any support on create_agent/create_deep_agents which are released in langchain 1.0

[shengegeshen1130]

Currently, wrapping agents created by create_agent/create_deep_agents do not yield correct result.
The ace_chain(langchain_agent).invoke will output different result compared with the langchain_agent.invoke. Any best practice?

[Lanzelot1]

Hi @shengegeshen1130,

This is fixed in commit fed57f4. ACELangChain now auto-detects CompiledStateGraph (returned
by create_agent/create_deep_agents) and properly handles the message-based I/O format.

This will be available in the next release (v0.7.2).

Thanks for reporting!