ޠj SrSSKrSSKJrJr SSKJr SSKJr S\S\ 4S\S\ \ \ \444S jr S \S\\ 4S\S\\ \ \ \444S jr S \S \S\4Sjrg)z.Custom tool decorator for OpenAI custom tools.N) AwaitableCallable)Any)toolfunc.returncX^S[S[[[[44U4SjjnU$)Nxrc>ST"U5S./$Ncustom_tool_call_output)typeoutput)r rs \/var/www/html/gaurav/venv/lib/python3.13/site-packages/langchain_openai/tools/custom_tool.pywrapped#_make_wrapped_func..wrapped s2d1gFGG)strlistdictr)rrs` r_make_wrapped_funcr s-H3H4S#X/H Nr coroutinec d^S[S[S[[[[44U4SjjnU$)Nargskwargsrc<># T"U0UD6IShvN nSUS./$N 7fr r)rrresultrs rr(_make_wrapped_coroutine..wrappeds+ $1&112fEFF2s  )rrrr)rrs` r_make_wrapped_coroutiner s5GSGCGDc3h4HG Nrrrc^S[S[4S[4U4SjjnU(a%[US5(aT(d U"US5$U$)aDecorator to create an OpenAI custom tool. Custom tools allow for tools with (potentially long) freeform string inputs. See below for an example using LangGraph: ```python @custom_tool def execute_code(code: str) -> str: """Execute python code.""" return "27" model = ChatOpenAI(model="gpt-5", output_version="responses/v1") agent = create_react_agent(model, [execute_code]) input_message = {"role": "user", "content": "Use the tool to calculate 3^3."} for step in agent.stream( {"messages": [input_message]}, stream_mode="values", ): step["messages"][-1].pretty_print() ``` You can also specify a format for a corresponding context-free grammar using the `format` kwarg: ```python from langchain_openai import ChatOpenAI, custom_tool from langgraph.prebuilt import create_react_agent grammar = """ start: expr expr: term (SP ADD SP term)* -> add | term term: factor (SP MUL SP factor)* -> mul | factor factor: INT SP: " " ADD: "+" MUL: "*" %import common.INT """ format = {"type": "grammar", "syntax": "lark", "definition": grammar} # highlight-next-line @custom_tool(format=format) def do_math(input_string: str) -> str: """Do a mathematical operation.""" return "27" model = ChatOpenAI(model="gpt-5", output_version="responses/v1") agent = create_react_agent(model, [do_math]) input_message = {"role": "user", "content": "Use the tool to calculate 3^3."} for step in agent.stream( {"messages": [input_message]}, stream_mode="values", ): step["messages"][-1].pretty_print() ``` r.rc>SS0nST;aTRS5US'[SSS0TD6"U5nXlURUl[ R "U5(a[U5UlU$[U5Ul U$)Nr custom_toolformat infer_schemaFr) poprmetadata__doc__ descriptioninspectiscoroutinefunctionr rrr)rr'tool_objrs r decoratorcustom_tool..decorator_sM* v !'H!5HX 5U5f5d;$#||  & &t , ,!8!>H /t4HMrr)rrcallable)rrr-s ` rr#r#sJH c* s  a!!&a!! r)r(r*collections.abcrrtypingrlangchain_core.toolsrrrrrr r#rrrr3s4/%Xc3h/HS$tCQTH~BV=V4WYs^+, c9T$sCx.1223TsTcTcTr