- CLI/docs: call the canonical lowercase docs MCP search tool and surface MCP errors instead of returning empty search results. Fixes #82702. (#82704) Thanks @hclsys.

- QA-Lab: ignore heartbeat-only operational transcripts when capturing runtime parity cells so background checks cannot replace the scenario reply. (#80323) Thanks @100yenadmin.

- Gateway/exec approvals: wait for accepted async approval follow-up runs instead of direct-fallback sending duplicate completions when retries use different nonce keys. Fixes #82711. (#82717) Thanks @udaymanish6.

- Agents/subagents: mark completed subagent handoffs as ready for parent review so requester agents verify results and continue required follow-up work before reporting done.

- CLI/config: add `--dry-run` support to `openclaw config unset`, with `--json` output and allow-exec validation parity with `config set`/`config patch` dry-run handling. (#81895) Thanks @giodl73-repo.

- Memory-core: retry disabled dreaming cron cleanup until cron is available after startup, so persisted managed dreaming jobs are removed after restart. Fixes #82383. (#82389) Thanks @neeravmakwana.

- Providers/xAI: keep retired Grok 3, Grok 4 Fast, Grok 4.1 Fast, and Grok Code slugs out of model pickers while preserving compatibility resolution for existing configs.

- `Result` — latest visible `assistant` reply text, otherwise sanitized latest tool/toolResult text. Terminal failed runs do not reuse captured reply text.

- `Status` — `completed successfully` / `failed` / `timed out` / `unknown`.

- Compact runtime/token stats.

- A delivery instruction telling the requester agent to rewrite in normal assistant voice (not forward raw internal metadata).

- A review instruction telling the requester agent to verify the result before deciding whether the original task is done.

- Follow-up guidance telling the requester agent to continue the task or record a follow-up when the child result leaves more action.

- A final-update instruction for the no-more-action path, written in normal assistant voice without forwarding raw internal metadata.

</Accordion>

<Accordion title="Modes and ACP runtime">

expect(msg).toContain("</prompt-data>");

expect(msg).toContain("raw subagent reply");

expect(msg).toContain("Stats:");

expect(msg).toContain("A completed subagent task is ready for user delivery.");

expect(msg).toContain("Convert the result above into your normal assistant voice");

expect(msg).toContain("A completed subagent task is ready for parent review.");

expect(msg).toContain(

"Review/verify the result above before deciding whether the original task is done.",

);

expect(msg).toContain(

"If additional action is required, continue the task or record a follow-up; otherwise send a truthful user-facing update.",

);

expect(msg).toContain("Keep this internal context private");

expect(call?.params?.internalEvents?.[0]?.type).toBe("task_completion");

expect(call?.params?.internalEvents?.[0]?.taskLabel).toBe("do thing");

expect(msg).toContain("tokens 1.0k (in 12 / out 1.0k)");

expect(msg).toContain("prompt/cache 197.0k");

expect(msg).toContain("session_id: child-session-usage");

expect(msg).toContain("A completed subagent task is ready for user delivery.");

expect(msg).toContain("A completed subagent task is ready for parent review.");

expect(msg).toContain(

"If additional action is required, continue the task or record a follow-up; otherwise send a truthful user-facing update.",

);

expect(msg).toContain(

`Reply ONLY: ${SILENT_REPLY_TOKEN} if this exact result was already delivered to the user in this same turn.`,

);

return `Convert this completion into a concise internal orchestration update for your parent agent in your own words. Keep this internal context private (don't mention system/log/stats/session details or announce type). If this result is duplicate or no update is needed, reply ONLY: ${SILENT_REPLY_TOKEN}.`;

}

if (params.expectsCompletionMessage) {

return `A completed ${params.announceType} is ready for user delivery. Convert the result above into your normal assistant voice and send that user-facing update now. Keep this internal context private (don't mention system/log/stats/session details or announce type).`;

return `A completed ${params.announceType} is ready for parent review. Review/verify the result above before deciding whether the original task is done. If additional action is required, continue the task or record a follow-up; otherwise send a truthful user-facing update. Keep this internal context private (don't mention system/log/stats/session details or announce type).`;

}

return `A completed ${params.announceType} is ready for user delivery. Convert the result above into your normal assistant voice and send that user-facing update now. Keep this internal context private (don't mention system/log/stats/session details or announce type), and do not copy the internal event text verbatim. Reply ONLY: ${SILENT_REPLY_TOKEN} if this exact result was already delivered to the user in this same turn.`;

return `A completed ${params.announceType} is ready for parent review. Review/verify the result above before deciding whether the original task is done. If additional action is required, continue the task or record a follow-up; otherwise send a truthful user-facing update. Keep this internal context private (don't mention system/log/stats/session details or announce type), and do not copy the internal event text verbatim. Reply ONLY: ${SILENT_REPLY_TOKEN} if this exact result was already delivered to the user in this same turn.`;

}

function buildAnnounceSteerMessage(events: AgentInternalEvent[]): string {