ReMeMiddleware

ReMe is embedded in-process (no separate service): the middleware instantiates a :class:reme.ReMe application whose LLM-backed jobs use the chat_model configured at construction. The app is built and owned by the middleware — pass workspace_dir and optionally a Parameters with chat_model / embedding_model; it is created lazily on first use. When chat_model is omitted, the AgentScope config supplies the LLM from ReMe's LLM_* environment variables. Providing an embedding_model enables the vector store; otherwise search stays keyword-only.

The model is fixed at construction (never taken from an agent), so the embedded app's single LLM is well-defined even when one middleware instance is shared across several agents. Per-conversation state — the ReMe session_id — is instead read live from each agent at hook time and never stored, keeping shared use isolated. Background retrieval tasks are likewise tracked per session_id so concurrent replies in different sessions never clobber each other's in-flight search.

AgentScope middleware has no framework-managed lifecycle, so the app is built once and started lazily on first use (idempotent). Call :meth:close for explicit teardown of the embedded app.

Example::

from agentscope.middleware import ReMeMiddleware
from agentscope.tool import Toolkit

mw = ReMeMiddleware(
    workspace_dir=".reme",
    parameters=ReMeMiddleware.Parameters(mode="both"),
)
agent = Agent(
    ...,
    toolkit=Toolkit(tools=await mw.list_tools()),
    middlewares=[mw],
)