intermediate⏱35 minutesLección 1 de 10

Gestión Avanzada de Estado

Domina esquemas de estado con TypedDict, reductores de estado (add, replace, merge) y funciones reductoras personalizadas para lógica de estado sofisticada.

Gestión Avanzada de Estado

State management is the heart of LangGraph. This lesson covers advanced state schemas, built-in reducers, and custom reducer functions that give you fine-grained control over how state updates are applied.

Enfoques de Esquema de Estado

LangGraph supports three schema definition approaches. Choose based on your needs:

python

from typing_extensions import TypedDict
from dataclasses import dataclass, field
from pydantic import BaseModel, Field
from typing import List, Optional

# 1. TypedDict — lightweight, no validation
class AgentState(TypedDict):
    messages: List[str]
    turn_count: int

# 2. dataclass — mutable, default values
@dataclass
class AgentState:
    messages: List[str] = field(default_factory=list)
    turn_count: int = 0

# 3. BaseModel — validation, serialization
class AgentState(BaseModel):
    messages: List[str] = Field(default_factory=list)
    turn_count: int = Field(default=0)

Característica	TypedDict	dataclass	BaseModel
Type hints only	Yes	Yes	Yes
Default values	No	Yes	Yes
Runtime validation	No	No	Yes
Serialization	Manual	Manual	Built-in
Performance	Fastest	Fast	Slightly slower
IDE support	Good	Excellent	Excellent

[!CONSEJO] Use TypedDict for simple agents, dataclass for agents needing defaults, and BaseModel for production systems requiring validation and serialization.

Reductores de Estado

Reducers control how multiple writes to the same state key are combined. Without a reducer, the last write wins.

El Predeterminado: Replace

python

class DefaultState(TypedDict):
    items: List[str]

def node_a(state: DefaultState) -> dict:
    return {"items": ["a"]}  # Replaces items

def node_b(state: DefaultState) -> dict:
    return {"items": ["b"]}  # Replaces items again — "a" is lost

# Result: items = ["b"]

El Reductor Add

Annotated[type, add] uses operator.add to combine values:

python

from typing import Annotated
from operator import add

class AppendState(TypedDict):
    items: Annotated[List[str], add]

def node_a(state: AppendState) -> dict:
    return {"items": ["a"]}  # Appended

def node_b(state: AppendState) -> dict:
    return {"items": ["b"]}  # Appended

# Result: items = ["a", "b"]

[!NOTA] The add reducer requires both values to be of the same type that supports +. For lists, both must be lists; for ints, both must be ints.

Reductores Integrados

operator.add

Works on lists (concatenation), numbers (addition), and strings:

python

from operator import add

class CounterState(TypedDict):
    count: Annotated[int, add]
    logs: Annotated[List[str], add]
    text: Annotated[str, add]

def increment(state: CounterState) -> dict:
    return {"count": 1}  # Adds 1 to current count

def add_log(state: CounterState) -> dict:
    return {"logs": ["Processing step"]}  # Appends to list

def add_text(state: CounterState) -> dict:
    return {"text": " more"}  # Concatenates strings

replace (predeterminado)

The default behavior — no annotation needed:

python

class NoReducerState(TypedDict):
    value: str  # Last write wins by default

def first(state: NoReducerState) -> dict:
    return {"value": "first"}

def second(state: NoReducerState) -> dict:
    return {"value": "second"}  # Overwrites

# Result: value = "second"

Reductores Personalizados

For complex merge logic, define a custom function:

python

from typing import Annotated

def merge_counts(old: dict, new: dict) -> dict:
    """Deep merge two count dictionaries."""
    result = old.copy()
    for key, value in new.items():
        if key in result:
            result[key] = result[key] + value
        else:
            result[key] = value
    return result

class CustomState(TypedDict):
    counts: Annotated[dict, merge_counts]

def node_a(state: CustomState) -> dict:
    return {"counts": {"apples": 5, "oranges": 3}}

def node_b(state: CustomState) -> dict:
    return {"counts": {"apples": 2, "bananas": 4}}

# Result: counts = {"apples": 7, "oranges": 3, "bananas": 4}

Firma de Reductor Personalizado

A reducer function receives (current_value, new_update) and returns the merged value:

python

def my_reducer(current: ValueType, update: ValueType) -> ValueType:
    # Combine current and update
    return merged_value

[!IMPORTANTE] The reducer receives the existing state value and the new update from the node. It must return the new value for that key. Reducers run every time a node writes to that key.

Patrones Avanzados de Reductores

Reductor Max

python

def max_reducer(current: int, update: int) -> int:
    return max(current, update)

class MaxState(TypedDict):
    highest_score: Annotated[int, max_reducer]

def player_1(state: MaxState) -> dict:
    return {"highest_score": 85}

def player_2(state: MaxState) -> dict:
    return {"highest_score": 92}

# Result: highest_score = 92 (max of all writes)

Reductor de Deduplicación de Lista

python

def dedup_append(current: List[str], update: List[str]) -> List[str]:
    seen = set(current)
    result = current[:]
    for item in update:
        if item not in seen:
            seen.add(item)
            result.append(item)
    return result

class DedupState(TypedDict):
    unique_items: Annotated[List[str], dedup_append]

def add_items(state: DedupState) -> dict:
    return {"unique_items": ["a", "b", "a"]}

# Result: unique_items = ["a", "b"] (duplicate "a" removed)

Fusión por Marca de Tiempo

python

def latest_wins(current: dict, update: dict) -> dict:
    current.update(update)
    return current

class MetadataState(TypedDict):
    metadata: Annotated[dict, latest_wins]

def node_a(state: MetadataState) -> dict:
    return {"metadata": {"status": "processing", "started_at": "2024-01-01"}}

def node_b(state: MetadataState) -> dict:
    return {"metadata": {"status": "completed", "completed_at": "2024-01-02"}}

# Result: metadata = {status: "completed", started_at: "2024-01-01", completed_at: "2024-01-02"}

Composición de Reductores

Combine multiple reducers across different fields:

python

from typing import Annotated
from operator import add

def merge_dicts(a: dict, b: dict) -> dict:
    result = a.copy()
    result.update(b)
    return result

class CompositeState(TypedDict):
    messages: Annotated[List[str], add]          # Append
    score: Annotated[int, add]                   # Sum
    config: Annotated[dict, merge_dicts]         # Shallow merge
    status: str                                   # Replace (default)
    max_val: Annotated[float, max_reducer]        # Custom: max

Validación de Estado con Pydantic

Add runtime validation to state fields:

python

from pydantic import BaseModel, Field, field_validator
from typing import List, Optional

class ValidatedState(BaseModel):
    messages: List[str] = Field(default_factory=list)
    temperature: float = Field(default=0.7, ge=0.0, le=2.0)
    max_tokens: int = Field(default=1024, gt=0, le=8192)

    @field_validator("messages")
    @classmethod
    def check_message_limit(cls, v: List[str]) -> List[str]:
        if len(v) > 100:
            raise ValueError("Too many messages (max 100)")
        return v

[!ADVERTENCIA] Pydantic validation runs on every state update. For high-throughput graphs, this adds overhead. Use it judiciously in production.

Persistencia de Estado entre Ejecuciones

Without persistence, state is ephemeral. To persist state:

python

from langgraph.checkpoint.memory import MemorySaver

checkpointer = MemorySaver()
app = builder.compile(checkpointer=checkpointer)

# State is saved after each node execution
config = {"configurable": {"thread_id": "user-session-1"}}
result = app.invoke(initial_state, config)

# Retrieve state for a thread
saved_state = app.get_state(config)
print(saved_state.values)

Persistence is covered in depth in Lesson 2. It's mentioned here because it interacts with state reducers — persisted state is restored and reducers continue from where they left off.

Preguntas Prácticas

Practice Question

Which state definition approach provides runtime validation?

Practice Question

What is the default state update behavior without a reducer?

Practice Question

What typing construct applies a reducer to a state field?

Practice Question

What is the signature of a custom reducer function?

Practice Question

Which operator does the 'add' reducer use?

Practice Question

What does a custom reducer returning max(current, update) accomplish?

Practice Question

When using add reducer on a list, what type must node returns be?

Practice Question

How do you apply different reducers to different fields in the same state?

Practice Question

Which state approach is recommended for production systems needing serialization?

Practice Question

What happens when Pydantic validation fails on a state update?

[!ÉXITO]

Conclusiones Clave

Three state approaches: TypedDict (lightweight), dataclass (defaults), BaseModel (validation)
Default reducer is "last write wins" (replace)
Annotated[type, add] appends with operator.add
Custom reducers: def reducer(current, update) -> new_value
Different fields can have different reducers via Annotated
Pydantic BaseModel adds runtime validation at the cost of performance
Custom reducers enable patterns like max, dedup, and deep merge

Progreso10%

Persistencia y Puntos de Control

Contenido del Curso

1. Gestión Avanzada de Estado 2. Persistencia y Puntos de Control 3. Memoria de Conversación 4. Memoria de Resumen 5. Humano-en-el-bucle con Interrupciones 6. Flujos de Aprobación 7. Fundamentos de Multi-Agente 8. Comunicación y Supervisión entre Agentes 9. Streaming de Tokens 10. Proyecto Intermedio: Sistema de Investigación Multi-Agente