@letta-ai/letta-client 1.0.0-alpha.15 → 1.0.0-alpha.17

package/src/resources/agents/agents.ts

@@ -33,6 +33,7 @@ import {
   FolderDetachParams,
   FolderListParams,
   FolderListResponse,
+  FolderListResponsesArrayPage,
   Folders,
 } from './folders';
 import * as GroupsAPI from './groups';
@@ -66,6 +67,8 @@ import {
   MessageRole,
   MessageSendAsyncParams,
   MessageSendParams,
+  MessageSendParamsNonStreaming,
+  MessageSendParamsStreaming,
   MessageStreamParams,
   MessageType,
   Messages,
@@ -90,18 +93,12 @@ import {
   UserMessage,
 } from './messages';
 import * as AgentsToolsAPI from './tools';
-import {
-  ToolAttachParams,
-  ToolDetachParams,
-  ToolListParams,
-  ToolListResponse,
-  ToolUpdateApprovalParams,
-  Tools,
-} from './tools';
+import { ToolAttachParams, ToolDetachParams, ToolListParams, ToolUpdateApprovalParams, Tools } from './tools';
 import * as BlocksBlocksAPI from '../blocks/blocks';
 import * as GroupsGroupsAPI from '../groups/groups';
 import * as IdentitiesAPI from '../identities/identities';
 import * as ModelsAPI from '../models/models';
+import * as RunsAPI from '../runs/runs';
 import { APIPromise } from '../../core/api-promise';
 import { ArrayPage, type ArrayPageParams, PagePromise } from '../../core/pagination';
 import { type Uploadable } from '../../core/uploads';
@@ -153,13 +150,6 @@ export class Agents extends APIResource {
     return this._client.delete(path`/v1/agents/${agentID}`, options);
   }
 
-  /**
-   * Get the total number of agents.
-   */
-  count(options?: RequestOptions): APIPromise<AgentCountResponse> {
-    return this._client.get('/v1/agents/count', options);
-  }
-
   /**
    * Export the serialized JSON representation of an agent, formatted with
    * indentation.
@@ -264,16 +254,6 @@ export interface AgentEnvironmentVariable {
  * 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.
- *
- * Parameters: id (str): The unique identifier of the agent. name (str): The name
- * of the agent (must be unique to the user). created_at (datetime): The datetime
- * the agent was created. message_ids (List[str]): The ids of the messages in the
- * agent's in-context memory. memory (Memory): The in-context memory of the agent.
- * tools (List[str]): The tools used by the agent. This includes any memory editing
- * functions specified in `memory`. system (str): The system prompt used by the
- * agent. llm_config (LLMConfig): The LLM configuration used by the agent.
- * embedding_config (EmbeddingConfig): The embedding configuration used by the
- * agent.
  */
 export interface AgentState {
   /**
@@ -292,17 +272,20 @@ export interface AgentState {
   blocks: Array<BlocksAPI.Block>;
 
   /**
-   * The embedding configuration used by the agent.
+   * @deprecated Deprecated: Use `embedding` field instead. The embedding
+   * configuration used by the agent.
    */
   embedding_config: ModelsAPI.EmbeddingConfig;
 
   /**
-   * The LLM configuration used by the agent.
+   * @deprecated Deprecated: Use `model` field instead. The LLM configuration used by
+   * the agent.
    */
   llm_config: ModelsAPI.LlmConfig;
 
   /**
-   * @deprecated The in-context memory of the agent.
+   * @deprecated Deprecated: Use `blocks` field instead. The in-context memory of the
+   * agent.
    */
   memory: AgentState.Memory;
 
@@ -356,6 +339,11 @@ export interface AgentState {
    */
   description?: string | null;
 
+  /**
+   * The embedding model handle used by the agent (format: provider/model-name).
+   */
+  embedding?: string | null;
+
   /**
    * If set to True, memory management will move to a background agent thread.
    */
@@ -377,7 +365,8 @@ export interface AgentState {
   identities?: Array<IdentitiesAPI.Identity>;
 
   /**
-   * @deprecated The ids of the identities associated with this agent.
+   * @deprecated Deprecated: Use `identities` field instead. The ids of the
+   * identities associated with this agent.
    */
   identity_ids?: Array<string>;
 
@@ -391,6 +380,11 @@ export interface AgentState {
    */
   last_run_duration_ms?: number | null;
 
+  /**
+   * The stop reason from the agent's last run.
+   */
+  last_stop_reason?: RunsAPI.StopReasonType | null;
+
   /**
    * The id of the user that made this object.
    */
@@ -425,7 +419,29 @@ export interface AgentState {
   metadata?: { [key: string]: unknown } | null;
 
   /**
-   * @deprecated The multi-agent group that this agent manages
+   * The model handle used by the agent (format: provider/model-name).
+   */
+  model?: string | null;
+
+  /**
+   * The model settings used by the agent.
+   */
+  model_settings?:
+    | AgentState.OpenAIModelSettings
+    | AgentState.AnthropicModelSettings
+    | AgentState.GoogleAIModelSettings
+    | AgentState.GoogleVertexModelSettings
+    | AgentState.AzureModelSettings
+    | AgentState.XaiModelSettings
+    | AgentState.GroqModelSettings
+    | AgentState.DeepseekModelSettings
+    | AgentState.TogetherModelSettings
+    | AgentState.BedrockModelSettings
+    | null;
+
+  /**
+   * @deprecated Deprecated: Use `managed_group` field instead. The multi-agent group
+   * that this agent manages.
    */
   multi_agent_group?: GroupsGroupsAPI.Group | null;
 
@@ -441,7 +457,7 @@ export interface AgentState {
   project_id?: string | null;
 
   /**
-   * The response format used by the agent when returning from `send_message`.
+   * The response format used by the agent
    */
   response_format?: TextResponseFormat | JsonSchemaResponseFormat | JsonObjectResponseFormat | null;
 
@@ -488,7 +504,8 @@ export interface AgentState {
 
 export namespace AgentState {
   /**
-   * @deprecated The in-context memory of the agent.
+   * @deprecated Deprecated: Use `blocks` field instead. The in-context memory of the
+   * agent.
    */
   export interface Memory {
     /**
@@ -628,15 +645,15 @@ export namespace AgentState {
   }
 
   /**
-   * Representation of a source, which is a collection of files and passages.
-   *
-   * Parameters: id (str): The ID of the source name (str): The name of the source.
-   * embedding_config (EmbeddingConfig): The embedding configuration used by the
-   * source. user_id (str): The ID of the user that created the source. metadata
-   * (dict): Metadata associated with the source. description (str): The description
-   * of the source.
+   * (Deprecated: Use Folder) Representation of a source, which is a collection of
+   * files and passages.
    */
   export interface Source {
+    /**
+     * The human-friendly ID of the Source
+     */
+    id: string;
+
     /**
      * The embedding configuration used by the source.
      */
@@ -647,11 +664,6 @@ export namespace AgentState {
      */
     name: string;
 
-    /**
-     * The human-friendly ID of the Source
-     */
-    id?: string;
-
     /**
      * The timestamp when the source was created.
      */
@@ -692,6 +704,413 @@ export namespace AgentState {
      */
     vector_db_provider?: ArchivesAPI.VectorDBProvider;
   }
+
+  export interface OpenAIModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'openai';
+
+    /**
+     * The reasoning configuration for the model.
+     */
+    reasoning?: OpenAIModelSettings.Reasoning;
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+
+  export namespace OpenAIModelSettings {
+    /**
+     * The reasoning configuration for the model.
+     */
+    export interface Reasoning {
+      /**
+       * The reasoning effort to use when generating text reasoning models
+       */
+      reasoning_effort?: 'minimal' | 'low' | 'medium' | 'high';
+    }
+  }
+
+  export interface AnthropicModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'anthropic';
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+
+    /**
+     * The thinking configuration for the model.
+     */
+    thinking?: AnthropicModelSettings.Thinking;
+
+    /**
+     * Soft control for how verbose model output should be, used for GPT-5 models.
+     */
+    verbosity?: 'low' | 'medium' | 'high' | null;
+  }
+
+  export namespace AnthropicModelSettings {
+    /**
+     * The thinking configuration for the model.
+     */
+    export interface Thinking {
+      /**
+       * The maximum number of tokens the model can use for extended thinking.
+       */
+      budget_tokens?: number;
+
+      /**
+       * The type of thinking to use.
+       */
+      type?: 'enabled' | 'disabled';
+    }
+  }
+
+  export interface GoogleAIModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'google_ai';
+
+    /**
+     * The response schema for the model.
+     */
+    response_schema?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+
+    /**
+     * The thinking configuration for the model.
+     */
+    thinking_config?: GoogleAIModelSettings.ThinkingConfig;
+  }
+
+  export namespace GoogleAIModelSettings {
+    /**
+     * The thinking configuration for the model.
+     */
+    export interface ThinkingConfig {
+      /**
+       * Whether to include thoughts in the model's response.
+       */
+      include_thoughts?: boolean;
+
+      /**
+       * The thinking budget for the model.
+       */
+      thinking_budget?: number;
+    }
+  }
+
+  export interface GoogleVertexModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'google_vertex';
+
+    /**
+     * The response schema for the model.
+     */
+    response_schema?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+
+    /**
+     * The thinking configuration for the model.
+     */
+    thinking_config?: GoogleVertexModelSettings.ThinkingConfig;
+  }
+
+  export namespace GoogleVertexModelSettings {
+    /**
+     * The thinking configuration for the model.
+     */
+    export interface ThinkingConfig {
+      /**
+       * Whether to include thoughts in the model's response.
+       */
+      include_thoughts?: boolean;
+
+      /**
+       * The thinking budget for the model.
+       */
+      thinking_budget?: number;
+    }
+  }
+
+  /**
+   * Azure OpenAI model configuration (OpenAI-compatible).
+   */
+  export interface AzureModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'azure';
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+
+  /**
+   * xAI model configuration (OpenAI-compatible).
+   */
+  export interface XaiModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'xai';
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+
+  /**
+   * Groq model configuration (OpenAI-compatible).
+   */
+  export interface GroqModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'groq';
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+
+  /**
+   * Deepseek model configuration (OpenAI-compatible).
+   */
+  export interface DeepseekModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'deepseek';
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+
+  /**
+   * Together AI model configuration (OpenAI-compatible).
+   */
+  export interface TogetherModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'together';
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+
+  /**
+   * AWS Bedrock model configuration.
+   */
+  export interface BedrockModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'bedrock';
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
 }
 
 /**
@@ -1031,8 +1450,6 @@ export interface TextResponseFormat {
 
 export type AgentDeleteResponse = unknown;
 
-export type AgentCountResponse = number;
-
 export type AgentExportFileResponse = string;
 
 /**
@@ -1052,7 +1469,7 @@ export interface AgentCreateParams {
   agent_type?: AgentType;
 
   /**
-   * The base template id of the agent.
+   * @deprecated Deprecated: No longer used. The base template id of the agent.
    */
   base_template_id?: string | null;
 
@@ -1072,13 +1489,13 @@ export interface AgentCreateParams {
   description?: string | null;
 
   /**
-   * The embedding configuration handle used by the agent, specified in the format
-   * provider/model-name.
+   * The embedding model handle used by the agent (format: provider/model-name).
    */
   embedding?: string | null;
 
   /**
-   * The embedding chunk size used by the agent.
+   * @deprecated Deprecated: No longer used. The embedding chunk size used by the
+   * agent.
    */
   embedding_chunk_size?: number | null;
 
@@ -1088,6 +1505,7 @@ export interface AgentCreateParams {
   embedding_config?: ModelsAPI.EmbeddingConfig | null;
 
   /**
+   * @deprecated Deprecated: Use `model` field to configure reasoning instead.
    * Whether to enable internal extended thinking step for a reasoner model.
    */
   enable_reasoner?: boolean | null;
@@ -1098,12 +1516,14 @@ export interface AgentCreateParams {
   enable_sleeptime?: boolean | null;
 
   /**
-   * Deprecated: please use the 'create agents from a template' endpoint instead.
+   * @deprecated Deprecated: please use the 'create agents from a template' endpoint
+   * instead.
    */
   from_template?: string | null;
 
   /**
-   * If set to True, the agent will be hidden.
+   * @deprecated Deprecated: No longer used. If set to True, the agent will be
+   * hidden.
    */
   hidden?: boolean | null;
 
@@ -1124,8 +1544,8 @@ export interface AgentCreateParams {
   include_base_tools?: boolean;
 
   /**
-   * If true, automatically creates and attaches a default data source for this
-   * agent.
+   * @deprecated If true, automatically creates and attaches a default data source
+   * for this agent.
    */
   include_default_source?: boolean;
 
@@ -1152,14 +1572,14 @@ export interface AgentCreateParams {
   max_files_open?: number | null;
 
   /**
-   * The maximum number of tokens to generate for reasoning step. If not set, the
-   * model will use its default value.
+   * @deprecated Deprecated: Use `model` field to configure reasoning tokens instead.
+   * The maximum number of tokens to generate for reasoning step.
    */
   max_reasoning_tokens?: number | null;
 
   /**
-   * The maximum number of tokens to generate, including reasoning step. If not set,
-   * the model will use its default value.
+   * @deprecated Deprecated: Use `model` field to configure max output tokens
+   * instead. The maximum number of tokens to generate, including reasoning step.
    */
   max_tokens?: number | null;
 
@@ -1169,7 +1589,8 @@ export interface AgentCreateParams {
   memory_blocks?: Array<BlocksBlocksAPI.CreateBlock> | null;
 
   /**
-   * The variables that should be set for the agent.
+   * @deprecated Deprecated: Only relevant for creating agents from a template. Use
+   * the 'create agents from a template' endpoint instead.
    */
   memory_variables?: { [key: string]: string } | null;
 
@@ -1186,18 +1607,34 @@ export interface AgentCreateParams {
   metadata?: { [key: string]: unknown } | null;
 
   /**
-   * The LLM configuration handle used by the agent, specified in the format
-   * provider/model-name, as an alternative to specifying llm_config.
+   * The model handle for the agent to use (format: provider/model-name).
    */
   model?: string | null;
 
+  /**
+   * The model settings for the agent.
+   */
+  model_settings?:
+    | AgentCreateParams.OpenAIModelSettings
+    | AgentCreateParams.AnthropicModelSettings
+    | AgentCreateParams.GoogleAIModelSettings
+    | AgentCreateParams.GoogleVertexModelSettings
+    | AgentCreateParams.AzureModelSettings
+    | AgentCreateParams.XaiModelSettings
+    | AgentCreateParams.GroqModelSettings
+    | AgentCreateParams.DeepseekModelSettings
+    | AgentCreateParams.TogetherModelSettings
+    | AgentCreateParams.BedrockModelSettings
+    | null;
+
   /**
    * The name of the agent.
    */
   name?: string;
 
   /**
-   * If set to True, enables parallel tool calling. Defaults to False.
+   * @deprecated Deprecated: Use `model` field to configure parallel tool calls
+   * instead. If set to True, enables parallel tool calling.
    */
   parallel_tool_calls?: boolean | null;
 
@@ -1209,17 +1646,19 @@ export interface AgentCreateParams {
 
   /**
    * @deprecated Deprecated: Project should now be passed via the X-Project header
-   * instead of in the request body. If using the sdk, this can be done via the new
-   * x_project field below.
+   * instead of in the request body. If using the SDK, this can be done via the
+   * x_project parameter.
    */
   project?: string | null;
 
   /**
-   * The id of the project the agent belongs to.
+   * @deprecated Deprecated: No longer used. The id of the project the agent belongs
+   * to.
    */
   project_id?: string | null;
 
   /**
+   * @deprecated Deprecated: Use `model` field to configure reasoning instead.
    * Whether to enable reasoning for this agent.
    */
   reasoning?: boolean | null;
@@ -1250,12 +1689,13 @@ export interface AgentCreateParams {
   tags?: Array<string> | null;
 
   /**
-   * Deprecated: No longer used
+   * @deprecated Deprecated: No longer used.
    */
   template?: boolean;
 
   /**
-   * The id of the template the agent belongs to.
+   * @deprecated Deprecated: No longer used. The id of the template the agent belongs
+   * to.
    */
   template_id?: string | null;
 
@@ -1265,7 +1705,8 @@ export interface AgentCreateParams {
   timezone?: string | null;
 
   /**
-   * Deprecated: use `secrets` field instead.
+   * @deprecated Deprecated: Use `secrets` field instead. Environment variables for
+   * tool execution.
    */
   tool_exec_environment_variables?: { [key: string]: string } | null;
 
@@ -1295,6 +1736,415 @@ export interface AgentCreateParams {
   tools?: Array<string> | null;
 }
 
+export namespace AgentCreateParams {
+  export interface OpenAIModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'openai';
+
+    /**
+     * The reasoning configuration for the model.
+     */
+    reasoning?: OpenAIModelSettings.Reasoning;
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+
+  export namespace OpenAIModelSettings {
+    /**
+     * The reasoning configuration for the model.
+     */
+    export interface Reasoning {
+      /**
+       * The reasoning effort to use when generating text reasoning models
+       */
+      reasoning_effort?: 'minimal' | 'low' | 'medium' | 'high';
+    }
+  }
+
+  export interface AnthropicModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'anthropic';
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+
+    /**
+     * The thinking configuration for the model.
+     */
+    thinking?: AnthropicModelSettings.Thinking;
+
+    /**
+     * Soft control for how verbose model output should be, used for GPT-5 models.
+     */
+    verbosity?: 'low' | 'medium' | 'high' | null;
+  }
+
+  export namespace AnthropicModelSettings {
+    /**
+     * The thinking configuration for the model.
+     */
+    export interface Thinking {
+      /**
+       * The maximum number of tokens the model can use for extended thinking.
+       */
+      budget_tokens?: number;
+
+      /**
+       * The type of thinking to use.
+       */
+      type?: 'enabled' | 'disabled';
+    }
+  }
+
+  export interface GoogleAIModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'google_ai';
+
+    /**
+     * The response schema for the model.
+     */
+    response_schema?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+
+    /**
+     * The thinking configuration for the model.
+     */
+    thinking_config?: GoogleAIModelSettings.ThinkingConfig;
+  }
+
+  export namespace GoogleAIModelSettings {
+    /**
+     * The thinking configuration for the model.
+     */
+    export interface ThinkingConfig {
+      /**
+       * Whether to include thoughts in the model's response.
+       */
+      include_thoughts?: boolean;
+
+      /**
+       * The thinking budget for the model.
+       */
+      thinking_budget?: number;
+    }
+  }
+
+  export interface GoogleVertexModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'google_vertex';
+
+    /**
+     * The response schema for the model.
+     */
+    response_schema?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+
+    /**
+     * The thinking configuration for the model.
+     */
+    thinking_config?: GoogleVertexModelSettings.ThinkingConfig;
+  }
+
+  export namespace GoogleVertexModelSettings {
+    /**
+     * The thinking configuration for the model.
+     */
+    export interface ThinkingConfig {
+      /**
+       * Whether to include thoughts in the model's response.
+       */
+      include_thoughts?: boolean;
+
+      /**
+       * The thinking budget for the model.
+       */
+      thinking_budget?: number;
+    }
+  }
+
+  /**
+   * Azure OpenAI model configuration (OpenAI-compatible).
+   */
+  export interface AzureModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'azure';
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+
+  /**
+   * xAI model configuration (OpenAI-compatible).
+   */
+  export interface XaiModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'xai';
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+
+  /**
+   * Groq model configuration (OpenAI-compatible).
+   */
+  export interface GroqModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'groq';
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+
+  /**
+   * Deepseek model configuration (OpenAI-compatible).
+   */
+  export interface DeepseekModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'deepseek';
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+
+  /**
+   * Together AI model configuration (OpenAI-compatible).
+   */
+  export interface TogetherModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'together';
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+
+  /**
+   * AWS Bedrock model configuration.
+   */
+  export interface BedrockModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'bedrock';
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+}
+
 export interface AgentRetrieveParams {
   /**
    * Specify which relational fields to include in the response. No relationships are
@@ -1363,6 +2213,11 @@ export interface AgentListParams extends ArrayPageParams {
    */
   include_relationships?: Array<string> | null;
 
+  /**
+   * Filter agents by their last stop reason.
+   */
+  last_stop_reason?: RunsAPI.StopReasonType | null;
+
   /**
    * If True, only returns agents that match ALL given tags. Otherwise, return agents
    * that have ANY of the passed-in tags.
@@ -1488,8 +2343,7 @@ export interface AgentModifyParams {
   description?: string | null;
 
   /**
-   * The embedding configuration handle used by the agent, specified in the format
-   * provider/model-name.
+   * The embedding model handle used by the agent (format: provider/model-name).
    */
   embedding?: string | null;
 
@@ -1523,6 +2377,11 @@ export interface AgentModifyParams {
    */
   last_run_duration_ms?: number | null;
 
+  /**
+   * The stop reason from the agent's last run.
+   */
+  last_stop_reason?: RunsAPI.StopReasonType | null;
+
   /**
    * Configuration for Language Model (LLM) connection and generation parameters.
    */
@@ -1535,8 +2394,8 @@ export interface AgentModifyParams {
   max_files_open?: number | null;
 
   /**
-   * The maximum number of tokens to generate, including reasoning step. If not set,
-   * the model will use its default value.
+   * @deprecated Deprecated: Use `model` field to configure max output tokens
+   * instead. The maximum number of tokens to generate, including reasoning step.
    */
   max_tokens?: number | null;
 
@@ -1558,18 +2417,34 @@ export interface AgentModifyParams {
   metadata?: { [key: string]: unknown } | null;
 
   /**
-   * The LLM configuration handle used by the agent, specified in the format
-   * provider/model-name, as an alternative to specifying llm_config.
+   * The model handle used by the agent (format: provider/model-name).
    */
   model?: string | null;
 
+  /**
+   * The model settings for the agent.
+   */
+  model_settings?:
+    | AgentModifyParams.OpenAIModelSettings
+    | AgentModifyParams.AnthropicModelSettings
+    | AgentModifyParams.GoogleAIModelSettings
+    | AgentModifyParams.GoogleVertexModelSettings
+    | AgentModifyParams.AzureModelSettings
+    | AgentModifyParams.XaiModelSettings
+    | AgentModifyParams.GroqModelSettings
+    | AgentModifyParams.DeepseekModelSettings
+    | AgentModifyParams.TogetherModelSettings
+    | AgentModifyParams.BedrockModelSettings
+    | null;
+
   /**
    * The name of the agent.
    */
   name?: string | null;
 
   /**
-   * If set to True, enables parallel tool calling. Defaults to False.
+   * @deprecated Deprecated: Use `model` field to configure parallel tool calls
+   * instead. If set to True, enables parallel tool calling.
    */
   parallel_tool_calls?: boolean | null;
 
@@ -1585,11 +2460,13 @@ export interface AgentModifyParams {
   project_id?: string | null;
 
   /**
+   * @deprecated Deprecated: Use `model` field to configure reasoning instead.
    * Whether to enable reasoning for this agent.
    */
   reasoning?: boolean | null;
 
   /**
+   * @deprecated Deprecated: Use `model` field to configure response format instead.
    * The response format for the agent.
    */
   response_format?: TextResponseFormat | JsonSchemaResponseFormat | JsonObjectResponseFormat | null;
@@ -1650,6 +2527,415 @@ export interface AgentModifyParams {
   > | null;
 }
 
+export namespace AgentModifyParams {
+  export interface OpenAIModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'openai';
+
+    /**
+     * The reasoning configuration for the model.
+     */
+    reasoning?: OpenAIModelSettings.Reasoning;
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+
+  export namespace OpenAIModelSettings {
+    /**
+     * The reasoning configuration for the model.
+     */
+    export interface Reasoning {
+      /**
+       * The reasoning effort to use when generating text reasoning models
+       */
+      reasoning_effort?: 'minimal' | 'low' | 'medium' | 'high';
+    }
+  }
+
+  export interface AnthropicModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'anthropic';
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+
+    /**
+     * The thinking configuration for the model.
+     */
+    thinking?: AnthropicModelSettings.Thinking;
+
+    /**
+     * Soft control for how verbose model output should be, used for GPT-5 models.
+     */
+    verbosity?: 'low' | 'medium' | 'high' | null;
+  }
+
+  export namespace AnthropicModelSettings {
+    /**
+     * The thinking configuration for the model.
+     */
+    export interface Thinking {
+      /**
+       * The maximum number of tokens the model can use for extended thinking.
+       */
+      budget_tokens?: number;
+
+      /**
+       * The type of thinking to use.
+       */
+      type?: 'enabled' | 'disabled';
+    }
+  }
+
+  export interface GoogleAIModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'google_ai';
+
+    /**
+     * The response schema for the model.
+     */
+    response_schema?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+
+    /**
+     * The thinking configuration for the model.
+     */
+    thinking_config?: GoogleAIModelSettings.ThinkingConfig;
+  }
+
+  export namespace GoogleAIModelSettings {
+    /**
+     * The thinking configuration for the model.
+     */
+    export interface ThinkingConfig {
+      /**
+       * Whether to include thoughts in the model's response.
+       */
+      include_thoughts?: boolean;
+
+      /**
+       * The thinking budget for the model.
+       */
+      thinking_budget?: number;
+    }
+  }
+
+  export interface GoogleVertexModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'google_vertex';
+
+    /**
+     * The response schema for the model.
+     */
+    response_schema?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+
+    /**
+     * The thinking configuration for the model.
+     */
+    thinking_config?: GoogleVertexModelSettings.ThinkingConfig;
+  }
+
+  export namespace GoogleVertexModelSettings {
+    /**
+     * The thinking configuration for the model.
+     */
+    export interface ThinkingConfig {
+      /**
+       * Whether to include thoughts in the model's response.
+       */
+      include_thoughts?: boolean;
+
+      /**
+       * The thinking budget for the model.
+       */
+      thinking_budget?: number;
+    }
+  }
+
+  /**
+   * Azure OpenAI model configuration (OpenAI-compatible).
+   */
+  export interface AzureModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'azure';
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+
+  /**
+   * xAI model configuration (OpenAI-compatible).
+   */
+  export interface XaiModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'xai';
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+
+  /**
+   * Groq model configuration (OpenAI-compatible).
+   */
+  export interface GroqModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'groq';
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+
+  /**
+   * Deepseek model configuration (OpenAI-compatible).
+   */
+  export interface DeepseekModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'deepseek';
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+
+  /**
+   * Together AI model configuration (OpenAI-compatible).
+   */
+  export interface TogetherModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'together';
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+
+  /**
+   * AWS Bedrock model configuration.
+   */
+  export interface BedrockModelSettings {
+    /**
+     * The maximum number of tokens the model can generate.
+     */
+    max_output_tokens?: number;
+
+    /**
+     * Whether to enable parallel tool calling.
+     */
+    parallel_tool_calls?: boolean;
+
+    /**
+     * The provider of the model.
+     */
+    provider?: 'bedrock';
+
+    /**
+     * The response format for the model.
+     */
+    response_format?:
+      | AgentsAPI.TextResponseFormat
+      | AgentsAPI.JsonSchemaResponseFormat
+      | AgentsAPI.JsonObjectResponseFormat
+      | null;
+
+    /**
+     * The temperature of the model.
+     */
+    temperature?: number;
+  }
+}
+
 Agents.Tools = Tools;
 Agents.Folders = Folders;
 Agents.Files = Files;
@@ -1677,7 +2963,6 @@ export declare namespace Agents {
     type TerminalToolRule as TerminalToolRule,
     type TextResponseFormat as TextResponseFormat,
     type AgentDeleteResponse as AgentDeleteResponse,
-    type AgentCountResponse as AgentCountResponse,
     type AgentExportFileResponse as AgentExportFileResponse,
     type AgentImportFileResponse as AgentImportFileResponse,
     type AgentStatesArrayPage as AgentStatesArrayPage,
@@ -1691,7 +2976,6 @@ export declare namespace Agents {
 
   export {
     Tools as Tools,
-    type ToolListResponse as ToolListResponse,
     type ToolListParams as ToolListParams,
     type ToolAttachParams as ToolAttachParams,
     type ToolDetachParams as ToolDetachParams,
@@ -1701,6 +2985,7 @@ export declare namespace Agents {
   export {
     Folders as Folders,
     type FolderListResponse as FolderListResponse,
+    type FolderListResponsesArrayPage as FolderListResponsesArrayPage,
     type FolderListParams as FolderListParams,
     type FolderAttachParams as FolderAttachParams,
     type FolderDetachParams as FolderDetachParams,
@@ -1779,6 +3064,8 @@ export declare namespace Agents {
     type MessageModifyParams as MessageModifyParams,
     type MessageResetParams as MessageResetParams,
     type MessageSendParams as MessageSendParams,
+    type MessageSendParamsNonStreaming as MessageSendParamsNonStreaming,
+    type MessageSendParamsStreaming as MessageSendParamsStreaming,
     type MessageSendAsyncParams as MessageSendAsyncParams,
     type MessageStreamParams as MessageStreamParams,
   };