issues: read

permission-issues: read

permission-issues: read

GITHUB_TOKEN: ${{ github.token }}

- Skills CLI: allow `openclaw skills install` and `openclaw skills update` to target shared managed skills with `--global`. (#74466) Thanks @Marvae.

- Browser CLI: add `openclaw browser evaluate --timeout-ms` so long-running page functions can extend both the evaluate action and request timeout budgets. (#83447) Thanks @eefreenyc.

- QA-Lab: add a report-only dreaming shadow-trial scenario so candidate memory promotion can be evaluated without mutating `MEMORY.md`. Thanks @iFiras-Max1.

- Telegram: add allowlisted native DM draft previews for transient tool progress while keeping final answers on the normal persistent delivery path. (#83622) Thanks @akrimm702.

- Browser: enforce current-tab URL allowlist checks for `/act` evaluate/batch actions and `/highlight` routes while leaving tab-management actions unblocked. (#78523)

- CI: require real-behavior-proof verdict markers to come from the ClawSweeper GitHub App before accepting exact-head proof. (#83692)

- Control UI: stop the chat reading indicator from sticking after an assistant response finishes. (#83515) Thanks @njuboy11.

- Skills: reject empty or whitespace-only skill names and descriptions during quick validation. (#27061)

- Telegram: log successful outbound text and media deliveries with account, chat, message, operation, thread, reply, silent, and chunk metadata while keeping message bodies out of logs. Fixes #83196. (#83247) Thanks @jrwrest.

- Release stability: repair broad-gate regressions in requester-agent completion handoff, QA-Lab mock spawn attribution, Slack monitor test isolation, plugin uninstall peer fixtures, and Node-floor launcher contract coverage.

- Memory indexing: propagate memory directory creation failures immediately instead of reporting an unusable directory as ready. Thanks @he-yufeng.

- CLI/skills: require unique case-insensitive fallback matches in `openclaw skills info` so case-only collisions return not-found instead of showing guidance for the wrong skill. (#38713)

- direct-chat tool progress: optional native `sendMessageDraft` status preview when enabled and supported

Tool-progress preview updates are the short status lines shown while tools run, for example command execution, file reads, planning updates, patch summaries, or Codex preamble/commentary text in Codex app-server mode. Telegram keeps these enabled by default to match released OpenClaw behavior from `v2026.4.22` and later.

Direct chats can use native Telegram drafts for these tool-progress lines without persisting tool chatter into chat history. Native drafts stop before answer text starts; final answers stay on the normal persistent delivery path. This lane is off by default and should be gated to trusted DM IDs first:

```json

{

"channels": {

"telegram": {

"streaming": {

"mode": "partial",

"preview": {

"toolProgress": true,

"nativeToolProgress": true,

"nativeToolProgressAllowFrom": ["123456789"]

}

}

}

}

}

```

To keep the edited preview for answer text but hide tool-progress lines, set:

openclaw browser evaluate --timeout-ms 30000 --fn 'async () => { await window.ready; return true; }'

Use `evaluate --timeout-ms <ms>` when the page-side function may need longer

openclaw skills install <slug> --global

openclaw skills update <slug> --global

openclaw skills update --all --global

`search`/`install`/`update` use ClawHub directly. By default, `install` and

`update` target the active workspace `skills/` directory; with `--global`, they

target the shared managed skills directory. `list`/`info`/`check` still inspect

the local skills visible to the current workspace and config. Workspace-backed

commands resolve the target workspace from `--agent <id>`, then the current

working directory when it is inside a configured agent workspace, then the

default agent.

- `--global` targets the shared managed skills directory and cannot be combined

with `--agent <id>`.

- `update <slug>` updates a single tracked skill. Add `--global` to target the

shared managed skills directory instead of the workspace.

- `update --all` updates tracked ClawHub installs in the selected workspace, or

in the shared managed skills directory when combined with `--global`.

QA Lab includes a report-only scenario for exploring how a future dreaming

shadow trial could review a candidate memory before promotion. The scenario asks

an agent to compare a baseline answer with an answer that can use the candidate

memory, then write a local report with a verdict, reason, and risk flags.

This coverage is intentionally scoped to QA. It verifies that the report artifact

stays separate from `MEMORY.md` and that the agent does not claim the candidate

was promoted. It does not add production shadow-trial behavior or change the

deep-phase promotion engine.

**Troubleshooting: group @mention triggers typing then silence (no error)**

Symptom: a group/channel @mention shows the typing indicator and the gateway log reports `dispatch complete (queuedFinal=false, replies=0)`, but no message lands in the room. DMs to the same agent reply normally.

Cause: the group/channel visible-reply mode resolves to `"message_tool"`, so OpenClaw runs the turn but suppresses the final assistant text unless the agent calls `message(action=send)`. There is no error because suppression is the configured behavior. Normal group and channel turns default to `"automatic"`, so this symptom only appears when `messages.groupChat.visibleReplies` (or global `messages.visibleReplies`) is explicitly set to `"message_tool"`. Harness `defaultVisibleReplies` does not apply here — the group/channel resolver ignores it; it only affects direct/source chats (the Codex harness suppresses direct-chat finals that way).

Fix: either pick a stronger tool-calling model, remove the explicit `"message_tool"` override to fall back to the `"automatic"` default, or set `messages.groupChat.visibleReplies: "automatic"` to force visible replies for every group/channel request. The gateway hot-reloads `messages` config after the file is saved; only restart the gateway when file watching or config reload is disabled in the deployment.