fix: notify agent session on background exec completion by default by wenkang-xie · Pull Request #46926 · openclaw/openclaw

wenkang-xie · 2026-03-15T05:41:38Z

Summary

Background exec processes that complete successfully with empty output currently silently exit without notifying the parent agent session. This is the #1 UX gap in multi-agent orchestration workflows.

Problem

When an orchestrator agent (e.g., Hikari) dispatches a coding agent (Claude Code, Codex) via exec background:true, the coding agent finishes but the orchestrator is never woken up — users see silence until they manually check in.

Root cause: notifyOnExitEmptySuccess defaults to false, so successful exits with empty/cleared output skip the system event + heartbeat wake entirely.

Related issue: #18237

Changes

Change	Before	After
`notifyOnExitEmptySuccess` default	`false`	`true`
Exec exit wake coalesce delay	250ms	50ms
Config docs	"default: false"	"default: true"
Tests	Assert empty-success is skipped	Assert empty-success is emitted

Why

Agents should always know when background work finishes. A silent success is indistinguishable from a hang or crash from the orchestrator's perspective.
50ms coalesce is appropriate for exec exit events — they are time-sensitive in orchestration flows where the agent needs to report results or start the next phase immediately.
Backward compatible — users who prefer the old behavior can set tools.exec.notifyOnExitEmptySuccess: false.

Testing

All 24 tests in bash-tools.test.ts pass ✅
Test cases updated to reflect new default behavior

Fixes #18237

greptile-apps · 2026-03-15T05:44:58Z

Greptile Summary

This PR flips notifyOnExitEmptySuccess from opt-in to opt-out across the exec tool stack, ensuring orchestrator agents are always woken up when a background exec session completes with empty output. It also tightens the heartbeat coalesce window from the platform default to 50 ms for faster agent wake-up in multi-agent orchestration flows. Config docs and tests are updated consistently.

Default changed (bash-tools.exec.ts): defaults?.notifyOnExitEmptySuccess !== false now correctly makes true the default; backward compatibility is preserved via the explicit false opt-out.
Coalesce tightened (bash-tools.exec-runtime.ts): coalesceMs: 50 is a reasonable value for time-sensitive exec-exit events.
Tests updated (bash-tools.test.ts): The first NOOP_NOTIFY_CASES entry now correctly tests default behavior by passing {} to the tool factory (i.e., no explicit setting), matching the new intent.
Latent inconsistency (bash-tools.exec-runtime.ts line 327): runExecProcess still stores notifyOnExitEmptySuccess with opts.notifyOnExitEmptySuccess === true, which silently falls back to false when the option is omitted. Current callers always pass an explicit value so there is no active bug, but changing this to !== false would keep the lower-level API consistent with the new default.

Confidence Score: 4/5

Safe to merge; the behavior change is intentional, backward-compatible, and all current code paths pass explicit values so no silent regressions exist today.
The core logic change in createExecTool is small and correct. Current callers of runExecProcess always pass explicit values, so the === true inconsistency is a latent (not active) risk. Tests cover both the new default and the explicit opt-out path. The coalesce reduction to 50 ms is low risk.
src/agents/bash-tools.exec-runtime.ts — the === true guard on line 327 is inconsistent with the new default and should ideally be !== false.

Comments Outside Diff (1)

src/agents/bash-tools.exec-runtime.ts, line 327 (link)

runExecProcess still defaults notifyOnExitEmptySuccess to false

The PR changes the intent to "always notify by default" and correctly updates createExecTool to use !== false. However, runExecProcess still stores the value with a strict === true guard:
```
notifyOnExitEmptySuccess: opts.notifyOnExitEmptySuccess === true,
```
Because notifyOnExitEmptySuccess is typed as optional, any direct caller that omits it (or passes undefined) will get the old opt-in default of false, silently missing the new behavior. Current callers always pass explicit values so there is no active bug, but this creates a latent trap for future callers of runExecProcess.

For consistency with the PR's stated intent, this line should mirror the guard used in createExecTool:

This preserves the gateway path (which explicitly passes false) while making the implicit default true everywhere.

Prompt To Fix All With AI

This is a comment left during a code review.
Path: src/agents/bash-tools.exec-runtime.ts
Line: 327

Comment:
**`runExecProcess` still defaults `notifyOnExitEmptySuccess` to `false`**

The PR changes the intent to "always notify by default" and correctly updates `createExecTool` to use `!== false`. However, `runExecProcess` still stores the value with a strict `=== true` guard:

```ts
notifyOnExitEmptySuccess: opts.notifyOnExitEmptySuccess === true,
```

Because `notifyOnExitEmptySuccess` is typed as `optional`, any direct caller that omits it (or passes `undefined`) will get the old opt-in default of `false`, silently missing the new behavior. Current callers always pass explicit values so there is no active bug, but this creates a latent trap for future callers of `runExecProcess`.

For consistency with the PR's stated intent, this line should mirror the guard used in `createExecTool`:

```suggestion
    notifyOnExitEmptySuccess: opts.notifyOnExitEmptySuccess !== false,
```

This preserves the gateway path (which explicitly passes `false`) while making the implicit default `true` everywhere.

How can I resolve this? If you propose a fix, please make it concise.

_{Last reviewed commit: 73ac9de}

Previously, successful background exec processes with empty output would silently complete without notifying the parent agent session. This caused a major UX gap in multi-agent orchestration workflows where an orchestrator agent dispatches coding agents (Claude Code, Codex) in background — the orchestrator was never woken up on completion, leaving users waiting indefinitely. Changes: - Default notifyOnExitEmptySuccess to true (was false) Background processes that complete successfully now always enqueue a system event, even when stdout is empty. Agents should always know when their dispatched work finishes. - Align runExecProcess default with createExecTool (both use !== false) - Reduce exec exit wake coalesce delay to 50ms (was 250ms) Exec completion is time-sensitive for orchestration flows. - Update tests and config docs to reflect new defaults Users who want the old behavior can set: tools.exec.notifyOnExitEmptySuccess: false Fixes openclaw#18237

wenkang-xie · 2026-03-16T07:42:33Z

CI Failures — Unrelated to This PR

All failing checks are pre-existing upstream issues, none touch files changed in this PR:

Job	Failure	Related to PR?
`check`	`OpenClawPluginApi` unused import lint error	❌
`startup-memory`	Startup memory test	❌
`checks-windows (3,5,6)`	Windows short path mismatch (`RUNNER~1` vs `runneradmin`) in plugin discovery/hooks tests	❌
`channels`	Discord `native-command.commands-allowfrom.test.ts` — 4 assertion failures	❌
`extensions`	Synology Chat `z.string is not a function` TypeError	❌

This PR only modifies:

src/agents/bash-tools.exec.ts (1 line: default flip)
src/agents/bash-tools.exec-runtime.ts (2 lines: default flip + coalesce)
src/agents/bash-tools.test.ts (test case labels + factory args)
src/config/types.tools.ts (JSDoc update)
src/config/schema.help.ts (help text update)

The bash-tools.test.ts suite (24/24 tests) passes on all platforms including Windows.

clawsweeper · 2026-04-28T07:06:57Z

Thanks for the context here. I swept through the related work, and this is now duplicate or superseded.

Close as superseded: the useful chat/orchestration gap is now carried by the active narrower replacement at #39726, while this branch is stale/conflicting and would regress the current exec-event wake contract.

So I’m closing this here and keeping the remaining discussion on the canonical linked item.

Review details

Best possible solution:

Route the remaining empty-success chat wake work through #39726 and leave any broader global default change to a separate maintainer policy decision.

Do we have a high-confidence way to reproduce the issue?

Yes, source-level. Current main explicitly defaults notifyOnExitEmptySuccess off and drops completed empty-output exec notifications unless the flag is true; I did not run live behavior in this read-only review.

Is this the best way to solve the issue?

No, not as patched. The narrower chat-scoped replacement is the safer maintainable path, and this branch would need a rebase to preserve exec-event wake metadata plus docs/proof alignment.

Security review:

Security review cleared: The diff changes exec completion notification defaults, tests, and config-help text without adding dependencies, workflows, permissions, secret handling, package resolution, downloads, or new command-execution capability.

What I checked:

Current main default remains explicit-only: createExecTool still derives notifyOnExitEmptySuccess with defaults?.notifyOnExitEmptySuccess === true, so omitted config stays silent by default. (src/agents/bash-tools.exec.ts:1212, 9ac871c34b7d)
Current main suppresses empty successful completions: maybeNotifyOnExit returns before enqueueing an event when a completed background exec has no output unless session.notifyOnExitEmptySuccess is explicitly true. (src/agents/bash-tools.exec-runtime.ts:336, 9ac871c34b7d)
Current main requires exec-event wake metadata: Exec completion heartbeats now use source: "exec-event", intent: "event", reason: "exec-event", and coalesceMs: 0; heartbeat preflight only classifies the exact exec-event source/reason as an exec-event wake. (src/agents/bash-tools.exec-runtime.ts:347, 9ac871c34b7d)
This PR branch is stale against that wake contract: The PR patch changes the completion wake back to reason: exec:<session-id>:exit with no exec-event source/intent metadata, and live PR metadata reports the branch as conflicting. (src/agents/bash-tools.exec-runtime.ts:227, 043d64062703)
Active superseding replacement: agents: notify chat sessions on empty bg success #39726 is open, repaired by a member comment as the canonical contributor path, and scopes the remaining empty-success wake change to reply-capable chat contexts with explicit opt-out and non-chat silence preserved. (7b7b6bd5e6f7)
Public docs still describe default false: Current public gateway docs still say tools.exec.notifyOnExitEmptySuccess defaults to false, so any replacement that changes default behavior must sync docs/help surfaces. Public docs: docs/gateway/background-process.md. (docs/gateway/background-process.md:57, 9ac871c34b7d)

Likely related people:

steipete: Recent main history shows repeated exec, heartbeat, and test maintenance near the affected runtime/defaulting paths, including heartbeat wake compatibility and exec event routing work. (role: recent area contributor; confidence: high; commits: c6817d8d7ab9, 9180173f9a79, 864899d1b0c9; files: src/agents/bash-tools.exec-runtime.ts, src/agents/bash-tools.exec.ts, src/agents/bash-tools.test.ts)
rstar327: Authored the merged exec-event wake contract that this branch would accidentally undo. (role: introduced related wake behavior; confidence: medium; commits: 43fe68f9efd0; files: src/agents/bash-tools.exec-runtime.ts, src/agents/bash-tools.test.ts)
jalehman: Authored the merged exec completion delivery-context fix adjacent to chat/Telegram completion routing. (role: adjacent delivery-context contributor; confidence: medium; commits: 29142a9d4764; files: src/agents/bash-tools.exec-runtime.ts, src/agents/bash-tools.exec.ts, src/agents/bash-tools.test.ts)
vincentkoc: Pushed the narrow repair commits to the active superseding chat-scoped PR and appears in recent exec/process telemetry and notify test-helper history. (role: recent replacement repair contributor; confidence: medium; commits: 7b7b6bd5e6f7, 3e3bba4f305e, 156ee544edae; files: src/agents/bash-tools.exec.ts, src/agents/bash-tools.exec-runtime.ts, src/agents/bash-tools.test.ts)

Codex review notes: model gpt-5.5, reasoning high; reviewed against 9ac871c34b7d.

Marvinthebored · 2026-04-29T21:41:18Z

Concrete workflow gap from #74308/#50398 that seems to make this PR the right vehicle rather than another docs-only resubmission:

Current skills/coding-agent/SKILL.md requires coding-agent launches to use exec background:true, then tells the caller to require the worker to self-notify with openclaw message send and not rely on heartbeat/system-event delivery.
In the failing workflow, the delegated CLI worker finishes or otherwise stops producing output, but the caller session is not woken. From the user's point of view the coding-agent call has killed the workflow: the parent has gone to sleep forever unless a human manually checks/polls the process.
The docs-only alternative in docs(skills): make coding-agent completion parent-owned #74308 tried to change the skill contract to parent-owned stdout/result-block reporting, but it was closed as “low-signal process-doc churn without a maintainer-owned workflow change.” Fair enough: the missing maintainer-owned workflow change is exactly the runtime behavior this PR addresses.

Why this PR matters for the skill contract: a worker-side openclaw message send is not a reliable completion contract for a delegated coding CLI. It may not have the right channel/plugin route, may be sandboxed/constrained, and if it completes with empty output or the send path fails/hangs, the parent still needs a runtime wake so it can inspect process log/poll and report/continue. Today notifyOnExitEmptySuccess is still opt-in on main, so an empty successful background exec can be indistinguishable from a hung coding agent.

So my recommendation is: land/rebase this runtime default change first (or an equivalent maintainer-owned completion wake), then update coding-agent docs narrowly to say the parent owns final reporting after the completion wake, with worker self-send optional rather than mandatory. That would give the closed #74308 a concrete workflow gap and an implementation anchor instead of another freestanding docs-contract debate.

…26.6.8) (#1144) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.6.6` → `2026.6.8` | --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.6.8`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#202668) [Compare Source](openclaw/openclaw@v2026.6.6...v2026.6.8) ##### Highlights - Telegram and WhatsApp channel delivery are richer and less brittle: Telegram can send structured rich text with tables, lists, expandable blockquotes, prompt-preserving CLI backend delivery, retired native draft migration, and safer rich-media boundaries, while WhatsApp now honors configured ACP bindings. ([#92679](openclaw/openclaw#92679), [#84082](openclaw/openclaw#84082), [#89421](openclaw/openclaw#89421), [#92513](openclaw/openclaw#92513)) Thanks [@obviyus](https://github.com/obviyus), [@jzakirov](https://github.com/jzakirov), [@spacegeologist](https://github.com/spacegeologist), and [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Agent and Gateway recovery is sharper across account-scoped DM sends, generated media completions, restart shutdown aborts, yielded subagent pauses, yielded cron media, heartbeat dedupe, session identity prompts, and unknown OpenAI agent selector rejection. ([#92788](openclaw/openclaw#92788), [#91246](openclaw/openclaw#91246), [#91357](openclaw/openclaw#91357), [#92631](openclaw/openclaw#92631), [#92146](openclaw/openclaw#92146), [#91287](openclaw/openclaw#91287), [#92468](openclaw/openclaw#92468), [#92510](openclaw/openclaw#92510)) Thanks [@yetval](https://github.com/yetval), [@TurboTheTurtle](https://github.com/TurboTheTurtle), [@ooiuuii](https://github.com/ooiuuii), [@openperf](https://github.com/openperf), [@IWhatsskill](https://github.com/IWhatsskill), [@ZengWen-DT](https://github.com/ZengWen-DT), and [@zhangguiping-xydt](https://github.com/zhangguiping-xydt). - Provider/model handling expands and tightens with GLM-5.2, Claude Haiku 4.5 catalog rows, OpenRouter and Google Vertex provider-prefix normalization, managed SecretRef auth, bounded model browse discovery, storeless OpenAI Responses replay gating, and Claude 4.5 Copilot tool-streaming safety. ([#92796](openclaw/openclaw#92796), [#90116](openclaw/openclaw#90116), [#92627](openclaw/openclaw#92627), [#91218](openclaw/openclaw#91218), [#90686](openclaw/openclaw#90686), [#92247](openclaw/openclaw#92247), [#90706](openclaw/openclaw#90706), [#75393](openclaw/openclaw#75393)) Thanks [@arkyu2077](https://github.com/arkyu2077), [@liuhao1024](https://github.com/liuhao1024), [@bymle](https://github.com/bymle), [@rohitjavvadi](https://github.com/rohitjavvadi), [@samson910022](https://github.com/samson910022), [@snowzlm](https://github.com/snowzlm), and [@Kailigithub](https://github.com/Kailigithub). - `/usage` and reply payload hooks now have a native full footer renderer, default template, fixed-decimal formatting, credential-aware limits, better partial-count handling, and warnings for broken templates instead of silent bad output. ([#92657](openclaw/openclaw#92657), [#89835](openclaw/openclaw#89835), [#89629](openclaw/openclaw#89629)) Thanks [@Marvinthebored](https://github.com/Marvinthebored). - UI and mobile flows are steadier: workspace files can collapse and start collapsed, WebChat backscroll survives streaming, the sidebar session picker remains interactive above the desktop workbench, reset soft args survive UI dispatch, stale dashboard session parent lineage is preserved, and iOS reconnects stale foreground gateways. ([#92779](openclaw/openclaw#92779), [#92622](openclaw/openclaw#92622), [#92705](openclaw/openclaw#92705), [#91353](openclaw/openclaw#91353), [#90658](openclaw/openclaw#90658), [#92552](openclaw/openclaw#92552)) Thanks [@shakkernerd](https://github.com/shakkernerd), [@TurboTheTurtle](https://github.com/TurboTheTurtle), [@NianJiuZst](https://github.com/NianJiuZst), [@zhouhe-xydt](https://github.com/zhouhe-xydt), [@luoyanglang](https://github.com/luoyanglang), and [@Solvely-Colin](https://github.com/Solvely-Colin). - Memory, state, and diagnostics recover cleaner: oversized OpenAI embedding batches split before 431s, QMD memory search stays available in transient mode, SQLite avoids WAL on NFS state volumes, stuck-session recovery scheduling no longer resets warning backoff, and Infinity chunk limits stay genuinely unbounded. ([#92650](openclaw/openclaw#92650), [#92618](openclaw/openclaw#92618), [#92639](openclaw/openclaw#92639), [#91247](openclaw/openclaw#91247), [#92752](openclaw/openclaw#92752), [#92735](openclaw/openclaw#92735)) Thanks [@mushuiyu886](https://github.com/mushuiyu886), [@TurboTheTurtle](https://github.com/TurboTheTurtle), [@849261680](https://github.com/849261680), [@gnanam1990](https://github.com/gnanam1990), and [@yhterrance](https://github.com/yhterrance). ##### Changes - Providers/models: add GLM-5.2 support and Claude Haiku 4.5 catalog entries while keeping provider-qualified model IDs normalized across OpenRouter and Google Vertex paths. ([#92796](openclaw/openclaw#92796), [#90116](openclaw/openclaw#90116), [#92627](openclaw/openclaw#92627), [#91218](openclaw/openclaw#91218)) Thanks [@arkyu2077](https://github.com/arkyu2077), [@liuhao1024](https://github.com/liuhao1024), and [@bymle](https://github.com/bymle). - Channel plugins: ship Telegram rich-message delivery and WhatsApp ACP binding support, including rich prompt handoff to CLI backends and transport fixtures for richer drafts. ([#92679](openclaw/openclaw#92679), [#92513](openclaw/openclaw#92513)) Thanks [@obviyus](https://github.com/obviyus) and [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Agent commands: support `/btw` in CLI-backed sessions and keep CLI usage-error exits classified as usage failures instead of successful runs. ([#92669](openclaw/openclaw#92669), [#92162](openclaw/openclaw#92162)) Thanks [@joshavant](https://github.com/joshavant) and [@Pandah97](https://github.com/Pandah97). - Usage hooks: add built-in full footer rendering, default footer templates, per-turn usage state, credential-aware limits, and fixed-decimal formatting for usage-bar templates. ([#92657](openclaw/openclaw#92657), [#89835](openclaw/openclaw#89835), [#89629](openclaw/openclaw#89629)) Thanks [@Marvinthebored](https://github.com/Marvinthebored). - Docs and operator guidance: document node config examples, clarify before-install hook scope, correct agent default concurrency comments, refresh ZAI provider docs, and update channel/group docs for current Telegram and WhatsApp behavior. ([#92677](openclaw/openclaw#92677), [#92766](openclaw/openclaw#92766), [#92695](openclaw/openclaw#92695)) Thanks [@liuhao1024](https://github.com/liuhao1024), [@sallyom](https://github.com/sallyom), and [@ArielSmoliar](https://github.com/ArielSmoliar). ##### Fixes - Onboarding/skills: show the Homebrew install recommendation only on macOS and Linux, so FreeBSD and other unsupported platforms no longer get a misleading brew prompt. Fixes [#68893](openclaw/openclaw#68893); carries forward [#68894](openclaw/openclaw#68894), [#68910](openclaw/openclaw#68910), [#68941](openclaw/openclaw#68941), [#68943](openclaw/openclaw#68943), [#69002](openclaw/openclaw#69002), and [#69545](openclaw/openclaw#69545). Thanks [@yurivict](https://github.com/yurivict), [@Sanjays2402](https://github.com/Sanjays2402), [@Eruditi](https://github.com/Eruditi), [@JustInCache](https://github.com/JustInCache), [@nnish16](https://github.com/nnish16), and [@Mlightsnow](https://github.com/Mlightsnow). - Channels and delivery: preserve account-scoped DM channel send policy, rich Telegram final replies, rich Telegram tables and lists, Telegram thread-create CLI remapping, Slack outbound `message_sent` hooks, contributed message-tool schema optionality, same-channel generated media completions, and channel chunking around surrogate pairs and Infinity limits. ([#92788](openclaw/openclaw#92788), [#92679](openclaw/openclaw#92679), [#89421](openclaw/openclaw#89421), [#89943](openclaw/openclaw#89943), [#91137](openclaw/openclaw#91137), [#91246](openclaw/openclaw#91246), [#92735](openclaw/openclaw#92735)) Thanks [@yetval](https://github.com/yetval), [@obviyus](https://github.com/obviyus), [@spacegeologist](https://github.com/spacegeologist), [@rishitamrakar](https://github.com/rishitamrakar), [@lundog](https://github.com/lundog), [@TurboTheTurtle](https://github.com/TurboTheTurtle), and [@yhterrance](https://github.com/yhterrance). - Auto-reply/groups: keep ordinary group text replies on automatic final-reply delivery while allowing `message(action=send)` for files, images, and other attachments to the same group or topic. Carries forward [#43276](openclaw/openclaw#43276); refs [#48004](openclaw/openclaw#48004). Thanks [@NayukiChiba](https://github.com/NayukiChiba) and [@ShakaRover](https://github.com/ShakaRover). - Auto-reply/skills: preserve multiline payloads for `/skill` and direct skill slash commands while keeping command-head normalization for aliases, colon syntax, and bot mentions. Fixes [#79155](openclaw/openclaw#79155); carries forward [#81305](openclaw/openclaw#81305). Thanks [@web3blind](https://github.com/web3blind). - iMessage: normalize leading NUL sent-message echo prefixes while preserving interior NUL bytes and the leading attributedBody marker handling from [#73942](openclaw/openclaw#73942). Carries forward [#63581](openclaw/openclaw#63581). Thanks [@drvoss](https://github.com/drvoss). - Discord: give generated auto-thread titles a 60-second timeout and 4,096-token reasoning-model output budget, clamped to the selected model output cap. ([#64734](openclaw/openclaw#64734)) Thanks [@hanamizuki](https://github.com/hanamizuki). - Agent, cron, and Gateway runtime: mark active main sessions before restart shutdown aborts, pause yielded subagent runs whose terminal also signals abort, preserve yielded media completions, de-duplicate main-session heartbeat events, expose session identity in runtime prompts, reject unknown OpenAI agent selectors, keep generated media completions and slash-command block replies in WebChat, preserve fresh post-compaction usage while clearing stale usage snapshots, and require admin privileges for HTTP session/model override surfaces. ([#91357](openclaw/openclaw#91357), [#92631](openclaw/openclaw#92631), [#92146](openclaw/openclaw#92146), [#91287](openclaw/openclaw#91287), [#92468](openclaw/openclaw#92468), [#92510](openclaw/openclaw#92510), [#91246](openclaw/openclaw#91246), [#50795](openclaw/openclaw#50795), [#50845](openclaw/openclaw#50845), [#82874](openclaw/openclaw#82874), [#92651](openclaw/openclaw#92651), [#92646](openclaw/openclaw#92646)) Thanks [@ooiuuii](https://github.com/ooiuuii), [@openperf](https://github.com/openperf), [@IWhatsskill](https://github.com/IWhatsskill), [@ZengWen-DT](https://github.com/ZengWen-DT), [@zhangguiping-xydt](https://github.com/zhangguiping-xydt), [@Hollychou924](https://github.com/Hollychou924), [@leno23](https://github.com/leno23), and [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Agents/exec: default empty-success background completion notices on only for real chat channels, preserving explicit opt-outs and keeping generic providers silent while carrying forward the narrow UX intent from [#39726](openclaw/openclaw#39726) and [#46926](openclaw/openclaw#46926). Thanks [@Sapientropic](https://github.com/Sapientropic) and [@wenkang-xie](https://github.com/wenkang-xie). - Providers and model replay: preserve storeless OpenAI Responses replay compatibility, avoid eager tool streaming for Claude 4.5 in Copilot, honor profile auth for SecretRef model entries, bound model browsing, strip provider prefixes where runtimes need bare IDs, and surface nested embedding fetch failures. ([#90706](openclaw/openclaw#90706), [#75393](openclaw/openclaw#75393), [#90686](openclaw/openclaw#90686), [#92247](openclaw/openclaw#92247), [#92627](openclaw/openclaw#92627), [#91218](openclaw/openclaw#91218), [#92628](openclaw/openclaw#92628)) Thanks [@snowzlm](https://github.com/snowzlm), [@Kailigithub](https://github.com/Kailigithub), [@rohitjavvadi](https://github.com/rohitjavvadi), [@samson910022](https://github.com/samson910022), [@liuhao1024](https://github.com/liuhao1024), [@bymle](https://github.com/bymle), and [@mushuiyu886](https://github.com/mushuiyu886). - Memory, state, diagnostics, and config: split header-too-large embedding batches, keep QMD memory search enabled in transient mode, avoid SQLite WAL on NFS volumes, preserve recovery scheduling outside stuck-session warning backoff, and keep shell environment fallbacks contained in config write tests. ([#92650](openclaw/openclaw#92650), [#92618](openclaw/openclaw#92618), [#92639](openclaw/openclaw#92639), [#91247](openclaw/openclaw#91247), [#92752](openclaw/openclaw#92752)) Thanks [@mushuiyu886](https://github.com/mushuiyu886), [@TurboTheTurtle](https://github.com/TurboTheTurtle), [@849261680](https://github.com/849261680), and [@gnanam1990](https://github.com/gnanam1990). - Workspace setup state: store setup completion outside the workspace dot directory using an OpenClaw-named root file, migrate valid legacy state forward, and avoid clobbering generic root `workspace-state.json` files for TigerFS-style dot-path compatibility. This Clownfish replacement carries forward the focused [#53326](openclaw/openclaw#53326) fix idea because the original branch was closed and uneditable. ([#53326](openclaw/openclaw#53326), [#44783](openclaw/openclaw#44783), [#39446](openclaw/openclaw#39446)) Thanks [@1qh](https://github.com/1qh). - UI/mobile/TUI: preserve dashboard session parent lineage, WebChat backscroll, reset soft command args, sidebar session picker interactivity, collapsed workspace files, resolved `/model` confirmation refs, and stale foreground iOS Gateway reconnects. ([#90658](openclaw/openclaw#90658), [#92622](openclaw/openclaw#92622), [#91353](openclaw/openclaw#91353), [#92705](openclaw/openclaw#92705), [#92779](openclaw/openclaw#92779), [#92773](openclaw/openclaw#92773), [#92552](openclaw/openclaw#92552)) Thanks [@luoyanglang](https://github.com/luoyanglang), [@TurboTheTurtle](https://github.com/TurboTheTurtle), [@zhouhe-xydt](https://github.com/zhouhe-xydt), [@NianJiuZst](https://github.com/NianJiuZst), [@shakkernerd](https://github.com/shakkernerd), [@NarahariRaghava](https://github.com/NarahariRaghava), and [@Solvely-Colin](https://github.com/Solvely-Colin). - TUI: reload the active session after external `/new` or `/reset` session-change events so stale transcript and stream state clear promptly. Fixes [#38966](openclaw/openclaw#38966); carries forward [#40472](openclaw/openclaw#40472). Thanks [@yizhanzjz](https://github.com/yizhanzjz) and [@wsyjh8](https://github.com/wsyjh8). - Control UI: preserve Gateway Access tokens during same-normalized WebSocket URL edits and reload gateway-scoped tokens when switching endpoints. Fixes [#41545](openclaw/openclaw#41545); repairs [#42001](openclaw/openclaw#42001) with additional source PRs [#41546](openclaw/openclaw#41546), [#41552](openclaw/openclaw#41552), and [#41718](openclaw/openclaw#41718). Thanks [@wsyjh8](https://github.com/wsyjh8), [@llagy0020](https://github.com/llagy0020), [@llagy007](https://github.com/llagy007), [@pingfanfan](https://github.com/pingfanfan), and [@zheliu2](https://github.com/zheliu2). - Gateway CLI: tolerate a single transient clean WebSocket close before `hello-ok` so one-shot RPC calls reconnect instead of failing noisily, while repeated clean pre-hello closes still surface. Carries forward source PRs [#54475](openclaw/openclaw#54475) and [#54774](openclaw/openclaw#54774); [#85253](openclaw/openclaw#85253) covered adjacent connect assembly diagnostics. Thanks [@ruanrrn](https://github.com/ruanrrn). - Gateway/Linux: keep root-owned systemd user service lifecycle commands on root's user manager when a stale `SUDO_USER` remains in a root shell with root's user bus environment. Fixes [#81410](openclaw/openclaw#81410). Thanks [@Ericksza](https://github.com/Ericksza) and [@ChuckClose-tech](https://github.com/ChuckClose-tech). - Release and test reliability: extend slow Gateway/full-suite watchdogs, split local full-suite shards when throttled, stabilize plugin auth marker fixtures, avoid brittle provider-ref error text, and keep QA Lab bootstrap selection assertions aligned with flow-only scenarios. ([#92652](openclaw/openclaw#92652)) - macOS Peekaboo bridge: update the embedded Peekaboo package to 3.5.2 and route bundled-skill CLI commands through the OpenClaw app bridge so they inherit its Screen Recording and Accessibility grants. - Agent routing: route subagent RPC callbacks addressed to an agent-shaped `--to` target to the correct session key instead of falling back to the main session, so WeChat (and other channel) session-key callbacks reach the intended subagent session. ([#90231](openclaw/openclaw#90231)) Thanks [@zhangguiping-xydt](https://github.com/zhangguiping-xydt). - Cron: preserve model, fallback, thinking, timeout, light-context, unsafe-content, and tool allow-list overrides on implicit text payloads by promoting them to agent turns, while explicit system events still prune those fields. Fixes [#28905](openclaw/openclaw#28905); carries forward [#64060](openclaw/openclaw#64060) and [#73946](openclaw/openclaw#73946). Thanks [@liaoandi](https://github.com/liaoandi). - QQBot delivery: keep markdown table chunks self-contained across message boundaries by preserving table state across block deliveries, flushing unfinished table-row fragments as plain text, and detecting short pipe-terminated rows by column count so split rows are not sent as malformed markdown. ([#92428](openclaw/openclaw#92428)) Thanks [@sliverp](https://github.com/sliverp). </details> --- ### Configuration 📅 **Schedule**: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined). 🚦 **Automerge**: Disabled by config. Please merge this manually once you are satisfied. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about these updates again. --- - [ ] If you want to rebase/retry this PR, check this box --- This PR has been generated by [Renovate Bot](https://github.com/renovatebot/renovate).  Reviewed-on: https://git.erwanleboucher.dev/eleboucher/homelab/pulls/1144

openclaw-barnacle Bot added agents Agent runtime and tooling size: XS labels Mar 15, 2026

wenkang-xie force-pushed the fix/exec-wake-on-exit branch from 965bc09 to 043d640 Compare March 16, 2026 07:17

clawsweeper Bot mentioned this pull request Apr 27, 2026

Feature: config-level default task notify policy #64081

Open

clawsweeper Bot mentioned this pull request Apr 29, 2026

feat(exec): add onComplete="notify" for background process completion wakes #54549

Closed

1 task

clawsweeper Bot mentioned this pull request May 9, 2026

agents: notify chat sessions on empty bg success #39726

Closed

clawsweeper Bot closed this May 11, 2026

vincentkoc mentioned this pull request Jun 16, 2026

agents: notify chat exec empty-success completions #93525

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

fix: notify agent session on background exec completion by default#46926

fix: notify agent session on background exec completion by default#46926
wenkang-xie wants to merge 1 commit into
openclaw:mainfrom
wenkang-xie:fix/exec-wake-on-exit

wenkang-xie commented Mar 15, 2026 •

edited

Loading

Uh oh!

greptile-apps Bot commented Mar 15, 2026 •

edited

Loading

Comments Outside Diff (1)

Uh oh!

wenkang-xie commented Mar 16, 2026

Uh oh!

clawsweeper Bot commented Apr 28, 2026 •

edited

Loading

Uh oh!

Marvinthebored commented Apr 29, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Uh oh!

Conversation

wenkang-xie commented Mar 15, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Problem

Changes

Why

Testing

Uh oh!

greptile-apps Bot commented Mar 15, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Greptile Summary

Confidence Score: 4/5

Comments Outside Diff (1)

Uh oh!

wenkang-xie commented Mar 16, 2026

CI Failures — Unrelated to This PR

Uh oh!

clawsweeper Bot commented Apr 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Marvinthebored commented Apr 29, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

wenkang-xie commented Mar 15, 2026 •

edited

Loading

greptile-apps Bot commented Mar 15, 2026 •

edited

Loading

clawsweeper Bot commented Apr 28, 2026 •

edited

Loading