Agent API

Agent API

create_deep_agent

::: pydantic_deep.agent.create_deep_agent options: show_source: false

Parameters

Core

Feature Toggles

Subagents

Skills

Context Management

Checkpointing

Memory

Cost Tracking

Middleware

Other

Returns

Agent[DeepAgentDeps, str] or Agent[DeepAgentDeps, OutputDataT] - Configured Pydantic AI agent.

When output_type is provided, returns an agent typed with the output model.

Example

from pydantic_deep import create_deep_agent, SubAgentConfig

agent = create_deep_agent(
    model="openai:gpt-4.1",
    instructions="You are a coding assistant.",
    subagents=[
        SubAgentConfig(
            name="reviewer",
            description="Reviews code",
            instructions="Review code for issues.",
        ),
    ],
    skill_directories=[
        {"path": "~/.pydantic-deep/skills", "recursive": True},
    ],
    interrupt_on={"execute": True},
)

create_default_deps

::: pydantic_deep.agent.create_default_deps options: show_source: false

Signature

def create_default_deps(
    backend: BackendProtocol | None = None,
) -> DeepAgentDeps

Parameters

Returns

DeepAgentDeps - Configured dependencies instance.

Example

from pydantic_deep import create_default_deps
from pydantic_ai_backends import LocalBackend

# With default StateBackend
deps = create_default_deps()

# With custom backend
deps = create_default_deps(backend=LocalBackend("/workspace"))

DeepAgentDeps

::: pydantic_deep.deps.DeepAgentDeps options: show_source: false

Definition

@dataclass
class DeepAgentDeps:
    backend: BackendProtocol = field(default_factory=StateBackend)
    files: dict[str, FileData] = field(default_factory=dict)
    todos: list[Todo] = field(default_factory=list)
    subagents: dict[str, Any] = field(default_factory=dict)
    uploads: dict[str, UploadedFile] = field(default_factory=dict)
    ask_user: Callable | None = None
    share_todos: bool = False
    checkpoint_store: CheckpointStore | None = None

Attributes

Methods

get_todo_prompt

def get_todo_prompt(self) -> str

Generate system prompt section for current todos.

get_files_summary

def get_files_summary(self) -> str

Generate summary of files in memory.

get_subagents_summary

def get_subagents_summary(self) -> str

Generate summary of available subagents.

clone_for_subagent

def clone_for_subagent(self) -> DeepAgentDeps

Create isolated dependencies for a subagent.

• Same backend (shared)
• Empty todos (isolated)
• Empty subagents (no nested delegation)
• Same files (shared reference)

Example

from pydantic_deep import DeepAgentDeps, StateBackend, Todo

deps = DeepAgentDeps(
    backend=StateBackend(),
    todos=[
        Todo(
            content="Review code",
            status="pending",
            active_form="Reviewing code",
        ),
    ],
)

# Access todo prompt
print(deps.get_todo_prompt())

# Clone for subagent
subagent_deps = deps.clone_for_subagent()
assert subagent_deps.todos == []  # Isolated
assert subagent_deps.backend is deps.backend  # Shared