Types¶

Type definitions for the Agent library.

All Pydantic models and type definitions are centralized here.

class agent.types.ContentPart(**data)[source]¶

Bases: BaseModel

A part of message content (text, image, etc.).

Parameters:

data (Any)
type (Literal['text', 'image', 'image_url'])
text (str | None)
image_url (str | None)
image_data (bytes | None)
media_type (str | None)

type: Literal['text', 'image', 'image_url']¶

text: str | None¶

image_url: str | None¶

image_data: bytes | None¶

media_type: str | None¶

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

classmethod text_part(text)[source]¶

Create a text content part.

Parameters:: text (str)
Return type:: ContentPart

classmethod image_url_part(url)[source]¶

Create an image URL content part.

Parameters:: url (str)
Return type:: ContentPart

classmethod image_data_part(data, media_type='image/png')[source]¶

Create an image data content part.

Parameters:

data (bytes)
media_type (str)

Return type:

ContentPart

class agent.types.Message(**data)[source]¶

Bases: BaseModel

A normalized message in a conversation.

Parameters:

data (Any)
role (Literal['system', 'user', 'assistant', 'tool'])
content (str | list[ContentPart])
name (str | None)
tool_call_id (str | None)
tool_calls (list[dict[str, Any]] | None)

role: Literal['system', 'user', 'assistant', 'tool']¶

content: str | list[ContentPart]¶

name: str | None¶

tool_call_id: str | None¶

tool_calls: list[dict[str, Any]] | None¶

classmethod system(content)[source]¶

Create a system message.

Parameters:: content (str)
Return type:: Message

classmethod user(content)[source]¶

Create a user message.

Parameters:: content (str | list[ContentPart])
Return type:: Message

classmethod assistant(content=None, tool_calls=None)[source]¶

Create an assistant message.

Parameters:

content (str | None)
tool_calls (list[dict[str, Any]] | None)

Return type:

Message

classmethod tool(content, tool_call_id, name=None)[source]¶

Create a tool result message.

Parameters:

content (str)
tool_call_id (str)
name (str | None)

Return type:

Message

property text: str¶: Get the text content of the message.

model_config: ClassVar[ConfigDict] = {}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class agent.types.AgentRequest(**data)[source]¶

Bases: BaseModel

A normalized request to be sent to a provider.

Parameters:

data (Any)
input (str | None)
messages (list[Message])
system (str | None)
tools (list[Any])
output_schema (dict[str, Any] | None)
temperature (float | None)
max_tokens (int | None)
top_p (float | None)
stop (list[str] | None)
metadata (dict[str, Any])
session_id (str | None)

input: str | None¶

messages: list[Message]¶

system: str | None¶

tools: list[Any]¶

output_schema: dict[str, Any] | None¶

temperature: float | None¶

max_tokens: int | None¶

top_p: float | None¶

stop: list[str] | None¶

metadata: dict[str, Any]¶

session_id: str | None¶

property schema: dict[str, Any] | None¶: Alias for output_schema for backwards compatibility.

model_config: ClassVar[ConfigDict] = {}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

to_messages()[source]¶

Convert request to a list of messages.

Return type:: list[Message]

class agent.types.Usage(**data)[source]¶

Bases: BaseModel

Token usage information.

Parameters:

data (Any)
prompt_tokens (int)
completion_tokens (int)
total_tokens (int)

prompt_tokens: int¶

completion_tokens: int¶

total_tokens: int¶

classmethod from_dict(data)[source]¶

Create Usage from a dictionary.

Parameters:: data (dict[str, Any])
Return type:: Usage

model_config: ClassVar[ConfigDict] = {}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class agent.types.AgentResponse(**data)[source]¶

Bases: BaseModel

Normalized response from any provider.

Parameters:

data (Any)
text (str | None)
content (list[Any])
output (Any)
provider (str)
model (str)
usage (Usage | None)
stop_reason (str | None)
tool_calls (list[ToolCall])
raw (Any)
latency_ms (float | None)
cost_estimate (float | None)
request_id (str | None)

text: str | None¶

content: list[Any]¶

output: Any¶

provider: str¶

model: str¶

usage: Usage | None¶

stop_reason: str | None¶

tool_calls: list[ToolCall]¶

raw: Any¶

latency_ms: float | None¶

cost_estimate: float | None¶

request_id: str | None¶

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

property has_tool_calls: bool¶: Check if response contains tool calls.

to_dict()[source]¶

Convert response to a dictionary.

Return type:: dict[str, Any]

class agent.types.ToolSpec(**data)[source]¶

Bases: BaseModel

Specification for a tool that can be called by an LLM.

Parameters:

data (Any)
name (str)
description (str)
parameters (dict[str, Any])
function (Any | None)
is_async (bool)

name: str¶

description: str¶

parameters: dict[str, Any]¶

function: Any | None¶

is_async: bool¶

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

to_openai_schema()[source]¶

Convert to OpenAI function calling format.

Return type:: dict[str, Any]

to_anthropic_schema()[source]¶

Convert to Anthropic tool format.

Return type:: dict[str, Any]

to_gemini_schema()[source]¶

Convert to Gemini function declaration format.

Return type:: dict[str, Any]

class agent.types.ToolCall(**data)[source]¶

Bases: BaseModel

A tool call requested by the LLM.

Parameters:

data (Any)
id (str)
name (str)
arguments (dict[str, Any])

id: str¶

name: str¶

arguments: dict[str, Any]¶

to_dict()[source]¶

Convert to dictionary.

Return type:: dict[str, Any]

classmethod from_dict(data)[source]¶

Create from dictionary.

Parameters:: data (dict[str, Any])
Return type:: ToolCall

model_config: ClassVar[ConfigDict] = {}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class agent.types.ToolResult(**data)[source]¶

Bases: BaseModel

Result of executing a tool.

Parameters:

data (Any)
tool_call_id (str)
name (str)
content (str)
is_error (bool)

tool_call_id: str¶

name: str¶

content: str¶

is_error: bool¶

to_dict()[source]¶

Convert to dictionary.

Return type:: dict[str, Any]

model_config: ClassVar[ConfigDict] = {}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class agent.types.StreamEvent(**data)[source]¶

Bases: BaseModel

A normalized streaming event.

Parameters:

data (Any)
type (Literal['text_delta', 'tool_call_start', 'tool_call_delta', 'tool_result', 'message_start', 'message_end', 'usage', 'error'])
text (str | None)
tool_call (ToolCall | None)
tool_call_delta (dict[str, Any] | None)
tool_result (str | None)
usage (Usage | None)
error (str | None)
raw (Any)

type: Literal['text_delta', 'tool_call_start', 'tool_call_delta', 'tool_result', 'message_start', 'message_end', 'usage', 'error']¶

text: str | None¶

tool_call: ToolCall | None¶

tool_call_delta: dict[str, Any] | None¶

tool_result: str | None¶

usage: Usage | None¶

error: str | None¶

raw: Any¶

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

classmethod text_delta(text, raw=None)[source]¶

Create a text delta event.

Parameters:

text (str)
raw (Any)

Return type:

StreamEvent

classmethod tool_call_start(tool_call, raw=None)[source]¶

Create a tool call start event.

Parameters:

tool_call (ToolCall)
raw (Any)

Return type:

StreamEvent

classmethod tool_call_delta_event(tool_call_id, delta, raw=None)[source]¶

Create a tool call delta event.

Parameters:

tool_call_id (str)
delta (dict[str, Any])
raw (Any)

Return type:

StreamEvent

classmethod tool_result_event(tool_call_id, result, raw=None)[source]¶

Create a tool result event.

Parameters:

tool_call_id (str)
result (str)
raw (Any)

Return type:

StreamEvent

classmethod message_start_event(raw=None)[source]¶

Create a message start event.

Parameters:: raw (Any)
Return type:: StreamEvent

classmethod message_end(usage=None, raw=None)[source]¶

Create a message end event.

Parameters:

usage (Usage | None)
raw (Any)

Return type:

StreamEvent

classmethod usage_event(usage, raw=None)[source]¶

Create a usage event.

Parameters:

usage (Usage)
raw (Any)

Return type:

StreamEvent

classmethod error_event(error, raw=None)[source]¶

Create an error event.

Parameters:

error (str)
raw (Any)

Return type:

StreamEvent

class agent.types.AgentConfig(**data)[source]¶

Bases: BaseModel

Configuration for an Agent instance.

Parameters:

data (Any)
provider (str)
model (str)
api_key (str | None)
base_url (str | None)
timeout (float)
max_retries (int)
temperature (float | None)
max_tokens (int | None)
top_p (float | None)
default_system (str | None)
extra (dict[str, Any])

provider: str¶

model: str¶

api_key: str | None¶

base_url: str | None¶

timeout: float¶

max_retries: int¶

temperature: float | None¶

max_tokens: int | None¶

top_p: float | None¶

default_system: str | None¶

extra: dict[str, Any]¶

resolve_config()[source]¶

Resolve model alias and get API key/base URL from environment.

Return type:: AgentConfig

with_overrides(**kwargs)[source]¶

Create a new config with overrides.

Parameters:: kwargs (Any)
Return type:: AgentConfig

model_config: ClassVar[ConfigDict] = {}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class agent.types.ProviderCapabilities(**data)[source]¶

Bases: BaseModel

Declares what features a provider supports.

Parameters:

data (Any)
streaming (bool)
tools (bool)
structured_output (bool)
json_mode (bool)
vision (bool)
system_messages (bool)
batch (bool)
native_schema_output (bool)
max_context_tokens (int | None)
max_output_tokens (int | None)

streaming: bool¶

tools: bool¶

structured_output: bool¶

json_mode: bool¶

vision: bool¶

system_messages: bool¶

batch: bool¶

native_schema_output: bool¶

max_context_tokens: int | None¶

max_output_tokens: int | None¶

model_config: ClassVar[ConfigDict] = {}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class agent.types.RetryConfig(**data)[source]¶

Bases: BaseModel

Configuration for retry behavior.

Parameters:

data (Any)
max_retries (int)
initial_delay (float)
max_delay (float)
exponential_base (float)
jitter (bool)
retryable_errors (tuple[type[Exception], ...])

max_retries: int¶

initial_delay: float¶

max_delay: float¶

exponential_base: float¶

jitter: bool¶

retryable_errors: tuple[type[Exception], ...]¶

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

should_retry(error, attempt)[source]¶

Check if we should retry for this error.

Parameters:

error (Exception)
attempt (int)

Return type:

bool

get_delay(attempt, error=None)[source]¶

Calculate delay before next retry.

Parameters:

attempt (int)
error (Exception | None)

Return type:

float

class agent.types.ToolLoopConfig(**data)[source]¶

Bases: BaseModel

Configuration for tool loop behavior.

Parameters:

data (Any)
max_iterations (int)
max_tool_calls_per_iteration (int)
timeout_per_tool (float)
parallel_tool_execution (bool)
stop_on_error (bool)

max_iterations: int¶

max_tool_calls_per_iteration: int¶

timeout_per_tool: float¶

parallel_tool_execution: bool¶

stop_on_error: bool¶

model_config: ClassVar[ConfigDict] = {}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class agent.types.RoutingStrategy(*values)[source]¶

Bases: str, Enum

Available routing strategies.

FALLBACK = 'fallback'¶

ROUND_ROBIN = 'round_robin'¶

FASTEST = 'fastest'¶

CHEAPEST = 'cheapest'¶

CAPABILITY = 'capability'¶

CUSTOM = 'custom'¶

class agent.types.RouteResult(**data)[source]¶

Bases: BaseModel

Result of a routing decision.

Parameters:

data (Any)
agent (Any)
reason (str | None)

agent: Any¶

reason: str | None¶

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

Config¶

Configuration types for Agent.

agent.types.config.get_api_key(provider, api_key=None)[source]¶

Get API key for a provider.

Parameters:

provider (str)
api_key (str | None)

Return type:

str | None

agent.types.config.get_base_url(provider, base_url=None)[source]¶

Get base URL for a provider.

Parameters:

provider (str)
base_url (str | None)

Return type:

str | None

agent.types.config.resolve_model(model)[source]¶

Resolve model alias to full model name.

Parameters:: model (str)
Return type:: str

agent.types.config.estimate_cost(model, prompt_tokens, completion_tokens)[source]¶

Estimate cost for a request.

Parameters:

model (str)
prompt_tokens (int)
completion_tokens (int)

Return type:

float | None

class agent.types.config.ProviderCapabilities(**data)[source]¶

Bases: BaseModel

Declares what features a provider supports.

Parameters:

data (Any)
streaming (bool)
tools (bool)
structured_output (bool)
json_mode (bool)
vision (bool)
system_messages (bool)
batch (bool)
native_schema_output (bool)
max_context_tokens (int | None)
max_output_tokens (int | None)

streaming: bool¶

tools: bool¶

structured_output: bool¶

json_mode: bool¶

vision: bool¶

system_messages: bool¶

batch: bool¶

native_schema_output: bool¶

max_context_tokens: int | None¶

max_output_tokens: int | None¶

model_config: ClassVar[ConfigDict] = {}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class agent.types.config.AgentConfig(**data)[source]¶

Bases: BaseModel

Configuration for an Agent instance.

Parameters:

data (Any)
provider (str)
model (str)
api_key (str | None)
base_url (str | None)
timeout (float)
max_retries (int)
temperature (float | None)
max_tokens (int | None)
top_p (float | None)
default_system (str | None)
extra (dict[str, Any])

provider: str¶

model: str¶

api_key: str | None¶

base_url: str | None¶

timeout: float¶

max_retries: int¶

temperature: float | None¶

max_tokens: int | None¶

top_p: float | None¶

default_system: str | None¶

extra: dict[str, Any]¶

resolve_config()[source]¶

Resolve model alias and get API key/base URL from environment.

Return type:: AgentConfig

with_overrides(**kwargs)[source]¶

Create a new config with overrides.

Parameters:: kwargs (Any)
Return type:: AgentConfig

model_config: ClassVar[ConfigDict] = {}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class agent.types.config.RetryConfig(**data)[source]¶

Bases: BaseModel

Configuration for retry behavior.

Parameters:

data (Any)
max_retries (int)
initial_delay (float)
max_delay (float)
exponential_base (float)
jitter (bool)
retryable_errors (tuple[type[Exception], ...])

max_retries: int¶

initial_delay: float¶

max_delay: float¶

exponential_base: float¶

jitter: bool¶

retryable_errors: tuple[type[Exception], ...]¶

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

should_retry(error, attempt)[source]¶

Check if we should retry for this error.

Parameters:

error (Exception)
attempt (int)

Return type:

bool

get_delay(attempt, error=None)[source]¶

Calculate delay before next retry.

Parameters:

attempt (int)
error (Exception | None)

Return type:

float

class agent.types.config.ToolLoopConfig(**data)[source]¶

Bases: BaseModel

Configuration for tool loop behavior.

Parameters:

data (Any)
max_iterations (int)
max_tool_calls_per_iteration (int)
timeout_per_tool (float)
parallel_tool_execution (bool)
stop_on_error (bool)

max_iterations: int¶

max_tool_calls_per_iteration: int¶

timeout_per_tool: float¶

parallel_tool_execution: bool¶

stop_on_error: bool¶

model_config: ClassVar[ConfigDict] = {}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

Messages¶

Message types for Agent.

class agent.types.messages.ContentPart(**data)[source]¶

Bases: BaseModel

A part of message content (text, image, etc.).

Parameters:

data (Any)
type (Literal['text', 'image', 'image_url'])
text (str | None)
image_url (str | None)
image_data (bytes | None)
media_type (str | None)

type: Literal['text', 'image', 'image_url']¶

text: str | None¶

image_url: str | None¶

image_data: bytes | None¶

media_type: str | None¶

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

classmethod text_part(text)[source]¶

Create a text content part.

Parameters:: text (str)
Return type:: ContentPart

classmethod image_url_part(url)[source]¶

Create an image URL content part.

Parameters:: url (str)
Return type:: ContentPart

classmethod image_data_part(data, media_type='image/png')[source]¶

Create an image data content part.

Parameters:

data (bytes)
media_type (str)

Return type:

ContentPart

class agent.types.messages.Message(**data)[source]¶

Bases: BaseModel

A normalized message in a conversation.

Parameters:

data (Any)
role (Literal['system', 'user', 'assistant', 'tool'])
content (str | list[ContentPart])
name (str | None)
tool_call_id (str | None)
tool_calls (list[dict[str, Any]] | None)

role: Literal['system', 'user', 'assistant', 'tool']¶

content: str | list[ContentPart]¶

name: str | None¶

tool_call_id: str | None¶

tool_calls: list[dict[str, Any]] | None¶

classmethod system(content)[source]¶

Create a system message.

Parameters:: content (str)
Return type:: Message

classmethod user(content)[source]¶

Create a user message.

Parameters:: content (str | list[ContentPart])
Return type:: Message

classmethod assistant(content=None, tool_calls=None)[source]¶

Create an assistant message.

Parameters:

content (str | None)
tool_calls (list[dict[str, Any]] | None)

Return type:

Message

classmethod tool(content, tool_call_id, name=None)[source]¶

Create a tool result message.

Parameters:

content (str)
tool_call_id (str)
name (str | None)

Return type:

Message

property text: str¶: Get the text content of the message.

model_config: ClassVar[ConfigDict] = {}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class agent.types.messages.AgentRequest(**data)[source]¶

Bases: BaseModel

A normalized request to be sent to a provider.

Parameters:

data (Any)
input (str | None)
messages (list[Message])
system (str | None)
tools (list[Any])
output_schema (dict[str, Any] | None)
temperature (float | None)
max_tokens (int | None)
top_p (float | None)
stop (list[str] | None)
metadata (dict[str, Any])
session_id (str | None)

input: str | None¶

messages: list[Message]¶

system: str | None¶

tools: list[Any]¶

output_schema: dict[str, Any] | None¶

temperature: float | None¶

max_tokens: int | None¶

top_p: float | None¶

stop: list[str] | None¶

metadata: dict[str, Any]¶

session_id: str | None¶

property schema: dict[str, Any] | None¶: Alias for output_schema for backwards compatibility.

model_config: ClassVar[ConfigDict] = {}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

to_messages()[source]¶

Convert request to a list of messages.

Return type:: list[Message]

Response¶

Response types for Agent.

class agent.types.response.Usage(**data)[source]¶

Bases: BaseModel

Token usage information.

Parameters:

data (Any)
prompt_tokens (int)
completion_tokens (int)
total_tokens (int)

prompt_tokens: int¶

completion_tokens: int¶

total_tokens: int¶

classmethod from_dict(data)[source]¶

Create Usage from a dictionary.

Parameters:: data (dict[str, Any])
Return type:: Usage

model_config: ClassVar[ConfigDict] = {}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class agent.types.response.AgentResponse(**data)[source]¶

Bases: BaseModel

Normalized response from any provider.

Parameters:

data (Any)
text (str | None)
content (list[Any])
output (Any)
provider (str)
model (str)
usage (Usage | None)
stop_reason (str | None)
tool_calls (list[ToolCall])
raw (Any)
latency_ms (float | None)
cost_estimate (float | None)
request_id (str | None)

text: str | None¶

content: list[Any]¶

output: Any¶

provider: str¶

model: str¶

usage: Usage | None¶

stop_reason: str | None¶

tool_calls: list[ToolCall]¶

raw: Any¶

latency_ms: float | None¶

cost_estimate: float | None¶

request_id: str | None¶

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

property has_tool_calls: bool¶: Check if response contains tool calls.

to_dict()[source]¶

Convert response to a dictionary.

Return type:: dict[str, Any]

Router¶

Router types for Agent.

class agent.types.router.RoutingStrategy(*values)[source]¶

Bases: str, Enum

Available routing strategies.

FALLBACK = 'fallback'¶

ROUND_ROBIN = 'round_robin'¶

FASTEST = 'fastest'¶

CHEAPEST = 'cheapest'¶

CAPABILITY = 'capability'¶

CUSTOM = 'custom'¶

class agent.types.router.RouteResult(**data)[source]¶

Bases: BaseModel

Result of a routing decision.

Parameters:

data (Any)
agent (Any)
reason (str | None)

agent: Any¶

reason: str | None¶

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

Stream¶

Streaming types for Agent.

class agent.types.stream.StreamEvent(**data)[source]¶

Bases: BaseModel

A normalized streaming event.

Parameters:

data (Any)
type (Literal['text_delta', 'tool_call_start', 'tool_call_delta', 'tool_result', 'message_start', 'message_end', 'usage', 'error'])
text (str | None)
tool_call (ToolCall | None)
tool_call_delta (dict[str, Any] | None)
tool_result (str | None)
usage (Usage | None)
error (str | None)
raw (Any)

type: Literal['text_delta', 'tool_call_start', 'tool_call_delta', 'tool_result', 'message_start', 'message_end', 'usage', 'error']¶

text: str | None¶

tool_call: ToolCall | None¶

tool_call_delta: dict[str, Any] | None¶

tool_result: str | None¶

usage: Usage | None¶

error: str | None¶

raw: Any¶

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

classmethod text_delta(text, raw=None)[source]¶

Create a text delta event.

Parameters:

text (str)
raw (Any)

Return type:

StreamEvent

classmethod tool_call_start(tool_call, raw=None)[source]¶

Create a tool call start event.

Parameters:

tool_call (ToolCall)
raw (Any)

Return type:

StreamEvent

classmethod tool_call_delta_event(tool_call_id, delta, raw=None)[source]¶

Create a tool call delta event.

Parameters:

tool_call_id (str)
delta (dict[str, Any])
raw (Any)

Return type:

StreamEvent

classmethod tool_result_event(tool_call_id, result, raw=None)[source]¶

Create a tool result event.

Parameters:

tool_call_id (str)
result (str)
raw (Any)

Return type:

StreamEvent

classmethod message_start_event(raw=None)[source]¶

Create a message start event.

Parameters:: raw (Any)
Return type:: StreamEvent

classmethod message_end(usage=None, raw=None)[source]¶

Create a message end event.

Parameters:

usage (Usage | None)
raw (Any)

Return type:

StreamEvent

classmethod usage_event(usage, raw=None)[source]¶

Create a usage event.

Parameters:

usage (Usage)
raw (Any)

Return type:

StreamEvent

classmethod error_event(error, raw=None)[source]¶

Create an error event.

Parameters:

error (str)
raw (Any)

Return type:

StreamEvent

Tools¶

Tool-related types for Agent.

class agent.types.tools.ToolSpec(**data)[source]¶

Bases: BaseModel

Specification for a tool that can be called by an LLM.

Parameters:

data (Any)
name (str)
description (str)
parameters (dict[str, Any])
function (Any | None)
is_async (bool)

name: str¶

description: str¶

parameters: dict[str, Any]¶

function: Any | None¶

is_async: bool¶

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

to_openai_schema()[source]¶

Convert to OpenAI function calling format.

Return type:: dict[str, Any]

to_anthropic_schema()[source]¶

Convert to Anthropic tool format.

Return type:: dict[str, Any]

to_gemini_schema()[source]¶

Convert to Gemini function declaration format.

Return type:: dict[str, Any]

class agent.types.tools.ToolCall(**data)[source]¶

Bases: BaseModel

A tool call requested by the LLM.

Parameters:

data (Any)
id (str)
name (str)
arguments (dict[str, Any])

id: str¶

name: str¶

arguments: dict[str, Any]¶

to_dict()[source]¶

Convert to dictionary.

Return type:: dict[str, Any]

classmethod from_dict(data)[source]¶

Create from dictionary.

Parameters:: data (dict[str, Any])
Return type:: ToolCall

model_config: ClassVar[ConfigDict] = {}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class agent.types.tools.ToolResult(**data)[source]¶

Bases: BaseModel

Result of executing a tool.

Parameters:

data (Any)
tool_call_id (str)
name (str)
content (str)
is_error (bool)

tool_call_id: str¶

name: str¶

content: str¶

is_error: bool¶

to_dict()[source]¶

Convert to dictionary.

Return type:: dict[str, Any]

model_config: ClassVar[ConfigDict] = {}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].