+              }
+              let isMember = false;
+              try {
+                const membership = await github.rest.teams.getMembershipForUserInOrg({
+                  org: context.repo.owner,
+                  team_slug: maintainerTeam,
+                  username: normalized,
+                });
+                isMember = membership?.data?.state === "active";
+              } catch (error) {
+                if (error?.status !== 404) {
+                  throw error;
+                }
+              }
+              maintainerCache.set(normalized, isMember);
+              return isMember;
+            };
+
+            const countMaintainerMentions = async (body, authorLogin) => {
+              if (!body) {
+                return 0;
+              }
+              const normalizedAuthor = authorLogin ? normalizeLogin(authorLogin) : "";
+              if (normalizedAuthor && (await isMaintainer(normalizedAuthor))) {
+                return 0;
+              }
+
+              const haystack = body.toLowerCase();
+              const teamMention = `@${context.repo.owner.toLowerCase()}/${maintainerTeam}`;
+              if (haystack.includes(teamMention)) {
+                return 3;
+              }
+
+              const mentions = new Set();
+              for (const match of body.matchAll(mentionRegex)) {
+                mentions.add(normalizeLogin(match[1]));
+              }
+              if (normalizedAuthor) {
+                mentions.delete(normalizedAuthor);
+              }
+
+              let count = 0;
+              for (const login of mentions) {
+                if (await isMaintainer(login)) {
+                  count += 1;
+                }
+              }
+              return count;
+            };
+
+            const triggerLabel = "trigger-response";
+            const activePrLimitLabel = "r: too-many-prs";
+            const activePrLimitOverrideLabel = "r: too-many-prs-override";
+            const target = context.payload.issue ?? context.payload.pull_request;
+            if (!target) {
+              return;
+            }
+
+            const labelSet = new Set(
+              (target.labels ?? [])
+                .map((label) => (typeof label === "string" ? label : label?.name))
+                .filter((name) => typeof name === "string"),
+            );
+
+            const issue = context.payload.issue;
+            const pullRequest = context.payload.pull_request;
+            const comment = context.payload.comment;
+            if (comment) {
+              const authorLogin = comment.user?.login ?? "";
+              if (comment.user?.type === "Bot" || authorLogin.endsWith("[bot]")) {
+                return;
+              }
+
+              const commentBody = comment.body ?? "";
+              const responses = [];
+              const mentionCount = await countMaintainerMentions(commentBody, authorLogin);
+              if (mentionCount >= 3) {
+                responses.push(pingWarningMessage);
+              }
+
+              const commentHaystack = commentBody.toLowerCase();
+              const commentRule = rules.find((item) =>
+                (item.commentTriggers ?? []).some((trigger) =>
+                  commentHaystack.includes(trigger),
+                ),
+              );
+              if (commentRule) {
+                responses.push(commentRule.message);
+              }
+
+              if (responses.length > 0) {
+                await github.rest.issues.createComment({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: target.number,
+                  body: responses.join("\n\n"),
+                });
+              }
+              return;
+            }
+
+            if (issue) {
+              const action = context.payload.action;
+              if (action === "opened" || action === "edited") {
+                const issueText = `${issue.title ?? ""}\n${issue.body ?? ""}`.trim();
+                const authorLogin = issue.user?.login ?? "";
+                const mentionCount = await countMaintainerMentions(
+                  issueText,
+                  authorLogin,
+                );
+                if (mentionCount >= 3) {
+                  await github.rest.issues.createComment({
+                    owner: context.repo.owner,
+                    repo: context.repo.repo,
+                    issue_number: issue.number,
+                    body: pingWarningMessage,
+                  });
+                }
+
+                await syncBugSubtypeLabel(issue, labelSet);
+              }
+            }
+
+            const hasTriggerLabel = labelSet.has(triggerLabel);
+            if (hasTriggerLabel) {
+              labelSet.delete(triggerLabel);
+              try {
+                await github.rest.issues.removeLabel({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: target.number,
+                  name: triggerLabel,
+                });
+              } catch (error) {
+                if (error?.status !== 404) {
+                  throw error;
+                }
+              }
+            }
+
+            const isLabelEvent = context.payload.action === "labeled";
+            if (!hasTriggerLabel && !isLabelEvent) {
+              return;
+            }
+
+            if (issue) {
+              const title = issue.title ?? "";
+              const body = issue.body ?? "";
+              const haystack = `${title}\n${body}`.toLowerCase();
+              const hasMoltbookLabel = labelSet.has("r: moltbook");
+              const hasTestflightLabel = labelSet.has("r: testflight");
+              const hasSecurityLabel = labelSet.has("security");
+              if (title.toLowerCase().includes("security") && !hasSecurityLabel) {
+                await github.rest.issues.addLabels({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: issue.number,
+                  labels: ["security"],
+                });
+                labelSet.add("security");
+              }
+              if (title.toLowerCase().includes("testflight") && !hasTestflightLabel) {
+                await github.rest.issues.addLabels({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: issue.number,
+                  labels: ["r: testflight"],
+                });
+                labelSet.add("r: testflight");
+              }
+              if (haystack.includes("moltbook") && !hasMoltbookLabel) {
+                await github.rest.issues.addLabels({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: issue.number,
+                  labels: ["r: moltbook"],
+                });
+                labelSet.add("r: moltbook");
+              }
+            }
+
+            const invalidLabel = "invalid";
+            const spamLabel = "r: spam";
+            const dirtyLabel = "dirty";
+            const badBarnacleLabel = "bad-barnacle";
+            const noisyPrMessage =
+              "Closing this PR because it looks dirty (too many unrelated or unexpected changes). This usually happens when a branch picks up unrelated commits or a merge went sideways. Please recreate the PR from a clean branch.";
+
+            if (pullRequest) {
+              if (labelSet.has(badBarnacleLabel)) {
+                core.info(`Skipping PR auto-response checks for #${pullRequest.number} because ${badBarnacleLabel} is present.`);
+                return;
+              }
+
+              if (labelSet.has(dirtyLabel)) {
+                await github.rest.issues.createComment({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: pullRequest.number,
+                  body: noisyPrMessage,
+                });
+                await github.rest.issues.update({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: pullRequest.number,
+                  state: "closed",
+                });
+                return;
+              }
+              const labelCount = labelSet.size;
+              if (labelCount > 20) {
+                await github.rest.issues.createComment({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: pullRequest.number,
+                  body: noisyPrMessage,
+                });
+                await github.rest.issues.update({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: pullRequest.number,
+                  state: "closed",
+                });
+                return;
+              }
+              if (labelSet.has(spamLabel)) {
+                await github.rest.issues.update({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: pullRequest.number,
+                  state: "closed",
+                });
+                await github.rest.issues.lock({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: pullRequest.number,
+                  lock_reason: "spam",
+                });
+                return;
+              }
+              if (labelSet.has(invalidLabel)) {
+                await github.rest.issues.update({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: pullRequest.number,
+                  state: "closed",
+                });
+                return;
+              }
+            }
+
+            if (issue && labelSet.has(spamLabel)) {
+              await github.rest.issues.update({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: issue.number,
+                state: "closed",
+                state_reason: "not_planned",
+              });
+              await github.rest.issues.lock({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: issue.number,
+                lock_reason: "spam",
+              });
+              return;
+            }
+
+            if (issue && labelSet.has(invalidLabel)) {
+              await github.rest.issues.update({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: issue.number,
+                state: "closed",
+                state_reason: "not_planned",
+              });
+              return;
+            }
+
+            if (pullRequest && labelSet.has(activePrLimitOverrideLabel)) {
+              labelSet.delete(activePrLimitLabel);
+            }
+
+            const rule = rules.find((item) => labelSet.has(item.label));
+            if (!rule) {
+              return;
+            }
+
+            const issueNumber = target.number;
+
+            await github.rest.issues.createComment({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: issueNumber,
+              body: rule.message,
+            });
+
+            if (rule.close) {
+              await github.rest.issues.update({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: issueNumber,
+                state: "closed",
+              });
+            }
+
+            if (rule.lock) {
+              await github.rest.issues.lock({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: issueNumber,
+                lock_reason: rule.lockReason ?? "resolved",
+              });
+            }

.github/workflows/ci.yml

@@ -1231,7 +1231,6 @@ jobs:
           NODE_OPTIONS: --max-old-space-size=6144
           OPENCLAW_NODE_TEST_CONFIGS_JSON: ${{ toJson(matrix.configs) }}
           OPENCLAW_NODE_TEST_INCLUDE_PATTERNS_JSON: ${{ toJson(matrix.includePatterns) }}
-          OPENCLAW_VITEST_SHARD_NAME: ${{ matrix.shard_name }}
           OPENCLAW_TEST_PROJECTS_PARALLEL: "2"
         shell: bash
         run: |

.github/workflows/codeql.yml

@@ -19,14 +19,13 @@ permissions:
 
 jobs:
   analyze:
-    name: Analyze (${{ matrix.job_name }})
+    name: Analyze (${{ matrix.language }})
     runs-on: ${{ matrix.runs_on }}
     strategy:
       fail-fast: false
       matrix:
         include:
-          - job_name: javascript-typescript-core
-            language: javascript-typescript
+          - language: javascript-typescript
             runs_on: blacksmith-32vcpu-ubuntu-2404
             needs_node: true
             needs_python: false
@@ -34,21 +33,8 @@ jobs:
             needs_swift_tools: false
             needs_manual_build: false
             needs_autobuild: false
-            analyze_category: javascript-typescript-core
-            config_file: ./.github/codeql/codeql-javascript-typescript-core.yml
-          - job_name: javascript-typescript-extensions
-            language: javascript-typescript
-            runs_on: blacksmith-32vcpu-ubuntu-2404
-            needs_node: true
-            needs_python: false
-            needs_java: false
-            needs_swift_tools: false
-            needs_manual_build: false
-            needs_autobuild: false
-            analyze_category: javascript-typescript-extensions
-            config_file: ./.github/codeql/codeql-javascript-typescript-extensions.yml
-          - job_name: actions
-            language: actions
+            config_file: ./.github/codeql/codeql-javascript-typescript.yml
+          - language: actions
             runs_on: blacksmith-16vcpu-ubuntu-2404
             needs_node: false
             needs_python: false
@@ -56,10 +42,8 @@ jobs:
             needs_swift_tools: false
             needs_manual_build: false
             needs_autobuild: false
-            analyze_category: actions
             config_file: ""
-          - job_name: python
-            language: python
+          - language: python
             runs_on: blacksmith-16vcpu-ubuntu-2404
             needs_node: false
             needs_python: true
@@ -67,10 +51,8 @@ jobs:
             needs_swift_tools: false
             needs_manual_build: false
             needs_autobuild: false
-            analyze_category: python
             config_file: ""
-          - job_name: java-kotlin
-            language: java-kotlin
+          - language: java-kotlin
             runs_on: blacksmith-16vcpu-ubuntu-2404
             needs_node: false
             needs_python: false
@@ -78,10 +60,8 @@ jobs:
             needs_swift_tools: false
             needs_manual_build: true
             needs_autobuild: false
-            analyze_category: java-kotlin
             config_file: ""
-          - job_name: swift
-            language: swift
+          - language: swift
             runs_on: ${{ github.repository == 'openclaw/openclaw' && 'blacksmith-12vcpu-macos-latest' || 'macos-latest' }}
             needs_node: false
             needs_python: false
@@ -89,7 +69,6 @@ jobs:
             needs_swift_tools: true
             needs_manual_build: true
             needs_autobuild: false
-            analyze_category: swift
             config_file: ""
     steps:
       - name: Checkout
@@ -156,4 +135,4 @@ jobs:
       - name: Analyze
         uses: github/codeql-action/analyze@b25d0ebf40e5b63ee81e1bd6e5d2a12b7c2aeb61 # v4
         with:
-          category: "/language:${{ matrix.analyze_category }}"
+          category: "/language:${{ matrix.language }}"

.github/workflows/openclaw-live-and-e2e-checks-reusable.yml

@@ -430,11 +430,6 @@ jobs:
             command: pnpm test:docker:doctor-switch
             timeout_minutes: 60
             release_path: true
-          - suite_id: docker-session-runtime-context
-            label: Session Runtime Context Docker E2E
-            command: pnpm test:docker:session-runtime-context
-            timeout_minutes: 60
-            release_path: true
           - suite_id: docker-qr
             label: QR Import Docker E2E
             command: pnpm test:docker:qr

AGENTS.md

@@ -57,9 +57,7 @@ Telegraph style. Root rules only. Read scoped `AGENTS.md` before subtree work.
 ## GitHub / CI
 
 - Triage: list first, hydrate few. Use bounded `gh --json --jq`; avoid repeated full comment scans.
-- Automatic PR/issue discovery: skip maintainer-owned items unless directly relevant. Do not comment, close, label, retitle, rebase, fix up, or land them without Peter asking.
 - Search/dedupe: prefer `gh search issues 'repo:openclaw/openclaw is:open <terms>' --json number,title,state,updatedAt --limit 20`.
-- GitHub search boolean text is fussy. If `OR` queries return empty, split exact terms and search title/body/comments separately before concluding no hits.
 - PR shortlist: `gh pr list ...`; then `gh pr view <n> --json number,title,body,closingIssuesReferences,files,statusCheckRollup,reviewDecision`.
 - After landing PR: search duplicate open issues/PRs. Before closing: comment why + canonical link.
 - GH comments with markdown backticks, `$`, or shell snippets: avoid inline double-quoted `--body`; use single quotes or `--body-file`.
@@ -124,8 +122,7 @@ Telegraph style. Root rules only. Read scoped `AGENTS.md` before subtree work.
 
 - Docs change with behavior/API. Use docs list/read_when hints; docs links per `docs/AGENTS.md`.
 - Changelog user-facing only; pure test/internal usually no entry.
-- Changelog placement: active version `### Changes`/`### Fixes`; every added entry must include at least one `Thanks @author` attribution, using credited GitHub username(s). Never add `Thanks @steipete`.
-- Changelog bullets are always single-line. No wrapping/continuation across multiple lines. Long entries stay on one long line so dedupe, PR-ref, and credit-audit tooling work and so the visual style stays uniform.
+- Changelog placement: active version `### Changes`/`### Fixes`; every added entry must include at least one `Thanks @author` attribution, using credited GitHub username(s).
 
 ## Git
 

CHANGELOG.md

@@ -8,27 +8,27 @@ Docs: https://docs.openclaw.ai
 
 ### Changes
 
-- Plugins/tokenjuice: bump the bundled tokenjuice runtime to 0.6.3. Thanks @vincentkoc.
-- TTS/agents: allow `agents.list[].tts` to override global `messages.tts` for per-agent voices while keeping shared provider credentials and preferences in the existing TTS config surface.
-- TTS/agents: make `/tts audio`, `/tts status`, and the `tts` agent tool honor the active `agents.list[].tts` voice/provider override.
-- Providers/Azure Speech: add Azure Speech as a bundled TTS provider with Speech-resource auth, voice listing, SSML escaping, native Ogg/Opus voice-note output, and telephony output. (#51776) Thanks @leonchui.
-- CLI/image generation: expose generic `--background` on `openclaw infer image generate` and `openclaw infer image edit`, keep `--openai-background` as an OpenAI alias, and let fal image generation honor `--output-format png|jpeg`. Thanks @steipete.
-- Browser/config: allow local managed Chrome launch discovery and post-launch CDP readiness timeouts to be raised for slower hosts such as Raspberry Pi. Fixes #66803. Thanks @beat843796.
+- CLI/image generation: expose generic `--background` on
+  `openclaw infer image generate` and `openclaw infer image edit`, keep
+  `--openai-background` as an OpenAI alias, and let fal image generation honor
+  `--output-format png|jpeg`. Thanks @steipete.
+- Browser/config: allow local managed Chrome launch discovery and post-launch
+  CDP readiness timeouts to be raised for slower hosts such as Raspberry Pi.
+  Fixes #66803. Thanks @beat843796.
 - Discord: allow `channels.discord.voice.model` to override the LLM used for voice channel responses while keeping STT and TTS on their existing media settings. (#64368) Thanks @mrdavey.
 - Browser/CLI: add `openclaw browser start --headless` as a one-shot local managed browser launch override without rewriting persisted browser config. Thanks @BenediktSchackenberg.
 - CLI/Crestodian: open interactive Crestodian in the full OpenClaw TUI shell instead of a basic readline prompt.
 - CLI/Crestodian: shorten the startup greeting to the active planner/model, config state, Gateway probe result, and next debug action instead of dumping every discovered backend.
-- Plugins: migrate the local plugin registry automatically during package install/update, keeping install metadata in the plugin index while indexing existing plugin manifests for the new cold registry path. Thanks @vincentkoc and @shakkernerd.
-- Plugins/doctor: make `openclaw doctor --fix` refresh the plugin index and cold registry index when needed without treating plugin install records as authored config. Thanks @vincentkoc and @shakkernerd.
+- Plugins: migrate the local plugin registry automatically during package install/update, preserving legacy config and install-ledger state while indexing existing plugin manifests for the new cold registry path. Thanks @vincentkoc.
+- Plugins/doctor: make `openclaw doctor --fix` move legacy `plugins.installs`
+  config records into the managed plugin install ledger and refresh the cold
+  registry index when needed. Thanks @vincentkoc.
 - Diagnostics/OTEL: align model-call GenAI span attributes with OpenTelemetry stability opt-in semantics, keeping legacy `gen_ai.system` by default while emitting `gen_ai.provider.name` under `OTEL_SEMCONV_STABILITY_OPT_IN=gen_ai_latest_experimental`. Thanks @vincentkoc.
-- Diagnostics/OTEL: support signal-specific OTLP endpoint overrides for traces, metrics, and logs via config or standard OTEL environment variables. Thanks @vincentkoc.
-- Diagnostics/OTEL: emit bounded telemetry exporter health diagnostics for startup and log-export failures without exporting raw error text. Thanks @vincentkoc.
 - Plugins/CLI: add `openclaw plugins registry` for explicit persisted-registry inspection and `--refresh` repair without making normal startup rescan plugin locations. Thanks @vincentkoc.
 - Plugins/CLI: make `openclaw plugins list` read the cold persisted registry snapshot by default, leaving module-aware diagnostics to `plugins doctor` and `plugins inspect`. Thanks @vincentkoc.
 - Plugins/startup: move gateway startup plugin planning onto the versioned cold registry index, with postinstall repair for older registry files that predate startup metadata. Thanks @vincentkoc.
 - Plugins/startup: normalize startup and provider plugin enablement through registry aliases so boot paths do not need the legacy manifest alias scan. Thanks @vincentkoc.
 - Providers/plugins: resolve provider ownership, provider discovery scopes, and catalog-hook provider ids from the cold plugin registry instead of rescanning manifests on those paths. Thanks @vincentkoc.
-- Plugins/registry: keep installed plugin index records focused on install/state/load paths and resolve plugin capabilities from manifests scoped to indexed plugins. Thanks @shakkernerd.
 - Plugins/chat commands: refresh the persisted plugin registry after `/plugins enable` and `/plugins disable`, matching the CLI mutation path. Thanks @vincentkoc.
 - Plugins/compat: mark `OPENCLAW_DISABLE_PERSISTED_PLUGIN_REGISTRY` as a deprecated break-glass switch and point operators at registry repair instead. Thanks @vincentkoc.
 - Plugins/registry: ignore stale persisted registry reads when plugin policy no longer matches current config, and stamp generated registry files with a do-not-edit warning. Thanks @vincentkoc.
@@ -38,136 +38,86 @@ Docs: https://docs.openclaw.ai
 - Diagnostics/OTEL: export existing tool-loop diagnostics as `openclaw.tool.loop` counters and spans without loop messages, session identifiers, params, or tool output. Thanks @vincentkoc.
 - Diagnostics/OTEL: export diagnostic memory samples and pressure as bounded memory histograms, counters, and pressure spans to help spot leak regressions without session or payload data. Thanks @vincentkoc.
 - Diagnostics/OTEL: add the GenAI `gen_ai.client.token.usage` histogram for input/output model usage while keeping session identifiers and aggregate cache counters out of the semantic metric. Thanks @vincentkoc.
-- Plugins/install: consolidate managed plugin install metadata into the state-managed plugin index at `plugins/installs.json`, replacing the temporary `plugins/installed-index.json` path and removing `plugins.installs` as an authored config surface. Thanks @vincentkoc and @shakkernerd.
+- Plugins/install: move managed plugin install metadata from `plugins.installs`
+  to the state-managed `plugins/installs.json` ledger, with legacy config reads
+  kept as a deprecated compatibility fallback. Thanks @vincentkoc.
 - Diagnostics/OTEL: add the GenAI `gen_ai.client.operation.duration` histogram for model-call latency in seconds with bounded provider/model/API and error attributes. Thanks @vincentkoc.
 - Diagnostics/OTEL: add GenAI usage token attributes to model-usage spans, including cache read/write input token counts without session identifiers or prompt/response content. Thanks @vincentkoc.
 - Diagnostics/OTEL: include bounded GenAI operation, provider, and request-model attributes on model-usage spans so token usage remains self-describing without diagnostic identifiers. Thanks @vincentkoc.
 - Diagnostics/OTEL: keep model-usage span GenAI provider attributes aligned with the existing semantic-convention opt-in policy, using legacy `gen_ai.system` unless latest experimental GenAI conventions are enabled. Thanks @vincentkoc.
 - Diagnostics/OTEL: keep `gen_ai.request.model` present on GenAI token usage metrics with a bounded `unknown` fallback when model usage events do not include a model. Thanks @vincentkoc.
 - Docs/OTEL: document the GenAI token and model-call duration metrics, model-usage span attributes, and `OTEL_SEMCONV_STABILITY_OPT_IN=gen_ai_latest_experimental` provider-attribute behavior. Thanks @vincentkoc.
-- Diagnostics/trace: add an internal traceparent propagation helper that only formats trusted dispatcher metadata, keeping plugin-emitted diagnostic traces out of outbound propagation by default. Thanks @vincentkoc.
 - Diagnostics/OTEL: add bounded outbound message delivery lifecycle diagnostics and export them as low-cardinality delivery spans/metrics without message body, recipient, room, or media-path data. (#71471) Thanks @vincentkoc and @jlapenna.
 - Diagnostics/OTEL: emit bounded exec-process diagnostics and export them as `openclaw.exec` spans without exposing command text, working directories, or container identifiers. (#71451) Thanks @vincentkoc and @jlapenna.
 - Diagnostics/OTEL: support `OPENCLAW_OTEL_PRELOADED=1` so the plugin can reuse an already-registered OpenTelemetry SDK while keeping OpenClaw diagnostic listeners wired. (#71450) Thanks @vincentkoc and @jlapenna.
 - Providers/Xiaomi: add MiMo TTS as a bundled speech provider with MP3/WAV output and voice-note Opus transcoding. Fixes #52376. (#55614) Thanks @zoujiejun.
 - Providers/ElevenLabs: include `eleven_v3` in the bundled TTS model catalog so model selection surfaces can offer ElevenLabs v3. (#68321) Thanks @itsuzef.
 - Providers/Local CLI TTS: add a bundled local command speech provider with file/stdout input, voice-note Opus conversion, and telephony PCM output. (#56239) Thanks @solar2ain.
-- Providers/Inworld: add Inworld as a bundled speech provider with streaming TTS synthesis, voice listing, voice-note output, and PCM telephony output. (#55972) Thanks @cshape.
-- Providers/Volcengine: add Volcengine/BytePlus Seed Speech as a bundled TTS provider with API-key auth, native Ogg/Opus voice-note output, and MP3 audio-file output. (#55641) Thanks @xuruiray.
 - Android/Talk Mode: expose Talk Mode in the Voice tab with runtime-owned voice capture modes and microphone foreground-service escalation. Thanks @alex-latitude.
 - Providers/LiteLLM: register `litellm` as an image-generation provider so `image_generate model=litellm/...` calls and `agents.defaults.imageGenerationModel.fallbacks` entries resolve through the LiteLLM proxy. Thanks @zqchris.
-- Providers/fal: add Seedance 2.0 reference-to-video models with multi-image, video, and audio reference input mapping plus model-specific capability limits for `video_generate`. Thanks @shivanker.
-- Codex harness: require Codex app-server `0.125.0` or newer and cover native MCP `PreToolUse`, `PostToolUse`, and `PermissionRequest` payloads through the OpenClaw hook relay.
-- Agents/Codex: teach prompts and `agents_list` to surface native Codex app-server availability so agents prefer `/codex ...` over Codex ACP unless ACP/acpx is explicit. Thanks @vincentkoc.
-- ACPX/Droid: add Factory Droid to the live ACP bind Docker matrix, including `.factory` settings staging, `FACTORY_API_KEY` forwarding, and the single-agent `test:docker:live-acp-bind:droid` recipe.
 
 ### Fixes
 
-- ACP: send subagent and async-task completion wakes to external ACP harnesses as
-  plain prompts instead of OpenClaw internal runtime-context envelopes, while
-  keeping those envelopes out of ACP transcripts.
-- Agents/Claude: treat zero-token empty `stop` turns as failed provider output,
-  retry once, repair replay, and allow configured model fallback instead of
-  preserving them as successful silent replies. Fixes #71880. Thanks @MagnaAI.
-- Diagnostics/OTEL: treat normal early model stream cleanup as a completed model call instead of exporting a misleading `StreamAbandoned` error span. Thanks @vincentkoc.
-- Gateway/pairing: stop corrupt or unreadable device/node pairing stores from being treated as empty state, preserving `paired.json` for repair instead of overwriting approved pairings. Fixes #71873. Thanks @iret77.
-- ACP: keep `/acp` management commands, plus local `/status` and `/unfocus`, on the Gateway path inside ACP-bound threads so they are not consumed as ACP prompt text. Fixes #66298. Thanks @kindomLee.
-- ACP: wait for the configured runtime backend to become healthy before startup identity reconciliation, avoiding transient acpx warnings during Gateway boot. Fixes #40566.
-- Channels/ACP bindings: time out configured binding readiness checks instead of letting Discord preflight hang forever when an ACP target never settles. Fixes #68776.
-- Control UI: hide the chat loading skeleton during background history reloads when existing messages or active stream content are already visible, avoiding reload flashes on high-latency local gateways. Fixes #71844. Thanks @WolvenRA.
-- Agents/images: scrub old `[media attached: ...]`, `[Image: source: ...]`,
-  and `media://inbound/...` markers from pruned model replay context so stale
-  media refs are not rehydrated as fresh prompt images. Fixes #71868. Thanks
-  @jmeadlock.
-- CLI/status: label the OpenClaw Serve/Funnel setting as `Tailscale exposure`
-  and show daemon state separately when available, so `gateway.tailscale.mode:
-"off"` no longer reads like the Tailscale daemon is stopped. Fixes #71790.
-  Thanks @pesvobodak.
-- Plugins/Bonjour: stop ciao mDNS watchdog failures from looping forever when the advertiser stays stuck in `probing` or `announcing`; Bonjour now disables itself for the current Gateway process after repeated failed restarts while the Gateway keeps running. Fixes #69011. Thanks @siddharthaagarwalofficial-ux, @FiredMosquito831, and @spikefcz.
-- Gateway/Fly.io: seed Control UI allowed origins from the actual runtime bind and port so CLI-driven non-loopback starts do not crash before config exists. Fixes #71823.
-- Gateway/proxy: bootstrap env proxy dispatching from direct Gateway startup so provider and plugin network requests honor `HTTPS_PROXY`/`HTTP_PROXY` before the first embedded agent attempt runs. (#71833) Thanks @mjamiv.
-- Models/LM Studio: preserve `@iq*` quant suffixes in model refs and provider matching so `/model lmstudio/...@iq3_xxs` keeps the exact LM Studio variant. Fixes #71474. (#71486) Thanks @Bartok9, @XinwuC, and @Sanjays2402.
-- Matrix/cron: preserve the live Matrix delivery target when creating implicit announce reminder jobs so mixed-case room IDs are not reconstructed from lowercased session keys. Fixes #71798.
-- Feishu: accept Schema 2.0 card action callbacks that report `context.open_chat_id` instead of legacy `context.chat_id`, so button callbacks no longer drop as malformed. Fixes #71670. Thanks @eddy1068.
-- Feishu: keep synthetic card-action and bot-menu ids out of platform reply targets, using the real card callback message id when Feishu provides one and plain-sending otherwise. Fixes #71673. Thanks @eddy1068.
-- Plugins/QQ Bot: prefer an installed QQ Bot plugin that declares it replaces the bundled `qqbot` channel, preventing duplicate `qqbot_channel_api` and `qqbot_remind` tool registration noise. Fixes #63102.
-- Browser automation: keep stable tab ids and labels attached when Chromium replaces the raw target after form submissions or other action-triggered navigations, and return the replacement `targetId` from `/act` when the match is provable. Fixes #46137.
-- QQ Bot: make `qqbot_remind` schedule, list, and remove Gateway cron jobs directly for owner-authorized senders instead of returning `cronParams` and relying on a follow-up generic `cron` tool call. Fixes #70865. (#70937) Thanks @GaosCode.
-- Agents/ACP: hide `sessions_spawn` ACP runtime options unless an ACP backend is loaded, and make `/acp doctor` call out `plugins.allow` blocking bundled `acpx`. Thanks @vincentkoc.
-- Media delivery: avoid sending generated image attachments twice when the assistant reply already includes explicit `MEDIA:` lines for the same turn, and reject unsafe remote `MEDIA:` URLs before delivery. Thanks @pashpashpash.
-- Codex harness: ignore retryable app-server error notifications after Codex recovers, and preserve the real nested error message for terminal app-server failures instead of replacing it with a generic failure. Thanks @pashpashpash.
-- Agents/subagents: keep queued subagent announces session-only when the requester has no external channel target, avoiding ambiguous multi-channel delivery failures. Fixes #59201. Thanks @larrylhollan.
-- Image understanding: preserve configured provider-prefixed vision model metadata when callers request the model without the provider prefix, so custom image models keep their `input: ["text", "image"]` capability. Fixes #33185. Thanks @Kobe9312 and @vincentkoc.
-- Plugins/install: restore the previous plugin index records if a concurrent config write conflict interrupts install, update, or uninstall metadata commits. Thanks @shakkernerd.
-- Plugins/update: restore previous plugin index records if core update or channel setup hits a concurrent config write conflict after plugin metadata changes. Thanks @shakkernerd.
-- Plugins/onboarding: defer channel/provider plugin install records until the owning config write commits, keeping setup failures from advancing the plugin index ahead of `openclaw.json`. Thanks @shakkernerd.
-- Plugins/config: route configure and agent setup writes with pending plugin install records through the plugin index commit helper so provider onboarding metadata is not stripped by plain config writes. Thanks @shakkernerd.
-- Plugins/channels: merge pending channel plugin install records with the existing plugin index before config writes, preserving unrelated tracked installs during channel setup, resolve, remove, and capability repair flows. Thanks @shakkernerd.
-- Plugins/config: defer shipped `plugins.installs` index migration during config writes until the guarded config commit window and roll it back if the config write fails before commit. Thanks @shakkernerd.
-- Sessions: keep embedded runtime context out of the visible user prompt by sending it as a hidden next-turn custom message, and teach doctor to repair affected 2026.4.24 transcripts with duplicated prompt-rewrite branches. Fixes #71761.
-- Gateway/subagents: keep direct-loopback backend RPCs authenticated with the shared gateway token/password off stale CLI paired-device scope baselines, so internal calls no longer hit `scope-upgrade` pairing prompts while remote, browser, node, device-token, and explicit-device paths still require normal pairing approval. Fixes #63548.
-- Providers/Azure OpenAI: give deployment-scoped image generation requests a longer 600s default timeout so slow `gpt-image-2` generations can complete without a per-call `timeoutMs`. Fixes #71705. Thanks @voytas75.
-- Gateway/plugins: link source-checkout bundled runtime dependency caches instead of recursively copying `node_modules` on the gateway main thread, preventing local status, node, and skill probes from timing out during startup cache restores. Thanks @steipete.
-- Skills/remote nodes: only expose remote macOS skill bins for connected nodes, clear stale bin matches when node probes fail, and include probe command, timeout, bin count, and connection state in timeout logs. Thanks @steipete.
-- CLI/gateway: keep diagnostic probes from creating first-time read-only device pairings, while still reusing cached device tokens for detailed read probes. Fixes #71766. Thanks @SunboZ.
-- CLI/plugins: keep `message` startup, `channels logs`, `agents delete`, and `agents set-identity` off broad plugin preloading; message delivery still loads plugins when the action actually runs.
-- Image understanding: resolve configured image models such as local LM Studio vision entries before reporting `Unknown model` when the discovery registry has not registered that provider. Fixes #66486. Thanks @zhanggpcsu.
-- Sessions: separate reset freshness from session-store `updatedAt`, so heartbeat, cron, exec, and gateway bookkeeping no longer prevent configured daily/idle resets from rolling long-running channel sessions. Fixes #68315, #63732, #63820, and #69083. Thanks @maxatv, @longhairedsi, @bradfreels, and @akessel56.
-- Sessions: clear queued system-event notices during `/new`, `/reset`, gateway `sessions.reset`, and daily/idle rollover so stale background updates cannot leak into the first prompt of the fresh session. Fixes #66864. Thanks @opeyio, @Magicray1217, and @cedillarack.
-- CLI/agents: keep `agents bind`, `agents unbind`, and `agents bindings` on setup-safe channel metadata paths so they do not preload bundled plugin runtimes or stage runtime dependencies. Fixes #71743.
-- Plugins/registry: preserve explicit disabled plugin records during registry migration without persisting every unused bundled plugin discovered on disk. Thanks @shakkernerd.
-- Windows/native: keep CLI startup and bundled provider plugin loading off Windows ESM raw-path failure paths, fixing native onboarding/install smoke on Node 24. Thanks @steipete.
-- Plugins/doctor: read bundled channel doctor capabilities through the same packaged plugin directory resolver used by plugin loading, so published installs keep Matrix DM allowlist repairs on `channels.matrix.dm.*` instead of writing invalid top-level `dmPolicy` keys. Fixes #71757.
-- Plugins/Windows: keep bundled plugin Jiti loaders off the native import path on Windows so channel plugins such as Telegram no longer crash with `ERR_UNSUPPORTED_ESM_URL_SCHEME` on `C:\...` paths. Fixes #71749. Thanks @smeyer9.
-- Providers/Ollama: use Ollama's current `/api/web_search` endpoint and honor `https://ollama.com` model-provider base URLs for Ollama Web Search. Fixes #71741. Thanks @madhvidua.
-- Memory/Ollama: serialize Ollama memory embedding batches and add an inline batch timeout override, with longer defaults for local/self-hosted embedding providers. Thanks @steipete.
-- Sessions/usage: exclude compaction checkpoint transcript snapshots from usage totals and session discovery, while keeping old checkpoint files removable. Thanks @steipete.
-- CLI/agents: keep `openclaw agents list --json` on the config-only path by default, avoiding bundled plugin loading unless callers request `--bindings`. Fixes #71739. Thanks @kaloster.
-- Plugins/install: force plugin dependency installs to stay project-local even when inherited npm config requests global installs, so successful installs still materialize the plugin's staged `node_modules`.
-- Providers/Google: transcode Gemini TTS PCM to Opus for voice-note targets so WhatsApp and other native voice-note replies can play as voice messages.
-- TTS/WhatsApp: mark non-Opus provider output as voice-note intent so channel delivery transcodes MP3/WebM replies to Ogg/Opus PTT audio.
-- Plugins/runtime deps: reuse existing external bundled-plugin stage roots when mirrored plugin roots are inspected again, avoiding second-generation `openclaw-unknown-*` stages and repeated first-turn restaging. Fixes #71599.
-- iOS/macOS Talk Mode: allow `talk.speechLocale` to set the speech recognition locale for non-English voice conversations. Fixes #44688.
-- Plugins/providers: honor explicit plugin candidate lists instead of reading a persisted registry snapshot from local state, keeping candidate-scoped provider discovery hermetic.
-- Plugins/doctor: keep bundled plugin runtime-dependency repairs inside the managed OpenClaw stage even when user npm prefix/global config points npm at `$HOME/node_modules`. Fixes #71730.
-- ACP/sessions_spawn: reject normal OpenClaw config agent ids when callers explicitly request `runtime="acp"`, while allowing agents configured with `runtime.type="acp"` to resolve to their ACP harness id. Fixes #63914.
-- ACP/sessions_spawn: apply `runTimeoutSeconds` to ACP child turns and dispatch those turns on the background subagent lane, so quota-stalled ACP harnesses do not occupy the main agent lane indefinitely. Fixes #68823.
-- ACP/oneshot: reconcile runtime session identity before closing completed oneshot ACP runs, so finished `sessions.json` entries do not stay stuck with `acp.identity.state="pending"`.
-- ACPX: bundle `acpx@0.6.1` so unsupported generic model overrides fail clearly instead of silently falling back to the target adapter default.
-- ACP/models: document that non-Codex ACP model overrides require adapter support for ACP `models` plus `session/set_model`, so unsupported harnesses fail clearly instead of silently falling back to their defaults.
-- Plugins/Voice Call: treat missing provider credentials as setup-incomplete during Gateway startup and log the missing keys as a warning instead of a runtime startup error, while keeping explicit command/tool errors when used. Thanks @steipete.
-- Android/Talk Mode: prevent duplicate TTS playback when fast or repeated final chat events arrive while Talk Mode is waiting for its own response. Fixes #46546.
-- Tooling/check:changed: pass parent heavy-check lock markers to lint lanes so `pnpm check:changed` no longer waits on its own `lint:extensions` child. Thanks @steipete.
-- CLI/completion: dedupe provider auth flags before registering `openclaw onboard` options, so completion-cache refresh during update no longer fails when stale core fallback flags overlap plugin manifest flags. Fixes #71667.
-- Diagnostics/trace: report live context usage from the current prompt snapshot instead of provider turn totals, avoiding false near-full context spikes on cached or tool-heavy runs.
-- Providers/Google: honor `models.providers.google.request.allowPrivateNetwork` for Gemini TTS and telephony TTS, matching Google image generation and media understanding. (#71723) Thanks @ro-hansolo.
-- Providers/MiniMax: register `minimax-portal` for music and video generation, preserving OAuth auth and regional MiniMax base URLs across the shared `music_generate` and `video_generate` tools. (#63241) Thanks @tars90percent.
-- Providers/onboarding: keep Runway and Alibaba Model Studio out of the text-inference setup picker by scoping their video-generation auth choices to the media setup flow. (#65856) Thanks @Jah-yee.
+- Plugins/Voice Call: treat missing provider credentials as setup-incomplete
+  during Gateway startup and log the missing keys as a warning instead of a
+  runtime startup error, while keeping explicit command/tool errors when used. Thanks
+  @steipete.
+- Tooling/check:changed: pass parent heavy-check lock markers to lint lanes so
+  `pnpm check:changed` no longer waits on its own `lint:extensions` child.
+  Thanks @steipete.
+- CLI/completion: dedupe provider auth flags before registering `openclaw onboard`
+  options, so completion-cache refresh during update no longer fails when stale
+  core fallback flags overlap plugin manifest flags. Fixes #71667.
+- Diagnostics/trace: report live context usage from the current prompt snapshot
+  instead of provider turn totals, avoiding false near-full context spikes on
+  cached or tool-heavy runs.
 - Plugins/Bonjour: stop the gateway from crash-looping on `CIAO PROBING CANCELLED` when the mDNS watchdog cancels a stuck probe. Restores the rejection-handler wiring dropped during the bonjour plugin migration and shares unhandled-rejection state across module instances so plugin-staged copies of `openclaw/plugin-sdk/runtime` register into the same handler set the host consults. Especially affects Docker on macOS, where mDNS probing reliably hits the watchdog. Thanks @troyhitch.
-- Google Meet: report pinned Chrome nodes as offline or missing capabilities in setup/join diagnostics, keep inaccessible nodes out of auto-selection, and preflight local BlackHole/SoX requirements before agents try local Chrome. Thanks @steipete.
-- Providers/MiniMax: route `image-01` requests to the dedicated image generation endpoint while preserving CN endpoint selection. Fixes #61149. Thanks @mushuiyu886.
-- Plugins/startup: remove ownerless bundled runtime-dependency install locks after a short grace window and include lock owner details when startup times out waiting for a plugin runtime-deps lock.
-- Plugins/install: anchor bundled runtime-dependency npm installs with an OpenClaw-owned package manifest so Linux updates cannot accidentally write to a parent `$HOME/node_modules` tree. Fixes #71730.
-- Plugins/install: pass onboarding plugin config into plugin index writes so local plugin installs outside default discovery roots keep their install records. Thanks @shakkernerd.
-- Plugins/install: migrate shipped `plugins.installs` config records into the plugin index while stripping them from runtime config and future writes. Thanks @shakkernerd.
-- Plugins/install: keep migrated plugin install records in the plugin index even when the plugin manifest is missing or invalid, so update, uninstall, inspect, and audit can still recover broken installs. Thanks @shakkernerd.
-- Plugins/security: keep plugin audit JSON check ids stable while reporting plugin index install-record findings with updated wording. Thanks @shakkernerd.
-- CLI/config: reject direct `plugins.installs` edits with guidance to use `openclaw plugins install`, `openclaw plugins update`, or `openclaw plugins uninstall` instead. Thanks @shakkernerd.
-- Live tests/voice: accept common STT variants for OpenClaw and ElevenLabs brand names so provider smoke tests fail on real regressions rather than equivalent transcripts.
-- Agents/replies: forward sanitized underlying agent failure details on external channels instead of replacing unknown failures with a generic retry message.
-- CLI/MCP: translate OpenClaw `mcp.servers.*.transport` entries into Claude/Gemini CLI `type` fields so streamable HTTP MCP servers load in CLI backend sessions. (#71724) Thanks @Blockchain-Oracle.
-- Browser/CDP: honor configured remote and `attachOnly` CDP HTTP/WebSocket timeouts when opening tabs through raw CDP or `/json/new` fallback. (#54238) Thanks @FuncWei.
-- WhatsApp/TTS: send visible text separately from PTT voice-note audio instead of relying on hidden voice-note captions. Fixes #51081.
-- Browser/client: avoid telling agents to restart OpenClaw for dispatcher timeouts on external browser profiles such as `attachOnly`, remote CDP, and existing-session. (#40815) Thanks @0xsline.
-- Agents/TTS: preserve `[[audio_as_voice]]` directives on trusted text tool-result `MEDIA:` payloads so generated audio still delivers as a voice note. (#46535) Thanks @azade-c.
-- Agents/TTS: keep queued tool media when an assistant ends with `NO_REPLY` on non-block delivery paths, so media-only generated audio replies still send. (#60025) Thanks @bradlind1.
-- Telegram/STT: frame inbound voice-note transcripts as machine-generated, untrusted text in agent context while preserving raw transcript mention detection. Closes #33360. Thanks @smartchainark.
+- Google Meet: report pinned Chrome nodes as offline or missing capabilities in
+  setup/join diagnostics, keep inaccessible nodes out of auto-selection, and
+  preflight local BlackHole/SoX requirements before agents try local Chrome.
+  Thanks @steipete.
+- Providers/MiniMax: route `image-01` requests to the dedicated image
+  generation endpoint while preserving CN endpoint selection. Fixes #61149.
+  Thanks @mushuiyu886.
+- Plugins/startup: remove ownerless bundled runtime-dependency install locks
+  after a short grace window and include lock owner details when startup times
+  out waiting for a plugin runtime-deps lock.
+- Live tests/voice: accept common STT variants for OpenClaw and ElevenLabs
+  brand names so provider smoke tests fail on real regressions rather than
+  equivalent transcripts.
+- Agents/replies: forward sanitized underlying agent failure details on external
+  channels instead of replacing unknown failures with a generic retry message.
+- Browser/CDP: honor configured remote and `attachOnly` CDP HTTP/WebSocket
+  timeouts when opening tabs through raw CDP or `/json/new` fallback. (#54238)
+  Thanks @FuncWei.
+- WhatsApp/TTS: send visible text separately from PTT voice-note audio instead
+  of relying on hidden voice-note captions. Fixes #51081.
+- Browser/client: avoid telling agents to restart OpenClaw for dispatcher
+  timeouts on external browser profiles such as `attachOnly`, remote CDP, and
+  existing-session. (#40815) Thanks @0xsline.
+- Agents/TTS: preserve `[[audio_as_voice]]` directives on trusted text
+  tool-result `MEDIA:` payloads so generated audio still delivers as a voice
+  note. (#46535) Thanks @azade-c.
+- Agents/TTS: keep queued tool media when an assistant ends with `NO_REPLY` on
+  non-block delivery paths, so media-only generated audio replies still send.
+  (#60025) Thanks @bradlind1.
+- Telegram/STT: frame inbound voice-note transcripts as machine-generated,
+  untrusted text in agent context while preserving raw transcript mention
+  detection. Closes #33360. Thanks @smartchainark.
 - Subagents/browser: show an actionable `/tools` notice when browser automation is configured but filtered out by the active tool profile, and document that coding-profile agents should use `tools.alsoAllow: ["browser"]` rather than subagent allowlists alone.
 - Control UI/Quick Settings: persist the assistant avatar override to browser local storage (mirroring the user avatar) so uploaded image data URLs no longer fail config validation with "Too big: expected string to have <=200 characters". Also lift the gateway-side `ui.assistant.avatar` length cap to match the user avatar size budget for non-UI clients writing the field directly. Thanks @BunsDev.
-- Plugin SDK: share diagnostic event subscriptions across duplicate source/dist module graphs so legacy root SDK imports still receive runtime diagnostic events.
-- Agents/Bedrock: prevent empty assistant stream-error turns from poisoning Converse replay by persisting, repairing, and replaying a non-empty fallback block. Fixes #71572. (#71627) Thanks @openperf.
-- Agents/Anthropic/Bedrock: strip thinking blocks with missing, empty, or blank replay signatures before provider conversion, falling back to non-empty omitted-reasoning text when needed so corrupted signed-thinking history no longer poisons subsequent turns. Fixes #45010. (#70054) Thanks @castaples.
-- Agents/Anthropic/Bedrock: preserve stripped thinking-only assistant replay turns with non-empty omitted-reasoning text so provider adapters keep strict user/assistant turn shape. Thanks @wujiaming88.
+- Plugin SDK: share diagnostic event subscriptions across duplicate source/dist
+  module graphs so legacy root SDK imports still receive runtime diagnostic events.
+- Agents/Bedrock: prevent empty assistant stream-error turns from poisoning
+  Converse replay by persisting, repairing, and replaying a non-empty fallback
+  block. Fixes #71572. (#71627) Thanks @openperf.
+- Agents/Anthropic/Bedrock: strip thinking blocks with missing, empty, or blank
+  replay signatures before provider conversion, falling back to non-empty
+  omitted-reasoning text when needed so corrupted signed-thinking history no
+  longer poisons subsequent turns. Fixes #45010. (#70054) Thanks @castaples.
+- Agents/Anthropic/Bedrock: preserve stripped thinking-only assistant replay
+  turns with non-empty omitted-reasoning text so provider adapters keep strict
+  user/assistant turn shape. Thanks @wujiaming88.
 - ACP/Codex: pass `sessions_spawn(runtime="acp")` model and thinking overrides into Codex ACP startup, normalize `openai-codex/*` refs and slash reasoning suffixes, and recognize managed Codex ACP wrapper commands without blocking current `gpt-5.5` sessions. Fixes #40393. (#71643) Thanks @91wan.
 - Browser/CDP: make readiness diagnostics use the same discovery-first fallback as reachability for bare `ws://` Browserless and Browserbase CDP URLs. Fixes #69532.
 - Browser/CDP: explain that loopback Browserless or other externally managed CDP services need `attachOnly: true` and matching Browserless `EXTERNAL` endpoint when reporting local port ownership conflicts, and fall back to the configured bare WebSocket root when a discovered Browserless endpoint rejects CDP. Fixes #49815.
@@ -179,7 +129,9 @@ Docs: https://docs.openclaw.ai
 - Plugins/model defaults: run Skill Workshop review, Active Memory recall, and session-memory slug generation on the configured agent default model instead of the hardcoded OpenAI SDK fallback when hook context lacks model metadata. Fixes #71659.
 - Providers/Venice: fill the required DeepSeek V4 `reasoning_content` placeholder for `venice/deepseek-v4-pro` and `venice/deepseek-v4-flash` replay turns without sending native DeepSeek `thinking` controls that Venice rejects. Fixes #71628.
 - Browser/existing-session: support per-profile Chrome MCP command/args, map `cdpUrl` to `--browserUrl` or `--wsEndpoint`, and avoid combining endpoint flags with `--userDataDir`. Fixes #47879, #48037, and #62706. Thanks @puneet1409, @zhehao, and @madkow1001.
-- Media/plugins: bound MIME sniffing and ZIP archive preflight before handing untrusted files to `file-type` or `jszip`, reducing parser CPU and memory exposure for attachments and ClawHub plugin archives. Thanks @vincentkoc.
+- Media/plugins: bound MIME sniffing and ZIP archive preflight before handing
+  untrusted files to `file-type` or `jszip`, reducing parser CPU and memory
+  exposure for attachments and ClawHub plugin archives. Thanks @vincentkoc.
 - Memory-host SDK: use trusted env-proxy mode for remote embedding and batch HTTP calls only when Undici will proxy that target, preserving SSRF DNS pinning for `ALL_PROXY`-only and `NO_PROXY` bypass cases. Fixes #52162. (#71506) Thanks @DhtIsCoding.
 - Gateway/dashboard: render Control UI and WebSocket links with `https://`/`wss://` when `gateway.tls.enabled=true`, including `openclaw gateway status`. Fixes #71494. (#71499) Thanks @deepkilo.
 - Agents/OpenAI-compatible: default proxy/local completions tool requests to `tool_choice: "auto"` when tools are present, so providers enter native tool-calling mode instead of replying with plain-text tool directives. (#71472) Thanks @Speed-maker.
@@ -219,12 +171,12 @@ Docs: https://docs.openclaw.ai
 - Browser/Linux: detect Chromium-based installs under `/opt/google`, `/opt/brave.com`, `/usr/lib/chromium`, and `/usr/lib/chromium-browser` before asking users to set `browser.executablePath`. (#48563) Thanks @lupuletic.
 - Sessions/browser: close tracked browser tabs when idle, daily, `/new`, or `/reset` session rollover archives the previous transcript, preventing tabs from leaking past the old session. Thanks @jakozloski.
 - Sessions/forking: fall back to transcript-estimated parent token counts when cached totals are stale or missing, so oversized thread forks start fresh instead of cloning the full parent transcript. Thanks @jalehman.
-- OpenAI/Codex: send Codex Responses system prompts through top-level `instructions` while preserving the existing native Codex payload controls.
+- OpenAI/Codex: send Codex Responses system prompts through top-level
+  `instructions` while preserving the existing native Codex payload controls.
 - MCP/CLI: retire bundled MCP runtimes at the end of one-shot `openclaw agent` and `openclaw infer model run` gateway/local executions, so repeated scripted runs do not accumulate stdio MCP child processes. Fixes #71457. Thanks @spartoviMD.
 - OpenAI/Codex image generation: canonicalize legacy `openai-codex.baseUrl` values such as `https://chatgpt.com/backend-api` to the Codex Responses backend before calling `gpt-image-2`, matching the chat transport. Fixes #71460. Thanks @GodsBoy.
 - Control UI: make `/usage` use the fresh context snapshot for context percentage, and include cache-write tokens in the Usage overview cache-hit denominator. Fixes #47885. Thanks @imwyvern and @Ante042.
 - GitHub Copilot: preserve encrypted Responses reasoning item IDs during replay so Copilot can validate encrypted reasoning payloads across requests. (#71448) Thanks @a410979729-sys.
-- GitHub Copilot: never rewrite connection-bound reasoning item IDs regardless of whether `encrypted_content` is present, fixing a 400 "Encrypted content item_id did not match" error with `gpt-5.3-codex` and future Codex models that fall through to the forward-compat catch-all with `reasoning: false`. Also recognize Codex-named models as reasoning-capable so they inherit the correct capability flags. Refs #68735. Thanks @InvalidPandaa.
 - Agents/replies: recover final-answer text when streamed assistant chunks contain only whitespace, preventing completed turns from surfacing as empty-payload errors. Fixes #71454. (#71467) Thanks @Sanjays2402.
 - Feishu/TTS: transcode voice-intent MP3 and other audio replies to Ogg/Opus before sending native Feishu audio bubbles, while keeping ordinary MP3 attachments as files. Fixes #61249 and #37868. Thanks @sg1416-zg and @ycjlb2023-peteryi.
 - WhatsApp/TTS: transcode MP3/WebM audio, including Microsoft Edge TTS output, to Ogg/Opus before sending PTT voice notes.
@@ -238,10 +190,6 @@ Docs: https://docs.openclaw.ai
 - Sessions: make `sessions_spawn(mode="session")` errors name usable alternatives when the current channel cannot bind subagent threads. Fixes #67400. (#67790) Thanks @stainlu.
 - Agents/Claude CLI: pass the OpenClaw system prompt through Claude's prompt-file flag so Windows runs avoid argv length failures without changing system prompt semantics. Fixes #69158. (#69211) Thanks @skylee-01, @cassioanorte, @Syu0, and @Stache73.
 - Agents/CLI sessions: bind `google-gemini-cli` session auth-epoch to the Google account identity in `~/.gemini/oauth_creds.json`, so Gemini-backed agents resume their conversation after gateway restart instead of minting a fresh session, and stale bindings are invalidated when the authenticated Google account changes. Fixes #70973. (#71076) Thanks @openperf.
-- Slack: stop treating user mentions in assistant-authored message edit blocks as sender attribution, preventing edited bot messages from spoofing a mentioned DM user. (#71700) Thanks @vincentkoc.
-- Codex: consume unauthorized bound conversation inbound claims before they can fall through to other claim handlers or enqueue Codex turns. (#71702) Thanks @vincentkoc.
-- Codex media understanding: require approval-checked app-server image turns while explicitly declining tool, file, permission, and elicitation approval requests for the bounded image worker. (#71703) Thanks @vincentkoc.
-- Agents/Claude CLI: allow large live `stream-json` JSONL lines up to the existing per-turn raw limit, preventing large Telegram, WebChat, MCP, and image turns from aborting on the old stdout buffer cap. Fixes #71793, #71080, and #70766. (#71897) Thanks @chacher86, @shivamgrover21, and @tpjordan.
 
 ## 2026.4.24
 
@@ -523,7 +471,6 @@ Docs: https://docs.openclaw.ai
 - Slack: route native stream fallback replies through the normal chunked sender so long buffered Slack Connect responses are not dropped or duplicated. (#71124) Thanks @martingarramon.
 - WhatsApp: transcribe accepted voice notes before agent dispatch while keeping spoken transcripts out of command authorization. (#64120) Thanks @rogerdigital.
 - Plugins/CLI: expose channel plugin CLI descriptors during discovery-mode plugin loads so snapshot registries keep channel commands visible without activating full runtimes. (#71309) Thanks @gumadeiras.
-- Matrix: separate recovery-key, backup, and owner-trust diagnostics during E2EE recovery, add recovery-key rotation for backup reset, and cover destructive backup restore paths in QA. (#71311) Thanks @gumadeiras.
 - WhatsApp: deliver media generated by tool-result replies while still suppressing text-only tool chatter. (#60968) Thanks @adaclaw.
 - Config/agents: accept `agents.list[].contextTokens` in strict config validation so per-agent overrides survive hot reload, letting `/status` reflect the configured model window instead of the 200k fallback. Fixes #70692. (#71247) Thanks @statxc.
 - Heartbeat: include async exec completion details in heartbeat prompts so command-finished notifications relay the actual output. (#71213) Thanks @GodsBoy.
@@ -659,19 +606,9 @@ Docs: https://docs.openclaw.ai
 
 ### Fixes
 
-- Dependencies: refresh workspace package pins and lockfile entries for AWS SDK,
-  Anthropic SDK, ACP SDK, Matrix crypto, TypeBox, Vite, tsdown, Slack Bolt,
-  CopilotKit AIMock, and related bundled plugin packages. Thanks @steipete.
-- Gateway/env: import each missing expected login-shell env var independently,
-  so an existing gateway token no longer prevents `env.shellEnv` from loading
-  plugin credentials such as `TWILIO_*` from `.profile`. Thanks @steipete.
-- macOS/Gateway pairing: silently accept same-host native app
-  `metadata-upgrade` reconnects, so macOS patch-version changes update paired
-  metadata instead of spamming security audit warnings and `pairing required`
-  disconnects. Thanks @steipete.
 - CLI/Gateway: wait for one-shot gateway RPC clients to finish WebSocket teardown before the CLI process exits, reducing hangs where commands like `openclaw status` or `openclaw version` could finish their work but stay alive until an external timeout killed them (#70691). Thanks @Takhoffman.
 - Thinking defaults/status: raise the implicit default thinking level for reasoning-capable models from legacy `off`/`low` fallback behavior to a safe provider-supported `medium` equivalent when no explicit config default is set, preserve configured-model reasoning metadata when runtime catalog loading is empty, and make `/status` report the same resolved default as runtime (#70601). Thanks @Takhoffman.
-- Gateway/model pricing: extend OpenRouter and LiteLLM catalog fetch timeouts to 60 seconds, reducing noisy timeout warnings during slow upstream responses. Thanks @steipete.
+- Gateway/model pricing: fetch OpenRouter and LiteLLM pricing asynchronously at startup and extend catalog fetch timeouts to 30 seconds, reducing noisy timeout warnings during slow upstream responses.
 - Agents/failover: classify bare undici transport failures (`terminated`, `UND_ERR_SOCKET`, `UND_ERR_CONNECT_TIMEOUT`, body/header timeouts, aborted streams) and pi-ai's openai-codex `Request failed` sentinel as `timeout`, so Cloudflare 502s with empty bodies and mid-response socket resets actually enter the configured fallback chain instead of surfacing as unclassified errors. Fixes #69368. (#69677) Thanks @sk7n4k3d.
 - Providers/Anthropic Vertex: restore ADC-backed model discovery after the lightweight provider-discovery path by resolving emitted discovery entries, exposing synthetic auth on bootstrap discovery, and honoring copied env snapshots when probing the default GCP ADC path. Fixes #65715. (#65716) Thanks @feiskyer.
 - Plugins/install: add newly installed plugin ids to an existing `plugins.allow` list before enabling them, so allowlisted configs load installed plugins after restart.

appcast.xml

@@ -2,54 +2,6 @@
 <rss xmlns:sparkle="http://www.andymatuschak.org/xml-namespaces/sparkle" version="2.0">
     <channel>
         <title>OpenClaw</title>
-        <item>
-            <title>2026.4.24</title>
-            <pubDate>Sat, 25 Apr 2026 19:34:45 +0000</pubDate>
-            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
-            <sparkle:version>2026042490</sparkle:version>
-            <sparkle:shortVersionString>2026.4.24</sparkle:shortVersionString>
-            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
-            <description><![CDATA[<h2>OpenClaw 2026.4.24</h2>
-<h3>Highlights</h3>
-<ul>
-<li>Google Meet joins OpenClaw as a bundled participant plugin, with personal Google auth, Chrome/Twilio realtime sessions, paired-node Chrome support, artifact/attendance exports, and recovery tooling for already-open Meet tabs.</li>
-<li>DeepSeek V4 Flash and V4 Pro are in the bundled catalog, V4 Flash is the onboarding default, and DeepSeek thinking/replay behavior is fixed for follow-up tool-call turns.</li>
-<li>Talk, Voice Call, and Google Meet can use realtime voice loops that consult the full OpenClaw agent for deeper tool-backed answers.</li>
-<li>Browser automation gets coordinate clicks, longer default action budgets, per-profile headless overrides, and steadier tab reuse/recovery.</li>
-<li>Plugin and model infrastructure is lighter at startup: static model catalogs, manifest-backed model rows, lazy provider dependencies, and external runtime-dependency repair for packaged installs.</li>
-</ul>
-<h3>Fixes</h3>
-<ul>
-<li>Packaged installs: preserve package-root runtime dependencies and their exported subpaths when bundled plugin runtime mirrors fall back to copying shared chunks, fixing Windows npm updates that could fail to load copied <code>dist</code> modules.</li>
-<li>Heartbeat: clamp oversized scheduler delays through the shared safe timer helper, preventing <code>every</code> values over Node's timeout cap from becoming a 1 ms crash loop. Fixes #71414. (#71478) Thanks @hclsys.</li>
-<li>Telegram: remove the startup persisted-offset <code>getUpdates</code> preflight so polling restarts do not self-conflict before the runner starts. Fixes #69304. (#69779) Thanks @chinar-amrutkar.</li>
-<li>Browser/Playwright: ignore benign already-handled route races during guarded navigation so browser-page tasks no longer fail when Playwright tears down a route mid-flight. (#68708) Thanks @Steady-ai.</li>
-<li>Browser/aria snapshots: bind <code>format=aria</code> <code>axN</code> refs to live DOM nodes through backend DOM ids when Playwright is available, so follow-up browser actions can use those refs without timing out. (#62434) Thanks @MrKipler.</li>
-<li>Telegram: prevent duplicate in-process long pollers for the same bot token and add clearer <code>getUpdates</code> conflict diagnostics for external duplicate pollers. Fixes #56230.</li>
-<li>Browser/Linux: detect Chromium-based installs under <code>/opt/google</code>, <code>/opt/brave.com</code>, <code>/usr/lib/chromium</code>, and <code>/usr/lib/chromium-browser</code> before asking users to set <code>browser.executablePath</code>. (#48563) Thanks @lupuletic.</li>
-<li>Sessions/browser: close tracked browser tabs when idle, daily, <code>/new</code>, or <code>/reset</code> session rollover archives the previous transcript, preventing tabs from leaking past the old session. Thanks @jakozloski.</li>
-<li>Sessions/forking: fall back to transcript-estimated parent token counts when cached totals are stale or missing, so oversized thread forks start fresh instead of cloning the full parent transcript. Thanks @jalehman.</li>
-<li>OpenAI/Codex: send Codex Responses system prompts through top-level</li>
-</ul>
-  <code>instructions</code> while preserving the existing native Codex payload controls.
-<ul>
-<li>MCP/CLI: retire bundled MCP runtimes at the end of one-shot <code>openclaw agent</code> and <code>openclaw infer model run</code> gateway/local executions, so repeated scripted runs do not accumulate stdio MCP child processes. Fixes #71457.</li>
-<li>OpenAI/Codex image generation: canonicalize legacy <code>openai-codex.baseUrl</code> values such as <code>https://chatgpt.com/backend-api</code> to the Codex Responses backend before calling <code>gpt-image-2</code>, matching the chat transport. Fixes #71460.</li>
-<li>Control UI: make <code>/usage</code> use the fresh context snapshot for context percentage, and include cache-write tokens in the Usage overview cache-hit denominator. Fixes #47885. Thanks @imwyvern and @Ante042.</li>
-<li>GitHub Copilot: preserve encrypted Responses reasoning item IDs during replay so Copilot can validate encrypted reasoning payloads across requests. (#71448) Thanks @a410979729-sys.</li>
-<li>Agents/replies: recover final-answer text when streamed assistant chunks contain only whitespace, preventing completed turns from surfacing as empty-payload errors. Fixes #71454. (#71467) Thanks @Sanjays2402.</li>
-<li>Feishu/TTS: transcode voice-intent MP3 and other audio replies to Ogg/Opus before sending native Feishu audio bubbles, while keeping ordinary MP3 attachments as files. Fixes #61249 and #37868.</li>
-<li>Telegram/webhook: acknowledge validated webhook updates before running bot middleware, keeping slow agent turns from tripping Telegram delivery retries while preserving per-chat processing lanes. Fixes #71392. Thanks @joelforsberg46-source.</li>
-<li>MCP: retire one-shot embedded bundled MCP runtimes at run end, skip bundle-MCP startup when a runtime tool allowlist cannot reach bundle-MCP tools, and add <code>mcp.sessionIdleTtlMs</code> idle eviction for leaked session runtimes. Fixes #71106, #71110, #70389, and #70808.</li>
-<li>MCP/config reload: hot-apply <code>mcp.*</code> changes by disposing cached session MCP runtimes, and dispose bundled MCP runtimes during gateway shutdown so removed <code>mcp.servers</code> entries reap child processes promptly. Fixes #60656.</li>
-<li>Gateway/restart continuation: durably hand restart continuations to a session-delivery queue before deleting the restart sentinel, recover queued continuation work after crashy restarts, and fall back to a session-only wake when no channel route survives reboot. (#70780) Thanks @fuller-stack-dev.</li>
-<li>Agents/tool-result pruning: harden the tool-result character estimator and context-pruning loops against malformed <code>{ type: "text" }</code> blocks created by void or undefined tool handler results, serializing non-string text payloads for size accounting so they cannot bypass trimming as zero-sized. Fixes #34979. (#51267) Thanks @cgdusek, @alvinttang, and @coffeexcoin.</li>
-<li>Daemon/service-env: add Nix Home Manager profile bin directories to generated gateway service PATHs on macOS and Linux, honoring <code>NIX_PROFILES</code> right-to-left precedence and falling back to <code>~/.nix-profile/bin</code> when unset. Fixes #44402. (#59935) Thanks @jerome-benoit.</li>
-</ul>
-<p><a href="https://github.com/openclaw/openclaw/blob/main/CHANGELOG.md">View full changelog</a></p>
-]]></description>
-            <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.4.24/OpenClaw-2026.4.24.zip" length="48033180" type="application/octet-stream" sparkle:edSignature="wxOfxadSZ/9iXMitaC6SA9J6YPZC3P2tkeK7HZPHzjUIlzQTvOl7EjR4aRyXzaYt1N1AK5ba+YhuCwEngrTdCQ=="/>
-        </item>
         <item>
             <title>2026.4.22</title>
             <pubDate>Thu, 23 Apr 2026 15:18:00 +0000</pubDate>
@@ -363,5 +315,121 @@
 ]]></description>
             <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.4.20/OpenClaw-2026.4.20.zip" length="47535600" type="application/octet-stream" sparkle:edSignature="D7XcNGxmc10IIayYY91RZBoascFSnXyd4dg6cSpC3+PTIwVrWYs/FwSBc/1J+1P53LlnTHKDGQYMkWVNMnRSAQ=="/>
         </item>
+        <item>
+            <title>2026.4.15</title>
+            <pubDate>Thu, 16 Apr 2026 23:33:29 +0000</pubDate>
+            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
+            <sparkle:version>2026041590</sparkle:version>
+            <sparkle:shortVersionString>2026.4.15</sparkle:shortVersionString>
+            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
+            <description><![CDATA[<h2>OpenClaw 2026.4.15</h2>
+<h3>Changes</h3>
+<ul>
+<li>Anthropic/models: default Anthropic selections, <code>opus</code> aliases, Claude CLI defaults, and bundled image understanding to Claude Opus 4.7.</li>
+<li>Google/TTS: add Gemini text-to-speech support to the bundled <code>google</code> plugin, including provider registration, voice selection, WAV reply output, PCM telephony output, and setup/docs guidance. (#67515) Thanks @barronlroth.</li>
+<li>Control UI/Overview: add a Model Auth status card showing OAuth token health and provider rate-limit pressure at a glance, with attention callouts when OAuth tokens are expiring or expired. Backed by a new <code>models.authStatus</code> gateway method that strips credentials and caches for 60s. (#66211) Thanks @omarshahine.</li>
+<li>Memory/LanceDB: add cloud storage support to <code>memory-lancedb</code> so durable memory indexes can run on remote object storage instead of local disk only. (#63502) Thanks @rugvedS07.</li>
+<li>GitHub Copilot/memory search: add a GitHub Copilot embedding provider for memory search, and expose a dedicated Copilot embedding host helper so plugins can reuse the transport while honoring remote overrides, token refresh, and safer payload validation. (#61718) Thanks @feiskyer and @vincentkoc.</li>
+<li>Agents/local models: add experimental <code>agents.defaults.experimental.localModelLean: true</code> to drop heavyweight default tools like <code>browser</code>, <code>cron</code>, and <code>message</code>, reducing prompt size for weaker local-model setups without changing the normal path. (#66495) Thanks @ImLukeF.</li>
+<li>Packaging/plugins: localize bundled plugin runtime deps to their owning extensions, trim the published docs payload, and tighten install/package-manager guardrails so published builds stay leaner and core stops carrying extension-owned runtime baggage. (#67099) Thanks @vincentkoc.</li>
+<li>QA/Matrix: split Matrix live QA into a source-linked <code>qa-matrix</code> runner and keep repo-private <code>qa-*</code> surfaces out of packaged and published builds. (#66723) Thanks @gumadeiras.</li>
+<li>Docs/showcase: add a scannable hero, complete section jump links, and a responsive video grid for community examples. (#48493) Thanks @jchopard69.</li>
+</ul>
+<h3>Fixes</h3>
+<ul>
+<li>Gateway/tools: anchor trusted local <code>MEDIA:</code> tool-result passthrough on the exact raw name of this run's registered built-in tools, and reject client tool definitions whose names normalize-collide with a built-in or with another client tool in the same request (<code>400 invalid_request_error</code> on both JSON and SSE paths), so a client-supplied tool named like a built-in can no longer inherit its local-media trust. (#67303)</li>
+<li>Agents/replay recovery: classify the provider wording <code>401 input item ID does not belong to this connection</code> as replay-invalid, so users get the existing <code>/new</code> session reset guidance instead of a raw 401-style failure. (#66475) Thanks @dallylee.</li>
+<li>Gateway/webchat: enforce localRoots containment on webchat audio embedding path [AI-assisted]. (#67298) Thanks @pgondhi987.</li>
+<li>Matrix/pairing: block DM pairing-store entries from authorizing room control commands [AI-assisted]. (#67294) Thanks @pgondhi987.</li>
+<li>Docker/build: verify <code>@matrix-org/matrix-sdk-crypto-nodejs</code> native bindings with <code>find</code> under <code>node_modules</code> instead of a hardcoded <code>.pnpm/...</code> path so pnpm v10+ virtual-store layouts no longer fail the image build. (#67143) thanks @ly85206559.</li>
+<li>Matrix/E2EE: keep startup bootstrap conservative for passwordless token-auth bots, still attempt the guarded repair pass without requiring <code>channels.matrix.password</code>, and document the remaining password-UIA limitation. (#66228) Thanks @SARAMALI15792.</li>
+<li>Cron/announce delivery: suppress mixed-content isolated cron announce replies that end with <code>NO_REPLY</code> so trailing silent sentinels no longer leak summary text to the target channel. (#65004) thanks @neo1027144-creator.</li>
+<li>Plugins/bundled channels: partition bundled channel lazy caches by active bundled root so <code>OPENCLAW_BUNDLED_PLUGINS_DIR</code> flips stop reusing stale plugin, setup, secrets, and runtime state. (#67200) Thanks @gumadeiras.</li>
+<li>Packaging/plugins: prune common test/spec cargo from bundled plugin runtime dependencies and fail npm release validation if packaged test cargo reappears, keeping published tarballs leaner without plugin-specific special cases. (#67275) thanks @gumadeiras.</li>
+<li>Agents/context + Memory: trim default startup/skills prompt budgets, cap <code>memory_get</code> excerpts by default with explicit continuation metadata, and keep QMD reads aligned with the same bounded excerpt contract so long sessions pull less context by default without losing deterministic follow-up reads.</li>
+<li>Matrix/commands: skip DM pairing-store reads on room traffic now that room control-command authorization ignores pairing-store entries, keeping the room path narrower without changing room auth behavior. (#67325) Thanks @gumadeiras.</li>
+<li>Memory-core/dreaming: skip dreaming narrative transcripts from session-store metadata before bootstrap records land so dream diary prompt/prose lines do not pollute session ingestion. (#67315) thanks @jalehman.</li>
+<li>Agents/local models: clarify low-context preflight hints for self-hosted models, point config-backed caps at the relevant OpenClaw setting, and stop suggesting larger models when <code>agents.defaults.contextTokens</code> is the real limit. (#66236) Thanks @ImLukeF.</li>
+<li>Dreaming/memory-core: change the default <code>dreaming.storage.mode</code> from <code>inline</code> to <code>separate</code> so Dreaming phase blocks (<code>## Light Sleep</code>, <code>## REM Sleep</code>) land in <code>memory/dreaming/{phase}/YYYY-MM-DD.md</code> instead of being injected into <code>memory/YYYY-MM-DD.md</code>. Daily memory files no longer get dominated by structured candidate output, and the daily-ingestion scanner that already strips dream marker blocks no longer has to compete with hundreds of phase-block lines on every run. Operators who want the previous behavior can opt in by setting <code>plugins.entries.memory-core.config.dreaming.storage.mode: "inline"</code>. (#66412) Thanks @mjamiv.</li>
+<li>Control UI/Overview: fix false-positive "missing" alerts on the Model Auth status card for aliased providers, env-backed OAuth with auth.profiles, and unresolvable env SecretRefs. (#67253) Thanks @omarshahine.</li>
+<li>Dashboard: constrain exec approval modal overflow on desktop so long command content no longer pushes action buttons out of view. (#67082) Thanks @Ziy1-Tan.</li>
+<li>Agents/CLI transcripts: persist successful CLI-backed turns into the OpenClaw session transcript so google-gemini-cli replies appear in session history and the Control UI again. (#67490) Thanks @obviyus.</li>
+<li>Discord/tool-call text: strip standalone Gemma-style <code><function>...</function></code> tool-call payloads from visible assistant text without truncating prose examples or trailing replies. (#67318) Thanks @joelnishanth.</li>
+<li>WhatsApp/web-session: drain the pending per-auth creds save queue before reopening sockets so reconnect-time auth bootstrap no longer races in-flight <code>creds.json</code> writes and falsely restores from backup. (#67464) Thanks @neeravmakwana.</li>
+<li>BlueBubbles/catchup: add a per-message retry ceiling (<code>catchup.maxFailureRetries</code>, default 10) so a persistently-failing message with a malformed payload no longer wedges the catchup cursor forever. After N consecutive <code>processMessage</code> failures against the same GUID, catchup logs a WARN, skips that message on subsequent sweeps, and lets the cursor advance past it. Transient failures still retry from the same point as before. Also fixes a lost-update race in the persistent dedupe file lock that silently dropped inbound GUIDs on concurrent writes, a dedupe file naming migration gap on version upgrade, and a balloon-event bypass that let catchup replay debouncer-coalesced events as standalone messages. (#67426, #66870) Thanks @omarshahine.</li>
+<li>Ollama/chat: strip the <code>ollama/</code> provider prefix from Ollama chat request model ids so configured refs like <code>ollama/qwen3:14b-q8_0</code> stop 404ing against the Ollama API. (#67457) Thanks @suboss87.</li>
+<li>Agents/tools: resolve non-workspace host tilde paths against the OS home directory and keep edit recovery aligned with that same path target, so <code>~/...</code> host edit/write operations stop failing or reading back the wrong file when <code>OPENCLAW_HOME</code> differs. (#62804) Thanks @stainlu.</li>
+<li>Speech/TTS: auto-enable the bundled Microsoft and ElevenLabs speech providers, and route generic TTS directive tokens through the explicit or active provider first so overrides like <code>[[tts:speed=1.2]]</code> stop silently landing on the wrong provider. (#62846) Thanks @stainlu.</li>
+<li>OpenAI Codex/models: normalize stale native transport metadata in both runtime resolution and discovery/listing so legacy <code>openai-codex</code> rows with missing <code>api</code> or <code>https://chatgpt.com/backend-api/v1</code> self-heal to the canonical Codex transport instead of routing requests through broken HTML/Cloudflare paths, combining the original fixes proposed in #66969 (saamuelng601-pixel) and #67159 (hclsys). (#67635)</li>
+<li>Agents/failover: treat HTML provider error pages as upstream transport failures for CDN-style 5xx responses without misclassifying embedded body text as API rate limits, while still preserving auth remediation for HTML 401/403 pages and proxy remediation for HTML 407 pages. (#67642) Thanks @stainlu.</li>
+<li>Gateway/skills: bump the cached skills-snapshot version whenever a config write touches <code>skills.*</code> (for example <code>skills.allowBundled</code>, <code>skills.entries.<id>.enabled</code>, or <code>skills.profile</code>). Existing agent sessions persist a <code>skillsSnapshot</code> in <code>sessions.json</code> that reuses the skill list frozen at session creation; without this invalidation, removing a bundled skill from the allowlist left the old snapshot live and the model kept calling the disabled tool, producing <code>Tool <name> not found</code> loops that ran until the embedded-run timeout. (#67401) Thanks @xantorres.</li>
+<li>Agents/tool-loop: enable the unknown-tool stream guard by default. Previously <code>resolveUnknownToolGuardThreshold</code> returned <code>undefined</code> unless <code>tools.loopDetection.enabled</code> was explicitly set to <code>true</code>, which left the protection off in the default configuration. A hallucinated or removed tool (for example <code>himalaya</code> after it was dropped from <code>skills.allowBundled</code>) would then loop "Tool X not found" attempts until the full embedded-run timeout. The guard has no false-positive surface because it only triggers on tools that are objectively not registered in the run, so it now stays on regardless of <code>tools.loopDetection.enabled</code> and still accepts <code>tools.loopDetection.unknownToolThreshold</code> as a per-run override (default 10). (#67401) Thanks @xantorres.</li>
+<li>TUI/streaming: add a client-side streaming watchdog to <code>tui-event-handlers</code> so the <code>streaming · Xm Ys</code> activity indicator resets to <code>idle</code> after 30s of delta silence on the active run. Guards against lost or late <code>state: "final"</code> chat events (WS reconnects, gateway restarts, etc.) leaving the TUI stuck on <code>streaming</code> indefinitely; a new system log line surfaces the reset so users know to send a new message to resync. The window is configurable via the new <code>streamingWatchdogMs</code> context option (set to <code>0</code> to disable), and the handler now exposes a <code>dispose()</code> that clears the pending timer on shutdown. (#67401) Thanks @xantorres.</li>
+<li>Extensions/lmstudio: add exponential backoff to the inference-preload wrapper so an LM Studio model-load failure (for example the built-in memory guardrail rejecting a load because the swap is saturated) no longer produces a WARN line every ~2s for every chat request. The wrapper now records consecutive preload failures per <code>(baseUrl, modelKey, contextLength)</code> tuple with a 5s → 10s → 20s → … → 5min cooldown and skips the preload step entirely while a cooldown is active, letting chat requests proceed directly to the stream (the model is often already loaded via the LM Studio UI). The combined <code>preload failed</code> log line now reports consecutive-failure count and remaining cooldown so operators can act on the real issue instead of drowning in repeated warnings. (#67401) Thanks @xantorres.</li>
+<li>Agents/replay: re-run tool/result pairing after strict replay tool-call ID sanitization on outbound requests so Anthropic-compatible providers like MiniMax no longer receive malformed orphan tool-result IDs such as <code>...toolresult1</code> during compaction and retry flows. (#67620) Thanks @stainlu.</li>
+<li>Gateway/startup: fix spurious SIGUSR1 restart loop on Linux/systemd when plugin auto-enable is the only startup config write; the config hash guard was not captured for that write path, causing chokidar to treat each boot write as an external change and trigger a reload → restart cycle that corrupts manifest.db after repeated cycles. Fixes #67436. (#67557) thanks @openperf</li>
+<li>Codex/harness: auto-enable the Codex plugin when <code>codex</code> is selected as an embedded agent harness runtime, including forced default, per-agent, and <code>OPENCLAW_AGENT_RUNTIME</code> paths. (#67474) Thanks @duqaXxX.</li>
+<li>OpenAI Codex/CLI: keep resumed <code>codex exec resume</code> runs on the safe non-interactive path without reintroducing the removed dangerous bypass flag by passing the supported <code>--skip-git-repo-check</code> resume arg plus Codex's native <code>sandbox_mode="workspace-write"</code> config override. (#67666) Thanks @plgonzalezrx8.</li>
+<li>Codex/app-server: parse Desktop-originated app-server user agents such as <code>Codex Desktop/0.118.0</code>, keeping the version gate working when the Codex CLI inherits a multi-word originator. (#64666) Thanks @cyrusaf.</li>
+<li>Cron/announce delivery: keep isolated announce <code>NO_REPLY</code> stripping case-insensitive across direct and text delivery, preserve structured media-only sends when a caption strips silent, and derive main-session awareness from the cleaned payloads so silent captions no longer leak stale <code>NO_REPLY</code> text. (#65016) Thanks @BKF-Gitty.</li>
+<li>Sessions/Codex: skip redundant <code>delivery-mirror</code> transcript appends only when the latest assistant message has the same visible text, preventing duplicate visible replies on Codex-backed turns without suppressing repeated answers across turns. (#67185) Thanks @andyylin.</li>
+<li>Auto-reply/prompt-cache: keep volatile inbound chat IDs out of the stable system prompt so task-scoped adapters can reuse prompt caches across runs, while preserving conversation metadata for the user turn and media-only messages. (#65071) Thanks @MonkeyLeeT.</li>
+<li>BlueBubbles/inbound: restore inbound image attachment downloads on Node 22+ by stripping incompatible bundled-undici dispatchers from the non-SSRF fetch path, accept <code>updated-message</code> webhooks carrying attachments, use event-type-aware dedup keys so attachment follow-ups are not rejected as duplicates, and retry attachment fetch from the BB API when the initial webhook arrives with an empty array. (#64105, #61861, #65430, #67510) Thanks @omarshahine.</li>
+<li>Agents/skills: sort prompt-facing <code>available_skills</code> entries by skill name after merging sources so <code>skills.load.extraDirs</code> order no longer changes prompt-cache prefixes. (#64198) Thanks @Bartok9.</li>
+<li>Agents/OpenAI Responses: add <code>models.providers.*.models.*.compat.supportsPromptCacheKey</code> so OpenAI-compatible proxies that forward <code>prompt_cache_key</code> can keep prompt caching enabled while incompatible endpoints can still force stripping. (#67427) Thanks @damselem.</li>
+<li>Agents/context engines: keep loop-hook and final <code>afterTurn</code> prompt-cache touch metadata aligned with the current assistant turn so cache-aware context engines retain accurate cache TTL state during tool loops. (#67767) thanks @jalehman.</li>
+<li>Memory/dreaming: strip AI-facing inbound metadata envelopes from session-corpus user turns before normalization so REM topic extraction sees the user's actual message text, including array-shaped split envelopes. (#66548) Thanks @zqchris.</li>
+<li>Agents/errors: detect standalone Cloudflare/CDN HTML challenge pages before transport DNS classification so provider block pages no longer appear as local DNS lookup failures. (#67704) Thanks @chris-yyau.</li>
+<li>Security/approvals: redact secrets in exec approval prompts so inline approval review can no longer leak credential material in rendered prompt content. (#61077, #64790)</li>
+<li>CLI/configure: re-read the persisted config hash after writes so config updates stop failing with stale-hash races. (#64188, #66528)</li>
+<li>CLI/update: prune stale packaged <code>dist</code> chunks after npm upgrades and keep downgrade/verify inventory checks compat-safe so global upgrades stop failing on stale chunk imports. (#66959) Thanks @obviyus.</li>
+<li>Onboarding/CLI: fix channel-selection crashes on globally installed CLI setups during onboarding. (#66736)</li>
+<li>Video generation/live tests: bound provider polling for live video smoke, default to the fast non-FAL text-to-video path, and use a one-second lobster prompt so release validation no longer waits indefinitely on slow provider queues.</li>
+<li>Memory-core/QMD <code>memory_get</code>: reject reads of arbitrary workspace markdown paths and only allow canonical memory files (<code>MEMORY.md</code>, <code>memory.md</code>, <code>DREAMS.md</code>, <code>dreams.md</code>, <code>memory/**</code>) plus exact paths of active indexed QMD workspace documents, so the QMD memory backend can no longer be used as a generic workspace-file read shim that bypasses <code>read</code> tool-policy denials. (#66026) Thanks @eleqtrizit.</li>
+<li>Cron/agents: forward embedded-run tool policy and internal event params into the attempt layer so <code>--tools</code> allowlists, cron-owned message-tool suppression, explicit message targeting, and command-path internal events all take effect at runtime again. (#62675) Thanks @hexsprite.</li>
+<li>Setup/providers: guard preferred-provider lookup during setup so malformed plugin metadata with a missing provider id no longer crashes the wizard with <code>Cannot read properties of undefined (reading 'trim')</code>. (#66649) Thanks @Tianworld.</li>
+<li>Matrix/security: normalize sandboxed profile avatar params, preserve <code>mxc://</code> avatar URLs, and surface gmail watcher stop failures during reload. (#64701) Thanks @slepybear.</li>
+<li>Telegram/documents: drop leaked binary caption bytes from inbound Telegram text handling so document uploads like <code>.mobi</code> or <code>.epub</code> no longer explode prompt token counts. (#66663) Thanks @joelnishanth.</li>
+<li>Gateway/auth: resolve the active gateway bearer per-request on the HTTP server and the HTTP upgrade handler via <code>getResolvedAuth()</code>, mirroring the WebSocket path, so a secret rotated through <code>secrets.reload</code> or config hot-reload stops authenticating on <code>/v1/*</code>, <code>/tools/invoke</code>, plugin HTTP routes, and the canvas upgrade path immediately instead of remaining valid on HTTP until gateway restart. (#66651) Thanks @mmaps.</li>
+<li>Agents/compaction: cap the compaction reserve-token floor to the model context window so small-context local models (e.g. Ollama with 16K tokens) no longer trigger context-overflow errors or infinite compaction loops on every prompt. (#65671) Thanks @openperf.</li>
+<li>Agents/OpenAI Responses: classify the exact <code>Unknown error (no error details in response)</code> transport failure as failover reason <code>unknown</code> so assistant/model fallback still runs for that no-details failure path. (#65254) Thanks @OpenCodeEngineer.</li>
+<li>Models/probe: surface invalid-model probe failures as <code>format</code> instead of <code>unknown</code> in <code>models list --probe</code>, and lock the invalid-model fallback path in with regression coverage. (#50028) Thanks @xiwuqi.</li>
+<li>Agents/failover: classify OpenAI-compatible <code>finish_reason: network_error</code> stream failures as timeout so model fallback retries continue instead of stopping with an unknown failover reason. (#61784) thanks @lawrence3699.</li>
+<li>Onboarding/channels: normalize channel setup metadata before discovery and validation so malformed or mixed-shape channel plugin metadata no longer breaks setup and onboarding channel lists. (#66706) Thanks @darkamenosa.</li>
+<li>Slack/native commands: fix option menus for slash commands such as <code>/verbose</code> when Slack renders native buttons by giving each button a unique action ID while still routing them through the shared <code>openclaw_cmdarg*</code> listener. Thanks @Wangmerlyn.</li>
+<li>Feishu/webhook: harden the webhook transport and card-action replay guards to fail closed on missing <code>encryptKey</code> and blank callback tokens — refuse to start the webhook transport without an <code>encryptKey</code>, reject unsigned requests when no key is present instead of accepting them, and drop blank card-action tokens before the dedupe claim and dispatcher. Defense-in-depth over the already-closed monitor-account layer. (#66707) Thanks @eleqtrizit.</li>
+<li>Agents/workspace files: route <code>agents.files.get</code>, <code>agents.files.set</code>, and workspace listing through the shared <code>fs-safe</code> helpers (<code>openFileWithinRoot</code>/<code>readFileWithinRoot</code>/<code>writeFileWithinRoot</code>), reject symlink aliases for allowlisted agent files, and have <code>fs-safe</code> resolve opened-file real paths from the file descriptor before falling back to path-based <code>realpath</code> so a symlink swap between <code>open</code> and <code>realpath</code> can no longer redirect the validated path off the intended inode. (#66636) Thanks @eleqtrizit.</li>
+<li>Gateway/MCP loopback: switch the <code>/mcp</code> bearer comparison from plain <code>!==</code> to constant-time <code>safeEqualSecret</code> (matching the convention every other auth surface in the codebase uses), and reject non-loopback browser-origin requests via <code>checkBrowserOrigin</code> before the auth gate runs. Loopback origins (<code>127.0.0.1:*</code>, <code>localhost:*</code>, same-origin) still go through, including the <code>localhost</code>↔<code>127.0.0.1</code> host mismatch that browsers flag as <code>Sec-Fetch-Site: cross-site</code>. (#66665) Thanks @eleqtrizit.</li>
+<li>Auto-reply/billing: classify pure billing cooldown fallback summaries from structured fallback reasons so users see billing guidance instead of the generic failure reply. (#66363) Thanks @Rohan5commit.</li>
+<li>Agents/fallback: preserve the original prompt body on model fallback retries with session history so the retrying model keeps the active task instead of only seeing a generic continue message. (#66029) Thanks @WuKongAI-CMU.</li>
+<li>Reply/secrets: resolve active reply channel/account SecretRefs before reply-run message-action discovery so channel token SecretRefs (for example Discord) do not degrade into discovery-time unresolved-secret failures. (#66796) Thanks @joshavant.</li>
+<li>Agents/Anthropic: ignore non-positive Anthropic Messages token overrides and fail locally when no positive token budget remains, so invalid <code>max_tokens</code> values no longer reach the provider API. (#66664) thanks @jalehman</li>
+<li>Agents/context engines: preserve prompt-only token counts, not full request totals, when deferred maintenance reuses after-turn runtime context so background compaction bookkeeping matches the active prompt window. (#66820) thanks @jalehman.</li>
+<li>BlueBubbles/inbound: add a persistent file-backed GUID dedupe so MessagePoller webhook replays after BB Server restart or reconnect no longer cause the agent to re-reply to already-handled messages. (#19176, #12053, #66816) Thanks @omarshahine.</li>
+<li>Secrets/plugins/status: align SecretRef inspect-vs-strict handling across plugin preload, read-only status/agents surfaces, and runtime auth paths so unresolved refs no longer crash read-only CLI flows while runtime-required non-env refs stay strict. (#66818) Thanks @joshavant.</li>
+<li>Memory/dreaming: stop ordinary transcripts that merely quote the dream-diary prompt from being classified as internal dreaming runs and silently dropped from session recall ingestion. (#66852) Thanks @gumadeiras.</li>
+<li>Telegram/documents: sanitize binary reply context and ZIP-like archive extraction so <code>.epub</code> and <code>.mobi</code> uploads can no longer leak raw binary into prompt context through reply metadata or archive-to-<code>text/plain</code> coercion. (#66877) Thanks @martinfrancois.</li>
+<li>Telegram/native commands: restore plugin-registry-backed auto defaults for native commands and native skills so Telegram slash commands keep registering when <code>commands.native</code> and <code>commands.nativeSkills</code> stay on <code>auto</code>. (#66843) Thanks @kashevk0.</li>
+<li>OpenRouter/Qwen3: parse <code>reasoning_details</code> stream deltas as thinking content without skipping same-chunk tool calls, so Qwen3 replies no longer fail empty on OpenRouter and mixed reasoning/tool-call chunks still execute normally. (#66905) Thanks @bladin.</li>
+<li>BlueBubbles/catchup: replay missed webhook messages after gateway restart via a persistent per-account cursor and <code>/api/v1/message/query?after=<ts></code> pass, so messages delivered while the gateway was down no longer disappear. Uses the existing <code>processMessage</code> path and is deduped by #66816's inbound GUID cache. (#66857, #66721) Thanks @omarshahine.</li>
+<li>Telegram/native commands: keep Telegram command-sync cache process-local so gateway restarts re-register the menu instead of trusting stale on-disk sync state after Telegram cleared commands out-of-band. (#66730) Thanks @nightq.</li>
+<li>Audio/self-hosted STT: restore <code>models.providers.*.request.allowPrivateNetwork</code> for audio transcription so private or LAN speech-to-text endpoints stop tripping SSRF blocks after the v2026.4.14 regression. (#66692) Thanks @jhsmith409.</li>
+<li>Auto-reply/media: allow workspace-rooted absolute media paths in auto-reply send flows so valid local media references no longer fail path validation. (#66689)</li>
+<li>WhatsApp/Baileys media upload: harden encrypted upload handling so large outbound media sends avoid buffer spikes and reliability regressions. (#65966) Thanks @frankekn.</li>
+<li>QQBot/cron: guard against undefined <code>event.content</code> in <code>parseFaceTags</code> and <code>filterInternalMarkers</code> so cron-triggered agent turns with no content payload no longer crash with <code>TypeError: Cannot read properties of undefined (reading 'startsWith')</code>. (#66302) Thanks @xinmotlanthua.</li>
+<li>CLI/plugins: stop <code>--dangerously-force-unsafe-install</code> plugin installs from falling back to hook-pack installs after security scan failures, while still preserving non-security fallback behavior for real hook packs. (#58909) Thanks @hxy91819.</li>
+<li>Claude CLI/sessions: classify <code>No conversation found with session ID</code> as <code>session_expired</code> so expired CLI-backed conversations clear the stale binding and recover on the next turn. (#65028) thanks @Ivan-Fn.</li>
+<li>Context Engine: gracefully fall back to the legacy engine when a third-party context engine plugin fails at resolution time (unregistered id, factory throw, or contract violation), preventing a full gateway outage on every channel. (#66930) Thanks @openperf.</li>
+<li>Control UI/chat: keep optimistic user message cards visible during active sends by deferring same-session history reloads until the active run ends, including aborted and errored runs. (#66997) Thanks @scotthuang and @vincentkoc.</li>
+<li>Media/Slack: allow host-local CSV and Markdown uploads only when the fallback buffer actually decodes as text, so real plain-text files work without letting opaque non-text blobs renamed to <code>.csv</code> or <code>.md</code> slip past the host-read guard. (#67047) Thanks @Unayung.</li>
+<li>Ollama/onboarding: split setup into <code>Cloud + Local</code>, <code>Cloud only</code>, and <code>Local only</code>, support direct <code>OLLAMA_API_KEY</code> cloud setup without a local daemon, and keep Ollama web search on the local-host path. (#67005) Thanks @obviyus.</li>
+<li>Webchat/security: reject remote-host <code>file://</code> URLs in the media embedding path. (#67293) Thanks @pgondhi987.</li>
+<li>Dreaming/memory-core: use the ingestion day, not the source file day, for daily recall dedupe so repeat sweeps of the same daily note can increment <code>dailyCount</code> across days instead of stalling at <code>1</code>. (#67091) Thanks @Bartok9.</li>
+<li>Node-host/tools.exec: let approval binding distinguish known native binaries from mutable shell payload files, while still fail-closing unknown or racy file probes so absolute-path node-host commands like <code>/usr/bin/whoami</code> no longer get rejected as unsafe interpreter/runtime commands. (#66731) Thanks @tmimmanuel.</li>
+</ul>
+<p><a href="https://github.com/openclaw/openclaw/blob/main/CHANGELOG.md">View full changelog</a></p>
+]]></description>
+            <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.4.15/OpenClaw-2026.4.15.zip" length="47501638" type="application/octet-stream" sparkle:edSignature="JUG3cicpJqCQDvp7VYoN6qBuN4Kn4s0+QQFjlMR69OZlwViLdiStPIHa+1vpuoR4miYhJc9knSDVCFzSfQuYCQ=="/>
+        </item>
     </channel>
-</rss>
+</rss>

apps/android/app/src/main/java/ai/openclaw/app/voice/TalkModeManager.kt

@@ -226,15 +226,14 @@ class TalkModeManager(
     // If this is a response we initiated, handle normally below.
     // Otherwise, if ttsOnAllResponses, finish streaming TTS on terminal events.
     val pending = pendingRunId
-    val knownRun = pending == runId || hasRunCompletion(runId)
-    if (!knownRun) {
+    if (pending == null || runId != pending) {
       if (ttsOnAllResponses && state == "final") {
         val text = extractTextFromChatEventMessage(obj["message"])
         if (!text.isNullOrBlank()) {
           playTtsForText(text)
         }
       }
-      return
+      if (pending == null || runId != pending) return
     }
     Log.d(tag, "chat event arrived runId=$runId state=$state pendingRunId=$pendingRunId")
     val terminal =
@@ -540,7 +539,6 @@ class TalkModeManager(
 
   private suspend fun sendChat(message: String, session: GatewaySession): String {
     val runId = UUID.randomUUID().toString()
-    armPendingRun(runId)
     val params =
       buildJsonObject {
         put("sessionKey", JsonPrimitive(mainSessionKey.ifBlank { "main" }))
@@ -549,29 +547,19 @@ class TalkModeManager(
         put("timeoutMs", JsonPrimitive(30_000))
         put("idempotencyKey", JsonPrimitive(runId))
       }
-    try {
-      val res = session.request("chat.send", params.toString())
-      val parsed = parseRunId(res) ?: runId
-      if (parsed != runId) {
-        pendingRunId = parsed
-      }
-      return parsed
-    } catch (err: Throwable) {
-      clearPendingRun(runId)
-      throw err
+    val res = session.request("chat.send", params.toString())
+    val parsed = parseRunId(res) ?: runId
+    if (parsed != runId) {
+      pendingRunId = parsed
     }
+    return parsed
   }
 
   private suspend fun waitForChatFinal(runId: String): Boolean {
-    consumeRunCompletion(runId)?.let { return it }
-    val deferred =
-      if (pendingRunId == runId) {
-        pendingFinal ?: armPendingRun(runId)
-      } else {
-        armPendingRun(runId)
-      }
-
-    consumeRunCompletion(runId)?.let { return it }
+    pendingFinal?.cancel()
+    val deferred = CompletableDeferred<Boolean>()
+    pendingRunId = runId
+    pendingFinal = deferred
 
     val result =
       withContext(Dispatchers.IO) {
@@ -582,25 +570,11 @@ class TalkModeManager(
         }
       }
 
-    if (!result && pendingRunId == runId) {
-      clearPendingRun(runId)
-    }
-    return result
-  }
-
-  private fun armPendingRun(runId: String): CompletableDeferred<Boolean> {
-    pendingFinal?.cancel()
-    val deferred = CompletableDeferred<Boolean>()
-    pendingRunId = runId
-    pendingFinal = deferred
-    return deferred
-  }
-
-  private fun clearPendingRun(runId: String) {
-    if (pendingRunId == runId) {
+    if (!result) {
       pendingFinal = null
       pendingRunId = null
     }
+    return result
   }
 
   private fun cacheRunCompletion(runId: String, isFinal: Boolean) {
@@ -619,12 +593,6 @@ class TalkModeManager(
     }
   }
 
-  private fun hasRunCompletion(runId: String): Boolean {
-    synchronized(completedRunsLock) {
-      return completedRunStates.containsKey(runId)
-    }
-  }
-
   private fun consumeRunText(runId: String): String? {
     synchronized(completedRunsLock) {
       return completedRunTexts.remove(runId)

apps/android/app/src/test/java/ai/openclaw/app/voice/TalkModeManagerTest.kt

@@ -5,7 +5,6 @@ import ai.openclaw.app.gateway.DeviceAuthTokenStore
 import ai.openclaw.app.gateway.DeviceIdentityStore
 import ai.openclaw.app.gateway.GatewaySession
 import java.util.concurrent.atomic.AtomicLong
-import kotlinx.coroutines.CompletableDeferred
 import kotlinx.coroutines.CoroutineScope
 import kotlinx.coroutines.Dispatchers
 import kotlinx.coroutines.Job
@@ -50,34 +49,6 @@ class TalkModeManagerTest {
     assertEquals(12L, playbackGeneration(manager).get())
   }
 
-  @Test
-  fun duplicateFinalForPendingTalkRunDoesNotStartAllResponseTts() {
-    val manager = createManager()
-    val final = CompletableDeferred<Boolean>()
-
-    manager.ttsOnAllResponses = true
-    setPrivateField(manager, "pendingRunId", "run-talk")
-    setPrivateField(manager, "pendingFinal", final)
-
-    manager.handleGatewayEvent("chat", chatFinalPayload(runId = "run-talk", text = "spoken once"))
-    assertTrue(final.isCompleted)
-    assertEquals(0L, playbackGeneration(manager).get())
-
-    manager.handleGatewayEvent("chat", chatFinalPayload(runId = "run-talk", text = "spoken once"))
-
-    assertEquals(0L, playbackGeneration(manager).get())
-  }
-
-  @Test
-  fun nonPendingFinalStillUsesAllResponseTts() {
-    val manager = createManager()
-
-    manager.ttsOnAllResponses = true
-    manager.handleGatewayEvent("chat", chatFinalPayload(runId = "run-other", text = "speak this"))
-
-    assertEquals(1L, playbackGeneration(manager).get())
-  }
-
   private fun createManager(): TalkModeManager {
     val app = RuntimeEnvironment.getApplication()
     val sessionJob = SupervisorJob()
@@ -115,22 +86,6 @@ class TalkModeManagerTest {
     field.isAccessible = true
     return field.get(target)
   }
-
-  private fun chatFinalPayload(runId: String, text: String): String {
-    return """
-      {
-        "runId": "$runId",
-        "sessionKey": "main",
-        "state": "final",
-        "message": {
-          "role": "assistant",
-          "content": [
-            { "type": "text", "text": "$text" }
-          ]
-        }
-      }
-    """.trimIndent()
-  }
 }
 
 private class InMemoryDeviceAuthStore : DeviceAuthTokenStore {

apps/ios/Sources/Settings/SettingsTab.swift

@@ -21,7 +21,6 @@ struct SettingsTab: View {
     @AppStorage("node.instanceId") private var instanceId: String = UUID().uuidString
     @AppStorage("voiceWake.enabled") private var voiceWakeEnabled: Bool = false
     @AppStorage("talk.enabled") private var talkEnabled: Bool = false
-    @AppStorage(TalkSpeechLocale.storageKey) private var talkSpeechLocale: String = TalkSpeechLocale.automaticID
     @AppStorage("talk.button.enabled") private var talkButtonEnabled: Bool = true
     @AppStorage("talk.background.enabled") private var talkBackgroundEnabled: Bool = false
     @AppStorage("camera.enabled") private var cameraEnabled: Bool = true
@@ -279,11 +278,6 @@ struct SettingsTab: View {
                             help: "Enables voice conversation mode with your connected OpenClaw agent.") { newValue in
                                 self.appModel.setTalkEnabled(newValue)
                             }
-                        Picker("Speech Language", selection: self.$talkSpeechLocale) {
-                            ForEach(TalkSpeechLocale.supportedOptions()) { option in
-                                Text(option.label).tag(option.id)
-                            }
-                        }
                         self.featureToggle(
                             "Background Listening",
                             isOn: self.$talkBackgroundEnabled,

apps/ios/Sources/Voice/TalkModeGatewayConfig.swift

@@ -12,7 +12,6 @@ struct TalkModeGatewayConfigState {
     let rawConfigApiKey: String?
     let interruptOnSpeech: Bool?
     let silenceTimeoutMs: Int
-    let speechLocaleID: String?
 }
 
 enum TalkModeGatewayConfigParser {
@@ -54,7 +53,6 @@ enum TalkModeGatewayConfigParser {
         let silenceTimeoutMs = TalkConfigParsing.resolvedSilenceTimeoutMs(
             talk,
             fallback: defaultSilenceTimeoutMs)
-        let speechLocaleID = TalkConfigParsing.resolvedSpeechLocaleID(talk)
 
         return TalkModeGatewayConfigState(
             activeProvider: activeProvider,
@@ -66,7 +64,6 @@ enum TalkModeGatewayConfigParser {
             defaultOutputFormat: defaultOutputFormat,
             rawConfigApiKey: rawConfigApiKey,
             interruptOnSpeech: interruptOnSpeech,
-            silenceTimeoutMs: silenceTimeoutMs,
-            speechLocaleID: speechLocaleID)
+            silenceTimeoutMs: silenceTimeoutMs)
     }
 }

apps/ios/Sources/Voice/TalkModeManager.swift

@@ -87,7 +87,6 @@ final class TalkModeManager: NSObject {
     private var apiKey: String?
     private var voiceAliases: [String: String] = [:]
     private var interruptOnSpeech: Bool = true
-    private var gatewaySpeechLocaleID: String?
     private var mainSessionKey: String = "main"
     private var fallbackVoiceId: String?
     private var lastPlaybackWasPCM: Bool = false
@@ -501,17 +500,12 @@ final class TalkModeManager: NSObject {
         #endif
 
         self.stopRecognition()
-        let localSpeechLocale = UserDefaults.standard.string(forKey: TalkSpeechLocale.storageKey)
-        let resolvedSpeech = TalkSpeechLocale.makeRecognizer(
-            localSelection: localSpeechLocale,
-            gatewaySelection: self.gatewaySpeechLocaleID)
-        self.speechRecognizer = resolvedSpeech.recognizer
+        self.speechRecognizer = SFSpeechRecognizer()
         guard let recognizer = self.speechRecognizer else {
             throw NSError(domain: "TalkMode", code: 1, userInfo: [
                 NSLocalizedDescriptionKey: "Speech recognizer unavailable",
             ])
         }
-        GatewayDiagnostics.log("talk speech: locale=\(resolvedSpeech.localeID ?? "default")")
 
         self.recognitionRequest = SFSpeechAudioBufferRecognitionRequest()
         self.recognitionRequest?.shouldReportPartialResults = true
@@ -2033,7 +2027,6 @@ extension TalkModeManager {
             if let interrupt = parsed.interruptOnSpeech {
                 self.interruptOnSpeech = interrupt
             }
-            self.gatewaySpeechLocaleID = parsed.speechLocaleID
             self.silenceWindow = TimeInterval(parsed.silenceTimeoutMs) / 1000
             if parsed.normalizedPayload || parsed.defaultVoiceId != nil || parsed.rawConfigApiKey != nil {
                 GatewayDiagnostics.log(
@@ -2048,7 +2041,6 @@ extension TalkModeManager {
             self.gatewayTalkDefaultModelId = nil
             self.gatewayTalkApiKeyConfigured = false
             self.gatewayTalkConfigLoaded = false
-            self.gatewaySpeechLocaleID = nil
             self.silenceWindow = TimeInterval(Self.defaultSilenceTimeoutMs) / 1000
         }
     }

apps/ios/Sources/Voice/TalkSpeechLocale.swift

@@ -1,100 +0,0 @@
-import Foundation
-import OpenClawKit
-import Speech
-
-enum TalkSpeechLocale {
-    static let storageKey = "talk.speechLocale"
-    static let automaticID = "auto"
-    static let fallbackLocaleID = "en-US"
-
-    struct Option: Identifiable {
-        let id: String
-        let label: String
-    }
-
-    static func supportedOptions(
-        supportedLocales: Set<Locale> = SFSpeechRecognizer.supportedLocales()
-    ) -> [Option] {
-        var seen = Set<String>()
-        let dynamic: [Option] = supportedLocales
-            .compactMap { locale in
-                let id = self.canonicalID(locale.identifier)
-                guard seen.insert(id).inserted else { return nil }
-                return Option(id: id, label: self.friendlyName(for: locale))
-            }
-            .sorted { (lhs: Option, rhs: Option) in
-                lhs.label.localizedCaseInsensitiveCompare(rhs.label) == .orderedAscending
-            }
-        return [Option(id: self.automaticID, label: "Automatic")] + dynamic
-    }
-
-    static func resolvedLocaleID(
-        localSelection: String?,
-        gatewaySelection: String?,
-        deviceLocaleID: String = Locale.autoupdatingCurrent.identifier,
-        fallbackLocaleID: String = Self.fallbackLocaleID,
-        supportedLocaleIDs: Set<String>
-    ) -> String? {
-        TalkConfigParsing.resolvedSpeechRecognitionLocaleID(
-            preferredLocaleIDs: [
-                TalkConfigParsing.normalizedExplicitSpeechLocaleID(localSelection),
-                TalkConfigParsing.normalizedExplicitSpeechLocaleID(gatewaySelection),
-                deviceLocaleID,
-            ],
-            fallbackLocaleID: fallbackLocaleID,
-            supportedLocaleIDs: supportedLocaleIDs)
-    }
-
-    static func makeRecognizer(
-        localSelection: String?,
-        gatewaySelection: String?,
-        supportedLocales: Set<Locale> = SFSpeechRecognizer.supportedLocales()
-    ) -> (recognizer: SFSpeechRecognizer?, localeID: String?) {
-        let supportedIDs = Set(supportedLocales.map(\.identifier))
-        guard let localeID = self.resolvedLocaleID(
-            localSelection: localSelection,
-            gatewaySelection: gatewaySelection,
-            supportedLocaleIDs: supportedIDs)
-        else {
-            let recognizer = SFSpeechRecognizer()
-            return (recognizer, recognizer?.locale.identifier)
-        }
-
-        if let recognizer = SFSpeechRecognizer(locale: Locale(identifier: localeID)) {
-            return (recognizer, localeID)
-        }
-
-        let recognizer = SFSpeechRecognizer()
-        return (recognizer, recognizer?.locale.identifier)
-    }
-
-    static func normalizedExplicitLocaleID(_ raw: String?) -> String? {
-        TalkConfigParsing.normalizedExplicitSpeechLocaleID(raw, automaticID: self.automaticID)
-    }
-
-    private static func normalizedLocaleID(_ raw: String?) -> String? {
-        TalkConfigParsing.normalizedSpeechLocaleID(raw)
-    }
-
-    private static func canonicalID(_ raw: String) -> String {
-        raw.replacingOccurrences(of: "_", with: "-")
-    }
-
-    private static func friendlyName(for locale: Locale) -> String {
-        let id = self.canonicalID(locale.identifier)
-        let cleanLocale = Locale(identifier: id)
-        if let langCode = cleanLocale.language.languageCode?.identifier,
-           let lang = cleanLocale.localizedString(forLanguageCode: langCode),
-           let regionCode = cleanLocale.region?.identifier,
-           let region = cleanLocale.localizedString(forRegionCode: regionCode)
-        {
-            return "\(lang) (\(region))"
-        }
-        if let langCode = cleanLocale.language.languageCode?.identifier,
-           let lang = cleanLocale.localizedString(forLanguageCode: langCode)
-        {
-            return lang
-        }
-        return cleanLocale.localizedString(forIdentifier: id) ?? id
-    }
-}

apps/ios/Tests/Logic/TalkConfigParsingTests.swift

@@ -47,16 +47,6 @@ private let iOSSilenceTimeoutMs = 900
                 fallback: iOSSilenceTimeoutMs) == 1500)
     }
 
-    @Test func readsConfiguredSpeechLocale() {
-        let talk: [String: Any] = [
-            "speechLocale": " ru-RU ",
-        ]
-
-        #expect(
-            TalkConfigParsing.resolvedSpeechLocaleID(
-                TalkConfigParsing.bridgeFoundationDictionary(talk)) == "ru-RU")
-    }
-
     @Test func defaultsSilenceTimeoutMsWhenMissing() {
         #expect(TalkConfigParsing.resolvedSilenceTimeoutMs(nil, fallback: iOSSilenceTimeoutMs) == iOSSilenceTimeoutMs)
     }

apps/ios/Tests/TalkSpeechLocaleTests.swift

@@ -1,41 +0,0 @@
-import Foundation
-import Testing
-@testable import OpenClaw
-
-@Suite struct TalkSpeechLocaleTests {
-    @Test func localSelectionOverridesGatewayConfig() {
-        let locale = TalkSpeechLocale.resolvedLocaleID(
-            localSelection: "de-DE",
-            gatewaySelection: "ru-RU",
-            deviceLocaleID: "en-US",
-            supportedLocaleIDs: ["de-DE", "ru-RU", "en-US"])
-
-        #expect(locale == "de-DE")
-    }
-
-    @Test func automaticLocalSelectionAllowsGatewayConfig() {
-        let locale = TalkSpeechLocale.resolvedLocaleID(
-            localSelection: TalkSpeechLocale.automaticID,
-            gatewaySelection: "ru_RU",
-            deviceLocaleID: "en-US",
-            supportedLocaleIDs: ["ru-RU", "en-US"])
-
-        #expect(locale == "ru-RU")
-    }
-
-    @Test func unsupportedConfiguredLocaleFallsBackToDeviceThenEnglish() {
-        let deviceLocale = TalkSpeechLocale.resolvedLocaleID(
-            localSelection: "zz-ZZ",
-            gatewaySelection: nil,
-            deviceLocaleID: "fr-FR",
-            supportedLocaleIDs: ["fr-FR", "en-US"])
-        let english = TalkSpeechLocale.resolvedLocaleID(
-            localSelection: "zz-ZZ",
-            gatewaySelection: nil,
-            deviceLocaleID: "yy-YY",
-            supportedLocaleIDs: ["en-US"])
-
-        #expect(deviceLocale == "fr-FR")
-        #expect(english == "en-US")
-    }
-}

apps/macos/Sources/OpenClaw/AppState.swift

@@ -176,23 +176,6 @@ final class AppState {
         }
     }
 
-    var talkPhaseSoundsEnabled: Bool {
-        didSet {
-            self.ifNotPreview {
-                UserDefaults.standard.set(self.talkPhaseSoundsEnabled, forKey: talkPhaseSoundsEnabledKey)
-            }
-        }
-    }
-
-    var talkShiftToStopEnabled: Bool {
-        didSet {
-            self.ifNotPreview {
-                UserDefaults.standard.set(self.talkShiftToStopEnabled, forKey: talkShiftToStopEnabledKey)
-                Task { TalkSpeechInterruptMonitor.shared.setEnabled(self.talkShiftToStopEnabled && self.talkEnabled) }
-            }
-        }
-    }
-
     /// Gateway-provided UI accent color (hex). Optional; clients provide a default.
     var seamColorHex: String?
 
@@ -326,18 +309,6 @@ final class AppState {
         self.voiceWakeTriggersTalkMode = UserDefaults.standard
             .object(forKey: voiceWakeTriggersTalkModeKey) as? Bool ?? false
         self.talkEnabled = UserDefaults.standard.bool(forKey: talkEnabledKey)
-        if let storedPhaseSounds = UserDefaults.standard.object(forKey: talkPhaseSoundsEnabledKey) as? Bool {
-            self.talkPhaseSoundsEnabled = storedPhaseSounds
-        } else {
-            self.talkPhaseSoundsEnabled = true
-            UserDefaults.standard.set(true, forKey: talkPhaseSoundsEnabledKey)
-        }
-        if let storedShiftToStop = UserDefaults.standard.object(forKey: talkShiftToStopEnabledKey) as? Bool {
-            self.talkShiftToStopEnabled = storedShiftToStop
-        } else {
-            self.talkShiftToStopEnabled = true
-            UserDefaults.standard.set(true, forKey: talkShiftToStopEnabledKey)
-        }
         self.seamColorHex = nil
         if let storedHeartbeats = UserDefaults.standard.object(forKey: heartbeatsEnabledKey) as? Bool {
             self.heartbeatsEnabled = storedHeartbeats
@@ -807,8 +778,6 @@ extension AppState {
         state.voiceWakeAdditionalLocaleIDs = ["en-US", "de-DE"]
         state.voicePushToTalkEnabled = false
         state.talkEnabled = false
-        state.talkPhaseSoundsEnabled = true
-        state.talkShiftToStopEnabled = true
         state.iconOverride = .system
         state.heartbeatsEnabled = true
         state.connectionMode = .local

apps/macos/Sources/OpenClaw/Constants.swift

@@ -24,8 +24,6 @@ let voiceWakeAdditionalLocalesKey = "openclaw.voiceWakeAdditionalLocaleIDs"
 let voicePushToTalkEnabledKey = "openclaw.voicePushToTalkEnabled"
 let voiceWakeTriggersTalkModeKey = "openclaw.voiceWakeTriggersTalkMode"
 let talkEnabledKey = "openclaw.talkEnabled"
-let talkPhaseSoundsEnabledKey = "openclaw.talkPhaseSoundsEnabled"
-let talkShiftToStopEnabledKey = "openclaw.talkShiftToStopEnabled"
 let iconOverrideKey = "openclaw.iconOverride"
 let connectionModeKey = "openclaw.connectionMode"
 let remoteTargetKey = "openclaw.remoteTarget"

apps/macos/Sources/OpenClaw/ExecAllowlistMatcher.swift

@@ -14,8 +14,7 @@ enum ExecAllowlistMatcher {
                     if self.matches(pattern: pattern, target: target) { return entry }
                 } else if pattern != "*",
                           !ExecApprovalHelpers.patternHasPathSelector(rawExecutable),
-                          self.matchesExecutableBasename(pattern: pattern, resolution: resolution)
-                {
+                          self.matchesExecutableBasename(pattern: pattern, resolution: resolution) {
                     return entry
                 }
             case .invalid:

apps/macos/Sources/OpenClaw/ExecApprovals.swift

@@ -618,8 +618,7 @@ enum ExecApprovalsStore {
 
         if !ExecApprovalHelpers.patternHasPathSelector(trimmedPattern),
            !trimmedResolved.isEmpty,
-           case let .valid(migratedPattern) = ExecApprovalHelpers.validateAllowlistPattern(trimmedResolved)
-        {
+           case let .valid(migratedPattern) = ExecApprovalHelpers.validateAllowlistPattern(trimmedResolved) {
             return ExecAllowlistEntry(
                 id: entry.id,
                 pattern: migratedPattern,

apps/macos/Sources/OpenClaw/TalkModeController.swift

@@ -1,4 +1,3 @@
-import AppKit
 import Observation
 
 @MainActor
@@ -18,10 +17,6 @@ final class TalkModeController {
         } else {
             TalkOverlayController.shared.dismiss()
         }
-        TalkSpeechInterruptMonitor.shared.setEnabled(enabled && AppStateStore.shared.talkShiftToStopEnabled)
-        // Talk Mode and Push-to-Talk share the right Option key — disable PTT while Talk Mode is active.
-        let pttEnabled = !enabled && AppStateStore.shared.voicePushToTalkEnabled
-        VoicePushToTalkHotkey.shared.setEnabled(pttEnabled)
         await TalkModeRuntime.shared.setEnabled(enabled)
         // Resume voice wake listener *after* TalkMode audio is fully torn down.
         // Check swabbleEnabled (not voiceWakeTriggersTalkMode) so the paused wake listener
@@ -32,15 +27,8 @@ final class TalkModeController {
     }
 
     func updatePhase(_ phase: TalkModePhase) {
-        let previousPhase = self.phase
         self.phase = phase
         TalkOverlayController.shared.updatePhase(phase)
-
-        // Play distinct system sounds for each phase transition.
-        if phase != previousPhase {
-            Self.playPhaseSound(phase, previousPhase: previousPhase)
-        }
-
         let effectivePhase = self.isPaused ? "paused" : phase.rawValue
         Task {
             await GatewayConnection.shared.talkMode(
@@ -49,25 +37,6 @@ final class TalkModeController {
         }
     }
 
-    private static func playPhaseSound(_ phase: TalkModePhase, previousPhase: TalkModePhase) {
-        guard AppStateStore.shared.talkPhaseSoundsEnabled else { return }
-        let soundName: String? = switch phase {
-        case .thinking:
-            "Tink" // 생각 중: 짧고 가벼운 소리
-        case .speaking:
-            "Pop" // 대답 시작: 톡 소리
-        case .listening:
-            // 대답 중단(speaking→listening): 부드러운 종료음
-            // 듣기 시작(thinking→listening 등): 잠수함 소리
-            previousPhase == .speaking ? "Bottle" : "Submarine"
-        case .idle:
-            nil
-        }
-        if let soundName {
-            NSSound(named: NSSound.Name(soundName))?.play()
-        }
-    }
-
     func updateLevel(_ level: Double) {
         TalkOverlayController.shared.updateLevel(level)
     }

apps/macos/Sources/OpenClaw/TalkModeGatewayConfig.swift

@@ -11,7 +11,6 @@ struct TalkModeGatewayConfigState {
     let outputFormat: String?
     let interruptOnSpeech: Bool
     let silenceTimeoutMs: Int
-    let speechLocaleID: String?
     let apiKey: String?
     let seamColorHex: String?
 }
@@ -54,7 +53,6 @@ enum TalkModeGatewayConfigParser {
         }
         let outputFormat = activeConfig?["outputFormat"]?.stringValue
         let interrupt = talk?["interruptOnSpeech"]?.boolValue
-        let speechLocaleID = TalkConfigParsing.resolvedSpeechLocaleID(talk)
         let apiKey = activeConfig?["apiKey"]?.stringValue
         let resolvedVoice: String? = if activeProvider == defaultProvider {
             (voice?.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty == false ? voice : nil) ??
@@ -80,7 +78,6 @@ enum TalkModeGatewayConfigParser {
             outputFormat: outputFormat,
             interruptOnSpeech: interrupt ?? true,
             silenceTimeoutMs: silenceTimeoutMs,
-            speechLocaleID: speechLocaleID,
             apiKey: resolvedApiKey,
             seamColorHex: rawSeam.isEmpty ? nil : rawSeam)
     }
@@ -107,7 +104,6 @@ enum TalkModeGatewayConfigParser {
             outputFormat: nil,
             interruptOnSpeech: true,
             silenceTimeoutMs: defaultSilenceTimeoutMs,
-            speechLocaleID: nil,
             apiKey: resolvedApiKey,
             seamColorHex: nil)
     }

apps/macos/Sources/OpenClaw/TalkModeRuntime.swift

@@ -70,7 +70,6 @@ actor TalkModeRuntime {
     private var defaultOutputFormat: String?
     private var interruptOnSpeech: Bool = true
     private var activeTalkProvider = TalkModeRuntime.defaultTalkProvider
-    private var speechLocaleID: String?
     private var lastInterruptedAtSeconds: Double?
     private var voiceAliases: [String: String] = [:]
     private var lastSpokenText: String?
@@ -187,23 +186,12 @@ actor TalkModeRuntime {
         self.recognitionGeneration &+= 1
         let generation = self.recognitionGeneration
 
-        let voiceWakeLocale = await MainActor.run { AppStateStore.shared.voiceWakeLocaleID }
-        let supportedLocaleIDs = Set(SFSpeechRecognizer.supportedLocales().map(\.identifier))
-        let localeID = TalkConfigParsing.resolvedSpeechRecognitionLocaleID(
-            preferredLocaleIDs: [
-                self.speechLocaleID,
-                voiceWakeLocale,
-                Locale.autoupdatingCurrent.identifier,
-            ],
-            supportedLocaleIDs: supportedLocaleIDs)
-        self.recognizer = localeID
-            .map { SFSpeechRecognizer(locale: Locale(identifier: $0)) }
-            ?? SFSpeechRecognizer()
+        let locale = await MainActor.run { AppStateStore.shared.voiceWakeLocaleID }
+        self.recognizer = SFSpeechRecognizer(locale: Locale(identifier: locale))
         guard let recognizer, recognizer.isAvailable else {
             self.logger.error("talk recognizer unavailable")
             return
         }
-        self.logger.debug("talk recognizer locale=\(recognizer.locale.identifier, privacy: .public)")
 
         let request = SFSpeechAudioBufferRecognitionRequest()
         Self.configureRecognitionRequest(request)
@@ -1021,22 +1009,11 @@ extension TalkModeRuntime {
         self.defaultOutputFormat = cfg.outputFormat
         self.interruptOnSpeech = cfg.interruptOnSpeech
         self.activeTalkProvider = cfg.activeProvider
-        let configuredSilenceMs = cfg.silenceTimeoutMs
-        let locale = await MainActor.run { AppStateStore.shared.voiceWakeLocaleID }
-        let isCJKLocale = locale.hasPrefix("ko") || locale.hasPrefix("ja") || locale.hasPrefix("zh")
-        let effectiveSilenceMs = isCJKLocale ? max(configuredSilenceMs, 2000) : configuredSilenceMs
-        if isCJKLocale, configuredSilenceMs < 2000 {
-            self.logger
-                .info(
-                    "talk CJK locale: silence timeout clamped " +
-                        "\(configuredSilenceMs, privacy: .public)ms -> 2000ms")
-        }
-        self.silenceWindow = TimeInterval(effectiveSilenceMs) / 1000
-        self.speechLocaleID = cfg.speechLocaleID
+        self.silenceWindow = TimeInterval(cfg.silenceTimeoutMs) / 1000
         self.apiKey = cfg.apiKey
         let hasApiKey = (cfg.apiKey?.isEmpty == false)
-        let voiceLabel = cfg.voiceId.flatMap { $0.isEmpty ? nil : $0 } ?? "none"
-        let modelLabel = cfg.modelId.flatMap { $0.isEmpty ? nil : $0 } ?? "none"
+        let voiceLabel = (cfg.voiceId?.isEmpty == false) ? cfg.voiceId! : "none"
+        let modelLabel = (cfg.modelId?.isEmpty == false) ? cfg.modelId! : "none"
         self.logger
             .info(
                 "talk config provider=\(cfg.activeProvider, privacy: .public) " +
@@ -1044,8 +1021,7 @@ extension TalkModeRuntime {
                     "modelId=\(modelLabel, privacy: .public) " +
                     "apiKey=\(hasApiKey, privacy: .public) " +
                     "interrupt=\(cfg.interruptOnSpeech, privacy: .public) " +
-                    "silenceTimeoutMs=\(cfg.silenceTimeoutMs, privacy: .public) " +
-                    "speechLocale=\(cfg.speechLocaleID ?? "device", privacy: .public)")
+                    "silenceTimeoutMs=\(cfg.silenceTimeoutMs, privacy: .public)")
     }
 
     static func selectTalkProviderConfig(

apps/macos/Sources/OpenClaw/TalkSpeechInterruptMonitor.swift

@@ -1,57 +0,0 @@
-import AppKit
-import OSLog
-
-/// Monitors right Option key (keyCode 61) to interrupt Talk Mode speech.
-/// Independent of Push-to-Talk — active whenever Talk Mode is enabled.
-final class TalkSpeechInterruptMonitor: @unchecked Sendable {
-    static let shared = TalkSpeechInterruptMonitor()
-
-    private let logger = Logger(subsystem: "ai.openclaw", category: "talk.interrupt")
-    private var globalMonitor: Any?
-    private var localMonitor: Any?
-
-    func setEnabled(_ enabled: Bool) {
-        DispatchQueue.main.async { [weak self] in
-            guard let self else { return }
-            if enabled {
-                self.startMonitoring()
-            } else {
-                self.stopMonitoring()
-            }
-        }
-    }
-
-    private func startMonitoring() {
-        guard self.globalMonitor == nil, self.localMonitor == nil else { return }
-        self.globalMonitor = NSEvent.addGlobalMonitorForEvents(matching: .flagsChanged) { [weak self] event in
-            self?.handleFlags(keyCode: event.keyCode, modifierFlags: event.modifierFlags)
-        }
-        self.localMonitor = NSEvent.addLocalMonitorForEvents(matching: .flagsChanged) { [weak self] event in
-            self?.handleFlags(keyCode: event.keyCode, modifierFlags: event.modifierFlags)
-            return event
-        }
-        self.logger.info("talk interrupt monitor started")
-    }
-
-    private func stopMonitoring() {
-        if let globalMonitor {
-            NSEvent.removeMonitor(globalMonitor)
-            self.globalMonitor = nil
-        }
-        if let localMonitor {
-            NSEvent.removeMonitor(localMonitor)
-            self.localMonitor = nil
-        }
-        self.logger.info("talk interrupt monitor stopped")
-    }
-
-    private func handleFlags(keyCode: UInt16, modifierFlags: NSEvent.ModifierFlags) {
-        // Right Option key down (keyCode 61).
-        guard keyCode == 61, modifierFlags.contains(.option) else { return }
-        Task { @MainActor in
-            guard TalkModeController.shared.phase == .speaking else { return }
-            self.logger.info("right option — interrupting talk mode speech")
-            TalkModeController.shared.stopSpeaking(reason: .userTap)
-        }
-    }
-}

apps/macos/Sources/OpenClaw/VoicePushToTalk.swift

@@ -80,7 +80,6 @@ final class VoicePushToTalkHotkey: @unchecked Sendable {
 
     private func updateModifierState(keyCode: UInt16, modifierFlags: NSEvent.ModifierFlags) {
         // assert(Thread.isMainThread)  - Removed for Swift 6
-
         // Right Option (keyCode 61) acts as a hold-to-talk modifier.
         if keyCode == 61 {
             self.optionDown = modifierFlags.contains(.option)

apps/macos/Sources/OpenClaw/VoiceWakeSettings.swift

@@ -72,31 +72,6 @@ struct VoiceWakeSettings: View {
                     binding: self.$state.voicePushToTalkEnabled)
                     .disabled(!voiceWakeSupported)
 
-                if self.state.voicePushToTalkEnabled, self.state.talkEnabled {
-                    Text("Push-to-Talk is paused while Talk Mode is active. It resumes when Talk Mode is turned off.")
-                        .font(.footnote)
-                        .foregroundStyle(.secondary)
-                        .padding(.leading, 20)
-                }
-
-                SettingsToggleRow(
-                    title: "Play phase-transition sounds",
-                    subtitle: """
-                    Play short system sounds when Talk Mode switches between
-                    listening, thinking, and speaking.
-                    """,
-                    binding: self.$state.talkPhaseSoundsEnabled)
-                    .disabled(!voiceWakeSupported)
-
-                SettingsToggleRow(
-                    title: "Press Right Option to stop speech",
-                    subtitle: """
-                    Tap the right Option key to interrupt the assistant while it is
-                    speaking and return to listening.
-                    """,
-                    binding: self.$state.talkShiftToStopEnabled)
-                    .disabled(!voiceWakeSupported)
-
                 if !voiceWakeSupported {
                     Label("Voice Wake requires macOS 26 or newer.", systemImage: "exclamationmark.triangle.fill")
                         .font(.callout)

apps/macos/Tests/OpenClawIPCTests/TalkModeGatewayConfigTests.swift

@@ -25,10 +25,10 @@ struct TalkModeGatewayConfigTests {
                             "voiceId": "unused-voice",
                         ],
                     ],
-                    "speechLocale": "ru-RU",
                 ]),
             ],
-            issues: nil)
+            issues: nil
+        )
 
         let parsed = TalkModeGatewayConfigParser.parse(
             snapshot: snapshot,
@@ -37,12 +37,12 @@ struct TalkModeGatewayConfigTests {
             defaultSilenceTimeoutMs: TalkDefaults.silenceTimeoutMs,
             envVoice: "env-voice",
             sagVoice: "sag-voice",
-            envApiKey: "env-key")
+            envApiKey: "env-key"
+        )
 
         #expect(parsed.activeProvider == "mlx")
         #expect(parsed.modelId == nil)
         #expect(parsed.apiKey == nil)
         #expect(parsed.voiceId == "unused-voice")
-        #expect(parsed.speechLocaleID == "ru-RU")
     }
 }

apps/shared/OpenClawKit/Sources/OpenClawKit/TalkConfigParsing.swift

@@ -56,46 +56,6 @@ public enum TalkConfigParsing {
         self.resolvedPositiveInt(talk?["silenceTimeoutMs"], fallback: fallback)
     }
 
-    public static func normalizedSpeechLocaleID(_ value: String?) -> String? {
-        let trimmed = (value ?? "").trimmingCharacters(in: .whitespacesAndNewlines)
-        return trimmed.isEmpty ? nil : trimmed.replacingOccurrences(of: "_", with: "-")
-    }
-
-    public static func resolvedSpeechLocaleID(
-        _ talk: [String: AnyCodable]?,
-        fallback: String? = nil
-    ) -> String? {
-        self.normalizedSpeechLocaleID(talk?["speechLocale"]?.stringValue)
-            ?? self.normalizedSpeechLocaleID(fallback)
-    }
-
-    public static func normalizedExplicitSpeechLocaleID(
-        _ value: String?,
-        automaticID: String = "auto"
-    ) -> String? {
-        let normalized = self.normalizedSpeechLocaleID(value)
-        return normalized == automaticID ? nil : normalized
-    }
-
-    public static func resolvedSpeechRecognitionLocaleID(
-        preferredLocaleIDs: [String?],
-        fallbackLocaleID: String = "en-US",
-        supportedLocaleIDs: Set<String>
-    ) -> String? {
-        let supported = Set(supportedLocaleIDs.compactMap(self.normalizedSpeechLocaleID))
-        var seen = Set<String>()
-        let candidates = (preferredLocaleIDs + [fallbackLocaleID])
-            .compactMap(self.normalizedSpeechLocaleID)
-
-        for candidate in candidates {
-            guard seen.insert(candidate).inserted else { continue }
-            if supported.isEmpty || supported.contains(candidate) {
-                return candidate
-            }
-        }
-        return nil
-    }
-
     private static func normalizedTalkProviderID(_ raw: String?) -> String? {
         let trimmed = (raw ?? "").trimmingCharacters(in: .whitespacesAndNewlines).lowercased()
         return trimmed.isEmpty ? nil : trimmed

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

@@ -116,21 +116,4 @@ struct TalkConfigParsingTests {
         #expect(TalkConfigParsing.resolvedPositiveInt(AnyCodable(true), fallback: 700) == 700)
         #expect(TalkConfigParsing.resolvedPositiveInt(AnyCodable("1500"), fallback: 700) == 700)
     }
-
-    @Test func resolvesSpeechLocaleID() {
-        #expect(TalkConfigParsing.resolvedSpeechLocaleID(["speechLocale": AnyCodable(" ru_RU ")]) == "ru-RU")
-        #expect(TalkConfigParsing.resolvedSpeechLocaleID(["speechLocale": AnyCodable("")], fallback: "en-US") == "en-US")
-    }
-
-    @Test func resolvesSpeechRecognitionLocaleFromSupportedFallbacks() {
-        let locale = TalkConfigParsing.resolvedSpeechRecognitionLocaleID(
-            preferredLocaleIDs: ["zz-ZZ", "fr-FR"],
-            supportedLocaleIDs: ["fr-FR", "en-US"])
-        let fallback = TalkConfigParsing.resolvedSpeechRecognitionLocaleID(
-            preferredLocaleIDs: ["zz-ZZ", "yy-YY"],
-            supportedLocaleIDs: ["en-US"])
-
-        #expect(locale == "fr-FR")
-        #expect(fallback == "en-US")
-    }
 }

docs/.generated/config-baseline.sha256

@@ -1,4 +1,4 @@
-3efb041739877bd5387ffc87e0ddd11be43d80d38e7779407ce8091dcb797e5e  config-baseline.json
-5c6e35c5846f654d717d4b20853649e0b45a746423834f539b2a2223abcd5226  config-baseline.core.json
+6ed33ef102e7c92816243bfabc3626222a679c3270c12ec5ea47b28b66204b3b  config-baseline.json
+f86cb4d57ec1f5fd75008be0ab86151194945eb013a47ab4bdeaddafd3780da7  config-baseline.core.json
 7cd9c908f066c143eab2a201efbc9640f483ab28bba92ddeca1d18cc2b528bc3  config-baseline.channel.json
-a5479c182ec987bb21e814b8a4e7b3bda7190ae5c2b35fd5ca403dfa48afa115  config-baseline.plugin.json
+7825b56a5b3fcdbe2e09ef8fe5d9f12ac3598435afebe20413051e45b0d1968e  config-baseline.plugin.json

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

@@ -1,2 +1,2 @@
-690c1cd4c0c2c3d31577958120e14ac0bf555af529e03aa5e7965b1d04659c49  plugin-sdk-api-baseline.json
-a0e6ba472ddd3acea34c0a8fda8cbb7d1172b1671a671d5fef5a9f42d749ce0d  plugin-sdk-api-baseline.jsonl
+f813474b1623f06e1465daacd56db970e8e92ab1be122faee0fa2a1dc2d4fc43  plugin-sdk-api-baseline.json
+b3ea88c0c9b4cf6d9a46f0d34149063303853e78ef9708224608e4da79b23190  plugin-sdk-api-baseline.jsonl

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

@@ -11,14 +11,6 @@
     "source": "OpenAI provider",
     "target": "OpenAI provider"
   },
-  {
-    "source": "Azure Speech",
-    "target": "Azure Speech"
-  },
-  {
-    "source": "Azure Speech provider",
-    "target": "Azure Speech provider"
-  },
   {
     "source": "Status",
     "target": "Status"
@@ -119,10 +111,6 @@
     "source": "BytePlus (International)",
     "target": "BytePlus（国际版）"
   },
-  {
-    "source": "Volcengine TTS HTTP API",
-    "target": "Volcengine TTS HTTP API"
-  },
   {
     "source": "Amazon Bedrock Mantle",
     "target": "Amazon Bedrock Mantle"

docs/automation/cron-jobs.md

@@ -84,7 +84,7 @@ This fires ~5–6 times per month instead of 0–1 times per month. OpenClaw use
 | Current session | `current`           | Bound at creation time   | Context-aware recurring work    |
 | Custom session  | `session:custom-id` | Persistent named session | Workflows that build on history |
 
-**Main session** jobs enqueue a system event and optionally wake the heartbeat (`--wake now` or `--wake next-heartbeat`). Those system events do not extend daily/idle reset freshness for the target session. **Isolated** jobs run a dedicated agent turn with a fresh session. **Custom sessions** (`session:xxx`) persist context across runs, enabling workflows like daily standups that build on previous summaries.
+**Main session** jobs enqueue a system event and optionally wake the heartbeat (`--wake now` or `--wake next-heartbeat`). **Isolated** jobs run a dedicated agent turn with a fresh session. **Custom sessions** (`session:xxx`) persist context across runs, enabling workflows like daily standups that build on previous summaries.
 
 For isolated jobs, “fresh session” means a new transcript/session id for each run. OpenClaw may carry safe preferences such as thinking/fast/verbose settings, labels, and explicit user-selected model/auth overrides, but it does not inherit ambient conversation context from an older cron row: channel/group routing, send or queue policy, elevation, origin, or ACP runtime binding. Use `current` or `session:<id>` when a recurring job should deliberately build on the same conversation context.
 
@@ -140,7 +140,7 @@ forever.
 | `webhook`  | POST finished event payload to a URL                                |
 | `none`     | No runner fallback delivery                                         |
 
-Use `--announce --channel telegram --to "-1001234567890"` for channel delivery. For Telegram forum topics, use `-1001234567890:topic:123`. Slack/Discord/Mattermost targets should use explicit prefixes (`channel:<id>`, `user:<id>`). Matrix room IDs are case-sensitive; use the exact room ID or `room:!room:server` form from Matrix.
+Use `--announce --channel telegram --to "-1001234567890"` for channel delivery. For Telegram forum topics, use `-1001234567890:topic:123`. Slack/Discord/Mattermost targets should use explicit prefixes (`channel:<id>`, `user:<id>`).
 
 For isolated jobs, chat delivery is shared. If a chat route is available, the
 agent can use the `message` tool even when the job uses `--no-deliver`. If the
@@ -148,11 +148,6 @@ agent sends to the configured/current target, OpenClaw skips the fallback
 announce. Otherwise `announce`, `webhook`, and `none` only control what the
 runner does with the final reply after the agent turn.
 
-When an agent creates an isolated reminder from an active chat, OpenClaw stores
-the preserved live delivery target for the fallback announce route. Internal
-session keys may be lowercase; provider delivery targets are not reconstructed
-from those keys when current chat context is available.
-
 Failure notifications follow a separate destination path:
 
 - `cron.failureDestination` sets a global default for failure notifications.
@@ -423,9 +418,6 @@ openclaw doctor
 - Delivery mode `none` means no runner fallback send is expected. The agent can
   still send directly with the `message` tool when a chat route is available.
 - Delivery target missing/invalid (`channel`/`to`) means outbound was skipped.
-- For Matrix, copied or legacy jobs with lowercased `delivery.to` room IDs can
-  fail because Matrix room IDs are case-sensitive. Edit the job to the exact
-  `!room:server` or `room:!room:server` value from Matrix.
 - Channel auth errors (`unauthorized`, `Forbidden`) mean delivery was blocked by credentials.
 - If the isolated run returns only the silent token (`NO_REPLY` / `no_reply`),
   OpenClaw suppresses direct outbound delivery and also suppresses the fallback
@@ -433,18 +425,6 @@ openclaw doctor
 - If the agent should message the user itself, check that the job has a usable
   route (`channel: "last"` with a previous chat, or an explicit channel/target).
 
-### Cron or heartbeat appears to prevent `/new`-style rollover
-
-- Daily and idle reset freshness is not based on `updatedAt`; see
-  [Session management](/concepts/session#session-lifecycle).
-- Cron wakeups, heartbeat runs, exec notifications, and gateway bookkeeping may
-  update the session row for routing/status, but they do not extend
-  `sessionStartedAt` or `lastInteractionAt`.
-- For legacy rows created before those fields existed, OpenClaw can recover
-  `sessionStartedAt` from the transcript JSONL session header when the file is
-  still available. Legacy idle rows without `lastInteractionAt` use that
-  recovered start time as their idle baseline.
-
 ### Timezone gotchas
 
 - Cron without `--tz` uses the gateway host timezone.

docs/automation/hooks.md

@@ -126,11 +126,6 @@ Each event includes: `type`, `action`, `sessionKey`, `timestamp`, `messages` (pu
 
 **Compaction events**: `session:compact:before` includes `messageCount`, `tokenCount`. `session:compact:after` adds `compactedCount`, `summaryLength`, `tokensBefore`, `tokensAfter`.
 
-`command:stop` observes the user issuing `/stop`; it is cancellation/command
-lifecycle, not an agent-finalization gate. Plugins that need to inspect a
-natural final answer and ask the agent for one more pass should use the typed
-plugin hook `before_agent_finalize` instead. See [Plugin hooks](/plugins/hooks).
-
 ## Hook discovery
 
 Hooks are discovered from these directories, in order of increasing override precedence:

docs/automation/index.md

@@ -93,7 +93,7 @@ See [Hooks](/automation/hooks).
 
 ### Heartbeat
 
-Heartbeat is a periodic main-session turn (default every 30 minutes). It batches multiple checks (inbox, calendar, notifications) in one agent turn with full session context. Heartbeat turns do not create task records and do not extend daily/idle session reset freshness. Use `HEARTBEAT.md` for a small checklist, or a `tasks:` block when you want due-only periodic checks inside heartbeat itself. Empty heartbeat files skip as `empty-heartbeat-file`; due-only task mode skips as `no-tasks-due`.
+Heartbeat is a periodic main-session turn (default every 30 minutes). It batches multiple checks (inbox, calendar, notifications) in one agent turn with full session context. Heartbeat turns do not create task records. Use `HEARTBEAT.md` for a small checklist, or a `tasks:` block when you want due-only periodic checks inside heartbeat itself. Empty heartbeat files skip as `empty-heartbeat-file`; due-only task mode skips as `no-tasks-due`.
 
 See [Heartbeat](/gateway/heartbeat).
 

docs/channels/matrix.md

@@ -398,12 +398,6 @@ Restore room keys from server backup:
 openclaw matrix verify backup restore
 ```
 
-If the backup key is not already loaded on disk, pass the Matrix recovery key:
-
-```bash
-openclaw matrix verify backup restore --recovery-key "<your-recovery-key>"
-```
-
 Interactive self-verification flow:
 
 ```bash
@@ -486,8 +480,6 @@ openclaw matrix verify status
 ```
 
     Add `--account <id>` to target a named account. This can also recreate secret storage if the current backup secret cannot be loaded safely.
-    Add `--rotate-recovery-key` only when you intentionally want the old recovery
-    key to stop unlocking the fresh backup baseline.
 
   </Accordion>
 
@@ -509,34 +501,6 @@ openclaw matrix verify status
 
   </Accordion>
 
-  <Accordion title="Deleted or invalid Matrix device">
-    If `verify status` says the current device is no longer listed on the
-    homeserver, create a new OpenClaw Matrix device. For password login:
-
-```bash
-openclaw matrix account add \
-  --account assistant \
-  --homeserver https://matrix.example.org \
-  --user-id '@assistant:example.org' \
-  --password '<password>' \
-  --device-name OpenClaw-Gateway
-```
-
-    For token auth, create a fresh access token in your Matrix client or admin UI,
-    then update OpenClaw:
-
-```bash
-openclaw matrix account add \
-  --account assistant \
-  --homeserver https://matrix.example.org \
-  --access-token '<token>'
-```
-
-    Replace `assistant` with the account ID from the failed command, or omit
-    `--account` for the default account.
-
-  </Accordion>
-
   <Accordion title="Device hygiene">
     Old OpenClaw-managed devices can accumulate. List and prune:
 
@@ -883,11 +847,6 @@ Matrix accepts these target forms anywhere OpenClaw asks you for a room or user
 - Rooms: `!room:server`, `room:!room:server`, or `matrix:room:!room:server`
 - Aliases: `#alias:server`, `channel:#alias:server`, or `matrix:channel:#alias:server`
 
-Matrix room IDs are case-sensitive. Use the exact room ID casing from Matrix
-when configuring explicit delivery targets, cron jobs, bindings, or allowlists.
-OpenClaw keeps internal session keys canonical for storage, so those lowercase
-keys are not a reliable source for Matrix delivery IDs.
-
 Live directory lookup uses the logged-in Matrix account:
 
 - User lookups query the Matrix user directory on that homeserver.

docs/channels/msteams.md

@@ -5,7 +5,7 @@ read_when:
 title: "Microsoft Teams"
 ---
 
-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.
+Text and DM attachments are supported; channel and 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.
 
 ## Bundled plugin
 
@@ -27,64 +27,25 @@ openclaw plugins install ./path/to/local/msteams-plugin
 
 Details: [Plugins](/tools/plugin)
 
-## Quick setup
+## Quick setup (beginner)
 
-The [`@microsoft/teams.cli`](https://www.npmjs.com/package/@microsoft/teams.cli) handles bot registration, manifest creation, and credential generation in a single command.
+1. Ensure the Microsoft Teams plugin is available.
+   - Current packaged OpenClaw releases already bundle it.
+   - Older/custom installs can add it manually with the commands above.
+2. Create an **Azure Bot** (App ID + client secret + tenant ID).
+3. Configure OpenClaw with those credentials.
+4. Expose `/api/messages` (port 3978 by default) via a public URL or tunnel.
+5. Install the Teams app package and start the gateway.
 
-**1. Install and log in**
-
-```bash
-npm install -g @microsoft/teams.cli@preview
-teams login
-teams status   # verify you're logged in and see your tenant info
-```
-
-> **Note:** The Teams CLI is currently in preview. Commands and flags may change between releases.
-
-**2. Start a tunnel** (Teams can't reach localhost)
-
-Install and authenticate the devtunnel CLI if you haven't already ([getting started guide](https://learn.microsoft.com/en-us/azure/developer/dev-tunnels/get-started)).
-
-```bash
-# One-time setup (persistent URL across sessions):
-devtunnel create my-openclaw-bot --allow-anonymous
-devtunnel port create my-openclaw-bot -p 3978 --protocol auto
-
-# Each dev session:
-devtunnel host my-openclaw-bot
-# Your endpoint: https://<tunnel-id>.devtunnels.ms/api/messages
-```
-
-> **Note:** `--allow-anonymous` is required because Teams can't authenticate with devtunnels. Each incoming bot request is still validated by the Teams SDK automatically.
-
-Alternatives: `ngrok http 3978` or `tailscale funnel 3978` (but these may change URLs each session).
-
-**3. Create the app**
-
-```bash
-teams app create \
-  --name "OpenClaw" \
-  --endpoint "https://<your-tunnel-url>/api/messages"
-```
-
-This single command:
-
-- Creates an Entra ID (Azure AD) application
-- Generates a client secret
-- Builds and uploads a Teams app manifest (with icons)
-- Registers the bot (Teams-managed by default — no Azure subscription needed)
-
-The output will show `CLIENT_ID`, `CLIENT_SECRET`, `TENANT_ID`, and a **Teams App ID** — note these for the next steps. It also offers to install the app in Teams directly.
-
-**4. Configure OpenClaw** using the credentials from the output:
+Minimal config (client secret):
 
 ```json5
 {
   channels: {
     msteams: {
       enabled: true,
-      appId: "<CLIENT_ID>",
-      appPassword: "<CLIENT_SECRET>",
+      appId: "<APP_ID>",
+      appPassword: "<APP_PASSWORD>",
       tenantId: "<TENANT_ID>",
       webhook: { port: 3978, path: "/api/messages" },
     },
@@ -92,34 +53,10 @@ The output will show `CLIENT_ID`, `CLIENT_SECRET`, `TENANT_ID`, and a **Teams Ap
 }
 ```
 
-Or use environment variables directly: `MSTEAMS_APP_ID`, `MSTEAMS_APP_PASSWORD`, `MSTEAMS_TENANT_ID`.
-
-**5. Install the app in Teams**
-
-`teams app create` will prompt you to install the app — select "Install in Teams". If you skipped it, you can get the link later:
-
-```bash
-teams app get <teamsAppId> --install-link
-```
-
-**6. Verify everything works**
-
-```bash
-teams app doctor <teamsAppId>
-```
-
-This runs diagnostics across bot registration, AAD app config, manifest validity, and SSO setup.
-
-For production deployments, consider using [federated authentication](#federated-authentication-certificate--managed-identity) (certificate or managed identity) instead of client secrets.
+For production deployments, consider using [federated authentication](#federated-authentication) (certificate or managed identity) instead of client secrets.
 
 Note: group chats are blocked by default (`channels.msteams.groupPolicy: "allowlist"`). To allow group replies, set `channels.msteams.groupAllowFrom` (or use `groupPolicy: "open"` to allow any member, mention-gated).
 
-## Goals
-
-- Talk to OpenClaw via Teams DMs, group chats, or channels.
-- Keep routing deterministic: replies always go back to the channel they arrived on.
-- Default to safe channel behavior (mentions required unless configured otherwise).
-
 ## Config writes
 
 By default, Microsoft Teams is allowed to write config updates triggered by `/config set|unset` (requires `commands.config: true`).
@@ -189,93 +126,54 @@ Example:
 }
 ```
 
-<details>
-<summary><strong>Manual setup (without the Teams CLI)</strong></summary>
+## Azure Bot setup
 
-If you can't use the Teams CLI, you can set up the bot manually through the Azure Portal.
+Before configuring OpenClaw, create an Azure Bot resource and capture its credentials.
 
-### How it works
+<Steps>
+  <Step title="Create the Azure Bot">
+    Go to [Create Azure Bot](https://portal.azure.com/#create/Microsoft.AzureBot) and fill in the **Basics** tab:
 
-1. Ensure the Microsoft Teams plugin is available (bundled in current releases).
-2. Create an **Azure Bot** (App ID + secret + tenant ID).
-3. Build a **Teams app package** that references the bot and includes the RSC permissions below.
-4. Upload/install the Teams app into a team (or personal scope for DMs).
-5. Configure `msteams` in `~/.openclaw/openclaw.json` (or env vars) and start the gateway.
-6. The gateway listens for Bot Framework webhook traffic on `/api/messages` by default.
+    | Field              | Value                                                    |
+    | ------------------ | -------------------------------------------------------- |
+    | **Bot handle**     | Your bot name, e.g. `openclaw-msteams` (must be unique)  |
+    | **Subscription**   | Your Azure subscription                                  |
+    | **Resource group** | Create new or use existing                               |
+    | **Pricing tier**   | **Free** for dev/testing                                 |
+    | **Type of App**    | **Single Tenant** (recommended)                          |
+    | **Creation type**  | **Create new Microsoft App ID**                          |
 
-### Step 1: Create Azure Bot
+    <Note>
+    New multi-tenant bots were deprecated after 2025-07-31. Use **Single Tenant** for new bots.
+    </Note>
 
-1. Go to [Create Azure Bot](https://portal.azure.com/#create/Microsoft.AzureBot)
-2. Fill in the **Basics** tab:
+    Click **Review + create** → **Create** (wait ~1-2 minutes).
 
-   | Field              | Value                                                    |
-   | ------------------ | -------------------------------------------------------- |
-   | **Bot handle**     | Your bot name, e.g., `openclaw-msteams` (must be unique) |
-   | **Subscription**   | Select your Azure subscription                           |
-   | **Resource group** | Create new or use existing                               |
-   | **Pricing tier**   | **Free** for dev/testing                                 |
-   | **Type of App**    | **Single Tenant** (recommended - see note below)         |
-   | **Creation type**  | **Create new Microsoft App ID**                          |
+  </Step>
 
-> **Deprecation notice:** Creation of new multi-tenant bots was deprecated after 2025-07-31. Use **Single Tenant** for new bots.
+  <Step title="Capture credentials">
+    From the Azure Bot resource → **Configuration**:
 
-3. Click **Review + create** → **Create** (wait ~1-2 minutes)
+    - copy **Microsoft App ID** → `appId`
+    - **Manage Password** → **Certificates & secrets** → **New client secret** → copy the value → `appPassword`
+    - **Overview** → **Directory (tenant) ID** → `tenantId`
 
-### Step 2: Get Credentials
+  </Step>
 
-1. Go to your Azure Bot resource → **Configuration**
-2. Copy **Microsoft App ID** → this is your `appId`
-3. Click **Manage Password** → go to the App Registration
-4. Under **Certificates & secrets** → **New client secret** → copy the **Value** → this is your `appPassword`
-5. Go to **Overview** → copy **Directory (tenant) ID** → this is your `tenantId`
+  <Step title="Configure messaging endpoint">
+    Azure Bot → **Configuration** → set **Messaging endpoint**:
 
-### Step 3: Configure Messaging Endpoint
+    - Production: `https://your-domain.com/api/messages`
+    - Local dev: use a tunnel (see [Local development](#local-development-tunneling))
 
-1. In Azure Bot → **Configuration**
-2. Set **Messaging endpoint** to your webhook URL:
-   - Production: `https://your-domain.com/api/messages`
-   - Local dev: Use a tunnel (see [Local Development](#local-development-tunneling) below)
+  </Step>
 
-### Step 4: Enable Teams Channel
+  <Step title="Enable the Teams channel">
+    Azure Bot → **Channels** → click **Microsoft Teams** → Configure → Save. Accept the Terms of Service.
+  </Step>
+</Steps>
 
-1. In Azure Bot → **Channels**
-2. Click **Microsoft Teams** → Configure → Save
-3. Accept the Terms of Service
-
-### Step 5: Build Teams App Manifest
-
-- Include a `bot` entry with `botId = <App ID>`.
-- Scopes: `personal`, `team`, `groupChat`.
-- `supportsFiles: true` (required for personal scope file handling).
-- Add RSC permissions (see [RSC Permissions](#current-teams-rsc-permissions-manifest)).
-- Create icons: `outline.png` (32x32) and `color.png` (192x192).
-- Zip all three files together: `manifest.json`, `outline.png`, `color.png`.
-
-### Step 6: Configure OpenClaw
-
-```json5
-{
-  channels: {
-    msteams: {
-      enabled: true,
-      appId: "<APP_ID>",
-      appPassword: "<APP_PASSWORD>",
-      tenantId: "<TENANT_ID>",
-      webhook: { port: 3978, path: "/api/messages" },
-    },
-  },
-}
-```
-
-Environment variables: `MSTEAMS_APP_ID`, `MSTEAMS_APP_PASSWORD`, `MSTEAMS_TENANT_ID`.
-
-### Step 7: Run the Gateway
-
-The Teams channel starts automatically when the plugin is available and `msteams` config exists with credentials.
-
-</details>
-
-## Federated Authentication (Certificate + Managed Identity)
+## Federated authentication
 
 > Added in 2026.3.24
 
@@ -370,7 +268,7 @@ Use Azure Managed Identity for passwordless authentication. This is ideal for de
 - `MSTEAMS_USE_MANAGED_IDENTITY=true`
 - `MSTEAMS_MANAGED_IDENTITY_CLIENT_ID=<client-id>` (only for user-assigned)
 
-### AKS Workload Identity Setup
+### AKS workload identity setup
 
 For AKS deployments using workload identity:
 
@@ -417,55 +315,63 @@ For AKS deployments using workload identity:
 
 **Default behavior:** When `authType` is not set, OpenClaw defaults to client secret authentication. Existing configurations continue to work without changes.
 
-## Local Development (Tunneling)
+## Local development (tunneling)
 
-Teams can't reach `localhost`. Use a persistent dev tunnel so your URL stays the same across sessions:
+Teams can't reach `localhost`. Use a tunnel for local development:
+
+**Option A: ngrok**
 
 ```bash
-# One-time setup:
-devtunnel create my-openclaw-bot --allow-anonymous
-devtunnel port create my-openclaw-bot -p 3978 --protocol auto
-
-# Each dev session:
-devtunnel host my-openclaw-bot
+ngrok http 3978
+# Copy the https URL, e.g., https://abc123.ngrok.io
+# Set messaging endpoint to: https://abc123.ngrok.io/api/messages
 ```
 
-Alternatives: `ngrok http 3978` or `tailscale funnel 3978` (URLs may change each session).
-
-If your tunnel URL changes, update the endpoint:
+**Option B: Tailscale Funnel**
 
 ```bash
-teams app update <teamsAppId> --endpoint "https://<new-url>/api/messages"
+tailscale funnel 3978
+# Use your Tailscale funnel URL as the messaging endpoint
 ```
 
-## Testing the Bot
+## Teams Developer Portal (alternative)
 
-**Run diagnostics:**
+Instead of manually creating a manifest ZIP, you can use the [Teams Developer Portal](https://dev.teams.microsoft.com/apps):
 
-```bash
-teams app doctor <teamsAppId>
-```
+1. Click **+ New app**
+2. Fill in basic info (name, description, developer info)
+3. Go to **App features** → **Bot**
+4. Select **Enter a bot ID manually** and paste your Azure Bot App ID
+5. Check scopes: **Personal**, **Team**, **Group Chat**
+6. Click **Distribute** → **Download app package**
+7. In Teams: **Apps** → **Manage your apps** → **Upload a custom app** → select the ZIP
 
-Checks bot registration, AAD app, manifest, and SSO configuration in one pass.
+This is often easier than hand-editing JSON manifests.
 
-**Send a test message:**
+## Testing the bot
 
-1. Install the Teams app (use the install link from `teams app get <id> --install-link`)
+**Option A: Azure Web Chat (verify webhook first)**
+
+1. In Azure Portal → your Azure Bot resource → **Test in Web Chat**
+2. Send a message - you should see a response
+3. This confirms your webhook endpoint works before Teams setup
+
+**Option B: Teams (after app installation)**
+
+1. Install the Teams app (sideload or org catalog)
 2. Find the bot in Teams and send a DM
 3. Check gateway logs for incoming activity
 
-## Environment variables
+<Accordion title="Environment variable overrides">
 
-All config keys can be set via environment variables instead:
+Any of the bot/auth config keys can also be set via env vars:
 
-- `MSTEAMS_APP_ID`
-- `MSTEAMS_APP_PASSWORD`
-- `MSTEAMS_TENANT_ID`
-- `MSTEAMS_AUTH_TYPE` (optional: `"secret"` or `"federated"`)
-- `MSTEAMS_CERTIFICATE_PATH` (federated + certificate)
-- `MSTEAMS_CERTIFICATE_THUMBPRINT` (optional, not required for auth)
-- `MSTEAMS_USE_MANAGED_IDENTITY` (federated + managed identity)
-- `MSTEAMS_MANAGED_IDENTITY_CLIENT_ID` (user-assigned MI only)
+- `MSTEAMS_APP_ID`, `MSTEAMS_APP_PASSWORD`, `MSTEAMS_TENANT_ID`
+- `MSTEAMS_AUTH_TYPE` (`"secret"` or `"federated"`)
+- `MSTEAMS_CERTIFICATE_PATH`, `MSTEAMS_CERTIFICATE_THUMBPRINT` (federated + certificate)
+- `MSTEAMS_USE_MANAGED_IDENTITY`, `MSTEAMS_MANAGED_IDENTITY_CLIENT_ID` (federated + managed identity; client ID only for user-assigned)
+
+</Accordion>
 
 ## Member info action
 
@@ -487,7 +393,7 @@ The action is gated by `channels.msteams.actions.memberInfo` (default: enabled w
 - In other words, allowlists gate who can trigger the agent; only specific supplemental context paths are filtered today.
 - DM history can be limited with `channels.msteams.dmHistoryLimit` (user turns). Per-user overrides: `channels.msteams.dms["<user_id>"].historyLimit`.
 
-## Current Teams RSC Permissions (Manifest)
+## Current Teams RSC permissions
 
 These are the **existing resourceSpecific permissions** in our Teams app manifest. They only apply inside the team/chat where the app is installed.
 
@@ -505,13 +411,7 @@ These are the **existing resourceSpecific permissions** in our Teams app manifes
 
 - `ChatMessage.Read.Chat` (Application) - receive all group chat messages without @mention
 
-To add RSC permissions via the Teams CLI:
-
-```bash
-teams app rsc add <teamsAppId> ChannelMessage.Read.Group --type Application
-```
-
-## Example Teams Manifest (redacted)
+## Example Teams manifest
 
 Minimal, valid example with the required fields. Replace IDs and URLs.
 
@@ -573,31 +473,18 @@ Minimal, valid example with the required fields. Replace IDs and URLs.
 
 To update an already-installed Teams app (e.g., to add RSC permissions):
 
-```bash
-# Download, edit, and re-upload the manifest
-teams app manifest download <teamsAppId> manifest.json
-# Edit manifest.json locally...
-teams app manifest upload manifest.json <teamsAppId>
-# Version is auto-bumped if content changed
-```
-
-After updating, reinstall the app in each team for new permissions to take effect, and **fully quit and relaunch Teams** (not just close the window) to clear cached app metadata.
-
-<details>
-<summary>Manual manifest update (without CLI)</summary>
-
 1. Update your `manifest.json` with the new settings
 2. **Increment the `version` field** (e.g., `1.0.0` → `1.1.0`)
 3. **Re-zip** the manifest with icons (`manifest.json`, `outline.png`, `color.png`)
 4. Upload the new zip:
-   - **Teams Admin Center:** Teams apps → Manage apps → find your app → Upload new version
-   - **Sideload:** In Teams → Apps → Manage your apps → Upload a custom app
-
-</details>
+   - **Option A (Teams Admin Center):** Teams Admin Center → Teams apps → Manage apps → find your app → Upload new version
+   - **Option B (Sideload):** In Teams → Apps → Manage your apps → Upload a custom app
+5. **For team channels:** Reinstall the app in each team for new permissions to take effect
+6. **Fully quit and relaunch Teams** (not just close the window) to clear cached app metadata
 
 ## Capabilities: RSC only vs Graph
 
-### With **Teams RSC only** (app installed, no Graph API permissions)
+### Teams RSC only (no Graph API permissions)
 
 Works:
 
@@ -611,7 +498,7 @@ Does NOT work:
 - Downloading attachments stored in SharePoint/OneDrive.
 - Reading message history (beyond the live webhook event).
 
-### With **Teams RSC + Microsoft Graph Application permissions**
+### Teams RSC plus Microsoft Graph application permissions
 
 Adds:
 
@@ -643,7 +530,7 @@ If you need images/files in **channels** or want to fetch **message history**, y
 
 **Additional permission for user mentions:** User @mentions work out of the box for users in the conversation. However, if you want to dynamically search and mention users who are **not in the current conversation**, add `User.Read.All` (Application) permission and grant admin consent.
 
-## Known Limitations
+## Known limitations
 
 ### Webhook timeouts
 
@@ -665,40 +552,53 @@ Teams markdown is more limited than Slack or Discord:
 
 ## Configuration
 
-Key settings (see `/gateway/configuration` for shared channel patterns):
+Grouped settings (see `/gateway/configuration` for shared channel patterns).
 
-- `channels.msteams.enabled`: enable/disable the channel.
-- `channels.msteams.appId`, `channels.msteams.appPassword`, `channels.msteams.tenantId`: bot credentials.
-- `channels.msteams.webhook.port` (default `3978`)
-- `channels.msteams.webhook.path` (default `/api/messages`)
-- `channels.msteams.dmPolicy`: `pairing | allowlist | open | disabled` (default: pairing)
-- `channels.msteams.allowFrom`: DM allowlist (AAD object IDs recommended). The wizard resolves names to IDs during setup when Graph access is available.
-- `channels.msteams.dangerouslyAllowNameMatching`: break-glass toggle to re-enable mutable UPN/display-name matching and direct team/channel name routing.
-- `channels.msteams.textChunkLimit`: outbound text chunk size.
-- `channels.msteams.chunkMode`: `length` (default) or `newline` to split on blank lines (paragraph boundaries) before length chunking.
-- `channels.msteams.mediaAllowHosts`: allowlist for inbound attachment hosts (defaults to Microsoft/Teams domains).
-- `channels.msteams.mediaAuthAllowHosts`: allowlist for attaching Authorization headers on media retries (defaults to Graph + Bot Framework hosts).
-- `channels.msteams.requireMention`: require @mention in channels/groups (default true).
-- `channels.msteams.replyStyle`: `thread | top-level` (see [Reply Style](#reply-style-threads-vs-posts)).
-- `channels.msteams.teams.<teamId>.replyStyle`: per-team override.
-- `channels.msteams.teams.<teamId>.requireMention`: per-team override.
-- `channels.msteams.teams.<teamId>.tools`: default per-team tool policy overrides (`allow`/`deny`/`alsoAllow`) used when a channel override is missing.
-- `channels.msteams.teams.<teamId>.toolsBySender`: default per-team per-sender tool policy overrides (`"*"` wildcard supported).
-- `channels.msteams.teams.<teamId>.channels.<conversationId>.replyStyle`: per-channel override.
-- `channels.msteams.teams.<teamId>.channels.<conversationId>.requireMention`: per-channel override.
-- `channels.msteams.teams.<teamId>.channels.<conversationId>.tools`: per-channel tool policy overrides (`allow`/`deny`/`alsoAllow`).
-- `channels.msteams.teams.<teamId>.channels.<conversationId>.toolsBySender`: per-channel per-sender tool policy overrides (`"*"` wildcard supported).
-- `toolsBySender` keys should use explicit prefixes:
-  `id:`, `e164:`, `username:`, `name:` (legacy unprefixed keys still map to `id:` only).
-- `channels.msteams.actions.memberInfo`: enable or disable the Graph-backed member info action (default: enabled when Graph credentials are available).
-- `channels.msteams.authType`: authentication type — `"secret"` (default) or `"federated"`.
-- `channels.msteams.certificatePath`: path to PEM certificate file (federated + certificate auth).
-- `channels.msteams.certificateThumbprint`: certificate thumbprint (optional, not required for auth).
-- `channels.msteams.useManagedIdentity`: enable managed identity auth (federated mode).
-- `channels.msteams.managedIdentityClientId`: client ID for user-assigned managed identity.
-- `channels.msteams.sharePointSiteId`: SharePoint site ID for file uploads in group chats/channels (see [Sending files in group chats](#sending-files-in-group-chats)).
+<AccordionGroup>
+  <Accordion title="Core and webhook">
+    - `channels.msteams.enabled`
+    - `channels.msteams.appId`, `appPassword`, `tenantId`: bot credentials
+    - `channels.msteams.webhook.port` (default `3978`)
+    - `channels.msteams.webhook.path` (default `/api/messages`)
+  </Accordion>
 
-## Routing & Sessions
+  <Accordion title="Authentication">
+    - `authType`: `"secret"` (default) or `"federated"`
+    - `certificatePath`, `certificateThumbprint`: federated + certificate auth (thumbprint optional)
+    - `useManagedIdentity`, `managedIdentityClientId`: federated + managed identity auth
+  </Accordion>
+
+  <Accordion title="Access control">
+    - `dmPolicy`: `pairing | allowlist | open | disabled` (default: pairing)
+    - `allowFrom`: DM allowlist, prefer AAD object IDs; the wizard resolves names when Graph access is available
+    - `dangerouslyAllowNameMatching`: break-glass for mutable UPN/display-name and team/channel name routing
+    - `requireMention`: require @mention in channels/groups (default `true`)
+  </Accordion>
+
+  <Accordion title="Team and channel overrides">
+    All of these override the top-level defaults:
+
+    - `teams.<teamId>.replyStyle`, `.requireMention`
+    - `teams.<teamId>.tools`, `.toolsBySender`: per-team tool policy defaults
+    - `teams.<teamId>.channels.<conversationId>.replyStyle`, `.requireMention`
+    - `teams.<teamId>.channels.<conversationId>.tools`, `.toolsBySender`
+
+    `toolsBySender` keys accept `id:`, `e164:`, `username:`, `name:` prefixes (unprefixed keys map to `id:`). `"*"` is a wildcard.
+
+  </Accordion>
+
+  <Accordion title="Delivery, media, and actions">
+    - `textChunkLimit`: outbound text chunk size
+    - `chunkMode`: `length` (default) or `newline` (split on paragraph boundaries before length)
+    - `mediaAllowHosts`: inbound attachment host allowlist (defaults to Microsoft/Teams domains)
+    - `mediaAuthAllowHosts`: hosts that may receive Authorization headers on retries (defaults to Graph + Bot Framework)
+    - `replyStyle`: `thread | top-level` (see [Reply style](#reply-style-threads-vs-posts))
+    - `actions.memberInfo`: toggle the Graph-backed member info action (default on when Graph is available)
+    - `sharePointSiteId`: required for file uploads in group chats/channels (see [Sending files in group chats](#sending-files-in-group-chats))
+  </Accordion>
+</AccordionGroup>
+
+## Routing and sessions
 
 - Session keys follow the standard agent format (see [/concepts/session](/concepts/session)):
   - Direct messages share the main session (`agent:<agentId>:<mainKey>`).
@@ -706,7 +606,7 @@ Key settings (see `/gateway/configuration` for shared channel patterns):
     - `agent:<agentId>:msteams:channel:<conversationId>`
     - `agent:<agentId>:msteams:group:<conversationId>`
 
-## Reply Style: Threads vs Posts
+## Reply style: threads vs posts
 
 Teams recently introduced two channel UI styles over the same underlying data model:
 
@@ -741,7 +641,7 @@ Teams recently introduced two channel UI styles over the same underlying data mo
 }
 ```
 
-## Attachments & Images
+## Attachments and images
 
 **Current limitations:**
 
@@ -824,7 +724,7 @@ Per-user sharing is more secure as only the chat participants can access the fil
 
 Uploaded files are stored in a `/OpenClawShared/` folder in the configured SharePoint site's default document library.
 
-## Polls (Adaptive Cards)
+## Polls (adaptive cards)
 
 OpenClaw sends Teams polls as Adaptive Cards (there is no native Teams poll API).
 
@@ -833,7 +733,7 @@ OpenClaw sends Teams polls as Adaptive Cards (there is no native Teams poll API)
 - The gateway must stay online to record votes.
 - Polls do not auto-post result summaries yet (inspect the store file if needed).
 
-## Presentation Cards
+## Presentation cards
 
 Send semantic presentation payloads to Teams users or conversations using the `message` tool or CLI. OpenClaw renders them as Teams Adaptive Cards from the generic presentation contract.
 
@@ -921,7 +821,7 @@ Note: Without the `user:` prefix, names default to group/team resolution. Always
 - Proactive messages are only possible **after** a user has interacted, because we store conversation references at that point.
 - See `/gateway/configuration` for `dmPolicy` and allowlist gating.
 
-## Team and Channel IDs (Common Gotcha)
+## Team and channel IDs
 
 The `groupId` query parameter in Teams URLs is **NOT** the team ID used for configuration. Extract IDs from the URL path instead:
 
@@ -947,7 +847,7 @@ https://teams.microsoft.com/l/channel/19%3A15bc...%40thread.tacv2/ChannelName?gr
 - Channel ID = path segment after `/channel/` (URL-decoded)
 - **Ignore** the `groupId` query parameter
 
-## Private Channels
+## Private channels
 
 Bots have limited support in private channels:
 
@@ -997,12 +897,23 @@ Bots have limited support in private channels:
 - [RSC permissions reference](https://learn.microsoft.com/en-us/microsoftteams/platform/graph-api/rsc/resource-specific-consent)
 - [Teams bot file handling](https://learn.microsoft.com/en-us/microsoftteams/platform/bots/how-to/bots-filesv4) (channel/group requires Graph)
 - [Proactive messaging](https://learn.microsoft.com/en-us/microsoftteams/platform/bots/how-to/conversations/send-proactive-messages)
-- [@microsoft/teams.cli](https://www.npmjs.com/package/@microsoft/teams.cli) - Teams CLI for bot management
 
 ## Related
 
-- [Channels Overview](/channels) — all supported channels
-- [Pairing](/channels/pairing) — DM authentication and pairing flow
-- [Groups](/channels/groups) — group chat behavior and mention gating
-- [Channel Routing](/channels/channel-routing) — session routing for messages
-- [Security](/gateway/security) — access model and hardening
+<CardGroup cols={2}>
+  <Card title="Channels overview" icon="list" href="/channels">
+    All supported channels.
+  </Card>
+  <Card title="Pairing" icon="link" href="/channels/pairing">
+    DM authentication and pairing flow.
+  </Card>
+  <Card title="Groups" icon="users" href="/channels/groups">
+    Group chat behavior and mention gating.
+  </Card>
+  <Card title="Channel routing" icon="route" href="/channels/channel-routing">
+    Session routing for messages.
+  </Card>
+  <Card title="Security" icon="shield" href="/gateway/security">
+    Access model and hardening.
+  </Card>
+</CardGroup>

docs/channels/whatsapp.md

@@ -361,10 +361,9 @@ When the linked self number is also present in `allowFrom`, WhatsApp self-chat s
 
   <Accordion title="Outbound media behavior">
     - supports image, video, audio (PTT voice-note), and document payloads
-    - audio media is sent through the Baileys `audio` payload with `ptt: true`, so WhatsApp clients render it as a push-to-talk voice note
-    - reply payloads preserve `audioAsVoice`; TTS voice-note output for WhatsApp stays on this PTT path even when the provider returns MP3 or WebM
-    - native Ogg/Opus audio is sent as `audio/ogg; codecs=opus` for voice-note compatibility
-    - non-Ogg audio, including Microsoft Edge TTS MP3/WebM output, is transcoded with `ffmpeg` to 48 kHz mono Ogg/Opus before PTT delivery
+    - reply payloads preserve `audioAsVoice`; WhatsApp sends audio media as Baileys PTT voice notes
+    - non-Ogg audio, including Microsoft Edge TTS MP3/WebM output, is transcoded to Ogg/Opus before PTT delivery
+    - native Ogg/Opus audio is sent with `audio/ogg; codecs=opus` for voice-note compatibility
     - animated GIF playback is supported via `gifPlayback: true` on video sends
     - captions are applied to the first media item when sending multi-media reply payloads, except PTT voice notes send the audio first and visible text separately because WhatsApp clients do not render voice-note captions consistently
     - media source can be HTTP(S), `file://`, or local paths

docs/ci.md

@@ -98,7 +98,7 @@ Local changed-lane logic lives in `scripts/changed-lanes.mjs` and is executed by
 
 On pushes, the `checks` matrix adds the push-only `compat-node22` lane. On pull requests, that lane is skipped and the matrix stays focused on the normal test/channel lanes.
 
-The slowest Node test families are split or balanced so each job stays small without over-reserving runners: channel contracts run as three weighted shards, bundled plugin tests balance across six extension workers, small core unit lanes are paired, auto-reply runs as four balanced workers with the reply subtree split into agent-runner, dispatch, and commands/state-routing shards, and agentic gateway/plugin configs are spread across the existing source-only agentic Node jobs instead of waiting on built artifacts. Broad browser, QA, media, and miscellaneous plugin tests use their dedicated Vitest configs instead of the shared plugin catch-all. Extension shard jobs run up to two plugin config groups at a time with one Vitest worker per group and a larger Node heap so import-heavy plugin batches do not create extra CI jobs. The broad agents lane uses the shared Vitest file-parallel scheduler because it is import/scheduling dominated rather than owned by a single slow test file. `runtime-config` runs with the infra core-runtime shard to keep the shared runtime shard from owning the tail. Include-pattern shards record timing entries using the CI shard name, so `.artifacts/vitest-shard-timings.json` can distinguish a whole config from a filtered shard. `check-additional` keeps package-boundary compile/canary work together and separates runtime topology architecture from gateway watch coverage; the boundary guard shard runs its small independent guards concurrently inside one job. Gateway watch, channel tests, and the core support-boundary shard run concurrently inside `build-artifacts` after `dist/` and `dist-runtime/` are already built, keeping their old check names as lightweight verifier jobs while avoiding two extra Blacksmith workers and a second artifact-consumer queue.
+The slowest Node test families are split or balanced so each job stays small without over-reserving runners: channel contracts run as three weighted shards, bundled plugin tests balance across six extension workers, small core unit lanes are paired, auto-reply runs as three balanced workers instead of six tiny workers, and agentic gateway/plugin configs are spread across the existing source-only agentic Node jobs instead of waiting on built artifacts. Broad browser, QA, media, and miscellaneous plugin tests use their dedicated Vitest configs instead of the shared plugin catch-all. Extension shard jobs run up to two plugin config groups at a time with one Vitest worker per group and a larger Node heap so import-heavy plugin batches do not create extra CI jobs. The broad agents lane uses the shared Vitest file-parallel scheduler because it is import/scheduling dominated rather than owned by a single slow test file. `runtime-config` runs with the infra core-runtime shard to keep the shared runtime shard from owning the tail. `check-additional` keeps package-boundary compile/canary work together and separates runtime topology architecture from gateway watch coverage; the boundary guard shard runs its small independent guards concurrently inside one job. Gateway watch, channel tests, and the core support-boundary shard run concurrently inside `build-artifacts` after `dist/` and `dist-runtime/` are already built, keeping their old check names as lightweight verifier jobs while avoiding two extra Blacksmith workers and a second artifact-consumer queue.
 Android CI runs both `testPlayDebugUnitTest` and `testThirdPartyDebugUnitTest`, then builds the Play debug APK. The third-party flavor has no separate source set or manifest; its unit-test lane still compiles that flavor with the SMS/call-log BuildConfig flags, while avoiding a duplicate debug APK packaging job on every Android-relevant push.
 `extension-fast` is PR-only because push runs already execute the full bundled plugin shards. That keeps changed-plugin feedback for reviews without reserving an extra Blacksmith worker on `main` for coverage already present in `checks-node-extensions`.
 
@@ -132,10 +132,7 @@ pnpm test:channels
 pnpm test:contracts:channels
 pnpm check:docs     # docs format + lint + broken links
 pnpm build          # build dist when CI artifact/build-smoke lanes matter
-pnpm ci:timings                               # summarize the latest origin/main push CI run
-pnpm ci:timings:recent                        # compare recent successful main CI runs
 node scripts/ci-run-timings.mjs <run-id>      # summarize wall time, queue time, and slowest jobs
-node scripts/ci-run-timings.mjs --latest-main # ignore issue/comment noise and choose origin/main push CI
 node scripts/ci-run-timings.mjs --recent 10   # compare recent successful main CI runs
 pnpm test:perf:groups --full-suite --allow-failures --output .artifacts/test-perf/baseline-before.json
 pnpm test:perf:groups:compare .artifacts/test-perf/baseline-before.json .artifacts/test-perf/after-agent.json

docs/cli/browser.md

@@ -138,10 +138,6 @@ the optional label, and the raw `targetId`. Agents should pass
 `suggestedTargetId` back into `focus`, `close`, snapshots, and actions. You can
 assign a label with `open --label`, `tab new --label`, or `tab label`; labels,
 tab ids, raw target ids, and unique target-id prefixes are all accepted.
-When Chromium replaces the underlying raw target during a navigation or form
-submit, OpenClaw keeps the stable `tabId`/label attached to the replacement tab
-when it can prove the match. Raw target ids remain volatile; prefer
-`suggestedTargetId`.
 
 ## Snapshot / screenshot / actions
 
@@ -189,10 +185,6 @@ openclaw browser wait --text "Done"
 openclaw browser evaluate --fn '(el) => el.textContent' --ref <ref>
 ```
 
-Action responses return the current raw `targetId` after action-triggered page
-replacement when OpenClaw can prove the replacement tab. Scripts should still
-store and pass `suggestedTargetId`/labels for long-lived workflows.
-
 File + dialog helpers:
 
 ```bash

docs/cli/crestodian.md

@@ -239,13 +239,13 @@ Security contract for remote rescue:
   operation, where the runtime already has unsandboxed local authority.
 - Require an explicit owner identity. Rescue must not accept wildcard sender
   rules, open group policy, unauthenticated webhooks, or anonymous channels.
-- Owner DMs only by default. Group/channel rescue requires explicit opt-in.
+- Owner DMs only by default. Group/channel rescue requires explicit opt-in and
+  should still route approval prompts to the owner DM.
 - Remote rescue cannot open the local TUI or switch into an interactive agent
   session. Use local `openclaw` for agent handoff.
 - Persistent writes still require approval, even in rescue mode.
-- Audit every applied rescue operation. Message-channel rescue records channel,
-  account, sender, and source-address metadata. Config-mutating operations also
-  record config hashes before and after.
+- Audit every applied rescue operation, including channel, account, sender,
+  session key, operation, config hash before, and config hash after.
 - Never echo secrets. SecretRef inspection should report availability, not
   values.
 - If the Gateway is alive, prefer Gateway typed operations. If the Gateway is

docs/cli/cron.md

@@ -138,10 +138,6 @@ Delivery ownership note:
 - `announce` fallback-delivers the final reply only when the agent did not send
   directly to the resolved target. `webhook` posts the finished payload to a URL.
   `none` disables runner fallback delivery.
-- Reminders created from an active chat preserve the live chat delivery target
-  for fallback announce delivery. Internal session keys may be lowercase; do not
-  use them as a source of truth for case-sensitive provider IDs such as Matrix
-  room IDs.
 
 ## Common admin commands
 

docs/cli/gateway.md

@@ -188,9 +188,6 @@ Notes:
 
 - `gateway status` stays available for diagnostics even when the local CLI config is missing or invalid.
 - Default `gateway status` proves service state, WebSocket connect, and the auth capability visible at handshake time. It does not prove read/write/admin operations.
-- Diagnostic probes are non-mutating for first-time device auth: they reuse an
-  existing cached device token when one exists, but they do not create a new CLI
-  device identity or read-only device pairing record just to check status.
 - `gateway status` resolves configured auth SecretRefs for probe auth when possible.
 - If a required auth SecretRef is unresolved in this command path, `gateway status --json` reports `rpc.authWarning` when probe connectivity/auth fails; pass `--token`/`--password` explicitly or resolve the secret source first.
 - If the probe succeeds, unresolved auth-ref warnings are suppressed to avoid false positives.
@@ -228,8 +225,6 @@ Interpretation:
 - `Capability: read-only|write-capable|admin-capable|pairing-pending|connect-only` reports what the probe could prove about auth. It is separate from reachability.
 - `Read probe: ok` means read-scope detail RPC calls (`health`/`status`/`system-presence`/`config.get`) also succeeded.
 - `Read probe: limited - missing scope: operator.read` means connect succeeded but read-scope RPC is limited. This is reported as **degraded** reachability, not full failure.
-- Like `gateway status`, probe reuses existing cached device auth but does not
-  create first-time device identity or pairing state.
 - Exit code is non-zero only when no probed target is reachable.
 
 JSON notes (`--json`):

docs/cli/hooks.md

@@ -209,8 +209,7 @@ deprecation warning and forwards to `openclaw plugins install`.
 
 Npm specs are **registry-only** (package name + optional **exact version** or
 **dist-tag**). Git/URL/file specs and semver ranges are rejected. Dependency
-installs run project-local with `--ignore-scripts` for safety, even when your
-shell has global npm install settings.
+installs run with `--ignore-scripts` for safety.
 
 Bare specs and `@latest` stay on the stable track. If npm resolves either of
 those to a prerelease, OpenClaw stops and asks you to opt in explicitly with a

docs/cli/mcp.md

@@ -384,11 +384,6 @@ Important behavior:
   milliseconds of idle time (default 10 minutes; set `0` to disable) and
   one-shot embedded runs clean them up at run end
 
-Runtime adapters may normalize this shared registry into the shape their
-downstream client expects. For example, embedded Pi consumes OpenClaw
-`transport` values directly, while Claude Code and Gemini receive CLI-native
-`type` values such as `http`, `sse`, or `stdio`.
-
 ## Saved MCP server definitions
 
 OpenClaw also stores a lightweight MCP server registry in config for surfaces

docs/cli/plugins.md

@@ -109,8 +109,7 @@ visibility and per-hook enablement, not package installation.
 
 Npm specs are **registry-only** (package name + optional **exact version** or
 **dist-tag**). Git/URL/file specs and semver ranges are rejected. Dependency
-installs run project-local with `--ignore-scripts` for safety, even when your
-shell has global npm install settings.
+installs run with `--ignore-scripts` for safety.
 
 Bare specs and `@latest` stay on the stable track. If npm resolves either of
 those to a prerelease, OpenClaw stops and asks you to opt in explicitly with a
@@ -219,8 +218,7 @@ For runtime hook debugging:
   from a module-loaded inspection pass.
 - `openclaw gateway status --deep --require-rpc` confirms the reachable Gateway,
   service/process hints, config path, and RPC health.
-- Non-bundled conversation hooks (`llm_input`, `llm_output`,
-  `before_agent_finalize`, `agent_end`) require
+- Non-bundled conversation hooks (`llm_input`, `llm_output`, `agent_end`) require
   `plugins.entries.<id>.hooks.allowConversationAccess=true`.
 
 Use `--link` to avoid copying a local directory (adds to `plugins.load.paths`):
@@ -233,17 +231,19 @@ openclaw plugins install -l ./my-plugin
 source path instead of copying over a managed install target.
 
 Use `--pin` on npm installs to save the resolved exact spec (`name@version`) in
-the managed plugin index while keeping the default behavior unpinned.
+the managed install ledger while keeping the default behavior unpinned.
 
-### Plugin Index
+### Install Ledger
 
-Plugin install metadata is machine-managed state, not user config. Installs
+Plugin install metadata is machine-managed state, not user config. New installs
 and updates write it to `plugins/installs.json` under the active OpenClaw state
-directory. Its top-level `installRecords` map is the durable source of install
-metadata, including records for broken or missing plugin manifests. The
-`plugins` array is the manifest-derived cold registry cache. The file includes a
-do-not-edit warning and is used by `openclaw plugins update`, uninstall,
-diagnostics, and the cold plugin registry.
+directory. The file includes a do-not-edit warning and is used by
+`openclaw plugins update`, uninstall, diagnostics, and the cold plugin registry.
+
+Legacy `plugins.installs` entries in `openclaw.json` remain readable as a
+deprecated compatibility fallback. When install/update/uninstall paths rewrite
+plugin install state, OpenClaw writes the ledger file and removes
+`plugins.installs` from the persisted config payload.
 
 ### Uninstall
 
@@ -253,8 +253,8 @@ openclaw plugins uninstall <id> --dry-run
 openclaw plugins uninstall <id> --keep-files
 ```
 
-`uninstall` removes plugin records from `plugins.entries`, the persisted plugin
-index, the plugin allowlist, and linked `plugins.load.paths` entries when
+`uninstall` removes plugin records from `plugins.entries`, the managed install
+ledger, the plugin allowlist, and linked `plugins.load.paths` entries when
 applicable.
 For active memory plugins, the memory slot resets to `memory-core`.
 
@@ -274,7 +274,7 @@ openclaw plugins update @openclaw/voice-call@beta
 openclaw plugins update openclaw-codex-app-server --dangerously-force-unsafe-install
 ```
 
-Updates apply to tracked plugin installs in the managed plugin index and
+Updates apply to tracked plugin installs in the managed install ledger and
 tracked hook-pack installs in `hooks.internal.installs`.
 
 When you pass a plugin id, OpenClaw reuses the recorded install spec for that
@@ -364,8 +364,8 @@ Normal startup, provider owner lookup, channel setup classification, and plugin
 inventory can read it without importing plugin runtime modules.
 
 Use `plugins registry` to inspect whether the persisted registry is present,
-current, or stale. Use `--refresh` to rebuild it from the persisted plugin
-index, config policy, and manifest/package metadata. This is a repair path, not
+current, or stale. Use `--refresh` to rebuild it from the durable install
+ledger, config policy, and manifest/package metadata. This is a repair path, not
 a runtime activation path.
 
 `OPENCLAW_DISABLE_PERSISTED_PLUGIN_REGISTRY=1` is a deprecated break-glass

docs/concepts/agent-runtimes.md

@@ -46,20 +46,6 @@ That means OpenClaw selects an OpenAI model ref, then asks the Codex app-server
 runtime to run the embedded agent turn. It does not mean the channel, model
 provider catalog, or OpenClaw session store becomes Codex.
 
-When the bundled `codex` plugin is enabled, natural-language Codex control
-should use the native `/codex` command surface (`/codex bind`, `/codex threads`,
-`/codex resume`, `/codex steer`, `/codex stop`) instead of ACP. Use ACP for
-Codex only when the user explicitly asks for ACP/acpx or is testing the ACP
-adapter path. Claude Code, Gemini CLI, OpenCode, Cursor, and similar external
-harnesses still use ACP.
-
-| You mean...                             | Use...                                       |
-| --------------------------------------- | -------------------------------------------- |
-| Codex app-server chat/thread control    | `/codex ...` from the bundled `codex` plugin |
-| Codex app-server embedded agent runtime | `embeddedHarness.runtime: "codex"`           |
-| OpenAI Codex OAuth on the PI runner     | `openai-codex/*` model refs                  |
-| Claude Code or other external harness   | ACP/acpx                                     |
-
 For the OpenAI-family prefix split, see [OpenAI](/providers/openai) and
 [Model providers](/concepts/model-providers). For the Codex runtime support
 contract, see [Codex harness](/plugins/codex-harness#v1-support-contract).

docs/concepts/memory-search.md

@@ -135,11 +135,6 @@ earlier conversations. This is opt-in via
 **Only keyword matches?** Your embedding provider may not be configured. Check
 `openclaw memory status --deep`.
 
-**Local embeddings time out?** `ollama`, `lmstudio`, and `local` use a longer
-inline batch timeout by default. If the host is simply slow, set
-`agents.defaults.memorySearch.sync.embeddingBatchTimeoutSeconds` and rerun
-`openclaw memory index --force`.
-
 **CJK text not found?** Rebuild the FTS index with
 `openclaw memory index --force`.
 

docs/concepts/qa-e2e-automation.md

@@ -50,21 +50,6 @@ pnpm qa:lab:watch
 rebuilds that bundle on change, and the browser auto-reloads when the QA Lab
 asset hash changes.
 
-For a local OpenTelemetry trace smoke, run:
-
-```bash
-pnpm qa:otel:smoke
-```
-
-That script starts a local OTLP/HTTP trace receiver, runs the
-`otel-trace-smoke` QA scenario with the `diagnostics-otel` plugin enabled, then
-decodes the exported protobuf spans and asserts the release-critical shape:
-`openclaw.run`, `openclaw.model.call`, `openclaw.context.assembled`, and
-`openclaw.message.delivery` must be present; model calls must not export
-`StreamAbandoned` on successful turns; raw diagnostic IDs and
-`openclaw.content.*` attributes must stay out of the trace. It writes
-`otel-smoke-summary.json` next to the QA suite artifacts.
-
 For a transport-real Matrix smoke lane, run:
 
 ```bash

docs/concepts/session-pruning.md

@@ -35,23 +35,15 @@ cache-write size, directly lowering cost.
 
 ## Legacy image cleanup
 
-OpenClaw also builds a separate idempotent replay view for sessions that
-persist raw image blocks or prompt-hydration media markers in history.
+OpenClaw also runs a separate idempotent cleanup for older legacy sessions that
+persisted raw image blocks in history.
 
 - It preserves the **3 most recent completed turns** byte-for-byte so prompt
   cache prefixes for recent follow-ups stay stable.
-- In the replay view, older already-processed image blocks from `user` or
-  `toolResult` history can be replaced with
-  `[image data removed - already processed by model]`.
-- Older textual media references such as `[media attached: ...]`,
-  `[Image: source: ...]`, and `media://inbound/...` can be replaced with
-  `[media reference removed - already processed by model]`. Current-turn
-  attachment markers stay intact so vision models can still hydrate fresh
-  images.
-- The raw session transcript is not rewritten, so history viewers can still
-  render the original message entries and their images.
+- Older already-processed image blocks in `user` or `toolResult` history can be
+  replaced with `[image data removed - already processed by model]`.
 - This is separate from normal cache-TTL pruning. It exists to stop repeated
-  image payloads or stale media refs from busting prompt caches on later turns.
+  image payloads from busting prompt caches on later turns.
 
 ## Smart defaults
 

docs/concepts/session.md

@@ -3,7 +3,6 @@ summary: "How OpenClaw manages conversation sessions"
 read_when:
   - You want to understand session routing and isolation
   - You want to configure DM scope for multi-user setups
-  - You are debugging daily or idle session resets
 title: "Session management"
 ---
 
@@ -60,21 +59,13 @@ Verify your setup with `openclaw security audit`.
 Sessions are reused until they expire:
 
 - **Daily reset** (default) -- new session at 4:00 AM local time on the gateway
-  host. Daily freshness is based on when the current `sessionId` started, not
-  on later metadata writes.
+  host.
 - **Idle reset** (optional) -- new session after a period of inactivity. Set
-  `session.reset.idleMinutes`. Idle freshness is based on the last real
-  user/channel interaction, so heartbeat, cron, and exec system events do not
-  keep the session alive.
+  `session.reset.idleMinutes`.
 - **Manual reset** -- type `/new` or `/reset` in chat. `/new <model>` also
   switches the model.
 
 When both daily and idle resets are configured, whichever expires first wins.
-Heartbeat, cron, exec, and other system-event turns may write session metadata,
-but those writes do not extend daily or idle reset freshness. When a reset
-rolls the session, queued system-event notices for the old session are
-discarded so stale background updates are not prepended to the first prompt in
-the new session.
 
 Sessions with an active provider-owned CLI session are not cut by the implicit
 daily default. Use `/reset` or configure `session.reset` explicitly when those
@@ -88,18 +79,6 @@ session data.
 - **Store:** `~/.openclaw/agents/<agentId>/sessions/sessions.json`
 - **Transcripts:** `~/.openclaw/agents/<agentId>/sessions/<sessionId>.jsonl`
 
-`sessions.json` keeps separate lifecycle timestamps:
-
-- `sessionStartedAt`: when the current `sessionId` began; daily reset uses this.
-- `lastInteractionAt`: last user/channel interaction that extends idle lifetime.
-- `updatedAt`: last store-row mutation; useful for listing and pruning, but not
-  authoritative for daily/idle reset freshness.
-
-Older rows without `sessionStartedAt` are resolved from the transcript JSONL
-session header when available. If an older row also lacks `lastInteractionAt`,
-idle freshness falls back to that session start time, not to later bookkeeping
-writes.
-
 ## Session maintenance
 
 OpenClaw automatically bounds session storage over time. By default, it runs

docs/docs.json

@@ -1301,7 +1301,6 @@
                   "providers/bedrock-mantle",
                   "providers/anthropic",
                   "providers/arcee",
-                  "providers/azure-speech",
                   "providers/chutes",
                   "providers/claude-max-api-proxy",
                   "providers/cloudflare-ai-gateway",
@@ -1318,7 +1317,6 @@
                   "providers/groq",
                   "providers/huggingface",
                   "providers/inferrs",
-                  "providers/inworld",
                   "providers/kilocode",
                   "providers/litellm",
                   "providers/lmstudio",
@@ -1437,12 +1435,11 @@
                     "group": "Health and diagnostics",
                     "pages": [
                       "gateway/health",
+                      "gateway/diagnostics",
                       "gateway/heartbeat",
                       "gateway/doctor",
-                      "logging",
-                      "gateway/opentelemetry",
                       "gateway/logging",
-                      "gateway/diagnostics",
+                      "logging",
                       "gateway/troubleshooting"
                     ]
                   },

docs/gateway/bonjour.md

@@ -139,7 +139,6 @@ The Gateway writes a rolling log file (printed on startup as
 - `bonjour: advertise failed ...`
 - `bonjour: ... name conflict resolved` / `hostname conflict resolved`
 - `bonjour: watchdog detected non-announced service ...`
-- `bonjour: disabling advertiser after ... failed restarts ...`
 
 ## Debugging on iOS node
 
@@ -156,10 +155,6 @@ The log includes browser state transitions and result‑set changes.
 
 - **Bonjour doesn’t cross networks**: use Tailnet or SSH.
 - **Multicast blocked**: some Wi‑Fi networks disable mDNS.
-- **Advertiser stuck in probing/announcing**: hosts with blocked multicast,
-  container bridges, WSL, or interface churn can leave the ciao advertiser in a
-  non-announced state. OpenClaw retries a few times and then disables Bonjour
-  for the current Gateway process instead of restarting the advertiser forever.
 - **Sleep / interface churn**: macOS may temporarily drop mDNS results; retry.
 - **Browse works but resolve fails**: keep machine names simple (avoid emojis or
   punctuation), then restart the Gateway. The service instance name derives from

docs/gateway/config-agents.md

@@ -899,14 +899,6 @@ scripts/sandbox-browser-setup.sh   # optional browser image
 
 ### `agents.list` (per-agent overrides)
 
-Use `agents.list[].tts` to give an agent its own TTS provider, voice, model,
-style, or auto-TTS mode. The agent block deep-merges over global
-`messages.tts`, so shared credentials can stay in one place while individual
-agents override only the voice or provider fields they need. The active agent's
-override applies to automatic spoken replies, `/tts audio`, `/tts status`, and
-the `tts` agent tool. See [Text-to-speech](/tools/tts#per-agent-voice-overrides)
-for provider examples and precedence.
-
 ```json5
 {
   agents: {
@@ -923,11 +915,6 @@ for provider examples and precedence.
         fastModeDefault: false, // per-agent fast mode override
         embeddedHarness: { runtime: "auto", fallback: "pi" },
         params: { cacheRetention: "none" }, // overrides matching defaults.models params by key
-        tts: {
-          providers: {
-            elevenlabs: { voiceId: "EXAVITQu4vr4xnSDxMaL" },
-          },
-        },
         skills: ["docs-search"], // replaces agents.defaults.skills when set
         identity: {
           name: "Samantha",
@@ -963,7 +950,6 @@ for provider examples and precedence.
 - `default`: when multiple are set, first wins (warning logged). If none set, first list entry is default.
 - `model`: string form overrides `primary` only; object form `{ primary, fallbacks }` overrides both (`[]` disables global fallbacks). Cron jobs that only override `primary` still inherit default fallbacks unless you set `fallbacks: []`.
 - `params`: per-agent stream params merged over the selected model entry in `agents.defaults.models`. Use this for agent-specific overrides like `cacheRetention`, `temperature`, or `maxTokens` without duplicating the whole model catalog.
-- `tts`: optional per-agent text-to-speech overrides. The block deep-merges over `messages.tts`, so keep shared provider credentials and fallback policy in `messages.tts` and set only persona-specific values such as provider, voice, model, style, or auto mode here.
 - `skills`: optional per-agent skill allowlist. If omitted, the agent inherits `agents.defaults.skills` when set; an explicit list replaces defaults instead of merging, and `[]` means no skills.
 - `thinkingDefault`: optional per-agent default thinking level (`off | minimal | low | medium | high | xhigh | adaptive | max`). Overrides `agents.defaults.thinkingDefault` for this agent when no per-message or session override is set. The selected provider/model profile controls which values are valid; for Google Gemini, `adaptive` keeps provider-owned dynamic thinking (`thinkingLevel` omitted on Gemini 3/3.1, `thinkingBudget: -1` on Gemini 2.5).
 - `reasoningDefault`: optional per-agent default reasoning visibility (`on | off | stream`). Applies when no per-message or session reasoning override is set.
@@ -1176,7 +1162,7 @@ See [Multi-Agent Sandbox & Tools](/tools/multi-agent-sandbox-tools) for preceden
   - `per-channel-peer`: isolate per channel + sender (recommended for multi-user inboxes).
   - `per-account-channel-peer`: isolate per account + channel + sender (recommended for multi-account).
 - **`identityLinks`**: map canonical ids to provider-prefixed peers for cross-channel session sharing.
-- **`reset`**: primary reset policy. `daily` resets at `atHour` local time; `idle` resets after `idleMinutes`. When both configured, whichever expires first wins. Daily reset freshness uses the session row's `sessionStartedAt`; idle reset freshness uses `lastInteractionAt`. Background/system-event writes such as heartbeat, cron wakeups, exec notifications, and gateway bookkeeping can update `updatedAt`, but they do not keep daily/idle sessions fresh.
+- **`reset`**: primary reset policy. `daily` resets at `atHour` local time; `idle` resets after `idleMinutes`. When both configured, whichever expires first wins.
 - **`resetByType`**: per-type overrides (`direct`, `group`, `thread`). Legacy `dm` accepted as alias for `direct`.
 - **`parentForkMaxTokens`**: max parent-session `totalTokens` allowed when creating a forked thread session (default `100000`).
   - If parent `totalTokens` is above this value, OpenClaw starts a fresh thread session instead of inheriting parent transcript history.
@@ -1346,7 +1332,6 @@ Defaults for Talk mode (macOS/iOS/Android).
       },
       system: {},
     },
-    speechLocale: "ru-RU",
     silenceTimeoutMs: 1500,
     interruptOnSpeech: true,
   },
@@ -1361,7 +1346,6 @@ Defaults for Talk mode (macOS/iOS/Android).
 - `providers.*.voiceAliases` lets Talk directives use friendly names.
 - `providers.mlx.modelId` selects the Hugging Face repo used by the macOS local MLX helper. If omitted, macOS uses `mlx-community/Soprano-80M-bf16`.
 - macOS MLX playback runs through the bundled `openclaw-mlx-tts` helper when present, or an executable on `PATH`; `OPENCLAW_MLX_TTS_BIN` overrides the helper path for development.
-- `speechLocale` sets the BCP 47 locale id used by iOS/macOS Talk speech recognition. Leave unset to use the device default.
 - `silenceTimeoutMs` controls how long Talk mode waits after user silence before it sends the transcript. Unset keeps the platform default pause window (`700 ms on macOS and Android, 900 ms on iOS`).
 
 ---

docs/gateway/configuration-reference.md

@@ -43,7 +43,6 @@ Moved to a dedicated page — see
 - `session.*` (session lifecycle, compaction, pruning)
 - `messages.*` (message delivery, TTS, markdown rendering)
 - `talk.*` (Talk mode)
-  - `talk.speechLocale`: optional BCP 47 locale id for Talk speech recognition on iOS/macOS
   - `talk.silenceTimeoutMs`: when unset, Talk keeps the platform default pause window before sending the transcript (`700 ms on macOS and Android, 900 ms on iOS`)
 
 ## Tools and custom providers
@@ -160,7 +159,7 @@ See [MCP](/cli/mcp#openclaw-as-an-mcp-client-registry) and
 - `plugins.entries.<id>.apiKey`: plugin-level API key convenience field (when supported by the plugin).
 - `plugins.entries.<id>.env`: plugin-scoped env var map.
 - `plugins.entries.<id>.hooks.allowPromptInjection`: when `false`, core blocks `before_prompt_build` and ignores prompt-mutating fields from legacy `before_agent_start`, while preserving legacy `modelOverride` and `providerOverride`. Applies to native plugin hooks and supported bundle-provided hook directories.
-- `plugins.entries.<id>.hooks.allowConversationAccess`: when `true`, trusted non-bundled plugins may read raw conversation content from typed hooks such as `llm_input`, `llm_output`, `before_agent_finalize`, and `agent_end`.
+- `plugins.entries.<id>.hooks.allowConversationAccess`: when `true`, trusted non-bundled plugins may read raw conversation content from typed hooks such as `llm_input`, `llm_output`, and `agent_end`.
 - `plugins.entries.<id>.subagent.allowModelOverride`: explicitly trust this plugin to request per-run `provider` and `model` overrides for background subagent runs.
 - `plugins.entries.<id>.subagent.allowedModels`: optional allowlist of canonical `provider/model` targets for trusted subagent overrides. Use `"*"` only when you intentionally want to allow any model.
 - `plugins.entries.<id>.config`: plugin-defined config object (validated by native OpenClaw plugin schema when available).
@@ -187,6 +186,14 @@ See [MCP](/cli/mcp#openclaw-as-an-mcp-client-registry) and
 - Enabled Claude bundle plugins can also contribute embedded Pi defaults from `settings.json`; OpenClaw applies those as sanitized agent settings, not as raw OpenClaw config patches.
 - `plugins.slots.memory`: pick the active memory plugin id, or `"none"` to disable memory plugins.
 - `plugins.slots.contextEngine`: pick the active context engine plugin id; defaults to `"legacy"` unless you install and select another engine.
+- `plugins.installs`: deprecated compatibility fallback for legacy
+  CLI-managed install metadata. New plugin installs write the managed
+  `plugins/installs.json` state ledger instead.
+  - Legacy records include `source`, `spec`, `sourcePath`, `installPath`,
+    `version`, `resolvedName`, `resolvedVersion`, `resolvedSpec`, `integrity`,
+    `shasum`, `resolvedAt`, `installedAt`.
+  - Treat `plugins.installs.*` as managed state; prefer CLI commands over
+    manual edits.
 
 See [Plugins](/tools/plugin).
 
@@ -869,9 +876,6 @@ Notes:
     otel: {
       enabled: false,
       endpoint: "https://otel-collector.example.com:4318",
-      tracesEndpoint: "https://traces.example.com/v1/traces",
-      metricsEndpoint: "https://metrics.example.com/v1/metrics",
-      logsEndpoint: "https://logs.example.com/v1/logs",
       protocol: "http/protobuf", // http/protobuf | grpc
       headers: { "x-tenant-id": "my-org" },
       serviceName: "openclaw-gateway",
@@ -904,9 +908,8 @@ Notes:
 - `enabled`: master toggle for instrumentation output (default: `true`).
 - `flags`: array of flag strings enabling targeted log output (supports wildcards like `"telegram.*"` or `"*"`).
 - `stuckSessionWarnMs`: age threshold in ms for emitting stuck-session warnings while a session remains in processing state.
-- `otel.enabled`: enables the OpenTelemetry export pipeline (default: `false`). For the full configuration, signal catalog, and privacy model, see [OpenTelemetry export](/gateway/opentelemetry).
+- `otel.enabled`: enables the OpenTelemetry export pipeline (default: `false`).
 - `otel.endpoint`: collector URL for OTel export.
-- `otel.tracesEndpoint` / `otel.metricsEndpoint` / `otel.logsEndpoint`: optional signal-specific OTLP endpoints. When set, they override `otel.endpoint` for that signal only.
 - `otel.protocol`: `"http/protobuf"` (default) or `"grpc"`.
 - `otel.headers`: extra HTTP/gRPC metadata headers sent with OTel export requests.
 - `otel.serviceName`: service name for resource attributes.
@@ -916,7 +919,6 @@ Notes:
 - `otel.captureContent`: opt-in raw content capture for OTEL span attributes. Defaults to off. Boolean `true` captures non-system message/tool content; the object form lets you enable `inputMessages`, `outputMessages`, `toolInputs`, `toolOutputs`, and `systemPrompt` explicitly.
 - `OTEL_SEMCONV_STABILITY_OPT_IN=gen_ai_latest_experimental`: environment toggle for latest experimental GenAI span provider attributes. By default spans keep the legacy `gen_ai.system` attribute for compatibility; GenAI metrics use bounded semantic attributes.
 - `OPENCLAW_OTEL_PRELOADED=1`: environment toggle for hosts that already registered a global OpenTelemetry SDK. OpenClaw then skips plugin-owned SDK startup/shutdown while keeping diagnostic listeners active.
-- `OTEL_EXPORTER_OTLP_TRACES_ENDPOINT`, `OTEL_EXPORTER_OTLP_METRICS_ENDPOINT`, and `OTEL_EXPORTER_OTLP_LOGS_ENDPOINT`: signal-specific endpoint env vars used when the matching config key is unset.
 - `cacheTrace.enabled`: log cache trace snapshots for embedded runs (default: `false`).
 - `cacheTrace.filePath`: output path for cache trace JSONL (default: `$OPENCLAW_STATE_DIR/logs/cache-trace.jsonl`).
 - `cacheTrace.includeMessages` / `includePrompt` / `includeSystem`: control what is included in cache trace output (all default: `true`).
@@ -955,7 +957,7 @@ Notes:
 ```json5
 {
   acp: {
-    enabled: true,
+    enabled: false,
     dispatch: { enabled: true },
     backend: "acpx",
     defaultAgent: "main",
@@ -979,10 +981,9 @@ Notes:
 }
 ```
 
-- `enabled`: global ACP feature gate (default: `true`; set `false` to hide ACP dispatch and spawn affordances).
+- `enabled`: global ACP feature gate (default: `false`).
 - `dispatch.enabled`: independent gate for ACP session turn dispatch (default: `true`). Set `false` to keep ACP commands available while blocking execution.
 - `backend`: default ACP runtime backend id (must match a registered ACP runtime plugin).
-  If `plugins.allow` is set, include the backend plugin id (for example `acpx`) or the bundled default plugin will not load.
 - `defaultAgent`: fallback ACP target agent id when spawns do not specify an explicit target.
 - `allowedAgents`: allowlist of agent ids permitted for ACP runtime sessions; empty means no additional restriction.
 - `maxConcurrentSessions`: maximum concurrently active ACP sessions.

docs/gateway/diagnostics.md

@@ -129,10 +129,9 @@ diagnostic event collection:
 Disabling diagnostics reduces bug-report detail. It does not affect normal
 Gateway logging.
 
-## Related
+## Related docs
 
-- [Health checks](/gateway/health)
+- [Health Checks](/gateway/health)
 - [Gateway CLI](/cli/gateway#gateway-diagnostics-export)
-- [Gateway protocol](/gateway/protocol#system-and-identity)
+- [Gateway Protocol](/gateway/protocol#system-and-identity)
 - [Logging](/logging)
-- [OpenTelemetry export](/gateway/opentelemetry) — separate flow for streaming diagnostics to a collector

docs/gateway/doctor.md

@@ -70,7 +70,6 @@ cat ~/.openclaw/openclaw.json
 - Legacy plugin manifest contract key migration (`speechProviders`, `realtimeTranscriptionProviders`, `realtimeVoiceProviders`, `mediaUnderstandingProviders`, `imageGenerationProviders`, `videoGenerationProviders`, `webFetchProviders`, `webSearchProviders` → `contracts`).
 - Legacy cron store migration (`jobId`, `schedule.cron`, top-level delivery/payload fields, payload `provider`, simple `notify: true` webhook fallback jobs).
 - Session lock file inspection and stale lock cleanup.
-- Session transcript repair for duplicated prompt-rewrite branches created by affected 2026.4.24 builds.
 - State integrity and permissions checks (sessions, transcripts, state dir).
 - Config file permission checks (chmod 600) when running locally.
 - Model auth health: checks OAuth expiry, can refresh expiring tokens, and reports auth-profile cooldown/disabled states.
@@ -318,15 +317,6 @@ considered stale (dead PID or older than 30 minutes). In `--fix` / `--repair`
 mode it removes stale lock files automatically; otherwise it prints a note and
 instructs you to rerun with `--fix`.
 
-### 3d) Session transcript branch repair
-
-Doctor scans agent session JSONL files for the duplicated branch shape created
-by the 2026.4.24 prompt transcript rewrite bug: an abandoned user turn with
-OpenClaw internal runtime context plus an active sibling containing the same
-visible user prompt. In `--fix` / `--repair` mode, doctor backs up each affected
-file next to the original and rewrites the transcript to the active branch so
-gateway history and memory readers no longer see duplicate turns.
-
 ### 4) State integrity checks (session persistence, routing, and safety)
 
 The state directory is the operational brainstem. If it vanishes, you lose

docs/gateway/heartbeat.md

@@ -263,9 +263,8 @@ Use `accountId` to target a specific account on multi-account channels like Tele
 - If the resolved heartbeat target supports typing, OpenClaw shows typing while
   the heartbeat run is active. This uses the same target the heartbeat would
   send chat output to, and it is disabled by `typingMode: "never"`.
-- Heartbeat-only replies do **not** keep the session alive. Heartbeat metadata
-  may update the session row, but idle expiry uses `lastInteractionAt` from the
-  last real user/channel message, and daily expiry uses `sessionStartedAt`.
+- Heartbeat-only replies do **not** keep the session alive; the last `updatedAt`
+  is restored so idle expiry behaves normally.
 - Control UI and WebChat history hide heartbeat prompts and OK-only
   acknowledgments. The underlying session transcript can still contain those
   turns for audit/replay.

docs/gateway/index.md

@@ -112,12 +112,6 @@ All of these run on the main Gateway port and use the same trusted operator auth
 | Gateway port | `--port` → `OPENCLAW_GATEWAY_PORT` → `gateway.port` → `18789` |
 | Bind mode    | CLI/override → `gateway.bind` → `loopback`                    |
 
-Gateway startup uses the same effective port and bind when it seeds local
-Control UI origins for non-loopback binds. For example, `--bind lan --port 3000`
-seeds `http://localhost:3000` and `http://127.0.0.1:3000` before runtime
-validation runs. Add any remote browser origins, such as HTTPS proxy URLs, to
-`gateway.controlUi.allowedOrigins` explicitly.
-
 ### Hot reload modes
 
 | `gateway.reload.mode` | Behavior                                   |

docs/gateway/logging.md

@@ -114,6 +114,5 @@ This keeps existing file logs stable while making interactive output scannable.
 
 ## Related
 
-- [Logging](/logging)
-- [OpenTelemetry export](/gateway/opentelemetry)
+- [Logging overview](/logging)
 - [Diagnostics export](/gateway/diagnostics)

docs/gateway/opentelemetry.md

@@ -1,308 +0,0 @@
----
-summary: "Export OpenClaw diagnostics to any OpenTelemetry collector via the diagnostics-otel plugin (OTLP/HTTP)"
-title: "OpenTelemetry export"
-read_when:
-  - You want to send OpenClaw model usage, message flow, or session metrics to an OpenTelemetry collector
-  - You are wiring traces, metrics, or logs into Grafana, Datadog, Honeycomb, New Relic, Tempo, or another OTLP backend
-  - You need the exact metric names, span names, or attribute shapes to build dashboards or alerts
----
-
-OpenClaw exports diagnostics through the bundled `diagnostics-otel` plugin
-using **OTLP/HTTP (protobuf)**. Any collector or backend that accepts OTLP/HTTP
-works without code changes. For local file logs and how to read them, see
-[Logging](/logging).
-
-## How it fits together
-
-- **Diagnostics events** are structured, in-process records emitted by the
-  Gateway and bundled plugins for model runs, message flow, sessions, queues,
-  and exec.
-- **`diagnostics-otel` plugin** subscribes to those events and exports them as
-  OpenTelemetry **metrics**, **traces**, and **logs** over OTLP/HTTP.
-- Exporters only attach when both the diagnostics surface and the plugin are
-  enabled, so the in-process cost stays near zero by default.
-
-## Quick start
-
-```json5
-{
-  plugins: {
-    allow: ["diagnostics-otel"],
-    entries: {
-      "diagnostics-otel": { enabled: true },
-    },
-  },
-  diagnostics: {
-    enabled: true,
-    otel: {
-      enabled: true,
-      endpoint: "http://otel-collector:4318",
-      protocol: "http/protobuf",
-      serviceName: "openclaw-gateway",
-      traces: true,
-      metrics: true,
-      logs: true,
-      sampleRate: 0.2,
-      flushIntervalMs: 60000,
-    },
-  },
-}
-```
-
-You can also enable the plugin from the CLI:
-
-```bash
-openclaw plugins enable diagnostics-otel
-```
-
-<Note>
-`protocol` currently supports `http/protobuf` only. `grpc` is ignored.
-</Note>
-
-## Signals exported
-
-| Signal      | What goes in it                                                                                                                   |
-| ----------- | --------------------------------------------------------------------------------------------------------------------------------- |
-| **Metrics** | Counters and histograms for token usage, cost, run duration, message flow, queue lanes, session state, exec, and memory pressure. |
-| **Traces**  | Spans for model usage, model calls, tool execution, exec, webhook/message processing, context assembly, and tool loops.           |
-| **Logs**    | Structured `logging.file` records exported over OTLP when `diagnostics.otel.logs` is enabled.                                     |
-
-Toggle `traces`, `metrics`, and `logs` independently. All three default to on
-when `diagnostics.otel.enabled` is true.
-
-## Configuration reference
-
-```json5
-{
-  diagnostics: {
-    enabled: true,
-    otel: {
-      enabled: true,
-      endpoint: "http://otel-collector:4318",
-      tracesEndpoint: "http://otel-collector:4318/v1/traces",
-      metricsEndpoint: "http://otel-collector:4318/v1/metrics",
-      logsEndpoint: "http://otel-collector:4318/v1/logs",
-      protocol: "http/protobuf", // grpc is ignored
-      serviceName: "openclaw-gateway",
-      headers: { "x-collector-token": "..." },
-      traces: true,
-      metrics: true,
-      logs: true,
-      sampleRate: 0.2, // root-span sampler, 0.0..1.0
-      flushIntervalMs: 60000, // metric export interval (min 1000ms)
-      captureContent: {
-        enabled: false,
-        inputMessages: false,
-        outputMessages: false,
-        toolInputs: false,
-        toolOutputs: false,
-        systemPrompt: false,
-      },
-    },
-  },
-}
-```
-
-### Environment variables
-
-| Variable                                                                                                          | Purpose                                                                                                                                                                                                                                    |
-| ----------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| `OTEL_EXPORTER_OTLP_ENDPOINT`                                                                                     | Override `diagnostics.otel.endpoint`. If the value already contains `/v1/traces`, `/v1/metrics`, or `/v1/logs`, it is used as-is.                                                                                                          |
-| `OTEL_EXPORTER_OTLP_TRACES_ENDPOINT` / `OTEL_EXPORTER_OTLP_METRICS_ENDPOINT` / `OTEL_EXPORTER_OTLP_LOGS_ENDPOINT` | Signal-specific endpoint overrides used when the matching `diagnostics.otel.*Endpoint` config key is unset. Signal-specific config wins over signal-specific env, which wins over the shared endpoint.                                     |
-| `OTEL_SERVICE_NAME`                                                                                               | Override `diagnostics.otel.serviceName`.                                                                                                                                                                                                   |
-| `OTEL_EXPORTER_OTLP_PROTOCOL`                                                                                     | Override the wire protocol (only `http/protobuf` is honored today).                                                                                                                                                                        |
-| `OTEL_SEMCONV_STABILITY_OPT_IN`                                                                                   | Set to `gen_ai_latest_experimental` to emit the latest experimental GenAI span attribute (`gen_ai.provider.name`) instead of the legacy `gen_ai.system`. GenAI metrics always use bounded, low-cardinality semantic attributes regardless. |
-| `OPENCLAW_OTEL_PRELOADED`                                                                                         | Set to `1` when another preload or host process already registered the global OpenTelemetry SDK. The plugin then skips its own NodeSDK lifecycle but still wires diagnostic listeners and honors `traces`/`metrics`/`logs`.                |
-
-## Privacy and content capture
-
-Raw model/tool content is **not** exported by default. Spans carry bounded
-identifiers (channel, provider, model, error category, hash-only request ids)
-and never include prompt text, response text, tool inputs, tool outputs, or
-session keys.
-
-Set `diagnostics.otel.captureContent.*` to `true` only when your collector and
-retention policy are approved for prompt, response, tool, or system-prompt
-text. Each subkey is opt-in independently:
-
-- `inputMessages` — user prompt content.
-- `outputMessages` — model response content.
-- `toolInputs` — tool argument payloads.
-- `toolOutputs` — tool result payloads.
-- `systemPrompt` — assembled system/developer prompt.
-
-When any subkey is enabled, model and tool spans get bounded, redacted
-`openclaw.content.*` attributes for that class only.
-
-## Sampling and flushing
-
-- **Traces:** `diagnostics.otel.sampleRate` (root-span only, `0.0` drops all,
-  `1.0` keeps all).
-- **Metrics:** `diagnostics.otel.flushIntervalMs` (minimum `1000`).
-- **Logs:** OTLP logs respect `logging.level` (file log level). Console
-  redaction does **not** apply to OTLP logs. High-volume installs should
-  prefer OTLP collector sampling/filtering over local sampling.
-
-## Exported metrics
-
-### Model usage
-
-- `openclaw.tokens` (counter, attrs: `openclaw.token`, `openclaw.channel`, `openclaw.provider`, `openclaw.model`)
-- `openclaw.cost.usd` (counter, attrs: `openclaw.channel`, `openclaw.provider`, `openclaw.model`)
-- `openclaw.run.duration_ms` (histogram, attrs: `openclaw.channel`, `openclaw.provider`, `openclaw.model`)
-- `openclaw.context.tokens` (histogram, attrs: `openclaw.context`, `openclaw.channel`, `openclaw.provider`, `openclaw.model`)
-- `gen_ai.client.token.usage` (histogram, GenAI semantic-conventions metric, attrs: `gen_ai.token.type` = `input`/`output`, `gen_ai.provider.name`, `gen_ai.operation.name`, `gen_ai.request.model`)
-- `gen_ai.client.operation.duration` (histogram, seconds, GenAI semantic-conventions metric, attrs: `gen_ai.provider.name`, `gen_ai.operation.name`, `gen_ai.request.model`, optional `error.type`)
-
-### Message flow
-
-- `openclaw.webhook.received` (counter, attrs: `openclaw.channel`, `openclaw.webhook`)
-- `openclaw.webhook.error` (counter, attrs: `openclaw.channel`, `openclaw.webhook`)
-- `openclaw.webhook.duration_ms` (histogram, attrs: `openclaw.channel`, `openclaw.webhook`)
-- `openclaw.message.queued` (counter, attrs: `openclaw.channel`, `openclaw.source`)
-- `openclaw.message.processed` (counter, attrs: `openclaw.channel`, `openclaw.outcome`)
-- `openclaw.message.duration_ms` (histogram, attrs: `openclaw.channel`, `openclaw.outcome`)
-- `openclaw.message.delivery.started` (counter, attrs: `openclaw.channel`, `openclaw.delivery.kind`)
-- `openclaw.message.delivery.duration_ms` (histogram, attrs: `openclaw.channel`, `openclaw.delivery.kind`, `openclaw.outcome`, `openclaw.errorCategory`)
-
-### Queues and sessions
-
-- `openclaw.queue.lane.enqueue` (counter, attrs: `openclaw.lane`)
-- `openclaw.queue.lane.dequeue` (counter, attrs: `openclaw.lane`)
-- `openclaw.queue.depth` (histogram, attrs: `openclaw.lane` or `openclaw.channel=heartbeat`)
-- `openclaw.queue.wait_ms` (histogram, attrs: `openclaw.lane`)
-- `openclaw.session.state` (counter, attrs: `openclaw.state`, `openclaw.reason`)
-- `openclaw.session.stuck` (counter, attrs: `openclaw.state`)
-- `openclaw.session.stuck_age_ms` (histogram, attrs: `openclaw.state`)
-- `openclaw.run.attempt` (counter, attrs: `openclaw.attempt`)
-
-### Exec
-
-- `openclaw.exec.duration_ms` (histogram, attrs: `openclaw.exec.target`, `openclaw.exec.mode`, `openclaw.outcome`, `openclaw.failureKind`)
-
-### Diagnostics internals (memory and tool loop)
-
-- `openclaw.memory.heap_used_bytes` (histogram, attrs: `openclaw.memory.kind`)
-- `openclaw.memory.rss_bytes` (histogram)
-- `openclaw.memory.pressure` (counter, attrs: `openclaw.memory.level`)
-- `openclaw.tool.loop.iterations` (counter, attrs: `openclaw.toolName`, `openclaw.outcome`)
-- `openclaw.tool.loop.duration_ms` (histogram, attrs: `openclaw.toolName`, `openclaw.outcome`)
-
-## Exported spans
-
-- `openclaw.model.usage`
-  - `openclaw.channel`, `openclaw.provider`, `openclaw.model`
-  - `openclaw.tokens.*` (input/output/cache_read/cache_write/total)
-  - `gen_ai.system` by default, or `gen_ai.provider.name` when the latest GenAI semantic conventions are opted in
-  - `gen_ai.request.model`, `gen_ai.operation.name`, `gen_ai.usage.*`
-- `openclaw.run`
-  - `openclaw.outcome`, `openclaw.channel`, `openclaw.provider`, `openclaw.model`, `openclaw.errorCategory`
-- `openclaw.model.call`
-  - `gen_ai.system` by default, or `gen_ai.provider.name` when the latest GenAI semantic conventions are opted in
-  - `gen_ai.request.model`, `gen_ai.operation.name`, `openclaw.provider`, `openclaw.model`, `openclaw.api`, `openclaw.transport`
-  - `openclaw.provider.request_id_hash` (bounded SHA-based hash of the upstream provider request id; raw ids are not exported)
-- `openclaw.tool.execution`
-  - `gen_ai.tool.name`, `openclaw.toolName`, `openclaw.errorCategory`, `openclaw.tool.params.*`
-- `openclaw.exec`
-  - `openclaw.exec.target`, `openclaw.exec.mode`, `openclaw.outcome`, `openclaw.failureKind`, `openclaw.exec.command_length`, `openclaw.exec.exit_code`, `openclaw.exec.timed_out`
-- `openclaw.webhook.processed`
-  - `openclaw.channel`, `openclaw.webhook`, `openclaw.chatId`
-- `openclaw.webhook.error`
-  - `openclaw.channel`, `openclaw.webhook`, `openclaw.chatId`, `openclaw.error`
-- `openclaw.message.processed`
-  - `openclaw.channel`, `openclaw.outcome`, `openclaw.chatId`, `openclaw.messageId`, `openclaw.reason`
-- `openclaw.message.delivery`
-  - `openclaw.channel`, `openclaw.delivery.kind`, `openclaw.outcome`, `openclaw.errorCategory`, `openclaw.delivery.result_count`
-- `openclaw.session.stuck`
-  - `openclaw.state`, `openclaw.ageMs`, `openclaw.queueDepth`
-- `openclaw.context.assembled`
-  - `openclaw.prompt.size`, `openclaw.history.size`, `openclaw.context.tokens`, `openclaw.errorCategory` (no prompt, history, response, or session-key content)
-- `openclaw.tool.loop`
-  - `openclaw.toolName`, `openclaw.outcome`, `openclaw.iterations`, `openclaw.errorCategory` (no loop messages, params, or tool output)
-- `openclaw.memory.pressure`
-  - `openclaw.memory.level`, `openclaw.memory.heap_used_bytes`, `openclaw.memory.rss_bytes`
-
-When content capture is explicitly enabled, model and tool spans can also
-include bounded, redacted `openclaw.content.*` attributes for the specific
-content classes you opted into.
-
-## Diagnostic event catalog
-
-The events below back the metrics and spans above. Plugins can also subscribe
-to them directly without OTLP export.
-
-**Model usage**
-
-- `model.usage` — tokens, cost, duration, context, provider/model/channel,
-  session ids. `usage` is provider/turn accounting for cost and telemetry;
-  `context.used` is the current prompt/context snapshot and can be lower than
-  provider `usage.total` when cached input or tool-loop calls are involved.
-
-**Message flow**
-
-- `webhook.received` / `webhook.processed` / `webhook.error`
-- `message.queued` / `message.processed`
-- `message.delivery.started` / `message.delivery.completed` / `message.delivery.error`
-
-**Queue and session**
-
-- `queue.lane.enqueue` / `queue.lane.dequeue`
-- `session.state` / `session.stuck`
-- `run.attempt`
-- `diagnostic.heartbeat` (aggregate counters: webhooks/queue/session)
-
-**Exec**
-
-- `exec.process.completed` — terminal outcome, duration, target, mode, exit
-  code, and failure kind. Command text and working directories are not
-  included.
-
-## Without an exporter
-
-You can keep diagnostics events available to plugins or custom sinks without
-running `diagnostics-otel`:
-
-```json5
-{
-  diagnostics: { enabled: true },
-}
-```
-
-For targeted debug output without raising `logging.level`, use diagnostics
-flags. Flags are case-insensitive and support wildcards (e.g. `telegram.*` or
-`*`):
-
-```json5
-{
-  diagnostics: { flags: ["telegram.http"] },
-}
-```
-
-Or as a one-off env override:
-
-```bash
-OPENCLAW_DIAGNOSTICS=telegram.http,telegram.payload openclaw gateway
-```
-
-Flag output goes to the standard log file (`logging.file`) and is still
-redacted by `logging.redactSensitive`. Full guide:
-[Diagnostics flags](/diagnostics/flags).
-
-## Disable
-
-```json5
-{
-  diagnostics: { otel: { enabled: false } },
-}
-```
-
-You can also leave `diagnostics-otel` out of `plugins.allow`, or run
-`openclaw plugins disable diagnostics-otel`.
-
-## Related
-
-- [Logging](/logging) — file logs, console output, CLI tailing, and the Control UI Logs tab
-- [Gateway logging internals](/gateway/logging) — WS log styles, subsystem prefixes, and console capture
-- [Diagnostics flags](/diagnostics/flags) — targeted debug-log flags
-- [Diagnostics export](/gateway/diagnostics) — operator support-bundle tool (separate from OTEL export)
-- [Configuration reference](/gateway/configuration-reference#diagnostics) — full `diagnostics.*` field reference

docs/gateway/pairing.md

@@ -148,12 +148,11 @@ Security boundary:
 When an already paired device reconnects with only non-sensitive metadata
 changes (for example, display name or client platform hints), OpenClaw treats
 that as a `metadata-upgrade`. Silent auto-approval is narrow: it applies only
-to trusted non-browser local reconnects that already proved possession of local
-or shared credentials, including same-host native app reconnects after OS
-version metadata changes. Browser/Control UI clients and remote clients still
-use the explicit re-approval flow. Scope upgrades (read to write/admin) and
-public key changes are **not** eligible for metadata-upgrade auto-approval —
-they stay as explicit re-approval requests.
+to trusted local CLI/helper reconnects that already proved possession of the
+shared token or password over loopback. Browser/Control UI clients and remote
+clients still use the explicit re-approval flow. Scope upgrades (read to
+write/admin) and public key changes are **not** eligible for metadata-upgrade
+auto-approval — they stay as explicit re-approval requests.
 
 ## QR pairing helpers
 

docs/gateway/protocol.md

@@ -110,14 +110,6 @@ permissions:
 }
 ```
 
-Trusted same-process backend clients (`client.id: "gateway-client"`,
-`client.mode: "backend"`) may omit `device` on direct loopback connections when
-they authenticate with the shared gateway token/password. This path is reserved
-for internal control-plane RPCs and keeps stale CLI/device pairing baselines from
-blocking local backend work such as subagent session updates. Remote clients,
-browser-origin clients, node clients, and explicit device-token/device-identity
-clients still use the normal pairing and scope-upgrade checks.
-
 When a device token is issued, `hello-ok` also includes:
 
 ```json
@@ -577,13 +569,11 @@ rather than the pre-handshake defaults.
   trusted shared-secret helper flows.
 - Same-host tailnet or LAN connects are still treated as remote for pairing and
   require approval.
-- WS clients normally include `device` identity during `connect` (operator +
-  node). The only device-less operator exceptions are explicit trust paths:
+- All WS clients must include `device` identity during `connect` (operator + node).
+  Control UI can omit it only in these modes:
   - `gateway.controlUi.allowInsecureAuth=true` for localhost-only insecure HTTP compatibility.
   - successful `gateway.auth.mode: "trusted-proxy"` operator Control UI auth.
   - `gateway.controlUi.dangerouslyDisableDeviceAuth=true` (break-glass, severe security downgrade).
-  - direct-loopback `gateway-client` backend RPCs authenticated with the shared
-    gateway token/password.
 - All connections must sign the server-provided `connect.challenge` nonce.
 
 ### Device auth migration diagnostics

docs/gateway/security/audit-checks.md

@@ -97,9 +97,9 @@ exhaustive):
 | `tools.exec.safe_bin_trusted_dirs_risky`                      | warn          | `safeBinTrustedDirs` includes mutable or risky directories                           | `tools.exec.safeBinTrustedDirs`, `agents.list[].tools.exec.safeBinTrustedDirs`                       | no       |
 | `skills.workspace.symlink_escape`                             | warn          | Workspace `skills/**/SKILL.md` resolves outside workspace root (symlink-chain drift) | workspace `skills/**` filesystem state                                                               | no       |
 | `plugins.extensions_no_allowlist`                             | warn          | Plugins are installed without an explicit plugin allowlist                           | `plugins.allowlist`                                                                                  | no       |
-| `plugins.installs_unpinned_npm_specs`                         | warn          | Plugin index records are not pinned to immutable npm specs                           | plugin install metadata                                                                              | no       |
-| `plugins.installs_missing_integrity`                          | warn          | Plugin index records lack integrity metadata                                         | plugin install metadata                                                                              | no       |
-| `plugins.installs_version_drift`                              | warn          | Plugin index records drift from installed packages                                   | plugin install metadata                                                                              | no       |
+| `plugins.installs_unpinned_npm_specs`                         | warn          | Plugin install records are not pinned to immutable npm specs                         | plugin install metadata                                                                              | no       |
+| `plugins.installs_missing_integrity`                          | warn          | Plugin install records lack integrity metadata                                       | plugin install metadata                                                                              | no       |
+| `plugins.installs_version_drift`                              | warn          | Plugin install records drift from installed packages                                 | plugin install metadata                                                                              | no       |
 | `plugins.code_safety`                                         | warn/critical | Plugin code scan found suspicious or dangerous patterns                              | plugin code / install source                                                                         | no       |
 | `plugins.code_safety.entry_path`                              | warn          | Plugin entry path points into hidden or `node_modules` locations                     | plugin manifest `entry`                                                                              | no       |
 | `plugins.code_safety.entry_escape`                            | critical      | Plugin entry escapes the plugin directory                                            | plugin manifest `entry`                                                                              | no       |

docs/gateway/security/index.md

@@ -92,11 +92,6 @@ Treat Gateway and node as one operator trust domain, with different roles:
 - **Gateway** is the control plane and policy surface (`gateway.auth`, tool policy, routing).
 - **Node** is remote execution surface paired to that Gateway (commands, device actions, host-local capabilities).
 - A caller authenticated to the Gateway is trusted at Gateway scope. After pairing, node actions are trusted operator actions on that node.
-- Direct loopback backend clients authenticated with the shared gateway
-  token/password can make internal control-plane RPCs without presenting a user
-  device identity. This is not a remote or browser pairing bypass: network
-  clients, node clients, device-token clients, and explicit device identities
-  still go through pairing and scope-upgrade enforcement.
 - `sessionKey` is routing/context selection, not per-user auth.
 - Exec approvals (allowlist + ask) are guardrails for operator intent, not hostile multi-tenant isolation.
 - OpenClaw's product default for trusted single-operator setups is that host exec on `gateway`/`node` is allowed without approval prompts (`security="full"`, `ask="off"` unless you tighten it). That default is intentional UX, not a vulnerability by itself.
@@ -509,7 +504,7 @@ Plugins run **in-process** with the Gateway. Treat them as trusted code:
 - If you install or update plugins (`openclaw plugins install <package>`, `openclaw plugins update <id>`), treat it like running untrusted code:
   - The install path is the per-plugin directory under the active plugin install root.
   - OpenClaw runs a built-in dangerous-code scan before install/update. `critical` findings block by default.
-  - OpenClaw uses `npm pack`, then runs a project-local `npm install --omit=dev --ignore-scripts` in that directory. Inherited global npm install settings are ignored so dependencies stay under the plugin install path.
+  - OpenClaw uses `npm pack` and then runs `npm install --omit=dev` in that directory (npm lifecycle scripts can execute code during install).
   - Prefer pinned, exact versions (`@scope/pkg@1.2.3`), and inspect the unpacked code on disk before enabling.
   - `--dangerously-force-unsafe-install` is break-glass only for built-in scan false positives on plugin install/update flows. It does not bypass plugin `before_install` hook policy blocks and does not bypass scan failures.
   - Gateway-backed skill dependency installs follow the same dangerous/suspicious split: built-in `critical` findings block unless the caller explicitly sets `dangerouslyForceUnsafeInstall`, while suspicious findings still warn only. `openclaw skills install` remains the separate ClawHub skill download/install flow.

docs/gateway/tailscale.md

@@ -16,10 +16,6 @@ Tailscale provides HTTPS, routing, and (for Serve) identity headers.
 - `funnel`: Public HTTPS via `tailscale funnel`. OpenClaw requires a shared password.
 - `off`: Default (no Tailscale automation).
 
-Status and audit output use **Tailscale exposure** for this OpenClaw Serve/Funnel
-mode. `off` means OpenClaw is not managing Serve or Funnel; it does not mean the
-local Tailscale daemon is stopped or logged out.
-
 ## Auth
 
 Set `gateway.auth.mode` to control the handshake:

docs/gateway/troubleshooting.md

@@ -200,12 +200,6 @@ Use `error.details.code` from the failed `connect` response to pick the next act
 | `AUTH_DEVICE_TOKEN_MISMATCH` | Cached per-device token is stale or revoked.                                                                                                                                                 | Rotate/re-approve device token using [devices CLI](/cli/devices), then reconnect.                                                                                                                                                                                                        |
 | `PAIRING_REQUIRED`           | Device identity needs approval. Check `error.details.reason` for `not-paired`, `scope-upgrade`, `role-upgrade`, or `metadata-upgrade`, and use `requestId` / `remediationHint` when present. | Approve pending request: `openclaw devices list` then `openclaw devices approve <requestId>`. Scope/role upgrades use the same flow after you review the requested access.                                                                                                               |
 
-Direct loopback backend RPCs authenticated with the shared gateway
-token/password should not depend on the CLI's paired-device scope baseline. If
-subagents or other internal calls still fail with `scope-upgrade`, verify the
-caller is using `client.id: "gateway-client"` and `client.mode: "backend"` and
-is not forcing an explicit `deviceIdentity` or device token.
-
 Device auth v2 migration check:
 
 ```bash

docs/help/testing-live.md

@@ -164,18 +164,6 @@ OPENCLAW_LIVE_CLI_BACKEND=1 \
   pnpm test:live src/gateway/gateway-cli-backend.live.test.ts
 ```
 
-Cheap Gemini MCP config smoke:
-
-```bash
-OPENCLAW_LIVE_TEST=1 \
-  pnpm test:live src/agents/cli-runner/bundle-mcp.gemini.live.test.ts
-```
-
-This does not ask Gemini to generate a response. It writes the same system
-settings OpenClaw gives Gemini, then runs `gemini --debug mcp list` to prove a
-saved `transport: "streamable-http"` server is normalized to Gemini's HTTP MCP
-shape and can connect to a local streamable-HTTP MCP server.
-
 Docker recipe:
 
 ```bash
@@ -219,7 +207,6 @@ Notes:
 - Overrides:
   - `OPENCLAW_LIVE_ACP_BIND_AGENT=claude`
   - `OPENCLAW_LIVE_ACP_BIND_AGENT=codex`
-  - `OPENCLAW_LIVE_ACP_BIND_AGENT=droid`
   - `OPENCLAW_LIVE_ACP_BIND_AGENT=gemini`
   - `OPENCLAW_LIVE_ACP_BIND_AGENT=opencode`
   - `OPENCLAW_LIVE_ACP_BIND_AGENTS=claude,codex,gemini`
@@ -251,7 +238,6 @@ Single-agent Docker recipes:
 ```bash
 pnpm test:docker:live-acp-bind:claude
 pnpm test:docker:live-acp-bind:codex
-pnpm test:docker:live-acp-bind:droid
 pnpm test:docker:live-acp-bind:gemini
 pnpm test:docker:live-acp-bind:opencode
 ```
@@ -260,9 +246,8 @@ Docker notes:
 
 - The Docker runner lives at `scripts/test-live-acp-bind-docker.sh`.
 - By default, it runs the ACP bind smoke against the aggregate live CLI agents in sequence: `claude`, `codex`, then `gemini`.
-- Use `OPENCLAW_LIVE_ACP_BIND_AGENTS=claude`, `OPENCLAW_LIVE_ACP_BIND_AGENTS=codex`, `OPENCLAW_LIVE_ACP_BIND_AGENTS=droid`, `OPENCLAW_LIVE_ACP_BIND_AGENTS=gemini`, or `OPENCLAW_LIVE_ACP_BIND_AGENTS=opencode` to narrow the matrix.
-- It sources `~/.profile`, stages the matching CLI auth material into the container, then installs the requested live CLI (`@anthropic-ai/claude-code`, `@openai/codex`, Factory Droid via `https://app.factory.ai/cli`, `@google/gemini-cli`, or `opencode-ai`) if missing. The ACP backend itself is the bundled embedded `acpx/runtime` package from the `acpx` plugin.
-- The Droid Docker variant stages `~/.factory` for settings, forwards `FACTORY_API_KEY`, and requires that API key because local Factory OAuth/keyring auth is not portable into the container. It uses ACPX's built-in `droid exec --output-format acp` registry entry.
+- Use `OPENCLAW_LIVE_ACP_BIND_AGENTS=claude`, `OPENCLAW_LIVE_ACP_BIND_AGENTS=codex`, `OPENCLAW_LIVE_ACP_BIND_AGENTS=gemini`, or `OPENCLAW_LIVE_ACP_BIND_AGENTS=opencode` to narrow the matrix.
+- It sources `~/.profile`, stages the matching CLI auth material into the container, then installs the requested live CLI (`@anthropic-ai/claude-code`, `@openai/codex`, `@google/gemini-cli`, or `opencode-ai`) if missing. The ACP backend itself is the bundled embedded `acpx/runtime` package from the `acpx` plugin.
 - The OpenCode Docker variant is a strict single-agent regression lane. It writes a temporary `OPENCODE_CONFIG_CONTENT` default model from `OPENCLAW_LIVE_ACP_BIND_OPENCODE_MODEL` (default `opencode/kimi-k2.6`) after sourcing `~/.profile`, and `pnpm test:docker:live-acp-bind:opencode` requires a bound assistant transcript instead of accepting the generic post-bind skip.
 - Direct `acpx` CLI calls are only a manual/workaround path for comparing behavior outside the Gateway. The Docker ACP bind smoke exercises OpenClaw's embedded `acpx` runtime backend.
 

docs/help/testing.md

@@ -120,12 +120,6 @@ runs the same lanes before release approval.
     endpoint.
   - Use `OPENCLAW_NPM_ONBOARD_CHANNEL=discord` to run the same packaged-install
     lane with Discord.
-- `pnpm test:docker:session-runtime-context`
-  - Runs a deterministic built-app Docker smoke for embedded runtime context
-    transcripts. It verifies hidden OpenClaw runtime context is persisted as a
-    non-display custom message instead of leaking into the visible user turn,
-    then seeds an affected broken session JSONL and verifies
-    `openclaw doctor --fix` rewrites it to the active branch with a backup.
 - `pnpm test:docker:npm-telegram-live`
   - Installs a published OpenClaw package in Docker, runs installed-package
     onboarding, configures Telegram through the installed CLI, then reuses the
@@ -399,11 +393,10 @@ Think of the suites as “increasing realism” (and increasing flakiness/cost):
     - `pnpm test --watch` still uses the native root `vitest.config.ts` project graph, because a multi-shard watch loop is not practical.
     - `pnpm test`, `pnpm test:watch`, and `pnpm test:perf:imports` route explicit file/directory targets through scoped lanes first, so `pnpm test extensions/discord/src/monitor/message-handler.preflight.test.ts` avoids paying the full root project startup tax.
     - `pnpm test:changed` expands changed git paths into the same scoped lanes when the diff only touches routable source/test files; config/setup edits still fall back to the broad root-project rerun.
-    - `pnpm check:changed` is the normal smart local gate for narrow work. It classifies the diff into core, core tests, extensions, extension tests, apps, docs, release metadata, live Docker tooling, and tooling, then runs the matching typecheck/lint/test lanes. Public Plugin SDK and plugin-contract changes include one extension validation pass because extensions depend on those core contracts. Release metadata-only version bumps run targeted version/config/root-dependency checks instead of the full suite, with a guard that rejects package changes outside the top-level version field.
-    - Live Docker ACP harness edits run a focused local gate: shell syntax for the live Docker auth scripts, live Docker scheduler dry-run, ACP bind unit tests, and the ACPX extension tests. `package.json` changes are included only when the diff is limited to `scripts["test:docker:live-*"]`; dependency, export, version, and other package-surface edits still use the broader guards.
+    - `pnpm check:changed` is the normal smart local gate for narrow work. It classifies the diff into core, core tests, extensions, extension tests, apps, docs, release metadata, and tooling, then runs the matching typecheck/lint/test lanes. Public Plugin SDK and plugin-contract changes include one extension validation pass because extensions depend on those core contracts. Release metadata-only version bumps run targeted version/config/root-dependency checks instead of the full suite, with a guard that rejects package changes outside the top-level version field.
     - Import-light unit tests from agents, commands, plugins, auto-reply helpers, `plugin-sdk`, and similar pure utility areas route through the `unit-fast` lane, which skips `test/setup-openclaw-runtime.ts`; stateful/runtime-heavy files stay on the existing lanes.
     - Selected `plugin-sdk` and `commands` helper source files also map changed-mode runs to explicit sibling tests in those light lanes, so helper edits avoid rerunning the full heavy suite for that directory.
-    - `auto-reply` has dedicated buckets for top-level core helpers, top-level `reply.*` integration tests, and the `src/auto-reply/reply/**` subtree. CI further splits the reply subtree into agent-runner, dispatch, and commands/state-routing shards so one import-heavy bucket does not own the full Node tail.
+    - `auto-reply` has three dedicated buckets: top-level core helpers, top-level `reply.*` integration tests, and the `src/auto-reply/reply/**` subtree. This keeps the heaviest reply harness work off the cheap status/chunk/token tests.
 
   </Accordion>
 
@@ -469,10 +462,6 @@ Think of the suites as “increasing realism” (and increasing flakiness/cost):
       import-breakdown output.
     - `pnpm test:perf:imports:changed` scopes the same profiling view to
       files changed since `origin/main`.
-    - Shard timing data is written to `.artifacts/vitest-shard-timings.json`.
-      Whole-config runs use the config path as the key; include-pattern CI
-      shards append the shard name so filtered shards can be tracked
-      separately.
     - When one hot test still spends most of its time in startup imports,
       keep heavy dependencies behind a narrow local `*.runtime.ts` seam and
       mock that seam directly instead of deep-importing runtime helpers just
@@ -594,19 +583,18 @@ These Docker runners split into two buckets:
   `OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=90000`. Override those env vars when you
   explicitly want the larger exhaustive scan.
 - `test:docker:all` builds the live Docker image once via `test:docker:live-build`, then reuses it for the live Docker lanes. It also builds one shared `scripts/e2e/Dockerfile` image via `test:docker:e2e-build` and reuses it for the E2E container smoke runners that exercise the built app. The aggregate uses a weighted local scheduler: `OPENCLAW_DOCKER_ALL_PARALLELISM` controls process slots, while resource caps keep heavy live, npm-install, and multi-service lanes from all starting at once. Defaults are 10 slots, `OPENCLAW_DOCKER_ALL_LIVE_LIMIT=6`, `OPENCLAW_DOCKER_ALL_NPM_LIMIT=8`, and `OPENCLAW_DOCKER_ALL_SERVICE_LIMIT=7`; tune `OPENCLAW_DOCKER_ALL_WEIGHT_LIMIT` or `OPENCLAW_DOCKER_ALL_DOCKER_LIMIT` only when the Docker host has more headroom. The runner performs a Docker preflight by default, removes stale OpenClaw E2E containers, prints status every 30 seconds, stores successful lane timings in `.artifacts/docker-tests/lane-timings.json`, and uses those timings to start longer lanes first on later runs. Use `OPENCLAW_DOCKER_ALL_DRY_RUN=1` to print the weighted lane manifest without building or running Docker.
-- Container smoke runners: `test:docker:openwebui`, `test:docker:onboard`, `test:docker:npm-onboard-channel-agent`, `test:docker:session-runtime-context`, `test:docker:agents-delete-shared-workspace`, `test:docker:gateway-network`, `test:docker:mcp-channels`, `test:docker:pi-bundle-mcp-tools`, `test:docker:cron-mcp-cleanup`, `test:docker:plugins`, `test:docker:plugin-update`, and `test:docker:config-reload` boot one or more real containers and verify higher-level integration paths.
+- Container smoke runners: `test:docker:openwebui`, `test:docker:onboard`, `test:docker:npm-onboard-channel-agent`, `test:docker:agents-delete-shared-workspace`, `test:docker:gateway-network`, `test:docker:mcp-channels`, `test:docker:pi-bundle-mcp-tools`, `test:docker:cron-mcp-cleanup`, `test:docker:plugins`, `test:docker:plugin-update`, and `test:docker:config-reload` 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:
 
 - Direct models: `pnpm test:docker:live-models` (script: `scripts/test-live-models-docker.sh`)
-- ACP bind smoke: `pnpm test:docker:live-acp-bind` (script: `scripts/test-live-acp-bind-docker.sh`; covers Claude, Codex, and Gemini by default, with strict Droid/OpenCode coverage via `pnpm test:docker:live-acp-bind:droid` and `pnpm test:docker:live-acp-bind:opencode`)
+- ACP bind smoke: `pnpm test:docker:live-acp-bind` (script: `scripts/test-live-acp-bind-docker.sh`; covers Claude, Codex, and Gemini by default, with strict OpenCode coverage via `pnpm test:docker:live-acp-bind:opencode`)
 - CLI backend smoke: `pnpm test:docker:live-cli-backend` (script: `scripts/test-live-cli-backend-docker.sh`)
 - Codex app-server harness smoke: `pnpm test:docker:live-codex-harness` (script: `scripts/test-live-codex-harness-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`)
 - Npm tarball onboarding/channel/agent smoke: `pnpm test:docker:npm-onboard-channel-agent` installs the packed OpenClaw tarball globally in Docker, configures OpenAI via env-ref onboarding plus Telegram by default, verifies doctor repairs activated plugin runtime deps, and runs one mocked OpenAI agent turn. Reuse a prebuilt tarball with `OPENCLAW_NPM_ONBOARD_PACKAGE_TGZ=/path/to/openclaw-*.tgz`, skip the host rebuild with `OPENCLAW_NPM_ONBOARD_HOST_BUILD=0`, or switch channel with `OPENCLAW_NPM_ONBOARD_CHANNEL=discord`.
-- Session runtime context smoke: `pnpm test:docker:session-runtime-context` verifies hidden runtime context transcript persistence plus doctor repair of affected duplicated prompt-rewrite branches.
 - Bun global install smoke: `bash scripts/e2e/bun-global-install-smoke.sh` packs the current tree, installs it with `bun install -g` in an isolated home, and verifies `openclaw infer image providers --json` returns bundled image providers instead of hanging. Reuse a prebuilt tarball with `OPENCLAW_BUN_GLOBAL_SMOKE_PACKAGE_TGZ=/path/to/openclaw-*.tgz`, skip the host build with `OPENCLAW_BUN_GLOBAL_SMOKE_HOST_BUILD=0`, or copy `dist/` from a built Docker image with `OPENCLAW_BUN_GLOBAL_SMOKE_DIST_IMAGE=openclaw-dockerfile-smoke:local`.
 - Installer Docker smoke: `bash scripts/test-install-sh-docker.sh` shares one npm cache across its root, update, and direct-npm containers. Update smoke defaults to npm `latest` as the stable baseline before upgrading to the candidate tarball. Non-root installer checks keep an isolated npm cache so root-owned cache entries do not mask user-local install behavior. Set `OPENCLAW_INSTALL_SMOKE_NPM_CACHE_DIR=/path/to/cache` to reuse the root/update/direct-npm cache across local reruns.
 - Install Smoke CI skips the duplicate direct-npm global update with `OPENCLAW_INSTALL_SMOKE_SKIP_NPM_GLOBAL=1`; run the script locally without that env when direct `npm install -g` coverage is needed.

docs/install/fly.md

@@ -193,14 +193,7 @@ read_when:
       },
       "gateway": {
         "mode": "local",
-        "bind": "auto",
-        "controlUi": {
-          "allowedOrigins": [
-            "https://my-openclaw.fly.dev",
-            "http://localhost:3000",
-            "http://127.0.0.1:3000"
-          ]
-        }
+        "bind": "auto"
       },
       "meta": {}
     }
@@ -209,12 +202,6 @@ read_when:
 
     **Note:** With `OPENCLAW_STATE_DIR=/data`, the config path is `/data/openclaw.json`.
 
-    **Note:** Replace `https://my-openclaw.fly.dev` with your real Fly app
-    origin. Gateway startup seeds local Control UI origins from the runtime
-    `--bind` and `--port` values so first boot can proceed before config exists,
-    but browser access through Fly still needs the exact HTTPS origin listed in
-    `gateway.controlUi.allowedOrigins`.
-
     **Note:** The Discord token can come from either:
 
     - Environment variable: `DISCORD_BOT_TOKEN` (recommended for secrets)

docs/install/migrating-matrix.md

@@ -93,20 +93,16 @@ If your old installation had local-only encrypted history that was never backed
    openclaw matrix verify backup status
    ```
 
-5. Put the recovery key for the Matrix account you are repairing in an account-specific environment variable. For a single default account, `MATRIX_RECOVERY_KEY` is fine. For multiple accounts, use one variable per account, for example `MATRIX_RECOVERY_KEY_ASSISTANT`, and add `--account assistant` to the command.
-
-6. If OpenClaw tells you a recovery key is needed, run the command for the matching account:
+5. If OpenClaw tells you a recovery key is needed, run:
 
    ```bash
-   printf '%s\n' "$MATRIX_RECOVERY_KEY" | openclaw matrix verify backup restore --recovery-key-stdin
-   printf '%s\n' "$MATRIX_RECOVERY_KEY_ASSISTANT" | openclaw matrix verify backup restore --recovery-key-stdin --account assistant
+   openclaw matrix verify backup restore --recovery-key "<your-recovery-key>"
    ```
 
-7. If this device is still unverified, run the command for the matching account:
+6. If this device is still unverified, run:
 
    ```bash
-   printf '%s\n' "$MATRIX_RECOVERY_KEY" | openclaw matrix verify device --recovery-key-stdin
-   printf '%s\n' "$MATRIX_RECOVERY_KEY_ASSISTANT" | openclaw matrix verify device --recovery-key-stdin --account assistant
+   openclaw matrix verify device "<your-recovery-key>"
    ```
 
    If the recovery key is accepted and backup is usable, but `Cross-signing verified`
@@ -120,13 +116,13 @@ If your old installation had local-only encrypted history that was never backed
    and type `yes` only when they match. The command exits successfully only
    after `Cross-signing verified` becomes `yes`.
 
-8. If you are intentionally abandoning unrecoverable old history and want a fresh backup baseline for future messages, run:
+7. If you are intentionally abandoning unrecoverable old history and want a fresh backup baseline for future messages, run:
 
    ```bash
    openclaw matrix verify backup reset --yes
    ```
 
-9. If no server-side key backup exists yet, create one for future recoveries:
+8. If no server-side key backup exists yet, create one for future recoveries:
 
    ```bash
    openclaw matrix verify bootstrap
@@ -246,15 +242,15 @@ If the old store reports room keys that were never backed up, OpenClaw warns ins
 - Meaning: some old room keys existed only in the old local store and had never been uploaded to Matrix backup.
 - What to do: expect some old encrypted history to remain unavailable unless you can recover those keys manually from another verified client.
 
-`Legacy Matrix encrypted state for account "..." has backed-up room keys, but no local backup decryption key was found. Ask the operator to run "openclaw matrix verify backup restore --recovery-key-stdin" after upgrade if they have the recovery key.`
+`Legacy Matrix encrypted state for account "..." has backed-up room keys, but no local backup decryption key was found. Ask the operator to run "openclaw matrix verify backup restore --recovery-key <key>" after upgrade if they have the recovery key.`
 
 - Meaning: backup exists, but OpenClaw could not recover the recovery key automatically.
-- What to do: run `printf '%s\n' "$MATRIX_RECOVERY_KEY" | openclaw matrix verify backup restore --recovery-key-stdin`.
+- What to do: run `openclaw matrix verify backup restore --recovery-key "<your-recovery-key>"`.
 
 `Failed inspecting legacy Matrix encrypted state for account "..." (...): ...`
 
 - Meaning: OpenClaw found the old encrypted store, but it could not inspect it safely enough to prepare recovery.
-- What to do: rerun `openclaw doctor --fix`. If it repeats, keep the old state directory intact and recover using another verified Matrix client plus `printf '%s\n' "$MATRIX_RECOVERY_KEY" | openclaw matrix verify backup restore --recovery-key-stdin`.
+- What to do: rerun `openclaw doctor --fix`. If it repeats, keep the old state directory intact and recover using another verified Matrix client plus `openclaw matrix verify backup restore --recovery-key "<your-recovery-key>"`.
 
 `Legacy Matrix backup key was found for account "...", but .../recovery-key.json already contains a different recovery key. Leaving the existing file unchanged.`
 
@@ -269,39 +265,39 @@ If the old store reports room keys that were never backed up, OpenClaw warns ins
 `matrix: failed restoring room keys from legacy encrypted-state backup: ...`
 
 - Meaning: the new plugin attempted restore but Matrix returned an error.
-- What to do: run `openclaw matrix verify backup status`, then retry with `printf '%s\n' "$MATRIX_RECOVERY_KEY" | openclaw matrix verify backup restore --recovery-key-stdin` if needed.
+- What to do: run `openclaw matrix verify backup status`, then retry with `openclaw matrix verify backup restore --recovery-key "<your-recovery-key>"` if needed.
 
 ### Manual recovery messages
 
 `Backup key is not loaded on this device. Run 'openclaw matrix verify backup restore' to load it and restore old room keys.`
 
 - Meaning: OpenClaw knows you should have a backup key, but it is not active on this device.
-- What to do: run `openclaw matrix verify backup restore`, or set `MATRIX_RECOVERY_KEY` and run `printf '%s\n' "$MATRIX_RECOVERY_KEY" | openclaw matrix verify backup restore --recovery-key-stdin` if needed.
+- What to do: run `openclaw matrix verify backup restore`, or pass `--recovery-key` if needed.
 
-`Store a recovery key with 'openclaw matrix verify device --recovery-key-stdin', then run 'openclaw matrix verify backup restore'.`
+`Store a recovery key with 'openclaw matrix verify device <key>', then run 'openclaw matrix verify backup restore'.`
 
 - Meaning: this device does not currently have the recovery key stored.
-- What to do: set `MATRIX_RECOVERY_KEY`, run `printf '%s\n' "$MATRIX_RECOVERY_KEY" | openclaw matrix verify device --recovery-key-stdin`, then restore the backup.
+- What to do: verify the device with your recovery key first, then restore the backup.
 
-`Backup key mismatch on this device. Re-run 'openclaw matrix verify device --recovery-key-stdin' with the matching recovery key.`
+`Backup key mismatch on this device. Re-run 'openclaw matrix verify device <key>' with the matching recovery key.`
 
 - Meaning: the stored key does not match the active Matrix backup.
-- What to do: set `MATRIX_RECOVERY_KEY` to the correct key and run `printf '%s\n' "$MATRIX_RECOVERY_KEY" | openclaw matrix verify device --recovery-key-stdin`.
+- What to do: rerun `openclaw matrix verify device "<your-recovery-key>"` with the correct key.
 
 If you accept losing unrecoverable old encrypted history, you can instead reset the
 current backup baseline with `openclaw matrix verify backup reset --yes`. When the
 stored backup secret is broken, that reset may also recreate secret storage so the
 new backup key can load correctly after restart.
 
-`Backup trust chain is not verified on this device. Re-run 'openclaw matrix verify device --recovery-key-stdin'.`
+`Backup trust chain is not verified on this device. Re-run 'openclaw matrix verify device <key>'.`
 
 - Meaning: the backup exists, but this device does not trust the cross-signing chain strongly enough yet.
-- What to do: set `MATRIX_RECOVERY_KEY` and run `printf '%s\n' "$MATRIX_RECOVERY_KEY" | openclaw matrix verify device --recovery-key-stdin`.
+- What to do: rerun `openclaw matrix verify device "<your-recovery-key>"`.
 
 `Matrix recovery key is required`
 
 - Meaning: you tried a recovery step without supplying a recovery key when one was required.
-- What to do: rerun the command with `--recovery-key-stdin`, for example `printf '%s\n' "$MATRIX_RECOVERY_KEY" | openclaw matrix verify device --recovery-key-stdin`.
+- What to do: rerun the command with your recovery key.
 
 `Invalid Matrix recovery key: ...`
 
@@ -317,7 +313,7 @@ new backup key can load correctly after restart.
 - What to do: run `openclaw matrix verify self`, accept the request in another
   Matrix client, compare the SAS, and type `yes` only when it matches. The
   command waits for full Matrix identity trust before reporting success. Use
-  `printf '%s\n' "$MATRIX_RECOVERY_KEY" | openclaw matrix verify bootstrap --recovery-key-stdin --force-reset-cross-signing`
+  `openclaw matrix verify bootstrap --recovery-key "<your-recovery-key>" --force-reset-cross-signing`
   only when you intentionally want to replace the current cross-signing identity.
 
 `Matrix key backup is not active on this device after loading from secret storage.`
@@ -325,10 +321,10 @@ new backup key can load correctly after restart.
 - Meaning: secret storage did not produce an active backup session on this device.
 - What to do: verify the device first, then recheck with `openclaw matrix verify backup status`.
 
-`Matrix crypto backend cannot load backup keys from secret storage. Verify this device with 'openclaw matrix verify device --recovery-key-stdin' first.`
+`Matrix crypto backend cannot load backup keys from secret storage. Verify this device with 'openclaw matrix verify device <key>' first.`
 
 - Meaning: this device cannot restore from secret storage until device verification is complete.
-- What to do: run `printf '%s\n' "$MATRIX_RECOVERY_KEY" | openclaw matrix verify device --recovery-key-stdin` first.
+- What to do: run `openclaw matrix verify device "<your-recovery-key>"` first.
 
 ### Custom plugin install messages
 
@@ -344,7 +340,7 @@ Run these checks in order:
 ```bash
 openclaw matrix verify status --verbose
 openclaw matrix verify backup status --verbose
-printf '%s\n' "$MATRIX_RECOVERY_KEY" | openclaw matrix verify backup restore --recovery-key-stdin --verbose
+openclaw matrix verify backup restore --recovery-key "<your-recovery-key>" --verbose
 ```
 
 If the backup restores successfully but some old rooms are still missing history, those missing keys were probably never backed up by the previous plugin.

docs/install/updating.md

@@ -74,10 +74,6 @@ ReadWritePaths=/var/lib/openclaw /home/openclaw/.openclaw /tmp
 
 If `OPENCLAW_PLUGIN_STAGE_DIR` is not set, OpenClaw uses `$STATE_DIRECTORY` when
 systemd provides it, then falls back to `~/.openclaw/plugin-runtime-deps`.
-The repair step treats that stage as an OpenClaw-owned local package root and
-ignores user npm prefix/global settings, so global-install npm config does not
-redirect bundled plugin dependencies into `~/node_modules` or the global package
-tree.
 
 ### Bundled plugin runtime dependencies
 

docs/logging.md

@@ -1,12 +1,14 @@
 ---
-summary: "File logs, console output, CLI tailing, and the Control UI Logs tab"
+summary: "Logging overview: file logs, console output, CLI tailing, and the Control UI"
 read_when:
-  - You need a beginner-friendly overview of OpenClaw logging
-  - You want to configure log levels, formats, or redaction
+  - You need a beginner-friendly overview of logging
+  - You want to configure log levels or formats
   - You are troubleshooting and need to find logs quickly
-title: "Logging"
+title: "Logging overview"
 ---
 
+# Logging
+
 OpenClaw has two main log surfaces:
 
 - **File logs** (JSON lines) written by the Gateway.
@@ -169,35 +171,308 @@ Tool summaries can redact sensitive tokens before they hit the console:
 
 Redaction affects **console output only** and does not alter file logs.
 
-## Diagnostics and OpenTelemetry
+## Diagnostics + OpenTelemetry
 
-Diagnostics are structured, machine-readable events for model runs and
+Diagnostics are structured, machine-readable events for model runs **and**
 message-flow telemetry (webhooks, queueing, session state). They do **not**
-replace logs — they feed metrics, traces, and exporters. Events are emitted
-in-process whether or not you export them.
+replace logs; they exist to feed metrics, traces, and other exporters.
 
-Two adjacent surfaces:
+Diagnostics events are emitted in-process, but exporters only attach when
+diagnostics + the exporter plugin are enabled.
 
-- **OpenTelemetry export** — send metrics, traces, and logs over OTLP/HTTP to
-  any OpenTelemetry-compatible collector or backend (Grafana, Datadog,
-  Honeycomb, New Relic, Tempo, etc.). Full configuration, signal catalog,
-  metric/span names, env vars, and privacy model live on a dedicated page:
-  [OpenTelemetry export](/gateway/opentelemetry).
-- **Diagnostics flags** — targeted debug-log flags that route extra logs to
-  `logging.file` without raising `logging.level`. Flags are case-insensitive
-  and support wildcards (`telegram.*`, `*`). Configure under `diagnostics.flags`
-  or via the `OPENCLAW_DIAGNOSTICS=...` env override. Full guide:
-  [Diagnostics flags](/diagnostics/flags).
+### OpenTelemetry vs OTLP
 
-To enable diagnostics events for plugins or custom sinks without OTLP export:
+- **OpenTelemetry (OTel)**: the data model + SDKs for traces, metrics, and logs.
+- **OTLP**: the wire protocol used to export OTel data to a collector/backend.
+- OpenClaw exports via **OTLP/HTTP (protobuf)** today.
 
-```json5
+### Signals exported
+
+- **Metrics**: counters + histograms (token usage, message flow, queueing).
+- **Traces**: spans for model usage + webhook/message processing.
+- **Logs**: exported over OTLP when `diagnostics.otel.logs` is enabled. Log
+  volume can be high; keep `logging.level` and exporter filters in mind.
+
+### Diagnostic event catalog
+
+Model usage:
+
+- `model.usage`: tokens, cost, duration, context, provider/model/channel, session ids.
+  `usage` is provider/turn accounting for cost and telemetry; `context.used`
+  is the current prompt/context snapshot and can be lower than provider
+  `usage.total` when cached input or tool-loop calls are involved.
+
+Message flow:
+
+- `webhook.received`: webhook ingress per channel.
+- `webhook.processed`: webhook handled + duration.
+- `webhook.error`: webhook handler errors.
+- `message.queued`: message enqueued for processing.
+- `message.processed`: outcome + duration + optional error.
+- `message.delivery.started`: outbound delivery attempt started.
+- `message.delivery.completed`: outbound delivery attempt finished + duration/result count.
+- `message.delivery.error`: outbound delivery attempt failed + duration/bounded error category.
+
+Queue + session:
+
+- `queue.lane.enqueue`: command queue lane enqueue + depth.
+- `queue.lane.dequeue`: command queue lane dequeue + wait time.
+- `session.state`: session state transition + reason.
+- `session.stuck`: session stuck warning + age.
+- `run.attempt`: run retry/attempt metadata.
+- `diagnostic.heartbeat`: aggregate counters (webhooks/queue/session).
+
+Exec:
+
+- `exec.process.completed`: terminal exec process outcome, duration, target, mode,
+  exit code, and failure kind. Command text and working directories are not
+  included.
+
+### Enable diagnostics (no exporter)
+
+Use this if you want diagnostics events available to plugins or custom sinks:
+
+```json
 {
-  diagnostics: { enabled: true },
+  "diagnostics": {
+    "enabled": true
+  }
 }
 ```
 
-For OTLP export to a collector, see [OpenTelemetry export](/gateway/opentelemetry).
+### Diagnostics flags (targeted logs)
+
+Use flags to turn on extra, targeted debug logs without raising `logging.level`.
+Flags are case-insensitive and support wildcards (e.g. `telegram.*` or `*`).
+
+```json
+{
+  "diagnostics": {
+    "flags": ["telegram.http"]
+  }
+}
+```
+
+Env override (one-off):
+
+```
+OPENCLAW_DIAGNOSTICS=telegram.http,telegram.payload
+```
+
+Notes:
+
+- Flag logs go to the standard log file (same as `logging.file`).
+- Output is still redacted according to `logging.redactSensitive`.
+- Full guide: [/diagnostics/flags](/diagnostics/flags).
+
+### Export to OpenTelemetry
+
+Diagnostics can be exported via the `diagnostics-otel` plugin (OTLP/HTTP). This
+works with any OpenTelemetry collector/backend that accepts OTLP/HTTP.
+
+```json
+{
+  "plugins": {
+    "allow": ["diagnostics-otel"],
+    "entries": {
+      "diagnostics-otel": {
+        "enabled": true
+      }
+    }
+  },
+  "diagnostics": {
+    "enabled": true,
+    "otel": {
+      "enabled": true,
+      "endpoint": "http://otel-collector:4318",
+      "protocol": "http/protobuf",
+      "serviceName": "openclaw-gateway",
+      "traces": true,
+      "metrics": true,
+      "logs": true,
+      "sampleRate": 0.2,
+      "flushIntervalMs": 60000,
+      "captureContent": {
+        "enabled": false,
+        "inputMessages": false,
+        "outputMessages": false,
+        "toolInputs": false,
+        "toolOutputs": false,
+        "systemPrompt": false
+      }
+    }
+  }
+}
+```
+
+Notes:
+
+- You can also enable the plugin with `openclaw plugins enable diagnostics-otel`.
+- `protocol` currently supports `http/protobuf` only. `grpc` is ignored.
+- Metrics include token usage, cost, context size, run duration, and message-flow
+  counters/histograms (webhooks, queueing, session state, queue depth/wait),
+  plus GenAI token usage and model-call duration histograms.
+- Traces/metrics can be toggled with `traces` / `metrics` (default: on). Traces
+  include model usage spans plus webhook/message processing spans when enabled.
+- Raw model/tool content is not exported by default. Use
+  `diagnostics.otel.captureContent` only when your collector and retention policy
+  are approved for prompt, response, tool, or system prompt text.
+- Set `headers` when your collector requires auth.
+- Environment variables supported: `OTEL_EXPORTER_OTLP_ENDPOINT`,
+  `OTEL_SERVICE_NAME`, `OTEL_EXPORTER_OTLP_PROTOCOL`.
+- Set `OTEL_SEMCONV_STABILITY_OPT_IN=gen_ai_latest_experimental` to emit the
+  latest experimental GenAI provider span attribute (`gen_ai.provider.name`)
+  instead of the legacy span attribute (`gen_ai.system`). GenAI metrics always
+  use bounded, low-cardinality semantic attributes.
+- Set `OPENCLAW_OTEL_PRELOADED=1` when another preload or host process already
+  registered the global OpenTelemetry SDK. In that mode the plugin does not start
+  or shut down its own SDK, but it still wires OpenClaw diagnostic listeners and
+  honors `diagnostics.otel.traces`, `metrics`, and `logs`.
+
+### Exported metrics (names + types)
+
+Model usage:
+
+- `openclaw.tokens` (counter, attrs: `openclaw.token`, `openclaw.channel`,
+  `openclaw.provider`, `openclaw.model`)
+- `openclaw.cost.usd` (counter, attrs: `openclaw.channel`, `openclaw.provider`,
+  `openclaw.model`)
+- `openclaw.run.duration_ms` (histogram, attrs: `openclaw.channel`,
+  `openclaw.provider`, `openclaw.model`)
+- `openclaw.context.tokens` (histogram, attrs: `openclaw.context`,
+  `openclaw.channel`, `openclaw.provider`, `openclaw.model`)
+- `gen_ai.client.token.usage` (histogram, GenAI semantic-conventions metric,
+  attrs: `gen_ai.token.type` = `input`/`output`, `gen_ai.provider.name`,
+  `gen_ai.operation.name`, `gen_ai.request.model`)
+- `gen_ai.client.operation.duration` (histogram, seconds, GenAI
+  semantic-conventions metric, attrs: `gen_ai.provider.name`,
+  `gen_ai.operation.name`, `gen_ai.request.model`, optional `error.type`)
+
+Message flow:
+
+- `openclaw.webhook.received` (counter, attrs: `openclaw.channel`,
+  `openclaw.webhook`)
+- `openclaw.webhook.error` (counter, attrs: `openclaw.channel`,
+  `openclaw.webhook`)
+- `openclaw.webhook.duration_ms` (histogram, attrs: `openclaw.channel`,
+  `openclaw.webhook`)
+- `openclaw.message.queued` (counter, attrs: `openclaw.channel`,
+  `openclaw.source`)
+- `openclaw.message.processed` (counter, attrs: `openclaw.channel`,
+  `openclaw.outcome`)
+- `openclaw.message.duration_ms` (histogram, attrs: `openclaw.channel`,
+  `openclaw.outcome`)
+- `openclaw.message.delivery.started` (counter, attrs: `openclaw.channel`,
+  `openclaw.delivery.kind`)
+- `openclaw.message.delivery.duration_ms` (histogram, attrs:
+  `openclaw.channel`, `openclaw.delivery.kind`, `openclaw.outcome`,
+  `openclaw.errorCategory`)
+
+Queues + sessions:
+
+- `openclaw.queue.lane.enqueue` (counter, attrs: `openclaw.lane`)
+- `openclaw.queue.lane.dequeue` (counter, attrs: `openclaw.lane`)
+- `openclaw.queue.depth` (histogram, attrs: `openclaw.lane` or
+  `openclaw.channel=heartbeat`)
+- `openclaw.queue.wait_ms` (histogram, attrs: `openclaw.lane`)
+- `openclaw.session.state` (counter, attrs: `openclaw.state`, `openclaw.reason`)
+- `openclaw.session.stuck` (counter, attrs: `openclaw.state`)
+- `openclaw.session.stuck_age_ms` (histogram, attrs: `openclaw.state`)
+- `openclaw.run.attempt` (counter, attrs: `openclaw.attempt`)
+
+Exec:
+
+- `openclaw.exec.duration_ms` (histogram, attrs: `openclaw.exec.target`,
+  `openclaw.exec.mode`, `openclaw.outcome`, `openclaw.failureKind`)
+
+Diagnostics internals (memory + tool loop):
+
+- `openclaw.memory.heap_used_bytes` (histogram, attrs: `openclaw.memory.kind`)
+- `openclaw.memory.rss_bytes` (histogram)
+- `openclaw.memory.pressure` (counter, attrs: `openclaw.memory.level`)
+- `openclaw.tool.loop.iterations` (counter, attrs: `openclaw.toolName`,
+  `openclaw.outcome`)
+- `openclaw.tool.loop.duration_ms` (histogram, attrs: `openclaw.toolName`,
+  `openclaw.outcome`)
+
+### Exported spans (names + key attributes)
+
+- `openclaw.model.usage`
+  - `openclaw.channel`, `openclaw.provider`, `openclaw.model`
+  - `openclaw.tokens.*` (input/output/cache_read/cache_write/total)
+  - `gen_ai.system` by default, or `gen_ai.provider.name` when latest GenAI
+    semantic conventions are opted in
+  - `gen_ai.request.model`, `gen_ai.operation.name`, `gen_ai.usage.*`
+- `openclaw.run`
+  - `openclaw.outcome`, `openclaw.channel`, `openclaw.provider`,
+    `openclaw.model`, `openclaw.errorCategory`
+- `openclaw.model.call`
+  - `gen_ai.system` by default, or `gen_ai.provider.name` when latest GenAI
+    semantic conventions are opted in
+  - `gen_ai.request.model`, `gen_ai.operation.name`,
+    `openclaw.provider`, `openclaw.model`, `openclaw.api`,
+    `openclaw.transport`, `openclaw.provider.request_id_hash` (bounded
+    SHA-based hash of the upstream provider request id; raw ids are not
+    exported)
+- `openclaw.tool.execution`
+  - `gen_ai.tool.name`, `openclaw.toolName`, `openclaw.errorCategory`,
+    `openclaw.tool.params.*`
+- `openclaw.exec`
+  - `openclaw.exec.target`, `openclaw.exec.mode`, `openclaw.outcome`,
+    `openclaw.failureKind`, `openclaw.exec.command_length`,
+    `openclaw.exec.exit_code`, `openclaw.exec.timed_out`
+- `openclaw.webhook.processed`
+  - `openclaw.channel`, `openclaw.webhook`, `openclaw.chatId`
+- `openclaw.webhook.error`
+  - `openclaw.channel`, `openclaw.webhook`, `openclaw.chatId`,
+    `openclaw.error`
+- `openclaw.message.processed`
+  - `openclaw.channel`, `openclaw.outcome`, `openclaw.chatId`,
+    `openclaw.messageId`, `openclaw.reason`
+- `openclaw.message.delivery`
+  - `openclaw.channel`, `openclaw.delivery.kind`, `openclaw.outcome`,
+    `openclaw.errorCategory`, `openclaw.delivery.result_count`
+- `openclaw.session.stuck`
+  - `openclaw.state`, `openclaw.ageMs`, `openclaw.queueDepth`
+- `openclaw.context.assembled`
+  - `openclaw.prompt.size`, `openclaw.history.size`,
+    `openclaw.context.tokens`, `openclaw.errorCategory` (no prompt,
+    history, response, or session-key content)
+- `openclaw.tool.loop`
+  - `openclaw.toolName`, `openclaw.outcome`, `openclaw.iterations`,
+    `openclaw.errorCategory` (no loop messages, params, or tool output)
+- `openclaw.memory.pressure`
+  - `openclaw.memory.level`, `openclaw.memory.heap_used_bytes`,
+    `openclaw.memory.rss_bytes`
+
+When content capture is explicitly enabled, model/tool spans can also include
+bounded, redacted `openclaw.content.*` attributes for the specific content
+classes you opted into.
+
+### Sampling + flushing
+
+- Trace sampling: `diagnostics.otel.sampleRate` (0.0–1.0, root spans only).
+- Metric export interval: `diagnostics.otel.flushIntervalMs` (min 1000ms).
+
+### Protocol notes
+
+- OTLP/HTTP endpoints can be set via `diagnostics.otel.endpoint` or
+  `OTEL_EXPORTER_OTLP_ENDPOINT`.
+- If the endpoint already contains `/v1/traces` or `/v1/metrics`, it is used as-is.
+- If the endpoint already contains `/v1/logs`, it is used as-is for logs.
+- `OTEL_SEMCONV_STABILITY_OPT_IN=gen_ai_latest_experimental` controls only the
+  GenAI span provider attribute shape. Existing dashboards that read
+  `gen_ai.system` can keep the default until they migrate.
+- `OPENCLAW_OTEL_PRELOADED=1` reuses an externally registered OpenTelemetry SDK
+  for traces/metrics instead of starting a plugin-owned NodeSDK.
+- `diagnostics.otel.logs` enables OTLP log export for the main logger output.
+
+### Log export behavior
+
+- OTLP logs use the same structured records written to `logging.file`.
+- Respect `logging.level` (file log level). Console redaction does **not** apply
+  to OTLP logs.
+- High-volume installs should prefer OTLP collector sampling/filtering.
 
 ## Troubleshooting tips
 
@@ -208,7 +483,5 @@ For OTLP export to a collector, see [OpenTelemetry export](/gateway/opentelemetr
 
 ## Related
 
-- [OpenTelemetry export](/gateway/opentelemetry) — OTLP/HTTP export, metric/span catalog, privacy model
-- [Diagnostics flags](/diagnostics/flags) — targeted debug-log flags
-- [Gateway logging internals](/gateway/logging) — WS log styles, subsystem prefixes, and console capture
-- [Configuration reference](/gateway/configuration-reference#diagnostics) — full `diagnostics.*` field reference
+- [Gateway Logging Internals](/gateway/logging) — WS log styles, subsystem prefixes, and console capture
+- [Diagnostics](/gateway/configuration-reference#diagnostics) — OpenTelemetry export and cache trace config

docs/nodes/talk.md

@@ -63,7 +63,6 @@ Supported keys:
       },
       system: {},
     },
-    speechLocale: "ru-RU",
     silenceTimeoutMs: 1500,
     interruptOnSpeech: true,
   },
@@ -79,7 +78,6 @@ Defaults:
 - `providers.elevenlabs.modelId`: defaults to `eleven_v3` when unset.
 - `providers.mlx.modelId`: defaults to `mlx-community/Soprano-80M-bf16` when unset.
 - `providers.elevenlabs.apiKey`: falls back to `ELEVENLABS_API_KEY` (or gateway shell profile if available).
-- `speechLocale`: optional BCP 47 locale id for on-device Talk speech recognition on iOS/macOS. Leave unset to use the device default.
 - `outputFormat`: defaults to `pcm_44100` on macOS/iOS and `pcm_24000` on Android (set `mp3_*` to force MP3 streaming)
 
 ## macOS UI

docs/plugins/architecture-internals.md

@@ -771,11 +771,9 @@ Security guardrail: every `openclaw.extensions` entry must stay inside the plugi
 directory after symlink resolution. Entries that escape the package directory are
 rejected.
 
-Security note: `openclaw plugins install` installs plugin dependencies with a
-project-local `npm install --omit=dev --ignore-scripts` (no lifecycle scripts,
-no dev dependencies at runtime), ignoring inherited global npm install settings.
-Keep plugin dependency trees "pure JS/TS" and avoid packages that require
-`postinstall` builds.
+Security note: `openclaw plugins install` installs plugin dependencies with
+`npm install --omit=dev --ignore-scripts` (no lifecycle scripts, no dev dependencies at runtime). Keep plugin dependency
+trees "pure JS/TS" and avoid packages that require `postinstall` builds.
 
 Optional: `openclaw.setupEntry` can point at a lightweight setup-only module.
 When OpenClaw needs setup surfaces for a disabled channel plugin, or
@@ -905,7 +903,7 @@ normalized facts warn if the parsed npm package name drifts from that identity.
 They also warn when `defaultChoice` is invalid or points at a source that is
 not available, and when npm integrity metadata is present without a valid npm
 source. Consumers should treat `installSource` as an additive optional field so
-hand-built entries and catalog shims do not have to synthesize it.
+older hand-built entries and compatibility shims do not have to synthesize it.
 This lets onboarding and diagnostics explain source-plane state without
 importing plugin runtime.
 
@@ -914,15 +912,17 @@ Official external npm entries should prefer an exact `npmSpec` plus
 compatibility, but they surface source-plane warnings so the catalog can move
 toward pinned, integrity-checked installs without breaking existing plugins.
 When onboarding installs from a local catalog path, it records a managed plugin
-plugin index entry with `source: "path"` and a workspace-relative
+install ledger entry with `source: "path"` and a workspace-relative
 `sourcePath` when possible. The absolute operational load path stays in
 `plugins.load.paths`; the install record avoids duplicating local workstation
 paths into long-lived config. This keeps local development installs visible to
 source-plane diagnostics without adding a second raw filesystem-path disclosure
-surface. The persisted `plugins/installs.json` plugin index is the install
-source of truth and can be refreshed without loading plugin runtime modules.
-Its `installRecords` map is durable even when a plugin manifest is missing or
-invalid; its `plugins` array is a rebuildable manifest/cache view.
+surface. Legacy `plugins.installs` config entries are still read as a
+compatibility fallback while the state-managed `plugins/installs.json` ledger
+becomes the install source of truth.
+`openclaw doctor --fix` migrates those legacy config entries into the managed
+ledger and refreshes the cold registry index without loading plugin runtime
+modules.
 
 ## Context engine plugins
 

docs/plugins/codex-harness.md

@@ -20,12 +20,6 @@ If you are trying to orient yourself, start with
 `openai/gpt-5.5` is the model ref, `codex` is the runtime, and Telegram,
 Discord, Slack, or another channel remains the communication surface.
 
-The same plugin also owns the native `/codex` chat-control command surface. If
-the plugin is enabled and the user asks to bind, resume, steer, stop, or inspect
-Codex threads from chat, agents should prefer `/codex ...` over ACP. ACP remains
-the explicit fallback when the user asks for ACP/acpx or is testing the ACP
-Codex adapter.
-
 Native Codex turns keep OpenClaw plugin hooks as the public compatibility layer.
 These are in-process OpenClaw hooks, not Codex `hooks.json` command hooks:
 
@@ -34,7 +28,6 @@ These are in-process OpenClaw hooks, not Codex `hooks.json` command hooks:
 - `llm_input`, `llm_output`
 - `before_tool_call`, `after_tool_call`
 - `before_message_write` for mirrored transcript records
-- `before_agent_finalize` through Codex `Stop` relay
 - `agent_end`
 
 Plugins can also register runtime-neutral tool-result middleware to rewrite
@@ -110,9 +103,7 @@ Codex after changing config.
 ## Requirements
 
 - OpenClaw with the bundled `codex` plugin available.
-- Codex app-server `0.125.0` or newer. The bundled plugin manages a compatible
-  Codex app-server binary by default, so local `codex` commands on `PATH` do
-  not affect normal harness startup.
+- Codex app-server `0.118.0` or newer.
 - Codex auth available to the app-server process.
 
 The plugin blocks older or unversioned app-server handshakes. That keeps
@@ -348,18 +339,12 @@ fallback catalog:
 
 ## App-server connection and policy
 
-By default, the plugin starts OpenClaw's managed Codex binary locally with:
+By default, the plugin starts Codex locally with:
 
 ```bash
 codex app-server --listen stdio://
 ```
 
-The managed binary is declared as a bundled plugin runtime dependency and staged
-with the rest of the `codex` plugin dependencies. This keeps the app-server
-version tied to the bundled plugin instead of whichever separate Codex CLI
-happens to be installed locally. Set `appServer.command` only when you
-intentionally want to run a different executable.
-
 By default, OpenClaw starts local Codex harness sessions in YOLO mode:
 `approvalPolicy: "never"`, `approvalsReviewer: "user"`, and
 `sandbox: "danger-full-access"`. This is the trusted local operator posture used
@@ -428,7 +413,7 @@ Supported `appServer` fields:
 | Field               | Default                                  | Meaning                                                                                                      |
 | ------------------- | ---------------------------------------- | ------------------------------------------------------------------------------------------------------------ |
 | `transport`         | `"stdio"`                                | `"stdio"` spawns Codex; `"websocket"` connects to `url`.                                                     |
-| `command`           | managed Codex binary                     | Executable for stdio transport. Leave unset to use the managed binary; set it only for an explicit override. |
+| `command`           | `"codex"`                                | Executable for stdio transport.                                                                              |
 | `args`              | `["app-server", "--listen", "stdio://"]` | Arguments for stdio transport.                                                                               |
 | `url`               | unset                                    | WebSocket app-server URL.                                                                                    |
 | `authToken`         | unset                                    | Bearer token for WebSocket transport.                                                                        |
@@ -440,7 +425,8 @@ Supported `appServer` fields:
 | `approvalsReviewer` | `"user"`                                 | Use `"auto_review"` to let Codex review native approval prompts. `guardian_subagent` remains a legacy alias. |
 | `serviceTier`       | unset                                    | Optional Codex app-server service tier: `"fast"`, `"flex"`, or `null`. Invalid legacy values are ignored.    |
 
-Environment overrides remain available for local testing:
+The older environment variables still work as fallbacks for local testing when
+the matching config field is unset:
 
 - `OPENCLAW_CODEX_APP_SERVER_BIN`
 - `OPENCLAW_CODEX_APP_SERVER_ARGS`
@@ -448,9 +434,6 @@ Environment overrides remain available for local testing:
 - `OPENCLAW_CODEX_APP_SERVER_APPROVAL_POLICY`
 - `OPENCLAW_CODEX_APP_SERVER_SANDBOX`
 
-`OPENCLAW_CODEX_APP_SERVER_BIN` bypasses the managed binary when
-`appServer.command` is unset.
-
 `OPENCLAW_CODEX_APP_SERVER_GUARDIAN=1` was removed. Use
 `plugins.entries.codex.config.appServer.mode: "guardian"` instead, or
 `OPENCLAW_CODEX_APP_SERVER_MODE=guardian` for one-off local testing. Config is
@@ -568,7 +551,7 @@ normal turns. On the next message, OpenClaw resumes that Codex thread, passes th
 currently selected OpenClaw model into app-server, and keeps extended history
 enabled.
 
-The command surface requires Codex app-server `0.125.0` or newer. Individual
+The command surface requires Codex app-server `0.118.0` or newer. Individual
 control methods are reported as `unsupported by this Codex app-server` if a
 future or custom app-server does not expose that JSON-RPC method.
 
@@ -584,10 +567,10 @@ The Codex harness has three hook layers:
 
 OpenClaw does not use project or global Codex `hooks.json` files to route
 OpenClaw plugin behavior. For the supported native tool and permission bridge,
-OpenClaw injects per-thread Codex config for `PreToolUse`, `PostToolUse`,
-`PermissionRequest`, and `Stop`. Other Codex hooks such as `SessionStart` and
-`UserPromptSubmit` remain Codex-level controls; they are not exposed as
-OpenClaw plugin hooks in the v1 contract.
+OpenClaw injects per-thread Codex config for `PreToolUse`, `PostToolUse`, and
+`PermissionRequest`. Other Codex hooks such as `SessionStart`,
+`UserPromptSubmit`, and `Stop` remain Codex-level controls; they are not exposed
+as OpenClaw plugin hooks in the v1 contract.
 
 For OpenClaw dynamic tools, OpenClaw executes the tool after Codex asks for the
 call, so OpenClaw fires the plugin and middleware behavior it owns in the
@@ -614,30 +597,31 @@ around that boundary.
 
 Supported in Codex runtime v1:
 
-| Surface                                       | Support                                 | Why                                                                                                                                                                                                   |
-| --------------------------------------------- | --------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| OpenAI model loop through Codex               | Supported                               | Codex app-server owns the OpenAI turn, native thread resume, and native tool continuation.                                                                                                            |
-| OpenClaw channel routing and delivery         | Supported                               | Telegram, Discord, Slack, WhatsApp, iMessage, and other channels stay outside the model runtime.                                                                                                      |
-| OpenClaw dynamic tools                        | Supported                               | Codex asks OpenClaw to execute these tools, so OpenClaw stays in the execution path.                                                                                                                  |
-| Prompt and context plugins                    | Supported                               | OpenClaw builds prompt overlays and projects context into the Codex turn before starting or resuming the thread.                                                                                      |
-| Context engine lifecycle                      | Supported                               | Assemble, ingest or after-turn maintenance, and context-engine compaction coordination run for Codex turns.                                                                                           |
-| Dynamic tool hooks                            | Supported                               | `before_tool_call`, `after_tool_call`, and tool-result middleware run around OpenClaw-owned dynamic tools.                                                                                            |
-| Lifecycle hooks                               | Supported as adapter observations       | `llm_input`, `llm_output`, `agent_end`, `before_compaction`, and `after_compaction` fire with honest Codex-mode payloads.                                                                             |
-| Final-answer revision gate                    | Supported through the native hook relay | Codex `Stop` is relayed to `before_agent_finalize`; `revise` asks Codex for one more model pass before finalization.                                                                                  |
-| Native shell, patch, and MCP block or observe | Supported through the native hook relay | Codex `PreToolUse` and `PostToolUse` are relayed for committed native tool surfaces, including MCP payloads on Codex app-server `0.125.0` or newer. Blocking is supported; argument rewriting is not. |
-| Native permission policy                      | Supported through the native hook relay | Codex `PermissionRequest` can be routed through OpenClaw policy where the runtime exposes it. If OpenClaw returns no decision, Codex continues through its normal guardian or user approval path.     |
-| App-server trajectory capture                 | Supported                               | OpenClaw records the request it sent to app-server and the app-server notifications it receives.                                                                                                      |
+| Surface                                 | Support                                 | Why                                                                                                                                        |
+| --------------------------------------- | --------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
+| OpenAI model loop through Codex         | Supported                               | Codex app-server owns the OpenAI turn, native thread resume, and native tool continuation.                                                 |
+| OpenClaw channel routing and delivery   | Supported                               | Telegram, Discord, Slack, WhatsApp, iMessage, and other channels stay outside the model runtime.                                           |
+| OpenClaw dynamic tools                  | Supported                               | Codex asks OpenClaw to execute these tools, so OpenClaw stays in the execution path.                                                       |
+| Prompt and context plugins              | Supported                               | OpenClaw builds prompt overlays and projects context into the Codex turn before starting or resuming the thread.                           |
+| Context engine lifecycle                | Supported                               | Assemble, ingest or after-turn maintenance, and context-engine compaction coordination run for Codex turns.                                |
+| Dynamic tool hooks                      | Supported                               | `before_tool_call`, `after_tool_call`, and tool-result middleware run around OpenClaw-owned dynamic tools.                                 |
+| Lifecycle hooks                         | Supported as adapter observations       | `llm_input`, `llm_output`, `agent_end`, `before_compaction`, and `after_compaction` fire with honest Codex-mode payloads.                  |
+| Native shell and patch block or observe | Supported through the native hook relay | Codex `PreToolUse` and `PostToolUse` are relayed for the committed native tool surfaces. Blocking is supported; argument rewriting is not. |
+| Native permission policy                | Supported through the native hook relay | Codex `PermissionRequest` can be routed through OpenClaw policy where the runtime exposes it.                                              |
+| App-server trajectory capture           | Supported                               | OpenClaw records the request it sent to app-server and the app-server notifications it receives.                                           |
 
 Not supported in Codex runtime v1:
 
-| Surface                                             | V1 boundary                                                                                                                                     | Future path                                                                               |
-| --------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------- |
-| Native tool argument mutation                       | Codex native pre-tool hooks can block, but OpenClaw does not rewrite Codex-native tool arguments.                                               | Requires Codex hook/schema support for replacement tool input.                            |
-| Editable Codex-native transcript history            | Codex owns canonical native thread history. OpenClaw owns a mirror and can project future context, but should not mutate unsupported internals. | Add explicit Codex app-server APIs if native thread surgery is needed.                    |
-| `tool_result_persist` for Codex-native tool records | That hook transforms OpenClaw-owned transcript writes, not Codex-native tool records.                                                           | Could mirror transformed records, but canonical rewrite needs Codex support.              |
-| Rich native compaction metadata                     | OpenClaw observes compaction start and completion, but does not receive a stable kept/dropped list, token delta, or summary payload.            | Needs richer Codex compaction events.                                                     |
-| Compaction intervention                             | Current OpenClaw compaction hooks are notification-level in Codex mode.                                                                         | Add Codex pre/post compaction hooks if plugins need to veto or rewrite native compaction. |
-| Byte-for-byte model API request capture             | OpenClaw can capture app-server requests and notifications, but Codex core builds the final OpenAI API request internally.                      | Needs a Codex model-request tracing event or debug API.                                   |
+| Surface                                             | V1 boundary                                                                                                                                     | Future path                                                                                               |
+| --------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- |
+| Native tool argument mutation                       | Codex native pre-tool hooks can block, but OpenClaw does not rewrite Codex-native tool arguments.                                               | Requires Codex hook/schema support for replacement tool input.                                            |
+| Editable Codex-native transcript history            | Codex owns canonical native thread history. OpenClaw owns a mirror and can project future context, but should not mutate unsupported internals. | Add explicit Codex app-server APIs if native thread surgery is needed.                                    |
+| `tool_result_persist` for Codex-native tool records | That hook transforms OpenClaw-owned transcript writes, not Codex-native tool records.                                                           | Could mirror transformed records, but canonical rewrite needs Codex support.                              |
+| Rich native compaction metadata                     | OpenClaw observes compaction start and completion, but does not receive a stable kept/dropped list, token delta, or summary payload.            | Needs richer Codex compaction events.                                                                     |
+| Compaction intervention                             | Current OpenClaw compaction hooks are notification-level in Codex mode.                                                                         | Add Codex pre/post compaction hooks if plugins need to veto or rewrite native compaction.                 |
+| Stop or final-answer gating                         | Codex has native stop hooks, but OpenClaw does not expose final-answer gating as a v1 plugin contract.                                          | Future opt-in primitive with loop and timeout safeguards.                                                 |
+| Native MCP hook parity as a committed v1 surface    | The relay is generic, but OpenClaw has not version-gated and tested native MCP pre/post hook behavior end to end.                               | Add OpenClaw MCP relay tests and docs once the supported app-server protocol floor covers those payloads. |
+| Byte-for-byte model API request capture             | OpenClaw can capture app-server requests and notifications, but Codex core builds the final OpenAI API request internally.                      | Needs a Codex model-request tracing event or debug API.                                                   |
 
 ## Tools, media, and compaction
 
@@ -648,15 +632,9 @@ harness. Text, images, video, music, TTS, approvals, and messaging-tool output
 continue through the normal OpenClaw delivery path.
 
 The native hook relay is intentionally generic, but the v1 support contract is
-limited to the Codex-native tool and permission paths that OpenClaw tests. In
-the Codex runtime, that includes shell, patch, and MCP `PreToolUse`,
-`PostToolUse`, and `PermissionRequest` payloads. Do not assume every future
-Codex hook event is an OpenClaw plugin surface until the runtime contract names
-it.
-
-For `PermissionRequest`, OpenClaw only returns explicit allow or deny decisions
-when policy decides. A no-decision result is not an allow. Codex treats it as no
-hook decision and falls through to its own guardian or user approval path.
+limited to the Codex-native tool and permission paths that OpenClaw tests. Do not
+assume every future Codex hook event is an OpenClaw plugin surface until the
+runtime contract names it.
 
 Codex MCP tool approval elicitations are routed through OpenClaw's plugin
 approval flow when Codex marks `_meta.codex_approval_kind` as
@@ -699,9 +677,7 @@ explicitly set `embeddedHarness.fallback: "pi"`. Once Codex app-server is
 selected, its failures surface directly without extra fallback config.
 
 **The app-server is rejected:** upgrade Codex so the app-server handshake
-reports version `0.125.0` or newer. Same-version prereleases or build-suffixed
-versions such as `0.125.0-alpha.2` or `0.125.0+custom` are rejected because the
-stable `0.125.0` protocol floor is what OpenClaw tests.
+reports version `0.118.0` or newer.
 
 **Model discovery is slow:** lower `plugins.entries.codex.config.discovery.timeoutMs`
 or disable discovery.

docs/plugins/community.md

@@ -105,10 +105,6 @@ Connect OpenClaw to QQ via the QQ Bot API. Supports private chats, group
 mentions, channel messages, and rich media including voice, images, videos,
 and files.
 
-Current OpenClaw releases bundle QQ Bot. Use the bundled setup in
-[QQ Bot](/channels/qqbot) for normal installs; install this external plugin only
-when you intentionally want the Tencent-maintained standalone package.
-
 - **npm:** `@tencent-connect/openclaw-qqbot`
 - **repo:** [github.com/tencent-connect/openclaw-qqbot](https://github.com/tencent-connect/openclaw-qqbot)
 

docs/plugins/hooks.md

@@ -64,7 +64,6 @@ observation-only.
 - `before_prompt_build` — add dynamic context or system-prompt text before the model call
 - `before_agent_start` — compatibility-only combined phase; prefer the two hooks above
 - **`before_agent_reply`** — short-circuit the model turn with a synthetic reply or silence
-- **`before_agent_finalize`** — inspect the natural final answer and request one more model pass
 - `agent_end` — observe final messages, success state, and run duration
 
 **Conversation observation**
@@ -112,8 +111,8 @@ observation-only.
 - `event.params`
 - optional `event.runId`
 - optional `event.toolCallId`
-- context fields such as `ctx.agentId`, `ctx.sessionKey`, `ctx.sessionId`,
-  `ctx.runId`, `ctx.jobId` (set on cron-driven runs), and diagnostic `ctx.trace`
+- context fields such as `ctx.agentId`, `ctx.sessionKey`, `ctx.sessionId`, and
+  diagnostic `ctx.trace`
 
 It can return:
 
@@ -178,9 +177,6 @@ so your plugin does not depend on a legacy combined phase.
 
 `before_agent_start` and `agent_end` include `event.runId` when OpenClaw can
 identify the active run. The same value is also available on `ctx.runId`.
-Cron-driven runs also expose `ctx.jobId` (the originating cron job id) so
-plugin hooks can scope metrics, side effects, or state to a specific scheduled
-job.
 
 Use `model_call_started` and `model_call_ended` for provider-call telemetry
 that should not receive raw prompts, history, responses, headers, request
@@ -189,16 +185,7 @@ bodies, or provider request IDs. These hooks include stable metadata such as
 `durationMs`/`outcome`, and `upstreamRequestIdHash` when OpenClaw can derive a
 bounded provider request-id hash.
 
-`before_agent_finalize` runs only when a harness is about to accept a natural
-final assistant answer. It is not the `/stop` cancellation path and does not
-run when the user aborts a turn. Return `{ action: "revise", reason }` to ask
-the harness for one more model pass before finalization, `{ action:
-"finalize", reason? }` to force finalization, or omit a result to continue.
-Codex native `Stop` hooks are relayed into this hook as OpenClaw
-`before_agent_finalize` decisions.
-
-Non-bundled plugins that need `llm_input`, `llm_output`,
-`before_agent_finalize`, or `agent_end` must set:
+Non-bundled plugins that need `llm_input`, `llm_output`, or `agent_end` must set:
 
 ```json
 {

docs/plugins/manifest.md

@@ -508,11 +508,6 @@ runtime loads. Read-only channel setup/status discovery can use this metadata
 directly for configured external channels when no setup entry is available, or
 when `setup.requiresRuntime: false` declares setup runtime unnecessary.
 
-`channelConfigs` is plugin manifest metadata, not a new top-level user config
-section. Users still configure channel instances under `channels.<channel-id>`.
-OpenClaw reads manifest metadata to decide which plugin owns that configured
-channel before plugin runtime code executes.
-
 For a channel plugin, `configSchema` and `channelConfigs` describe different
 paths:
 
@@ -559,43 +554,6 @@ Each channel entry can include:
 | `description` | `string`                 | Short channel description for inspect and catalog surfaces.                               |
 | `preferOver`  | `string[]`               | Legacy or lower-priority plugin ids this channel should outrank in selection surfaces.    |
 
-### Replacing another channel plugin
-
-Use `preferOver` when your plugin is the preferred owner for a channel id that
-another plugin can also provide. Common cases are a renamed plugin id, a
-standalone plugin that supersedes a bundled plugin, or a maintained fork that
-keeps the same channel id for config compatibility.
-
-```json
-{
-  "id": "acme-chat",
-  "channels": ["chat"],
-  "channelConfigs": {
-    "chat": {
-      "schema": {
-        "type": "object",
-        "additionalProperties": false,
-        "properties": {
-          "webhookUrl": { "type": "string" }
-        }
-      },
-      "preferOver": ["chat"]
-    }
-  }
-}
-```
-
-When `channels.chat` is configured, OpenClaw considers both the channel id and
-the preferred plugin id. If the lower-priority plugin was only selected because
-it is bundled or enabled by default, OpenClaw disables it in the effective
-runtime config so one plugin owns the channel and its tools. Explicit user
-selection still wins: if the user explicitly enables both plugins, OpenClaw
-preserves that choice and reports duplicate channel/tool diagnostics instead of
-silently changing the requested plugin set.
-
-Keep `preferOver` scoped to plugin ids that can really provide the same channel.
-It is not a general priority field and it does not rename user config keys.
-
 ## modelSupport reference
 
 Use `modelSupport` when OpenClaw should infer your provider plugin from

docs/plugins/sdk-agent-harness.md

@@ -46,23 +46,6 @@ Before a harness is selected, OpenClaw has already resolved:
 That split is intentional. A harness runs a prepared attempt; it does not pick
 providers, replace channel delivery, or silently switch models.
 
-The prepared attempt also includes `params.runtimePlan`, an OpenClaw-owned
-policy bundle for runtime decisions that must stay shared across PI and native
-harnesses:
-
-- `runtimePlan.tools.normalize(...)` and
-  `runtimePlan.tools.logDiagnostics(...)` for provider-aware tool schema policy
-- `runtimePlan.transcript.resolvePolicy(...)` for transcript sanitization and
-  tool-call repair policy
-- `runtimePlan.delivery.isSilentPayload(...)` for shared `NO_REPLY` and media
-  delivery suppression
-- `runtimePlan.outcome.classifyRunResult(...)` for model fallback classification
-- `runtimePlan.observability` for resolved provider/model/harness metadata
-
-Harnesses may use the plan for decisions that need to match PI behavior, but
-should still treat it as host-owned attempt state. Do not mutate it or use it to
-switch providers/models inside a turn.
-
 ## Register a harness
 
 **Import:** `openclaw/plugin-sdk/agent-harness`
@@ -159,11 +142,9 @@ Codex provider and harness for compatibility.
 For operator setup, model prefix examples, and Codex-only configs, see
 [Codex Harness](/plugins/codex-harness).
 
-OpenClaw requires Codex app-server `0.125.0` or newer. The Codex plugin checks
+OpenClaw requires Codex app-server `0.118.0` or newer. The Codex plugin checks
 the app-server initialize handshake and blocks older or unversioned servers so
-OpenClaw only runs against the protocol surface it has been tested with. The
-`0.125.0` floor includes the native MCP hook payload support that landed in
-Codex `0.124.0`, while pinning OpenClaw to the newer tested stable line.
+OpenClaw only runs against the protocol surface it has been tested with.
 
 ### Tool-result middleware
 
@@ -179,16 +160,6 @@ middleware, but new result transforms should use the runtime-neutral API.
 The Pi-only `api.registerEmbeddedExtensionFactory(...)` hook has been removed;
 Pi tool-result transforms must use runtime-neutral middleware.
 
-### Terminal outcome classification
-
-Native harnesses that own their own protocol projection can use
-`classifyAgentHarnessTerminalOutcome(...)` from
-`openclaw/plugin-sdk/agent-harness-runtime` when a completed turn produced no
-visible assistant text. The helper returns `empty`, `reasoning-only`, or
-`planning-only` so OpenClaw's fallback policy can decide whether to retry on a
-different model. It intentionally leaves prompt errors, in-flight turns, and
-intentional silent replies such as `NO_REPLY` unclassified.
-
 ### Native Codex harness mode
 
 The bundled `codex` harness is the native Codex mode for embedded OpenClaw

docs/plugins/sdk-migration.md

@@ -262,7 +262,6 @@ releases.
   | `plugin-sdk/inbound-reply-dispatch` | Inbound reply helpers | Shared record-and-dispatch helpers |
   | `plugin-sdk/messaging-targets` | Messaging target parsing | Target parsing/matching helpers |
   | `plugin-sdk/outbound-media` | Outbound media helpers | Shared outbound media loading |
-  | `plugin-sdk/outbound-send-deps` | Outbound send dependency helpers | Lightweight `resolveOutboundSendDep` lookup without importing the full outbound runtime |
   | `plugin-sdk/outbound-runtime` | Outbound runtime helpers | Outbound delivery, identity/send delegate, session, formatting, and payload planning helpers |
   | `plugin-sdk/thread-bindings-runtime` | Thread-binding helpers | Thread-binding lifecycle and adapter helpers |
   | `plugin-sdk/agent-media-payload` | Legacy media payload helpers | Agent media payload builder for legacy field layouts |

docs/plugins/sdk-provider-plugins.md

@@ -626,13 +626,7 @@ API key auth, and dynamic model resolution.
           label: "Acme Video",
           capabilities: {
             generate: { maxVideos: 1, maxDurationSeconds: 10, supportsResolution: true },
-            imageToVideo: {
-              enabled: true,
-              maxVideos: 1,
-              maxInputImages: 1,
-              maxInputImagesByModel: { "acme/reference-to-video": 9 },
-              maxDurationSeconds: 5,
-            },
+            imageToVideo: { enabled: true, maxVideos: 1, maxInputImages: 1, maxDurationSeconds: 5 },
             videoToVideo: { enabled: false },
           },
           generateVideo: async (req) => ({ videos: [] }),

docs/plugins/sdk-setup.md

@@ -554,9 +554,8 @@ openclaw plugins install <package-name>
 
 <Info>
   For npm-sourced installs, `openclaw plugins install` runs
-  project-local `npm install --ignore-scripts` (no lifecycle scripts), ignoring
-  inherited global npm install settings. Keep plugin dependency trees pure JS/TS
-  and avoid packages that require `postinstall` builds.
+  `npm install --ignore-scripts` (no lifecycle scripts). Keep plugin dependency
+  trees pure JS/TS and avoid packages that require `postinstall` builds.
 </Info>
 
 Bundled OpenClaw-owned plugins are the only startup repair exception: when a

docs/plugins/sdk-subpaths.md

@@ -50,7 +50,6 @@ For the plugin authoring guide, see [Plugin SDK overview](/plugins/sdk-overview)
     | `plugin-sdk/inbound-reply-dispatch` | Shared inbound record-and-dispatch helpers |
     | `plugin-sdk/messaging-targets` | Target parsing/matching helpers |
     | `plugin-sdk/outbound-media` | Shared outbound media loading helpers |
-    | `plugin-sdk/outbound-send-deps` | Lightweight outbound send dependency lookup for channel adapters |
     | `plugin-sdk/outbound-runtime` | Outbound delivery, identity, send delegate, session, formatting, and payload planning helpers |
     | `plugin-sdk/poll-runtime` | Narrow poll normalization helpers |
     | `plugin-sdk/thread-bindings-runtime` | Thread-binding lifecycle and adapter helpers |
@@ -191,7 +190,7 @@ For the plugin authoring guide, see [Plugin SDK overview](/plugins/sdk-overview)
     | `plugin-sdk/models-provider-runtime` | `/models` command/provider reply helpers |
     | `plugin-sdk/skill-commands-runtime` | Skill command listing helpers |
     | `plugin-sdk/native-command-registry` | Native command registry/build/serialize helpers |
-    | `plugin-sdk/agent-harness` | Experimental trusted-plugin surface for low-level agent harnesses: harness types, active-run steer/abort helpers, OpenClaw tool bridge helpers, runtime-plan tool policy helpers, terminal outcome classification, tool progress formatting/detail helpers, and attempt result utilities |
+    | `plugin-sdk/agent-harness` | Experimental trusted-plugin surface for low-level agent harnesses: harness types, active-run steer/abort helpers, OpenClaw tool bridge helpers, tool progress formatting/detail helpers, and attempt result utilities |
     | `plugin-sdk/provider-zai-endpoint` | Z.AI endpoint detection helpers |
     | `plugin-sdk/infra-runtime` | System event/heartbeat helpers |
     | `plugin-sdk/collection-runtime` | Small bounded cache helpers |

docs/providers/azure-speech.md

@@ -1,119 +0,0 @@
----
-summary: "Azure AI Speech text-to-speech for OpenClaw replies"
-read_when:
-  - You want Azure Speech synthesis for outbound replies
-  - You need native Ogg Opus voice-note output from Azure Speech
-title: "Azure Speech"
----
-
-Azure Speech is an Azure AI Speech text-to-speech provider. In OpenClaw it
-synthesizes outbound reply audio as MP3 by default, native Ogg/Opus for voice
-notes, and 8 kHz mulaw audio for telephony channels such as Voice Call.
-
-OpenClaw uses the Azure Speech REST API directly with SSML and sends the
-provider-owned output format through `X-Microsoft-OutputFormat`.
-
-| Detail                  | Value                                                                                                          |
-| ----------------------- | -------------------------------------------------------------------------------------------------------------- |
-| Website                 | [Azure AI Speech](https://azure.microsoft.com/products/ai-services/ai-speech)                                  |
-| Docs                    | [Speech REST text-to-speech](https://learn.microsoft.com/azure/ai-services/speech-service/rest-text-to-speech) |
-| Auth                    | `AZURE_SPEECH_KEY` plus `AZURE_SPEECH_REGION`                                                                  |
-| Default voice           | `en-US-JennyNeural`                                                                                            |
-| Default file output     | `audio-24khz-48kbitrate-mono-mp3`                                                                              |
-| Default voice-note file | `ogg-24khz-16bit-mono-opus`                                                                                    |
-
-## Getting started
-
-<Steps>
-  <Step title="Create an Azure Speech resource">
-    In the Azure portal, create a Speech resource. Copy **KEY 1** from
-    Resource Management > Keys and Endpoint, and copy the resource location
-    such as `eastus`.
-
-    ```
-    AZURE_SPEECH_KEY=<speech-resource-key>
-    AZURE_SPEECH_REGION=eastus
-    ```
-
-  </Step>
-  <Step title="Select Azure Speech in messages.tts">
-    ```json5
-    {
-      messages: {
-        tts: {
-          auto: "always",
-          provider: "azure-speech",
-          providers: {
-            "azure-speech": {
-              voice: "en-US-JennyNeural",
-              lang: "en-US",
-            },
-          },
-        },
-      },
-    }
-    ```
-  </Step>
-  <Step title="Send a message">
-    Send a reply through any connected channel. OpenClaw synthesizes the audio
-    with Azure Speech and delivers MP3 for standard audio, or Ogg/Opus when
-    the channel expects a voice note.
-  </Step>
-</Steps>
-
-## Configuration options
-
-| Option                  | Path                                                        | Description                                                                                           |
-| ----------------------- | ----------------------------------------------------------- | ----------------------------------------------------------------------------------------------------- |
-| `apiKey`                | `messages.tts.providers.azure-speech.apiKey`                | Azure Speech resource key. Falls back to `AZURE_SPEECH_KEY`, `AZURE_SPEECH_API_KEY`, or `SPEECH_KEY`. |
-| `region`                | `messages.tts.providers.azure-speech.region`                | Azure Speech resource region. Falls back to `AZURE_SPEECH_REGION` or `SPEECH_REGION`.                 |
-| `endpoint`              | `messages.tts.providers.azure-speech.endpoint`              | Optional Azure Speech endpoint/base URL override.                                                     |
-| `baseUrl`               | `messages.tts.providers.azure-speech.baseUrl`               | Optional Azure Speech base URL override.                                                              |
-| `voice`                 | `messages.tts.providers.azure-speech.voice`                 | Azure voice ShortName (default `en-US-JennyNeural`).                                                  |
-| `lang`                  | `messages.tts.providers.azure-speech.lang`                  | SSML language code (default `en-US`).                                                                 |
-| `outputFormat`          | `messages.tts.providers.azure-speech.outputFormat`          | Audio-file output format (default `audio-24khz-48kbitrate-mono-mp3`).                                 |
-| `voiceNoteOutputFormat` | `messages.tts.providers.azure-speech.voiceNoteOutputFormat` | Voice-note output format (default `ogg-24khz-16bit-mono-opus`).                                       |
-
-## Notes
-
-<AccordionGroup>
-  <Accordion title="Authentication">
-    Azure Speech uses a Speech resource key, not an Azure OpenAI key. The key
-    is sent as `Ocp-Apim-Subscription-Key`; OpenClaw derives
-    `https://<region>.tts.speech.microsoft.com` from `region` unless you
-    provide `endpoint` or `baseUrl`.
-  </Accordion>
-  <Accordion title="Voice names">
-    Use the Azure Speech voice `ShortName` value, for example
-    `en-US-JennyNeural`. The bundled provider can list voices through the
-    same Speech resource and filters voices marked deprecated or retired.
-  </Accordion>
-  <Accordion title="Audio outputs">
-    Azure accepts output formats such as `audio-24khz-48kbitrate-mono-mp3`,
-    `ogg-24khz-16bit-mono-opus`, and `riff-24khz-16bit-mono-pcm`. OpenClaw
-    requests Ogg/Opus for `voice-note` targets so channels can send native
-    voice bubbles without an extra MP3 conversion.
-  </Accordion>
-  <Accordion title="Alias">
-    `azure` is accepted as a provider alias for existing PRs and user config,
-    but new config should use `azure-speech` to avoid confusion with Azure
-    OpenAI model providers.
-  </Accordion>
-</AccordionGroup>
-
-## Related
-
-<CardGroup cols={2}>
-  <Card title="Text-to-speech" href="/tools/tts" icon="waveform-lines">
-    TTS overview, providers, and `messages.tts` config.
-  </Card>
-  <Card title="Configuration" href="/gateway/configuration" icon="gear">
-    Full config reference including `messages.tts` settings.
-  </Card>
-  <Card title="Providers" href="/providers" icon="grid">
-    All bundled OpenClaw providers.
-  </Card>
-  <Card title="Troubleshooting" href="/help/troubleshooting" icon="wrench">
-    Common issues and debugging steps.
-  </Card>
-</CardGroup>

docs/providers/fal.md

@@ -79,10 +79,10 @@ To use fal as the default image provider:
 The bundled `fal` video-generation provider defaults to
 `fal/fal-ai/minimax/video-01-live`.
 
-| Capability | Value                                                              |
-| ---------- | ------------------------------------------------------------------ |
-| Modes      | Text-to-video, single-image reference, Seedance reference-to-video |
-| Runtime    | Queue-backed submit/status/result flow for long-running jobs       |
+| Capability | Value                                                        |
+| ---------- | ------------------------------------------------------------ |
+| Modes      | Text-to-video, single-image reference                        |
+| Runtime    | Queue-backed submit/status/result flow for long-running jobs |
 
 <AccordionGroup>
   <Accordion title="Available video models">
@@ -94,10 +94,8 @@ The bundled `fal` video-generation provider defaults to
 
     - `fal/bytedance/seedance-2.0/fast/text-to-video`
     - `fal/bytedance/seedance-2.0/fast/image-to-video`
-    - `fal/bytedance/seedance-2.0/fast/reference-to-video`
     - `fal/bytedance/seedance-2.0/text-to-video`
     - `fal/bytedance/seedance-2.0/image-to-video`
-    - `fal/bytedance/seedance-2.0/reference-to-video`
 
   </Accordion>
 
@@ -115,25 +113,6 @@ The bundled `fal` video-generation provider defaults to
     ```
   </Accordion>
 
-  <Accordion title="Seedance 2.0 reference-to-video config example">
-    ```json5
-    {
-      agents: {
-        defaults: {
-          videoGenerationModel: {
-            primary: "fal/bytedance/seedance-2.0/fast/reference-to-video",
-          },
-        },
-      },
-    }
-    ```
-
-    Reference-to-video accepts up to 9 images, 3 videos, and 3 audio references
-    through the shared `video_generate` `images`, `videos`, and `audioRefs`
-    parameters, with at most 12 total reference files.
-
-  </Accordion>
-
   <Accordion title="HeyGen video-agent config example">
     ```json5
     {

docs/providers/google.md

@@ -252,8 +252,8 @@ The bundled `google` speech provider uses the Gemini API TTS path with
 
 - Default voice: `Kore`
 - Auth: `messages.tts.providers.google.apiKey`, `models.providers.google.apiKey`, `GEMINI_API_KEY`, or `GOOGLE_API_KEY`
-- Output: WAV for regular TTS attachments, Opus for voice-note targets, PCM for Talk/telephony
-- Voice-note output: Google PCM is wrapped as WAV and transcoded to 48 kHz Opus with `ffmpeg`
+- Output: WAV for regular TTS attachments, PCM for Talk/telephony
+- Native voice-note output: not supported on this Gemini API path because the API returns PCM rather than Opus
 
 To use Google as the default TTS provider:
 

docs/providers/index.md

@@ -31,7 +31,6 @@ Looking for chat channel docs (WhatsApp/Telegram/Discord/Slack/Mattermost (plugi
 - [Amazon Bedrock Mantle](/providers/bedrock-mantle)
 - [Anthropic (API + Claude CLI)](/providers/anthropic)
 - [Arcee AI (Trinity models)](/providers/arcee)
-- [Azure Speech](/providers/azure-speech)
 - [BytePlus (International)](/concepts/model-providers#byteplus-international)
 - [Chutes](/providers/chutes)
 - [Cloudflare AI Gateway](/providers/cloudflare-ai-gateway)

docs/providers/inworld.md

@@ -1,115 +0,0 @@
----
-summary: "Inworld streaming text-to-speech for OpenClaw replies"
-read_when:
-  - You want Inworld speech synthesis for outbound replies
-  - You need PCM telephony or OGG_OPUS voice-note output from Inworld
-title: "Inworld"
----
-
-Inworld is a streaming text-to-speech (TTS) provider. In OpenClaw it
-synthesizes outbound reply audio (MP3 by default, OGG_OPUS for voice notes)
-and PCM audio for telephony channels such as Voice Call.
-
-OpenClaw posts to Inworld's streaming TTS endpoint, concatenates the
-returned base64 audio chunks into a single buffer, and hands the result to
-the standard reply-audio pipeline.
-
-| Detail        | Value                                                       |
-| ------------- | ----------------------------------------------------------- |
-| Website       | [inworld.ai](https://inworld.ai)                            |
-| Docs          | [docs.inworld.ai/tts/tts](https://docs.inworld.ai/tts/tts)  |
-| Auth          | `INWORLD_API_KEY` (HTTP Basic, Base64 dashboard credential) |
-| Default voice | `Sarah`                                                     |
-| Default model | `inworld-tts-1.5-max`                                       |
-
-## Getting started
-
-<Steps>
-  <Step title="Set your API key">
-    Copy the credential from your Inworld dashboard (Workspace > API Keys)
-    and set it as an env var. The value is sent verbatim as the HTTP Basic
-    credential, so do not Base64-encode it again or convert it to a bearer
-    token.
-
-    ```
-    INWORLD_API_KEY=<base64-credential-from-dashboard>
-    ```
-
-  </Step>
-  <Step title="Select Inworld in messages.tts">
-    ```json5
-    {
-      messages: {
-        tts: {
-          auto: "always",
-          provider: "inworld",
-          providers: {
-            inworld: {
-              voiceId: "Sarah",
-              modelId: "inworld-tts-1.5-max",
-            },
-          },
-        },
-      },
-    }
-    ```
-  </Step>
-  <Step title="Send a message">
-    Send a reply through any connected channel. OpenClaw synthesizes the
-    audio with Inworld and delivers it as MP3 (or OGG_OPUS when the channel
-    expects a voice note).
-  </Step>
-</Steps>
-
-## Configuration options
-
-| Option        | Path                                         | Description                                                       |
-| ------------- | -------------------------------------------- | ----------------------------------------------------------------- |
-| `apiKey`      | `messages.tts.providers.inworld.apiKey`      | Base64 dashboard credential. Falls back to `INWORLD_API_KEY`.     |
-| `baseUrl`     | `messages.tts.providers.inworld.baseUrl`     | Override Inworld API base URL (default `https://api.inworld.ai`). |
-| `voiceId`     | `messages.tts.providers.inworld.voiceId`     | Voice identifier (default `Sarah`).                               |
-| `modelId`     | `messages.tts.providers.inworld.modelId`     | TTS model id (default `inworld-tts-1.5-max`).                     |
-| `temperature` | `messages.tts.providers.inworld.temperature` | Sampling temperature `0..2` (optional).                           |
-
-## Notes
-
-<AccordionGroup>
-  <Accordion title="Authentication">
-    Inworld uses HTTP Basic auth with a single Base64-encoded credential
-    string. Copy it verbatim from the Inworld dashboard. The provider sends
-    it as `Authorization: Basic <apiKey>` without any further encoding, so
-    do not Base64-encode it yourself and do not pass a bearer-style token.
-    See [TTS auth notes](/tools/tts#inworld-primary) for the same callout.
-  </Accordion>
-  <Accordion title="Models">
-    Supported model ids: `inworld-tts-1.5-max` (default),
-    `inworld-tts-1.5-mini`, `inworld-tts-1-max`, `inworld-tts-1`.
-  </Accordion>
-  <Accordion title="Audio outputs">
-    Replies use MP3 by default. When the channel target is `voice-note`
-    OpenClaw asks Inworld for `OGG_OPUS` so the audio plays as a native
-    voice bubble. Telephony synthesis uses raw `PCM` at 22050 Hz to feed
-    the telephony bridge.
-  </Accordion>
-  <Accordion title="Custom endpoints">
-    Override the API host with `messages.tts.providers.inworld.baseUrl`.
-    Trailing slashes are stripped before requests are sent.
-  </Accordion>
-</AccordionGroup>
-
-## Related
-
-<CardGroup cols={2}>
-  <Card title="Text-to-speech" href="/tools/tts" icon="waveform-lines">
-    TTS overview, providers, and `messages.tts` config.
-  </Card>
-  <Card title="Configuration" href="/gateway/configuration" icon="gear">
-    Full config reference including `messages.tts` settings.
-  </Card>
-  <Card title="Providers" href="/providers" icon="grid">
-    All bundled OpenClaw providers.
-  </Card>
-  <Card title="Troubleshooting" href="/help/troubleshooting" icon="wrench">
-    Common issues and debugging steps.
-  </Card>
-</CardGroup>

docs/providers/minimax.md

@@ -17,10 +17,10 @@ MiniMax also provides:
 
 Provider split:
 
-| Provider ID      | Auth    | Capabilities                                                                                        |
-| ---------------- | ------- | --------------------------------------------------------------------------------------------------- |
-| `minimax`        | API key | Text, image generation, music generation, video generation, image understanding, speech, web search |
-| `minimax-portal` | OAuth   | Text, image generation, music generation, video generation, image understanding, speech             |
+| Provider ID      | Auth    | Capabilities                                                    |
+| ---------------- | ------- | --------------------------------------------------------------- |
+| `minimax`        | API key | Text, image generation, image understanding, speech, web search |
+| `minimax-portal` | OAuth   | Text, image generation, image understanding, speech             |
 
 ## Built-in catalog
 
@@ -235,13 +235,6 @@ Both `minimax` and `minimax-portal` register `image_generate` with the same
 `image-01` model. API-key setups use `MINIMAX_API_KEY`; OAuth setups can use
 the bundled `minimax-portal` auth path instead.
 
-Image generation always uses MiniMax's dedicated image endpoint
-(`/v1/image_generation`) and ignores `models.providers.minimax.baseUrl`,
-since that field configures the chat/Anthropic-compatible base URL. Set
-`MINIMAX_API_HOST=https://api.minimaxi.com` to route image generation
-through the CN endpoint; the default global endpoint is
-`https://api.minimax.io`.
-
 When onboarding or API-key setup writes explicit `models.providers.minimax`
 entries, OpenClaw materializes `MiniMax-M2.7` and
 `MiniMax-M2.7-highspeed` as text-only chat models. Image understanding is
@@ -286,11 +279,10 @@ The bundled `minimax` plugin registers MiniMax T2A v2 as a speech provider for
 
 ### Music generation
 
-The bundled MiniMax plugin registers music generation through the shared
-`music_generate` tool for both `minimax` and `minimax-portal`.
+The bundled `minimax` plugin also registers music generation through the shared
+`music_generate` tool.
 
 - Default music model: `minimax/music-2.6`
-- OAuth music model: `minimax-portal/music-2.6`
 - Also supports `minimax/music-2.5` and `minimax/music-2.0`
 - Prompt controls: `lyrics`, `instrumental`, `durationSeconds`
 - Output format: `mp3`
@@ -316,11 +308,10 @@ See [Music Generation](/tools/music-generation) for shared tool parameters, prov
 
 ### Video generation
 
-The bundled MiniMax plugin registers video generation through the shared
-`video_generate` tool for both `minimax` and `minimax-portal`.
+The bundled `minimax` plugin also registers video generation through the shared
+`video_generate` tool.
 
 - Default video model: `minimax/MiniMax-Hailuo-2.3`
-- OAuth video model: `minimax-portal/MiniMax-Hailuo-2.3`
 - Modes: text-to-video and single-image reference flows
 - Supports `aspectRatio` and `resolution`
 

docs/providers/openai.md

@@ -543,8 +543,6 @@ For image-generation requests on a recognized Azure host, OpenClaw:
 - Sends the `api-key` header instead of `Authorization: Bearer`
 - Uses deployment-scoped paths (`/openai/deployments/{deployment}/...`)
 - Appends `?api-version=...` to each request
-- Uses a 600s default request timeout for Azure image-generation calls.
-  Per-call `timeoutMs` values still override this default.
 
 Other base URLs (public OpenAI, OpenAI-compatible proxies) keep the standard
 OpenAI image request shape.

docs/providers/volcengine.md

@@ -1,23 +1,20 @@
 ---
-summary: "Volcano Engine setup (Doubao models, coding endpoints, and Seed Speech TTS)"
+summary: "Volcano Engine setup (Doubao models, general + coding endpoints)"
 title: "Volcengine (Doubao)"
 read_when:
   - You want to use Volcano Engine or Doubao models with OpenClaw
   - You need the Volcengine API key setup
-  - You want to use Volcengine Speech text-to-speech
 ---
 
 The Volcengine provider gives access to Doubao models and third-party models
 hosted on Volcano Engine, with separate endpoints for general and coding
-workloads. The same bundled plugin can also register Volcengine Speech as a TTS
-provider.
+workloads.
 
-| Detail     | Value                                                      |
-| ---------- | ---------------------------------------------------------- |
-| Providers  | `volcengine` (general + TTS) + `volcengine-plan` (coding)  |
-| Model auth | `VOLCANO_ENGINE_API_KEY`                                   |
-| TTS auth   | `VOLCENGINE_TTS_API_KEY` or `BYTEPLUS_SEED_SPEECH_API_KEY` |
-| API        | OpenAI-compatible models, BytePlus Seed Speech TTS         |
+| Detail    | Value                                               |
+| --------- | --------------------------------------------------- |
+| Providers | `volcengine` (general) + `volcengine-plan` (coding) |
+| Auth      | `VOLCANO_ENGINE_API_KEY`                            |
+| API       | OpenAI-compatible                                   |
 
 ## Getting started
 
@@ -98,59 +95,6 @@ Both providers are configured from a single API key. Setup registers both automa
   </Tab>
 </Tabs>
 
-## Text-to-speech
-
-Volcengine TTS uses the BytePlus Seed Speech HTTP API and is configured
-separately from the OpenAI-compatible Doubao model API key. In the BytePlus
-console, open Seed Speech > Settings > API Keys and copy the API key, then set:
-
-```bash
-export VOLCENGINE_TTS_API_KEY="byteplus_seed_speech_api_key"
-export VOLCENGINE_TTS_RESOURCE_ID="seed-tts-1.0"
-```
-
-Then enable it in `openclaw.json`:
-
-```json5
-{
-  messages: {
-    tts: {
-      auto: "always",
-      provider: "volcengine",
-      providers: {
-        volcengine: {
-          apiKey: "byteplus_seed_speech_api_key",
-          voice: "en_female_anna_mars_bigtts",
-          speedRatio: 1.0,
-        },
-      },
-    },
-  },
-}
-```
-
-For voice-note targets, OpenClaw asks Volcengine for provider-native
-`ogg_opus`. For normal audio attachments, it asks for `mp3`. Provider aliases
-`bytedance` and `doubao` also resolve to the same speech provider.
-
-The default resource id is `seed-tts-1.0` because that is what BytePlus grants
-to newly created Seed Speech API keys in the default project. If your project
-has TTS 2.0 entitlement, set `VOLCENGINE_TTS_RESOURCE_ID=seed-tts-2.0`.
-
-<Warning>
-`VOLCANO_ENGINE_API_KEY` is for the ModelArk/Doubao model endpoints and is not a
-Seed Speech API key. TTS needs a Seed Speech API key from the BytePlus Speech
-Console, or a legacy Speech Console AppID/token pair.
-</Warning>
-
-Legacy AppID/token auth remains supported for older Speech Console applications:
-
-```bash
-export VOLCENGINE_TTS_APPID="speech_app_id"
-export VOLCENGINE_TTS_TOKEN="speech_access_token"
-export VOLCENGINE_TTS_CLUSTER="volcano_tts"
-```
-
 ## Advanced configuration
 
 <AccordionGroup>
@@ -168,10 +112,8 @@ export VOLCENGINE_TTS_CLUSTER="volcano_tts"
   </Accordion>
 
   <Accordion title="Environment variables for daemon processes">
-    If the Gateway runs as a daemon (launchd/systemd), make sure model and TTS
-    env vars such as `VOLCANO_ENGINE_API_KEY`, `VOLCENGINE_TTS_API_KEY`,
-    `BYTEPLUS_SEED_SPEECH_API_KEY`, `VOLCENGINE_TTS_APPID`, and
-    `VOLCENGINE_TTS_TOKEN` are available to that process (for example, in
+    If the Gateway runs as a daemon (launchd/systemd), make sure
+    `VOLCANO_ENGINE_API_KEY` is available to that process (for example, in
     `~/.openclaw/.env` or via `env.shellEnv`).
   </Accordion>
 </AccordionGroup>

docs/reference/RELEASING.md

@@ -49,10 +49,6 @@ OpenClaw has three public release lanes:
 - Run `pnpm build && pnpm ui:build` before `pnpm release:check` so the expected
   `dist/*` release artifacts and Control UI bundle exist for the pack
   validation step
-- Run `pnpm qa:otel:smoke` when validating release telemetry. It exercises
-  QA-lab through a local OTLP/HTTP receiver and verifies the exported trace
-  span names, bounded attributes, and content/identifier redaction without
-  requiring Opik, Langfuse, or another external collector.
 - Run `pnpm release:check` before every tagged release
 - Release checks now run in a separate manual workflow:
   `OpenClaw Release Checks`

docs/reference/memory-config.md

@@ -219,17 +219,6 @@ to an existing local file. `hf:` and HTTP(S) model references can still be used
 explicitly with `provider: "local"`, but they do not make `auto` select local
 before the model is available on disk.
 
-### Inline embedding timeout
-
-| Key                                 | Type     | Default          | Description                                                              |
-| ----------------------------------- | -------- | ---------------- | ------------------------------------------------------------------------ |
-| `sync.embeddingBatchTimeoutSeconds` | `number` | provider default | Override the timeout for inline embedding batches during memory indexing |
-
-Unset uses the provider default: 600 seconds for local/self-hosted providers
-such as `local`, `ollama`, and `lmstudio`, and 120 seconds for hosted providers.
-
-Increase this when local CPU-bound embedding batches are healthy but slow.
-
 ---
 
 ## Hybrid search config
@@ -358,10 +347,6 @@ Prevents re-embedding unchanged text during reindex or transcript updates.
 Available for `openai`, `gemini`, and `voyage`. OpenAI batch is typically
 fastest and cheapest for large backfills.
 
-This is separate from `sync.embeddingBatchTimeoutSeconds`, which controls inline
-embedding calls used by local/self-hosted providers and hosted providers when
-provider batch APIs are not active.
-
 ---
 
 ## Session memory search (experimental)