Agents
Modify Agent
Retrieve Agent
Export Agent
Import Agent
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.
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.
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.
The type of agent.
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.
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.
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.
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.
compatibility_type: Optional[Literal["gguf", "mlx"]]
The framework compatibility type for the model.
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.
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
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.
Deprecatedmemory: Memory
Deprecated: Use blocks field instead. The in-context memory of the agent.
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 controlling prompt rendering.
Literal["memgpt_agent", "memgpt_v2_agent", "letta_v1_agent", 6 more]
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.
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
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.
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.
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.
vector_db_provider: Optional[VectorDBProvider]
The vector database provider used for this source's passages
system: str
The system prompt used by the agent.
tags: List[str]
The tags associated with the agent.
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.
Optional list of npm packages required by this tool.
name: str
Name of the npm package.
version: Optional[str]
Optional version of the package, following semantic versioning.
Optional list of pip packages required by this tool.
name: str
Name of the pip package.
version: Optional[str]
Optional version of the package, following semantic versioning.
return_char_limit: Optional[int]
The maximum number of characters in the response.
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.
base_template_id: Optional[str]
The base template id of the agent.
created_at: Optional[datetime]
The timestamp when the object was created.
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.
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.
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.
The type of the identity.
name: str
The name of the identity.
project_id: Optional[str]
The project id of the identity, if applicable.
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
value: Union[str, float, bool, Dict[str, object]]
The value of the property
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.
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.
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.
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.
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.
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.
template_id: Optional[str]
The id of the template.
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.
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.
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.
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.
template_id: Optional[str]
The id of the template.
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
class TextResponseFormat: …
Response format for plain text responses.
type: Optional[Literal["text"]]
The type of the response format.
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.
class JsonObjectResponseFormat: …
Response format for JSON object responses.
type: Optional[Literal["json_object"]]
The type of the response format.
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.
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.
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).
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.
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.
value_enc: Optional[str]
Encrypted secret value (stored as encrypted string)
tool_rules: Optional[List[ToolRule]]
The list of tool rules.
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"]]
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"]]
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"]]
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"]]
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"]]
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"]]
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"]]
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"]]
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"]]
updated_at: Optional[datetime]
The timestamp when the object was last updated.
AgentType = Literal["memgpt_agent", "memgpt_v2_agent", "letta_v1_agent", 6 more]
Enum to represent the type of 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"]]
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"]]
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"]]
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"]]
class JsonObjectResponseFormat: …
Response format for JSON object responses.
type: Optional[Literal["json_object"]]
The type of the response format.
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.
Sent via the Anthropic Messages API
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.
class ImageContent: …
source: Source
The source of the image.
class SourceURLImage: …
url: str
The URL of the image.
type: Optional[Literal["url"]]
The source type for the image.
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.
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.
type: Optional[Literal["image"]]
The type of the message.
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.
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.
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.
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.
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.
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"]]
class MessageCreate: …
Request to create a message
The content of the message.
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.
class ImageContent: …
source: Source
The source of the image.
class SourceURLImage: …
url: str
The URL of the image.
type: Optional[Literal["url"]]
The source type for the image.
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.
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.
type: Optional[Literal["image"]]
The type of the message.
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.
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.
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.
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.
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.
role: Literal["user", "system", "assistant"]
The role of the participant.
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.
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"]]
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"]]
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"]]
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"]]
class TextResponseFormat: …
Response format for plain text responses.
type: Optional[Literal["text"]]
The type of the response format.
AgentsMessages
List Messages
Send Message
Modify Message
Send Message Streaming
Cancel Message
Send Message Async
Reset Messages
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
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.
class ToolReturn: …
status: Literal["success", "error"]
type: Optional[Literal["tool"]]
The message type to be created.
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.
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
Deprecatedtool_call: ToolCall
The tool call that has been requested by the llm to run
class ToolCall: …
class ToolCallDelta: …
message_type: Optional[Literal["approval_request_message"]]
The type of the message.
tool_calls: Optional[ToolCalls]
The tool calls that have been requested by the llm to run, which are pending approval
class ToolCallDelta: …
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
Deprecatedapproval_request_id: Optional[str]
The message ID of the approval request
approvals: Optional[List[Approval]]
The list of approval responses
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.
class ToolReturn: …
status: Literal["success", "error"]
type: Optional[Literal["tool"]]
The message type to be created.
Deprecatedapprove: Optional[bool]
Whether the tool has been approved
message_type: Optional[Literal["approval_response_message"]]
The type of the message.
Deprecatedreason: Optional[str]
An optional explanation for the provided approval status
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)
The message content sent by the agent (can be a string or an array of content parts)
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.
message_type: Optional[Literal["assistant_message"]]
The type of the message.
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.
event_type: Literal["compaction"]
message_type: Optional[Literal["event"]]
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
state: Literal["redacted", "omitted"]
message_type: Optional[Literal["hidden_reasoning_message"]]
The type of the message.
class ImageContent: …
source: Source
The source of the image.
class SourceURLImage: …
url: str
The URL of the image.
type: Optional[Literal["url"]]
The source type for the image.
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.
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.
type: Optional[Literal["image"]]
The type of the message.
JobStatus = Literal["created", "running", "completed", 4 more]
Status of the job.
JobType = Literal["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.
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
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
content: str
The message content sent by the system
message_type: Optional[Literal["system_message"]]
The type of the 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)
The message content sent by the user (can be a string or an array of multi-modal content parts)
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.
class ImageContent: …
source: Source
The source of the image.
class SourceURLImage: …
url: str
The URL of the image.
type: Optional[Literal["url"]]
The source type for the image.
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.
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.
type: Optional[Literal["image"]]
The type of the message.
message_type: Optional[Literal["user_message"]]
The type of the message.
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
message_type: Optional[Literal["reasoning_message"]]
The type of the message.
source: Optional[Literal["reasoner_model", "non_reasoner_model"]]
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
state: Literal["redacted", "omitted"]
message_type: Optional[Literal["hidden_reasoning_message"]]
The type of the message.
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
Deprecatedtool_call: ToolCall
class ToolCall: …
class ToolCallDelta: …
message_type: Optional[Literal["tool_call_message"]]
The type of the message.
tool_calls: Optional[ToolCalls]
class ToolCallDelta: …
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
Deprecatedstatus: Literal["success", "error"]
message_type: Optional[Literal["tool_return_message"]]
The type of the message.
status: Literal["success", "error"]
type: Optional[Literal["tool"]]
The message type to be created.
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)
The message content sent by the agent (can be a string or an array of content parts)
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.
message_type: Optional[Literal["assistant_message"]]
The type of the message.
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
Deprecatedtool_call: ToolCall
The tool call that has been requested by the llm to run
class ToolCall: …
class ToolCallDelta: …
message_type: Optional[Literal["approval_request_message"]]
The type of the message.
tool_calls: Optional[ToolCalls]
The tool calls that have been requested by the llm to run, which are pending approval
class ToolCallDelta: …
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
Deprecatedapproval_request_id: Optional[str]
The message ID of the approval request
approvals: Optional[List[Approval]]
The list of approval responses
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.
class ToolReturn: …
status: Literal["success", "error"]
type: Optional[Literal["tool"]]
The message type to be created.
Deprecatedapprove: Optional[bool]
Whether the tool has been approved
message_type: Optional[Literal["approval_response_message"]]
The type of the message.
Deprecatedreason: Optional[str]
An optional explanation for the provided approval status
class SummaryMessage: …
A message representing a summary of the conversation. Sent to the LLM as a user or system message depending on the provider.
message_type: Optional[Literal["summary"]]
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.
event_type: Literal["compaction"]
message_type: Optional[Literal["event"]]
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.
Only return specified message types in the response. If None (default) returns all messages.
input: Optional[Union[str, List[InputUnionMember1], null]]
Syntactic sugar for a single user message. Equivalent to messages=[{'role': 'user', 'content': input}].
InputUnionMember1 = List[InputUnionMember1]
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.
class ImageContent: …
source: Source
The source of the image.
class SourceURLImage: …
url: str
The URL of the image.
type: Optional[Literal["url"]]
The source type for the image.
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.
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.
type: Optional[Literal["image"]]
The type of the message.
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.
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.
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.
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.
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.
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.
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.
class MessageCreate: …
Request to create a message
The content of the message.
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.
class ImageContent: …
source: Source
The source of the image.
class SourceURLImage: …
url: str
The URL of the image.
type: Optional[Literal["url"]]
The source type for the image.
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.
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.
type: Optional[Literal["image"]]
The type of the message.
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.
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.
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.
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.
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.
role: Literal["user", "system", "assistant"]
The role of the participant.
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.
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
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.
class ToolReturn: …
status: Literal["success", "error"]
type: Optional[Literal["tool"]]
The message type to be created.
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.
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
The messages returned by the agent.
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
content: str
The message content sent by the system
message_type: Optional[Literal["system_message"]]
The type of the 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)
The message content sent by the user (can be a string or an array of multi-modal content parts)
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.
class ImageContent: …
source: Source
The source of the image.
class SourceURLImage: …
url: str
The URL of the image.
type: Optional[Literal["url"]]
The source type for the image.
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.
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.
type: Optional[Literal["image"]]
The type of the message.
message_type: Optional[Literal["user_message"]]
The type of the message.
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
message_type: Optional[Literal["reasoning_message"]]
The type of the message.
source: Optional[Literal["reasoner_model", "non_reasoner_model"]]
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
state: Literal["redacted", "omitted"]
message_type: Optional[Literal["hidden_reasoning_message"]]
The type of the message.
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
Deprecatedtool_call: ToolCall
class ToolCall: …
class ToolCallDelta: …
message_type: Optional[Literal["tool_call_message"]]
The type of the message.
tool_calls: Optional[ToolCalls]
class ToolCallDelta: …
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
Deprecatedstatus: Literal["success", "error"]
message_type: Optional[Literal["tool_return_message"]]
The type of the message.
status: Literal["success", "error"]
type: Optional[Literal["tool"]]
The message type to be created.
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)
The message content sent by the agent (can be a string or an array of content parts)
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.
message_type: Optional[Literal["assistant_message"]]
The type of the message.
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
Deprecatedtool_call: ToolCall
The tool call that has been requested by the llm to run
class ToolCall: …
class ToolCallDelta: …
message_type: Optional[Literal["approval_request_message"]]
The type of the message.
tool_calls: Optional[ToolCalls]
The tool calls that have been requested by the llm to run, which are pending approval
class ToolCallDelta: …
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
Deprecatedapproval_request_id: Optional[str]
The message ID of the approval request
approvals: Optional[List[Approval]]
The list of approval responses
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.
class ToolReturn: …
status: Literal["success", "error"]
type: Optional[Literal["tool"]]
The message type to be created.
Deprecatedapprove: Optional[bool]
Whether the tool has been approved
message_type: Optional[Literal["approval_response_message"]]
The type of the message.
Deprecatedreason: Optional[str]
An optional explanation for the provided approval status
class SummaryMessage: …
A message representing a summary of the conversation. Sent to the LLM as a user or system message depending on the provider.
message_type: Optional[Literal["summary"]]
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.
event_type: Literal["compaction"]
message_type: Optional[Literal["event"]]
stop_reason: StopReason
The stop reason from Letta indicating why agent loop stopped execution.
The reason why execution stopped.
message_type: Optional[Literal["stop_reason"]]
The type of the message.
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"]]
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).
Only return specified message types in the response. If None (default) returns all messages.
input: Optional[Union[str, List[InputUnionMember1], null]]
Syntactic sugar for a single user message. Equivalent to messages=[{'role': 'user', 'content': input}].
InputUnionMember1 = List[InputUnionMember1]
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.
class ImageContent: …
source: Source
The source of the image.
class SourceURLImage: …
url: str
The URL of the image.
type: Optional[Literal["url"]]
The source type for the image.
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.
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.
type: Optional[Literal["image"]]
The type of the message.
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.
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.
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.
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.
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.
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.
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.
class MessageCreate: …
Request to create a message
The content of the message.
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.
class ImageContent: …
source: Source
The source of the image.
class SourceURLImage: …
url: str
The URL of the image.
type: Optional[Literal["url"]]
The source type for the image.
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.
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.
type: Optional[Literal["image"]]
The type of the message.
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.
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.
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.
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.
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.
role: Literal["user", "system", "assistant"]
The role of the participant.
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.
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
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.
class ToolReturn: …
status: Literal["success", "error"]
type: Optional[Literal["tool"]]
The message type to be created.
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.
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.
Streaming response type for Server-Sent Events (SSE) endpoints. Each event in the stream will be one of these types.
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
content: str
The message content sent by the system
message_type: Optional[Literal["system_message"]]
The type of the 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)
The message content sent by the user (can be a string or an array of multi-modal content parts)
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.
class ImageContent: …
source: Source
The source of the image.
class SourceURLImage: …
url: str
The URL of the image.
type: Optional[Literal["url"]]
The source type for the image.
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.
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.
type: Optional[Literal["image"]]
The type of the message.
message_type: Optional[Literal["user_message"]]
The type of the message.
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
message_type: Optional[Literal["reasoning_message"]]
The type of the message.
source: Optional[Literal["reasoner_model", "non_reasoner_model"]]
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
state: Literal["redacted", "omitted"]
message_type: Optional[Literal["hidden_reasoning_message"]]
The type of the message.
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
Deprecatedtool_call: ToolCall
class ToolCall: …
class ToolCallDelta: …
message_type: Optional[Literal["tool_call_message"]]
The type of the message.
tool_calls: Optional[ToolCalls]
class ToolCallDelta: …
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
Deprecatedstatus: Literal["success", "error"]
message_type: Optional[Literal["tool_return_message"]]
The type of the message.
status: Literal["success", "error"]
type: Optional[Literal["tool"]]
The message type to be created.
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)
The message content sent by the agent (can be a string or an array of content parts)
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.
message_type: Optional[Literal["assistant_message"]]
The type of the message.
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
Deprecatedtool_call: ToolCall
The tool call that has been requested by the llm to run
class ToolCall: …
class ToolCallDelta: …
message_type: Optional[Literal["approval_request_message"]]
The type of the message.
tool_calls: Optional[ToolCalls]
The tool calls that have been requested by the llm to run, which are pending approval
class ToolCallDelta: …
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
Deprecatedapproval_request_id: Optional[str]
The message ID of the approval request
approvals: Optional[List[Approval]]
The list of approval responses
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.
class ToolReturn: …
status: Literal["success", "error"]
type: Optional[Literal["tool"]]
The message type to be created.
Deprecatedapprove: Optional[bool]
Whether the tool has been approved
message_type: Optional[Literal["approval_response_message"]]
The type of the message.
Deprecatedreason: Optional[str]
An optional explanation for the provided approval status
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.
class LettaStopReason: …
The stop reason from Letta indicating why agent loop stopped execution.
The reason why execution stopped.
message_type: Optional[Literal["stop_reason"]]
The type of the message.
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"]]
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 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.
class ImageContent: …
source: Source
The source of the image.
class SourceURLImage: …
url: str
The URL of the image.
type: Optional[Literal["url"]]
The source type for the image.
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.
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.
type: Optional[Literal["image"]]
The type of the message.
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.
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.
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.
class ApprovalLettaSchemasMessageToolReturn: …
status: Literal["success", "error"]
The status of the tool call
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.
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.
class ImageContent: …
source: Source
The source of the image.
class SourceURLImage: …
url: str
The URL of the image.
type: Optional[Literal["url"]]
The source type for the image.
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.
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.
type: Optional[Literal["image"]]
The type of the message.
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.
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.
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.
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.
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.
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.
created_at: Optional[datetime]
The timestamp when the object was created.
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.
function: ToolCallFunction
type: Literal["function"]
tool_returns: Optional[List[ToolReturn]]
Tool execution return information for prior tool calls
status: Literal["success", "error"]
The status of the tool call
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.
MessageRole = Literal["assistant", "user", "tool", 3 more]
MessageType = Literal["system_message", "user_message", "assistant_message", 6 more]
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.
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.
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
message_type: Optional[Literal["reasoning_message"]]
The type of the message.
source: Optional[Literal["reasoner_model", "non_reasoner_model"]]
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.
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.
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.
created_at: Optional[datetime]
The timestamp when the run was created.
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.
Only return specified message types in the response. If None (default) returns all messages.
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.
stop_reason: Optional[StopReasonType]
The reason why the run was stopped.
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.
message_type: Optional[Literal["summary"]]
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
content: str
The message content sent by the system
message_type: Optional[Literal["system_message"]]
The type of the message.
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.
class ToolCall: …
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.
class ToolCallDelta: …
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
Deprecatedtool_call: ToolCall
class ToolCall: …
class ToolCallDelta: …
message_type: Optional[Literal["tool_call_message"]]
The type of the message.
tool_calls: Optional[ToolCalls]
class ToolCallDelta: …
class ToolReturn: …
status: Literal["success", "error"]
type: Optional[Literal["tool"]]
The message type to be created.
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.
class UpdateAssistantMessage: …
The message content sent by the assistant (can be a string or an array of content parts)
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.
message_type: Optional[Literal["assistant_message"]]
class UpdateReasoningMessage: …
message_type: Optional[Literal["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"]]
class UpdateUserMessage: …
The message content sent by the user (can be a string or an array of multi-modal content parts)
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.
class ImageContent: …
source: Source
The source of the image.
class SourceURLImage: …
url: str
The URL of the image.
type: Optional[Literal["url"]]
The source type for the image.
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.
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.
type: Optional[Literal["image"]]
The type of the message.
message_type: Optional[Literal["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)
The message content sent by the user (can be a string or an array of multi-modal content parts)
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.
class ImageContent: …
source: Source
The source of the image.
class SourceURLImage: …
url: str
The URL of the image.
type: Optional[Literal["url"]]
The source type for the image.
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.
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.
type: Optional[Literal["image"]]
The type of the message.
message_type: Optional[Literal["user_message"]]
The type of the message.
AgentsBlocks
Retrieve Block For Agent
Modify Block For Agent
List Blocks For Agent
Attach Block To Agent
Detach Block From Agent
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.