# Agent ## AI Task `client.agent.automate(AgentAutomateParamsbody, RequestOptionsoptions?): AutomateEvent | Stream` **post** `/automate` Execute AI-powered browser automation tasks using natural language with optional geotargeting. This endpoint **always streams** responses using Server-Sent Events (SSE). **Streaming Response:** - All responses are streamed using Server-Sent Events (`text/event-stream`) - Real-time progress updates and results as they're generated **Geotargeting:** - Optionally specify a country code for geotargeted browsing **Use Cases:** - Web scraping and data extraction - Form filling and interaction - Navigation and information gathering - Multi-step web workflows - Content analysis from web pages ### Parameters - `body: AgentAutomateParams` - `task: string` The task description in natural language - `data?: unknown` JSON data to provide context for form filling or complex tasks - `geo_target?: GeotargetGeoTarget` Optional geotargeting parameters for proxy requests - `country?: string` Country code using ISO 3166-1 alpha-2 standard (2 letters, e.g., "US", "GB", "JP"). See: https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2 - `guardrails?: string` Safety constraints for execution - `interactive?: boolean` Enable interactive mode to allow human-in-the-loop input during task execution - `maxIterations?: number` Maximum task iterations - `maxValidationAttempts?: number` Maximum validation attempts - `trusted_hostnames?: Array` TrustedHostnames lists hostnames where the action firewall is bypassed for fills and submissions. WARNING: on listed hosts, prompt injection from page content can drive the agent to fill and submit any field, including personal and credential data. Use only for sites you fully trust to receive your data. - `unsafe_mode?: boolean` UnsafeMode disables the action firewall entirely. WARNING: prompt injection from page content can then cause the agent to submit your data, including credentials, personal information, and conversation context, to attacker-controlled forms. Only enable for trusted, controlled environments. - `url?: string` Starting URL for the task ### Returns - `AutomateEvent = V1AutomateEventAgentAction | V1AutomateEventAgentExtracted | V1AutomateEventAgentProcessing | 30 more` A Server-Sent Event from /v1/automate. Typed discriminated union keyed on event. - `V1AutomateEventAgentAction` Envelope for the "agent:action" event from /v1/automate. - `data: Data` Event data for action execution - `action: string` - `iterationId: string` - `timestamp: number` - `ref?: string | null` - `value?: string | null` - `event: "agent:action"` - `"agent:action"` - `V1AutomateEventAgentExtracted` Envelope for the "agent:extracted" event from /v1/automate. - `data: Data` Event data for extracted data - `extractedData: string` - `iterationId: string` - `timestamp: number` - `event: "agent:extracted"` - `"agent:extracted"` - `V1AutomateEventAgentProcessing` Envelope for the "agent:processing" event from /v1/automate. - `data: Data` Event data for when the agent is waiting for model generation - `hasScreenshot: boolean` - `iterationId: string` - `operation: string` - `timestamp: number` - `event: "agent:processing"` - `"agent:processing"` - `V1AutomateEventAgentReasoned` Envelope for the "agent:reasoned" event from /v1/automate. - `data: Data` Event data for agent reasoning - `iterationId: string` - `reasoning: string` - `timestamp: number` - `event: "agent:reasoned"` - `"agent:reasoned"` - `V1AutomateEventAgentStatus` Envelope for the "agent:status" event from /v1/automate. - `data: Data` Event data for status messages - `iterationId: string` - `message: string` - `timestamp: number` - `event: "agent:status"` - `"agent:status"` - `V1AutomateEventAgentStep` Envelope for the "agent:step" event from /v1/automate. - `data: Data` Event data for agent step tracking (each loop iteration) - `currentIteration: number` - `iterationId: string` - `timestamp: number` - `event: "agent:step"` - `"agent:step"` - `V1AutomateEventAgentWaiting` Envelope for the "agent:waiting" event from /v1/automate. - `data: Data` Event data for waiting notifications - `iterationId: string` - `seconds: number` - `timestamp: number` - `event: "agent:waiting"` - `"agent:waiting"` - `V1AutomateEventAIGeneration` Envelope for the "ai:generation" event from /v1/automate. - `data: Data` Event data when AI generation occurs - `finishReason: "stop" | "length" | "content-filter" | 3 more` - `"stop"` - `"length"` - `"content-filter"` - `"tool-calls"` - `"error"` - `"other"` - `iterationId: string` - `prompt: string` - `schema: unknown` - `timestamp: number` - `usage: Usage` - `inputTokens?: number` - `outputTokens?: number` - `totalTokens?: number` - `messages?: Array` - `System` A system message. It can contain system information. Note: using the "system" part of the prompt is strongly preferred to increase the resilience against prompt injection attacks, and because not all providers support several system messages. - `content: string` - `role: "system"` - `"system"` - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `User` A user message. It can contain text or a combination of text and images. - `content: string | Array` Content of a user message. It can be a string or an array of text and image parts. - `string` - `Array` - `Text` Text content part of a prompt. It contains a string of text. - `text: string` The text content. - `type: "text"` - `"text"` - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Image` Image content part of a prompt. It contains an image. - `image: string | UnionMember1 | ByteLength | V1GlobalBuffer` Image data. Can either be: - data: a base64-encoded string, a Uint8Array, an ArrayBuffer, or a Buffer - URL: a URL that points to the image - `string` - `UnionMember1` - `buffer: Buffer` - `byteLength: number` - `byteLength: number` - `byteOffset: number` - `BYTES_PER_ELEMENT: number` - `length: number` - `ByteLength` - `byteLength: number` - `V1GlobalBuffer` - `buffer: Buffer` - `byteLength: number` - `byteLength: number` - `byteOffset: number` - `BYTES_PER_ELEMENT: number` - `length: number` - `type: "image"` - `"image"` - `mediaType?: string` Optional IANA media type of the image. - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `File` File content part of a prompt. It contains a file. - `data: string | UnionMember1 | ByteLength | V1GlobalBuffer` File data. Can either be: - data: a base64-encoded string, a Uint8Array, an ArrayBuffer, or a Buffer - URL: a URL that points to the image - `string` - `UnionMember1` - `buffer: Buffer` - `byteLength: number` - `byteLength: number` - `byteOffset: number` - `BYTES_PER_ELEMENT: number` - `length: number` - `ByteLength` - `byteLength: number` - `V1GlobalBuffer` - `mediaType: string` IANA media type of the file. - `type: "file"` - `"file"` - `filename?: string` Optional filename of the file. - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `role: "user"` - `"user"` - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Assistant` An assistant message. It can contain text, tool calls, or a combination of text and tool calls. - `content: string | Array` Content of an assistant message. It can be a string or an array of text, image, reasoning, redacted reasoning, and tool call parts. - `string` - `Array` - `Text` Text content part of a prompt. It contains a string of text. - `text: string` The text content. - `type: "text"` - `"text"` - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `File` File content part of a prompt. It contains a file. - `data: string | UnionMember1 | ByteLength | V1GlobalBuffer` File data. Can either be: - data: a base64-encoded string, a Uint8Array, an ArrayBuffer, or a Buffer - URL: a URL that points to the image - `string` - `UnionMember1` - `buffer: Buffer` - `byteLength: number` - `byteLength: number` - `byteOffset: number` - `BYTES_PER_ELEMENT: number` - `length: number` - `ByteLength` - `byteLength: number` - `V1GlobalBuffer` - `mediaType: string` IANA media type of the file. - `type: "file"` - `"file"` - `filename?: string` Optional filename of the file. - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Reasoning` Reasoning content part of a prompt. It contains a reasoning. - `text: string` The reasoning text. - `type: "reasoning"` - `"reasoning"` - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ToolCall` Tool call content part of a prompt. It contains a tool call (usually generated by the AI model). - `input: unknown` Arguments of the tool call. This is a JSON-serializable object that matches the tool's input schema. - `toolCallId: string` ID of the tool call. This ID is used to match the tool call with the tool result. - `toolName: string` Name of the tool that is being called. - `type: "tool-call"` - `"tool-call"` - `providerExecuted?: boolean` Whether the tool call was executed by the provider. - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ToolResult` Tool result content part of a prompt. It contains the result of the tool call with the matching ID. - `output: Text | Json | ExecutionDenied | 3 more` Result of the tool call. This is a JSON-serializable object. - `Text` - `type: "text"` Text tool output that should be directly sent to the API. - `"text"` - `value: string` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Json` - `type: "json"` - `"json"` - `value: string | number | boolean | 2 more | null` A JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ExecutionDenied` - `type: "execution-denied"` Type when the user has denied the execution of the tool call. - `"execution-denied"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `reason?: string` Optional reason for the execution denial. - `ErrorText` - `type: "error-text"` - `"error-text"` - `value: string` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ErrorJson` - `type: "error-json"` - `"error-json"` - `value: string | number | boolean | 2 more | null` A JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Content` - `type: "content"` - `"content"` - `value: Array` - `Text` - `text: string` Text content. - `type: "text"` - `"text"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Media` - `data: string` - `mediaType: string` - `type: "media"` Deprecated. Use image-data or file-data instead. - `"media"` - `FileData` - `data: string` Base-64 encoded media data. - `mediaType: string` IANA media type. - `type: "file-data"` - `"file-data"` - `filename?: string` Optional filename of the file. - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `FileURL` - `type: "file-url"` - `"file-url"` - `url: string` URL of the file. - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `FileID` - `fileId: string | Record` ID of the file. If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. 'openai' or 'anthropic'. - `string` - `Record` - `type: "file-id"` - `"file-id"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ImageData` - `data: string` Base-64 encoded image data. - `mediaType: string` IANA media type. - `type: "image-data"` Images that are referenced using base64 encoded data. - `"image-data"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ImageURL` - `type: "image-url"` Images that are referenced using a URL. - `"image-url"` - `url: string` URL of the image. - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ImageFileID` - `fileId: string | Record` Image that is referenced using a provider file id. If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. 'openai' or 'anthropic'. - `string` - `Record` - `type: "image-file-id"` Images that are referenced using a provider file id. - `"image-file-id"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Custom` - `type: "custom"` Custom content part. This can be used to implement provider-specific content parts. - `"custom"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `toolCallId: string` ID of the tool call that this result is associated with. - `toolName: string` Name of the tool that generated this result. - `type: "tool-result"` - `"tool-result"` - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ToolApprovalRequest` Tool approval request prompt part. - `approvalId: string` ID of the tool approval. - `toolCallId: string` ID of the tool call that the approval request is for. - `type: "tool-approval-request"` - `"tool-approval-request"` - `role: "assistant"` - `"assistant"` - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Tool` A tool message. It contains the result of one or more tool calls. - `content: Array` Content of a tool message. It is an array of tool result parts. - `ToolResult` Tool result content part of a prompt. It contains the result of the tool call with the matching ID. - `output: Text | Json | ExecutionDenied | 3 more` Result of the tool call. This is a JSON-serializable object. - `Text` - `type: "text"` Text tool output that should be directly sent to the API. - `"text"` - `value: string` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Json` - `type: "json"` - `"json"` - `value: string | number | boolean | 2 more | null` A JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ExecutionDenied` - `type: "execution-denied"` Type when the user has denied the execution of the tool call. - `"execution-denied"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `reason?: string` Optional reason for the execution denial. - `ErrorText` - `type: "error-text"` - `"error-text"` - `value: string` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ErrorJson` - `type: "error-json"` - `"error-json"` - `value: string | number | boolean | 2 more | null` A JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Content` - `type: "content"` - `"content"` - `value: Array` - `Text` - `text: string` Text content. - `type: "text"` - `"text"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Media` - `data: string` - `mediaType: string` - `type: "media"` Deprecated. Use image-data or file-data instead. - `"media"` - `FileData` - `data: string` Base-64 encoded media data. - `mediaType: string` IANA media type. - `type: "file-data"` - `"file-data"` - `filename?: string` Optional filename of the file. - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `FileURL` - `type: "file-url"` - `"file-url"` - `url: string` URL of the file. - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `FileID` - `fileId: string | Record` ID of the file. If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. 'openai' or 'anthropic'. - `string` - `Record` - `type: "file-id"` - `"file-id"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ImageData` - `data: string` Base-64 encoded image data. - `mediaType: string` IANA media type. - `type: "image-data"` Images that are referenced using base64 encoded data. - `"image-data"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ImageURL` - `type: "image-url"` Images that are referenced using a URL. - `"image-url"` - `url: string` URL of the image. - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ImageFileID` - `fileId: string | Record` Image that is referenced using a provider file id. If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. 'openai' or 'anthropic'. - `string` - `Record` - `type: "image-file-id"` Images that are referenced using a provider file id. - `"image-file-id"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Custom` - `type: "custom"` Custom content part. This can be used to implement provider-specific content parts. - `"custom"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `toolCallId: string` ID of the tool call that this result is associated with. - `toolName: string` Name of the tool that generated this result. - `type: "tool-result"` - `"tool-result"` - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ToolApprovalResponse` Tool approval response prompt part. - `approvalId: string` ID of the tool approval. - `approved: boolean` Flag indicating whether the approval was granted or denied. - `type: "tool-approval-response"` - `"tool-approval-response"` - `providerExecuted?: boolean` Flag indicating whether the tool call is provider-executed. Only provider-executed tool approval responses should be sent to the model. - `reason?: string` Optional reason for the approval or denial. - `role: "tool"` - `"tool"` - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `object?: unknown` - `providerMetadata?: Record` - `temperature?: number` - `warnings?: Array` - `event: "ai:generation"` - `"ai:generation"` - `V1AutomateEventAIGenerationError` Envelope for the "ai:generation:error" event from /v1/automate. - `data: Data` Event data when AI generation error occurs - `error: string` - `iterationId: string` - `prompt: string` - `schema: unknown` - `timestamp: number` - `messages?: Array` - `event: "ai:generation:error"` - `"ai:generation:error"` - `V1AutomateEventBrowserActionCompleted` Envelope for the "browser:action_completed" event from /v1/automate. - `data: Data` Event data for action results - `iterationId: string` - `success: boolean` - `timestamp: number` - `error?: string` - `event: "browser:action_completed"` - `"browser:action_completed"` - `V1AutomateEventBrowserActionStarted` Envelope for the "browser:action_started" event from /v1/automate. - `data: Data` Event data for action execution - `action: string` - `iterationId: string` - `timestamp: number` - `ref?: string | null` - `value?: string | null` - `event: "browser:action_started"` - `"browser:action_started"` - `V1AutomateEventBrowserNavigated` Envelope for the "browser:navigated" event from /v1/automate. - `data: Data` Event data when navigating to a page - `iterationId: string` - `timestamp: number` - `title: string` - `url: string` - `event: "browser:navigated"` - `"browser:navigated"` - `V1AutomateEventBrowserReconnected` Envelope for the "browser:reconnected" event from /v1/automate. - `data: Data` Event data when the browser reconnects after a mid-task disconnect - `endpointIndex: number` 1-based index of the CDP endpoint now in use - `iterationId: string` - `startingUrl: string` The original starting URL the agent is restarting execution from - `timestamp: number` - `total: number` Total number of configured CDP endpoints - `event: "browser:reconnected"` - `"browser:reconnected"` - `V1AutomateEventBrowserScreenshotCaptured` Envelope for the "browser:screenshot_captured" event from /v1/automate. - `data: Data` Event data for screenshot capture - `format: "jpeg" | "png"` - `"jpeg"` - `"png"` - `iterationId: string` - `size: number` - `timestamp: number` - `event: "browser:screenshot_captured"` - `"browser:screenshot_captured"` - `V1AutomateEventBrowserScreenshotCapturedImage` Envelope for the "browser:screenshot_captured_image" event from /v1/automate. - `data: Data` Event data for screenshot image capture with full image data This event contains the complete screenshot and can be very large - `image: string` - `iterationId: string` - `mediaType: "image/jpeg" | "image/png"` - `"image/jpeg"` - `"image/png"` - `timestamp: number` - `event: "browser:screenshot_captured_image"` - `"browser:screenshot_captured_image"` - `V1AutomateEventCdpEndpointConnected` Envelope for the "cdp:endpoint_connected" event from /v1/automate. - `data: Data` Event data when a CDP endpoint is successfully connected to - `endpointIndex: number` 1-based index of the endpoint that connected - `iterationId: string` - `timestamp: number` - `total: number` Total number of configured CDP endpoints - `event: "cdp:endpoint_connected"` - `"cdp:endpoint_connected"` - `V1AutomateEventCdpEndpointCycle` Envelope for the "cdp:endpoint_cycle" event from /v1/automate. - `data: Data` Event data when a CDP endpoint fails and the next one is being tried - `attempt: number` 1-based index of the endpoint attempt that failed - `error: string` Sanitized error identifier from the failed connection attempt (error.name, not error.message — full messages may contain endpoint URLs) - `iterationId: string` - `timestamp: number` - `total: number` Total number of configured CDP endpoints - `event: "cdp:endpoint_cycle"` - `"cdp:endpoint_cycle"` - `V1AutomateEventComplete` Envelope for the "complete" event from /v1/automate. - `data: Data` Payload for the `complete` stream event. Structurally identical to TaskExecutionResult from webAgent.ts — the `complete` event's data is the agent's final TaskExecutionResult, stringified onto the SSE stream. - `finalAnswer: string | null` Final answer or result from the agent - `stats: Stats` Execution statistics - `actions: number` - `durationMs: number` - `endTime: number` - `iterations: number` - `startTime: number` - `success: boolean` Whether the task completed successfully - `error?: Error` Structured error information for failed tasks - `code: "TASK_ABORTED" | "MAX_ITERATIONS" | "MAX_ERRORS" | "TASK_FAILED"` Error codes for task failures - `"TASK_ABORTED"` - `"MAX_ITERATIONS"` - `"MAX_ERRORS"` - `"TASK_FAILED"` - `message: string` Human-readable error message - `event: "complete"` - `"complete"` - `V1AutomateEventDone` Envelope for the "done" event from /v1/automate. - `data: Record` Payload for the `done` stream terminator event. Empty today; reserved for future metadata. - `event: "done"` - `"done"` - `V1AutomateEventError` Envelope for the "error" event from /v1/automate. - `data: Data` Payload for the top-level `error` stream event. Emitted when an uncaught error escapes the task runner. Mirrors `ErrorResponse` from the server package's `taskRunner.ts` — kept structurally aligned so schema and runtime stay consistent. Distinct from agent-level error events like `ai:generation:error` and `task:validation_error`, which are emitted through the normal event emitter during the agent loop. - `error: Error` - `code: string` - `message: string` - `timestamp: string` ISO-8601 timestamp - `success: false` - `false` - `event: "error"` - `"error"` - `V1AutomateEventInteractiveFormDataError` Envelope for the "interactive:form_data:error" event from /v1/automate. - `data: Data` Event data when form validation fails and the agent re-requests data. Carries both the error context and the fields that need new values. Callers respond to this the same way as a request event. - `fieldErrors: Record` Per-field error messages from validation (field ref -> error text) - `fields: Array` - `fieldType: "text" | "email" | "phone" | 8 more` Semantic field type - `"text"` - `"email"` - `"phone"` - `"date"` - `"number"` - `"select"` - `"checkbox"` - `"radio"` - `"textarea"` - `"password"` - `"other"` - `label: string` The field's visible label - `ref: string` Element ref from the accessibility tree (e.g., "E42") - `required: boolean` Whether this field must be filled - `currentValue?: string` Current value if already partially filled - `description?: string` Additional context (e.g., validation error message on re-request) - `options?: Array` Available options for select/radio fields - `formDescription: string` - `iterationId: string` - `pageTitle: string` - `pageUrl: string` - `requestId: string` - `timestamp: number` - `event: "interactive:form_data:error"` - `"interactive:form_data:error"` - `V1AutomateEventInteractiveFormDataRequest` Envelope for the "interactive:form_data:request" event from /v1/automate. - `data: Data` Event data when the agent requests user data for form fields - `fields: Array` - `fieldType: "text" | "email" | "phone" | 8 more` Semantic field type - `"text"` - `"email"` - `"phone"` - `"date"` - `"number"` - `"select"` - `"checkbox"` - `"radio"` - `"textarea"` - `"password"` - `"other"` - `label: string` The field's visible label - `ref: string` Element ref from the accessibility tree (e.g., "E42") - `required: boolean` Whether this field must be filled - `currentValue?: string` Current value if already partially filled - `description?: string` Additional context (e.g., validation error message on re-request) - `options?: Array` Available options for select/radio fields - `formDescription: string` - `iterationId: string` - `pageTitle: string` - `pageUrl: string` - `requestId: string` - `timestamp: number` - `event: "interactive:form_data:request"` - `"interactive:form_data:request"` - `V1AutomateEventSystemDebugCompression` Envelope for the "system:debug_compression" event from /v1/automate. - `data: Data` Event data for compression debug info - `compressedSize: number` - `compressionPercent: number` - `iterationId: string` - `originalSize: number` - `timestamp: number` - `event: "system:debug_compression"` - `"system:debug_compression"` - `V1AutomateEventSystemDebugMessage` Envelope for the "system:debug_message" event from /v1/automate. - `data: Data` Event data for message debug info - `iterationId: string` - `messages: Array` - `timestamp: number` - `event: "system:debug_message"` - `"system:debug_message"` - `V1AutomateEventTaskAborted` Envelope for the "task:aborted" event from /v1/automate. - `data: Data` Event data when a task is aborted - `finalAnswer: string` - `iterationId: string` - `reason: string` - `timestamp: number` - `event: "task:aborted"` - `"task:aborted"` - `V1AutomateEventTaskCompleted` Envelope for the "task:completed" event from /v1/automate. - `data: Data` Event data when a task is completed - `finalAnswer: string | null` - `iterationId: string` - `timestamp: number` - `success?: boolean` - `event: "task:completed"` - `"task:completed"` - `V1AutomateEventTaskMetrics` Envelope for the "task:metrics" event from /v1/automate. - `data: Data` - `aiGenerationCount: number` - `aiGenerationErrorCount: number` - `eventCounts: Record` - `iterationId: string` - `stepCount: number` - `timestamp: number` - `totalInputTokens: number` - `totalOutputTokens: number` - `event: "task:metrics"` - `"task:metrics"` - `V1AutomateEventTaskMetricsIncremental` Envelope for the "task:metrics_incremental" event from /v1/automate. - `data: Data` - `aiGenerationCount: number` - `aiGenerationErrorCount: number` - `eventCounts: Record` - `iterationId: string` - `stepCount: number` - `timestamp: number` - `totalInputTokens: number` - `totalOutputTokens: number` - `event: "task:metrics_incremental"` - `"task:metrics_incremental"` - `V1AutomateEventTaskSetup` Envelope for the "task:setup" event from /v1/automate. - `data: Data` Event data when a task is setup - `browserName: string` - `iterationId: string` - `task: string` - `timestamp: number` - `data?: unknown` - `guardrails?: string` - `hasApiKey?: boolean` - `keySource?: "global" | "env" | "not_set"` - `"global"` - `"env"` - `"not_set"` - `model?: string` - `provider?: string` - `proxy?: string` - `pwCdpEndpoint?: string` - `pwCdpEndpointCount?: number` Total number of CDP endpoints configured (index, not URLs) - `pwCdpEndpoints?: Array` - `pwEndpoint?: string` - `url?: string` - `vision?: boolean` - `event: "task:setup"` - `"task:setup"` - `V1AutomateEventTaskStarted` Envelope for the "task:started" event from /v1/automate. - `data: Data` Event data when a task is started - `iterationId: string` - `plan: string` - `successCriteria: string` - `task: string` - `timestamp: number` - `url: string` - `actionItems?: Array` - `event: "task:started"` - `"task:started"` - `V1AutomateEventTaskTraceContext` Envelope for the "task:trace_context" event from /v1/automate. - `data: Data` Payload for the task:trace_context event. Carries the OpenTelemetry trace ID for this /v1/automate request so consumers can deep-link to distributed-tracing UIs (e.g. Cloud Trace, Cloud Logging) for the run. - `traceId: string` W3C trace ID — 32-character lowercase hexadecimal string. - `event: "task:trace_context"` - `"task:trace_context"` - `V1AutomateEventTaskValidated` Envelope for the "task:validated" event from /v1/automate. - `data: Data` Event data for task validation - `completionQuality: "failed" | "partial" | "complete" | "excellent"` - `"failed"` - `"partial"` - `"complete"` - `"excellent"` - `finalAnswer: string` - `iterationId: string` - `observation: string` - `timestamp: number` - `feedback?: string` - `event: "task:validated"` - `"task:validated"` - `V1AutomateEventTaskValidationError` Envelope for the "task:validation_error" event from /v1/automate. - `data: Data` Event data for validation errors during action response processing - `errors: Array` - `iterationId: string` - `rawResponse: unknown` - `retryCount: number` - `timestamp: number` - `event: "task:validation_error"` - `"task:validation_error"` ### Example ```typescript import Tabstack from '@tabstack/sdk'; const client = new Tabstack({ apiKey: process.env['TABSTACK_API_KEY'], // This is the default and can be omitted }); const automateEvent = await client.agent.automate({ task: 'Find the top 3 trending repositories and extract their names, descriptions, and star counts', guardrails: "browse and extract only, don't interact with repositories", url: 'https://github.com/trending', }); console.log(automateEvent); ``` #### Response ```json event: start data: {"task": "Find the top 3 trending repositories", "url": "https://github.com/trending"} event: agent:processing data: {"operation": "Creating task plan", "hasScreenshot": false} event: browser:navigated data: {"title": "Trending - GitHub", "url": "https://github.com/trending"} event: agent:extracted data: {"extractedData": "[{\"name\": \"awesome-ai\", \"stars\": \"45.2k\"}]"} event: task:completed data: {"success": true, "finalAnswer": "Top 3 trending repos extracted"} event: complete data: {"success": true} event: done data: {} ``` ## Submit Input Response `client.agent.automateInput(stringrequestID, AgentAutomateInputParamsbody, RequestOptionsoptions?): AgentAutomateInputResponse` **post** `/automate/{requestID}/input` Submit a response to an interactive form data request from an in-progress automation task. When the AI agent encounters a form requiring user data, it emits an `interactive:form_data:request` or `interactive:form_data:error` SSE event containing a `requestId`. Use this endpoint to provide the requested data or cancel the request. **Lifecycle:** - Input requests expire after 2 minutes by default - Expired or already-answered requests return `410 Gone` - Successful submissions return `202 Accepted` (fire-and-forget from caller's perspective) ### Parameters - `requestID: string` - `body: AgentAutomateInputParams` - `cancelled?: boolean` Set to true to cancel/decline the request - `fields?: Array` Field values as array of {ref, value} pairs (required when not cancelled) - `ref?: string` - `value?: string` ### Returns - `AgentAutomateInputResponse` - `status?: string` ### Example ```typescript import Tabstack from '@tabstack/sdk'; const client = new Tabstack({ apiKey: process.env['TABSTACK_API_KEY'], // This is the default and can be omitted }); const response = await client.agent.automateInput('requestID'); console.log(response.status); ``` #### Response ```json { "status": "accepted" } ``` ## Research `client.agent.research(AgentResearchParamsbody, RequestOptionsoptions?): ResearchEvent | Stream` **post** `/research` Execute AI-powered research queries that search the web, analyze sources, and synthesize comprehensive answers. This endpoint **always streams** responses using Server-Sent Events (SSE). **Streaming Response:** - All responses are streamed using Server-Sent Events (`text/event-stream`) - Real-time progress updates as research progresses through phases **Research Modes:** - `fast` - Quick answers with minimal web searches (default) - `balanced` - Standard research with multiple iterations **Use Cases:** - Answering complex questions with cited sources - Synthesizing information from multiple web sources - Research reports on specific topics - Fact-checking and verification tasks ### Parameters - `body: AgentResearchParams` - `query: string` The research query or question to answer. Maximum 10,000 characters. - `fetch_timeout?: number` Timeout in seconds for fetching web pages - `mode?: "fast" | "balanced"` Research mode: fast (quick answers, default), balanced (standard research) - `"fast"` - `"balanced"` - `nocache?: boolean` Skip cache and force fresh research ### Returns - `ResearchEvent = V1ResearchEventAnalyzingEnd | V1ResearchEventAnalyzingStart | V1ResearchEventComplete | 20 more` A Server-Sent Event from /v1/research. Typed discriminated union keyed on event. - `V1ResearchEventAnalyzingEnd` Envelope for the "analyzing:end" event from /v1/research. - `data: Data` - `analyzed: number` - `failed: number` - `iteration: number` - `message: string` - `samples: Array` - `domain: string` - `title: string` - `url: string` - `urlSource: "user-input" | "search-result" | "extracted-link"` URL source tracking - where a URL came from - `"user-input"` - `"search-result"` - `"extracted-link"` - `relevance?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `reliability?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `summary?: string` - `timestamp: number` - `event: "analyzing:end"` - `"analyzing:end"` - `V1ResearchEventAnalyzingStart` Envelope for the "analyzing:start" event from /v1/research. - `data: Data` - `iteration: number` - `message: string` - `pageCount: number` - `timestamp: number` - `event: "analyzing:start"` - `"analyzing:start"` - `V1ResearchEventComplete` Envelope for the "complete" event from /v1/research. - `data: Data` complete - Research finished successfully - `message: string` - `metadata: Metadata` Research metadata Note: citedPages, gapEvaluations, outline, and judgments are optional to support fast mode, which skips these phases for maximum speed. - `executedQueries: Array>` - `mode: "fast" | "balanced" | "deep" | 2 more` Research mode determines depth, thinking budget, and quality controls Modes (in order of cost/thoroughness): - **fast**: Quick answers with minimal validation (~$2, 1 iteration, no judge) - **balanced**: Standard research with moderate depth (~$8, 3 iterations, Flash models, no judge) - **deep**: Thorough research with judge review (~$15, 5 iterations, Flash models, with judge) - **max**: Maximum quality with Pro models (~$40, 5 iterations, Pro models, with judge) - **ultra**: Ultimate tier - all Pro models, 10 iterations (expensive, for when accuracy is paramount) - `"fast"` - `"balanced"` - `"deep"` - `"max"` - `"ultra"` - `prompt: string` - `queryComplexity: "simple" | "moderate" | "complex"` - `"simple"` - `"moderate"` - `"complex"` - `researchObjective: string` - `researchPlan: string` - `researchQuestions: Array` - `totalPagesAnalyzed: number` Total pages analyzed across all iterations - `citedPages?: Array` Pages cited in the report, ordered by first citation appearance - `id: string` - `claims: Array` - `sourceQueries: Array` - `url: string` - `depth?: number` - `fullText?: string` Full page text (fetched markdown or search excerpts). Only populated when `includeFullText: true` in ResearchOptions. - Fast mode: Parallel API excerpts (~5000 chars) - Other modes: Fetched page markdown - `parentUrl?: string` - `relevance?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `reliability?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `summary?: string` LLM-generated summary. Undefined in fast mode (no content analysis). - `title?: string` - `urlSource?: "user-input" | "search-result" | "extracted-link"` URL source tracking - where a URL came from - `"user-input"` - `"search-result"` - `"extracted-link"` - `gapEvaluations?: Array` - `gapDescription: string` Based on unanswered/partial questions, what specific information is still needed? - `questionAssessments: Array` Assessment of each research question's status and findings - `findings: string` What we learned (if answered/partial) or what's missing (if unanswered) - `question: string` The research question being assessed - `status: "answered" | "partial" | "unanswered"` Status: answered (clear info), partial (some info, gaps remain), unanswered (no relevant info) - `"answered"` - `"partial"` - `"unanswered"` - `researchCoverage: "Light" | "Moderate" | "Solid" | "Comprehensive"` Research coverage level - assesses quality across all questions. Hierarchy: Light < Moderate < Solid < Comprehensive - **Light**: Basic info on some questions, most need more depth → Continue - **Moderate**: Multiple questions answered, some remain partial → Continue - **Solid**: Most questions well-answered with validated sources → Sufficient to stop - **Comprehensive**: All questions thoroughly answered, exceptional depth → Definitely stop - `"Light"` - `"Moderate"` - `"Solid"` - `"Comprehensive"` - `shouldContinueResearch: boolean` Explicit decision: should research continue with another iteration? - Considers: how many questions unanswered/partial, coverage for mode, remaining iterations - Drives query generation: true → generate queries, false → stop researching - `newResearchQuestions?: Array` New research questions to add (optional, use sparingly) - Only if original decomposition missed something critical - Maximum 2-3 new questions total across all iterations - Most iterations should return empty array or omit this field - `searchQueries?: Array` Search queries to address identified gaps (only when shouldContinueResearch is true) - Target unanswered questions first, then partial questions - 3-10 targeted queries if shouldContinueResearch is true - Omit or provide empty array if shouldContinueResearch is false - `judgments?: Array` - `approved: boolean` - `observation: string` - `score: number` - `feedback?: string` - `metrics?: Metrics` Complete research metrics - `cachedFetches: number` Cached fetch count (subset of fetches) - `cachedSearches: Record` Cached search count by provider name (subset of searches) - `fetches: number` Fetch count (number of pages fetched) - `iterations: number` Number of research iterations performed - `phases: Record` Phase timings with duration in milliseconds - `duration: number` - `robotsBlocked: number` Number of URLs blocked by robots.txt - `searches: Record` Search count by provider name (e.g., "bright-data", "parallel") - `successRates: SuccessRates` Success rate metrics - `analyzes: number` - `fetches: number` - `searches: number` - `tokens: Record` Token usage by model ID (e.g., "gemini-2.5-flash") - `input: number` - `output: number` - `totalDuration: number` Total duration in milliseconds - `outline?: Outline` Report outline from research writer - `directAnswer: string` - `keyTakeaways: Array` - `outline: string` - `relevantSourceIds: Array` - `urlSources?: URLSources` - `extractedLinks: number` - `searchResults: number` - `userProvided: number` - `report: string` - `timestamp: number` - `event: "complete"` - `"complete"` - `V1ResearchEventError` Envelope for the "error" event from /v1/research. - `data: Data` error - Research failed - `error: Error` - `message: string` - `name: string` - `stack?: string` - `message: string` - `timestamp: number` - `activity?: "prefetching" | "planning" | "iteration" | 7 more` Activity types for research workflow - `"prefetching"` - `"planning"` - `"iteration"` - `"searching"` - `"analyzing"` - `"following"` - `"evaluating"` - `"outlining"` - `"writing"` - `"judging"` - `iteration?: number` - `event: "error"` - `"error"` - `V1ResearchEventEvaluatingEnd` Envelope for the "evaluating:end" event from /v1/research. - `data: Data` - `coverage: "Light" | "Moderate" | "Solid" | "Comprehensive"` - `"Light"` - `"Moderate"` - `"Solid"` - `"Comprehensive"` - `gaps: string` - `iteration: number` - `message: string` - `nextQueries: Array` - `questionAssessments: Array` - `findings: string` What we learned (if answered/partial) or what's missing (if unanswered) - `question: string` The research question being assessed - `status: "answered" | "partial" | "unanswered"` Status: answered (clear info), partial (some info, gaps remain), unanswered (no relevant info) - `shouldContinue: boolean` - `timestamp: number` - `event: "evaluating:end"` - `"evaluating:end"` - `V1ResearchEventEvaluatingStart` Envelope for the "evaluating:start" event from /v1/research. - `data: Data` - `iteration: number` - `message: string` - `pagesAnalyzed: number` Total pages analyzed so far (including this iteration) - `questionCount: number` Number of research questions being assessed - `timestamp: number` - `event: "evaluating:start"` - `"evaluating:start"` - `V1ResearchEventFollowingEnd` Envelope for the "following:end" event from /v1/research. - `data: Data` - `failed: number` - `followed: number` - `iteration: number` - `message: string` - `samples: Array` - `domain: string` - `title: string` - `url: string` - `urlSource: "user-input" | "search-result" | "extracted-link"` URL source tracking - where a URL came from - `"user-input"` - `"search-result"` - `"extracted-link"` - `relevance?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `reliability?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `summary?: string` - `timestamp: number` - `event: "following:end"` - `"following:end"` - `V1ResearchEventFollowingStart` Envelope for the "following:start" event from /v1/research. - `data: Data` - `iteration: number` - `linkCount: number` - `message: string` - `timestamp: number` - `event: "following:start"` - `"following:start"` - `V1ResearchEventIterationEnd` Envelope for the "iteration:end" event from /v1/research. - `data: Data` - `isLast: boolean` Whether this is the final iteration - `iteration: number` - `message: string` - `timestamp: number` - `stopReason?: "max_iterations" | "coverage_sufficient"` Why research iterations stopped (only present when isLast is true) - `"max_iterations"` - `"coverage_sufficient"` - `event: "iteration:end"` - `"iteration:end"` - `V1ResearchEventIterationStart` Envelope for the "iteration:start" event from /v1/research. - `data: Data` - `iteration: number` - `maxIterations: number` Maximum iterations for this research mode - `message: string` - `queries: Array` Search queries to execute in this iteration - `timestamp: number` - `event: "iteration:start"` - `"iteration:start"` - `V1ResearchEventJudgingEnd` Envelope for the "judging:end" event from /v1/research. - `data: Data` - `approved: boolean` - `attempt: number` - `message: string` - `score: number` - `timestamp: number` - `feedback?: string` - `event: "judging:end"` - `"judging:end"` - `V1ResearchEventJudgingStart` Envelope for the "judging:start" event from /v1/research. - `data: Data` - `attempt: number` - `maxAttempts: number` Maximum attempts allowed (1 + maxRevisions) - `message: string` - `timestamp: number` - `event: "judging:start"` - `"judging:start"` - `V1ResearchEventOutliningEnd` Envelope for the "outlining:end" event from /v1/research. - `data: Data` - `message: string` - `sourcesSelected: number` - `timestamp: number` - `event: "outlining:end"` - `"outlining:end"` - `V1ResearchEventOutliningStart` Envelope for the "outlining:start" event from /v1/research. - `data: Data` - `message: string` - `pagesAnalyzed: number` Total pages analyzed across all iterations - `qualityPageCount: number` Pages that meet quality threshold (medium+ relevance and reliability) - `timestamp: number` - `event: "outlining:start"` - `"outlining:start"` - `V1ResearchEventPlanningEnd` Envelope for the "planning:end" event from /v1/research. - `data: Data` - `complexity: "simple" | "moderate" | "complex"` - `"simple"` - `"moderate"` - `"complex"` - `message: string` - `objective: string` - `plan: string` - `queries: Array` - `questions: Array` - `timestamp: number` - `event: "planning:end"` - `"planning:end"` - `V1ResearchEventPlanningStart` Envelope for the "planning:start" event from /v1/research. - `data: Data` - `hasPrefetchedContext: boolean` Whether prefetched user-provided URLs exist for context - `message: string` - `timestamp: number` - `event: "planning:start"` - `"planning:start"` - `V1ResearchEventPrefetchingEnd` Envelope for the "prefetching:end" event from /v1/research. - `data: Data` - `failed: number` - `fetched: number` - `message: string` - `timestamp: number` - `event: "prefetching:end"` - `"prefetching:end"` - `V1ResearchEventPrefetchingStart` Envelope for the "prefetching:start" event from /v1/research. - `data: Data` - `message: string` - `timestamp: number` - `urlCount: number` - `urls: Array` - `event: "prefetching:start"` - `"prefetching:start"` - `V1ResearchEventSearchingEnd` Envelope for the "searching:end" event from /v1/research. - `data: Data` - `iteration: number` - `message: string` - `timestamp: number` - `urlsFound: number` - `urlsNew: number` - `event: "searching:end"` - `"searching:end"` - `V1ResearchEventSearchingStart` Envelope for the "searching:start" event from /v1/research. - `data: Data` - `iteration: number` - `message: string` - `queries: Array` - `timestamp: number` - `event: "searching:start"` - `"searching:start"` - `V1ResearchEventStart` Envelope for the "start" event from /v1/research. - `data: Data` start - Research begins - `message: string` - `timestamp: number` - `event: "start"` - `"start"` - `V1ResearchEventWritingEnd` Envelope for the "writing:end" event from /v1/research. - `data: Data` - `attempt: number` - `message: string` - `timestamp: number` - `event: "writing:end"` - `"writing:end"` - `V1ResearchEventWritingStart` Envelope for the "writing:start" event from /v1/research. - `data: Data` - `attempt: number` - `isRevision: boolean` Whether this is a revision attempt (attempt > 1) - `maxAttempts: number` Maximum attempts allowed (1 + maxRevisions) - `message: string` - `timestamp: number` - `previousScore?: number` Previous judgment score if this is a revision - `event: "writing:start"` - `"writing:start"` ### Example ```typescript import Tabstack from '@tabstack/sdk'; const client = new Tabstack({ apiKey: process.env['TABSTACK_API_KEY'], // This is the default and can be omitted }); const researchEvent = await client.agent.research({ query: 'What are the latest developments in quantum computing?', }); console.log(researchEvent); ``` ## Domain Types ### Automate Event - `AutomateEvent = V1AutomateEventAgentAction | V1AutomateEventAgentExtracted | V1AutomateEventAgentProcessing | 30 more` A Server-Sent Event from /v1/automate. Typed discriminated union keyed on event. - `V1AutomateEventAgentAction` Envelope for the "agent:action" event from /v1/automate. - `data: Data` Event data for action execution - `action: string` - `iterationId: string` - `timestamp: number` - `ref?: string | null` - `value?: string | null` - `event: "agent:action"` - `"agent:action"` - `V1AutomateEventAgentExtracted` Envelope for the "agent:extracted" event from /v1/automate. - `data: Data` Event data for extracted data - `extractedData: string` - `iterationId: string` - `timestamp: number` - `event: "agent:extracted"` - `"agent:extracted"` - `V1AutomateEventAgentProcessing` Envelope for the "agent:processing" event from /v1/automate. - `data: Data` Event data for when the agent is waiting for model generation - `hasScreenshot: boolean` - `iterationId: string` - `operation: string` - `timestamp: number` - `event: "agent:processing"` - `"agent:processing"` - `V1AutomateEventAgentReasoned` Envelope for the "agent:reasoned" event from /v1/automate. - `data: Data` Event data for agent reasoning - `iterationId: string` - `reasoning: string` - `timestamp: number` - `event: "agent:reasoned"` - `"agent:reasoned"` - `V1AutomateEventAgentStatus` Envelope for the "agent:status" event from /v1/automate. - `data: Data` Event data for status messages - `iterationId: string` - `message: string` - `timestamp: number` - `event: "agent:status"` - `"agent:status"` - `V1AutomateEventAgentStep` Envelope for the "agent:step" event from /v1/automate. - `data: Data` Event data for agent step tracking (each loop iteration) - `currentIteration: number` - `iterationId: string` - `timestamp: number` - `event: "agent:step"` - `"agent:step"` - `V1AutomateEventAgentWaiting` Envelope for the "agent:waiting" event from /v1/automate. - `data: Data` Event data for waiting notifications - `iterationId: string` - `seconds: number` - `timestamp: number` - `event: "agent:waiting"` - `"agent:waiting"` - `V1AutomateEventAIGeneration` Envelope for the "ai:generation" event from /v1/automate. - `data: Data` Event data when AI generation occurs - `finishReason: "stop" | "length" | "content-filter" | 3 more` - `"stop"` - `"length"` - `"content-filter"` - `"tool-calls"` - `"error"` - `"other"` - `iterationId: string` - `prompt: string` - `schema: unknown` - `timestamp: number` - `usage: Usage` - `inputTokens?: number` - `outputTokens?: number` - `totalTokens?: number` - `messages?: Array` - `System` A system message. It can contain system information. Note: using the "system" part of the prompt is strongly preferred to increase the resilience against prompt injection attacks, and because not all providers support several system messages. - `content: string` - `role: "system"` - `"system"` - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `User` A user message. It can contain text or a combination of text and images. - `content: string | Array` Content of a user message. It can be a string or an array of text and image parts. - `string` - `Array` - `Text` Text content part of a prompt. It contains a string of text. - `text: string` The text content. - `type: "text"` - `"text"` - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Image` Image content part of a prompt. It contains an image. - `image: string | UnionMember1 | ByteLength | V1GlobalBuffer` Image data. Can either be: - data: a base64-encoded string, a Uint8Array, an ArrayBuffer, or a Buffer - URL: a URL that points to the image - `string` - `UnionMember1` - `buffer: Buffer` - `byteLength: number` - `byteLength: number` - `byteOffset: number` - `BYTES_PER_ELEMENT: number` - `length: number` - `ByteLength` - `byteLength: number` - `V1GlobalBuffer` - `buffer: Buffer` - `byteLength: number` - `byteLength: number` - `byteOffset: number` - `BYTES_PER_ELEMENT: number` - `length: number` - `type: "image"` - `"image"` - `mediaType?: string` Optional IANA media type of the image. - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `File` File content part of a prompt. It contains a file. - `data: string | UnionMember1 | ByteLength | V1GlobalBuffer` File data. Can either be: - data: a base64-encoded string, a Uint8Array, an ArrayBuffer, or a Buffer - URL: a URL that points to the image - `string` - `UnionMember1` - `buffer: Buffer` - `byteLength: number` - `byteLength: number` - `byteOffset: number` - `BYTES_PER_ELEMENT: number` - `length: number` - `ByteLength` - `byteLength: number` - `V1GlobalBuffer` - `mediaType: string` IANA media type of the file. - `type: "file"` - `"file"` - `filename?: string` Optional filename of the file. - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `role: "user"` - `"user"` - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Assistant` An assistant message. It can contain text, tool calls, or a combination of text and tool calls. - `content: string | Array` Content of an assistant message. It can be a string or an array of text, image, reasoning, redacted reasoning, and tool call parts. - `string` - `Array` - `Text` Text content part of a prompt. It contains a string of text. - `text: string` The text content. - `type: "text"` - `"text"` - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `File` File content part of a prompt. It contains a file. - `data: string | UnionMember1 | ByteLength | V1GlobalBuffer` File data. Can either be: - data: a base64-encoded string, a Uint8Array, an ArrayBuffer, or a Buffer - URL: a URL that points to the image - `string` - `UnionMember1` - `buffer: Buffer` - `byteLength: number` - `byteLength: number` - `byteOffset: number` - `BYTES_PER_ELEMENT: number` - `length: number` - `ByteLength` - `byteLength: number` - `V1GlobalBuffer` - `mediaType: string` IANA media type of the file. - `type: "file"` - `"file"` - `filename?: string` Optional filename of the file. - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Reasoning` Reasoning content part of a prompt. It contains a reasoning. - `text: string` The reasoning text. - `type: "reasoning"` - `"reasoning"` - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ToolCall` Tool call content part of a prompt. It contains a tool call (usually generated by the AI model). - `input: unknown` Arguments of the tool call. This is a JSON-serializable object that matches the tool's input schema. - `toolCallId: string` ID of the tool call. This ID is used to match the tool call with the tool result. - `toolName: string` Name of the tool that is being called. - `type: "tool-call"` - `"tool-call"` - `providerExecuted?: boolean` Whether the tool call was executed by the provider. - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ToolResult` Tool result content part of a prompt. It contains the result of the tool call with the matching ID. - `output: Text | Json | ExecutionDenied | 3 more` Result of the tool call. This is a JSON-serializable object. - `Text` - `type: "text"` Text tool output that should be directly sent to the API. - `"text"` - `value: string` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Json` - `type: "json"` - `"json"` - `value: string | number | boolean | 2 more | null` A JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ExecutionDenied` - `type: "execution-denied"` Type when the user has denied the execution of the tool call. - `"execution-denied"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `reason?: string` Optional reason for the execution denial. - `ErrorText` - `type: "error-text"` - `"error-text"` - `value: string` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ErrorJson` - `type: "error-json"` - `"error-json"` - `value: string | number | boolean | 2 more | null` A JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Content` - `type: "content"` - `"content"` - `value: Array` - `Text` - `text: string` Text content. - `type: "text"` - `"text"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Media` - `data: string` - `mediaType: string` - `type: "media"` Deprecated. Use image-data or file-data instead. - `"media"` - `FileData` - `data: string` Base-64 encoded media data. - `mediaType: string` IANA media type. - `type: "file-data"` - `"file-data"` - `filename?: string` Optional filename of the file. - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `FileURL` - `type: "file-url"` - `"file-url"` - `url: string` URL of the file. - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `FileID` - `fileId: string | Record` ID of the file. If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. 'openai' or 'anthropic'. - `string` - `Record` - `type: "file-id"` - `"file-id"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ImageData` - `data: string` Base-64 encoded image data. - `mediaType: string` IANA media type. - `type: "image-data"` Images that are referenced using base64 encoded data. - `"image-data"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ImageURL` - `type: "image-url"` Images that are referenced using a URL. - `"image-url"` - `url: string` URL of the image. - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ImageFileID` - `fileId: string | Record` Image that is referenced using a provider file id. If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. 'openai' or 'anthropic'. - `string` - `Record` - `type: "image-file-id"` Images that are referenced using a provider file id. - `"image-file-id"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Custom` - `type: "custom"` Custom content part. This can be used to implement provider-specific content parts. - `"custom"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `toolCallId: string` ID of the tool call that this result is associated with. - `toolName: string` Name of the tool that generated this result. - `type: "tool-result"` - `"tool-result"` - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ToolApprovalRequest` Tool approval request prompt part. - `approvalId: string` ID of the tool approval. - `toolCallId: string` ID of the tool call that the approval request is for. - `type: "tool-approval-request"` - `"tool-approval-request"` - `role: "assistant"` - `"assistant"` - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Tool` A tool message. It contains the result of one or more tool calls. - `content: Array` Content of a tool message. It is an array of tool result parts. - `ToolResult` Tool result content part of a prompt. It contains the result of the tool call with the matching ID. - `output: Text | Json | ExecutionDenied | 3 more` Result of the tool call. This is a JSON-serializable object. - `Text` - `type: "text"` Text tool output that should be directly sent to the API. - `"text"` - `value: string` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Json` - `type: "json"` - `"json"` - `value: string | number | boolean | 2 more | null` A JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ExecutionDenied` - `type: "execution-denied"` Type when the user has denied the execution of the tool call. - `"execution-denied"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `reason?: string` Optional reason for the execution denial. - `ErrorText` - `type: "error-text"` - `"error-text"` - `value: string` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ErrorJson` - `type: "error-json"` - `"error-json"` - `value: string | number | boolean | 2 more | null` A JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Content` - `type: "content"` - `"content"` - `value: Array` - `Text` - `text: string` Text content. - `type: "text"` - `"text"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Media` - `data: string` - `mediaType: string` - `type: "media"` Deprecated. Use image-data or file-data instead. - `"media"` - `FileData` - `data: string` Base-64 encoded media data. - `mediaType: string` IANA media type. - `type: "file-data"` - `"file-data"` - `filename?: string` Optional filename of the file. - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `FileURL` - `type: "file-url"` - `"file-url"` - `url: string` URL of the file. - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `FileID` - `fileId: string | Record` ID of the file. If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. 'openai' or 'anthropic'. - `string` - `Record` - `type: "file-id"` - `"file-id"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ImageData` - `data: string` Base-64 encoded image data. - `mediaType: string` IANA media type. - `type: "image-data"` Images that are referenced using base64 encoded data. - `"image-data"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ImageURL` - `type: "image-url"` Images that are referenced using a URL. - `"image-url"` - `url: string` URL of the image. - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ImageFileID` - `fileId: string | Record` Image that is referenced using a provider file id. If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. 'openai' or 'anthropic'. - `string` - `Record` - `type: "image-file-id"` Images that are referenced using a provider file id. - `"image-file-id"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `Custom` - `type: "custom"` Custom content part. This can be used to implement provider-specific content parts. - `"custom"` - `providerOptions?: Record>` Provider-specific options. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `toolCallId: string` ID of the tool call that this result is associated with. - `toolName: string` Name of the tool that generated this result. - `type: "tool-result"` - `"tool-result"` - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `ToolApprovalResponse` Tool approval response prompt part. - `approvalId: string` ID of the tool approval. - `approved: boolean` Flag indicating whether the approval was granted or denied. - `type: "tool-approval-response"` - `"tool-approval-response"` - `providerExecuted?: boolean` Flag indicating whether the tool call is provider-executed. Only provider-executed tool approval responses should be sent to the model. - `reason?: string` Optional reason for the approval or denial. - `role: "tool"` - `"tool"` - `providerOptions?: Record>` Additional provider-specific metadata. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. - `string` - `number` - `boolean` - `Record` - `string` - `number` - `boolean` - `unknown` - `Array` - `Array` - `string` - `number` - `boolean` - `unknown` - `Array` - `object?: unknown` - `providerMetadata?: Record` - `temperature?: number` - `warnings?: Array` - `event: "ai:generation"` - `"ai:generation"` - `V1AutomateEventAIGenerationError` Envelope for the "ai:generation:error" event from /v1/automate. - `data: Data` Event data when AI generation error occurs - `error: string` - `iterationId: string` - `prompt: string` - `schema: unknown` - `timestamp: number` - `messages?: Array` - `event: "ai:generation:error"` - `"ai:generation:error"` - `V1AutomateEventBrowserActionCompleted` Envelope for the "browser:action_completed" event from /v1/automate. - `data: Data` Event data for action results - `iterationId: string` - `success: boolean` - `timestamp: number` - `error?: string` - `event: "browser:action_completed"` - `"browser:action_completed"` - `V1AutomateEventBrowserActionStarted` Envelope for the "browser:action_started" event from /v1/automate. - `data: Data` Event data for action execution - `action: string` - `iterationId: string` - `timestamp: number` - `ref?: string | null` - `value?: string | null` - `event: "browser:action_started"` - `"browser:action_started"` - `V1AutomateEventBrowserNavigated` Envelope for the "browser:navigated" event from /v1/automate. - `data: Data` Event data when navigating to a page - `iterationId: string` - `timestamp: number` - `title: string` - `url: string` - `event: "browser:navigated"` - `"browser:navigated"` - `V1AutomateEventBrowserReconnected` Envelope for the "browser:reconnected" event from /v1/automate. - `data: Data` Event data when the browser reconnects after a mid-task disconnect - `endpointIndex: number` 1-based index of the CDP endpoint now in use - `iterationId: string` - `startingUrl: string` The original starting URL the agent is restarting execution from - `timestamp: number` - `total: number` Total number of configured CDP endpoints - `event: "browser:reconnected"` - `"browser:reconnected"` - `V1AutomateEventBrowserScreenshotCaptured` Envelope for the "browser:screenshot_captured" event from /v1/automate. - `data: Data` Event data for screenshot capture - `format: "jpeg" | "png"` - `"jpeg"` - `"png"` - `iterationId: string` - `size: number` - `timestamp: number` - `event: "browser:screenshot_captured"` - `"browser:screenshot_captured"` - `V1AutomateEventBrowserScreenshotCapturedImage` Envelope for the "browser:screenshot_captured_image" event from /v1/automate. - `data: Data` Event data for screenshot image capture with full image data This event contains the complete screenshot and can be very large - `image: string` - `iterationId: string` - `mediaType: "image/jpeg" | "image/png"` - `"image/jpeg"` - `"image/png"` - `timestamp: number` - `event: "browser:screenshot_captured_image"` - `"browser:screenshot_captured_image"` - `V1AutomateEventCdpEndpointConnected` Envelope for the "cdp:endpoint_connected" event from /v1/automate. - `data: Data` Event data when a CDP endpoint is successfully connected to - `endpointIndex: number` 1-based index of the endpoint that connected - `iterationId: string` - `timestamp: number` - `total: number` Total number of configured CDP endpoints - `event: "cdp:endpoint_connected"` - `"cdp:endpoint_connected"` - `V1AutomateEventCdpEndpointCycle` Envelope for the "cdp:endpoint_cycle" event from /v1/automate. - `data: Data` Event data when a CDP endpoint fails and the next one is being tried - `attempt: number` 1-based index of the endpoint attempt that failed - `error: string` Sanitized error identifier from the failed connection attempt (error.name, not error.message — full messages may contain endpoint URLs) - `iterationId: string` - `timestamp: number` - `total: number` Total number of configured CDP endpoints - `event: "cdp:endpoint_cycle"` - `"cdp:endpoint_cycle"` - `V1AutomateEventComplete` Envelope for the "complete" event from /v1/automate. - `data: Data` Payload for the `complete` stream event. Structurally identical to TaskExecutionResult from webAgent.ts — the `complete` event's data is the agent's final TaskExecutionResult, stringified onto the SSE stream. - `finalAnswer: string | null` Final answer or result from the agent - `stats: Stats` Execution statistics - `actions: number` - `durationMs: number` - `endTime: number` - `iterations: number` - `startTime: number` - `success: boolean` Whether the task completed successfully - `error?: Error` Structured error information for failed tasks - `code: "TASK_ABORTED" | "MAX_ITERATIONS" | "MAX_ERRORS" | "TASK_FAILED"` Error codes for task failures - `"TASK_ABORTED"` - `"MAX_ITERATIONS"` - `"MAX_ERRORS"` - `"TASK_FAILED"` - `message: string` Human-readable error message - `event: "complete"` - `"complete"` - `V1AutomateEventDone` Envelope for the "done" event from /v1/automate. - `data: Record` Payload for the `done` stream terminator event. Empty today; reserved for future metadata. - `event: "done"` - `"done"` - `V1AutomateEventError` Envelope for the "error" event from /v1/automate. - `data: Data` Payload for the top-level `error` stream event. Emitted when an uncaught error escapes the task runner. Mirrors `ErrorResponse` from the server package's `taskRunner.ts` — kept structurally aligned so schema and runtime stay consistent. Distinct from agent-level error events like `ai:generation:error` and `task:validation_error`, which are emitted through the normal event emitter during the agent loop. - `error: Error` - `code: string` - `message: string` - `timestamp: string` ISO-8601 timestamp - `success: false` - `false` - `event: "error"` - `"error"` - `V1AutomateEventInteractiveFormDataError` Envelope for the "interactive:form_data:error" event from /v1/automate. - `data: Data` Event data when form validation fails and the agent re-requests data. Carries both the error context and the fields that need new values. Callers respond to this the same way as a request event. - `fieldErrors: Record` Per-field error messages from validation (field ref -> error text) - `fields: Array` - `fieldType: "text" | "email" | "phone" | 8 more` Semantic field type - `"text"` - `"email"` - `"phone"` - `"date"` - `"number"` - `"select"` - `"checkbox"` - `"radio"` - `"textarea"` - `"password"` - `"other"` - `label: string` The field's visible label - `ref: string` Element ref from the accessibility tree (e.g., "E42") - `required: boolean` Whether this field must be filled - `currentValue?: string` Current value if already partially filled - `description?: string` Additional context (e.g., validation error message on re-request) - `options?: Array` Available options for select/radio fields - `formDescription: string` - `iterationId: string` - `pageTitle: string` - `pageUrl: string` - `requestId: string` - `timestamp: number` - `event: "interactive:form_data:error"` - `"interactive:form_data:error"` - `V1AutomateEventInteractiveFormDataRequest` Envelope for the "interactive:form_data:request" event from /v1/automate. - `data: Data` Event data when the agent requests user data for form fields - `fields: Array` - `fieldType: "text" | "email" | "phone" | 8 more` Semantic field type - `"text"` - `"email"` - `"phone"` - `"date"` - `"number"` - `"select"` - `"checkbox"` - `"radio"` - `"textarea"` - `"password"` - `"other"` - `label: string` The field's visible label - `ref: string` Element ref from the accessibility tree (e.g., "E42") - `required: boolean` Whether this field must be filled - `currentValue?: string` Current value if already partially filled - `description?: string` Additional context (e.g., validation error message on re-request) - `options?: Array` Available options for select/radio fields - `formDescription: string` - `iterationId: string` - `pageTitle: string` - `pageUrl: string` - `requestId: string` - `timestamp: number` - `event: "interactive:form_data:request"` - `"interactive:form_data:request"` - `V1AutomateEventSystemDebugCompression` Envelope for the "system:debug_compression" event from /v1/automate. - `data: Data` Event data for compression debug info - `compressedSize: number` - `compressionPercent: number` - `iterationId: string` - `originalSize: number` - `timestamp: number` - `event: "system:debug_compression"` - `"system:debug_compression"` - `V1AutomateEventSystemDebugMessage` Envelope for the "system:debug_message" event from /v1/automate. - `data: Data` Event data for message debug info - `iterationId: string` - `messages: Array` - `timestamp: number` - `event: "system:debug_message"` - `"system:debug_message"` - `V1AutomateEventTaskAborted` Envelope for the "task:aborted" event from /v1/automate. - `data: Data` Event data when a task is aborted - `finalAnswer: string` - `iterationId: string` - `reason: string` - `timestamp: number` - `event: "task:aborted"` - `"task:aborted"` - `V1AutomateEventTaskCompleted` Envelope for the "task:completed" event from /v1/automate. - `data: Data` Event data when a task is completed - `finalAnswer: string | null` - `iterationId: string` - `timestamp: number` - `success?: boolean` - `event: "task:completed"` - `"task:completed"` - `V1AutomateEventTaskMetrics` Envelope for the "task:metrics" event from /v1/automate. - `data: Data` - `aiGenerationCount: number` - `aiGenerationErrorCount: number` - `eventCounts: Record` - `iterationId: string` - `stepCount: number` - `timestamp: number` - `totalInputTokens: number` - `totalOutputTokens: number` - `event: "task:metrics"` - `"task:metrics"` - `V1AutomateEventTaskMetricsIncremental` Envelope for the "task:metrics_incremental" event from /v1/automate. - `data: Data` - `aiGenerationCount: number` - `aiGenerationErrorCount: number` - `eventCounts: Record` - `iterationId: string` - `stepCount: number` - `timestamp: number` - `totalInputTokens: number` - `totalOutputTokens: number` - `event: "task:metrics_incremental"` - `"task:metrics_incremental"` - `V1AutomateEventTaskSetup` Envelope for the "task:setup" event from /v1/automate. - `data: Data` Event data when a task is setup - `browserName: string` - `iterationId: string` - `task: string` - `timestamp: number` - `data?: unknown` - `guardrails?: string` - `hasApiKey?: boolean` - `keySource?: "global" | "env" | "not_set"` - `"global"` - `"env"` - `"not_set"` - `model?: string` - `provider?: string` - `proxy?: string` - `pwCdpEndpoint?: string` - `pwCdpEndpointCount?: number` Total number of CDP endpoints configured (index, not URLs) - `pwCdpEndpoints?: Array` - `pwEndpoint?: string` - `url?: string` - `vision?: boolean` - `event: "task:setup"` - `"task:setup"` - `V1AutomateEventTaskStarted` Envelope for the "task:started" event from /v1/automate. - `data: Data` Event data when a task is started - `iterationId: string` - `plan: string` - `successCriteria: string` - `task: string` - `timestamp: number` - `url: string` - `actionItems?: Array` - `event: "task:started"` - `"task:started"` - `V1AutomateEventTaskTraceContext` Envelope for the "task:trace_context" event from /v1/automate. - `data: Data` Payload for the task:trace_context event. Carries the OpenTelemetry trace ID for this /v1/automate request so consumers can deep-link to distributed-tracing UIs (e.g. Cloud Trace, Cloud Logging) for the run. - `traceId: string` W3C trace ID — 32-character lowercase hexadecimal string. - `event: "task:trace_context"` - `"task:trace_context"` - `V1AutomateEventTaskValidated` Envelope for the "task:validated" event from /v1/automate. - `data: Data` Event data for task validation - `completionQuality: "failed" | "partial" | "complete" | "excellent"` - `"failed"` - `"partial"` - `"complete"` - `"excellent"` - `finalAnswer: string` - `iterationId: string` - `observation: string` - `timestamp: number` - `feedback?: string` - `event: "task:validated"` - `"task:validated"` - `V1AutomateEventTaskValidationError` Envelope for the "task:validation_error" event from /v1/automate. - `data: Data` Event data for validation errors during action response processing - `errors: Array` - `iterationId: string` - `rawResponse: unknown` - `retryCount: number` - `timestamp: number` - `event: "task:validation_error"` - `"task:validation_error"` ### Research Event - `ResearchEvent = V1ResearchEventAnalyzingEnd | V1ResearchEventAnalyzingStart | V1ResearchEventComplete | 20 more` A Server-Sent Event from /v1/research. Typed discriminated union keyed on event. - `V1ResearchEventAnalyzingEnd` Envelope for the "analyzing:end" event from /v1/research. - `data: Data` - `analyzed: number` - `failed: number` - `iteration: number` - `message: string` - `samples: Array` - `domain: string` - `title: string` - `url: string` - `urlSource: "user-input" | "search-result" | "extracted-link"` URL source tracking - where a URL came from - `"user-input"` - `"search-result"` - `"extracted-link"` - `relevance?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `reliability?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `summary?: string` - `timestamp: number` - `event: "analyzing:end"` - `"analyzing:end"` - `V1ResearchEventAnalyzingStart` Envelope for the "analyzing:start" event from /v1/research. - `data: Data` - `iteration: number` - `message: string` - `pageCount: number` - `timestamp: number` - `event: "analyzing:start"` - `"analyzing:start"` - `V1ResearchEventComplete` Envelope for the "complete" event from /v1/research. - `data: Data` complete - Research finished successfully - `message: string` - `metadata: Metadata` Research metadata Note: citedPages, gapEvaluations, outline, and judgments are optional to support fast mode, which skips these phases for maximum speed. - `executedQueries: Array>` - `mode: "fast" | "balanced" | "deep" | 2 more` Research mode determines depth, thinking budget, and quality controls Modes (in order of cost/thoroughness): - **fast**: Quick answers with minimal validation (~$2, 1 iteration, no judge) - **balanced**: Standard research with moderate depth (~$8, 3 iterations, Flash models, no judge) - **deep**: Thorough research with judge review (~$15, 5 iterations, Flash models, with judge) - **max**: Maximum quality with Pro models (~$40, 5 iterations, Pro models, with judge) - **ultra**: Ultimate tier - all Pro models, 10 iterations (expensive, for when accuracy is paramount) - `"fast"` - `"balanced"` - `"deep"` - `"max"` - `"ultra"` - `prompt: string` - `queryComplexity: "simple" | "moderate" | "complex"` - `"simple"` - `"moderate"` - `"complex"` - `researchObjective: string` - `researchPlan: string` - `researchQuestions: Array` - `totalPagesAnalyzed: number` Total pages analyzed across all iterations - `citedPages?: Array` Pages cited in the report, ordered by first citation appearance - `id: string` - `claims: Array` - `sourceQueries: Array` - `url: string` - `depth?: number` - `fullText?: string` Full page text (fetched markdown or search excerpts). Only populated when `includeFullText: true` in ResearchOptions. - Fast mode: Parallel API excerpts (~5000 chars) - Other modes: Fetched page markdown - `parentUrl?: string` - `relevance?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `reliability?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `summary?: string` LLM-generated summary. Undefined in fast mode (no content analysis). - `title?: string` - `urlSource?: "user-input" | "search-result" | "extracted-link"` URL source tracking - where a URL came from - `"user-input"` - `"search-result"` - `"extracted-link"` - `gapEvaluations?: Array` - `gapDescription: string` Based on unanswered/partial questions, what specific information is still needed? - `questionAssessments: Array` Assessment of each research question's status and findings - `findings: string` What we learned (if answered/partial) or what's missing (if unanswered) - `question: string` The research question being assessed - `status: "answered" | "partial" | "unanswered"` Status: answered (clear info), partial (some info, gaps remain), unanswered (no relevant info) - `"answered"` - `"partial"` - `"unanswered"` - `researchCoverage: "Light" | "Moderate" | "Solid" | "Comprehensive"` Research coverage level - assesses quality across all questions. Hierarchy: Light < Moderate < Solid < Comprehensive - **Light**: Basic info on some questions, most need more depth → Continue - **Moderate**: Multiple questions answered, some remain partial → Continue - **Solid**: Most questions well-answered with validated sources → Sufficient to stop - **Comprehensive**: All questions thoroughly answered, exceptional depth → Definitely stop - `"Light"` - `"Moderate"` - `"Solid"` - `"Comprehensive"` - `shouldContinueResearch: boolean` Explicit decision: should research continue with another iteration? - Considers: how many questions unanswered/partial, coverage for mode, remaining iterations - Drives query generation: true → generate queries, false → stop researching - `newResearchQuestions?: Array` New research questions to add (optional, use sparingly) - Only if original decomposition missed something critical - Maximum 2-3 new questions total across all iterations - Most iterations should return empty array or omit this field - `searchQueries?: Array` Search queries to address identified gaps (only when shouldContinueResearch is true) - Target unanswered questions first, then partial questions - 3-10 targeted queries if shouldContinueResearch is true - Omit or provide empty array if shouldContinueResearch is false - `judgments?: Array` - `approved: boolean` - `observation: string` - `score: number` - `feedback?: string` - `metrics?: Metrics` Complete research metrics - `cachedFetches: number` Cached fetch count (subset of fetches) - `cachedSearches: Record` Cached search count by provider name (subset of searches) - `fetches: number` Fetch count (number of pages fetched) - `iterations: number` Number of research iterations performed - `phases: Record` Phase timings with duration in milliseconds - `duration: number` - `robotsBlocked: number` Number of URLs blocked by robots.txt - `searches: Record` Search count by provider name (e.g., "bright-data", "parallel") - `successRates: SuccessRates` Success rate metrics - `analyzes: number` - `fetches: number` - `searches: number` - `tokens: Record` Token usage by model ID (e.g., "gemini-2.5-flash") - `input: number` - `output: number` - `totalDuration: number` Total duration in milliseconds - `outline?: Outline` Report outline from research writer - `directAnswer: string` - `keyTakeaways: Array` - `outline: string` - `relevantSourceIds: Array` - `urlSources?: URLSources` - `extractedLinks: number` - `searchResults: number` - `userProvided: number` - `report: string` - `timestamp: number` - `event: "complete"` - `"complete"` - `V1ResearchEventError` Envelope for the "error" event from /v1/research. - `data: Data` error - Research failed - `error: Error` - `message: string` - `name: string` - `stack?: string` - `message: string` - `timestamp: number` - `activity?: "prefetching" | "planning" | "iteration" | 7 more` Activity types for research workflow - `"prefetching"` - `"planning"` - `"iteration"` - `"searching"` - `"analyzing"` - `"following"` - `"evaluating"` - `"outlining"` - `"writing"` - `"judging"` - `iteration?: number` - `event: "error"` - `"error"` - `V1ResearchEventEvaluatingEnd` Envelope for the "evaluating:end" event from /v1/research. - `data: Data` - `coverage: "Light" | "Moderate" | "Solid" | "Comprehensive"` - `"Light"` - `"Moderate"` - `"Solid"` - `"Comprehensive"` - `gaps: string` - `iteration: number` - `message: string` - `nextQueries: Array` - `questionAssessments: Array` - `findings: string` What we learned (if answered/partial) or what's missing (if unanswered) - `question: string` The research question being assessed - `status: "answered" | "partial" | "unanswered"` Status: answered (clear info), partial (some info, gaps remain), unanswered (no relevant info) - `shouldContinue: boolean` - `timestamp: number` - `event: "evaluating:end"` - `"evaluating:end"` - `V1ResearchEventEvaluatingStart` Envelope for the "evaluating:start" event from /v1/research. - `data: Data` - `iteration: number` - `message: string` - `pagesAnalyzed: number` Total pages analyzed so far (including this iteration) - `questionCount: number` Number of research questions being assessed - `timestamp: number` - `event: "evaluating:start"` - `"evaluating:start"` - `V1ResearchEventFollowingEnd` Envelope for the "following:end" event from /v1/research. - `data: Data` - `failed: number` - `followed: number` - `iteration: number` - `message: string` - `samples: Array` - `domain: string` - `title: string` - `url: string` - `urlSource: "user-input" | "search-result" | "extracted-link"` URL source tracking - where a URL came from - `"user-input"` - `"search-result"` - `"extracted-link"` - `relevance?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `reliability?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `summary?: string` - `timestamp: number` - `event: "following:end"` - `"following:end"` - `V1ResearchEventFollowingStart` Envelope for the "following:start" event from /v1/research. - `data: Data` - `iteration: number` - `linkCount: number` - `message: string` - `timestamp: number` - `event: "following:start"` - `"following:start"` - `V1ResearchEventIterationEnd` Envelope for the "iteration:end" event from /v1/research. - `data: Data` - `isLast: boolean` Whether this is the final iteration - `iteration: number` - `message: string` - `timestamp: number` - `stopReason?: "max_iterations" | "coverage_sufficient"` Why research iterations stopped (only present when isLast is true) - `"max_iterations"` - `"coverage_sufficient"` - `event: "iteration:end"` - `"iteration:end"` - `V1ResearchEventIterationStart` Envelope for the "iteration:start" event from /v1/research. - `data: Data` - `iteration: number` - `maxIterations: number` Maximum iterations for this research mode - `message: string` - `queries: Array` Search queries to execute in this iteration - `timestamp: number` - `event: "iteration:start"` - `"iteration:start"` - `V1ResearchEventJudgingEnd` Envelope for the "judging:end" event from /v1/research. - `data: Data` - `approved: boolean` - `attempt: number` - `message: string` - `score: number` - `timestamp: number` - `feedback?: string` - `event: "judging:end"` - `"judging:end"` - `V1ResearchEventJudgingStart` Envelope for the "judging:start" event from /v1/research. - `data: Data` - `attempt: number` - `maxAttempts: number` Maximum attempts allowed (1 + maxRevisions) - `message: string` - `timestamp: number` - `event: "judging:start"` - `"judging:start"` - `V1ResearchEventOutliningEnd` Envelope for the "outlining:end" event from /v1/research. - `data: Data` - `message: string` - `sourcesSelected: number` - `timestamp: number` - `event: "outlining:end"` - `"outlining:end"` - `V1ResearchEventOutliningStart` Envelope for the "outlining:start" event from /v1/research. - `data: Data` - `message: string` - `pagesAnalyzed: number` Total pages analyzed across all iterations - `qualityPageCount: number` Pages that meet quality threshold (medium+ relevance and reliability) - `timestamp: number` - `event: "outlining:start"` - `"outlining:start"` - `V1ResearchEventPlanningEnd` Envelope for the "planning:end" event from /v1/research. - `data: Data` - `complexity: "simple" | "moderate" | "complex"` - `"simple"` - `"moderate"` - `"complex"` - `message: string` - `objective: string` - `plan: string` - `queries: Array` - `questions: Array` - `timestamp: number` - `event: "planning:end"` - `"planning:end"` - `V1ResearchEventPlanningStart` Envelope for the "planning:start" event from /v1/research. - `data: Data` - `hasPrefetchedContext: boolean` Whether prefetched user-provided URLs exist for context - `message: string` - `timestamp: number` - `event: "planning:start"` - `"planning:start"` - `V1ResearchEventPrefetchingEnd` Envelope for the "prefetching:end" event from /v1/research. - `data: Data` - `failed: number` - `fetched: number` - `message: string` - `timestamp: number` - `event: "prefetching:end"` - `"prefetching:end"` - `V1ResearchEventPrefetchingStart` Envelope for the "prefetching:start" event from /v1/research. - `data: Data` - `message: string` - `timestamp: number` - `urlCount: number` - `urls: Array` - `event: "prefetching:start"` - `"prefetching:start"` - `V1ResearchEventSearchingEnd` Envelope for the "searching:end" event from /v1/research. - `data: Data` - `iteration: number` - `message: string` - `timestamp: number` - `urlsFound: number` - `urlsNew: number` - `event: "searching:end"` - `"searching:end"` - `V1ResearchEventSearchingStart` Envelope for the "searching:start" event from /v1/research. - `data: Data` - `iteration: number` - `message: string` - `queries: Array` - `timestamp: number` - `event: "searching:start"` - `"searching:start"` - `V1ResearchEventStart` Envelope for the "start" event from /v1/research. - `data: Data` start - Research begins - `message: string` - `timestamp: number` - `event: "start"` - `"start"` - `V1ResearchEventWritingEnd` Envelope for the "writing:end" event from /v1/research. - `data: Data` - `attempt: number` - `message: string` - `timestamp: number` - `event: "writing:end"` - `"writing:end"` - `V1ResearchEventWritingStart` Envelope for the "writing:start" event from /v1/research. - `data: Data` - `attempt: number` - `isRevision: boolean` Whether this is a revision attempt (attempt > 1) - `maxAttempts: number` Maximum attempts allowed (1 + maxRevisions) - `message: string` - `timestamp: number` - `previousScore?: number` Previous judgment score if this is a revision - `event: "writing:start"` - `"writing:start"` ### V1 Global Buffer - `V1GlobalBuffer` - `buffer: Buffer` - `byteLength: number` - `byteLength: number` - `byteOffset: number` - `BYTES_PER_ELEMENT: number` - `length: number` ### V1 Research Question Assessment - `V1ResearchQuestionAssessment` Assessment of a single research question - `findings: string` What we learned (if answered/partial) or what's missing (if unanswered) - `question: string` The research question being assessed - `status: "answered" | "partial" | "unanswered"` Status: answered (clear info), partial (some info, gaps remain), unanswered (no relevant info) - `"answered"` - `"partial"` - `"unanswered"` ### Agent Automate Input Response - `AgentAutomateInputResponse` - `status?: string`