@soat/sdk 0.77.1 → 0.78.0

package/dist/index.d.cts

@@ -526,6 +526,16 @@ type Agent = {
    * Maximum number of recent messages to include in the context window sent to the model. When null, all messages are included.
    */
   max_context_messages?: number | null;
+  /**
+   * Maximum number of tokens the model may generate per step of a turn. A response that reaches it stops with `stop_reason` `length`. Null leaves the model's default.
+   */
+  max_output_tokens?: number | null;
+  /**
+   * How much the model reasons before answering. Translated per provider (Anthropic thinking, Gemini thinking config, OpenAI reasoning effort) against what the model supports; a model that cannot reason ignores it. `none` turns reasoning off where the model allows it. Reasoning tokens are metered as output. Null leaves the model's default.
+   */
+  reasoning?: {
+    effort: 'none' | 'low' | 'medium' | 'high';
+  } | null;
   /**
    * When true, only one open session per actor_id is allowed for this agent. Creating a second open session for the same actor returns 409.
    */
@@ -587,7 +597,7 @@ type AgentVersion = {
    */
   version?: number;
   /**
-   * The agent's configuration as it stood at this version: every mutable field of the `Agent` schema (`instructions`, `model`, `tool_bindings`, `max_steps`, `tool_choice`, `stop_conditions`, `active_tool_ids`, `step_rules`, `boundary_policy`, `temperature`, `knowledge_config`, `output_schema`, `max_context_messages`, `single_session_per_actor`, `on_approval_expiry`, `guardrail_ids`, `ai_provider_id`, `model_route_id`, `name`), and none of its identity or bookkeeping fields (`id`, `project_id`, `version`, `active_release`, timestamps).
+   * The agent's configuration as it stood at this version: every mutable field of the `Agent` schema (`instructions`, `model`, `tool_bindings`, `max_steps`, `tool_choice`, `stop_conditions`, `active_tool_ids`, `step_rules`, `boundary_policy`, `temperature`, `knowledge_config`, `output_schema`, `max_context_messages`, `max_output_tokens`, `reasoning`, `single_session_per_actor`, `on_approval_expiry`, `guardrail_ids`, `ai_provider_id`, `model_route_id`, `name`), and none of its identity or bookkeeping fields (`id`, `project_id`, `version`, `active_release`, timestamps).
    *
    * Deliberately open rather than a fixed schema: an archive written by an earlier release of SOAT reflects the agent surface **of its own time**, so it may carry fields the current schema no longer defines, or lack ones it has since gained. Knowledge retrieval is not part of the snapshot — a version records which `knowledge_config` applied, while the documents and memory stores it resolves keep their own histories and are pinned at generation time.
    */
@@ -764,6 +774,16 @@ type CreateAgentRequest = {
    * Maximum number of recent messages included in the context window. Null means no limit.
    */
   max_context_messages?: number;
+  /**
+   * Maximum number of tokens the model may generate per step of a turn. A response that reaches it stops with `stop_reason` `length`. Null leaves the model's default.
+   */
+  max_output_tokens?: number | null;
+  /**
+   * How much the model reasons before answering. Translated per provider (Anthropic thinking, Gemini thinking config, OpenAI reasoning effort) against what the model supports; a model that cannot reason ignores it. `none` turns reasoning off where the model allows it. Reasoning tokens are metered as output. Null leaves the model's default.
+   */
+  reasoning?: {
+    effort: 'none' | 'low' | 'medium' | 'high';
+  } | null;
   /**
    * When true, only one open session per actor_id is allowed for this agent.
    */
@@ -899,6 +919,16 @@ type UpdateAgentRequest = {
    * Maximum number of recent messages included in the context window. Null means no limit.
    */
   max_context_messages?: number | null;
+  /**
+   * Maximum number of tokens the model may generate per step of a turn. A response that reaches it stops with `stop_reason` `length`. Null leaves the model's default.
+   */
+  max_output_tokens?: number | null;
+  /**
+   * How much the model reasons before answering. Translated per provider (Anthropic thinking, Gemini thinking config, OpenAI reasoning effort) against what the model supports; a model that cannot reason ignores it. `none` turns reasoning off where the model allows it. Reasoning tokens are metered as output. Null leaves the model's default.
+   */
+  reasoning?: {
+    effort: 'none' | 'low' | 'medium' | 'high';
+  } | null;
   /**
    * When true, only one open session per actor_id is allowed for this agent.
    */
@@ -2942,6 +2972,16 @@ type AgentResourceProperties = {
    * Maximum number of recent messages to include in the context window sent to the model. When null, all messages are included.
    */
   max_context_messages?: number | null;
+  /**
+   * Maximum number of tokens the model may generate per step of a turn. A response that reaches it stops with `stop_reason` `length`. Null leaves the model's default.
+   */
+  max_output_tokens?: number | null;
+  /**
+   * How much the model reasons before answering. Translated per provider (Anthropic thinking, Gemini thinking config, OpenAI reasoning effort) against what the model supports; a model that cannot reason ignores it. `none` turns reasoning off where the model allows it. Reasoning tokens are metered as output. Null leaves the model's default.
+   */
+  reasoning?: {
+    effort: 'none' | 'low' | 'medium' | 'high';
+  } | null;
   /**
    * When true, only one open session per actor_id is allowed for this agent.
    */
@@ -3671,6 +3711,10 @@ type SessionResourceProperties = {
    * Number of seconds of inactivity after which the session expires. 0 means never expires.
    */
   inactivity_ttl_seconds?: number;
+  /**
+   * Maximum number of recent conversation messages sent to the model on each generation, taking precedence over the agent's. null defers to the agent.
+   */
+  max_context_messages?: number | null;
   /**
    * Optional context object passed to tool calls. Write-only: no read of a session returns it.
    */
@@ -6251,6 +6295,11 @@ type SessionRecord = {
    *
    */
   message_delay_seconds?: number | null;
+  /**
+   * Maximum number of recent conversation messages sent to the model on each generation. Takes precedence over the agent's `max_context_messages`; null defers to it. A fork keeps its parent's value.
+   *
+   */
+  max_context_messages?: number | null;
   /**
    * Timestamp of the last activity on the session (message added or response generated).
    */
@@ -6331,6 +6380,11 @@ type CreateSessionRequest = {
    *
    */
   message_delay_seconds?: number | null;
+  /**
+   * Maximum number of recent conversation messages sent to the model on each generation, taking precedence over the agent's `max_context_messages`. null or absent defers to the agent.
+   *
+   */
+  max_context_messages?: number | null;
 };
 type UpdateSessionRequest = {
   /**
@@ -6361,6 +6415,11 @@ type UpdateSessionRequest = {
    *
    */
   message_delay_seconds?: number | null;
+  /**
+   * Maximum number of recent conversation messages sent to the model on each generation, taking precedence over the agent's `max_context_messages`. Set to null to defer to the agent.
+   *
+   */
+  max_context_messages?: number | null;
 };
 type AddSessionMessageRequest = {
   /**

package/dist/index.d.mts

@@ -526,6 +526,16 @@ type Agent = {
    * Maximum number of recent messages to include in the context window sent to the model. When null, all messages are included.
    */
   max_context_messages?: number | null;
+  /**
+   * Maximum number of tokens the model may generate per step of a turn. A response that reaches it stops with `stop_reason` `length`. Null leaves the model's default.
+   */
+  max_output_tokens?: number | null;
+  /**
+   * How much the model reasons before answering. Translated per provider (Anthropic thinking, Gemini thinking config, OpenAI reasoning effort) against what the model supports; a model that cannot reason ignores it. `none` turns reasoning off where the model allows it. Reasoning tokens are metered as output. Null leaves the model's default.
+   */
+  reasoning?: {
+    effort: 'none' | 'low' | 'medium' | 'high';
+  } | null;
   /**
    * When true, only one open session per actor_id is allowed for this agent. Creating a second open session for the same actor returns 409.
    */
@@ -587,7 +597,7 @@ type AgentVersion = {
    */
   version?: number;
   /**
-   * The agent's configuration as it stood at this version: every mutable field of the `Agent` schema (`instructions`, `model`, `tool_bindings`, `max_steps`, `tool_choice`, `stop_conditions`, `active_tool_ids`, `step_rules`, `boundary_policy`, `temperature`, `knowledge_config`, `output_schema`, `max_context_messages`, `single_session_per_actor`, `on_approval_expiry`, `guardrail_ids`, `ai_provider_id`, `model_route_id`, `name`), and none of its identity or bookkeeping fields (`id`, `project_id`, `version`, `active_release`, timestamps).
+   * The agent's configuration as it stood at this version: every mutable field of the `Agent` schema (`instructions`, `model`, `tool_bindings`, `max_steps`, `tool_choice`, `stop_conditions`, `active_tool_ids`, `step_rules`, `boundary_policy`, `temperature`, `knowledge_config`, `output_schema`, `max_context_messages`, `max_output_tokens`, `reasoning`, `single_session_per_actor`, `on_approval_expiry`, `guardrail_ids`, `ai_provider_id`, `model_route_id`, `name`), and none of its identity or bookkeeping fields (`id`, `project_id`, `version`, `active_release`, timestamps).
    *
    * Deliberately open rather than a fixed schema: an archive written by an earlier release of SOAT reflects the agent surface **of its own time**, so it may carry fields the current schema no longer defines, or lack ones it has since gained. Knowledge retrieval is not part of the snapshot — a version records which `knowledge_config` applied, while the documents and memory stores it resolves keep their own histories and are pinned at generation time.
    */
@@ -764,6 +774,16 @@ type CreateAgentRequest = {
    * Maximum number of recent messages included in the context window. Null means no limit.
    */
   max_context_messages?: number;
+  /**
+   * Maximum number of tokens the model may generate per step of a turn. A response that reaches it stops with `stop_reason` `length`. Null leaves the model's default.
+   */
+  max_output_tokens?: number | null;
+  /**
+   * How much the model reasons before answering. Translated per provider (Anthropic thinking, Gemini thinking config, OpenAI reasoning effort) against what the model supports; a model that cannot reason ignores it. `none` turns reasoning off where the model allows it. Reasoning tokens are metered as output. Null leaves the model's default.
+   */
+  reasoning?: {
+    effort: 'none' | 'low' | 'medium' | 'high';
+  } | null;
   /**
    * When true, only one open session per actor_id is allowed for this agent.
    */
@@ -899,6 +919,16 @@ type UpdateAgentRequest = {
    * Maximum number of recent messages included in the context window. Null means no limit.
    */
   max_context_messages?: number | null;
+  /**
+   * Maximum number of tokens the model may generate per step of a turn. A response that reaches it stops with `stop_reason` `length`. Null leaves the model's default.
+   */
+  max_output_tokens?: number | null;
+  /**
+   * How much the model reasons before answering. Translated per provider (Anthropic thinking, Gemini thinking config, OpenAI reasoning effort) against what the model supports; a model that cannot reason ignores it. `none` turns reasoning off where the model allows it. Reasoning tokens are metered as output. Null leaves the model's default.
+   */
+  reasoning?: {
+    effort: 'none' | 'low' | 'medium' | 'high';
+  } | null;
   /**
    * When true, only one open session per actor_id is allowed for this agent.
    */
@@ -2942,6 +2972,16 @@ type AgentResourceProperties = {
    * Maximum number of recent messages to include in the context window sent to the model. When null, all messages are included.
    */
   max_context_messages?: number | null;
+  /**
+   * Maximum number of tokens the model may generate per step of a turn. A response that reaches it stops with `stop_reason` `length`. Null leaves the model's default.
+   */
+  max_output_tokens?: number | null;
+  /**
+   * How much the model reasons before answering. Translated per provider (Anthropic thinking, Gemini thinking config, OpenAI reasoning effort) against what the model supports; a model that cannot reason ignores it. `none` turns reasoning off where the model allows it. Reasoning tokens are metered as output. Null leaves the model's default.
+   */
+  reasoning?: {
+    effort: 'none' | 'low' | 'medium' | 'high';
+  } | null;
   /**
    * When true, only one open session per actor_id is allowed for this agent.
    */
@@ -3671,6 +3711,10 @@ type SessionResourceProperties = {
    * Number of seconds of inactivity after which the session expires. 0 means never expires.
    */
   inactivity_ttl_seconds?: number;
+  /**
+   * Maximum number of recent conversation messages sent to the model on each generation, taking precedence over the agent's. null defers to the agent.
+   */
+  max_context_messages?: number | null;
   /**
    * Optional context object passed to tool calls. Write-only: no read of a session returns it.
    */
@@ -6251,6 +6295,11 @@ type SessionRecord = {
    *
    */
   message_delay_seconds?: number | null;
+  /**
+   * Maximum number of recent conversation messages sent to the model on each generation. Takes precedence over the agent's `max_context_messages`; null defers to it. A fork keeps its parent's value.
+   *
+   */
+  max_context_messages?: number | null;
   /**
    * Timestamp of the last activity on the session (message added or response generated).
    */
@@ -6331,6 +6380,11 @@ type CreateSessionRequest = {
    *
    */
   message_delay_seconds?: number | null;
+  /**
+   * Maximum number of recent conversation messages sent to the model on each generation, taking precedence over the agent's `max_context_messages`. null or absent defers to the agent.
+   *
+   */
+  max_context_messages?: number | null;
 };
 type UpdateSessionRequest = {
   /**
@@ -6361,6 +6415,11 @@ type UpdateSessionRequest = {
    *
    */
   message_delay_seconds?: number | null;
+  /**
+   * Maximum number of recent conversation messages sent to the model on each generation, taking precedence over the agent's `max_context_messages`. Set to null to defer to the agent.
+   *
+   */
+  max_context_messages?: number | null;
 };
 type AddSessionMessageRequest = {
   /**

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@soat/sdk",
-  "version": "0.77.1",
+  "version": "0.78.0",
   "description": "TypeScript SDK for SOAT — open-source infrastructure for production-ready AI agents.",
   "keywords": [
     "ai-agents",