@epilot/sdk 2.20.70 → 2.20.72

package/docs/identity.md

@@ -42,6 +42,7 @@ const { data } = await identityClient.listClients(...)
 - [`revokeClientOrganization`](#revokeclientorganization)
 - [`suspendClientOrganization`](#suspendclientorganization)
 - [`activateClientOrganization`](#activateclientorganization)
+- [`getUserSubject`](#getusersubject)
 
 **Session**
 - [`createIdentitySession`](#createidentitysession)
@@ -54,6 +55,7 @@ const { data } = await identityClient.listClients(...)
 - [`Error`](#error)
 - [`PartnerClientId`](#partnerclientid)
 - [`OrgId`](#orgid)
+- [`UserId`](#userid)
 - [`Environment`](#environment)
 - [`PartnerClientStatus`](#partnerclientstatus)
 - [`Scope`](#scope)
@@ -67,13 +69,13 @@ const { data } = await identityClient.listClients(...)
 - [`RotateSecretRequest`](#rotatesecretrequest)
 - [`AuthorizationPolicyInput`](#authorizationpolicyinput)
 - [`AuthorizationPolicy`](#authorizationpolicy)
-- [`PartnerAccount`](#partneraccount)
 - [`OrgEnablementStatus`](#orgenablementstatus)
 - [`OrgEnablementCreate`](#orgenablementcreate)
 - [`OrgEnablementUpdate`](#orgenablementupdate)
 - [`OrgEnablement`](#orgenablement)
 - [`OrgEnablementList`](#orgenablementlist)
 - [`IdentitySession`](#identitysession)
+- [`UserSubject`](#usersubject)
 
 ### `listClients`
 
@@ -523,10 +525,6 @@ const { data } = await client.listClientOrganizations({
         "recorded_by": "string",
         "recorded_at": "1970-01-01T00:00:00.000Z"
       },
-      "partner_account": {
-        "id": "string",
-        "label": "string"
-      },
       "created_at": "1970-01-01T00:00:00.000Z",
       "updated_at": "1970-01-01T00:00:00.000Z",
       "created_by": "string",
@@ -561,10 +559,6 @@ const { data } = await client.enableClientOrganization(
       allowed_scopes: ['openid'],
       customer_approval_ref: 'string',
       approved_at: '1970-01-01T00:00:00.000Z'
-    },
-    partner_account: {
-      id: 'string',
-      label: 'string'
     }
   },
 )
@@ -590,10 +584,6 @@ const { data } = await client.enableClientOrganization(
     "recorded_by": "string",
     "recorded_at": "1970-01-01T00:00:00.000Z"
   },
-  "partner_account": {
-    "id": "string",
-    "label": "string"
-  },
   "created_at": "1970-01-01T00:00:00.000Z",
   "updated_at": "1970-01-01T00:00:00.000Z",
   "created_by": "string",
@@ -638,10 +628,6 @@ const { data } = await client.getClientOrganization({
     "recorded_by": "string",
     "recorded_at": "1970-01-01T00:00:00.000Z"
   },
-  "partner_account": {
-    "id": "string",
-    "label": "string"
-  },
   "created_at": "1970-01-01T00:00:00.000Z",
   "updated_at": "1970-01-01T00:00:00.000Z",
   "created_by": "string",
@@ -674,10 +660,6 @@ const { data } = await client.updateClientOrganization(
       allowed_scopes: ['openid'],
       customer_approval_ref: 'string',
       approved_at: '1970-01-01T00:00:00.000Z'
-    },
-    partner_account: {
-      id: 'string',
-      label: 'string'
     }
   },
 )
@@ -703,10 +685,6 @@ const { data } = await client.updateClientOrganization(
     "recorded_by": "string",
     "recorded_at": "1970-01-01T00:00:00.000Z"
   },
-  "partner_account": {
-    "id": "string",
-    "label": "string"
-  },
   "created_at": "1970-01-01T00:00:00.000Z",
   "updated_at": "1970-01-01T00:00:00.000Z",
   "created_by": "string",
@@ -758,10 +736,6 @@ const { data } = await client.revokeClientOrganization(
     "recorded_by": "string",
     "recorded_at": "1970-01-01T00:00:00.000Z"
   },
-  "partner_account": {
-    "id": "string",
-    "label": "string"
-  },
   "created_at": "1970-01-01T00:00:00.000Z",
   "updated_at": "1970-01-01T00:00:00.000Z",
   "created_by": "string",
@@ -811,10 +785,6 @@ const { data } = await client.suspendClientOrganization(
     "recorded_by": "string",
     "recorded_at": "1970-01-01T00:00:00.000Z"
   },
-  "partner_account": {
-    "id": "string",
-    "label": "string"
-  },
   "created_at": "1970-01-01T00:00:00.000Z",
   "updated_at": "1970-01-01T00:00:00.000Z",
   "created_by": "string",
@@ -859,10 +829,6 @@ const { data } = await client.activateClientOrganization({
     "recorded_by": "string",
     "recorded_at": "1970-01-01T00:00:00.000Z"
   },
-  "partner_account": {
-    "id": "string",
-    "label": "string"
-  },
   "created_at": "1970-01-01T00:00:00.000Z",
   "updated_at": "1970-01-01T00:00:00.000Z",
   "created_by": "string",
@@ -874,6 +840,40 @@ const { data } = await client.activateClientOrganization({
 
 ---
 
+### `getUserSubject`
+
+The pairwise `sub` this client receives for one epilot user, so the partner can bind the person on its
+side **before** the first sign-in (for example a Babelforce agent provisioned through SCIM with
+`
+
+`GET /v1/identity/operator/clients/{client_id}/organizations/{org_id}/users/{user_id}:subject`
+
+```ts
+const { data } = await client.getUserSubject({
+  client_id: 'example',
+  org_id: 'example',
+  user_id: 'example',
+})
+```
+
+<details>
+<summary>Response</summary>
+
+```json
+{
+  "client_id": "bf-prod-x7k2",
+  "org_id": "739224",
+  "user_id": "100321",
+  "sub": "v1.dGhpcy1pcy1hLWR1bW15LXN1YmplY3QtdmFsdWUtMDAx",
+  "key_version": "v1",
+  "sector": "portal.epilot.cloud"
+}
+```
+
+</details>
+
+---
+
 ### `createIdentitySession`
 
 Called by the epilot portal through the portal-host proxy after every persisted 360 session.
@@ -958,6 +958,14 @@ epilot organization id, an opaque case-sensitive string
 type OrgId = string
 ```
 
+### `UserId`
+
+epilot user id (`custom:ivy_user_id` in a 360 token). A user belongs to exactly one organization.
+
+```ts
+type UserId = string
+```
+
 ### `Environment`
 
 Partner-side environment this client belongs to
@@ -1151,17 +1159,6 @@ type AuthorizationPolicy = {
 }
 ```
 
-### `PartnerAccount`
-
-Optional audit reference to the partner tenant this organization maps to. The partner enforces the mapping.
-
-```ts
-type PartnerAccount = {
-  id: string
-  label?: string
-}
-```
-
 ### `OrgEnablementStatus`
 
 ```ts
@@ -1180,10 +1177,6 @@ type OrgEnablementCreate = {
     customer_approval_ref: string
     approved_at: string // date-time
   }
-  partner_account?: {
-    id: string
-    label?: string
-  }
 }
 ```
 
@@ -1199,10 +1192,6 @@ type OrgEnablementUpdate = {
     customer_approval_ref: string
     approved_at: string // date-time
   }
-  partner_account?: {
-    id: string
-    label?: string
-  }
 }
 ```
 
@@ -1225,10 +1214,6 @@ type OrgEnablement = {
     recorded_by: string
     recorded_at: string // date-time
   }
-  partner_account?: {
-    id: string
-    label?: string
-  }
   created_at: string // date-time
   updated_at: string // date-time
   created_by?: string
@@ -1256,10 +1241,6 @@ type OrgEnablementList = {
       recorded_by: { ... }
       recorded_at: { ... }
     }
-    partner_account?: {
-      id: { ... }
-      label?: { ... }
-    }
     created_at: string // date-time
     updated_at: string // date-time
     created_by?: string
@@ -1277,3 +1258,16 @@ type IdentitySession = {
   expires_at: string // date-time
 }
 ```
+
+### `UserSubject`
+
+```ts
+type UserSubject = {
+  client_id: string
+  org_id: string
+  user_id: string
+  sub: string
+  key_version: string
+  sector: string
+}
+```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@epilot/sdk",
-  "version": "2.20.70",
+  "version": "2.20.72",
   "description": "JavaScript/TypeScript SDK for epilot APIs",
   "type": "module",
   "main": "./dist/index.cjs",

package/dist/ai-agents-ME5VRKMY.cjs

@@ -1,7 +0,0 @@
-"use strict";Object.defineProperty(exports, "__esModule", {value: true});require('./chunk-NJK5F5TF.cjs');
-
-// src/docs/ai-agents.json
-var ai_agents_default = '# AI Agents API\n\n- **Base URL:** `https://ai-agents.sls.epilot.io`\n- **Full API Docs:** [https://docs.epilot.io/api/ai-agents](https://docs.epilot.io/api/ai-agents)\n\n## Usage\n\n```ts\nimport { epilot } from \'@epilot/sdk\'\n\nepilot.authorize(() => \'<token>\')\nconst { data } = await epilot.aiAgents.createAgent(...)\n```\n\n### Tree-shakeable import\n\n```ts\nimport { getClient, authorize } from \'@epilot/sdk/ai-agents\'\n\nconst aiAgentsClient = getClient()\nauthorize(aiAgentsClient, () => \'<token>\')\nconst { data } = await aiAgentsClient.createAgent(...)\n```\n\n## Operations\n\n**Agents Configuration**\n- [`createAgent`](#createagent)\n- [`listAgents`](#listagents)\n- [`getAgentById`](#getagentbyid)\n- [`updateAgentById`](#updateagentbyid)\n- [`deleteAgentById`](#deleteagentbyid)\n\n**Agent Execution**\n- [`executeAgent`](#executeagent)\n- [`executeAgentStream`](#executeagentstream)\n- [`listExecutions`](#listexecutions)\n- [`getExecution`](#getexecution)\n- [`cancelExecution`](#cancelexecution)\n- [`getExecutionTrace`](#getexecutiontrace)\n- [`getExecutionFeedback`](#getexecutionfeedback)\n- [`putExecutionFeedback`](#putexecutionfeedback)\n- [`approveExecution`](#approveexecution)\n- [`rejectExecution`](#rejectexecution)\n- [`streamExecution`](#streamexecution)\n\n**Chat**\n- [`chat`](#chat)\n\n**Conversations**\n- [`listConversations`](#listconversations)\n- [`getConversation`](#getconversation)\n- [`deleteConversation`](#deleteconversation)\n- [`submitConversationFeedback`](#submitconversationfeedback)\n\n**Schemas**\n- [`AgentId`](#agentid)\n- [`CreateAgentRequest`](#createagentrequest)\n- [`UpdateAgentRequest`](#updateagentrequest)\n- [`AgentDefinition`](#agentdefinition)\n- [`ListAgentsResponse`](#listagentsresponse)\n- [`ListExecutionsResponse`](#listexecutionsresponse)\n- [`ApproveExecutionRequest`](#approveexecutionrequest)\n- [`RejectExecutionRequest`](#rejectexecutionrequest)\n- [`ExecuteAgentRequest`](#executeagentrequest)\n- [`ExecutionResponse`](#executionresponse)\n- [`ExecutionIterationProjection`](#executioniterationprojection)\n- [`ExecutionFeedback`](#executionfeedback)\n- [`ExecutionFeedbackResponse`](#executionfeedbackresponse)\n- [`PutExecutionFeedbackRequest`](#putexecutionfeedbackrequest)\n- [`ExecutionTrace`](#executiontrace)\n- [`ExecutionIteration`](#executioniteration)\n- [`PendingAction`](#pendingaction)\n- [`ExecutionError`](#executionerror)\n- [`ExecutionMetrics`](#executionmetrics)\n- [`AgentExecutionEventStatus`](#agentexecutioneventstatus)\n- [`AgentExecutionEvent`](#agentexecutionevent)\n- [`ToolPreview`](#toolpreview)\n- [`PreviewActionType`](#previewactiontype)\n- [`PreviewEntity`](#previewentity)\n- [`PreviewChange`](#previewchange)\n- [`PreviewValue`](#previewvalue)\n- [`ToolDefinition`](#tooldefinition)\n- [`SkillCategory`](#skillcategory)\n- [`AgentSource`](#agentsource)\n- [`SkillAvailability`](#skillavailability)\n- [`ExecutionContext`](#executioncontext)\n- [`ExecutionPattern`](#executionpattern)\n- [`ExecutionMode`](#executionmode)\n- [`ExecutionStatus`](#executionstatus)\n- [`ParameterType`](#parametertype)\n- [`InputParameterDefinition`](#inputparameterdefinition)\n- [`InputParametersSchema`](#inputparametersschema)\n- [`ModelConfig`](#modelconfig)\n- [`Error`](#error)\n- [`ChatRequest`](#chatrequest)\n- [`ChatMessage`](#chatmessage)\n- [`StreamingOptions`](#streamingoptions)\n- [`StreamEvent`](#streamevent)\n- [`ExecutionResult`](#executionresult)\n- [`ConversationItem`](#conversationitem)\n- [`MessageItem`](#messageitem)\n- [`MessageFeedback`](#messagefeedback)\n- [`SubmitFeedbackRequest`](#submitfeedbackrequest)\n- [`ListConversationsResponse`](#listconversationsresponse)\n- [`ConversationWithMessages`](#conversationwithmessages)\n\n### `createAgent`\n\nCreates a new custom agent. System skills cannot be created via this endpoint.\n\n`POST /v1/agents`\n\n```ts\nconst { data } = await client.createAgent(\n  null,\n  {\n    name: \'Email Reply Generator\',\n    description: \'string\',\n    category: \'message\',\n    icon: \'mail-reply\',\n    system_prompt: \'string\',\n    tools: [\'entity.search\', \'message.draft\'],\n    model_config: {\n      model_id: \'anthropic.claude-3-5-sonnet-20241022-v2:0\',\n      temperature: 0.7,\n      max_tokens: 4096,\n      thinking: false,\n      thinking_budget: 10000\n    },\n    max_iterations: 10,\n    execution_pattern: \'direct\',\n    execution_mode: \'automatic\',\n    output_schema: {},\n    input_parameters_schema: {\n      type: \'object\',\n      parameters: [\n        {\n          name: \'target_schema\',\n          label: \'Target Schema\',\n          type: \'entity-schema\',\n          description: \'Entity type to create\'\n        },\n        {\n          name: \'confidence_threshold\',\n          label: \'Confidence Threshold\',\n          type: \'number\',\n          minimum: 0,\n          maximum: 1,\n          default: 0.8\n        },\n        /* ... 1 more */\n      ],\n      required: [\'target_schema\']\n    }\n  },\n)\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "agent_id": "skill:email-categorizer",\n  "org_id": "string",\n  "name": "string",\n  "description": "string",\n  "category": "message",\n  "icon": "string",\n  "source": "system",\n  "availability": ["flows", "copilot"],\n  "allowed_entity_schemas": ["message"],\n  "system_prompt": "string",\n  "tools": ["string"],\n  "model_config": {\n    "model_id": "anthropic.claude-3-5-sonnet-20241022-v2:0",\n    "temperature": 0.7,\n    "max_tokens": 4096,\n    "thinking": false,\n    "thinking_budget": 10000\n  },\n  "max_iterations": 0,\n  "execution_pattern": "direct",\n  "execution_mode": "automatic",\n  "output_schema": {},\n  "input_parameters_schema": {\n    "type": "object",\n    "parameters": [\n      {\n        "name": "target_schema",\n        "label": "Target Schema",\n        "type": "entity-schema",\n        "description": "Entity type to create"\n      },\n      {\n        "name": "confidence_threshold",\n        "label": "Confidence Threshold",\n        "type": "number",\n        "minimum": 0,\n        "maximum": 1,\n        "default": 0.8\n      }\n    ],\n    "required": ["target_schema"]\n  },\n  "version": 0,\n  "created_at": "1970-01-01T00:00:00.000Z",\n  "updated_at": "1970-01-01T00:00:00.000Z",\n  "created_by": "string"\n}\n```\n\n</details>\n\n---\n\n### `listAgents`\n\nLists agents from both system skills and custom agents.\nUse query parameters to filter by source, availability, or entity schema.\n\n`GET /v1/agents`\n\n```ts\nconst { data } = await client.listAgents({\n  source: \'example\',\n  availability: \'example\',\n  entity_schema: \'example\',\n})\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "agents": [\n    {\n      "agent_id": "skill:email-categorizer",\n      "org_id": "string",\n      "name": "string",\n      "description": "string",\n      "category": "message",\n      "icon": "string",\n      "source": "system",\n      "availability": ["flows", "copilot"],\n      "allowed_entity_schemas": ["message"],\n      "system_prompt": "string",\n      "tools": ["string"],\n      "model_config": {\n        "model_id": "anthropic.claude-3-5-sonnet-20241022-v2:0",\n        "temperature": 0.7,\n        "max_tokens": 4096,\n        "thinking": false,\n        "thinking_budget": 10000\n      },\n      "max_iterations": 0,\n      "execution_pattern": "direct",\n      "execution_mode": "automatic",\n      "output_schema": {},\n      "input_parameters_schema": {\n        "type": "object",\n        "parameters": [\n          {\n            "name": "target_schema",\n            "label": "Target Schema",\n            "type": "entity-schema",\n            "description": "Entity type to create"\n          },\n          {\n            "name": "confidence_threshold",\n            "label": "Confidence Threshold",\n            "type": "number",\n            "minimum": 0,\n            "maximum": 1,\n            "default": 0.8\n          }\n        ],\n        "required": ["target_schema"]\n      },\n      "version": 0,\n      "created_at": "1970-01-01T00:00:00.000Z",\n      "updated_at": "1970-01-01T00:00:00.000Z",\n      "created_by": "string"\n    }\n  ],\n  "next_cursor": "string"\n}\n```\n\n</details>\n\n---\n\n### `getAgentById`\n\nRetrieves an agent by ID. Supports both:\n- System skill IDs (prefixed): "skill:email-categorizer"\n- Custom agent IDs (UUID): "0336a235-9417-4dd8-894c-fe81285bba75"\n\n`GET /v1/agents/{agent_id}`\n\n```ts\nconst { data } = await client.getAgentById({\n  agent_id: \'example\',\n})\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "agent_id": "skill:email-categorizer",\n  "org_id": "string",\n  "name": "string",\n  "description": "string",\n  "category": "message",\n  "icon": "string",\n  "source": "system",\n  "availability": ["flows", "copilot"],\n  "allowed_entity_schemas": ["message"],\n  "system_prompt": "string",\n  "tools": ["string"],\n  "model_config": {\n    "model_id": "anthropic.claude-3-5-sonnet-20241022-v2:0",\n    "temperature": 0.7,\n    "max_tokens": 4096,\n    "thinking": false,\n    "thinking_budget": 10000\n  },\n  "max_iterations": 0,\n  "execution_pattern": "direct",\n  "execution_mode": "automatic",\n  "output_schema": {},\n  "input_parameters_schema": {\n    "type": "object",\n    "parameters": [\n      {\n        "name": "target_schema",\n        "label": "Target Schema",\n        "type": "entity-schema",\n        "description": "Entity type to create"\n      },\n      {\n        "name": "confidence_threshold",\n        "label": "Confidence Threshold",\n        "type": "number",\n        "minimum": 0,\n        "maximum": 1,\n        "default": 0.8\n      }\n    ],\n    "required": ["target_schema"]\n  },\n  "version": 0,\n  "created_at": "1970-01-01T00:00:00.000Z",\n  "updated_at": "1970-01-01T00:00:00.000Z",\n  "created_by": "string"\n}\n```\n\n</details>\n\n---\n\n### `updateAgentById`\n\nUpdates a custom agent. System skills cannot be updated via this endpoint.\n\n`PUT /v1/agents/{agent_id}`\n\n```ts\nconst { data } = await client.updateAgentById(\n  {\n    agent_id: \'example\',\n  },\n  {\n    name: \'string\',\n    description: \'string\',\n    category: \'message\',\n    icon: \'string\',\n    system_prompt: \'string\',\n    tools: [\'string\'],\n    model_config: {\n      model_id: \'anthropic.claude-3-5-sonnet-20241022-v2:0\',\n      temperature: 0.7,\n      max_tokens: 4096,\n      thinking: false,\n      thinking_budget: 10000\n    },\n    max_iterations: 1,\n    execution_pattern: \'direct\',\n    execution_mode: \'automatic\',\n    output_schema: {},\n    input_parameters_schema: {\n      type: \'object\',\n      parameters: [\n        {\n          name: \'target_schema\',\n          label: \'Target Schema\',\n          type: \'entity-schema\',\n          description: \'Entity type to create\'\n        },\n        {\n          name: \'confidence_threshold\',\n          label: \'Confidence Threshold\',\n          type: \'number\',\n          minimum: 0,\n          maximum: 1,\n          default: 0.8\n        },\n        /* ... 1 more */\n      ],\n      required: [\'target_schema\']\n    }\n  },\n)\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "agent_id": "skill:email-categorizer",\n  "org_id": "string",\n  "name": "string",\n  "description": "string",\n  "category": "message",\n  "icon": "string",\n  "source": "system",\n  "availability": ["flows", "copilot"],\n  "allowed_entity_schemas": ["message"],\n  "system_prompt": "string",\n  "tools": ["string"],\n  "model_config": {\n    "model_id": "anthropic.claude-3-5-sonnet-20241022-v2:0",\n    "temperature": 0.7,\n    "max_tokens": 4096,\n    "thinking": false,\n    "thinking_budget": 10000\n  },\n  "max_iterations": 0,\n  "execution_pattern": "direct",\n  "execution_mode": "automatic",\n  "output_schema": {},\n  "input_parameters_schema": {\n    "type": "object",\n    "parameters": [\n      {\n        "name": "target_schema",\n        "label": "Target Schema",\n        "type": "entity-schema",\n        "description": "Entity type to create"\n      },\n      {\n        "name": "confidence_threshold",\n        "label": "Confidence Threshold",\n        "type": "number",\n        "minimum": 0,\n        "maximum": 1,\n        "default": 0.8\n      }\n    ],\n    "required": ["target_schema"]\n  },\n  "version": 0,\n  "created_at": "1970-01-01T00:00:00.000Z",\n  "updated_at": "1970-01-01T00:00:00.000Z",\n  "created_by": "string"\n}\n```\n\n</details>\n\n---\n\n### `deleteAgentById`\n\nDeletes a custom agent. System skills cannot be deleted via this endpoint.\n\n`DELETE /v1/agents/{agent_id}`\n\n```ts\nconst { data } = await client.deleteAgentById({\n  agent_id: \'example\',\n})\n```\n\n---\n\n### `executeAgent`\n\nExecutes an agent (system skill or custom agent).\nSupports both:\n- System skill IDs (prefixed): "skill:email-categorizer"\n- Custom agent IDs (UUID): "0336a235-9417-4dd8-894c-fe81285bba75"\n\n`POST /v1/agents/{agent_id}/execute`\n\n```ts\nconst { data } = await client.executeAgent(\n  {\n    agent_id: \'example\',\n  },\n  {\n    input: {\n      entity_id: \'string\',\n      entity_schema: \'string\',\n      workflow_id: \'string\',\n      workflow_execution_id: \'string\',\n      task_id: \'string\',\n      custom_data: {},\n      flow_context: [\n        {\n          entity_id: \'string\',\n          entity_schema: \'string\'\n        }\n      ]\n    },\n    parameters: {},\n    execution_mode_override: \'automatic\',\n    execution_context: \'flows\',\n    callback_url: \'https://example.com/path\',\n    timeout_ms: 30000\n  },\n)\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "execution_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n  "agent_id": "skill:email-categorizer",\n  "agent_source": "system",\n  "agent_name": "string",\n  "execution_context": "flows",\n  "org_id": "string",\n  "status": "pending",\n  "input": {},\n  "parameters": {},\n  "result": {\n    "response": "string",\n    "structured_output": {}\n  },\n  "error": {\n    "code": "TIMEOUT",\n    "message": "string",\n    "details": {}\n  },\n  "pending_action": {\n    "tool": "string",\n    "input": {},\n    "description": "string",\n    "preview": {\n      "action": {\n        "type": "move",\n        "verb": "Move Thread"\n      },\n      "source": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "target": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "changes": [\n        {\n          "field": "string",\n          "label": "string",\n          "from": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          },\n          "to": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          }\n        }\n      ],\n      "metadata": {},\n      "summary": "This email discusses solar panel installation and should be handled by the Service team."\n    }\n  },\n  "metrics": {\n    "total_tokens": 0,\n    "input_tokens": 0,\n    "output_tokens": 0,\n    "total_cost_usd": 0,\n    "duration_ms": 0,\n    "iteration_count": 0\n  },\n  "started_at": "1970-01-01T00:00:00.000Z",\n  "completed_at": "1970-01-01T00:00:00.000Z",\n  "iterations": [\n    {\n      "index": 0,\n      "tool": "string",\n      "status": "running",\n      "timestamp": "1970-01-01T00:00:00.000Z"\n    }\n  ]\n}\n```\n\n</details>\n\n---\n\n### `executeAgentStream`\n\nExecutes an agent with real-time streaming of tokens and tool events.\nReturns Server-Sent Events (SSE) stream with token-by-token output,\ntool call progress, and completion status.\n\n`POST /v1/agents/{agent_id}/execute/stream`\n\n```ts\nconst { data } = await client.executeAgentStream(\n  {\n    agent_id: \'example\',\n  },\n  {\n    input: {\n      entity_id: \'string\',\n      entity_schema: \'string\',\n      workflow_id: \'string\',\n      workflow_execution_id: \'string\',\n      task_id: \'string\',\n      custom_data: {},\n      flow_context: [\n        {\n          entity_id: \'string\',\n          entity_schema: \'string\'\n        }\n      ]\n    },\n    parameters: {},\n    execution_mode_override: \'automatic\',\n    execution_context: \'flows\',\n    callback_url: \'https://example.com/path\',\n    timeout_ms: 30000\n  },\n)\n```\n\n---\n\n### `listExecutions`\n\nList executions\n\n`GET /v1/executions`\n\n```ts\nconst { data } = await client.listExecutions({\n  agent_id: \'example\',\n  status: \'example\',\n  limit: 1,\n})\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "executions": [\n    {\n      "execution_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n      "agent_id": "skill:email-categorizer",\n      "agent_source": "system",\n      "agent_name": "string",\n      "execution_context": "flows",\n      "org_id": "string",\n      "status": "pending",\n      "input": {},\n      "parameters": {},\n      "result": {\n        "response": "string",\n        "structured_output": {}\n      },\n      "error": {\n        "code": "TIMEOUT",\n        "message": "string",\n        "details": {}\n      },\n      "pending_action": {\n        "tool": "string",\n        "input": {},\n        "description": "string",\n        "preview": {\n          "action": {\n            "type": "move",\n            "verb": "Move Thread"\n          },\n          "source": {\n            "type": "inbox",\n            "id": "string",\n            "name": "Support Inbox",\n            "schema": "string",\n            "icon": "string",\n            "url": "string"\n          },\n          "target": {\n            "type": "inbox",\n            "id": "string",\n            "name": "Support Inbox",\n            "schema": "string",\n            "icon": "string",\n            "url": "string"\n          },\n          "changes": [\n            {\n              "field": "string",\n              "label": "string",\n              "from": {\n                "type": "text",\n                "value": {},\n                "values": ["string"],\n                "id": "string",\n                "name": "string",\n                "schema": "string",\n                "color": "success"\n              },\n              "to": {\n                "type": "text",\n                "value": {},\n                "values": ["string"],\n                "id": "string",\n                "name": "string",\n                "schema": "string",\n                "color": "success"\n              }\n            }\n          ],\n          "metadata": {},\n          "summary": "This email discusses solar panel installation and should be handled by the Service team."\n        }\n      },\n      "metrics": {\n        "total_tokens": 0,\n        "input_tokens": 0,\n        "output_tokens": 0,\n        "total_cost_usd": 0,\n        "duration_ms": 0,\n        "iteration_count": 0\n      },\n      "started_at": "1970-01-01T00:00:00.000Z",\n      "completed_at": "1970-01-01T00:00:00.000Z",\n      "iterations": [\n        {\n          "index": 0,\n          "tool": "string",\n          "status": "running",\n          "timestamp": "1970-01-01T00:00:00.000Z"\n        }\n      ]\n    }\n  ],\n  "next_cursor": "string"\n}\n```\n\n</details>\n\n---\n\n### `getExecution`\n\nGet execution by ID\n\n`GET /v1/executions/{execution_id}`\n\n```ts\nconst { data } = await client.getExecution({\n  execution_id: \'example\',\n})\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "execution_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n  "agent_id": "skill:email-categorizer",\n  "agent_source": "system",\n  "agent_name": "string",\n  "execution_context": "flows",\n  "org_id": "string",\n  "status": "pending",\n  "input": {},\n  "parameters": {},\n  "result": {\n    "response": "string",\n    "structured_output": {}\n  },\n  "error": {\n    "code": "TIMEOUT",\n    "message": "string",\n    "details": {}\n  },\n  "pending_action": {\n    "tool": "string",\n    "input": {},\n    "description": "string",\n    "preview": {\n      "action": {\n        "type": "move",\n        "verb": "Move Thread"\n      },\n      "source": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "target": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "changes": [\n        {\n          "field": "string",\n          "label": "string",\n          "from": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          },\n          "to": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          }\n        }\n      ],\n      "metadata": {},\n      "summary": "This email discusses solar panel installation and should be handled by the Service team."\n    }\n  },\n  "metrics": {\n    "total_tokens": 0,\n    "input_tokens": 0,\n    "output_tokens": 0,\n    "total_cost_usd": 0,\n    "duration_ms": 0,\n    "iteration_count": 0\n  },\n  "started_at": "1970-01-01T00:00:00.000Z",\n  "completed_at": "1970-01-01T00:00:00.000Z",\n  "iterations": [\n    {\n      "index": 0,\n      "tool": "string",\n      "status": "running",\n      "timestamp": "1970-01-01T00:00:00.000Z"\n    }\n  ]\n}\n```\n\n</details>\n\n---\n\n### `cancelExecution`\n\nCancel execution\n\n`DELETE /v1/executions/{execution_id}`\n\n```ts\nconst { data } = await client.cancelExecution({\n  execution_id: \'example\',\n})\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "execution_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n  "agent_id": "skill:email-categorizer",\n  "agent_source": "system",\n  "agent_name": "string",\n  "execution_context": "flows",\n  "org_id": "string",\n  "status": "pending",\n  "input": {},\n  "parameters": {},\n  "result": {\n    "response": "string",\n    "structured_output": {}\n  },\n  "error": {\n    "code": "TIMEOUT",\n    "message": "string",\n    "details": {}\n  },\n  "pending_action": {\n    "tool": "string",\n    "input": {},\n    "description": "string",\n    "preview": {\n      "action": {\n        "type": "move",\n        "verb": "Move Thread"\n      },\n      "source": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "target": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "changes": [\n        {\n          "field": "string",\n          "label": "string",\n          "from": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          },\n          "to": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          }\n        }\n      ],\n      "metadata": {},\n      "summary": "This email discusses solar panel installation and should be handled by the Service team."\n    }\n  },\n  "metrics": {\n    "total_tokens": 0,\n    "input_tokens": 0,\n    "output_tokens": 0,\n    "total_cost_usd": 0,\n    "duration_ms": 0,\n    "iteration_count": 0\n  },\n  "started_at": "1970-01-01T00:00:00.000Z",\n  "completed_at": "1970-01-01T00:00:00.000Z",\n  "iterations": [\n    {\n      "index": 0,\n      "tool": "string",\n      "status": "running",\n      "timestamp": "1970-01-01T00:00:00.000Z"\n    }\n  ]\n}\n```\n\n</details>\n\n---\n\n### `getExecutionTrace`\n\nReturns the step-by-step reasoning and tool calls for ReAct mode executions. Returns empty iterations array for direct mode executions.\n\n`GET /v1/executions/{execution_id}/trace`\n\n```ts\nconst { data } = await client.getExecutionTrace({\n  execution_id: \'example\',\n})\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "execution_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n  "iterations": [\n    {\n      "iteration_index": 0,\n      "thought": "string",\n      "action": {\n        "tool": "string",\n        "input": {}\n      },\n      "observation": {},\n      "timestamp": "1970-01-01T00:00:00.000Z",\n      "tokens_used": 0,\n      "latency_ms": 0\n    }\n  ],\n  "total_iterations": 0\n}\n```\n\n</details>\n\n---\n\n### `getExecutionFeedback`\n\nGet execution feedback\n\n`GET /v1/executions/{execution_id}/feedback`\n\n```ts\nconst { data } = await client.getExecutionFeedback({\n  execution_id: \'example\',\n})\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "feedback": {\n    "rating": "up",\n    "comment": "string",\n    "user_id": "string",\n    "submitted_at": "1970-01-01T00:00:00.000Z"\n  }\n}\n```\n\n</details>\n\n---\n\n### `putExecutionFeedback`\n\nSubmit execution feedback\n\n`PUT /v1/executions/{execution_id}/feedback`\n\n```ts\nconst { data } = await client.putExecutionFeedback(\n  {\n    execution_id: \'example\',\n  },\n  {\n    rating: \'up\',\n    comment: \'string\'\n  },\n)\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "feedback": {\n    "rating": "up",\n    "comment": "string",\n    "user_id": "string",\n    "submitted_at": "1970-01-01T00:00:00.000Z"\n  }\n}\n```\n\n</details>\n\n---\n\n### `approveExecution`\n\nApproves a pending tool action when execution is in waiting_approval status\n\n`POST /v1/executions/{execution_id}/approve`\n\n```ts\nconst { data } = await client.approveExecution(\n  {\n    execution_id: \'example\',\n  },\n  {\n    reason: \'string\',\n    approved_action_ids: [\'string\'],\n    rejected_action_ids: [\'string\']\n  },\n)\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "execution_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n  "agent_id": "skill:email-categorizer",\n  "agent_source": "system",\n  "agent_name": "string",\n  "execution_context": "flows",\n  "org_id": "string",\n  "status": "pending",\n  "input": {},\n  "parameters": {},\n  "result": {\n    "response": "string",\n    "structured_output": {}\n  },\n  "error": {\n    "code": "TIMEOUT",\n    "message": "string",\n    "details": {}\n  },\n  "pending_action": {\n    "tool": "string",\n    "input": {},\n    "description": "string",\n    "preview": {\n      "action": {\n        "type": "move",\n        "verb": "Move Thread"\n      },\n      "source": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "target": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "changes": [\n        {\n          "field": "string",\n          "label": "string",\n          "from": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          },\n          "to": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          }\n        }\n      ],\n      "metadata": {},\n      "summary": "This email discusses solar panel installation and should be handled by the Service team."\n    }\n  },\n  "metrics": {\n    "total_tokens": 0,\n    "input_tokens": 0,\n    "output_tokens": 0,\n    "total_cost_usd": 0,\n    "duration_ms": 0,\n    "iteration_count": 0\n  },\n  "started_at": "1970-01-01T00:00:00.000Z",\n  "completed_at": "1970-01-01T00:00:00.000Z",\n  "iterations": [\n    {\n      "index": 0,\n      "tool": "string",\n      "status": "running",\n      "timestamp": "1970-01-01T00:00:00.000Z"\n    }\n  ]\n}\n```\n\n</details>\n\n---\n\n### `rejectExecution`\n\nRejects a pending tool action when execution is in waiting_approval status\n\n`POST /v1/executions/{execution_id}/reject`\n\n```ts\nconst { data } = await client.rejectExecution(\n  {\n    execution_id: \'example\',\n  },\n  {\n    reason: \'string\'\n  },\n)\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "execution_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n  "agent_id": "skill:email-categorizer",\n  "agent_source": "system",\n  "agent_name": "string",\n  "execution_context": "flows",\n  "org_id": "string",\n  "status": "pending",\n  "input": {},\n  "parameters": {},\n  "result": {\n    "response": "string",\n    "structured_output": {}\n  },\n  "error": {\n    "code": "TIMEOUT",\n    "message": "string",\n    "details": {}\n  },\n  "pending_action": {\n    "tool": "string",\n    "input": {},\n    "description": "string",\n    "preview": {\n      "action": {\n        "type": "move",\n        "verb": "Move Thread"\n      },\n      "source": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "target": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "changes": [\n        {\n          "field": "string",\n          "label": "string",\n          "from": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          },\n          "to": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          }\n        }\n      ],\n      "metadata": {},\n      "summary": "This email discusses solar panel installation and should be handled by the Service team."\n    }\n  },\n  "metrics": {\n    "total_tokens": 0,\n    "input_tokens": 0,\n    "output_tokens": 0,\n    "total_cost_usd": 0,\n    "duration_ms": 0,\n    "iteration_count": 0\n  },\n  "started_at": "1970-01-01T00:00:00.000Z",\n  "completed_at": "1970-01-01T00:00:00.000Z",\n  "iterations": [\n    {\n      "index": 0,\n      "tool": "string",\n      "status": "running",\n      "timestamp": "1970-01-01T00:00:00.000Z"\n    }\n  ]\n}\n```\n\n</details>\n\n---\n\n### `streamExecution`\n\nReconnects to an execution\'s event stream after approval. Replays missed events from event log and continues streaming if execution is still running.\n\n`GET /v1/executions/{execution_id}/stream`\n\n```ts\nconst { data } = await client.streamExecution({\n  execution_id: \'example\',\n  from_sequence: 1,\n})\n```\n\n---\n\n### `chat`\n\nInitiates a streaming chat session with an AI agent. Supports server-side conversation memory via conversationId or client-provided history via clientHistory.\n\n`POST /v1/chat`\n\n```ts\nconst { data } = await client.chat(\n  null,\n  {\n    agentId: \'string\',\n    message: \'string\',\n    conversationId: \'3fa85f64-5717-4562-b3fc-2c963f66afa6\',\n    clientHistory: [\n      {\n        role: \'user\',\n        content: \'string\',\n        tool_calls: [\n          {\n            id: \'string\',\n            name: \'string\',\n            input: {},\n            output: \'string\'\n          }\n        ]\n      }\n    ],\n    context: {\n      entityId: \'string\',\n      customData: {}\n    },\n    streaming: {\n      mode: \'updates\',\n      streamTokens: false,\n      includeMetadata: false\n    }\n  },\n)\n```\n\n---\n\n### `listConversations`\n\nLists conversations for the authenticated user, sorted by most recent.\n\n`GET /v1/conversations`\n\n```ts\nconst { data } = await client.listConversations({\n  agent_id: \'example\',\n  limit: 1,\n  cursor: \'example\',\n})\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "conversations": [\n    {\n      "conversation_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n      "user_id": "string",\n      "agent_id": "string",\n      "title": "string",\n      "message_count": 0,\n      "last_message": "string",\n      "last_message_at": "1970-01-01T00:00:00.000Z",\n      "context": {\n        "entityId": "string",\n        "customData": {}\n      },\n      "created_at": "1970-01-01T00:00:00.000Z",\n      "updated_at": "1970-01-01T00:00:00.000Z"\n    }\n  ],\n  "next_cursor": "string"\n}\n```\n\n</details>\n\n---\n\n### `getConversation`\n\nRetrieves a conversation and its message history.\n\n`GET /v1/conversations/{conversation_id}`\n\n```ts\nconst { data } = await client.getConversation({\n  conversation_id: \'example\',\n  message_limit: 1,\n})\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "conversation": {\n    "conversation_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n    "user_id": "string",\n    "agent_id": "string",\n    "title": "string",\n    "message_count": 0,\n    "last_message": "string",\n    "last_message_at": "1970-01-01T00:00:00.000Z",\n    "context": {\n      "entityId": "string",\n      "customData": {}\n    },\n    "created_at": "1970-01-01T00:00:00.000Z",\n    "updated_at": "1970-01-01T00:00:00.000Z"\n  },\n  "messages": [\n    {\n      "conversation_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n      "role": "user",\n      "content": "string",\n      "timestamp": "1970-01-01T00:00:00.000Z",\n      "tool_calls": [\n        {\n          "id": "string",\n          "name": "string",\n          "input": {},\n          "output": "string"\n        }\n      ],\n      "token_count": 0,\n      "trace_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n      "feedback": {\n        "rating": "up",\n        "comment": "string",\n        "user_id": "string",\n        "submitted_at": "1970-01-01T00:00:00.000Z"\n      }\n    }\n  ]\n}\n```\n\n</details>\n\n---\n\n### `deleteConversation`\n\nDeletes a conversation and all its messages.\n\n`DELETE /v1/conversations/{conversation_id}`\n\n```ts\nconst { data } = await client.deleteConversation({\n  conversation_id: \'example\',\n})\n```\n\n---\n\n### `submitConversationFeedback`\n\nRecords a thumbs up/down (with optional comment) for the assistant turn identified by its Langfuse trace id. The rating is persisted on the message and mirrored to Langfuse as a trace score.\n\n`POST /v1/conversations/{conversation_id}/feedback`\n\n```ts\nconst { data } = await client.submitConversationFeedback(\n  {\n    conversation_id: \'example\',\n  },\n  {\n    trace_id: \'3fa85f64-5717-4562-b3fc-2c963f66afa6\',\n    rating: \'up\',\n    comment: \'string\'\n  },\n)\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "feedback": {\n    "rating": "up",\n    "comment": "string",\n    "user_id": "string",\n    "submitted_at": "1970-01-01T00:00:00.000Z"\n  }\n}\n```\n\n</details>\n\n---\n\n## Schemas\n\n### `AgentId`\n\nAgent identifier. Can be either:\n- System skill ID (prefixed): "skill:email-categorizer", "skill:email-labeler"\n- Custom agent UUID: "0336a235-9417-4dd8-894c-fe81285bba75"\n\n\n```ts\ntype AgentId = string\n```\n\n### `CreateAgentRequest`\n\n```ts\ntype CreateAgentRequest = {\n  name: string\n  description?: string\n  category?: "message" | "entity" | "document" | "classification" | "custom"\n  icon?: string\n  system_prompt: string\n  tools?: string[]\n  model_config?: {\n    model_id?: string\n    temperature?: number\n    max_tokens?: number\n    thinking?: boolean\n    thinking_budget?: number\n  }\n  max_iterations?: number\n  execution_pattern: "direct" | "react"\n  execution_mode?: "automatic" | "approval" | "draft"\n  output_schema?: object\n  input_parameters_schema?: {\n    type: "object"\n    parameters: Array<{\n      name: { ... }\n      label: { ... }\n      type: { ... }\n      description?: { ... }\n      default?: { ... }\n      multi?: { ... }\n      dependsOn?: { ... }\n      visibleWhen?: { ... }\n      enum?: { ... }\n      minimum?: { ... }\n      maximum?: { ... }\n      step?: { ... }\n      minLength?: { ... }\n      maxLength?: { ... }\n      schemaFilter?: { ... }\n      attributeTypeFilter?: { ... }\n      hidden?: { ... }\n    }>\n    required?: string[]\n  }\n}\n```\n\n### `UpdateAgentRequest`\n\n```ts\ntype UpdateAgentRequest = {\n  name?: string\n  description?: string\n  category?: "message" | "entity" | "document" | "classification" | "custom"\n  icon?: string\n  system_prompt?: string\n  tools?: string[]\n  model_config?: {\n    model_id?: string\n    temperature?: number\n    max_tokens?: number\n    thinking?: boolean\n    thinking_budget?: number\n  }\n  max_iterations?: number\n  execution_pattern?: "direct" | "react"\n  execution_mode?: "automatic" | "approval" | "draft"\n  output_schema?: object\n  input_parameters_schema?: {\n    type: "object"\n    parameters: Array<{\n      name: { ... }\n      label: { ... }\n      type: { ... }\n      description?: { ... }\n      default?: { ... }\n      multi?: { ... }\n      dependsOn?: { ... }\n      visibleWhen?: { ... }\n      enum?: { ... }\n      minimum?: { ... }\n      maximum?: { ... }\n      step?: { ... }\n      minLength?: { ... }\n      maxLength?: { ... }\n      schemaFilter?: { ... }\n      attributeTypeFilter?: { ... }\n      hidden?: { ... }\n    }>\n    required?: string[]\n  }\n}\n```\n\n### `AgentDefinition`\n\n```ts\ntype AgentDefinition = {\n  agent_id?: string\n  org_id?: string\n  name?: string\n  description?: string\n  category?: "message" | "entity" | "document" | "classification" | "custom"\n  icon?: string\n  source?: "system" | "custom"\n  availability?: "flows" | "copilot" | "portals" | "all"[]\n  allowed_entity_schemas?: string[]\n  system_prompt?: string\n  tools?: string[]\n  model_config?: {\n    model_id?: string\n    temperature?: number\n    max_tokens?: number\n    thinking?: boolean\n    thinking_budget?: number\n  }\n  max_iterations?: number\n  execution_pattern?: "direct" | "react"\n  execution_mode?: "automatic" | "approval" | "draft"\n  output_schema?: object\n  input_parameters_schema?: {\n    type: "object"\n    parameters: Array<{\n      name: { ... }\n      label: { ... }\n      type: { ... }\n      description?: { ... }\n      default?: { ... }\n      multi?: { ... }\n      dependsOn?: { ... }\n      visibleWhen?: { ... }\n      enum?: { ... }\n      minimum?: { ... }\n      maximum?: { ... }\n      step?: { ... }\n      minLength?: { ... }\n      maxLength?: { ... }\n      schemaFilter?: { ... }\n      attributeTypeFilter?: { ... }\n      hidden?: { ... }\n    }>\n    required?: string[]\n  }\n  version?: number\n  created_at?: string // date-time\n  updated_at?: string // date-time\n  created_by?: string\n}\n```\n\n### `ListAgentsResponse`\n\n```ts\ntype ListAgentsResponse = {\n  agents?: Array<{\n    agent_id?: string\n    org_id?: string\n    name?: string\n    description?: string\n    category?: "message" | "entity" | "document" | "classification" | "custom"\n    icon?: string\n    source?: "system" | "custom"\n    availability?: "flows" | "copilot" | "portals" | "all"[]\n    allowed_entity_schemas?: string[]\n    system_prompt?: string\n    tools?: string[]\n    model_config?: {\n      model_id?: { ... }\n      temperature?: { ... }\n      max_tokens?: { ... }\n      thinking?: { ... }\n      thinking_budget?: { ... }\n    }\n    max_iterations?: number\n    execution_pattern?: "direct" | "react"\n    execution_mode?: "automatic" | "approval" | "draft"\n    output_schema?: object\n    input_parameters_schema?: {\n      type: { ... }\n      parameters: { ... }\n      required?: { ... }\n    }\n    version?: number\n    created_at?: string // date-time\n    updated_at?: string // date-time\n    created_by?: string\n  }>\n  next_cursor?: string\n}\n```\n\n### `ListExecutionsResponse`\n\n```ts\ntype ListExecutionsResponse = {\n  executions?: Array<{\n    execution_id?: string // uuid\n    agent_id?: string\n    agent_source?: "system" | "custom"\n    agent_name?: string\n    execution_context?: "flows" | "copilot" | "api"\n    org_id?: string\n    status?: "pending" | "running" | "waiting_approval" | "completed" | "failed" | "cancelled"\n    input?: object\n    parameters?: object\n    result?: {\n      response?: { ... }\n      structured_output?: { ... }\n    }\n    error?: {\n      code?: { ... }\n      message?: { ... }\n      details?: { ... }\n    }\n    pending_action?: {\n      tool?: { ... }\n      input?: { ... }\n      description?: { ... }\n      preview?: { ... }\n    }\n    metrics?: {\n      total_tokens?: { ... }\n      input_tokens?: { ... }\n      output_tokens?: { ... }\n      total_cost_usd?: { ... }\n      duration_ms?: { ... }\n      iteration_count?: { ... }\n    }\n    started_at?: string // date-time\n    completed_at?: string // date-time\n    iterations?: Array<{\n      index?: { ... }\n      tool?: { ... }\n      status?: { ... }\n      timestamp?: { ... }\n    }>\n  }>\n  next_cursor?: string\n}\n```\n\n### `ApproveExecutionRequest`\n\n```ts\ntype ApproveExecutionRequest = {\n  reason?: string\n  approved_action_ids?: string[]\n  rejected_action_ids?: string[]\n}\n```\n\n### `RejectExecutionRequest`\n\n```ts\ntype RejectExecutionRequest = {\n  reason: string\n}\n```\n\n### `ExecuteAgentRequest`\n\n```ts\ntype ExecuteAgentRequest = {\n  input?: {\n    entity_id?: string\n    entity_schema?: string\n    workflow_id?: string\n    workflow_execution_id?: string\n    task_id?: string\n    custom_data?: Record<string, unknown>\n    flow_context?: Array<{\n      entity_id: { ... }\n      entity_schema: { ... }\n    }>\n  }\n  parameters?: Record<string, unknown>\n  execution_mode_override?: "automatic" | "approval" | "draft"\n  execution_context?: "flows" | "copilot" | "api"\n  callback_url?: string // uri\n  timeout_ms?: number\n}\n```\n\n### `ExecutionResponse`\n\n```ts\ntype ExecutionResponse = {\n  execution_id?: string // uuid\n  agent_id?: string\n  agent_source?: "system" | "custom"\n  agent_name?: string\n  execution_context?: "flows" | "copilot" | "api"\n  org_id?: string\n  status?: "pending" | "running" | "waiting_approval" | "completed" | "failed" | "cancelled"\n  input?: object\n  parameters?: object\n  result?: {\n    response?: string\n    structured_output?: object\n  }\n  error?: {\n    code?: "TIMEOUT" | "MAX_ITERATIONS_EXCEEDED" | "TOOL_EXECUTION_FAILED" | "LLM_ERROR" | "INVALID_OUTPUT" | "REJECTED" | "INTERNAL_ERROR"\n    message?: string\n    details?: object\n  }\n  pending_action?: {\n    tool?: string\n    input?: object\n    description?: string\n    preview?: {\n      action?: { ... }\n      source?: { ... }\n      target?: { ... }\n      changes?: { ... }\n      metadata?: { ... }\n      summary?: { ... }\n    }\n  }\n  metrics?: {\n    total_tokens?: number\n    input_tokens?: number\n    output_tokens?: number\n    total_cost_usd?: number\n    duration_ms?: number\n    iteration_count?: number\n  }\n  started_at?: string // date-time\n  completed_at?: string // date-time\n  iterations?: Array<{\n    index?: number\n    tool?: string\n    status?: "running" | "completed"\n    timestamp?: string // date-time\n  }>\n}\n```\n\n### `ExecutionIterationProjection`\n\n```ts\ntype ExecutionIterationProjection = {\n  index?: number\n  tool?: string\n  status?: "running" | "completed"\n  timestamp?: string // date-time\n}\n```\n\n### `ExecutionFeedback`\n\n```ts\ntype ExecutionFeedback = {\n  rating: "up" | "down"\n  comment?: string\n  user_id: string\n  submitted_at: string // date-time\n}\n```\n\n### `ExecutionFeedbackResponse`\n\n```ts\ntype ExecutionFeedbackResponse = {\n  feedback: {\n    rating: "up" | "down"\n    comment?: string\n    user_id: string\n    submitted_at: string // date-time\n  }\n}\n```\n\n### `PutExecutionFeedbackRequest`\n\n```ts\ntype PutExecutionFeedbackRequest = {\n  rating: "up" | "down"\n  comment?: string\n}\n```\n\n### `ExecutionTrace`\n\n```ts\ntype ExecutionTrace = {\n  execution_id?: string // uuid\n  iterations?: Array<{\n    iteration_index?: number\n    thought?: string\n    action?: {\n      tool?: { ... }\n      input?: { ... }\n    }\n    observation?: object\n    timestamp?: string // date-time\n    tokens_used?: number\n    latency_ms?: number\n  }>\n  total_iterations?: number\n}\n```\n\n### `ExecutionIteration`\n\n```ts\ntype ExecutionIteration = {\n  iteration_index?: number\n  thought?: string\n  action?: {\n    tool?: string\n    input?: object\n  }\n  observation?: object\n  timestamp?: string // date-time\n  tokens_used?: number\n  latency_ms?: number\n}\n```\n\n### `PendingAction`\n\nAction waiting for approval (when status=waiting_approval)\n\n```ts\ntype PendingAction = {\n  tool?: string\n  input?: object\n  description?: string\n  preview?: {\n    action?: {\n      type: { ... }\n      verb: { ... }\n    }\n    source?: {\n      type?: { ... }\n      id?: { ... }\n      name?: { ... }\n      schema?: { ... }\n      icon?: { ... }\n      url?: { ... }\n    }\n    target?: {\n      type?: { ... }\n      id?: { ... }\n      name?: { ... }\n      schema?: { ... }\n      icon?: { ... }\n      url?: { ... }\n    }\n    changes?: Array<{\n      field?: { ... }\n      label?: { ... }\n      from?: { ... }\n      to?: { ... }\n    }>\n    metadata?: Record<string, {\n      type: { ... }\n      value?: { ... }\n      values?: { ... }\n      id?: { ... }\n      name?: { ... }\n      schema?: { ... }\n      color?: { ... }\n    }>\n    summary?: string\n  }\n}\n```\n\n### `ExecutionError`\n\n```ts\ntype ExecutionError = {\n  code?: "TIMEOUT" | "MAX_ITERATIONS_EXCEEDED" | "TOOL_EXECUTION_FAILED" | "LLM_ERROR" | "INVALID_OUTPUT" | "REJECTED" | "INTERNAL_ERROR"\n  message?: string\n  details?: object\n}\n```\n\n### `ExecutionMetrics`\n\n```ts\ntype ExecutionMetrics = {\n  total_tokens?: number\n  input_tokens?: number\n  output_tokens?: number\n  total_cost_usd?: number\n  duration_ms?: number\n  iteration_count?: number\n}\n```\n\n### `AgentExecutionEventStatus`\n\nLifecycle status carried on an agent execution event.\n\nDeliberately narrower than `ExecutionStatus`, which is the stored status of\nthe execution row: `pending` and `running` both surface as `started`, and\n`cancelled` surfaces as `failed`. Consumers must not assume the two\nvocabularies are interchang\n\n```ts\ntype AgentExecutionEventStatus = "started" | "completed" | "failed" | "approval_required"\n```\n\n### `AgentExecutionEvent`\n\nDetail payload of the `agent-execution-status-update` event, published on\nthe AI Agents event bus with source `ai-agents`.\n\n`execution_context` and `input` are present on every status, so a consumer\ncan tell whether an execution is theirs, and what it belonged to, from the\nterminal event alone \u2014 wit\n\n```ts\ntype AgentExecutionEvent = {\n  executionId: string\n  agentId: string\n  orgId: string\n  userId?: string\n  execution_status: "started" | "completed" | "failed" | "approval_required"\n  execution_context?: "flows" | "copilot" | "api"\n  input?: Record<string, unknown>\n  output?: Record<string, unknown>\n  error?: {\n    message?: string\n    code?: string\n    stack?: string\n  }\n  duration?: number\n  iterations?: number\n  iteration?: number\n  message?: string\n  toolCalls?: Array<{\n    name?: string\n    args?: Record<string, unknown>\n  }>\n  timestamp?: string // date-time\n}\n```\n\n### `ToolPreview`\n\nStructured preview data for approval UI. Provides a generic format that any tool can populate.\n\n```ts\ntype ToolPreview = {\n  action?: {\n    type: "move" | "create" | "update" | "delete" | "apply" | "send" | "link" | "unlink" | "batch_approval"\n    verb: string\n  }\n  source?: {\n    type?: string\n    id?: string\n    name?: string\n    schema?: string\n    icon?: string\n    url?: string\n  }\n  target?: {\n    type?: string\n    id?: string\n    name?: string\n    schema?: string\n    icon?: string\n    url?: string\n  }\n  changes?: Array<{\n    field?: string\n    label?: string\n    from?: {\n      type: { ... }\n      value?: { ... }\n      values?: { ... }\n      id?: { ... }\n      name?: { ... }\n      schema?: { ... }\n      color?: { ... }\n    }\n    to?: {\n      type: { ... }\n      value?: { ... }\n      values?: { ... }\n      id?: { ... }\n      name?: { ... }\n      schema?: { ... }\n      color?: { ... }\n    }\n  }>\n  metadata?: Record<string, {\n    type: "text" | "number" | "boolean" | "list" | "entity" | "badge"\n    value?: unknown\n    values?: string[]\n    id?: string\n    name?: string\n    schema?: string\n    color?: "success" | "warning" | "error" | "info"\n  }>\n  summary?: string\n}\n```\n\n### `PreviewActionType`\n\nType of action being previewed\n\n```ts\ntype PreviewActionType = "move" | "create" | "update" | "delete" | "apply" | "send" | "link" | "unlink" | "batch_approval"\n```\n\n### `PreviewEntity`\n\nEntity reference for preview display\n\n```ts\ntype PreviewEntity = {\n  type?: string\n  id?: string\n  name?: string\n  schema?: string\n  icon?: string\n  url?: string\n}\n```\n\n### `PreviewChange`\n\nA single field change in the preview\n\n```ts\ntype PreviewChange = {\n  field?: string\n  label?: string\n  from?: {\n    type: "text" | "number" | "boolean" | "list" | "entity" | "badge"\n    value?: unknown\n    values?: string[]\n    id?: string\n    name?: string\n    schema?: string\n    color?: "success" | "warning" | "error" | "info"\n  }\n  to?: {\n    type: "text" | "number" | "boolean" | "list" | "entity" | "badge"\n    value?: unknown\n    values?: string[]\n    id?: string\n    name?: string\n    schema?: string\n    color?: "success" | "warning" | "error" | "info"\n  }\n}\n```\n\n### `PreviewValue`\n\nTyped value for preview display\n\n```ts\ntype PreviewValue = {\n  type: "text" | "number" | "boolean" | "list" | "entity" | "badge"\n  value?: unknown\n  values?: string[]\n  id?: string\n  name?: string\n  schema?: string\n  color?: "success" | "warning" | "error" | "info"\n}\n```\n\n### `ToolDefinition`\n\n```ts\ntype ToolDefinition = {\n  tool_id?: string\n  name?: string\n  description?: string\n  category?: "entity" | "message" | "taxonomy" | "rag" | "workflow"\n  parameters?: object\n  returns?: object\n  requires_approval?: boolean\n  enabled?: boolean\n}\n```\n\n### `SkillCategory`\n\n```ts\ntype SkillCategory = "message" | "entity" | "document" | "classification" | "custom"\n```\n\n### `AgentSource`\n\n- system: Pre-built by epilot (system skills)\n- custom: Created by organization\n\n\n```ts\ntype AgentSource = "system" | "custom"\n```\n\n### `SkillAvailability`\n\nWhere the skill/agent is available:\n- flows: Available in workflow automations\n- copilot: Available as a sub-agent in copilot\n- portals: Available in end-user self-service portals\n- all: Available everywhere\n\n\n```ts\ntype SkillAvailability = "flows" | "copilot" | "portals" | "all"\n```\n\n### `ExecutionContext`\n\nWhere the execution was triggered from:\n- flows: Triggered from workflow automation\n- copilot: Triggered from copilot assistant\n- api: Direct API call\n\n\n```ts\ntype ExecutionContext = "flows" | "copilot" | "api"\n```\n\n### `ExecutionPattern`\n\n- direct: Single LLM call, no tools\n- react: Multi-step reasoning with tool use\n\n\n```ts\ntype ExecutionPattern = "direct" | "react"\n```\n\n### `ExecutionMode`\n\n- automatic: Execute without human intervention\n- approval: Pause for human approval before tool execution\n- draft: Execute but mark output as draft for review\n\n\n```ts\ntype ExecutionMode = "automatic" | "approval" | "draft"\n```\n\n### `ExecutionStatus`\n\n```ts\ntype ExecutionStatus = "pending" | "running" | "waiting_approval" | "completed" | "failed" | "cancelled"\n```\n\n### `ParameterType`\n\nBase types:\n- text: Text input field\n- textarea: Multi-line text input field\n- number: Numeric input field\n- boolean: Toggle switch\n- select: Dropdown selection (requires enum array)\n\nCustom types (domain-specific):\n- entity-schema: Entity schema selector (fetches from Entity API)\n- entity-attribute\n\n```ts\ntype ParameterType = "text" | "textarea" | "number" | "boolean" | "select" | "entity-schema" | "entity-attribute" | "entity-id" | "taxonomy" | "taxonomy-classification" | "shared-inbox" | "label" | "matching-criteria"\n```\n\n### `InputParameterDefinition`\n\n```ts\ntype InputParameterDefinition = {\n  name: string\n  label: string\n  type: "text" | "textarea" | "number" | "boolean" | "select" | "entity-schema" | "entity-attribute" | "entity-id" | "taxonomy" | "taxonomy-classification" | "shared-inbox" | "label" | "matching-criteria"\n  description?: string\n  default?: unknown\n  multi?: boolean\n  dependsOn?: string\n  visibleWhen?: Record<string, unknown[]>\n  enum?: string[]\n  minimum?: number\n  maximum?: number\n  step?: number\n  minLength?: number\n  maxLength?: number\n  schemaFilter?: string[]\n  attributeTypeFilter?: string[]\n  hidden?: boolean\n}\n```\n\n### `InputParametersSchema`\n\n```ts\ntype InputParametersSchema = {\n  type: "object"\n  parameters: Array<{\n    name: string\n    label: string\n    type: "text" | "textarea" | "number" | "boolean" | "select" | "entity-schema" | "entity-attribute" | "entity-id" | "taxonomy" | "taxonomy-classification" | "shared-inbox" | "label" | "matching-criteria"\n    description?: string\n    default?: unknown\n    multi?: boolean\n    dependsOn?: string\n    visibleWhen?: Record<string, unknown[]>\n    enum?: string[]\n    minimum?: number\n    maximum?: number\n    step?: number\n    minLength?: number\n    maxLength?: number\n    schemaFilter?: string[]\n    attributeTypeFilter?: string[]\n    hidden?: boolean\n  }>\n  required?: string[]\n}\n```\n\n### `ModelConfig`\n\n```ts\ntype ModelConfig = {\n  model_id?: string\n  temperature?: number\n  max_tokens?: number\n  thinking?: boolean\n  thinking_budget?: number\n}\n```\n\n### `Error`\n\n```ts\ntype Error = {\n  error?: string\n  message?: string\n  details?: object\n}\n```\n\n### `ChatRequest`\n\n```ts\ntype ChatRequest = {\n  agentId: string\n  message: string\n  conversationId?: string // uuid\n  clientHistory?: Array<{\n    role: "user" | "assistant" | "tool" | "system"\n    content: string\n    tool_calls?: Array<{\n      id?: { ... }\n      name?: { ... }\n      input?: { ... }\n      output?: { ... }\n    }>\n  }>\n  context?: {\n    entityId?: string\n    customData?: Record<string, unknown>\n  }\n  streaming?: {\n    mode?: "updates" | "messages"\n    streamTokens?: boolean\n    includeMetadata?: boolean\n  }\n}\n```\n\n### `ChatMessage`\n\n```ts\ntype ChatMessage = {\n  role: "user" | "assistant" | "tool" | "system"\n  content: string\n  tool_calls?: Array<{\n    id?: string\n    name?: string\n    input?: object\n    output?: string\n  }>\n}\n```\n\n### `StreamingOptions`\n\n```ts\ntype StreamingOptions = {\n  mode?: "updates" | "messages"\n  streamTokens?: boolean\n  includeMetadata?: boolean\n}\n```\n\n### `StreamEvent`\n\nServer-Sent Event for streaming responses\n\n```ts\ntype StreamEvent = {\n  type?: "token" | "agent_step" | "tool_call" | "tool_result" | "complete" | "error" | "metadata" | "needs_approval"\n  content?: string\n  index?: number\n  tool?: string\n  input?: object\n  output?: string\n  callId?: string\n  result?: {\n    response?: string\n    structured_output?: object\n    status?: "completed" | "failed" | "max_iterations" | "rejected"\n    metrics?: {\n      total_tokens?: { ... }\n      input_tokens?: { ... }\n      output_tokens?: { ... }\n      total_cost_usd?: { ... }\n      duration_ms?: { ... }\n      iteration_count?: { ... }\n    }\n  }\n  error?: {\n    code?: string\n    message?: string\n  }\n  conversationId?: string // uuid\n}\n```\n\n### `ExecutionResult`\n\n```ts\ntype ExecutionResult = {\n  response?: string\n  structured_output?: object\n  status?: "completed" | "failed" | "max_iterations" | "rejected"\n  metrics?: {\n    total_tokens?: number\n    input_tokens?: number\n    output_tokens?: number\n    total_cost_usd?: number\n    duration_ms?: number\n    iteration_count?: number\n  }\n}\n```\n\n### `ConversationItem`\n\n```ts\ntype ConversationItem = {\n  conversation_id?: string // uuid\n  user_id?: string\n  agent_id?: string\n  title?: string\n  message_count?: number\n  last_message?: string\n  last_message_at?: string // date-time\n  context?: {\n    entityId?: string\n    customData?: object\n  }\n  created_at?: string // date-time\n  updated_at?: string // date-time\n}\n```\n\n### `MessageItem`\n\n```ts\ntype MessageItem = {\n  conversation_id?: string // uuid\n  role?: "user" | "assistant" | "tool" | "system"\n  content?: string\n  timestamp?: string // date-time\n  tool_calls?: Array<{\n    id?: string\n    name?: string\n    input?: object\n    output?: string\n  }>\n  token_count?: number\n  trace_id?: string // uuid\n  feedback?: {\n    rating: "up" | "down"\n    comment?: string\n    user_id: string\n    submitted_at: string // date-time\n  }\n}\n```\n\n### `MessageFeedback`\n\n```ts\ntype MessageFeedback = {\n  rating: "up" | "down"\n  comment?: string\n  user_id: string\n  submitted_at: string // date-time\n}\n```\n\n### `SubmitFeedbackRequest`\n\n```ts\ntype SubmitFeedbackRequest = {\n  trace_id: string // uuid\n  rating: "up" | "down"\n  comment?: string\n}\n```\n\n### `ListConversationsResponse`\n\n```ts\ntype ListConversationsResponse = {\n  conversations?: Array<{\n    conversation_id?: string // uuid\n    user_id?: string\n    agent_id?: string\n    title?: string\n    message_count?: number\n    last_message?: string\n    last_message_at?: string // date-time\n    context?: {\n      entityId?: { ... }\n      customData?: { ... }\n    }\n    created_at?: string // date-time\n    updated_at?: string // date-time\n  }>\n  next_cursor?: string\n}\n```\n\n### `ConversationWithMessages`\n\n```ts\ntype ConversationWithMessages = {\n  conversation?: {\n    conversation_id?: string // uuid\n    user_id?: string\n    agent_id?: string\n    title?: string\n    message_count?: number\n    last_message?: string\n    last_message_at?: string // date-time\n    context?: {\n      entityId?: { ... }\n      customData?: { ... }\n    }\n    created_at?: string // date-time\n    updated_at?: string // date-time\n  }\n  messages?: Array<{\n    conversation_id?: string // uuid\n    role?: "user" | "assistant" | "tool" | "system"\n    content?: string\n    timestamp?: string // date-time\n    tool_calls?: Array<{\n      id?: { ... }\n      name?: { ... }\n      input?: { ... }\n      output?: { ... }\n    }>\n    token_count?: number\n    trace_id?: string // uuid\n    feedback?: {\n      rating: { ... }\n      comment?: { ... }\n      user_id: { ... }\n      submitted_at: { ... }\n    }\n  }>\n}\n```\n';
-
-
-exports.default = ai_agents_default;

package/dist/ai-agents-MY4QE4CP.js

@@ -1,7 +0,0 @@
-import "./chunk-YPSWSI3M.js";
-
-// src/docs/ai-agents.json
-var ai_agents_default = '# AI Agents API\n\n- **Base URL:** `https://ai-agents.sls.epilot.io`\n- **Full API Docs:** [https://docs.epilot.io/api/ai-agents](https://docs.epilot.io/api/ai-agents)\n\n## Usage\n\n```ts\nimport { epilot } from \'@epilot/sdk\'\n\nepilot.authorize(() => \'<token>\')\nconst { data } = await epilot.aiAgents.createAgent(...)\n```\n\n### Tree-shakeable import\n\n```ts\nimport { getClient, authorize } from \'@epilot/sdk/ai-agents\'\n\nconst aiAgentsClient = getClient()\nauthorize(aiAgentsClient, () => \'<token>\')\nconst { data } = await aiAgentsClient.createAgent(...)\n```\n\n## Operations\n\n**Agents Configuration**\n- [`createAgent`](#createagent)\n- [`listAgents`](#listagents)\n- [`getAgentById`](#getagentbyid)\n- [`updateAgentById`](#updateagentbyid)\n- [`deleteAgentById`](#deleteagentbyid)\n\n**Agent Execution**\n- [`executeAgent`](#executeagent)\n- [`executeAgentStream`](#executeagentstream)\n- [`listExecutions`](#listexecutions)\n- [`getExecution`](#getexecution)\n- [`cancelExecution`](#cancelexecution)\n- [`getExecutionTrace`](#getexecutiontrace)\n- [`getExecutionFeedback`](#getexecutionfeedback)\n- [`putExecutionFeedback`](#putexecutionfeedback)\n- [`approveExecution`](#approveexecution)\n- [`rejectExecution`](#rejectexecution)\n- [`streamExecution`](#streamexecution)\n\n**Chat**\n- [`chat`](#chat)\n\n**Conversations**\n- [`listConversations`](#listconversations)\n- [`getConversation`](#getconversation)\n- [`deleteConversation`](#deleteconversation)\n- [`submitConversationFeedback`](#submitconversationfeedback)\n\n**Schemas**\n- [`AgentId`](#agentid)\n- [`CreateAgentRequest`](#createagentrequest)\n- [`UpdateAgentRequest`](#updateagentrequest)\n- [`AgentDefinition`](#agentdefinition)\n- [`ListAgentsResponse`](#listagentsresponse)\n- [`ListExecutionsResponse`](#listexecutionsresponse)\n- [`ApproveExecutionRequest`](#approveexecutionrequest)\n- [`RejectExecutionRequest`](#rejectexecutionrequest)\n- [`ExecuteAgentRequest`](#executeagentrequest)\n- [`ExecutionResponse`](#executionresponse)\n- [`ExecutionIterationProjection`](#executioniterationprojection)\n- [`ExecutionFeedback`](#executionfeedback)\n- [`ExecutionFeedbackResponse`](#executionfeedbackresponse)\n- [`PutExecutionFeedbackRequest`](#putexecutionfeedbackrequest)\n- [`ExecutionTrace`](#executiontrace)\n- [`ExecutionIteration`](#executioniteration)\n- [`PendingAction`](#pendingaction)\n- [`ExecutionError`](#executionerror)\n- [`ExecutionMetrics`](#executionmetrics)\n- [`AgentExecutionEventStatus`](#agentexecutioneventstatus)\n- [`AgentExecutionEvent`](#agentexecutionevent)\n- [`ToolPreview`](#toolpreview)\n- [`PreviewActionType`](#previewactiontype)\n- [`PreviewEntity`](#previewentity)\n- [`PreviewChange`](#previewchange)\n- [`PreviewValue`](#previewvalue)\n- [`ToolDefinition`](#tooldefinition)\n- [`SkillCategory`](#skillcategory)\n- [`AgentSource`](#agentsource)\n- [`SkillAvailability`](#skillavailability)\n- [`ExecutionContext`](#executioncontext)\n- [`ExecutionPattern`](#executionpattern)\n- [`ExecutionMode`](#executionmode)\n- [`ExecutionStatus`](#executionstatus)\n- [`ParameterType`](#parametertype)\n- [`InputParameterDefinition`](#inputparameterdefinition)\n- [`InputParametersSchema`](#inputparametersschema)\n- [`ModelConfig`](#modelconfig)\n- [`Error`](#error)\n- [`ChatRequest`](#chatrequest)\n- [`ChatMessage`](#chatmessage)\n- [`StreamingOptions`](#streamingoptions)\n- [`StreamEvent`](#streamevent)\n- [`ExecutionResult`](#executionresult)\n- [`ConversationItem`](#conversationitem)\n- [`MessageItem`](#messageitem)\n- [`MessageFeedback`](#messagefeedback)\n- [`SubmitFeedbackRequest`](#submitfeedbackrequest)\n- [`ListConversationsResponse`](#listconversationsresponse)\n- [`ConversationWithMessages`](#conversationwithmessages)\n\n### `createAgent`\n\nCreates a new custom agent. System skills cannot be created via this endpoint.\n\n`POST /v1/agents`\n\n```ts\nconst { data } = await client.createAgent(\n  null,\n  {\n    name: \'Email Reply Generator\',\n    description: \'string\',\n    category: \'message\',\n    icon: \'mail-reply\',\n    system_prompt: \'string\',\n    tools: [\'entity.search\', \'message.draft\'],\n    model_config: {\n      model_id: \'anthropic.claude-3-5-sonnet-20241022-v2:0\',\n      temperature: 0.7,\n      max_tokens: 4096,\n      thinking: false,\n      thinking_budget: 10000\n    },\n    max_iterations: 10,\n    execution_pattern: \'direct\',\n    execution_mode: \'automatic\',\n    output_schema: {},\n    input_parameters_schema: {\n      type: \'object\',\n      parameters: [\n        {\n          name: \'target_schema\',\n          label: \'Target Schema\',\n          type: \'entity-schema\',\n          description: \'Entity type to create\'\n        },\n        {\n          name: \'confidence_threshold\',\n          label: \'Confidence Threshold\',\n          type: \'number\',\n          minimum: 0,\n          maximum: 1,\n          default: 0.8\n        },\n        /* ... 1 more */\n      ],\n      required: [\'target_schema\']\n    }\n  },\n)\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "agent_id": "skill:email-categorizer",\n  "org_id": "string",\n  "name": "string",\n  "description": "string",\n  "category": "message",\n  "icon": "string",\n  "source": "system",\n  "availability": ["flows", "copilot"],\n  "allowed_entity_schemas": ["message"],\n  "system_prompt": "string",\n  "tools": ["string"],\n  "model_config": {\n    "model_id": "anthropic.claude-3-5-sonnet-20241022-v2:0",\n    "temperature": 0.7,\n    "max_tokens": 4096,\n    "thinking": false,\n    "thinking_budget": 10000\n  },\n  "max_iterations": 0,\n  "execution_pattern": "direct",\n  "execution_mode": "automatic",\n  "output_schema": {},\n  "input_parameters_schema": {\n    "type": "object",\n    "parameters": [\n      {\n        "name": "target_schema",\n        "label": "Target Schema",\n        "type": "entity-schema",\n        "description": "Entity type to create"\n      },\n      {\n        "name": "confidence_threshold",\n        "label": "Confidence Threshold",\n        "type": "number",\n        "minimum": 0,\n        "maximum": 1,\n        "default": 0.8\n      }\n    ],\n    "required": ["target_schema"]\n  },\n  "version": 0,\n  "created_at": "1970-01-01T00:00:00.000Z",\n  "updated_at": "1970-01-01T00:00:00.000Z",\n  "created_by": "string"\n}\n```\n\n</details>\n\n---\n\n### `listAgents`\n\nLists agents from both system skills and custom agents.\nUse query parameters to filter by source, availability, or entity schema.\n\n`GET /v1/agents`\n\n```ts\nconst { data } = await client.listAgents({\n  source: \'example\',\n  availability: \'example\',\n  entity_schema: \'example\',\n})\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "agents": [\n    {\n      "agent_id": "skill:email-categorizer",\n      "org_id": "string",\n      "name": "string",\n      "description": "string",\n      "category": "message",\n      "icon": "string",\n      "source": "system",\n      "availability": ["flows", "copilot"],\n      "allowed_entity_schemas": ["message"],\n      "system_prompt": "string",\n      "tools": ["string"],\n      "model_config": {\n        "model_id": "anthropic.claude-3-5-sonnet-20241022-v2:0",\n        "temperature": 0.7,\n        "max_tokens": 4096,\n        "thinking": false,\n        "thinking_budget": 10000\n      },\n      "max_iterations": 0,\n      "execution_pattern": "direct",\n      "execution_mode": "automatic",\n      "output_schema": {},\n      "input_parameters_schema": {\n        "type": "object",\n        "parameters": [\n          {\n            "name": "target_schema",\n            "label": "Target Schema",\n            "type": "entity-schema",\n            "description": "Entity type to create"\n          },\n          {\n            "name": "confidence_threshold",\n            "label": "Confidence Threshold",\n            "type": "number",\n            "minimum": 0,\n            "maximum": 1,\n            "default": 0.8\n          }\n        ],\n        "required": ["target_schema"]\n      },\n      "version": 0,\n      "created_at": "1970-01-01T00:00:00.000Z",\n      "updated_at": "1970-01-01T00:00:00.000Z",\n      "created_by": "string"\n    }\n  ],\n  "next_cursor": "string"\n}\n```\n\n</details>\n\n---\n\n### `getAgentById`\n\nRetrieves an agent by ID. Supports both:\n- System skill IDs (prefixed): "skill:email-categorizer"\n- Custom agent IDs (UUID): "0336a235-9417-4dd8-894c-fe81285bba75"\n\n`GET /v1/agents/{agent_id}`\n\n```ts\nconst { data } = await client.getAgentById({\n  agent_id: \'example\',\n})\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "agent_id": "skill:email-categorizer",\n  "org_id": "string",\n  "name": "string",\n  "description": "string",\n  "category": "message",\n  "icon": "string",\n  "source": "system",\n  "availability": ["flows", "copilot"],\n  "allowed_entity_schemas": ["message"],\n  "system_prompt": "string",\n  "tools": ["string"],\n  "model_config": {\n    "model_id": "anthropic.claude-3-5-sonnet-20241022-v2:0",\n    "temperature": 0.7,\n    "max_tokens": 4096,\n    "thinking": false,\n    "thinking_budget": 10000\n  },\n  "max_iterations": 0,\n  "execution_pattern": "direct",\n  "execution_mode": "automatic",\n  "output_schema": {},\n  "input_parameters_schema": {\n    "type": "object",\n    "parameters": [\n      {\n        "name": "target_schema",\n        "label": "Target Schema",\n        "type": "entity-schema",\n        "description": "Entity type to create"\n      },\n      {\n        "name": "confidence_threshold",\n        "label": "Confidence Threshold",\n        "type": "number",\n        "minimum": 0,\n        "maximum": 1,\n        "default": 0.8\n      }\n    ],\n    "required": ["target_schema"]\n  },\n  "version": 0,\n  "created_at": "1970-01-01T00:00:00.000Z",\n  "updated_at": "1970-01-01T00:00:00.000Z",\n  "created_by": "string"\n}\n```\n\n</details>\n\n---\n\n### `updateAgentById`\n\nUpdates a custom agent. System skills cannot be updated via this endpoint.\n\n`PUT /v1/agents/{agent_id}`\n\n```ts\nconst { data } = await client.updateAgentById(\n  {\n    agent_id: \'example\',\n  },\n  {\n    name: \'string\',\n    description: \'string\',\n    category: \'message\',\n    icon: \'string\',\n    system_prompt: \'string\',\n    tools: [\'string\'],\n    model_config: {\n      model_id: \'anthropic.claude-3-5-sonnet-20241022-v2:0\',\n      temperature: 0.7,\n      max_tokens: 4096,\n      thinking: false,\n      thinking_budget: 10000\n    },\n    max_iterations: 1,\n    execution_pattern: \'direct\',\n    execution_mode: \'automatic\',\n    output_schema: {},\n    input_parameters_schema: {\n      type: \'object\',\n      parameters: [\n        {\n          name: \'target_schema\',\n          label: \'Target Schema\',\n          type: \'entity-schema\',\n          description: \'Entity type to create\'\n        },\n        {\n          name: \'confidence_threshold\',\n          label: \'Confidence Threshold\',\n          type: \'number\',\n          minimum: 0,\n          maximum: 1,\n          default: 0.8\n        },\n        /* ... 1 more */\n      ],\n      required: [\'target_schema\']\n    }\n  },\n)\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "agent_id": "skill:email-categorizer",\n  "org_id": "string",\n  "name": "string",\n  "description": "string",\n  "category": "message",\n  "icon": "string",\n  "source": "system",\n  "availability": ["flows", "copilot"],\n  "allowed_entity_schemas": ["message"],\n  "system_prompt": "string",\n  "tools": ["string"],\n  "model_config": {\n    "model_id": "anthropic.claude-3-5-sonnet-20241022-v2:0",\n    "temperature": 0.7,\n    "max_tokens": 4096,\n    "thinking": false,\n    "thinking_budget": 10000\n  },\n  "max_iterations": 0,\n  "execution_pattern": "direct",\n  "execution_mode": "automatic",\n  "output_schema": {},\n  "input_parameters_schema": {\n    "type": "object",\n    "parameters": [\n      {\n        "name": "target_schema",\n        "label": "Target Schema",\n        "type": "entity-schema",\n        "description": "Entity type to create"\n      },\n      {\n        "name": "confidence_threshold",\n        "label": "Confidence Threshold",\n        "type": "number",\n        "minimum": 0,\n        "maximum": 1,\n        "default": 0.8\n      }\n    ],\n    "required": ["target_schema"]\n  },\n  "version": 0,\n  "created_at": "1970-01-01T00:00:00.000Z",\n  "updated_at": "1970-01-01T00:00:00.000Z",\n  "created_by": "string"\n}\n```\n\n</details>\n\n---\n\n### `deleteAgentById`\n\nDeletes a custom agent. System skills cannot be deleted via this endpoint.\n\n`DELETE /v1/agents/{agent_id}`\n\n```ts\nconst { data } = await client.deleteAgentById({\n  agent_id: \'example\',\n})\n```\n\n---\n\n### `executeAgent`\n\nExecutes an agent (system skill or custom agent).\nSupports both:\n- System skill IDs (prefixed): "skill:email-categorizer"\n- Custom agent IDs (UUID): "0336a235-9417-4dd8-894c-fe81285bba75"\n\n`POST /v1/agents/{agent_id}/execute`\n\n```ts\nconst { data } = await client.executeAgent(\n  {\n    agent_id: \'example\',\n  },\n  {\n    input: {\n      entity_id: \'string\',\n      entity_schema: \'string\',\n      workflow_id: \'string\',\n      workflow_execution_id: \'string\',\n      task_id: \'string\',\n      custom_data: {},\n      flow_context: [\n        {\n          entity_id: \'string\',\n          entity_schema: \'string\'\n        }\n      ]\n    },\n    parameters: {},\n    execution_mode_override: \'automatic\',\n    execution_context: \'flows\',\n    callback_url: \'https://example.com/path\',\n    timeout_ms: 30000\n  },\n)\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "execution_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n  "agent_id": "skill:email-categorizer",\n  "agent_source": "system",\n  "agent_name": "string",\n  "execution_context": "flows",\n  "org_id": "string",\n  "status": "pending",\n  "input": {},\n  "parameters": {},\n  "result": {\n    "response": "string",\n    "structured_output": {}\n  },\n  "error": {\n    "code": "TIMEOUT",\n    "message": "string",\n    "details": {}\n  },\n  "pending_action": {\n    "tool": "string",\n    "input": {},\n    "description": "string",\n    "preview": {\n      "action": {\n        "type": "move",\n        "verb": "Move Thread"\n      },\n      "source": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "target": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "changes": [\n        {\n          "field": "string",\n          "label": "string",\n          "from": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          },\n          "to": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          }\n        }\n      ],\n      "metadata": {},\n      "summary": "This email discusses solar panel installation and should be handled by the Service team."\n    }\n  },\n  "metrics": {\n    "total_tokens": 0,\n    "input_tokens": 0,\n    "output_tokens": 0,\n    "total_cost_usd": 0,\n    "duration_ms": 0,\n    "iteration_count": 0\n  },\n  "started_at": "1970-01-01T00:00:00.000Z",\n  "completed_at": "1970-01-01T00:00:00.000Z",\n  "iterations": [\n    {\n      "index": 0,\n      "tool": "string",\n      "status": "running",\n      "timestamp": "1970-01-01T00:00:00.000Z"\n    }\n  ]\n}\n```\n\n</details>\n\n---\n\n### `executeAgentStream`\n\nExecutes an agent with real-time streaming of tokens and tool events.\nReturns Server-Sent Events (SSE) stream with token-by-token output,\ntool call progress, and completion status.\n\n`POST /v1/agents/{agent_id}/execute/stream`\n\n```ts\nconst { data } = await client.executeAgentStream(\n  {\n    agent_id: \'example\',\n  },\n  {\n    input: {\n      entity_id: \'string\',\n      entity_schema: \'string\',\n      workflow_id: \'string\',\n      workflow_execution_id: \'string\',\n      task_id: \'string\',\n      custom_data: {},\n      flow_context: [\n        {\n          entity_id: \'string\',\n          entity_schema: \'string\'\n        }\n      ]\n    },\n    parameters: {},\n    execution_mode_override: \'automatic\',\n    execution_context: \'flows\',\n    callback_url: \'https://example.com/path\',\n    timeout_ms: 30000\n  },\n)\n```\n\n---\n\n### `listExecutions`\n\nList executions\n\n`GET /v1/executions`\n\n```ts\nconst { data } = await client.listExecutions({\n  agent_id: \'example\',\n  status: \'example\',\n  limit: 1,\n})\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "executions": [\n    {\n      "execution_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n      "agent_id": "skill:email-categorizer",\n      "agent_source": "system",\n      "agent_name": "string",\n      "execution_context": "flows",\n      "org_id": "string",\n      "status": "pending",\n      "input": {},\n      "parameters": {},\n      "result": {\n        "response": "string",\n        "structured_output": {}\n      },\n      "error": {\n        "code": "TIMEOUT",\n        "message": "string",\n        "details": {}\n      },\n      "pending_action": {\n        "tool": "string",\n        "input": {},\n        "description": "string",\n        "preview": {\n          "action": {\n            "type": "move",\n            "verb": "Move Thread"\n          },\n          "source": {\n            "type": "inbox",\n            "id": "string",\n            "name": "Support Inbox",\n            "schema": "string",\n            "icon": "string",\n            "url": "string"\n          },\n          "target": {\n            "type": "inbox",\n            "id": "string",\n            "name": "Support Inbox",\n            "schema": "string",\n            "icon": "string",\n            "url": "string"\n          },\n          "changes": [\n            {\n              "field": "string",\n              "label": "string",\n              "from": {\n                "type": "text",\n                "value": {},\n                "values": ["string"],\n                "id": "string",\n                "name": "string",\n                "schema": "string",\n                "color": "success"\n              },\n              "to": {\n                "type": "text",\n                "value": {},\n                "values": ["string"],\n                "id": "string",\n                "name": "string",\n                "schema": "string",\n                "color": "success"\n              }\n            }\n          ],\n          "metadata": {},\n          "summary": "This email discusses solar panel installation and should be handled by the Service team."\n        }\n      },\n      "metrics": {\n        "total_tokens": 0,\n        "input_tokens": 0,\n        "output_tokens": 0,\n        "total_cost_usd": 0,\n        "duration_ms": 0,\n        "iteration_count": 0\n      },\n      "started_at": "1970-01-01T00:00:00.000Z",\n      "completed_at": "1970-01-01T00:00:00.000Z",\n      "iterations": [\n        {\n          "index": 0,\n          "tool": "string",\n          "status": "running",\n          "timestamp": "1970-01-01T00:00:00.000Z"\n        }\n      ]\n    }\n  ],\n  "next_cursor": "string"\n}\n```\n\n</details>\n\n---\n\n### `getExecution`\n\nGet execution by ID\n\n`GET /v1/executions/{execution_id}`\n\n```ts\nconst { data } = await client.getExecution({\n  execution_id: \'example\',\n})\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "execution_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n  "agent_id": "skill:email-categorizer",\n  "agent_source": "system",\n  "agent_name": "string",\n  "execution_context": "flows",\n  "org_id": "string",\n  "status": "pending",\n  "input": {},\n  "parameters": {},\n  "result": {\n    "response": "string",\n    "structured_output": {}\n  },\n  "error": {\n    "code": "TIMEOUT",\n    "message": "string",\n    "details": {}\n  },\n  "pending_action": {\n    "tool": "string",\n    "input": {},\n    "description": "string",\n    "preview": {\n      "action": {\n        "type": "move",\n        "verb": "Move Thread"\n      },\n      "source": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "target": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "changes": [\n        {\n          "field": "string",\n          "label": "string",\n          "from": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          },\n          "to": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          }\n        }\n      ],\n      "metadata": {},\n      "summary": "This email discusses solar panel installation and should be handled by the Service team."\n    }\n  },\n  "metrics": {\n    "total_tokens": 0,\n    "input_tokens": 0,\n    "output_tokens": 0,\n    "total_cost_usd": 0,\n    "duration_ms": 0,\n    "iteration_count": 0\n  },\n  "started_at": "1970-01-01T00:00:00.000Z",\n  "completed_at": "1970-01-01T00:00:00.000Z",\n  "iterations": [\n    {\n      "index": 0,\n      "tool": "string",\n      "status": "running",\n      "timestamp": "1970-01-01T00:00:00.000Z"\n    }\n  ]\n}\n```\n\n</details>\n\n---\n\n### `cancelExecution`\n\nCancel execution\n\n`DELETE /v1/executions/{execution_id}`\n\n```ts\nconst { data } = await client.cancelExecution({\n  execution_id: \'example\',\n})\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "execution_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n  "agent_id": "skill:email-categorizer",\n  "agent_source": "system",\n  "agent_name": "string",\n  "execution_context": "flows",\n  "org_id": "string",\n  "status": "pending",\n  "input": {},\n  "parameters": {},\n  "result": {\n    "response": "string",\n    "structured_output": {}\n  },\n  "error": {\n    "code": "TIMEOUT",\n    "message": "string",\n    "details": {}\n  },\n  "pending_action": {\n    "tool": "string",\n    "input": {},\n    "description": "string",\n    "preview": {\n      "action": {\n        "type": "move",\n        "verb": "Move Thread"\n      },\n      "source": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "target": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "changes": [\n        {\n          "field": "string",\n          "label": "string",\n          "from": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          },\n          "to": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          }\n        }\n      ],\n      "metadata": {},\n      "summary": "This email discusses solar panel installation and should be handled by the Service team."\n    }\n  },\n  "metrics": {\n    "total_tokens": 0,\n    "input_tokens": 0,\n    "output_tokens": 0,\n    "total_cost_usd": 0,\n    "duration_ms": 0,\n    "iteration_count": 0\n  },\n  "started_at": "1970-01-01T00:00:00.000Z",\n  "completed_at": "1970-01-01T00:00:00.000Z",\n  "iterations": [\n    {\n      "index": 0,\n      "tool": "string",\n      "status": "running",\n      "timestamp": "1970-01-01T00:00:00.000Z"\n    }\n  ]\n}\n```\n\n</details>\n\n---\n\n### `getExecutionTrace`\n\nReturns the step-by-step reasoning and tool calls for ReAct mode executions. Returns empty iterations array for direct mode executions.\n\n`GET /v1/executions/{execution_id}/trace`\n\n```ts\nconst { data } = await client.getExecutionTrace({\n  execution_id: \'example\',\n})\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "execution_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n  "iterations": [\n    {\n      "iteration_index": 0,\n      "thought": "string",\n      "action": {\n        "tool": "string",\n        "input": {}\n      },\n      "observation": {},\n      "timestamp": "1970-01-01T00:00:00.000Z",\n      "tokens_used": 0,\n      "latency_ms": 0\n    }\n  ],\n  "total_iterations": 0\n}\n```\n\n</details>\n\n---\n\n### `getExecutionFeedback`\n\nGet execution feedback\n\n`GET /v1/executions/{execution_id}/feedback`\n\n```ts\nconst { data } = await client.getExecutionFeedback({\n  execution_id: \'example\',\n})\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "feedback": {\n    "rating": "up",\n    "comment": "string",\n    "user_id": "string",\n    "submitted_at": "1970-01-01T00:00:00.000Z"\n  }\n}\n```\n\n</details>\n\n---\n\n### `putExecutionFeedback`\n\nSubmit execution feedback\n\n`PUT /v1/executions/{execution_id}/feedback`\n\n```ts\nconst { data } = await client.putExecutionFeedback(\n  {\n    execution_id: \'example\',\n  },\n  {\n    rating: \'up\',\n    comment: \'string\'\n  },\n)\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "feedback": {\n    "rating": "up",\n    "comment": "string",\n    "user_id": "string",\n    "submitted_at": "1970-01-01T00:00:00.000Z"\n  }\n}\n```\n\n</details>\n\n---\n\n### `approveExecution`\n\nApproves a pending tool action when execution is in waiting_approval status\n\n`POST /v1/executions/{execution_id}/approve`\n\n```ts\nconst { data } = await client.approveExecution(\n  {\n    execution_id: \'example\',\n  },\n  {\n    reason: \'string\',\n    approved_action_ids: [\'string\'],\n    rejected_action_ids: [\'string\']\n  },\n)\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "execution_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n  "agent_id": "skill:email-categorizer",\n  "agent_source": "system",\n  "agent_name": "string",\n  "execution_context": "flows",\n  "org_id": "string",\n  "status": "pending",\n  "input": {},\n  "parameters": {},\n  "result": {\n    "response": "string",\n    "structured_output": {}\n  },\n  "error": {\n    "code": "TIMEOUT",\n    "message": "string",\n    "details": {}\n  },\n  "pending_action": {\n    "tool": "string",\n    "input": {},\n    "description": "string",\n    "preview": {\n      "action": {\n        "type": "move",\n        "verb": "Move Thread"\n      },\n      "source": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "target": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "changes": [\n        {\n          "field": "string",\n          "label": "string",\n          "from": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          },\n          "to": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          }\n        }\n      ],\n      "metadata": {},\n      "summary": "This email discusses solar panel installation and should be handled by the Service team."\n    }\n  },\n  "metrics": {\n    "total_tokens": 0,\n    "input_tokens": 0,\n    "output_tokens": 0,\n    "total_cost_usd": 0,\n    "duration_ms": 0,\n    "iteration_count": 0\n  },\n  "started_at": "1970-01-01T00:00:00.000Z",\n  "completed_at": "1970-01-01T00:00:00.000Z",\n  "iterations": [\n    {\n      "index": 0,\n      "tool": "string",\n      "status": "running",\n      "timestamp": "1970-01-01T00:00:00.000Z"\n    }\n  ]\n}\n```\n\n</details>\n\n---\n\n### `rejectExecution`\n\nRejects a pending tool action when execution is in waiting_approval status\n\n`POST /v1/executions/{execution_id}/reject`\n\n```ts\nconst { data } = await client.rejectExecution(\n  {\n    execution_id: \'example\',\n  },\n  {\n    reason: \'string\'\n  },\n)\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "execution_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n  "agent_id": "skill:email-categorizer",\n  "agent_source": "system",\n  "agent_name": "string",\n  "execution_context": "flows",\n  "org_id": "string",\n  "status": "pending",\n  "input": {},\n  "parameters": {},\n  "result": {\n    "response": "string",\n    "structured_output": {}\n  },\n  "error": {\n    "code": "TIMEOUT",\n    "message": "string",\n    "details": {}\n  },\n  "pending_action": {\n    "tool": "string",\n    "input": {},\n    "description": "string",\n    "preview": {\n      "action": {\n        "type": "move",\n        "verb": "Move Thread"\n      },\n      "source": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "target": {\n        "type": "inbox",\n        "id": "string",\n        "name": "Support Inbox",\n        "schema": "string",\n        "icon": "string",\n        "url": "string"\n      },\n      "changes": [\n        {\n          "field": "string",\n          "label": "string",\n          "from": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          },\n          "to": {\n            "type": "text",\n            "value": {},\n            "values": ["string"],\n            "id": "string",\n            "name": "string",\n            "schema": "string",\n            "color": "success"\n          }\n        }\n      ],\n      "metadata": {},\n      "summary": "This email discusses solar panel installation and should be handled by the Service team."\n    }\n  },\n  "metrics": {\n    "total_tokens": 0,\n    "input_tokens": 0,\n    "output_tokens": 0,\n    "total_cost_usd": 0,\n    "duration_ms": 0,\n    "iteration_count": 0\n  },\n  "started_at": "1970-01-01T00:00:00.000Z",\n  "completed_at": "1970-01-01T00:00:00.000Z",\n  "iterations": [\n    {\n      "index": 0,\n      "tool": "string",\n      "status": "running",\n      "timestamp": "1970-01-01T00:00:00.000Z"\n    }\n  ]\n}\n```\n\n</details>\n\n---\n\n### `streamExecution`\n\nReconnects to an execution\'s event stream after approval. Replays missed events from event log and continues streaming if execution is still running.\n\n`GET /v1/executions/{execution_id}/stream`\n\n```ts\nconst { data } = await client.streamExecution({\n  execution_id: \'example\',\n  from_sequence: 1,\n})\n```\n\n---\n\n### `chat`\n\nInitiates a streaming chat session with an AI agent. Supports server-side conversation memory via conversationId or client-provided history via clientHistory.\n\n`POST /v1/chat`\n\n```ts\nconst { data } = await client.chat(\n  null,\n  {\n    agentId: \'string\',\n    message: \'string\',\n    conversationId: \'3fa85f64-5717-4562-b3fc-2c963f66afa6\',\n    clientHistory: [\n      {\n        role: \'user\',\n        content: \'string\',\n        tool_calls: [\n          {\n            id: \'string\',\n            name: \'string\',\n            input: {},\n            output: \'string\'\n          }\n        ]\n      }\n    ],\n    context: {\n      entityId: \'string\',\n      customData: {}\n    },\n    streaming: {\n      mode: \'updates\',\n      streamTokens: false,\n      includeMetadata: false\n    }\n  },\n)\n```\n\n---\n\n### `listConversations`\n\nLists conversations for the authenticated user, sorted by most recent.\n\n`GET /v1/conversations`\n\n```ts\nconst { data } = await client.listConversations({\n  agent_id: \'example\',\n  limit: 1,\n  cursor: \'example\',\n})\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "conversations": [\n    {\n      "conversation_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n      "user_id": "string",\n      "agent_id": "string",\n      "title": "string",\n      "message_count": 0,\n      "last_message": "string",\n      "last_message_at": "1970-01-01T00:00:00.000Z",\n      "context": {\n        "entityId": "string",\n        "customData": {}\n      },\n      "created_at": "1970-01-01T00:00:00.000Z",\n      "updated_at": "1970-01-01T00:00:00.000Z"\n    }\n  ],\n  "next_cursor": "string"\n}\n```\n\n</details>\n\n---\n\n### `getConversation`\n\nRetrieves a conversation and its message history.\n\n`GET /v1/conversations/{conversation_id}`\n\n```ts\nconst { data } = await client.getConversation({\n  conversation_id: \'example\',\n  message_limit: 1,\n})\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "conversation": {\n    "conversation_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n    "user_id": "string",\n    "agent_id": "string",\n    "title": "string",\n    "message_count": 0,\n    "last_message": "string",\n    "last_message_at": "1970-01-01T00:00:00.000Z",\n    "context": {\n      "entityId": "string",\n      "customData": {}\n    },\n    "created_at": "1970-01-01T00:00:00.000Z",\n    "updated_at": "1970-01-01T00:00:00.000Z"\n  },\n  "messages": [\n    {\n      "conversation_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n      "role": "user",\n      "content": "string",\n      "timestamp": "1970-01-01T00:00:00.000Z",\n      "tool_calls": [\n        {\n          "id": "string",\n          "name": "string",\n          "input": {},\n          "output": "string"\n        }\n      ],\n      "token_count": 0,\n      "trace_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",\n      "feedback": {\n        "rating": "up",\n        "comment": "string",\n        "user_id": "string",\n        "submitted_at": "1970-01-01T00:00:00.000Z"\n      }\n    }\n  ]\n}\n```\n\n</details>\n\n---\n\n### `deleteConversation`\n\nDeletes a conversation and all its messages.\n\n`DELETE /v1/conversations/{conversation_id}`\n\n```ts\nconst { data } = await client.deleteConversation({\n  conversation_id: \'example\',\n})\n```\n\n---\n\n### `submitConversationFeedback`\n\nRecords a thumbs up/down (with optional comment) for the assistant turn identified by its Langfuse trace id. The rating is persisted on the message and mirrored to Langfuse as a trace score.\n\n`POST /v1/conversations/{conversation_id}/feedback`\n\n```ts\nconst { data } = await client.submitConversationFeedback(\n  {\n    conversation_id: \'example\',\n  },\n  {\n    trace_id: \'3fa85f64-5717-4562-b3fc-2c963f66afa6\',\n    rating: \'up\',\n    comment: \'string\'\n  },\n)\n```\n\n<details>\n<summary>Response</summary>\n\n```json\n{\n  "feedback": {\n    "rating": "up",\n    "comment": "string",\n    "user_id": "string",\n    "submitted_at": "1970-01-01T00:00:00.000Z"\n  }\n}\n```\n\n</details>\n\n---\n\n## Schemas\n\n### `AgentId`\n\nAgent identifier. Can be either:\n- System skill ID (prefixed): "skill:email-categorizer", "skill:email-labeler"\n- Custom agent UUID: "0336a235-9417-4dd8-894c-fe81285bba75"\n\n\n```ts\ntype AgentId = string\n```\n\n### `CreateAgentRequest`\n\n```ts\ntype CreateAgentRequest = {\n  name: string\n  description?: string\n  category?: "message" | "entity" | "document" | "classification" | "custom"\n  icon?: string\n  system_prompt: string\n  tools?: string[]\n  model_config?: {\n    model_id?: string\n    temperature?: number\n    max_tokens?: number\n    thinking?: boolean\n    thinking_budget?: number\n  }\n  max_iterations?: number\n  execution_pattern: "direct" | "react"\n  execution_mode?: "automatic" | "approval" | "draft"\n  output_schema?: object\n  input_parameters_schema?: {\n    type: "object"\n    parameters: Array<{\n      name: { ... }\n      label: { ... }\n      type: { ... }\n      description?: { ... }\n      default?: { ... }\n      multi?: { ... }\n      dependsOn?: { ... }\n      visibleWhen?: { ... }\n      enum?: { ... }\n      minimum?: { ... }\n      maximum?: { ... }\n      step?: { ... }\n      minLength?: { ... }\n      maxLength?: { ... }\n      schemaFilter?: { ... }\n      attributeTypeFilter?: { ... }\n      hidden?: { ... }\n    }>\n    required?: string[]\n  }\n}\n```\n\n### `UpdateAgentRequest`\n\n```ts\ntype UpdateAgentRequest = {\n  name?: string\n  description?: string\n  category?: "message" | "entity" | "document" | "classification" | "custom"\n  icon?: string\n  system_prompt?: string\n  tools?: string[]\n  model_config?: {\n    model_id?: string\n    temperature?: number\n    max_tokens?: number\n    thinking?: boolean\n    thinking_budget?: number\n  }\n  max_iterations?: number\n  execution_pattern?: "direct" | "react"\n  execution_mode?: "automatic" | "approval" | "draft"\n  output_schema?: object\n  input_parameters_schema?: {\n    type: "object"\n    parameters: Array<{\n      name: { ... }\n      label: { ... }\n      type: { ... }\n      description?: { ... }\n      default?: { ... }\n      multi?: { ... }\n      dependsOn?: { ... }\n      visibleWhen?: { ... }\n      enum?: { ... }\n      minimum?: { ... }\n      maximum?: { ... }\n      step?: { ... }\n      minLength?: { ... }\n      maxLength?: { ... }\n      schemaFilter?: { ... }\n      attributeTypeFilter?: { ... }\n      hidden?: { ... }\n    }>\n    required?: string[]\n  }\n}\n```\n\n### `AgentDefinition`\n\n```ts\ntype AgentDefinition = {\n  agent_id?: string\n  org_id?: string\n  name?: string\n  description?: string\n  category?: "message" | "entity" | "document" | "classification" | "custom"\n  icon?: string\n  source?: "system" | "custom"\n  availability?: "flows" | "copilot" | "portals" | "all"[]\n  allowed_entity_schemas?: string[]\n  system_prompt?: string\n  tools?: string[]\n  model_config?: {\n    model_id?: string\n    temperature?: number\n    max_tokens?: number\n    thinking?: boolean\n    thinking_budget?: number\n  }\n  max_iterations?: number\n  execution_pattern?: "direct" | "react"\n  execution_mode?: "automatic" | "approval" | "draft"\n  output_schema?: object\n  input_parameters_schema?: {\n    type: "object"\n    parameters: Array<{\n      name: { ... }\n      label: { ... }\n      type: { ... }\n      description?: { ... }\n      default?: { ... }\n      multi?: { ... }\n      dependsOn?: { ... }\n      visibleWhen?: { ... }\n      enum?: { ... }\n      minimum?: { ... }\n      maximum?: { ... }\n      step?: { ... }\n      minLength?: { ... }\n      maxLength?: { ... }\n      schemaFilter?: { ... }\n      attributeTypeFilter?: { ... }\n      hidden?: { ... }\n    }>\n    required?: string[]\n  }\n  version?: number\n  created_at?: string // date-time\n  updated_at?: string // date-time\n  created_by?: string\n}\n```\n\n### `ListAgentsResponse`\n\n```ts\ntype ListAgentsResponse = {\n  agents?: Array<{\n    agent_id?: string\n    org_id?: string\n    name?: string\n    description?: string\n    category?: "message" | "entity" | "document" | "classification" | "custom"\n    icon?: string\n    source?: "system" | "custom"\n    availability?: "flows" | "copilot" | "portals" | "all"[]\n    allowed_entity_schemas?: string[]\n    system_prompt?: string\n    tools?: string[]\n    model_config?: {\n      model_id?: { ... }\n      temperature?: { ... }\n      max_tokens?: { ... }\n      thinking?: { ... }\n      thinking_budget?: { ... }\n    }\n    max_iterations?: number\n    execution_pattern?: "direct" | "react"\n    execution_mode?: "automatic" | "approval" | "draft"\n    output_schema?: object\n    input_parameters_schema?: {\n      type: { ... }\n      parameters: { ... }\n      required?: { ... }\n    }\n    version?: number\n    created_at?: string // date-time\n    updated_at?: string // date-time\n    created_by?: string\n  }>\n  next_cursor?: string\n}\n```\n\n### `ListExecutionsResponse`\n\n```ts\ntype ListExecutionsResponse = {\n  executions?: Array<{\n    execution_id?: string // uuid\n    agent_id?: string\n    agent_source?: "system" | "custom"\n    agent_name?: string\n    execution_context?: "flows" | "copilot" | "api"\n    org_id?: string\n    status?: "pending" | "running" | "waiting_approval" | "completed" | "failed" | "cancelled"\n    input?: object\n    parameters?: object\n    result?: {\n      response?: { ... }\n      structured_output?: { ... }\n    }\n    error?: {\n      code?: { ... }\n      message?: { ... }\n      details?: { ... }\n    }\n    pending_action?: {\n      tool?: { ... }\n      input?: { ... }\n      description?: { ... }\n      preview?: { ... }\n    }\n    metrics?: {\n      total_tokens?: { ... }\n      input_tokens?: { ... }\n      output_tokens?: { ... }\n      total_cost_usd?: { ... }\n      duration_ms?: { ... }\n      iteration_count?: { ... }\n    }\n    started_at?: string // date-time\n    completed_at?: string // date-time\n    iterations?: Array<{\n      index?: { ... }\n      tool?: { ... }\n      status?: { ... }\n      timestamp?: { ... }\n    }>\n  }>\n  next_cursor?: string\n}\n```\n\n### `ApproveExecutionRequest`\n\n```ts\ntype ApproveExecutionRequest = {\n  reason?: string\n  approved_action_ids?: string[]\n  rejected_action_ids?: string[]\n}\n```\n\n### `RejectExecutionRequest`\n\n```ts\ntype RejectExecutionRequest = {\n  reason: string\n}\n```\n\n### `ExecuteAgentRequest`\n\n```ts\ntype ExecuteAgentRequest = {\n  input?: {\n    entity_id?: string\n    entity_schema?: string\n    workflow_id?: string\n    workflow_execution_id?: string\n    task_id?: string\n    custom_data?: Record<string, unknown>\n    flow_context?: Array<{\n      entity_id: { ... }\n      entity_schema: { ... }\n    }>\n  }\n  parameters?: Record<string, unknown>\n  execution_mode_override?: "automatic" | "approval" | "draft"\n  execution_context?: "flows" | "copilot" | "api"\n  callback_url?: string // uri\n  timeout_ms?: number\n}\n```\n\n### `ExecutionResponse`\n\n```ts\ntype ExecutionResponse = {\n  execution_id?: string // uuid\n  agent_id?: string\n  agent_source?: "system" | "custom"\n  agent_name?: string\n  execution_context?: "flows" | "copilot" | "api"\n  org_id?: string\n  status?: "pending" | "running" | "waiting_approval" | "completed" | "failed" | "cancelled"\n  input?: object\n  parameters?: object\n  result?: {\n    response?: string\n    structured_output?: object\n  }\n  error?: {\n    code?: "TIMEOUT" | "MAX_ITERATIONS_EXCEEDED" | "TOOL_EXECUTION_FAILED" | "LLM_ERROR" | "INVALID_OUTPUT" | "REJECTED" | "INTERNAL_ERROR"\n    message?: string\n    details?: object\n  }\n  pending_action?: {\n    tool?: string\n    input?: object\n    description?: string\n    preview?: {\n      action?: { ... }\n      source?: { ... }\n      target?: { ... }\n      changes?: { ... }\n      metadata?: { ... }\n      summary?: { ... }\n    }\n  }\n  metrics?: {\n    total_tokens?: number\n    input_tokens?: number\n    output_tokens?: number\n    total_cost_usd?: number\n    duration_ms?: number\n    iteration_count?: number\n  }\n  started_at?: string // date-time\n  completed_at?: string // date-time\n  iterations?: Array<{\n    index?: number\n    tool?: string\n    status?: "running" | "completed"\n    timestamp?: string // date-time\n  }>\n}\n```\n\n### `ExecutionIterationProjection`\n\n```ts\ntype ExecutionIterationProjection = {\n  index?: number\n  tool?: string\n  status?: "running" | "completed"\n  timestamp?: string // date-time\n}\n```\n\n### `ExecutionFeedback`\n\n```ts\ntype ExecutionFeedback = {\n  rating: "up" | "down"\n  comment?: string\n  user_id: string\n  submitted_at: string // date-time\n}\n```\n\n### `ExecutionFeedbackResponse`\n\n```ts\ntype ExecutionFeedbackResponse = {\n  feedback: {\n    rating: "up" | "down"\n    comment?: string\n    user_id: string\n    submitted_at: string // date-time\n  }\n}\n```\n\n### `PutExecutionFeedbackRequest`\n\n```ts\ntype PutExecutionFeedbackRequest = {\n  rating: "up" | "down"\n  comment?: string\n}\n```\n\n### `ExecutionTrace`\n\n```ts\ntype ExecutionTrace = {\n  execution_id?: string // uuid\n  iterations?: Array<{\n    iteration_index?: number\n    thought?: string\n    action?: {\n      tool?: { ... }\n      input?: { ... }\n    }\n    observation?: object\n    timestamp?: string // date-time\n    tokens_used?: number\n    latency_ms?: number\n  }>\n  total_iterations?: number\n}\n```\n\n### `ExecutionIteration`\n\n```ts\ntype ExecutionIteration = {\n  iteration_index?: number\n  thought?: string\n  action?: {\n    tool?: string\n    input?: object\n  }\n  observation?: object\n  timestamp?: string // date-time\n  tokens_used?: number\n  latency_ms?: number\n}\n```\n\n### `PendingAction`\n\nAction waiting for approval (when status=waiting_approval)\n\n```ts\ntype PendingAction = {\n  tool?: string\n  input?: object\n  description?: string\n  preview?: {\n    action?: {\n      type: { ... }\n      verb: { ... }\n    }\n    source?: {\n      type?: { ... }\n      id?: { ... }\n      name?: { ... }\n      schema?: { ... }\n      icon?: { ... }\n      url?: { ... }\n    }\n    target?: {\n      type?: { ... }\n      id?: { ... }\n      name?: { ... }\n      schema?: { ... }\n      icon?: { ... }\n      url?: { ... }\n    }\n    changes?: Array<{\n      field?: { ... }\n      label?: { ... }\n      from?: { ... }\n      to?: { ... }\n    }>\n    metadata?: Record<string, {\n      type: { ... }\n      value?: { ... }\n      values?: { ... }\n      id?: { ... }\n      name?: { ... }\n      schema?: { ... }\n      color?: { ... }\n    }>\n    summary?: string\n  }\n}\n```\n\n### `ExecutionError`\n\n```ts\ntype ExecutionError = {\n  code?: "TIMEOUT" | "MAX_ITERATIONS_EXCEEDED" | "TOOL_EXECUTION_FAILED" | "LLM_ERROR" | "INVALID_OUTPUT" | "REJECTED" | "INTERNAL_ERROR"\n  message?: string\n  details?: object\n}\n```\n\n### `ExecutionMetrics`\n\n```ts\ntype ExecutionMetrics = {\n  total_tokens?: number\n  input_tokens?: number\n  output_tokens?: number\n  total_cost_usd?: number\n  duration_ms?: number\n  iteration_count?: number\n}\n```\n\n### `AgentExecutionEventStatus`\n\nLifecycle status carried on an agent execution event.\n\nDeliberately narrower than `ExecutionStatus`, which is the stored status of\nthe execution row: `pending` and `running` both surface as `started`, and\n`cancelled` surfaces as `failed`. Consumers must not assume the two\nvocabularies are interchang\n\n```ts\ntype AgentExecutionEventStatus = "started" | "completed" | "failed" | "approval_required"\n```\n\n### `AgentExecutionEvent`\n\nDetail payload of the `agent-execution-status-update` event, published on\nthe AI Agents event bus with source `ai-agents`.\n\n`execution_context` and `input` are present on every status, so a consumer\ncan tell whether an execution is theirs, and what it belonged to, from the\nterminal event alone \u2014 wit\n\n```ts\ntype AgentExecutionEvent = {\n  executionId: string\n  agentId: string\n  orgId: string\n  userId?: string\n  execution_status: "started" | "completed" | "failed" | "approval_required"\n  execution_context?: "flows" | "copilot" | "api"\n  input?: Record<string, unknown>\n  output?: Record<string, unknown>\n  error?: {\n    message?: string\n    code?: string\n    stack?: string\n  }\n  duration?: number\n  iterations?: number\n  iteration?: number\n  message?: string\n  toolCalls?: Array<{\n    name?: string\n    args?: Record<string, unknown>\n  }>\n  timestamp?: string // date-time\n}\n```\n\n### `ToolPreview`\n\nStructured preview data for approval UI. Provides a generic format that any tool can populate.\n\n```ts\ntype ToolPreview = {\n  action?: {\n    type: "move" | "create" | "update" | "delete" | "apply" | "send" | "link" | "unlink" | "batch_approval"\n    verb: string\n  }\n  source?: {\n    type?: string\n    id?: string\n    name?: string\n    schema?: string\n    icon?: string\n    url?: string\n  }\n  target?: {\n    type?: string\n    id?: string\n    name?: string\n    schema?: string\n    icon?: string\n    url?: string\n  }\n  changes?: Array<{\n    field?: string\n    label?: string\n    from?: {\n      type: { ... }\n      value?: { ... }\n      values?: { ... }\n      id?: { ... }\n      name?: { ... }\n      schema?: { ... }\n      color?: { ... }\n    }\n    to?: {\n      type: { ... }\n      value?: { ... }\n      values?: { ... }\n      id?: { ... }\n      name?: { ... }\n      schema?: { ... }\n      color?: { ... }\n    }\n  }>\n  metadata?: Record<string, {\n    type: "text" | "number" | "boolean" | "list" | "entity" | "badge"\n    value?: unknown\n    values?: string[]\n    id?: string\n    name?: string\n    schema?: string\n    color?: "success" | "warning" | "error" | "info"\n  }>\n  summary?: string\n}\n```\n\n### `PreviewActionType`\n\nType of action being previewed\n\n```ts\ntype PreviewActionType = "move" | "create" | "update" | "delete" | "apply" | "send" | "link" | "unlink" | "batch_approval"\n```\n\n### `PreviewEntity`\n\nEntity reference for preview display\n\n```ts\ntype PreviewEntity = {\n  type?: string\n  id?: string\n  name?: string\n  schema?: string\n  icon?: string\n  url?: string\n}\n```\n\n### `PreviewChange`\n\nA single field change in the preview\n\n```ts\ntype PreviewChange = {\n  field?: string\n  label?: string\n  from?: {\n    type: "text" | "number" | "boolean" | "list" | "entity" | "badge"\n    value?: unknown\n    values?: string[]\n    id?: string\n    name?: string\n    schema?: string\n    color?: "success" | "warning" | "error" | "info"\n  }\n  to?: {\n    type: "text" | "number" | "boolean" | "list" | "entity" | "badge"\n    value?: unknown\n    values?: string[]\n    id?: string\n    name?: string\n    schema?: string\n    color?: "success" | "warning" | "error" | "info"\n  }\n}\n```\n\n### `PreviewValue`\n\nTyped value for preview display\n\n```ts\ntype PreviewValue = {\n  type: "text" | "number" | "boolean" | "list" | "entity" | "badge"\n  value?: unknown\n  values?: string[]\n  id?: string\n  name?: string\n  schema?: string\n  color?: "success" | "warning" | "error" | "info"\n}\n```\n\n### `ToolDefinition`\n\n```ts\ntype ToolDefinition = {\n  tool_id?: string\n  name?: string\n  description?: string\n  category?: "entity" | "message" | "taxonomy" | "rag" | "workflow"\n  parameters?: object\n  returns?: object\n  requires_approval?: boolean\n  enabled?: boolean\n}\n```\n\n### `SkillCategory`\n\n```ts\ntype SkillCategory = "message" | "entity" | "document" | "classification" | "custom"\n```\n\n### `AgentSource`\n\n- system: Pre-built by epilot (system skills)\n- custom: Created by organization\n\n\n```ts\ntype AgentSource = "system" | "custom"\n```\n\n### `SkillAvailability`\n\nWhere the skill/agent is available:\n- flows: Available in workflow automations\n- copilot: Available as a sub-agent in copilot\n- portals: Available in end-user self-service portals\n- all: Available everywhere\n\n\n```ts\ntype SkillAvailability = "flows" | "copilot" | "portals" | "all"\n```\n\n### `ExecutionContext`\n\nWhere the execution was triggered from:\n- flows: Triggered from workflow automation\n- copilot: Triggered from copilot assistant\n- api: Direct API call\n\n\n```ts\ntype ExecutionContext = "flows" | "copilot" | "api"\n```\n\n### `ExecutionPattern`\n\n- direct: Single LLM call, no tools\n- react: Multi-step reasoning with tool use\n\n\n```ts\ntype ExecutionPattern = "direct" | "react"\n```\n\n### `ExecutionMode`\n\n- automatic: Execute without human intervention\n- approval: Pause for human approval before tool execution\n- draft: Execute but mark output as draft for review\n\n\n```ts\ntype ExecutionMode = "automatic" | "approval" | "draft"\n```\n\n### `ExecutionStatus`\n\n```ts\ntype ExecutionStatus = "pending" | "running" | "waiting_approval" | "completed" | "failed" | "cancelled"\n```\n\n### `ParameterType`\n\nBase types:\n- text: Text input field\n- textarea: Multi-line text input field\n- number: Numeric input field\n- boolean: Toggle switch\n- select: Dropdown selection (requires enum array)\n\nCustom types (domain-specific):\n- entity-schema: Entity schema selector (fetches from Entity API)\n- entity-attribute\n\n```ts\ntype ParameterType = "text" | "textarea" | "number" | "boolean" | "select" | "entity-schema" | "entity-attribute" | "entity-id" | "taxonomy" | "taxonomy-classification" | "shared-inbox" | "label" | "matching-criteria"\n```\n\n### `InputParameterDefinition`\n\n```ts\ntype InputParameterDefinition = {\n  name: string\n  label: string\n  type: "text" | "textarea" | "number" | "boolean" | "select" | "entity-schema" | "entity-attribute" | "entity-id" | "taxonomy" | "taxonomy-classification" | "shared-inbox" | "label" | "matching-criteria"\n  description?: string\n  default?: unknown\n  multi?: boolean\n  dependsOn?: string\n  visibleWhen?: Record<string, unknown[]>\n  enum?: string[]\n  minimum?: number\n  maximum?: number\n  step?: number\n  minLength?: number\n  maxLength?: number\n  schemaFilter?: string[]\n  attributeTypeFilter?: string[]\n  hidden?: boolean\n}\n```\n\n### `InputParametersSchema`\n\n```ts\ntype InputParametersSchema = {\n  type: "object"\n  parameters: Array<{\n    name: string\n    label: string\n    type: "text" | "textarea" | "number" | "boolean" | "select" | "entity-schema" | "entity-attribute" | "entity-id" | "taxonomy" | "taxonomy-classification" | "shared-inbox" | "label" | "matching-criteria"\n    description?: string\n    default?: unknown\n    multi?: boolean\n    dependsOn?: string\n    visibleWhen?: Record<string, unknown[]>\n    enum?: string[]\n    minimum?: number\n    maximum?: number\n    step?: number\n    minLength?: number\n    maxLength?: number\n    schemaFilter?: string[]\n    attributeTypeFilter?: string[]\n    hidden?: boolean\n  }>\n  required?: string[]\n}\n```\n\n### `ModelConfig`\n\n```ts\ntype ModelConfig = {\n  model_id?: string\n  temperature?: number\n  max_tokens?: number\n  thinking?: boolean\n  thinking_budget?: number\n}\n```\n\n### `Error`\n\n```ts\ntype Error = {\n  error?: string\n  message?: string\n  details?: object\n}\n```\n\n### `ChatRequest`\n\n```ts\ntype ChatRequest = {\n  agentId: string\n  message: string\n  conversationId?: string // uuid\n  clientHistory?: Array<{\n    role: "user" | "assistant" | "tool" | "system"\n    content: string\n    tool_calls?: Array<{\n      id?: { ... }\n      name?: { ... }\n      input?: { ... }\n      output?: { ... }\n    }>\n  }>\n  context?: {\n    entityId?: string\n    customData?: Record<string, unknown>\n  }\n  streaming?: {\n    mode?: "updates" | "messages"\n    streamTokens?: boolean\n    includeMetadata?: boolean\n  }\n}\n```\n\n### `ChatMessage`\n\n```ts\ntype ChatMessage = {\n  role: "user" | "assistant" | "tool" | "system"\n  content: string\n  tool_calls?: Array<{\n    id?: string\n    name?: string\n    input?: object\n    output?: string\n  }>\n}\n```\n\n### `StreamingOptions`\n\n```ts\ntype StreamingOptions = {\n  mode?: "updates" | "messages"\n  streamTokens?: boolean\n  includeMetadata?: boolean\n}\n```\n\n### `StreamEvent`\n\nServer-Sent Event for streaming responses\n\n```ts\ntype StreamEvent = {\n  type?: "token" | "agent_step" | "tool_call" | "tool_result" | "complete" | "error" | "metadata" | "needs_approval"\n  content?: string\n  index?: number\n  tool?: string\n  input?: object\n  output?: string\n  callId?: string\n  result?: {\n    response?: string\n    structured_output?: object\n    status?: "completed" | "failed" | "max_iterations" | "rejected"\n    metrics?: {\n      total_tokens?: { ... }\n      input_tokens?: { ... }\n      output_tokens?: { ... }\n      total_cost_usd?: { ... }\n      duration_ms?: { ... }\n      iteration_count?: { ... }\n    }\n  }\n  error?: {\n    code?: string\n    message?: string\n  }\n  conversationId?: string // uuid\n}\n```\n\n### `ExecutionResult`\n\n```ts\ntype ExecutionResult = {\n  response?: string\n  structured_output?: object\n  status?: "completed" | "failed" | "max_iterations" | "rejected"\n  metrics?: {\n    total_tokens?: number\n    input_tokens?: number\n    output_tokens?: number\n    total_cost_usd?: number\n    duration_ms?: number\n    iteration_count?: number\n  }\n}\n```\n\n### `ConversationItem`\n\n```ts\ntype ConversationItem = {\n  conversation_id?: string // uuid\n  user_id?: string\n  agent_id?: string\n  title?: string\n  message_count?: number\n  last_message?: string\n  last_message_at?: string // date-time\n  context?: {\n    entityId?: string\n    customData?: object\n  }\n  created_at?: string // date-time\n  updated_at?: string // date-time\n}\n```\n\n### `MessageItem`\n\n```ts\ntype MessageItem = {\n  conversation_id?: string // uuid\n  role?: "user" | "assistant" | "tool" | "system"\n  content?: string\n  timestamp?: string // date-time\n  tool_calls?: Array<{\n    id?: string\n    name?: string\n    input?: object\n    output?: string\n  }>\n  token_count?: number\n  trace_id?: string // uuid\n  feedback?: {\n    rating: "up" | "down"\n    comment?: string\n    user_id: string\n    submitted_at: string // date-time\n  }\n}\n```\n\n### `MessageFeedback`\n\n```ts\ntype MessageFeedback = {\n  rating: "up" | "down"\n  comment?: string\n  user_id: string\n  submitted_at: string // date-time\n}\n```\n\n### `SubmitFeedbackRequest`\n\n```ts\ntype SubmitFeedbackRequest = {\n  trace_id: string // uuid\n  rating: "up" | "down"\n  comment?: string\n}\n```\n\n### `ListConversationsResponse`\n\n```ts\ntype ListConversationsResponse = {\n  conversations?: Array<{\n    conversation_id?: string // uuid\n    user_id?: string\n    agent_id?: string\n    title?: string\n    message_count?: number\n    last_message?: string\n    last_message_at?: string // date-time\n    context?: {\n      entityId?: { ... }\n      customData?: { ... }\n    }\n    created_at?: string // date-time\n    updated_at?: string // date-time\n  }>\n  next_cursor?: string\n}\n```\n\n### `ConversationWithMessages`\n\n```ts\ntype ConversationWithMessages = {\n  conversation?: {\n    conversation_id?: string // uuid\n    user_id?: string\n    agent_id?: string\n    title?: string\n    message_count?: number\n    last_message?: string\n    last_message_at?: string // date-time\n    context?: {\n      entityId?: { ... }\n      customData?: { ... }\n    }\n    created_at?: string // date-time\n    updated_at?: string // date-time\n  }\n  messages?: Array<{\n    conversation_id?: string // uuid\n    role?: "user" | "assistant" | "tool" | "system"\n    content?: string\n    timestamp?: string // date-time\n    tool_calls?: Array<{\n      id?: { ... }\n      name?: { ... }\n      input?: { ... }\n      output?: { ... }\n    }>\n    token_count?: number\n    trace_id?: string // uuid\n    feedback?: {\n      rating: { ... }\n      comment?: { ... }\n      user_id: { ... }\n      submitted_at: { ... }\n    }\n  }>\n}\n```\n';
-export {
-  ai_agents_default as default
-};