ޠjt<|SSKJr SSKrSSKrSSKJrJr SSKJr SSK J r J r J r J r SSKJrJrJrJrJrJrJr SSKJrJr SSKJrJrJr SS KJr SS KJ r S r!\"\\-r#S r$SS jr%\%SS.SSjj5r&SSjr'\"SSS9"SS\55r("SS\5r)SSjr*SS.SSjjr+g) ) annotationsN)CallableSequence)partial) AnnotatedAnyLiteralcast) AnyMessage BaseMessageBaseMessageChunkMessageLikeRepresentation RemoveMessageconvert_to_messagesmessage_chunk_to_message) TypedDict deprecated)CONFCONFIG_KEY_SENDNS_SEP) StateGraph)LangGraphDeprecatedSinceV10) add_messages MessagesState MessageGraphREMOVE_ALL_MESSAGES__remove_all__c^SSU4SjjjnTRUl[[[[/[4U5$)Ncz>Ub Ub T"X40UD6$UcUbSU(aSOSS3n[U5e[T40UD6$)NzMMust specify non-null arguments for both 'left' and 'right'. Only received: 'leftrightz'.) ValueErrorr)r r!kwargsmsgfuncs Q/var/www/html/gaurav/venv/lib/python3.13/site-packages/langgraph/graph/message.py _add_messages,_add_messages_wrapper.._add_messages*sb   1.v. .  !2(,f':"> S/ !4*6* *)NN)r Messages | Noner!r*r#rreturnz3Messages | Callable[[Messages, Messages], Messages])__doc__r rMessages)r%r's` r&_add_messages_wrapperr.)sZ?C + +-< +OR + < + +!LLM (H-x78- HHr))formatc Sn[U[5(dU/n[U[5(dU/n[U5Vs/sHn[[ [ U55PM nn[U5Vs/sHn[[ [ U55PM nnUH5nUR bM[[R"55UlM7 [U5HdupTUR c#[[R"55Ul[U[5(dMLUR [:XdMbUnMf UbXS-S$UR5n[U5VVs0sHuptUR U_M nnn[5n UHnURUR 5=n bS[U[5(aU R!UR 5 MSU R#UR 5 XFU 'Mt[U[5(a[%SUR S35e['U5XR 'UR)U5 M UVs/sHoDR U ;dMUPM nnUS:Xa [+U5nU$U(aSU<S3n [%U 5eU$s snfs snfs snnfs snf)aKMerges two lists of messages, updating existing messages by ID. By default, this ensures the state is "append-only", unless the new message has the same ID as an existing message. Args: left: The base list of `Messages`. right: The list of `Messages` (or single `Message`) to merge into the base list. format: The format to return messages in. If `None` then `Messages` will be returned as is. If `langchain-openai` then `Messages` will be returned as `BaseMessage` objects with their contents formatted to match OpenAI message format, meaning contents can be string, `'text'` blocks, or `'image_url'` blocks and tool responses are returned as their own `ToolMessage` objects. !!! important "Requirement" Must have `langchain-core>=0.3.11` installed to use this feature. Returns: A new list of messages with the messages from `right` merged into `left`. If a message in `right` has the same ID as a message in `left`, the message from `right` will replace the message from `left`. Example: Basic usage ```python from langchain_core.messages import AIMessage, HumanMessage msgs1 = [HumanMessage(content="Hello", id="1")] msgs2 = [AIMessage(content="Hi there!", id="2")] add_messages(msgs1, msgs2) # [HumanMessage(content='Hello', id='1'), AIMessage(content='Hi there!', id='2')] ``` Example: Overwrite existing message ```python msgs1 = [HumanMessage(content="Hello", id="1")] msgs2 = [HumanMessage(content="Hello again", id="1")] add_messages(msgs1, msgs2) # [HumanMessage(content='Hello again', id='1')] ``` Example: Use in a StateGraph ```python from typing import Annotated from typing_extensions import TypedDict from langgraph.graph import StateGraph class State(TypedDict): messages: Annotated[list, add_messages] builder = StateGraph(State) builder.add_node("chatbot", lambda state: {"messages": [("assistant", "Hello")]}) builder.set_entry_point("chatbot") builder.set_finish_point("chatbot") graph = builder.compile() graph.invoke({}) # {'messages': [AIMessage(content='Hello', id=...)]} ``` Example: Use OpenAI message format ```python from typing import Annotated from typing_extensions import TypedDict from langgraph.graph import StateGraph, add_messages class State(TypedDict): messages: Annotated[list, add_messages(format="langchain-openai")] def chatbot_node(state: State) -> list: return { "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Here's an image:", "cache_control": {"type": "ephemeral"}, }, { "type": "image", "source": { "type": "base64", "media_type": "image/jpeg", "data": "1234", }, }, ], }, ] } builder = StateGraph(State) builder.add_node("chatbot", chatbot_node) builder.set_entry_point("chatbot") builder.set_finish_point("chatbot") graph = builder.compile() graph.invoke({"messages": []}) # { # 'messages': [ # HumanMessage( # content=[ # {"type": "text", "text": "Here's an image:"}, # { # "type": "image_url", # "image_url": {"url": "data:image/jpeg;base64,1234"}, # }, # ], # ), # ] # } ``` Nz?Attempting to delete a message with an ID that doesn't exist ('z')zlangchain-openaizUnrecognized format=z+. Expected one of 'langchain-openai', None.) isinstancelistrrr r idstruuiduuid4 enumeraterrcopysetgetadddiscardr"lenappend_format_messages) r r!r/remove_all_idxmidxmergedi merged_by_id ids_to_remove existing_idxr$s r&rr<s}~N dD ! !v eT " "%T* *A !&6!:;*   %U+ +A !&6!:;+    44<tzz|$ADE" 44<tzz|$AD a ' 'ADD4G,G N # !a')**YY[F(1&(9:(9ADD!G(9L:EM (,,QTT2 2L ?!]++!!!$$'%%add+'(|$!]++ UVWVZVZU[[]^"%VL  MM!  =A44}#s"J11"J6+J;$K:Kc/nUH<n[U[5(aURU5 M+URU5 M> U(a[US[5(aUnO[ S[ U55n[ S[ U55n[U5VVs0sH!upgURcMURU_M# nnn[U5n UHwn U Rn U cU RU 5 M%[U [5(aX;a SXU 'X MJMLX;aXX'MY[U 5X'U RU 5 My U Vs/sH owcMUPM sn$s snnfs snf)u**Experimental.** Batch reducer for use with `DeltaChannel`. Processes all writes in one pass — dedup by ID, `RemoveMessage` tombstoning — without calling `add_messages`. This reducer is batching-invariant, as required by `DeltaChannel`: `reducer(reducer(state, xs), ys) == reducer(state, xs + ys)`. Raw dict / string / tuple inputs are coerced to typed `BaseMessage` objects so that HTTP-driven graphs work without a separate coercion step. This is not full `add_messages` parity — `REMOVE_ALL_MESSAGES`, unknown-id `RemoveMessage` errors, missing-id UUID assignment, and `BaseMessageChunk` conversion are not handled here. Example:: from typing import Annotated from langgraph.channels.delta import DeltaChannel from langgraph.graph.message import _messages_delta_reducer class State(TypedDict): messages: Annotated[list, DeltaChannel(_messages_delta_reducer)] rlist[AnyMessage]N) r2r3extendr?r r rr8r4rr>) statewritesflatw state_msgsmsgsrErBindexresultr$mids r&_messages_delta_reducerrUsM<D  a   KKN KKN  E!Hk22 ,.A%.HI "$7$= >D&j11DAQTTa1 '+:&6Fff ; MM#  ] + +|%)Sz"J\!$5: VEJ MM#  /v!Av //#" 0sE'5E'E-E-z{MessageGraph is deprecated in langgraph 1.0.0, to be removed in 2.0.0. Please use StateGraph with a `messages` key instead.)categoryc0^\rSrSrSrSU4SjjrSrU=r$)ri8aA StateGraph where every node receives a list of messages as input and returns one or more messages as output. MessageGraph is a subclass of StateGraph whose entire state is a single, append-only* list of messages. Each node in a MessageGraph takes a list of messages as input and returns zero or more messages as output. The `add_messages` function is used to merge the output messages from each node into the existing list of messages in the graph's state. Examples: ```pycon >>> from langgraph.graph.message import MessageGraph ... >>> builder = MessageGraph() >>> builder.add_node("chatbot", lambda state: [("assistant", "Hello!")]) >>> builder.set_entry_point("chatbot") >>> builder.set_finish_point("chatbot") >>> builder.compile().invoke([("user", "Hi there.")]) [HumanMessage(content="Hi there.", id='...'), AIMessage(content="Hello!", id='...')] ``` ```pycon >>> from langchain_core.messages import AIMessage, HumanMessage, ToolMessage >>> from langgraph.graph.message import MessageGraph ... >>> builder = MessageGraph() >>> builder.add_node( ... "chatbot", ... lambda state: [ ... AIMessage( ... content="Hello!", ... tool_calls=[{"name": "search", "id": "123", "args": {"query": "X"}}], ... ) ... ], ... ) >>> builder.add_node( ... "search", lambda state: [ToolMessage(content="Searching...", tool_call_id="123")] ... ) >>> builder.set_entry_point("chatbot") >>> builder.add_edge("chatbot", "search") >>> builder.set_finish_point("search") >>> builder.compile().invoke([HumanMessage(content="Hi there. Can you search for X?")]) {'messages': [HumanMessage(content="Hi there. Can you search for X?", id='b8b7d8f4-7f4d-4f4d-9c1d-f8b8d8f4d9c1'), AIMessage(content="Hello!", id='f4d9c1d8-8d8f-4d9c-b8b7-d8f4f4d9c1d8'), ToolMessage(content="Searching...", id='d8f4f4d9-c1d8-4f4d-b8b7-d8f4f4d9c1d8', tool_call_id="123")]} ``` c>[R"S[SS9 [TU][ [ [[45 g)Nz}MessageGraph is deprecated in LangGraph v1.0.0, to be removed in v2.0.0. Please use StateGraph with a `messages` key instead.)rV stacklevel) warningswarnrsuper__init__rr3r r)self __class__s r&r^MessageGraph.__init__ks9  L0 4 #3\#ABCr))r+None)__name__ __module__ __qualname____firstlineno__r,r^__static_attributes__ __classcell__)r`s@r&rr8s ,\DDr)rc \rSrSr%S\S'Srg)ritz)Annotated[list[AnyMessage], add_messages]messagesrbN)rdrerfrg__annotations__rhrbr)r&rrts77r)rrkcSSKJn [U"U55$![a& Sn[R "U5 [ U5s$f=f)Nr)convert_to_openai_messageszMust have langchain-core>=0.3.11 installed to use automatic message formatting (format='langchain-openai'). Please update your langchain-core version or remove the 'format' flag. Returning un-formatted messages.)langchain_core.messagesrnr ImportErrorr[r\r3)rkrnr$s r&r@r@xsQ IF##=h#GHH    cH~s-A A ) state_keycl^ ^ SSKJm Jn SSKJn SSKJm U"5n[S[U/555nURc [S5e[USU5(aUSnURnO:[US[5(a"[U 4S jUS55(aUSn[U 4S jW5S5=n(aFUS n[[!["US 5R%[&55U4n UR)XS S9 U(aU[*[,"X4/5 U$)zWrite a message manually to the `messages` / `messages-tuple` stream mode. Will automatically write to the channel specified in the `state_key` unless `state_key` is `None`. r)BaseCallbackHandlerBaseCallbackManager) get_config)StreamMessagesHandlerc3"# UHov M g7fNrb).0xs r& push_message..s=<1# UHn[UT5v M g7frxr2)ryrzrss r&r{r|s 74Gq 1)**4Gsc3L># UHn[UT5(dMUv M g7frxr)ryrzrvs r&r{r|sEHq 1.C DHs$ $metadatalanggraph_checkpoint_nsF)dedupe)langchain_core.callbacks.basersrtlanggraph.configrulanggraph.pregel._messagesrvnextrr4r"r2handlersr3alltupler r5splitr_emitrr) messagerqrtruconfigmanagerrstream_handlerr message_metarsrvs @@r& push_messagers1 ,@ \F=17)<==Gzz122&%':;;%## F;' . .374:;4G744+&EHEt~*% $sH%>?@FFvN O   \5At _% ';&<= Nr))r%rr+z(Callable[[Messages, Messages], Messages])r r-r!r-r/z"Literal['langchain-openai'] | Noner+r-)rLrJrMzlist[list[AnyMessage]]r+rJ)rkzSequence[BaseMessage]r+zlist[BaseMessage])rz,MessageLikeRepresentation | BaseMessageChunkrqz str | Noner+r ), __future__rr6r[collections.abcrr functoolsrtypingrrr r ror r r rrrrtyping_extensionsrrlanggraph._internal._constantsrrrlanggraph.graph.staterlanggraph.warningsr__all__r3r-rr.rrUrrr@rrbr)r&rs+" .4HH,:  ) *-F F&I& 26 w w w / w  wwt>0 >0%;>0>0B B 5D:5D 5Dp8I8 I&'- 9-- -r)