`openclaw models auth login` was replacing `agents.defaults.models`
wholesale whenever a provider returned a `configPatch` with that key,
even if the patch only listed the new default model. Re-authenticating
an OAuth provider such as OpenAI Codex wiped aliases and per-model
params for every other provider.
Make replacement opt-in via `ProviderAuthResult.replaceDefaultModels`.
Ordinary logins merge their allowlist patch so unrelated entries
survive; the Anthropic -> Claude CLI migration opts in because it
renames keys the merge path would otherwise keep stale.
Fixes#69414.
Made-with: Cursor
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
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.
