i SrSSKJr SSKJr SSKJrJrJrJ r SSK J r \(aSSK J r Jr SSKJr "SS \5rg ) z%Model fallback middleware for agents.) annotations) TYPE_CHECKING)AgentMiddlewareModelCallResult ModelRequest ModelResponse)init_chat_model) AwaitableCallable) BaseChatModelch^\rSrSrSrSU4SjjrSSjrS SjrSrU=r $) ModelFallbackMiddlewarea Automatic fallback to alternative models on errors. Retries failed model calls with alternative models in sequence until success or all models exhausted. Primary model specified in create_agent(). Example: ```python from langchain.agents.middleware.model_fallback import ModelFallbackMiddleware from langchain.agents import create_agent fallback = ModelFallbackMiddleware( "openai:gpt-4o-mini", # Try first on error "anthropic:claude-sonnet-4-5-20250929", # Then this ) agent = create_agent( model="openai:gpt-4o", # Primary model middleware=[fallback], ) # If primary fails: tries gpt-4o-mini, then claude-sonnet-4-5-20250929 result = await agent.invoke({"messages": [HumanMessage("Hello")]}) ``` c>[TU]5 U/UQ7n/UlUHYn[U[5(a&URR [ U55 M>URR U5 M[ g)zInitialize model fallback middleware. Args: first_model: First fallback model (string name or instance). *additional_models: Additional fallbacks in order. N)super__init__models isinstancestrappendr )self first_modeladditional_models all_modelsmodel __class__s d/home/james-whalen/.local/lib/python3.13/site-packages/langchain/agents/middleware/model_fallback.pyr ModelFallbackMiddleware.__init__/sg "6$56 +- E%%% ""?5#9: ""5)  cU"U5$![a nUnSnAOSnAff=fURH,nXQlU"U5s $![a nUnSnAM&SnAff=f Ue)zTry fallback models in sequence on errors. Args: request: Initial model request. handler: Callback to execute the model. Returns: AIMessage from successful model call. Raises: Exception: If all models fail, re-raises last exception. N Exceptionrrrrequesthandlerelast_exceptionfallback_models rwrap_model_call'ModelFallbackMiddleware.wrap_model_callEsl& 7# # N #kkN*M w'' !"  *s'  A A AAc# U"U5IShvN $N![a nUnSnAOSnAff=fURH5nXQlU"U5IShvN s $![a nUnSnAM/SnAff=f Ue7f)aTry fallback models in sequence on errors (async version). Args: request: Initial model request. handler: Async callback to execute the model. Returns: AIMessage from successful model call. Raises: Exception: If all models fail, re-raises last exception. Nr!r#s rawrap_model_call(ModelFallbackMiddleware.awrap_model_callhs{&  )) )) N #kkN*M $W---- !"  *sfA6 A6 ,'A6,A6 AAAA6 A/"A*$A6*A//A6)r)rstr | BaseChatModelrr.returnNone)r$rr%z'Callable[[ModelRequest], ModelResponse]r/r)r$rr%z2Callable[[ModelRequest], Awaitable[ModelResponse]]r/r) __name__ __module__ __qualname____firstlineno____doc__rr)r,__static_attributes__ __classcell__)rs@rrrsr2*(*0*  *,!!9!  !F!!D!  !!rrN)r5 __future__rtypingr!langchain.agents.middleware.typesrrrrlangchain.chat_modelsr collections.abcr r *langchain_core.language_models.chat_modelsr rrrr?s4+"  23Htotr