@epilot/sdk 2.18.21 → 2.18.23

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (146) hide show
  1. package/definitions/ai-agents.json +121 -27
  2. package/definitions/customer-portal-runtime.json +1 -1
  3. package/definitions/customer-portal.json +207 -17
  4. package/definitions/message.json +164 -14
  5. package/dist/ai-agents-ME5VRKMY.cjs +7 -0
  6. package/dist/ai-agents-MY4QE4CP.js +7 -0
  7. package/dist/{ai-agents.d-BnR7CAeJ.d.cts → ai-agents.d-B3TkP4mo.d.cts} +152 -52
  8. package/dist/{ai-agents.d-BnR7CAeJ.d.ts → ai-agents.d-B3TkP4mo.d.ts} +152 -52
  9. package/dist/apis/access-token.cjs +6 -6
  10. package/dist/apis/access-token.js +1 -1
  11. package/dist/apis/address-suggestions.cjs +6 -6
  12. package/dist/apis/address-suggestions.js +1 -1
  13. package/dist/apis/address.cjs +6 -6
  14. package/dist/apis/address.js +1 -1
  15. package/dist/apis/ai-agents.cjs +6 -6
  16. package/dist/apis/ai-agents.d.cts +2 -2
  17. package/dist/apis/ai-agents.d.ts +2 -2
  18. package/dist/apis/ai-agents.js +1 -1
  19. package/dist/apis/app.cjs +6 -6
  20. package/dist/apis/app.js +1 -1
  21. package/dist/apis/audit-logs.cjs +6 -6
  22. package/dist/apis/audit-logs.js +1 -1
  23. package/dist/apis/automation.cjs +6 -6
  24. package/dist/apis/automation.js +1 -1
  25. package/dist/apis/billing.cjs +6 -6
  26. package/dist/apis/billing.js +1 -1
  27. package/dist/apis/blueprint-manifest.cjs +6 -6
  28. package/dist/apis/blueprint-manifest.js +1 -1
  29. package/dist/apis/calendar.cjs +6 -6
  30. package/dist/apis/calendar.js +1 -1
  31. package/dist/apis/configuration-hub.cjs +6 -6
  32. package/dist/apis/configuration-hub.js +1 -1
  33. package/dist/apis/consent.cjs +6 -6
  34. package/dist/apis/consent.js +1 -1
  35. package/dist/apis/customer-portal.cjs +8 -8
  36. package/dist/apis/customer-portal.d.cts +2 -2
  37. package/dist/apis/customer-portal.d.ts +2 -2
  38. package/dist/apis/customer-portal.js +2 -2
  39. package/dist/apis/dashboard.cjs +6 -6
  40. package/dist/apis/dashboard.js +1 -1
  41. package/dist/apis/data-governance.cjs +6 -6
  42. package/dist/apis/data-governance.js +1 -1
  43. package/dist/apis/deduplication.cjs +6 -6
  44. package/dist/apis/deduplication.js +1 -1
  45. package/dist/apis/design.cjs +6 -6
  46. package/dist/apis/design.js +1 -1
  47. package/dist/apis/document.cjs +6 -6
  48. package/dist/apis/document.js +1 -1
  49. package/dist/apis/email-settings.cjs +6 -6
  50. package/dist/apis/email-settings.js +1 -1
  51. package/dist/apis/email-template.cjs +6 -6
  52. package/dist/apis/email-template.js +1 -1
  53. package/dist/apis/entity-mapping.cjs +6 -6
  54. package/dist/apis/entity-mapping.js +1 -1
  55. package/dist/apis/entity.cjs +6 -6
  56. package/dist/apis/entity.js +1 -1
  57. package/dist/apis/environments.cjs +6 -6
  58. package/dist/apis/environments.js +1 -1
  59. package/dist/apis/event-catalog.cjs +6 -6
  60. package/dist/apis/event-catalog.js +1 -1
  61. package/dist/apis/file.cjs +6 -6
  62. package/dist/apis/file.js +1 -1
  63. package/dist/apis/iban.cjs +6 -6
  64. package/dist/apis/iban.js +1 -1
  65. package/dist/apis/integration-toolkit.cjs +6 -6
  66. package/dist/apis/integration-toolkit.js +1 -1
  67. package/dist/apis/journey.cjs +6 -6
  68. package/dist/apis/journey.js +1 -1
  69. package/dist/apis/kanban.cjs +6 -6
  70. package/dist/apis/kanban.js +1 -1
  71. package/dist/apis/message.cjs +6 -6
  72. package/dist/apis/message.d.cts +2 -2
  73. package/dist/apis/message.d.ts +2 -2
  74. package/dist/apis/message.js +1 -1
  75. package/dist/apis/metering.cjs +6 -6
  76. package/dist/apis/metering.js +1 -1
  77. package/dist/apis/notes.cjs +6 -6
  78. package/dist/apis/notes.js +1 -1
  79. package/dist/apis/notification.cjs +6 -6
  80. package/dist/apis/notification.js +1 -1
  81. package/dist/apis/organization.cjs +6 -6
  82. package/dist/apis/organization.js +1 -1
  83. package/dist/apis/partner-directory.cjs +6 -6
  84. package/dist/apis/partner-directory.js +1 -1
  85. package/dist/apis/permissions.cjs +6 -6
  86. package/dist/apis/permissions.js +1 -1
  87. package/dist/apis/pricing-tier.cjs +6 -6
  88. package/dist/apis/pricing-tier.js +1 -1
  89. package/dist/apis/pricing.cjs +6 -6
  90. package/dist/apis/pricing.js +1 -1
  91. package/dist/apis/purpose.cjs +6 -6
  92. package/dist/apis/purpose.js +1 -1
  93. package/dist/apis/query.cjs +6 -6
  94. package/dist/apis/query.js +1 -1
  95. package/dist/apis/sandbox.cjs +6 -6
  96. package/dist/apis/sandbox.js +1 -1
  97. package/dist/apis/sharing.cjs +6 -6
  98. package/dist/apis/sharing.js +1 -1
  99. package/dist/apis/snapshot.cjs +6 -6
  100. package/dist/apis/snapshot.js +1 -1
  101. package/dist/apis/submission.cjs +6 -6
  102. package/dist/apis/submission.js +1 -1
  103. package/dist/apis/target.cjs +6 -6
  104. package/dist/apis/target.js +1 -1
  105. package/dist/apis/targeting.cjs +6 -6
  106. package/dist/apis/targeting.js +1 -1
  107. package/dist/apis/template-variables.cjs +6 -6
  108. package/dist/apis/template-variables.js +1 -1
  109. package/dist/apis/user.cjs +6 -6
  110. package/dist/apis/user.js +1 -1
  111. package/dist/apis/validation-rules.cjs +6 -6
  112. package/dist/apis/validation-rules.js +1 -1
  113. package/dist/apis/webhooks.cjs +6 -6
  114. package/dist/apis/webhooks.js +1 -1
  115. package/dist/apis/workflow-definition.cjs +6 -6
  116. package/dist/apis/workflow-definition.js +1 -1
  117. package/dist/apis/workflow.cjs +6 -6
  118. package/dist/apis/workflow.js +1 -1
  119. package/dist/{chunk-EPDH37RS.js → chunk-AWKA7GZQ.js} +1 -1
  120. package/dist/{chunk-ZCEIXRDJ.cjs → chunk-J57SWYWL.cjs} +4 -4
  121. package/dist/{chunk-LKV3RKOP.cjs → chunk-QKEPXYEF.cjs} +1 -1
  122. package/dist/{chunk-C2BFLFHE.js → chunk-SCBBLLBK.js} +4 -4
  123. package/dist/customer-portal-JLUT56QQ.js +7 -0
  124. package/dist/customer-portal-NUYHT3HX.cjs +7 -0
  125. package/dist/{customer-portal-runtime-FZQLCEJQ.js → customer-portal-runtime-6CECA6UW.js} +1 -1
  126. package/dist/{customer-portal-runtime-7WW3YRWJ.cjs → customer-portal-runtime-QMONBHLN.cjs} +2 -2
  127. package/dist/{customer-portal.d-JVkJjm_e.d.cts → customer-portal.d-Ce8-UnSY.d.cts} +794 -42
  128. package/dist/{customer-portal.d-JVkJjm_e.d.ts → customer-portal.d-Ce8-UnSY.d.ts} +794 -42
  129. package/dist/index.cjs +10 -10
  130. package/dist/index.d.cts +3 -3
  131. package/dist/index.d.ts +3 -3
  132. package/dist/index.js +2 -2
  133. package/dist/message-LJ32JH6Z.cjs +7 -0
  134. package/dist/message-SSTVRGEF.js +7 -0
  135. package/dist/{message.d-BHWCGH3q.d.cts → message.d-DwnqO-Us.d.cts} +366 -25
  136. package/dist/{message.d-BHWCGH3q.d.ts → message.d-DwnqO-Us.d.ts} +366 -25
  137. package/docs/ai-agents.md +76 -19
  138. package/docs/customer-portal.md +209 -13
  139. package/docs/message.md +126 -2
  140. package/package.json +1 -1
  141. package/dist/ai-agents-3JK4UU2G.js +0 -7
  142. package/dist/ai-agents-XST3YUFA.cjs +0 -7
  143. package/dist/customer-portal-JDIXJD6C.cjs +0 -7
  144. package/dist/customer-portal-WIRQ7UCN.js +0 -7
  145. package/dist/message-BZN67NTB.js +0 -7
  146. package/dist/message-DBHA4PHI.cjs +0 -7
package/dist/ai-agents-MY4QE4CP.js ADDED
@@ -0,0 +1,7 @@
1
+ import "./chunk-YPSWSI3M.js";
2
+
3
+ // src/docs/ai-agents.json
4
+ 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';
5
+ export {
6
+ ai_agents_default as default
7
+ };