Update sample code for: LangGraph Tutorial: Build Stateful AI Agents in Python (#784)

* Update sample code for: LangGraph Tutorial: Build Stateful AI Agents in Python

Refresh the LangGraph companion code for the tutorial update:
- Bump to langgraph 1.2.5, langchain-openai 1.3.2, langchain-core 1.4.7,
  pydantic 2.13.4 (regenerated requirements.txt; pyproject floors raised)
- Switch the model to gpt-5.4-nano
- Fix check_escalation_status_node to fall back to 0 when no fine is
  extracted (avoids a TypeError on notices without a max potential fine)
- Store the boolean answer.is_true in follow_ups (was storing the model object)
- Drop the unused critical_fields_missing key from the agent's initial state
- Point the README API-key link at platform.openai.com/api-keys and match
  the new tutorial title

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* Sync example_emails.py dates to 2026 to match the tutorial

The companion emails still used 2024/2025 dates while the tutorial's
examples and REPL transcripts use 2026. Update Email 0 (May 15 / June 10,
2026) and Email 3 (June 10 / August 5, 2026) so extracted dates match the
tutorial output.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Bartosz Zaczyński <bartosz.zaczynski@gmail.com>

Author: 3 people

python-langgraph/README.md

@@ -1,6 +1,6 @@
-# LangGraph: Build Stateful AI Agents in Python
+# LangGraph Tutorial: Build Stateful AI Agents in Python
 
-This folder contains the source code for [LangGraph: Build Stateful AI Agents in Python](https://realpython.com/langgraph-python/)
+This folder contains the source code for [LangGraph Tutorial: Build Stateful AI Agents in Python](https://realpython.com/langgraph-python/)
 
 ## Setup
 
@@ -12,7 +12,7 @@ Create a new virtual environment, and run the following command to install LangG
 
 You'll use `langchain-openai` to interact with OpenAI LLMs, but keep in mind you can use any LLM provider you like with LangGraph and LangChain. You'll use [`pydantic`](https://realpython.com/python-pydantic/) to validate the information your agent parses from emails.
 
-Before moving forward, if you choose to use OpenAI, make sure you're signed up for an OpenAI account and you have a valid [API key](https://openai.com/api/). You'll need to set the following [environment variable](https://en.wikipedia.org/wiki/Environment_variable) before running any examples in this tutorial:
+Before moving forward, if you choose to use OpenAI, make sure you're signed up for an OpenAI account and you have a valid [API key](https://platform.openai.com/api-keys). You'll need to set the following [environment variable](https://en.wikipedia.org/wiki/Environment_variable) before running any examples in this tutorial:
 
 ```dotenv
 OPENAI_API_KEY=<YOUR-OPENAI-API-KEY>

python-langgraph/chains/binary_questions.py

@@ -23,7 +23,7 @@ class BinaryAnswer(BaseModel):
     ]
 )
 
-binary_question_model = ChatOpenAI(model="gpt-4o-mini", temperature=0)
+binary_question_model = ChatOpenAI(model="gpt-5.4-nano", temperature=0)
 
 BINARY_QUESTION_CHAIN = (
     binary_question_prompt

python-langgraph/chains/escalation_check.py

@@ -25,7 +25,7 @@ class EscalationCheck(BaseModel):
     ]
 )
 
-escalation_check_model = ChatOpenAI(model="gpt-4o-mini", temperature=0)
+escalation_check_model = ChatOpenAI(model="gpt-5.4-nano", temperature=0)
 
 ESCALATION_CHECK_CHAIN = (
     escalation_prompt

python-langgraph/chains/notice_extraction.py

@@ -98,7 +98,7 @@ def compliance_deadline(self) -> date | None:
     ]
 )
 
-notice_parser_model = ChatOpenAI(model="gpt-4o-mini", temperature=0)
+notice_parser_model = ChatOpenAI(model="gpt-5.4-nano", temperature=0)
 
 NOTICE_PARSER_CHAIN = (
     info_parse_prompt

python-langgraph/example_emails.py

@@ -1,7 +1,7 @@
 EMAILS = [
     # Email 1
     """
-    Date: October 15, 2024
+    Date: May 15, 2026
     From: Occupational Safety and Health Administration (OSHA)
     To: Blue Ridge Construction, project 111232345 - Downtown Office Complex
     Location: Dallas, TX
@@ -21,7 +21,7 @@
     Conduct an inspection of all scaffolding structures and reinforce unstable
     sections. Ensure all workers on-site are provided with necessary PPE and conduct
     safety training on proper usage.
-    Deadline for Compliance: All violations must be rectified by November 10, 2024.
+    Deadline for Compliance: All violations must be rectified by June 10, 2026.
     Failure to comply may result in fines of up to $25,000 per violation.
 
     Contact: For questions or to confirm compliance, please reach out to the OSHA
@@ -44,7 +44,7 @@
     """,
     # Email 4
     """
-    Date: January 10, 2025
+    Date: June 10, 2026
     From: City of Los Angeles Building and Safety Department
     To: West Coast Development, project 345678123 - Sunset Luxury
     Condominiums
@@ -62,8 +62,8 @@
     standards. Install additional fire extinguishers in compliance with
     fire code requirements. Reinforce or replace temporary support beams
     to ensure structural stability. Deadline for Compliance: Violations
-    must be addressed no later than February 5,
-    2025. Failure to comply may result in
+    must be addressed no later than August 5,
+    2026. Failure to comply may result in
     a stop-work order and additional fines.
     Contact: For questions or to schedule a re-inspection, please contact
     the Building and Safety Department at

python-langgraph/graphs/email_agent.py

@@ -62,7 +62,6 @@ def extract_notice_data(
     initial_state = {
         "notice_message": email,
         "notice_email_extract": None,
-        "critical_fields_missing": False,
         "escalation_text_criteria": escalation_criteria,
         "escalation_dollar_criteria": 100_000,
         "requires_escalation": False,
@@ -110,7 +109,7 @@ def determine_email_action(email: str) -> str:
 ]
 tool_node = ToolNode(tools)
 
-EMAIL_AGENT_MODEL = ChatOpenAI(model="gpt-4o-mini", temperature=0).bind_tools(
+EMAIL_AGENT_MODEL = ChatOpenAI(model="gpt-5.4-nano", temperature=0).bind_tools(
     tools
 )
 

python-langgraph/graphs/notice_extraction.py

@@ -51,7 +51,7 @@ def check_escalation_status_node(state: GraphState) -> GraphState:
 
     if (
         text_check
-        or state["notice_email_extract"].max_potential_fine
+        or (state["notice_email_extract"].max_potential_fine or 0)
         >= state["escalation_dollar_criteria"]
     ):
         state["requires_escalation"] = True
@@ -95,10 +95,10 @@ def answer_follow_up_question_node(state: GraphState) -> GraphState:
         answer = BINARY_QUESTION_CHAIN.invoke({"question": question})
 
         if state.get("follow_ups"):
-            state["follow_ups"][state["current_follow_up"]] = answer
+            state["follow_ups"][state["current_follow_up"]] = answer.is_true
 
         else:
-            state["follow_ups"] = {state["current_follow_up"]: answer}
+            state["follow_ups"] = {state["current_follow_up"]: answer.is_true}
 
     return state
 

python-langgraph/pyproject.toml

@@ -5,7 +5,7 @@ description = "Companion code to Real Python tutorial"
 readme = "README.md"
 requires-python = ">=3.12"
 dependencies = [
-    "langchain-openai>=0.3.2",
-    "langgraph>=0.2.67",
-    "pydantic[email]>=2.10.6",
+    "langchain-openai>=1.3.2",
+    "langgraph>=1.2.5",
+    "pydantic[email]>=2.13.4",
 ]

python-langgraph/requirements.txt

@@ -1,5 +1,5 @@
 # This file was autogenerated by uv via the following command:
-#    uv pip compile --output-file requirements.txt pyproject.toml
+#    uv pip compile pyproject.toml -o requirements.txt --python-version 3.12
 annotated-types==0.7.0
     # via pydantic
 anyio==4.8.0
@@ -34,44 +34,57 @@ idna==3.10
     #   email-validator
     #   httpx
     #   requests
-jiter==0.8.2
+jiter==0.15.0
     # via openai
 jsonpatch==1.33
     # via langchain-core
 jsonpointer==3.0.0
     # via jsonpatch
-langchain-core==0.3.33
+langchain-core==1.4.7
     # via
     #   langchain-openai
     #   langgraph
     #   langgraph-checkpoint
-langchain-openai==0.3.3
+    #   langgraph-prebuilt
+    #   langgraph-sdk
+langchain-openai==1.3.2
     # via python-langgraph (pyproject.toml)
-langgraph==0.2.69
+langchain-protocol==0.0.17
+    # via
+    #   langchain-core
+    #   langgraph-sdk
+langgraph==1.2.5
     # via python-langgraph (pyproject.toml)
-langgraph-checkpoint==2.0.10
+langgraph-checkpoint==4.1.1
+    # via
+    #   langgraph
+    #   langgraph-prebuilt
+langgraph-prebuilt==1.1.0
     # via langgraph
-langgraph-sdk==0.1.51
+langgraph-sdk==0.4.2
     # via langgraph
-langsmith==0.3.4
+langsmith==0.8.16
     # via langchain-core
-msgpack==1.1.0
-    # via langgraph-checkpoint
-openai==1.61.0
+openai==2.41.1
     # via langchain-openai
-orjson==3.10.15
+orjson==3.11.9
     # via
     #   langgraph-sdk
     #   langsmith
+ormsgpack==1.12.2
+    # via langgraph-checkpoint
 packaging==24.2
-    # via langchain-core
-pydantic==2.10.6
+    # via
+    #   langchain-core
+    #   langsmith
+pydantic==2.13.4
     # via
     #   python-langgraph (pyproject.toml)
     #   langchain-core
+    #   langgraph
     #   langsmith
     #   openai
-pydantic-core==2.27.2
+pydantic-core==2.46.4
     # via pydantic
 pyyaml==6.0.2
     # via langchain-core
@@ -94,13 +107,30 @@ tiktoken==0.8.0
     # via langchain-openai
 tqdm==4.67.1
     # via openai
-typing-extensions==4.12.2
+typing-extensions==4.15.0
     # via
+    #   anyio
     #   langchain-core
+    #   langchain-protocol
     #   openai
     #   pydantic
     #   pydantic-core
+    #   typing-inspection
+typing-inspection==0.4.2
+    # via pydantic
 urllib3==2.3.0
     # via requests
+uuid-utils==0.16.1
+    # via
+    #   langchain-core
+    #   langsmith
+websockets==15.0.1
+    # via
+    #   langgraph-sdk
+    #   langsmith
+xxhash==3.7.0
+    # via
+    #   langgraph
+    #   langsmith
 zstandard==0.23.0
     # via langsmith