Raise eligible Linux child processes own oom_score_adj from a child-side /bin/sh exec shim so cgroup memory pressure prefers transient workers over the long-lived gateway. Cover supervisor children, PTY shells, MCP stdio servers, and OpenClaw-launched browser processes through the shared process runtime seam.
Harden the wrapper for distroless images, shell startup env, per-child and process-level opt-outs, dash-compatible exec, and leading-dash command names. Document Linux verification and OOM behavior.
Fixes#70404.
Co-authored-by: Neerav Makwana <261249544+neeravmakwana@users.noreply.github.com>
Keep the acpx runtime type shim compatible with upstream probeAgent support and de-duplicate the rebased config/service wiring against current main. Normalize probeAgent the same way agent registry keys are normalized so mixed-case config resolves consistently.
Refs #68409
Add optional probeAgent field to acpx plugin config, carry through
resolveAcpxPluginConfig, forward to AcpxRuntime constructor so users
can set plugins.entries.acpx.config.probeAgent to any configured agent
id instead of hardcoding codex.
Refs #68409
- Drop redundant !lastToolError check from the messaging-tool clean-stop
early return; the earlier lastToolError early return already handles
that case, so the extra condition was dead and misleading.
- Update the CHANGELOG entry to reference only stopReason=stop; the pi-ai
StopReason type does not include end_turn, so the earlier mention was
a documentation-only discrepancy.
The agent runner was surfacing a '⚠️ Agent couldn't generate a response'
warning even when the assistant had already sent user-visible content
through a messaging tool and the turn ended cleanly. Treat that path as
a successful delivery and skip the warning while keeping real failure
modes (tool errors, stopReason=error, interrupted tool use) intact.
Fixes#70396.
The tts tool previously returned a fixed "Generated audio reply."
string in its content, so session transcripts lost what was actually
spoken. Across every channel, a voice-only reply left no text record
for future turns, forcing users to recover transcripts from the
provider's API. Echo the synthesized text back in the tool result
content (audio still delivered via details.media).
Sanitize the transcript before embedding so crafted utterances cannot
inject reply directives when tool output is rendered in verbose mode:
MEDIA: at line start and [[…]] markers are interrupted with a
zero-width word joiner (U+2060) that defuses parseReplyDirectives
without altering the visible text.
