mirror of
https://github.com/openclaw/openclaw.git
synced 2026-05-06 06:40:44 +00:00
fix: land ACP child sessions_send guard (#69817) (thanks @scotthuang)
This commit is contained in:
@@ -20,6 +20,7 @@ Docs: https://docs.openclaw.ai
|
||||
|
||||
### Fixes
|
||||
|
||||
- Agents/ACP: skip the `sessions_send` A2A ping-pong flow when a parent sends to its own background oneshot ACP child, preventing parent/child echo loops while preserving normal A2A delivery for non-parent senders. (#69817) Thanks @scotthuang.
|
||||
- Agents/subagents: stop terminal failed subagent runs from freezing or announcing captured reply text, so failover-exhausted runs report a clean failure instead of replaying stale assistant/tool output.
|
||||
- Security/external content: strip common self-hosted LLM chat-template special-token literals, including Qwen/ChatML, Llama, Gemma, Mistral, Phi, and GPT-OSS markers, from wrapped external content and metadata, preventing tokenizer-layer role-boundary spoofing against OpenAI-compatible backends that preserve special tokens in user text.
|
||||
- Auth/commands: require owner identity (an owner-candidate match or internal `operator.admin`) for owner-enforced commands instead of treating wildcard channel `allowFrom` or empty owner-candidate lists as sufficient, so non-owner senders can no longer reach owner-only commands through a permissive fallback when `enforceOwnerForCommands=true` and `commands.ownerAllowFrom` is unset. (#69774) Thanks @drobison00.
|
||||
|
||||
Reference in New Issue
Block a user