Skip to content
  • Auto
  • Light
  • Dark
DiscordForumGitHubSign up
View as Markdown
Copy Markdown

Open in Claude
Open in ChatGPT

Agents

List Agents
agents.list(AgentListParams**kwargs) -> SyncArrayPage[AgentState]
get/v1/agents/
Create Agent
agents.create(AgentCreateParams**kwargs) -> AgentState
post/v1/agents/
Modify Agent
agents.modify(stragent_id, AgentModifyParams**kwargs) -> AgentState
patch/v1/agents/{agent_id}
Retrieve Agent
agents.retrieve(stragent_id, AgentRetrieveParams**kwargs) -> AgentState
get/v1/agents/{agent_id}
Delete Agent
agents.delete(stragent_id) -> object
delete/v1/agents/{agent_id}
Export Agent
agents.export_file(stragent_id, AgentExportFileParams**kwargs) -> AgentExportFileResponse
get/v1/agents/{agent_id}/export
Import Agent
agents.import_file(AgentImportFileParams**kwargs) -> AgentImportFileResponse
post/v1/agents/import
ModelsExpand Collapse
class AgentEnvironmentVariable:
agent_id: str

The ID of the agent this environment variable belongs to.

key: str

The name of the environment variable.

value: str

The value of the environment variable.

id: Optional[str]

The human-friendly ID of the Agent-env

created_at: Optional[datetime]

The timestamp when the object was created.

formatdate-time
created_by_id: Optional[str]

The id of the user that made this object.

description: Optional[str]

An optional description of the environment variable.

last_updated_by_id: Optional[str]

The id of the user that made this object.

updated_at: Optional[datetime]

The timestamp when the object was last updated.

formatdate-time
value_enc: Optional[str]

Encrypted secret value (stored as encrypted string)

class AgentState:

Representation of an agent's state. This is the state of the agent at a given time, and is persisted in the DB backend. The state has all the information needed to recreate a persisted agent.

id: str

The id of the agent. Assigned by the database.

agent_type: AgentType

The type of agent.

Accepts one of the following:
"memgpt_agent"
"memgpt_v2_agent"
"letta_v1_agent"
"react_agent"
"workflow_agent"
"split_thread_agent"
"sleeptime_agent"
"voice_convo_agent"
"voice_sleeptime_agent"
blocks: List[Block]

The memory blocks used by the agent.

value: str

Value of the block.

id: Optional[str]

The human-friendly ID of the Block

base_template_id: Optional[str]

The base template id of the block.

created_by_id: Optional[str]

The id of the user that made this Block.

deployment_id: Optional[str]

The id of the deployment.

description: Optional[str]

Description of the block.

entity_id: Optional[str]

The id of the entity within the template.

hidden: Optional[bool]

If set to True, the block will be hidden.

is_template: Optional[bool]

Whether the block is a template (e.g. saved human/persona options).

label: Optional[str]

Label of the block (e.g. 'human', 'persona') in the context window.

last_updated_by_id: Optional[str]

The id of the user that last updated this Block.

limit: Optional[int]

Character limit of the block.

metadata: Optional[Dict[str, object]]

Metadata of the block.

preserve_on_migration: Optional[bool]

Preserve the block on template migration.

project_id: Optional[str]

The associated project id.

read_only: Optional[bool]

Whether the agent has read-only access to the block.

template_id: Optional[str]

The id of the template.

template_name: Optional[str]

Name of the block if it is a template.

Deprecatedembedding_config: EmbeddingConfig

Deprecated: Use embedding field instead. The embedding configuration used by the agent.

embedding_dim: int

The dimension of the embedding.

embedding_endpoint_type: Literal["openai", "anthropic", "bedrock", 16 more]

The endpoint type for the model.

Accepts one of the following:
"openai"
"anthropic"
"bedrock"
"google_ai"
"google_vertex"
"azure"
"groq"
"ollama"
"webui"
"webui-legacy"
"lmstudio"
"lmstudio-legacy"
"llamacpp"
"koboldcpp"
"vllm"
"hugging-face"
"mistral"
"together"
"pinecone"
embedding_model: str

The model for the embedding.

azure_deployment: Optional[str]

The Azure deployment for the model.

azure_endpoint: Optional[str]

The Azure endpoint for the model.

azure_version: Optional[str]

The Azure version for the model.

batch_size: Optional[int]

The maximum batch size for processing embeddings.

embedding_chunk_size: Optional[int]

The chunk size of the embedding.

embedding_endpoint: Optional[str]

The endpoint for the model (None if local).

handle: Optional[str]

The handle for this config, in the format provider/model-name.

Deprecatedllm_config: LlmConfig

Deprecated: Use model field instead. The LLM configuration used by the agent.

context_window: int

The context window size for the model.

model: str

LLM model name.

model_endpoint_type: Literal["openai", "anthropic", "google_ai", 18 more]

The endpoint type for the model.

Accepts one of the following:
"openai"
"anthropic"
"google_ai"
"google_vertex"
"azure"
"groq"
"ollama"
"webui"
"webui-legacy"
"lmstudio"
"lmstudio-legacy"
"lmstudio-chatcompletions"
"llamacpp"
"koboldcpp"
"vllm"
"hugging-face"
"mistral"
"together"
"bedrock"
"deepseek"
"xai"
compatibility_type: Optional[Literal["gguf", "mlx"]]

The framework compatibility type for the model.

Accepts one of the following:
"gguf"
"mlx"
display_name: Optional[str]

A human-friendly display name for the model.

enable_reasoner: Optional[bool]

Whether or not the model should use extended thinking if it is a 'reasoning' style model

frequency_penalty: Optional[float]

Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. From OpenAI: Number between -2.0 and 2.0.

handle: Optional[str]

The handle for this config, in the format provider/model-name.

max_reasoning_tokens: Optional[int]

Configurable thinking budget for extended thinking. Used for enable_reasoner and also for Google Vertex models like Gemini 2.5 Flash. Minimum value is 1024 when used with enable_reasoner.

max_tokens: Optional[int]

The maximum number of tokens to generate. If not set, the model will use its default value.

model_endpoint: Optional[str]

The endpoint for the model.

model_wrapper: Optional[str]

The wrapper for the model.

parallel_tool_calls: Optional[bool]

If set to True, enables parallel tool calling. Defaults to False.

provider_category: Optional[ProviderCategory]

The provider category for the model.

Accepts one of the following:
"base"
"byok"
provider_name: Optional[str]

The provider name for the model.

put_inner_thoughts_in_kwargs: Optional[bool]

Puts 'inner_thoughts' as a kwarg in the function call if this is set to True. This helps with function calling performance and also the generation of inner thoughts.

reasoning_effort: Optional[Literal["minimal", "low", "medium", "high"]]

The reasoning effort to use when generating text reasoning models

Accepts one of the following:
"minimal"
"low"
"medium"
"high"
temperature: Optional[float]

The temperature to use when generating text with the model. A higher temperature will result in more random text.

tier: Optional[str]

The cost tier for the model (cloud only).

verbosity: Optional[Literal["low", "medium", "high"]]

Soft control for how verbose model output should be, used for GPT-5 models.

Accepts one of the following:
"low"
"medium"
"high"
Deprecatedmemory: Memory

Deprecated: Use blocks field instead. The in-context memory of the agent.

blocks: List[Block]

Memory blocks contained in the agent's in-context memory

value: str

Value of the block.

id: Optional[str]

The human-friendly ID of the Block

base_template_id: Optional[str]

The base template id of the block.

created_by_id: Optional[str]

The id of the user that made this Block.

deployment_id: Optional[str]

The id of the deployment.

description: Optional[str]

Description of the block.

entity_id: Optional[str]

The id of the entity within the template.

hidden: Optional[bool]

If set to True, the block will be hidden.

is_template: Optional[bool]

Whether the block is a template (e.g. saved human/persona options).

label: Optional[str]

Label of the block (e.g. 'human', 'persona') in the context window.

last_updated_by_id: Optional[str]

The id of the user that last updated this Block.

limit: Optional[int]

Character limit of the block.

metadata: Optional[Dict[str, object]]

Metadata of the block.

preserve_on_migration: Optional[bool]

Preserve the block on template migration.

project_id: Optional[str]

The associated project id.

read_only: Optional[bool]

Whether the agent has read-only access to the block.

template_id: Optional[str]

The id of the template.

template_name: Optional[str]

Name of the block if it is a template.

agent_type: Optional[Union[AgentType, str, null]]

Agent type controlling prompt rendering.

Accepts one of the following:
Literal["memgpt_agent", "memgpt_v2_agent", "letta_v1_agent", 6 more]
Accepts one of the following:
"memgpt_agent"
"memgpt_v2_agent"
"letta_v1_agent"
"react_agent"
"workflow_agent"
"split_thread_agent"
"sleeptime_agent"
"voice_convo_agent"
"voice_sleeptime_agent"
MemoryAgentTypeUnionMember1 = str
file_blocks: Optional[List[MemoryFileBlock]]

Special blocks representing the agent's in-context memory of an attached file

file_id: str

Unique identifier of the file.

is_open: bool

True if the agent currently has the file open.

source_id: str

Unique identifier of the source.

value: str

Value of the block.

id: Optional[str]

The human-friendly ID of the Block

base_template_id: Optional[str]

The base template id of the block.

created_by_id: Optional[str]

The id of the user that made this Block.

deployment_id: Optional[str]

The id of the deployment.

description: Optional[str]

Description of the block.

entity_id: Optional[str]

The id of the entity within the template.

hidden: Optional[bool]

If set to True, the block will be hidden.

is_template: Optional[bool]

Whether the block is a template (e.g. saved human/persona options).

label: Optional[str]

Label of the block (e.g. 'human', 'persona') in the context window.

last_accessed_at: Optional[datetime]

UTC timestamp of the agent’s most recent access to this file. Any operations from the open, close, or search tools will update this field.

formatdate-time
last_updated_by_id: Optional[str]

The id of the user that last updated this Block.

limit: Optional[int]

Character limit of the block.

metadata: Optional[Dict[str, object]]

Metadata of the block.

preserve_on_migration: Optional[bool]

Preserve the block on template migration.

project_id: Optional[str]

The associated project id.

read_only: Optional[bool]

Whether the agent has read-only access to the block.

template_id: Optional[str]

The id of the template.

template_name: Optional[str]

Name of the block if it is a template.

prompt_template: Optional[str]

Deprecated. Ignored for performance.

name: str

The name of the agent.

sources: List[Source]

The sources used by the agent.

id: str

The human-friendly ID of the Source

embedding_config: EmbeddingConfig

The embedding configuration used by the source.

embedding_dim: int

The dimension of the embedding.

embedding_endpoint_type: Literal["openai", "anthropic", "bedrock", 16 more]

The endpoint type for the model.

Accepts one of the following:
"openai"
"anthropic"
"bedrock"
"google_ai"
"google_vertex"
"azure"
"groq"
"ollama"
"webui"
"webui-legacy"
"lmstudio"
"lmstudio-legacy"
"llamacpp"
"koboldcpp"
"vllm"
"hugging-face"
"mistral"
"together"
"pinecone"
embedding_model: str

The model for the embedding.

azure_deployment: Optional[str]

The Azure deployment for the model.

azure_endpoint: Optional[str]

The Azure endpoint for the model.

azure_version: Optional[str]

The Azure version for the model.

batch_size: Optional[int]

The maximum batch size for processing embeddings.

embedding_chunk_size: Optional[int]

The chunk size of the embedding.

embedding_endpoint: Optional[str]

The endpoint for the model (None if local).

handle: Optional[str]

The handle for this config, in the format provider/model-name.

name: str

The name of the source.

created_at: Optional[datetime]

The timestamp when the source was created.

formatdate-time
created_by_id: Optional[str]

The id of the user that made this Tool.

description: Optional[str]

The description of the source.

instructions: Optional[str]

Instructions for how to use the source.

last_updated_by_id: Optional[str]

The id of the user that made this Tool.

metadata: Optional[Dict[str, object]]

Metadata associated with the source.

updated_at: Optional[datetime]

The timestamp when the source was last updated.

formatdate-time
vector_db_provider: Optional[VectorDBProvider]

The vector database provider used for this source's passages

Accepts one of the following:
"native"
"tpuf"
"pinecone"
system: str

The system prompt used by the agent.

tags: List[str]

The tags associated with the agent.

tools: List[Tool]

The tools used by the agent.

id: str

The human-friendly ID of the Tool

args_json_schema: Optional[Dict[str, object]]

The args JSON schema of the function.

created_by_id: Optional[str]

The id of the user that made this Tool.

default_requires_approval: Optional[bool]

Default value for whether or not executing this tool requires approval.

description: Optional[str]

The description of the tool.

enable_parallel_execution: Optional[bool]

If set to True, then this tool will potentially be executed concurrently with other tools. Default False.

json_schema: Optional[Dict[str, object]]

The JSON schema of the function.

last_updated_by_id: Optional[str]

The id of the user that made this Tool.

metadata: Optional[Dict[str, object]]

A dictionary of additional metadata for the tool.

name: Optional[str]

The name of the function.

npm_requirements: Optional[List[NpmRequirement]]

Optional list of npm packages required by this tool.

name: str

Name of the npm package.

minLength1
version: Optional[str]

Optional version of the package, following semantic versioning.

pip_requirements: Optional[List[PipRequirement]]

Optional list of pip packages required by this tool.

name: str

Name of the pip package.

minLength1
version: Optional[str]

Optional version of the package, following semantic versioning.

return_char_limit: Optional[int]

The maximum number of characters in the response.

maximum1000000
minimum1
source_code: Optional[str]

The source code of the function.

source_type: Optional[str]

The type of the source code.

tags: Optional[List[str]]

Metadata tags.

tool_type: Optional[ToolType]

The type of the tool.

Accepts one of the following:
"custom"
"letta_core"
"letta_memory_core"
"letta_multi_agent_core"
"letta_sleeptime_core"
"letta_voice_sleeptime_core"
"letta_builtin"
"letta_files_core"
"external_langchain"
"external_composio"
"external_mcp"
base_template_id: Optional[str]

The base template id of the agent.

created_at: Optional[datetime]

The timestamp when the object was created.

formatdate-time
created_by_id: Optional[str]

The id of the user that made this object.

deployment_id: Optional[str]

The id of the deployment.

description: Optional[str]

The description of the agent.

embedding: Optional[Embedding]

Schema for defining settings for an embedding model

model: str

The name of the model.

provider: Literal["openai", "ollama"]

The provider of the model.

Accepts one of the following:
"openai"
"ollama"
enable_sleeptime: Optional[bool]

If set to True, memory management will move to a background agent thread.

entity_id: Optional[str]

The id of the entity within the template.

hidden: Optional[bool]

If set to True, the agent will be hidden.

identities: Optional[List[Identity]]

The identities associated with this agent.

id: str

The human-friendly ID of the Identity

Deprecatedagent_ids: List[str]

The IDs of the agents associated with the identity.

Deprecatedblock_ids: List[str]

The IDs of the blocks associated with the identity.

identifier_key: str

External, user-generated identifier key of the identity.

identity_type: IdentityType

The type of the identity.

Accepts one of the following:
"org"
"user"
"other"
name: str

The name of the identity.

project_id: Optional[str]

The project id of the identity, if applicable.

properties: Optional[List[IdentityProperty]]

List of properties associated with the identity

key: str

The key of the property

type: Literal["string", "number", "boolean", "json"]

The type of the property

Accepts one of the following:
"string"
"number"
"boolean"
"json"
value: Union[str, float, bool, Dict[str, object]]

The value of the property

Accepts one of the following:
ValueUnionMember0 = str
ValueUnionMember1 = float
ValueUnionMember2 = bool
ValueUnionMember3 = Dict[str, object]
Deprecatedidentity_ids: Optional[List[str]]

Deprecated: Use identities field instead. The ids of the identities associated with this agent.

last_run_completion: Optional[datetime]

The timestamp when the agent last completed a run.

formatdate-time
last_run_duration_ms: Optional[int]

The duration in milliseconds of the agent's last run.

last_stop_reason: Optional[StopReasonType]

The stop reason from the agent's last run.

Accepts one of the following:
"end_turn"
"error"
"llm_api_error"
"invalid_llm_response"
"invalid_tool_call"
"max_steps"
"no_tool_call"
"tool_rule"
"cancelled"
"requires_approval"
last_updated_by_id: Optional[str]

The id of the user that made this object.

managed_group: Optional[Group]

The multi-agent group that this agent manages

id: str

The id of the group. Assigned by the database.

agent_ids: List[str]
description: str
manager_type: ManagerType
Accepts one of the following:
"round_robin"
"supervisor"
"dynamic"
"sleeptime"
"voice_sleeptime"
"swarm"
base_template_id: Optional[str]

The base template id.

deployment_id: Optional[str]

The id of the deployment.

hidden: Optional[bool]

If set to True, the group will be hidden.

last_processed_message_id: Optional[str]
manager_agent_id: Optional[str]
max_message_buffer_length: Optional[int]

The desired maximum length of messages in the context window of the convo agent. This is a best effort, and may be off slightly due to user/assistant interleaving.

max_turns: Optional[int]
min_message_buffer_length: Optional[int]

The desired minimum length of messages in the context window of the convo agent. This is a best effort, and may be off-by-one due to user/assistant interleaving.

project_id: Optional[str]

The associated project id.

Deprecatedshared_block_ids: Optional[List[str]]
sleeptime_agent_frequency: Optional[int]
template_id: Optional[str]

The id of the template.

termination_token: Optional[str]
turns_counter: Optional[int]
max_files_open: Optional[int]

Maximum number of files that can be open at once for this agent. Setting this too high may exceed the context window, which will break the agent.

message_buffer_autoclear: Optional[bool]

If set to True, the agent will not remember previous messages (though the agent will still retain state via core memory blocks and archival/recall memory). Not recommended unless you have an advanced use case.

message_ids: Optional[List[str]]

The ids of the messages in the agent's in-context memory.

metadata: Optional[Dict[str, object]]

The metadata of the agent.

model: Optional[Model]

Schema for defining settings for a model

model: str

The name of the model.

max_output_tokens: Optional[int]

The maximum number of tokens the model can generate.

parallel_tool_calls: Optional[bool]

Whether to enable parallel tool calling.

Deprecatedmulti_agent_group: Optional[Group]

Deprecated: Use managed_group field instead. The multi-agent group that this agent manages.

id: str

The id of the group. Assigned by the database.

agent_ids: List[str]
description: str
manager_type: ManagerType
Accepts one of the following:
"round_robin"
"supervisor"
"dynamic"
"sleeptime"
"voice_sleeptime"
"swarm"
base_template_id: Optional[str]

The base template id.

deployment_id: Optional[str]

The id of the deployment.

hidden: Optional[bool]

If set to True, the group will be hidden.

last_processed_message_id: Optional[str]
manager_agent_id: Optional[str]
max_message_buffer_length: Optional[int]

The desired maximum length of messages in the context window of the convo agent. This is a best effort, and may be off slightly due to user/assistant interleaving.

max_turns: Optional[int]
min_message_buffer_length: Optional[int]

The desired minimum length of messages in the context window of the convo agent. This is a best effort, and may be off-by-one due to user/assistant interleaving.

project_id: Optional[str]

The associated project id.

Deprecatedshared_block_ids: Optional[List[str]]
sleeptime_agent_frequency: Optional[int]
template_id: Optional[str]

The id of the template.

termination_token: Optional[str]
turns_counter: Optional[int]
per_file_view_window_char_limit: Optional[int]

The per-file view window character limit for this agent. Setting this too high may exceed the context window, which will break the agent.

project_id: Optional[str]

The id of the project the agent belongs to.

response_format: Optional[ResponseFormat]

The response format used by the agent

Accepts one of the following:
class TextResponseFormat:

Response format for plain text responses.

type: Optional[Literal["text"]]

The type of the response format.

Accepts one of the following:
"text"
class JsonSchemaResponseFormat:

Response format for JSON schema-based responses.

json_schema: Dict[str, object]

The JSON schema of the response.

type: Optional[Literal["json_schema"]]

The type of the response format.

Accepts one of the following:
"json_schema"
class JsonObjectResponseFormat:

Response format for JSON object responses.

type: Optional[Literal["json_object"]]

The type of the response format.

Accepts one of the following:
"json_object"
secrets: Optional[List[AgentEnvironmentVariable]]

The environment variables for tool execution specific to this agent.

agent_id: str

The ID of the agent this environment variable belongs to.

key: str

The name of the environment variable.

value: str

The value of the environment variable.

id: Optional[str]

The human-friendly ID of the Agent-env

created_at: Optional[datetime]

The timestamp when the object was created.

formatdate-time
created_by_id: Optional[str]

The id of the user that made this object.

description: Optional[str]

An optional description of the environment variable.

last_updated_by_id: Optional[str]

The id of the user that made this object.

updated_at: Optional[datetime]

The timestamp when the object was last updated.

formatdate-time
value_enc: Optional[str]

Encrypted secret value (stored as encrypted string)

template_id: Optional[str]

The id of the template the agent belongs to.

timezone: Optional[str]

The timezone of the agent (IANA format).

Deprecatedtool_exec_environment_variables: Optional[List[AgentEnvironmentVariable]]

Deprecated: use secrets field instead.

agent_id: str

The ID of the agent this environment variable belongs to.

key: str

The name of the environment variable.

value: str

The value of the environment variable.

id: Optional[str]

The human-friendly ID of the Agent-env

created_at: Optional[datetime]

The timestamp when the object was created.

formatdate-time
created_by_id: Optional[str]

The id of the user that made this object.

description: Optional[str]

An optional description of the environment variable.

last_updated_by_id: Optional[str]

The id of the user that made this object.

updated_at: Optional[datetime]

The timestamp when the object was last updated.

formatdate-time
value_enc: Optional[str]

Encrypted secret value (stored as encrypted string)

tool_rules: Optional[List[ToolRule]]

The list of tool rules.

Accepts one of the following:
class ChildToolRule:

A ToolRule represents a tool that can be invoked by the agent.

children: List[str]

The children tools that can be invoked.

tool_name: str

The name of the tool. Must exist in the database for the user's organization.

child_arg_nodes: Optional[List[ChildArgNode]]

Optional list of typed child argument overrides. Each node must reference a child in 'children'.

name: str

The name of the child tool to invoke next.

args: Optional[Dict[str, object]]

Optional prefilled arguments for this child tool. Keys must match the tool's parameter names and values must satisfy the tool's JSON schema. Supports partial prefill; non-overlapping parameters are left to the model.

prompt_template: Optional[str]

Optional template string (ignored).

type: Optional[Literal["constrain_child_tools"]]
Accepts one of the following:
"constrain_child_tools"
class InitToolRule:

Represents the initial tool rule configuration.

tool_name: str

The name of the tool. Must exist in the database for the user's organization.

args: Optional[Dict[str, object]]

Optional prefilled arguments for this tool. When present, these values will override any LLM-provided arguments with the same keys during invocation. Keys must match the tool's parameter names and values must satisfy the tool's JSON schema. Supports partial prefill; non-overlapping parameters are left to the model.

prompt_template: Optional[str]

Optional template string (ignored). Rendering uses fast built-in formatting for performance.

type: Optional[Literal["run_first"]]
Accepts one of the following:
"run_first"
class TerminalToolRule:

Represents a terminal tool rule configuration where if this tool gets called, it must end the agent loop.

tool_name: str

The name of the tool. Must exist in the database for the user's organization.

prompt_template: Optional[str]

Optional template string (ignored).

type: Optional[Literal["exit_loop"]]
Accepts one of the following:
"exit_loop"
class ConditionalToolRule:

A ToolRule that conditionally maps to different child tools based on the output.

child_output_mapping: Dict[str, str]

The output case to check for mapping

tool_name: str

The name of the tool. Must exist in the database for the user's organization.

default_child: Optional[str]

The default child tool to be called. If None, any tool can be called.

prompt_template: Optional[str]

Optional template string (ignored).

require_output_mapping: Optional[bool]

Whether to throw an error when output doesn't match any case

type: Optional[Literal["conditional"]]
Accepts one of the following:
"conditional"
class ContinueToolRule:

Represents a tool rule configuration where if this tool gets called, it must continue the agent loop.

tool_name: str

The name of the tool. Must exist in the database for the user's organization.

prompt_template: Optional[str]

Optional template string (ignored).

type: Optional[Literal["continue_loop"]]
Accepts one of the following:
"continue_loop"
class RequiredBeforeExitToolRule:

Represents a tool rule configuration where this tool must be called before the agent loop can exit.

tool_name: str

The name of the tool. Must exist in the database for the user's organization.

prompt_template: Optional[str]

Optional template string (ignored).

type: Optional[Literal["required_before_exit"]]
Accepts one of the following:
"required_before_exit"
class MaxCountPerStepToolRule:

Represents a tool rule configuration which constrains the total number of times this tool can be invoked in a single step.

max_count_limit: int

The max limit for the total number of times this tool can be invoked in a single step.

tool_name: str

The name of the tool. Must exist in the database for the user's organization.

prompt_template: Optional[str]

Optional template string (ignored).

type: Optional[Literal["max_count_per_step"]]
Accepts one of the following:
"max_count_per_step"
class ParentToolRule:

A ToolRule that only allows a child tool to be called if the parent has been called.

children: List[str]

The children tools that can be invoked.

tool_name: str

The name of the tool. Must exist in the database for the user's organization.

prompt_template: Optional[str]

Optional template string (ignored).

type: Optional[Literal["parent_last_tool"]]
Accepts one of the following:
"parent_last_tool"
class RequiresApprovalToolRule:

Represents a tool rule configuration which requires approval before the tool can be invoked.

tool_name: str

The name of the tool. Must exist in the database for the user's organization.

prompt_template: Optional[str]

Optional template string (ignored). Rendering uses fast built-in formatting for performance.

type: Optional[Literal["requires_approval"]]
Accepts one of the following:
"requires_approval"
updated_at: Optional[datetime]

The timestamp when the object was last updated.

formatdate-time
AgentType = Literal["memgpt_agent", "memgpt_v2_agent", "letta_v1_agent", 6 more]

Enum to represent the type of agent.

Accepts one of the following:
"memgpt_agent"
"memgpt_v2_agent"
"letta_v1_agent"
"react_agent"
"workflow_agent"
"split_thread_agent"
"sleeptime_agent"
"voice_convo_agent"
"voice_sleeptime_agent"
class ChildToolRule:

A ToolRule represents a tool that can be invoked by the agent.

children: List[str]

The children tools that can be invoked.

tool_name: str

The name of the tool. Must exist in the database for the user's organization.

child_arg_nodes: Optional[List[ChildArgNode]]

Optional list of typed child argument overrides. Each node must reference a child in 'children'.

name: str

The name of the child tool to invoke next.

args: Optional[Dict[str, object]]

Optional prefilled arguments for this child tool. Keys must match the tool's parameter names and values must satisfy the tool's JSON schema. Supports partial prefill; non-overlapping parameters are left to the model.

prompt_template: Optional[str]

Optional template string (ignored).

type: Optional[Literal["constrain_child_tools"]]
Accepts one of the following:
"constrain_child_tools"
class ConditionalToolRule:

A ToolRule that conditionally maps to different child tools based on the output.

child_output_mapping: Dict[str, str]

The output case to check for mapping

tool_name: str

The name of the tool. Must exist in the database for the user's organization.

default_child: Optional[str]

The default child tool to be called. If None, any tool can be called.

prompt_template: Optional[str]

Optional template string (ignored).

require_output_mapping: Optional[bool]

Whether to throw an error when output doesn't match any case

type: Optional[Literal["conditional"]]
Accepts one of the following:
"conditional"
class ContinueToolRule:

Represents a tool rule configuration where if this tool gets called, it must continue the agent loop.

tool_name: str

The name of the tool. Must exist in the database for the user's organization.

prompt_template: Optional[str]

Optional template string (ignored).

type: Optional[Literal["continue_loop"]]
Accepts one of the following:
"continue_loop"
class InitToolRule:

Represents the initial tool rule configuration.

tool_name: str

The name of the tool. Must exist in the database for the user's organization.

args: Optional[Dict[str, object]]

Optional prefilled arguments for this tool. When present, these values will override any LLM-provided arguments with the same keys during invocation. Keys must match the tool's parameter names and values must satisfy the tool's JSON schema. Supports partial prefill; non-overlapping parameters are left to the model.

prompt_template: Optional[str]

Optional template string (ignored). Rendering uses fast built-in formatting for performance.

type: Optional[Literal["run_first"]]
Accepts one of the following:
"run_first"
class JsonObjectResponseFormat:

Response format for JSON object responses.

type: Optional[Literal["json_object"]]

The type of the response format.

Accepts one of the following:
"json_object"
class JsonSchemaResponseFormat:

Response format for JSON schema-based responses.

json_schema: Dict[str, object]

The JSON schema of the response.

type: Optional[Literal["json_schema"]]

The type of the response format.

Accepts one of the following:
"json_schema"
LettaMessageContentUnion = LettaMessageContentUnion

Sent via the Anthropic Messages API

Accepts one of the following:
class TextContent:
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
class ImageContent:
source: Source

The source of the image.

Accepts one of the following:
class SourceURLImage:
url: str

The URL of the image.

type: Optional[Literal["url"]]

The source type for the image.

Accepts one of the following:
"url"
class SourceBase64Image:
data: str

The base64 encoded image data.

media_type: str

The media type for the image.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

type: Optional[Literal["base64"]]

The source type for the image.

Accepts one of the following:
"base64"
class SourceLettaImage:
file_id: str

The unique identifier of the image file persisted in storage.

data: Optional[str]

The base64 encoded image data.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

media_type: Optional[str]

The media type for the image.

type: Optional[Literal["letta"]]

The source type for the image.

Accepts one of the following:
"letta"
type: Optional[Literal["image"]]

The type of the message.

Accepts one of the following:
"image"
class ToolCallContent:
id: str

A unique identifier for this specific tool call instance.

input: Dict[str, object]

The parameters being passed to the tool, structured as a dictionary of parameter names to values.

name: str

The name of the tool being called.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this tool call.

type: Optional[Literal["tool_call"]]

Indicates this content represents a tool call event.

Accepts one of the following:
"tool_call"
class ToolReturnContent:
content: str

The content returned by the tool execution.

is_error: bool

Indicates whether the tool execution resulted in an error.

tool_call_id: str

References the ID of the ToolCallContent that initiated this tool call.

type: Optional[Literal["tool_return"]]

Indicates this content represents a tool return event.

Accepts one of the following:
"tool_return"
class ReasoningContent:

Sent via the Anthropic Messages API

is_native: bool

Whether the reasoning content was generated by a reasoner model that processed this step.

reasoning: str

The intermediate reasoning or thought process content.

signature: Optional[str]

A unique identifier for this reasoning step.

type: Optional[Literal["reasoning"]]

Indicates this is a reasoning/intermediate step.

Accepts one of the following:
"reasoning"
class RedactedReasoningContent:

Sent via the Anthropic Messages API

data: str

The redacted or filtered intermediate reasoning content.

type: Optional[Literal["redacted_reasoning"]]

Indicates this is a redacted thinking step.

Accepts one of the following:
"redacted_reasoning"
class OmittedReasoningContent:

A placeholder for reasoning content we know is present, but isn't returned by the provider (e.g. OpenAI GPT-5 on ChatCompletions)

signature: Optional[str]

A unique identifier for this reasoning step.

type: Optional[Literal["omitted_reasoning"]]

Indicates this is an omitted reasoning step.

Accepts one of the following:
"omitted_reasoning"
class MaxCountPerStepToolRule:

Represents a tool rule configuration which constrains the total number of times this tool can be invoked in a single step.

max_count_limit: int

The max limit for the total number of times this tool can be invoked in a single step.

tool_name: str

The name of the tool. Must exist in the database for the user's organization.

prompt_template: Optional[str]

Optional template string (ignored).

type: Optional[Literal["max_count_per_step"]]
Accepts one of the following:
"max_count_per_step"
class MessageCreate:

Request to create a message

content: Union[List[LettaMessageContentUnion], str]

The content of the message.

Accepts one of the following:
ContentUnionMember0 = List[LettaMessageContentUnion]
Accepts one of the following:
class TextContent:
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
class ImageContent:
source: Source

The source of the image.

Accepts one of the following:
class SourceURLImage:
url: str

The URL of the image.

type: Optional[Literal["url"]]

The source type for the image.

Accepts one of the following:
"url"
class SourceBase64Image:
data: str

The base64 encoded image data.

media_type: str

The media type for the image.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

type: Optional[Literal["base64"]]

The source type for the image.

Accepts one of the following:
"base64"
class SourceLettaImage:
file_id: str

The unique identifier of the image file persisted in storage.

data: Optional[str]

The base64 encoded image data.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

media_type: Optional[str]

The media type for the image.

type: Optional[Literal["letta"]]

The source type for the image.

Accepts one of the following:
"letta"
type: Optional[Literal["image"]]

The type of the message.

Accepts one of the following:
"image"
class ToolCallContent:
id: str

A unique identifier for this specific tool call instance.

input: Dict[str, object]

The parameters being passed to the tool, structured as a dictionary of parameter names to values.

name: str

The name of the tool being called.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this tool call.

type: Optional[Literal["tool_call"]]

Indicates this content represents a tool call event.

Accepts one of the following:
"tool_call"
class ToolReturnContent:
content: str

The content returned by the tool execution.

is_error: bool

Indicates whether the tool execution resulted in an error.

tool_call_id: str

References the ID of the ToolCallContent that initiated this tool call.

type: Optional[Literal["tool_return"]]

Indicates this content represents a tool return event.

Accepts one of the following:
"tool_return"
class ReasoningContent:

Sent via the Anthropic Messages API

is_native: bool

Whether the reasoning content was generated by a reasoner model that processed this step.

reasoning: str

The intermediate reasoning or thought process content.

signature: Optional[str]

A unique identifier for this reasoning step.

type: Optional[Literal["reasoning"]]

Indicates this is a reasoning/intermediate step.

Accepts one of the following:
"reasoning"
class RedactedReasoningContent:

Sent via the Anthropic Messages API

data: str

The redacted or filtered intermediate reasoning content.

type: Optional[Literal["redacted_reasoning"]]

Indicates this is a redacted thinking step.

Accepts one of the following:
"redacted_reasoning"
class OmittedReasoningContent:

A placeholder for reasoning content we know is present, but isn't returned by the provider (e.g. OpenAI GPT-5 on ChatCompletions)

signature: Optional[str]

A unique identifier for this reasoning step.

type: Optional[Literal["omitted_reasoning"]]

Indicates this is an omitted reasoning step.

Accepts one of the following:
"omitted_reasoning"
ContentUnionMember1 = str
role: Literal["user", "system", "assistant"]

The role of the participant.

Accepts one of the following:
"user"
"system"
"assistant"
batch_item_id: Optional[str]

The id of the LLMBatchItem that this message is associated with

group_id: Optional[str]

The multi-agent group that the message was sent in

name: Optional[str]

The name of the participant.

otid: Optional[str]

The offline threading id associated with this message

sender_id: Optional[str]

The id of the sender of the message, can be an identity id or agent id

type: Optional[Literal["message"]]

The message type to be created.

Accepts one of the following:
"message"
class ParentToolRule:

A ToolRule that only allows a child tool to be called if the parent has been called.

children: List[str]

The children tools that can be invoked.

tool_name: str

The name of the tool. Must exist in the database for the user's organization.

prompt_template: Optional[str]

Optional template string (ignored).

type: Optional[Literal["parent_last_tool"]]
Accepts one of the following:
"parent_last_tool"
class RequiredBeforeExitToolRule:

Represents a tool rule configuration where this tool must be called before the agent loop can exit.

tool_name: str

The name of the tool. Must exist in the database for the user's organization.

prompt_template: Optional[str]

Optional template string (ignored).

type: Optional[Literal["required_before_exit"]]
Accepts one of the following:
"required_before_exit"
class RequiresApprovalToolRule:

Represents a tool rule configuration which requires approval before the tool can be invoked.

tool_name: str

The name of the tool. Must exist in the database for the user's organization.

prompt_template: Optional[str]

Optional template string (ignored). Rendering uses fast built-in formatting for performance.

type: Optional[Literal["requires_approval"]]
Accepts one of the following:
"requires_approval"
class TerminalToolRule:

Represents a terminal tool rule configuration where if this tool gets called, it must end the agent loop.

tool_name: str

The name of the tool. Must exist in the database for the user's organization.

prompt_template: Optional[str]

Optional template string (ignored).

type: Optional[Literal["exit_loop"]]
Accepts one of the following:
"exit_loop"
class TextResponseFormat:

Response format for plain text responses.

type: Optional[Literal["text"]]

The type of the response format.

Accepts one of the following:
"text"

AgentsMessages

List Messages
agents.messages.list(stragent_id, MessageListParams**kwargs) -> SyncArrayPage[LettaMessageUnion]
get/v1/agents/{agent_id}/messages
Send Message
agents.messages.send(stragent_id, MessageSendParams**kwargs) -> LettaResponse
post/v1/agents/{agent_id}/messages
Modify Message
agents.messages.modify(strmessage_id, MessageModifyParams**kwargs) -> MessageModifyResponse
patch/v1/agents/{agent_id}/messages/{message_id}
Send Message Streaming
agents.messages.stream(stragent_id, MessageStreamParams**kwargs) -> LettaStreamingResponse
post/v1/agents/{agent_id}/messages/stream
Cancel Message
agents.messages.cancel(stragent_id, MessageCancelParams**kwargs) -> MessageCancelResponse
post/v1/agents/{agent_id}/messages/cancel
Send Message Async
agents.messages.send_async(stragent_id, MessageSendAsyncParams**kwargs) -> Run
post/v1/agents/{agent_id}/messages/async
Reset Messages
agents.messages.reset(stragent_id, MessageResetParams**kwargs) -> AgentState
patch/v1/agents/{agent_id}/reset-messages
Summarize Messages
agents.messages.summarize(stragent_id)
post/v1/agents/{agent_id}/summarize
ModelsExpand Collapse
class ApprovalCreate:

Input to approve or deny a tool call request

Deprecatedapproval_request_id: Optional[str]

The message ID of the approval request

approvals: Optional[List[Approval]]

The list of approval responses

Accepts one of the following:
class ApprovalApprovalReturn:
approve: bool

Whether the tool has been approved

tool_call_id: str

The ID of the tool call that corresponds to this approval

reason: Optional[str]

An optional explanation for the provided approval status

type: Optional[Literal["approval"]]

The message type to be created.

Accepts one of the following:
"approval"
class ToolReturn:
status: Literal["success", "error"]
Accepts one of the following:
"success"
"error"
tool_call_id: str
tool_return: str
stderr: Optional[List[str]]
stdout: Optional[List[str]]
type: Optional[Literal["tool"]]

The message type to be created.

Accepts one of the following:
"tool"
Deprecatedapprove: Optional[bool]

Whether the tool has been approved

group_id: Optional[str]

The multi-agent group that the message was sent in

Deprecatedreason: Optional[str]

An optional explanation for the provided approval status

type: Optional[Literal["approval"]]

The message type to be created.

Accepts one of the following:
"approval"
class ApprovalRequestMessage:

A message representing a request for approval to call a tool (generated by the LLM to trigger tool execution).

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message tool_call (ToolCall): The tool call

id: str
date: datetime
Deprecatedtool_call: ToolCall

The tool call that has been requested by the llm to run

Accepts one of the following:
class ToolCall:
arguments: str
name: str
tool_call_id: str
class ToolCallDelta:
arguments: Optional[str]
name: Optional[str]
tool_call_id: Optional[str]
is_err: Optional[bool]
message_type: Optional[Literal["approval_request_message"]]

The type of the message.

Accepts one of the following:
"approval_request_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
tool_calls: Optional[ToolCalls]

The tool calls that have been requested by the llm to run, which are pending approval

Accepts one of the following:
ToolCallsUnionMember0 = List[ToolCall]
arguments: str
name: str
tool_call_id: str
class ToolCallDelta:
arguments: Optional[str]
name: Optional[str]
tool_call_id: Optional[str]
class ApprovalResponseMessage:

A message representing a response form the user indicating whether a tool has been approved to run.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message approve: (bool) Whether the tool has been approved approval_request_id: The ID of the approval request reason: (Optional[str]) An optional explanation for the provided approval status

id: str
date: datetime
Deprecatedapproval_request_id: Optional[str]

The message ID of the approval request

approvals: Optional[List[Approval]]

The list of approval responses

Accepts one of the following:
class ApprovalApprovalReturn:
approve: bool

Whether the tool has been approved

tool_call_id: str

The ID of the tool call that corresponds to this approval

reason: Optional[str]

An optional explanation for the provided approval status

type: Optional[Literal["approval"]]

The message type to be created.

Accepts one of the following:
"approval"
class ToolReturn:
status: Literal["success", "error"]
Accepts one of the following:
"success"
"error"
tool_call_id: str
tool_return: str
stderr: Optional[List[str]]
stdout: Optional[List[str]]
type: Optional[Literal["tool"]]

The message type to be created.

Accepts one of the following:
"tool"
Deprecatedapprove: Optional[bool]

Whether the tool has been approved

is_err: Optional[bool]
message_type: Optional[Literal["approval_response_message"]]

The type of the message.

Accepts one of the following:
"approval_response_message"
name: Optional[str]
otid: Optional[str]
Deprecatedreason: Optional[str]

An optional explanation for the provided approval status

run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class AssistantMessage:

A message sent by the LLM in response to user input. Used in the LLM context.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message content (Union[str, List[LettaAssistantMessageContentUnion]]): The message content sent by the agent (can be a string or an array of content parts)

id: str
content: Union[List[LettaAssistantMessageContentUnion], str]

The message content sent by the agent (can be a string or an array of content parts)

Accepts one of the following:
ContentUnionMember0 = List[LettaAssistantMessageContentUnion]
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
ContentUnionMember1 = str
date: datetime
is_err: Optional[bool]
message_type: Optional[Literal["assistant_message"]]

The type of the message.

Accepts one of the following:
"assistant_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class EventMessage:

A message for notifying the developer that an event that has occured (e.g. a compaction). Events are NOT part of the context window.

id: str
date: datetime
event_data: Dict[str, object]
event_type: Literal["compaction"]
Accepts one of the following:
"compaction"
is_err: Optional[bool]
message_type: Optional[Literal["event"]]
Accepts one of the following:
"event"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class HiddenReasoningMessage:

Representation of an agent's internal reasoning where reasoning content has been hidden from the response.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message state (Literal["redacted", "omitted"]): Whether the reasoning content was redacted by the provider or simply omitted by the API hidden_reasoning (Optional[str]): The internal reasoning of the agent

id: str
date: datetime
state: Literal["redacted", "omitted"]
Accepts one of the following:
"redacted"
"omitted"
hidden_reasoning: Optional[str]
is_err: Optional[bool]
message_type: Optional[Literal["hidden_reasoning_message"]]

The type of the message.

Accepts one of the following:
"hidden_reasoning_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class ImageContent:
source: Source

The source of the image.

Accepts one of the following:
class SourceURLImage:
url: str

The URL of the image.

type: Optional[Literal["url"]]

The source type for the image.

Accepts one of the following:
"url"
class SourceBase64Image:
data: str

The base64 encoded image data.

media_type: str

The media type for the image.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

type: Optional[Literal["base64"]]

The source type for the image.

Accepts one of the following:
"base64"
class SourceLettaImage:
file_id: str

The unique identifier of the image file persisted in storage.

data: Optional[str]

The base64 encoded image data.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

media_type: Optional[str]

The media type for the image.

type: Optional[Literal["letta"]]

The source type for the image.

Accepts one of the following:
"letta"
type: Optional[Literal["image"]]

The type of the message.

Accepts one of the following:
"image"
JobStatus = Literal["created", "running", "completed", 4 more]

Status of the job.

Accepts one of the following:
"created"
"running"
"completed"
"failed"
"pending"
"cancelled"
"expired"
JobType = Literal["job", "run", "batch"]
Accepts one of the following:
"job"
"run"
"batch"
class LettaAssistantMessageContentUnion:
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
LettaMessageUnion = LettaMessageUnion

A message generated by the system. Never streamed back on a response, only used for cursor pagination.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message content (str): The message content sent by the system

Accepts one of the following:
class SystemMessage:

A message generated by the system. Never streamed back on a response, only used for cursor pagination.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message content (str): The message content sent by the system

id: str
content: str

The message content sent by the system

date: datetime
is_err: Optional[bool]
message_type: Optional[Literal["system_message"]]

The type of the message.

Accepts one of the following:
"system_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class UserMessage:

A message sent by the user. Never streamed back on a response, only used for cursor pagination.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message content (Union[str, List[LettaUserMessageContentUnion]]): The message content sent by the user (can be a string or an array of multi-modal content parts)

id: str
content: Union[List[LettaUserMessageContentUnion], str]

The message content sent by the user (can be a string or an array of multi-modal content parts)

Accepts one of the following:
ContentUnionMember0 = List[LettaUserMessageContentUnion]
Accepts one of the following:
class TextContent:
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
class ImageContent:
source: Source

The source of the image.

Accepts one of the following:
class SourceURLImage:
url: str

The URL of the image.

type: Optional[Literal["url"]]

The source type for the image.

Accepts one of the following:
"url"
class SourceBase64Image:
data: str

The base64 encoded image data.

media_type: str

The media type for the image.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

type: Optional[Literal["base64"]]

The source type for the image.

Accepts one of the following:
"base64"
class SourceLettaImage:
file_id: str

The unique identifier of the image file persisted in storage.

data: Optional[str]

The base64 encoded image data.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

media_type: Optional[str]

The media type for the image.

type: Optional[Literal["letta"]]

The source type for the image.

Accepts one of the following:
"letta"
type: Optional[Literal["image"]]

The type of the message.

Accepts one of the following:
"image"
ContentUnionMember1 = str
date: datetime
is_err: Optional[bool]
message_type: Optional[Literal["user_message"]]

The type of the message.

Accepts one of the following:
"user_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class ReasoningMessage:

Representation of an agent's internal reasoning.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message source (Literal["reasoner_model", "non_reasoner_model"]): Whether the reasoning content was generated natively by a reasoner model or derived via prompting reasoning (str): The internal reasoning of the agent signature (Optional[str]): The model-generated signature of the reasoning step

id: str
date: datetime
reasoning: str
is_err: Optional[bool]
message_type: Optional[Literal["reasoning_message"]]

The type of the message.

Accepts one of the following:
"reasoning_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
signature: Optional[str]
source: Optional[Literal["reasoner_model", "non_reasoner_model"]]
Accepts one of the following:
"reasoner_model"
"non_reasoner_model"
step_id: Optional[str]
class HiddenReasoningMessage:

Representation of an agent's internal reasoning where reasoning content has been hidden from the response.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message state (Literal["redacted", "omitted"]): Whether the reasoning content was redacted by the provider or simply omitted by the API hidden_reasoning (Optional[str]): The internal reasoning of the agent

id: str
date: datetime
state: Literal["redacted", "omitted"]
Accepts one of the following:
"redacted"
"omitted"
hidden_reasoning: Optional[str]
is_err: Optional[bool]
message_type: Optional[Literal["hidden_reasoning_message"]]

The type of the message.

Accepts one of the following:
"hidden_reasoning_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class ToolCallMessage:

A message representing a request to call a tool (generated by the LLM to trigger tool execution).

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message tool_call (Union[ToolCall, ToolCallDelta]): The tool call

id: str
date: datetime
Deprecatedtool_call: ToolCall
Accepts one of the following:
class ToolCall:
arguments: str
name: str
tool_call_id: str
class ToolCallDelta:
arguments: Optional[str]
name: Optional[str]
tool_call_id: Optional[str]
is_err: Optional[bool]
message_type: Optional[Literal["tool_call_message"]]

The type of the message.

Accepts one of the following:
"tool_call_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
tool_calls: Optional[ToolCalls]
Accepts one of the following:
ToolCallsUnionMember0 = List[ToolCall]
arguments: str
name: str
tool_call_id: str
class ToolCallDelta:
arguments: Optional[str]
name: Optional[str]
tool_call_id: Optional[str]
class ToolReturnMessage:

A message representing the return value of a tool call (generated by Letta executing the requested tool).

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message tool_return (str): The return value of the tool (deprecated, use tool_returns) status (Literal["success", "error"]): The status of the tool call (deprecated, use tool_returns) tool_call_id (str): A unique identifier for the tool call that generated this message (deprecated, use tool_returns) stdout (Optional[List(str)]): Captured stdout (e.g. prints, logs) from the tool invocation (deprecated, use tool_returns) stderr (Optional[List(str)]): Captured stderr from the tool invocation (deprecated, use tool_returns) tool_returns (Optional[List[ToolReturn]]): List of tool returns for multi-tool support

id: str
date: datetime
Deprecatedstatus: Literal["success", "error"]
Accepts one of the following:
"success"
"error"
Deprecatedtool_call_id: str
Deprecatedtool_return: str
is_err: Optional[bool]
message_type: Optional[Literal["tool_return_message"]]

The type of the message.

Accepts one of the following:
"tool_return_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
Deprecatedstderr: Optional[List[str]]
Deprecatedstdout: Optional[List[str]]
step_id: Optional[str]
tool_returns: Optional[List[ToolReturn]]
status: Literal["success", "error"]
Accepts one of the following:
"success"
"error"
tool_call_id: str
tool_return: str
stderr: Optional[List[str]]
stdout: Optional[List[str]]
type: Optional[Literal["tool"]]

The message type to be created.

Accepts one of the following:
"tool"
class AssistantMessage:

A message sent by the LLM in response to user input. Used in the LLM context.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message content (Union[str, List[LettaAssistantMessageContentUnion]]): The message content sent by the agent (can be a string or an array of content parts)

id: str
content: Union[List[LettaAssistantMessageContentUnion], str]

The message content sent by the agent (can be a string or an array of content parts)

Accepts one of the following:
ContentUnionMember0 = List[LettaAssistantMessageContentUnion]
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
ContentUnionMember1 = str
date: datetime
is_err: Optional[bool]
message_type: Optional[Literal["assistant_message"]]

The type of the message.

Accepts one of the following:
"assistant_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class ApprovalRequestMessage:

A message representing a request for approval to call a tool (generated by the LLM to trigger tool execution).

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message tool_call (ToolCall): The tool call

id: str
date: datetime
Deprecatedtool_call: ToolCall

The tool call that has been requested by the llm to run

Accepts one of the following:
class ToolCall:
arguments: str
name: str
tool_call_id: str
class ToolCallDelta:
arguments: Optional[str]
name: Optional[str]
tool_call_id: Optional[str]
is_err: Optional[bool]
message_type: Optional[Literal["approval_request_message"]]

The type of the message.

Accepts one of the following:
"approval_request_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
tool_calls: Optional[ToolCalls]

The tool calls that have been requested by the llm to run, which are pending approval

Accepts one of the following:
ToolCallsUnionMember0 = List[ToolCall]
arguments: str
name: str
tool_call_id: str
class ToolCallDelta:
arguments: Optional[str]
name: Optional[str]
tool_call_id: Optional[str]
class ApprovalResponseMessage:

A message representing a response form the user indicating whether a tool has been approved to run.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message approve: (bool) Whether the tool has been approved approval_request_id: The ID of the approval request reason: (Optional[str]) An optional explanation for the provided approval status

id: str
date: datetime
Deprecatedapproval_request_id: Optional[str]

The message ID of the approval request

approvals: Optional[List[Approval]]

The list of approval responses

Accepts one of the following:
class ApprovalApprovalReturn:
approve: bool

Whether the tool has been approved

tool_call_id: str

The ID of the tool call that corresponds to this approval

reason: Optional[str]

An optional explanation for the provided approval status

type: Optional[Literal["approval"]]

The message type to be created.

Accepts one of the following:
"approval"
class ToolReturn:
status: Literal["success", "error"]
Accepts one of the following:
"success"
"error"
tool_call_id: str
tool_return: str
stderr: Optional[List[str]]
stdout: Optional[List[str]]
type: Optional[Literal["tool"]]

The message type to be created.

Accepts one of the following:
"tool"
Deprecatedapprove: Optional[bool]

Whether the tool has been approved

is_err: Optional[bool]
message_type: Optional[Literal["approval_response_message"]]

The type of the message.

Accepts one of the following:
"approval_response_message"
name: Optional[str]
otid: Optional[str]
Deprecatedreason: Optional[str]

An optional explanation for the provided approval status

run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class SummaryMessage:

A message representing a summary of the conversation. Sent to the LLM as a user or system message depending on the provider.

id: str
date: datetime
summary: str
is_err: Optional[bool]
message_type: Optional[Literal["summary"]]
Accepts one of the following:
"summary"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class EventMessage:

A message for notifying the developer that an event that has occured (e.g. a compaction). Events are NOT part of the context window.

id: str
date: datetime
event_data: Dict[str, object]
event_type: Literal["compaction"]
Accepts one of the following:
"compaction"
is_err: Optional[bool]
message_type: Optional[Literal["event"]]
Accepts one of the following:
"event"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class LettaRequest:
Deprecatedassistant_message_tool_kwarg: Optional[str]

The name of the message argument in the designated message tool. Still supported for legacy agent types, but deprecated for letta_v1_agent onward.

Deprecatedassistant_message_tool_name: Optional[str]

The name of the designated message tool. Still supported for legacy agent types, but deprecated for letta_v1_agent onward.

Deprecatedenable_thinking: Optional[str]

If set to True, enables reasoning before responses or tool calls from the agent.

include_return_message_types: Optional[List[MessageType]]

Only return specified message types in the response. If None (default) returns all messages.

Accepts one of the following:
"system_message"
"user_message"
"assistant_message"
"reasoning_message"
"hidden_reasoning_message"
"tool_call_message"
"tool_return_message"
"approval_request_message"
"approval_response_message"
input: Optional[Union[str, List[InputUnionMember1], null]]

Syntactic sugar for a single user message. Equivalent to messages=[{'role': 'user', 'content': input}].

Accepts one of the following:
InputUnionMember0 = str
InputUnionMember1 = List[InputUnionMember1]
Accepts one of the following:
class TextContent:
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
class ImageContent:
source: Source

The source of the image.

Accepts one of the following:
class SourceURLImage:
url: str

The URL of the image.

type: Optional[Literal["url"]]

The source type for the image.

Accepts one of the following:
"url"
class SourceBase64Image:
data: str

The base64 encoded image data.

media_type: str

The media type for the image.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

type: Optional[Literal["base64"]]

The source type for the image.

Accepts one of the following:
"base64"
class SourceLettaImage:
file_id: str

The unique identifier of the image file persisted in storage.

data: Optional[str]

The base64 encoded image data.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

media_type: Optional[str]

The media type for the image.

type: Optional[Literal["letta"]]

The source type for the image.

Accepts one of the following:
"letta"
type: Optional[Literal["image"]]

The type of the message.

Accepts one of the following:
"image"
class ToolCallContent:
id: str

A unique identifier for this specific tool call instance.

input: Dict[str, object]

The parameters being passed to the tool, structured as a dictionary of parameter names to values.

name: str

The name of the tool being called.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this tool call.

type: Optional[Literal["tool_call"]]

Indicates this content represents a tool call event.

Accepts one of the following:
"tool_call"
class ToolReturnContent:
content: str

The content returned by the tool execution.

is_error: bool

Indicates whether the tool execution resulted in an error.

tool_call_id: str

References the ID of the ToolCallContent that initiated this tool call.

type: Optional[Literal["tool_return"]]

Indicates this content represents a tool return event.

Accepts one of the following:
"tool_return"
class ReasoningContent:

Sent via the Anthropic Messages API

is_native: bool

Whether the reasoning content was generated by a reasoner model that processed this step.

reasoning: str

The intermediate reasoning or thought process content.

signature: Optional[str]

A unique identifier for this reasoning step.

type: Optional[Literal["reasoning"]]

Indicates this is a reasoning/intermediate step.

Accepts one of the following:
"reasoning"
class RedactedReasoningContent:

Sent via the Anthropic Messages API

data: str

The redacted or filtered intermediate reasoning content.

type: Optional[Literal["redacted_reasoning"]]

Indicates this is a redacted thinking step.

Accepts one of the following:
"redacted_reasoning"
class OmittedReasoningContent:

A placeholder for reasoning content we know is present, but isn't returned by the provider (e.g. OpenAI GPT-5 on ChatCompletions)

signature: Optional[str]

A unique identifier for this reasoning step.

type: Optional[Literal["omitted_reasoning"]]

Indicates this is an omitted reasoning step.

Accepts one of the following:
"omitted_reasoning"
class InputUnionMember1SummarizedReasoningContent:

The style of reasoning content returned by the OpenAI Responses API

id: str

The unique identifier for this reasoning step.

summary: List[InputUnionMember1SummarizedReasoningContentSummary]

Summaries of the reasoning content.

index: int

The index of the summary part.

text: str

The text of the summary part.

encrypted_content: Optional[str]

The encrypted reasoning content.

type: Optional[Literal["summarized_reasoning"]]

Indicates this is a summarized reasoning step.

Accepts one of the following:
"summarized_reasoning"
max_steps: Optional[int]

Maximum number of steps the agent should take to process the request.

messages: Optional[List[Message]]

The messages to be sent to the agent.

Accepts one of the following:
class MessageCreate:

Request to create a message

content: Union[List[LettaMessageContentUnion], str]

The content of the message.

Accepts one of the following:
ContentUnionMember0 = List[LettaMessageContentUnion]
Accepts one of the following:
class TextContent:
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
class ImageContent:
source: Source

The source of the image.

Accepts one of the following:
class SourceURLImage:
url: str

The URL of the image.

type: Optional[Literal["url"]]

The source type for the image.

Accepts one of the following:
"url"
class SourceBase64Image:
data: str

The base64 encoded image data.

media_type: str

The media type for the image.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

type: Optional[Literal["base64"]]

The source type for the image.

Accepts one of the following:
"base64"
class SourceLettaImage:
file_id: str

The unique identifier of the image file persisted in storage.

data: Optional[str]

The base64 encoded image data.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

media_type: Optional[str]

The media type for the image.

type: Optional[Literal["letta"]]

The source type for the image.

Accepts one of the following:
"letta"
type: Optional[Literal["image"]]

The type of the message.

Accepts one of the following:
"image"
class ToolCallContent:
id: str

A unique identifier for this specific tool call instance.

input: Dict[str, object]

The parameters being passed to the tool, structured as a dictionary of parameter names to values.

name: str

The name of the tool being called.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this tool call.

type: Optional[Literal["tool_call"]]

Indicates this content represents a tool call event.

Accepts one of the following:
"tool_call"
class ToolReturnContent:
content: str

The content returned by the tool execution.

is_error: bool

Indicates whether the tool execution resulted in an error.

tool_call_id: str

References the ID of the ToolCallContent that initiated this tool call.

type: Optional[Literal["tool_return"]]

Indicates this content represents a tool return event.

Accepts one of the following:
"tool_return"
class ReasoningContent:

Sent via the Anthropic Messages API

is_native: bool

Whether the reasoning content was generated by a reasoner model that processed this step.

reasoning: str

The intermediate reasoning or thought process content.

signature: Optional[str]

A unique identifier for this reasoning step.

type: Optional[Literal["reasoning"]]

Indicates this is a reasoning/intermediate step.

Accepts one of the following:
"reasoning"
class RedactedReasoningContent:

Sent via the Anthropic Messages API

data: str

The redacted or filtered intermediate reasoning content.

type: Optional[Literal["redacted_reasoning"]]

Indicates this is a redacted thinking step.

Accepts one of the following:
"redacted_reasoning"
class OmittedReasoningContent:

A placeholder for reasoning content we know is present, but isn't returned by the provider (e.g. OpenAI GPT-5 on ChatCompletions)

signature: Optional[str]

A unique identifier for this reasoning step.

type: Optional[Literal["omitted_reasoning"]]

Indicates this is an omitted reasoning step.

Accepts one of the following:
"omitted_reasoning"
ContentUnionMember1 = str
role: Literal["user", "system", "assistant"]

The role of the participant.

Accepts one of the following:
"user"
"system"
"assistant"
batch_item_id: Optional[str]

The id of the LLMBatchItem that this message is associated with

group_id: Optional[str]

The multi-agent group that the message was sent in

name: Optional[str]

The name of the participant.

otid: Optional[str]

The offline threading id associated with this message

sender_id: Optional[str]

The id of the sender of the message, can be an identity id or agent id

type: Optional[Literal["message"]]

The message type to be created.

Accepts one of the following:
"message"
class ApprovalCreate:

Input to approve or deny a tool call request

Deprecatedapproval_request_id: Optional[str]

The message ID of the approval request

approvals: Optional[List[Approval]]

The list of approval responses

Accepts one of the following:
class ApprovalApprovalReturn:
approve: bool

Whether the tool has been approved

tool_call_id: str

The ID of the tool call that corresponds to this approval

reason: Optional[str]

An optional explanation for the provided approval status

type: Optional[Literal["approval"]]

The message type to be created.

Accepts one of the following:
"approval"
class ToolReturn:
status: Literal["success", "error"]
Accepts one of the following:
"success"
"error"
tool_call_id: str
tool_return: str
stderr: Optional[List[str]]
stdout: Optional[List[str]]
type: Optional[Literal["tool"]]

The message type to be created.

Accepts one of the following:
"tool"
Deprecatedapprove: Optional[bool]

Whether the tool has been approved

group_id: Optional[str]

The multi-agent group that the message was sent in

Deprecatedreason: Optional[str]

An optional explanation for the provided approval status

type: Optional[Literal["approval"]]

The message type to be created.

Accepts one of the following:
"approval"
Deprecateduse_assistant_message: Optional[bool]

Whether the server should parse specific tool call arguments (default send_message) as AssistantMessage objects. Still supported for legacy agent types, but deprecated for letta_v1_agent onward.

class LettaResponse:

Response object from an agent interaction, consisting of the new messages generated by the agent and usage statistics. The type of the returned messages can be either Message or LettaMessage, depending on what was specified in the request.

Attributes: messages (List[Union[Message, LettaMessage]]): The messages returned by the agent. usage (LettaUsageStatistics): The usage statistics

messages: List[LettaMessageUnion]

The messages returned by the agent.

Accepts one of the following:
class SystemMessage:

A message generated by the system. Never streamed back on a response, only used for cursor pagination.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message content (str): The message content sent by the system

id: str
content: str

The message content sent by the system

date: datetime
is_err: Optional[bool]
message_type: Optional[Literal["system_message"]]

The type of the message.

Accepts one of the following:
"system_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class UserMessage:

A message sent by the user. Never streamed back on a response, only used for cursor pagination.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message content (Union[str, List[LettaUserMessageContentUnion]]): The message content sent by the user (can be a string or an array of multi-modal content parts)

id: str
content: Union[List[LettaUserMessageContentUnion], str]

The message content sent by the user (can be a string or an array of multi-modal content parts)

Accepts one of the following:
ContentUnionMember0 = List[LettaUserMessageContentUnion]
Accepts one of the following:
class TextContent:
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
class ImageContent:
source: Source

The source of the image.

Accepts one of the following:
class SourceURLImage:
url: str

The URL of the image.

type: Optional[Literal["url"]]

The source type for the image.

Accepts one of the following:
"url"
class SourceBase64Image:
data: str

The base64 encoded image data.

media_type: str

The media type for the image.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

type: Optional[Literal["base64"]]

The source type for the image.

Accepts one of the following:
"base64"
class SourceLettaImage:
file_id: str

The unique identifier of the image file persisted in storage.

data: Optional[str]

The base64 encoded image data.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

media_type: Optional[str]

The media type for the image.

type: Optional[Literal["letta"]]

The source type for the image.

Accepts one of the following:
"letta"
type: Optional[Literal["image"]]

The type of the message.

Accepts one of the following:
"image"
ContentUnionMember1 = str
date: datetime
is_err: Optional[bool]
message_type: Optional[Literal["user_message"]]

The type of the message.

Accepts one of the following:
"user_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class ReasoningMessage:

Representation of an agent's internal reasoning.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message source (Literal["reasoner_model", "non_reasoner_model"]): Whether the reasoning content was generated natively by a reasoner model or derived via prompting reasoning (str): The internal reasoning of the agent signature (Optional[str]): The model-generated signature of the reasoning step

id: str
date: datetime
reasoning: str
is_err: Optional[bool]
message_type: Optional[Literal["reasoning_message"]]

The type of the message.

Accepts one of the following:
"reasoning_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
signature: Optional[str]
source: Optional[Literal["reasoner_model", "non_reasoner_model"]]
Accepts one of the following:
"reasoner_model"
"non_reasoner_model"
step_id: Optional[str]
class HiddenReasoningMessage:

Representation of an agent's internal reasoning where reasoning content has been hidden from the response.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message state (Literal["redacted", "omitted"]): Whether the reasoning content was redacted by the provider or simply omitted by the API hidden_reasoning (Optional[str]): The internal reasoning of the agent

id: str
date: datetime
state: Literal["redacted", "omitted"]
Accepts one of the following:
"redacted"
"omitted"
hidden_reasoning: Optional[str]
is_err: Optional[bool]
message_type: Optional[Literal["hidden_reasoning_message"]]

The type of the message.

Accepts one of the following:
"hidden_reasoning_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class ToolCallMessage:

A message representing a request to call a tool (generated by the LLM to trigger tool execution).

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message tool_call (Union[ToolCall, ToolCallDelta]): The tool call

id: str
date: datetime
Deprecatedtool_call: ToolCall
Accepts one of the following:
class ToolCall:
arguments: str
name: str
tool_call_id: str
class ToolCallDelta:
arguments: Optional[str]
name: Optional[str]
tool_call_id: Optional[str]
is_err: Optional[bool]
message_type: Optional[Literal["tool_call_message"]]

The type of the message.

Accepts one of the following:
"tool_call_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
tool_calls: Optional[ToolCalls]
Accepts one of the following:
ToolCallsUnionMember0 = List[ToolCall]
arguments: str
name: str
tool_call_id: str
class ToolCallDelta:
arguments: Optional[str]
name: Optional[str]
tool_call_id: Optional[str]
class ToolReturnMessage:

A message representing the return value of a tool call (generated by Letta executing the requested tool).

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message tool_return (str): The return value of the tool (deprecated, use tool_returns) status (Literal["success", "error"]): The status of the tool call (deprecated, use tool_returns) tool_call_id (str): A unique identifier for the tool call that generated this message (deprecated, use tool_returns) stdout (Optional[List(str)]): Captured stdout (e.g. prints, logs) from the tool invocation (deprecated, use tool_returns) stderr (Optional[List(str)]): Captured stderr from the tool invocation (deprecated, use tool_returns) tool_returns (Optional[List[ToolReturn]]): List of tool returns for multi-tool support

id: str
date: datetime
Deprecatedstatus: Literal["success", "error"]
Accepts one of the following:
"success"
"error"
Deprecatedtool_call_id: str
Deprecatedtool_return: str
is_err: Optional[bool]
message_type: Optional[Literal["tool_return_message"]]

The type of the message.

Accepts one of the following:
"tool_return_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
Deprecatedstderr: Optional[List[str]]
Deprecatedstdout: Optional[List[str]]
step_id: Optional[str]
tool_returns: Optional[List[ToolReturn]]
status: Literal["success", "error"]
Accepts one of the following:
"success"
"error"
tool_call_id: str
tool_return: str
stderr: Optional[List[str]]
stdout: Optional[List[str]]
type: Optional[Literal["tool"]]

The message type to be created.

Accepts one of the following:
"tool"
class AssistantMessage:

A message sent by the LLM in response to user input. Used in the LLM context.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message content (Union[str, List[LettaAssistantMessageContentUnion]]): The message content sent by the agent (can be a string or an array of content parts)

id: str
content: Union[List[LettaAssistantMessageContentUnion], str]

The message content sent by the agent (can be a string or an array of content parts)

Accepts one of the following:
ContentUnionMember0 = List[LettaAssistantMessageContentUnion]
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
ContentUnionMember1 = str
date: datetime
is_err: Optional[bool]
message_type: Optional[Literal["assistant_message"]]

The type of the message.

Accepts one of the following:
"assistant_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class ApprovalRequestMessage:

A message representing a request for approval to call a tool (generated by the LLM to trigger tool execution).

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message tool_call (ToolCall): The tool call

id: str
date: datetime
Deprecatedtool_call: ToolCall

The tool call that has been requested by the llm to run

Accepts one of the following:
class ToolCall:
arguments: str
name: str
tool_call_id: str
class ToolCallDelta:
arguments: Optional[str]
name: Optional[str]
tool_call_id: Optional[str]
is_err: Optional[bool]
message_type: Optional[Literal["approval_request_message"]]

The type of the message.

Accepts one of the following:
"approval_request_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
tool_calls: Optional[ToolCalls]

The tool calls that have been requested by the llm to run, which are pending approval

Accepts one of the following:
ToolCallsUnionMember0 = List[ToolCall]
arguments: str
name: str
tool_call_id: str
class ToolCallDelta:
arguments: Optional[str]
name: Optional[str]
tool_call_id: Optional[str]
class ApprovalResponseMessage:

A message representing a response form the user indicating whether a tool has been approved to run.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message approve: (bool) Whether the tool has been approved approval_request_id: The ID of the approval request reason: (Optional[str]) An optional explanation for the provided approval status

id: str
date: datetime
Deprecatedapproval_request_id: Optional[str]

The message ID of the approval request

approvals: Optional[List[Approval]]

The list of approval responses

Accepts one of the following:
class ApprovalApprovalReturn:
approve: bool

Whether the tool has been approved

tool_call_id: str

The ID of the tool call that corresponds to this approval

reason: Optional[str]

An optional explanation for the provided approval status

type: Optional[Literal["approval"]]

The message type to be created.

Accepts one of the following:
"approval"
class ToolReturn:
status: Literal["success", "error"]
Accepts one of the following:
"success"
"error"
tool_call_id: str
tool_return: str
stderr: Optional[List[str]]
stdout: Optional[List[str]]
type: Optional[Literal["tool"]]

The message type to be created.

Accepts one of the following:
"tool"
Deprecatedapprove: Optional[bool]

Whether the tool has been approved

is_err: Optional[bool]
message_type: Optional[Literal["approval_response_message"]]

The type of the message.

Accepts one of the following:
"approval_response_message"
name: Optional[str]
otid: Optional[str]
Deprecatedreason: Optional[str]

An optional explanation for the provided approval status

run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class SummaryMessage:

A message representing a summary of the conversation. Sent to the LLM as a user or system message depending on the provider.

id: str
date: datetime
summary: str
is_err: Optional[bool]
message_type: Optional[Literal["summary"]]
Accepts one of the following:
"summary"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class EventMessage:

A message for notifying the developer that an event that has occured (e.g. a compaction). Events are NOT part of the context window.

id: str
date: datetime
event_data: Dict[str, object]
event_type: Literal["compaction"]
Accepts one of the following:
"compaction"
is_err: Optional[bool]
message_type: Optional[Literal["event"]]
Accepts one of the following:
"event"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
stop_reason: StopReason

The stop reason from Letta indicating why agent loop stopped execution.

stop_reason: StopReasonType

The reason why execution stopped.

Accepts one of the following:
"end_turn"
"error"
"llm_api_error"
"invalid_llm_response"
"invalid_tool_call"
"max_steps"
"no_tool_call"
"tool_rule"
"cancelled"
"requires_approval"
message_type: Optional[Literal["stop_reason"]]

The type of the message.

Accepts one of the following:
"stop_reason"
usage: Usage

The usage statistics of the agent.

completion_tokens: Optional[int]

The number of tokens generated by the agent.

message_type: Optional[Literal["usage_statistics"]]
Accepts one of the following:
"usage_statistics"
prompt_tokens: Optional[int]

The number of tokens in the prompt.

run_ids: Optional[List[str]]

The background task run IDs associated with the agent interaction

step_count: Optional[int]

The number of steps taken by the agent.

total_tokens: Optional[int]

The total number of tokens processed by the agent.

class LettaStreamingRequest:
Deprecatedassistant_message_tool_kwarg: Optional[str]

The name of the message argument in the designated message tool. Still supported for legacy agent types, but deprecated for letta_v1_agent onward.

Deprecatedassistant_message_tool_name: Optional[str]

The name of the designated message tool. Still supported for legacy agent types, but deprecated for letta_v1_agent onward.

background: Optional[bool]

Whether to process the request in the background (only used when streaming=true).

Deprecatedenable_thinking: Optional[str]

If set to True, enables reasoning before responses or tool calls from the agent.

include_pings: Optional[bool]

Whether to include periodic keepalive ping messages in the stream to prevent connection timeouts (only used when streaming=true).

include_return_message_types: Optional[List[MessageType]]

Only return specified message types in the response. If None (default) returns all messages.

Accepts one of the following:
"system_message"
"user_message"
"assistant_message"
"reasoning_message"
"hidden_reasoning_message"
"tool_call_message"
"tool_return_message"
"approval_request_message"
"approval_response_message"
input: Optional[Union[str, List[InputUnionMember1], null]]

Syntactic sugar for a single user message. Equivalent to messages=[{'role': 'user', 'content': input}].

Accepts one of the following:
InputUnionMember0 = str
InputUnionMember1 = List[InputUnionMember1]
Accepts one of the following:
class TextContent:
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
class ImageContent:
source: Source

The source of the image.

Accepts one of the following:
class SourceURLImage:
url: str

The URL of the image.

type: Optional[Literal["url"]]

The source type for the image.

Accepts one of the following:
"url"
class SourceBase64Image:
data: str

The base64 encoded image data.

media_type: str

The media type for the image.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

type: Optional[Literal["base64"]]

The source type for the image.

Accepts one of the following:
"base64"
class SourceLettaImage:
file_id: str

The unique identifier of the image file persisted in storage.

data: Optional[str]

The base64 encoded image data.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

media_type: Optional[str]

The media type for the image.

type: Optional[Literal["letta"]]

The source type for the image.

Accepts one of the following:
"letta"
type: Optional[Literal["image"]]

The type of the message.

Accepts one of the following:
"image"
class ToolCallContent:
id: str

A unique identifier for this specific tool call instance.

input: Dict[str, object]

The parameters being passed to the tool, structured as a dictionary of parameter names to values.

name: str

The name of the tool being called.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this tool call.

type: Optional[Literal["tool_call"]]

Indicates this content represents a tool call event.

Accepts one of the following:
"tool_call"
class ToolReturnContent:
content: str

The content returned by the tool execution.

is_error: bool

Indicates whether the tool execution resulted in an error.

tool_call_id: str

References the ID of the ToolCallContent that initiated this tool call.

type: Optional[Literal["tool_return"]]

Indicates this content represents a tool return event.

Accepts one of the following:
"tool_return"
class ReasoningContent:

Sent via the Anthropic Messages API

is_native: bool

Whether the reasoning content was generated by a reasoner model that processed this step.

reasoning: str

The intermediate reasoning or thought process content.

signature: Optional[str]

A unique identifier for this reasoning step.

type: Optional[Literal["reasoning"]]

Indicates this is a reasoning/intermediate step.

Accepts one of the following:
"reasoning"
class RedactedReasoningContent:

Sent via the Anthropic Messages API

data: str

The redacted or filtered intermediate reasoning content.

type: Optional[Literal["redacted_reasoning"]]

Indicates this is a redacted thinking step.

Accepts one of the following:
"redacted_reasoning"
class OmittedReasoningContent:

A placeholder for reasoning content we know is present, but isn't returned by the provider (e.g. OpenAI GPT-5 on ChatCompletions)

signature: Optional[str]

A unique identifier for this reasoning step.

type: Optional[Literal["omitted_reasoning"]]

Indicates this is an omitted reasoning step.

Accepts one of the following:
"omitted_reasoning"
class InputUnionMember1SummarizedReasoningContent:

The style of reasoning content returned by the OpenAI Responses API

id: str

The unique identifier for this reasoning step.

summary: List[InputUnionMember1SummarizedReasoningContentSummary]

Summaries of the reasoning content.

index: int

The index of the summary part.

text: str

The text of the summary part.

encrypted_content: Optional[str]

The encrypted reasoning content.

type: Optional[Literal["summarized_reasoning"]]

Indicates this is a summarized reasoning step.

Accepts one of the following:
"summarized_reasoning"
max_steps: Optional[int]

Maximum number of steps the agent should take to process the request.

messages: Optional[List[Message]]

The messages to be sent to the agent.

Accepts one of the following:
class MessageCreate:

Request to create a message

content: Union[List[LettaMessageContentUnion], str]

The content of the message.

Accepts one of the following:
ContentUnionMember0 = List[LettaMessageContentUnion]
Accepts one of the following:
class TextContent:
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
class ImageContent:
source: Source

The source of the image.

Accepts one of the following:
class SourceURLImage:
url: str

The URL of the image.

type: Optional[Literal["url"]]

The source type for the image.

Accepts one of the following:
"url"
class SourceBase64Image:
data: str

The base64 encoded image data.

media_type: str

The media type for the image.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

type: Optional[Literal["base64"]]

The source type for the image.

Accepts one of the following:
"base64"
class SourceLettaImage:
file_id: str

The unique identifier of the image file persisted in storage.

data: Optional[str]

The base64 encoded image data.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

media_type: Optional[str]

The media type for the image.

type: Optional[Literal["letta"]]

The source type for the image.

Accepts one of the following:
"letta"
type: Optional[Literal["image"]]

The type of the message.

Accepts one of the following:
"image"
class ToolCallContent:
id: str

A unique identifier for this specific tool call instance.

input: Dict[str, object]

The parameters being passed to the tool, structured as a dictionary of parameter names to values.

name: str

The name of the tool being called.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this tool call.

type: Optional[Literal["tool_call"]]

Indicates this content represents a tool call event.

Accepts one of the following:
"tool_call"
class ToolReturnContent:
content: str

The content returned by the tool execution.

is_error: bool

Indicates whether the tool execution resulted in an error.

tool_call_id: str

References the ID of the ToolCallContent that initiated this tool call.

type: Optional[Literal["tool_return"]]

Indicates this content represents a tool return event.

Accepts one of the following:
"tool_return"
class ReasoningContent:

Sent via the Anthropic Messages API

is_native: bool

Whether the reasoning content was generated by a reasoner model that processed this step.

reasoning: str

The intermediate reasoning or thought process content.

signature: Optional[str]

A unique identifier for this reasoning step.

type: Optional[Literal["reasoning"]]

Indicates this is a reasoning/intermediate step.

Accepts one of the following:
"reasoning"
class RedactedReasoningContent:

Sent via the Anthropic Messages API

data: str

The redacted or filtered intermediate reasoning content.

type: Optional[Literal["redacted_reasoning"]]

Indicates this is a redacted thinking step.

Accepts one of the following:
"redacted_reasoning"
class OmittedReasoningContent:

A placeholder for reasoning content we know is present, but isn't returned by the provider (e.g. OpenAI GPT-5 on ChatCompletions)

signature: Optional[str]

A unique identifier for this reasoning step.

type: Optional[Literal["omitted_reasoning"]]

Indicates this is an omitted reasoning step.

Accepts one of the following:
"omitted_reasoning"
ContentUnionMember1 = str
role: Literal["user", "system", "assistant"]

The role of the participant.

Accepts one of the following:
"user"
"system"
"assistant"
batch_item_id: Optional[str]

The id of the LLMBatchItem that this message is associated with

group_id: Optional[str]

The multi-agent group that the message was sent in

name: Optional[str]

The name of the participant.

otid: Optional[str]

The offline threading id associated with this message

sender_id: Optional[str]

The id of the sender of the message, can be an identity id or agent id

type: Optional[Literal["message"]]

The message type to be created.

Accepts one of the following:
"message"
class ApprovalCreate:

Input to approve or deny a tool call request

Deprecatedapproval_request_id: Optional[str]

The message ID of the approval request

approvals: Optional[List[Approval]]

The list of approval responses

Accepts one of the following:
class ApprovalApprovalReturn:
approve: bool

Whether the tool has been approved

tool_call_id: str

The ID of the tool call that corresponds to this approval

reason: Optional[str]

An optional explanation for the provided approval status

type: Optional[Literal["approval"]]

The message type to be created.

Accepts one of the following:
"approval"
class ToolReturn:
status: Literal["success", "error"]
Accepts one of the following:
"success"
"error"
tool_call_id: str
tool_return: str
stderr: Optional[List[str]]
stdout: Optional[List[str]]
type: Optional[Literal["tool"]]

The message type to be created.

Accepts one of the following:
"tool"
Deprecatedapprove: Optional[bool]

Whether the tool has been approved

group_id: Optional[str]

The multi-agent group that the message was sent in

Deprecatedreason: Optional[str]

An optional explanation for the provided approval status

type: Optional[Literal["approval"]]

The message type to be created.

Accepts one of the following:
"approval"
stream_tokens: Optional[bool]

Flag to determine if individual tokens should be streamed, rather than streaming per step (only used when streaming=true).

streaming: Optional[bool]

If True, returns a streaming response (Server-Sent Events). If False (default), returns a complete response.

Deprecateduse_assistant_message: Optional[bool]

Whether the server should parse specific tool call arguments (default send_message) as AssistantMessage objects. Still supported for legacy agent types, but deprecated for letta_v1_agent onward.

LettaStreamingResponse = LettaStreamingResponse

Streaming response type for Server-Sent Events (SSE) endpoints. Each event in the stream will be one of these types.

Accepts one of the following:
class SystemMessage:

A message generated by the system. Never streamed back on a response, only used for cursor pagination.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message content (str): The message content sent by the system

id: str
content: str

The message content sent by the system

date: datetime
is_err: Optional[bool]
message_type: Optional[Literal["system_message"]]

The type of the message.

Accepts one of the following:
"system_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class UserMessage:

A message sent by the user. Never streamed back on a response, only used for cursor pagination.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message content (Union[str, List[LettaUserMessageContentUnion]]): The message content sent by the user (can be a string or an array of multi-modal content parts)

id: str
content: Union[List[LettaUserMessageContentUnion], str]

The message content sent by the user (can be a string or an array of multi-modal content parts)

Accepts one of the following:
ContentUnionMember0 = List[LettaUserMessageContentUnion]
Accepts one of the following:
class TextContent:
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
class ImageContent:
source: Source

The source of the image.

Accepts one of the following:
class SourceURLImage:
url: str

The URL of the image.

type: Optional[Literal["url"]]

The source type for the image.

Accepts one of the following:
"url"
class SourceBase64Image:
data: str

The base64 encoded image data.

media_type: str

The media type for the image.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

type: Optional[Literal["base64"]]

The source type for the image.

Accepts one of the following:
"base64"
class SourceLettaImage:
file_id: str

The unique identifier of the image file persisted in storage.

data: Optional[str]

The base64 encoded image data.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

media_type: Optional[str]

The media type for the image.

type: Optional[Literal["letta"]]

The source type for the image.

Accepts one of the following:
"letta"
type: Optional[Literal["image"]]

The type of the message.

Accepts one of the following:
"image"
ContentUnionMember1 = str
date: datetime
is_err: Optional[bool]
message_type: Optional[Literal["user_message"]]

The type of the message.

Accepts one of the following:
"user_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class ReasoningMessage:

Representation of an agent's internal reasoning.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message source (Literal["reasoner_model", "non_reasoner_model"]): Whether the reasoning content was generated natively by a reasoner model or derived via prompting reasoning (str): The internal reasoning of the agent signature (Optional[str]): The model-generated signature of the reasoning step

id: str
date: datetime
reasoning: str
is_err: Optional[bool]
message_type: Optional[Literal["reasoning_message"]]

The type of the message.

Accepts one of the following:
"reasoning_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
signature: Optional[str]
source: Optional[Literal["reasoner_model", "non_reasoner_model"]]
Accepts one of the following:
"reasoner_model"
"non_reasoner_model"
step_id: Optional[str]
class HiddenReasoningMessage:

Representation of an agent's internal reasoning where reasoning content has been hidden from the response.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message state (Literal["redacted", "omitted"]): Whether the reasoning content was redacted by the provider or simply omitted by the API hidden_reasoning (Optional[str]): The internal reasoning of the agent

id: str
date: datetime
state: Literal["redacted", "omitted"]
Accepts one of the following:
"redacted"
"omitted"
hidden_reasoning: Optional[str]
is_err: Optional[bool]
message_type: Optional[Literal["hidden_reasoning_message"]]

The type of the message.

Accepts one of the following:
"hidden_reasoning_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class ToolCallMessage:

A message representing a request to call a tool (generated by the LLM to trigger tool execution).

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message tool_call (Union[ToolCall, ToolCallDelta]): The tool call

id: str
date: datetime
Deprecatedtool_call: ToolCall
Accepts one of the following:
class ToolCall:
arguments: str
name: str
tool_call_id: str
class ToolCallDelta:
arguments: Optional[str]
name: Optional[str]
tool_call_id: Optional[str]
is_err: Optional[bool]
message_type: Optional[Literal["tool_call_message"]]

The type of the message.

Accepts one of the following:
"tool_call_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
tool_calls: Optional[ToolCalls]
Accepts one of the following:
ToolCallsUnionMember0 = List[ToolCall]
arguments: str
name: str
tool_call_id: str
class ToolCallDelta:
arguments: Optional[str]
name: Optional[str]
tool_call_id: Optional[str]
class ToolReturnMessage:

A message representing the return value of a tool call (generated by Letta executing the requested tool).

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message tool_return (str): The return value of the tool (deprecated, use tool_returns) status (Literal["success", "error"]): The status of the tool call (deprecated, use tool_returns) tool_call_id (str): A unique identifier for the tool call that generated this message (deprecated, use tool_returns) stdout (Optional[List(str)]): Captured stdout (e.g. prints, logs) from the tool invocation (deprecated, use tool_returns) stderr (Optional[List(str)]): Captured stderr from the tool invocation (deprecated, use tool_returns) tool_returns (Optional[List[ToolReturn]]): List of tool returns for multi-tool support

id: str
date: datetime
Deprecatedstatus: Literal["success", "error"]
Accepts one of the following:
"success"
"error"
Deprecatedtool_call_id: str
Deprecatedtool_return: str
is_err: Optional[bool]
message_type: Optional[Literal["tool_return_message"]]

The type of the message.

Accepts one of the following:
"tool_return_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
Deprecatedstderr: Optional[List[str]]
Deprecatedstdout: Optional[List[str]]
step_id: Optional[str]
tool_returns: Optional[List[ToolReturn]]
status: Literal["success", "error"]
Accepts one of the following:
"success"
"error"
tool_call_id: str
tool_return: str
stderr: Optional[List[str]]
stdout: Optional[List[str]]
type: Optional[Literal["tool"]]

The message type to be created.

Accepts one of the following:
"tool"
class AssistantMessage:

A message sent by the LLM in response to user input. Used in the LLM context.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message content (Union[str, List[LettaAssistantMessageContentUnion]]): The message content sent by the agent (can be a string or an array of content parts)

id: str
content: Union[List[LettaAssistantMessageContentUnion], str]

The message content sent by the agent (can be a string or an array of content parts)

Accepts one of the following:
ContentUnionMember0 = List[LettaAssistantMessageContentUnion]
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
ContentUnionMember1 = str
date: datetime
is_err: Optional[bool]
message_type: Optional[Literal["assistant_message"]]

The type of the message.

Accepts one of the following:
"assistant_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class ApprovalRequestMessage:

A message representing a request for approval to call a tool (generated by the LLM to trigger tool execution).

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message tool_call (ToolCall): The tool call

id: str
date: datetime
Deprecatedtool_call: ToolCall

The tool call that has been requested by the llm to run

Accepts one of the following:
class ToolCall:
arguments: str
name: str
tool_call_id: str
class ToolCallDelta:
arguments: Optional[str]
name: Optional[str]
tool_call_id: Optional[str]
is_err: Optional[bool]
message_type: Optional[Literal["approval_request_message"]]

The type of the message.

Accepts one of the following:
"approval_request_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
tool_calls: Optional[ToolCalls]

The tool calls that have been requested by the llm to run, which are pending approval

Accepts one of the following:
ToolCallsUnionMember0 = List[ToolCall]
arguments: str
name: str
tool_call_id: str
class ToolCallDelta:
arguments: Optional[str]
name: Optional[str]
tool_call_id: Optional[str]
class ApprovalResponseMessage:

A message representing a response form the user indicating whether a tool has been approved to run.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message approve: (bool) Whether the tool has been approved approval_request_id: The ID of the approval request reason: (Optional[str]) An optional explanation for the provided approval status

id: str
date: datetime
Deprecatedapproval_request_id: Optional[str]

The message ID of the approval request

approvals: Optional[List[Approval]]

The list of approval responses

Accepts one of the following:
class ApprovalApprovalReturn:
approve: bool

Whether the tool has been approved

tool_call_id: str

The ID of the tool call that corresponds to this approval

reason: Optional[str]

An optional explanation for the provided approval status

type: Optional[Literal["approval"]]

The message type to be created.

Accepts one of the following:
"approval"
class ToolReturn:
status: Literal["success", "error"]
Accepts one of the following:
"success"
"error"
tool_call_id: str
tool_return: str
stderr: Optional[List[str]]
stdout: Optional[List[str]]
type: Optional[Literal["tool"]]

The message type to be created.

Accepts one of the following:
"tool"
Deprecatedapprove: Optional[bool]

Whether the tool has been approved

is_err: Optional[bool]
message_type: Optional[Literal["approval_response_message"]]

The type of the message.

Accepts one of the following:
"approval_response_message"
name: Optional[str]
otid: Optional[str]
Deprecatedreason: Optional[str]

An optional explanation for the provided approval status

run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class LettaPing:

Ping messages are a keep-alive to prevent SSE streams from timing out during long running requests.

message_type: Literal["ping"]

The type of the message.

Accepts one of the following:
"ping"
class LettaStopReason:

The stop reason from Letta indicating why agent loop stopped execution.

stop_reason: StopReasonType

The reason why execution stopped.

Accepts one of the following:
"end_turn"
"error"
"llm_api_error"
"invalid_llm_response"
"invalid_tool_call"
"max_steps"
"no_tool_call"
"tool_rule"
"cancelled"
"requires_approval"
message_type: Optional[Literal["stop_reason"]]

The type of the message.

Accepts one of the following:
"stop_reason"
class LettaUsageStatistics:

Usage statistics for the agent interaction.

Attributes: completion_tokens (int): The number of tokens generated by the agent. prompt_tokens (int): The number of tokens in the prompt. total_tokens (int): The total number of tokens processed by the agent. step_count (int): The number of steps taken by the agent.

completion_tokens: Optional[int]

The number of tokens generated by the agent.

message_type: Optional[Literal["usage_statistics"]]
Accepts one of the following:
"usage_statistics"
prompt_tokens: Optional[int]

The number of tokens in the prompt.

run_ids: Optional[List[str]]

The background task run IDs associated with the agent interaction

step_count: Optional[int]

The number of steps taken by the agent.

total_tokens: Optional[int]

The total number of tokens processed by the agent.

LettaUserMessageContentUnion = LettaUserMessageContentUnion
Accepts one of the following:
class TextContent:
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
class ImageContent:
source: Source

The source of the image.

Accepts one of the following:
class SourceURLImage:
url: str

The URL of the image.

type: Optional[Literal["url"]]

The source type for the image.

Accepts one of the following:
"url"
class SourceBase64Image:
data: str

The base64 encoded image data.

media_type: str

The media type for the image.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

type: Optional[Literal["base64"]]

The source type for the image.

Accepts one of the following:
"base64"
class SourceLettaImage:
file_id: str

The unique identifier of the image file persisted in storage.

data: Optional[str]

The base64 encoded image data.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

media_type: Optional[str]

The media type for the image.

type: Optional[Literal["letta"]]

The source type for the image.

Accepts one of the following:
"letta"
type: Optional[Literal["image"]]

The type of the message.

Accepts one of the following:
"image"
class Message:
Letta's internal representation of a message. Includes methods to convert to/from LLM provider formats.

Attributes:
    id (str): The unique identifier of the message.
    role (MessageRole): The role of the participant.
    text (str): The text of the message.
    user_id (str): The unique identifier of the user.
    agent_id (str): The unique identifier of the agent.
    model (str): The model used to make the function call.
    name (str): The name of the participant.
    created_at (datetime): The time the message was created.
    tool_calls (List[OpenAIToolCall,]): The list of tool calls requested.
    tool_call_id (str): The id of the tool call.
    step_id (str): The id of the step that this message was created in.
    otid (str): The offline threading id associated with this message.
    tool_returns (List[ToolReturn]): The list of tool returns requested.
    group_id (str): The multi-agent group that the message was sent in.
    sender_id (str): The id of the sender of the message, can be an identity id or agent id.

t

id: str

The human-friendly ID of the Message

The role of the participant.

Accepts one of the following:
"assistant"
"user"
"tool"
"function"
"system"
"approval"
agent_id: Optional[str]

The unique identifier of the agent.

approval_request_id: Optional[str]

The id of the approval request if this message is associated with a tool call request.

approvals: Optional[List[Approval]]

The list of approvals for this message.

Accepts one of the following:
class ApprovalApprovalReturn:
approve: bool

Whether the tool has been approved

tool_call_id: str

The ID of the tool call that corresponds to this approval

reason: Optional[str]

An optional explanation for the provided approval status

type: Optional[Literal["approval"]]

The message type to be created.

Accepts one of the following:
"approval"
class ApprovalLettaSchemasMessageToolReturn:
status: Literal["success", "error"]

The status of the tool call

Accepts one of the following:
"success"
"error"
func_response: Optional[str]

The function response string

stderr: Optional[List[str]]

Captured stderr from the tool invocation

stdout: Optional[List[str]]

Captured stdout (e.g. prints, logs) from the tool invocation

tool_call_id: Optional[object]

The ID for the tool call

approve: Optional[bool]

Whether tool call is approved.

batch_item_id: Optional[str]

The id of the LLMBatchItem that this message is associated with

content: Optional[List[Content]]

The content of the message.

Accepts one of the following:
class TextContent:
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
class ImageContent:
source: Source

The source of the image.

Accepts one of the following:
class SourceURLImage:
url: str

The URL of the image.

type: Optional[Literal["url"]]

The source type for the image.

Accepts one of the following:
"url"
class SourceBase64Image:
data: str

The base64 encoded image data.

media_type: str

The media type for the image.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

type: Optional[Literal["base64"]]

The source type for the image.

Accepts one of the following:
"base64"
class SourceLettaImage:
file_id: str

The unique identifier of the image file persisted in storage.

data: Optional[str]

The base64 encoded image data.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

media_type: Optional[str]

The media type for the image.

type: Optional[Literal["letta"]]

The source type for the image.

Accepts one of the following:
"letta"
type: Optional[Literal["image"]]

The type of the message.

Accepts one of the following:
"image"
class ToolCallContent:
id: str

A unique identifier for this specific tool call instance.

input: Dict[str, object]

The parameters being passed to the tool, structured as a dictionary of parameter names to values.

name: str

The name of the tool being called.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this tool call.

type: Optional[Literal["tool_call"]]

Indicates this content represents a tool call event.

Accepts one of the following:
"tool_call"
class ToolReturnContent:
content: str

The content returned by the tool execution.

is_error: bool

Indicates whether the tool execution resulted in an error.

tool_call_id: str

References the ID of the ToolCallContent that initiated this tool call.

type: Optional[Literal["tool_return"]]

Indicates this content represents a tool return event.

Accepts one of the following:
"tool_return"
class ReasoningContent:

Sent via the Anthropic Messages API

is_native: bool

Whether the reasoning content was generated by a reasoner model that processed this step.

reasoning: str

The intermediate reasoning or thought process content.

signature: Optional[str]

A unique identifier for this reasoning step.

type: Optional[Literal["reasoning"]]

Indicates this is a reasoning/intermediate step.

Accepts one of the following:
"reasoning"
class RedactedReasoningContent:

Sent via the Anthropic Messages API

data: str

The redacted or filtered intermediate reasoning content.

type: Optional[Literal["redacted_reasoning"]]

Indicates this is a redacted thinking step.

Accepts one of the following:
"redacted_reasoning"
class OmittedReasoningContent:

A placeholder for reasoning content we know is present, but isn't returned by the provider (e.g. OpenAI GPT-5 on ChatCompletions)

signature: Optional[str]

A unique identifier for this reasoning step.

type: Optional[Literal["omitted_reasoning"]]

Indicates this is an omitted reasoning step.

Accepts one of the following:
"omitted_reasoning"
class ContentSummarizedReasoningContent:

The style of reasoning content returned by the OpenAI Responses API

id: str

The unique identifier for this reasoning step.

summary: List[ContentSummarizedReasoningContentSummary]

Summaries of the reasoning content.

index: int

The index of the summary part.

text: str

The text of the summary part.

encrypted_content: Optional[str]

The encrypted reasoning content.

type: Optional[Literal["summarized_reasoning"]]

Indicates this is a summarized reasoning step.

Accepts one of the following:
"summarized_reasoning"
created_at: Optional[datetime]

The timestamp when the object was created.

formatdate-time
created_by_id: Optional[str]

The id of the user that made this object.

denial_reason: Optional[str]

The reason the tool call request was denied.

group_id: Optional[str]

The multi-agent group that the message was sent in

is_err: Optional[bool]

Whether this message is part of an error step. Used only for debugging purposes.

last_updated_by_id: Optional[str]

The id of the user that made this object.

model: Optional[str]

The model used to make the function call.

name: Optional[str]

For role user/assistant: the (optional) name of the participant. For role tool/function: the name of the function called.

otid: Optional[str]

The offline threading id associated with this message

run_id: Optional[str]

The id of the run that this message was created in.

sender_id: Optional[str]

The id of the sender of the message, can be an identity id or agent id

step_id: Optional[str]

The id of the step that this message was created in.

tool_call_id: Optional[str]

The ID of the tool call. Only applicable for role tool.

tool_calls: Optional[List[ToolCall]]

The list of tool calls requested. Only applicable for role assistant.

id: str
function: ToolCallFunction
arguments: str
name: str
type: Literal["function"]
Accepts one of the following:
"function"
tool_returns: Optional[List[ToolReturn]]

Tool execution return information for prior tool calls

status: Literal["success", "error"]

The status of the tool call

Accepts one of the following:
"success"
"error"
func_response: Optional[str]

The function response string

stderr: Optional[List[str]]

Captured stderr from the tool invocation

stdout: Optional[List[str]]

Captured stdout (e.g. prints, logs) from the tool invocation

tool_call_id: Optional[object]

The ID for the tool call

updated_at: Optional[datetime]

The timestamp when the object was last updated.

formatdate-time
MessageRole = Literal["assistant", "user", "tool", 3 more]
Accepts one of the following:
"assistant"
"user"
"tool"
"function"
"system"
"approval"
MessageType = Literal["system_message", "user_message", "assistant_message", 6 more]
Accepts one of the following:
"system_message"
"user_message"
"assistant_message"
"reasoning_message"
"hidden_reasoning_message"
"tool_call_message"
"tool_return_message"
"approval_request_message"
"approval_response_message"
class OmittedReasoningContent:

A placeholder for reasoning content we know is present, but isn't returned by the provider (e.g. OpenAI GPT-5 on ChatCompletions)

signature: Optional[str]

A unique identifier for this reasoning step.

type: Optional[Literal["omitted_reasoning"]]

Indicates this is an omitted reasoning step.

Accepts one of the following:
"omitted_reasoning"
class ReasoningContent:

Sent via the Anthropic Messages API

is_native: bool

Whether the reasoning content was generated by a reasoner model that processed this step.

reasoning: str

The intermediate reasoning or thought process content.

signature: Optional[str]

A unique identifier for this reasoning step.

type: Optional[Literal["reasoning"]]

Indicates this is a reasoning/intermediate step.

Accepts one of the following:
"reasoning"
class ReasoningMessage:

Representation of an agent's internal reasoning.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message source (Literal["reasoner_model", "non_reasoner_model"]): Whether the reasoning content was generated natively by a reasoner model or derived via prompting reasoning (str): The internal reasoning of the agent signature (Optional[str]): The model-generated signature of the reasoning step

id: str
date: datetime
reasoning: str
is_err: Optional[bool]
message_type: Optional[Literal["reasoning_message"]]

The type of the message.

Accepts one of the following:
"reasoning_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
signature: Optional[str]
source: Optional[Literal["reasoner_model", "non_reasoner_model"]]
Accepts one of the following:
"reasoner_model"
"non_reasoner_model"
step_id: Optional[str]
class RedactedReasoningContent:

Sent via the Anthropic Messages API

data: str

The redacted or filtered intermediate reasoning content.

type: Optional[Literal["redacted_reasoning"]]

Indicates this is a redacted thinking step.

Accepts one of the following:
"redacted_reasoning"
class Run:

Representation of a run - a conversation or processing session for an agent. Runs track when agents process messages and maintain the relationship between agents, steps, and messages.

id: str

The human-friendly ID of the Run

agent_id: str

The unique identifier of the agent associated with the run.

background: Optional[bool]

Whether the run was created in background mode.

base_template_id: Optional[str]

The base template ID that the run belongs to.

callback_error: Optional[str]

Optional error message from attempting to POST the callback endpoint.

callback_sent_at: Optional[datetime]

Timestamp when the callback was last attempted.

formatdate-time
callback_status_code: Optional[int]

HTTP status code returned by the callback endpoint.

callback_url: Optional[str]

If set, POST to this URL when the run completes.

completed_at: Optional[datetime]

The timestamp when the run was completed.

formatdate-time
created_at: Optional[datetime]

The timestamp when the run was created.

formatdate-time
metadata: Optional[Dict[str, object]]

Additional metadata for the run.

request_config: Optional[RequestConfig]

The request configuration for the run.

assistant_message_tool_kwarg: Optional[str]

The name of the message argument in the designated message tool.

assistant_message_tool_name: Optional[str]

The name of the designated message tool.

include_return_message_types: Optional[List[MessageType]]

Only return specified message types in the response. If None (default) returns all messages.

Accepts one of the following:
"system_message"
"user_message"
"assistant_message"
"reasoning_message"
"hidden_reasoning_message"
"tool_call_message"
"tool_return_message"
"approval_request_message"
"approval_response_message"
use_assistant_message: Optional[bool]

Whether the server should parse specific tool call arguments (default send_message) as AssistantMessage objects.

status: Optional[Literal["created", "running", "completed", 2 more]]

The current status of the run.

Accepts one of the following:
"created"
"running"
"completed"
"failed"
"cancelled"
stop_reason: Optional[StopReasonType]

The reason why the run was stopped.

Accepts one of the following:
"end_turn"
"error"
"llm_api_error"
"invalid_llm_response"
"invalid_tool_call"
"max_steps"
"no_tool_call"
"tool_rule"
"cancelled"
"requires_approval"
total_duration_ns: Optional[int]

Total run duration in nanoseconds

ttft_ns: Optional[int]

Time to first token for a run in nanoseconds

class SummaryMessage:

A message representing a summary of the conversation. Sent to the LLM as a user or system message depending on the provider.

id: str
date: datetime
summary: str
is_err: Optional[bool]
message_type: Optional[Literal["summary"]]
Accepts one of the following:
"summary"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class SystemMessage:

A message generated by the system. Never streamed back on a response, only used for cursor pagination.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message content (str): The message content sent by the system

id: str
content: str

The message content sent by the system

date: datetime
is_err: Optional[bool]
message_type: Optional[Literal["system_message"]]

The type of the message.

Accepts one of the following:
"system_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
class TextContent:
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
class ToolCall:
arguments: str
name: str
tool_call_id: str
class ToolCallContent:
id: str

A unique identifier for this specific tool call instance.

input: Dict[str, object]

The parameters being passed to the tool, structured as a dictionary of parameter names to values.

name: str

The name of the tool being called.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this tool call.

type: Optional[Literal["tool_call"]]

Indicates this content represents a tool call event.

Accepts one of the following:
"tool_call"
class ToolCallDelta:
arguments: Optional[str]
name: Optional[str]
tool_call_id: Optional[str]
class ToolCallMessage:

A message representing a request to call a tool (generated by the LLM to trigger tool execution).

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message tool_call (Union[ToolCall, ToolCallDelta]): The tool call

id: str
date: datetime
Deprecatedtool_call: ToolCall
Accepts one of the following:
class ToolCall:
arguments: str
name: str
tool_call_id: str
class ToolCallDelta:
arguments: Optional[str]
name: Optional[str]
tool_call_id: Optional[str]
is_err: Optional[bool]
message_type: Optional[Literal["tool_call_message"]]

The type of the message.

Accepts one of the following:
"tool_call_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]
tool_calls: Optional[ToolCalls]
Accepts one of the following:
ToolCallsUnionMember0 = List[ToolCall]
arguments: str
name: str
tool_call_id: str
class ToolCallDelta:
arguments: Optional[str]
name: Optional[str]
tool_call_id: Optional[str]
class ToolReturn:
status: Literal["success", "error"]
Accepts one of the following:
"success"
"error"
tool_call_id: str
tool_return: str
stderr: Optional[List[str]]
stdout: Optional[List[str]]
type: Optional[Literal["tool"]]

The message type to be created.

Accepts one of the following:
"tool"
class ToolReturnContent:
content: str

The content returned by the tool execution.

is_error: bool

Indicates whether the tool execution resulted in an error.

tool_call_id: str

References the ID of the ToolCallContent that initiated this tool call.

type: Optional[Literal["tool_return"]]

Indicates this content represents a tool return event.

Accepts one of the following:
"tool_return"
class UpdateAssistantMessage:
content: Union[List[LettaAssistantMessageContentUnion], str]

The message content sent by the assistant (can be a string or an array of content parts)

Accepts one of the following:
ContentUnionMember0 = List[LettaAssistantMessageContentUnion]
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
ContentUnionMember1 = str
message_type: Optional[Literal["assistant_message"]]
Accepts one of the following:
"assistant_message"
class UpdateReasoningMessage:
reasoning: str
message_type: Optional[Literal["reasoning_message"]]
Accepts one of the following:
"reasoning_message"
class UpdateSystemMessage:
content: str

The message content sent by the system (can be a string or an array of multi-modal content parts)

message_type: Optional[Literal["system_message"]]
Accepts one of the following:
"system_message"
class UpdateUserMessage:
content: Union[List[LettaUserMessageContentUnion], str]

The message content sent by the user (can be a string or an array of multi-modal content parts)

Accepts one of the following:
ContentUnionMember0 = List[LettaUserMessageContentUnion]
Accepts one of the following:
class TextContent:
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
class ImageContent:
source: Source

The source of the image.

Accepts one of the following:
class SourceURLImage:
url: str

The URL of the image.

type: Optional[Literal["url"]]

The source type for the image.

Accepts one of the following:
"url"
class SourceBase64Image:
data: str

The base64 encoded image data.

media_type: str

The media type for the image.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

type: Optional[Literal["base64"]]

The source type for the image.

Accepts one of the following:
"base64"
class SourceLettaImage:
file_id: str

The unique identifier of the image file persisted in storage.

data: Optional[str]

The base64 encoded image data.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

media_type: Optional[str]

The media type for the image.

type: Optional[Literal["letta"]]

The source type for the image.

Accepts one of the following:
"letta"
type: Optional[Literal["image"]]

The type of the message.

Accepts one of the following:
"image"
ContentUnionMember1 = str
message_type: Optional[Literal["user_message"]]
Accepts one of the following:
"user_message"
class UserMessage:

A message sent by the user. Never streamed back on a response, only used for cursor pagination.

Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message content (Union[str, List[LettaUserMessageContentUnion]]): The message content sent by the user (can be a string or an array of multi-modal content parts)

id: str
content: Union[List[LettaUserMessageContentUnion], str]

The message content sent by the user (can be a string or an array of multi-modal content parts)

Accepts one of the following:
ContentUnionMember0 = List[LettaUserMessageContentUnion]
Accepts one of the following:
class TextContent:
text: str

The text content of the message.

signature: Optional[str]

Stores a unique identifier for any reasoning associated with this text content.

type: Optional[Literal["text"]]

The type of the message.

Accepts one of the following:
"text"
class ImageContent:
source: Source

The source of the image.

Accepts one of the following:
class SourceURLImage:
url: str

The URL of the image.

type: Optional[Literal["url"]]

The source type for the image.

Accepts one of the following:
"url"
class SourceBase64Image:
data: str

The base64 encoded image data.

media_type: str

The media type for the image.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

type: Optional[Literal["base64"]]

The source type for the image.

Accepts one of the following:
"base64"
class SourceLettaImage:
file_id: str

The unique identifier of the image file persisted in storage.

data: Optional[str]

The base64 encoded image data.

detail: Optional[str]

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

media_type: Optional[str]

The media type for the image.

type: Optional[Literal["letta"]]

The source type for the image.

Accepts one of the following:
"letta"
type: Optional[Literal["image"]]

The type of the message.

Accepts one of the following:
"image"
ContentUnionMember1 = str
date: datetime
is_err: Optional[bool]
message_type: Optional[Literal["user_message"]]

The type of the message.

Accepts one of the following:
"user_message"
name: Optional[str]
otid: Optional[str]
run_id: Optional[str]
sender_id: Optional[str]
seq_id: Optional[int]
step_id: Optional[str]

AgentsBlocks

Retrieve Block For Agent
agents.blocks.retrieve(strblock_label, BlockRetrieveParams**kwargs) -> BlockResponse
get/v1/agents/{agent_id}/core-memory/blocks/{block_label}
Modify Block For Agent
agents.blocks.modify(strblock_label, BlockModifyParams**kwargs) -> BlockResponse
patch/v1/agents/{agent_id}/core-memory/blocks/{block_label}
List Blocks For Agent
agents.blocks.list(stragent_id, BlockListParams**kwargs) -> SyncArrayPage[BlockResponse]
get/v1/agents/{agent_id}/core-memory/blocks
Attach Block To Agent
agents.blocks.attach(strblock_id, BlockAttachParams**kwargs) -> AgentState
patch/v1/agents/{agent_id}/core-memory/blocks/attach/{block_id}
Detach Block From Agent
agents.blocks.detach(strblock_id, BlockDetachParams**kwargs) -> AgentState
patch/v1/agents/{agent_id}/core-memory/blocks/detach/{block_id}
ModelsExpand Collapse
class Block:

A Block represents a reserved section of the LLM's context window.

value: str

Value of the block.

id: Optional[str]

The human-friendly ID of the Block

base_template_id: Optional[str]

The base template id of the block.

created_by_id: Optional[str]

The id of the user that made this Block.

deployment_id: Optional[str]

The id of the deployment.

description: Optional[str]

Description of the block.

entity_id: Optional[str]

The id of the entity within the template.

hidden: Optional[bool]

If set to True, the block will be hidden.

is_template: Optional[bool]

Whether the block is a template (e.g. saved human/persona options).

label: Optional[str]

Label of the block (e.g. 'human', 'persona') in the context window.

last_updated_by_id: Optional[str]

The id of the user that last updated this Block.

limit: Optional[int]

Character limit of the block.

metadata: Optional[Dict[str, object]]

Metadata of the block.

preserve_on_migration: Optional[bool]

Preserve the block on template migration.

project_id: Optional[str]

The associated project id.

read_only: Optional[bool]

Whether the agent has read-only access to the block.

template_id: Optional[str]

The id of the template.

template_name: Optional[str]

Name of the block if it is a template.

class BlockModify:

Update a block

base_template_id: Optional[str]

The base template id of the block.

deployment_id: Optional[str]

The id of the deployment.

description: Optional[str]

Description of the block.

entity_id: Optional[str]

The id of the entity within the template.

hidden: Optional[bool]

If set to True, the block will be hidden.

is_template: Optional[bool]

Whether the block is a template (e.g. saved human/persona options).

label: Optional[str]

Label of the block (e.g. 'human', 'persona') in the context window.

limit: Optional[int]

Character limit of the block.

metadata: Optional[Dict[str, object]]

Metadata of the block.

preserve_on_migration: Optional[bool]

Preserve the block on template migration.

project_id: Optional[str]

The associated project id.

read_only: Optional[bool]

Whether the agent has read-only access to the block.

template_id: Optional[str]

The id of the template.

template_name: Optional[str]

Name of the block if it is a template.

value: Optional[str]

Value of the block.

AgentsTools

List Tools For Agent
agents.tools.list(stragent_id, ToolListParams**kwargs) -> SyncArrayPage[Tool]
get/v1/agents/{agent_id}/tools
Attach Tool To Agent
agents.tools.attach(strtool_id, ToolAttachParams**kwargs) -> AgentState
patch/v1/agents/{agent_id}/tools/attach/{tool_id}
Detach Tool From Agent
agents.tools.detach(strtool_id, ToolDetachParams**kwargs) -> AgentState
patch/v1/agents/{agent_id}/tools/detach/{tool_id}
Modify Approval For Tool
agents.tools.update_approval(strtool_name, ToolUpdateApprovalParams**kwargs) -> AgentState
patch/v1/agents/{agent_id}/tools/approval/{tool_name}

AgentsFolders

Attach Folder To Agent
agents.folders.attach(strfolder_id, FolderAttachParams**kwargs) -> AgentState
patch/v1/agents/{agent_id}/folders/attach/{folder_id}
Detach Folder From Agent
agents.folders.detach(strfolder_id, FolderDetachParams**kwargs) -> AgentState
patch/v1/agents/{agent_id}/folders/detach/{folder_id}
List Folders For Agent
agents.folders.list(stragent_id, FolderListParams**kwargs) -> SyncArrayPage[FolderListResponse]
get/v1/agents/{agent_id}/folders

AgentsFiles

Close All Files For Agent
agents.files.close_all(stragent_id) -> FileCloseAllResponse
patch/v1/agents/{agent_id}/files/close-all
Open File For Agent
agents.files.open(strfile_id, FileOpenParams**kwargs) -> FileOpenResponse
patch/v1/agents/{agent_id}/files/{file_id}/open
Close File For Agent
agents.files.close(strfile_id, FileCloseParams**kwargs) -> object
patch/v1/agents/{agent_id}/files/{file_id}/close
List Files For Agent
agents.files.list(stragent_id, FileListParams**kwargs) -> SyncNextFilesPage[FileListResponse]
get/v1/agents/{agent_id}/files

AgentsGroups

List Groups For Agent
agents.groups.list(stragent_id, GroupListParams**kwargs) -> SyncArrayPage[Group]
get/v1/agents/{agent_id}/groups

AgentsArchives

Attach Archive To Agent
agents.archives.attach(strarchive_id, ArchiveAttachParams**kwargs) -> object
patch/v1/agents/{agent_id}/archives/attach/{archive_id}
Detach Archive From Agent
agents.archives.detach(strarchive_id, ArchiveDetachParams**kwargs) -> object
patch/v1/agents/{agent_id}/archives/detach/{archive_id}

AgentsIdentities

Attach Identity To Agent
agents.identities.attach(stridentity_id, IdentityAttachParams**kwargs) -> object
patch/v1/agents/{agent_id}/identities/attach/{identity_id}
Detach Identity From Agent
agents.identities.detach(stridentity_id, IdentityDetachParams**kwargs) -> object
patch/v1/agents/{agent_id}/identities/detach/{identity_id}