Core Types
type ChatMode =
| "auto" | "fast" | "think" | "image" | "video"
| "code" | "research" | "roast" | "genui"
| "data_extraction";
type PersonaInput = "theo" | "none" | { system_prompt: string };
type CompletionAttachment =
| { type: "image_url"; url: string }
| { type: "image_base64"; data: string; mime_type: "image/png" | "image/jpeg" | "image/webp" | "image/gif" };
type TheoImageEngine =
| "auto" | "theo-1-create" | "theo-1-photo" | "theo-1-rapid"
| "theo-1-design" | "theo-1-studio" | "theo-1-type";
type TheoImageQuality = "draft" | "standard" | "hd";
type TheoStealthAspect = "square" | "portrait" | "landscape" | "wide";
type TheoStealthDuration = "5s" | "6s" | "10s";
Additional domain-specific modes are available for specialized use cases. Contact us or check the API for the full list.
Completion Request / Response Types
| Type | Used By | Description |
|---|
CompletionRequest | theo.complete(), theo.stream() | Request body — supports conversation, personality_config, response_style, theo_branding, brand_soul, attachments, stealth pins |
CompletionResponse | theo.complete() | Response — includes request_id, conversation_id, full usage |
CompletionUsage | CompletionResponse, StreamDoneData | { cost_cents, prompt_tokens, completion_tokens, total_tokens, cached? } |
GenUICompletionResponse | theo.complete() when mode === "genui" | Adds genui_code field |
PersonalityConfigInput | CompletionRequest.personality_config | Per-request trait + uncensored-mode override |
ResponseStyleInput | CompletionRequest.response_style | Per-request format/preciseness/intent override |
InlineConversation, InlineConversationMessage | CompletionRequest.conversation | Inline history envelope for stateless callers |
Streaming Types
| Type | Description |
|---|
TheoStream | Class returned by theo.stream() — async-iterable with cancel(), conversationId, usage, model, requestId, content, isCancelled |
StreamEvent | Discriminated union over meta | token | tool | artifact | genui_meta | skills | done | error |
StreamMetaData | Payload of the meta event |
StreamTokenData | { token: string } |
StreamToolData | { name, status, description? } |
StreamSkillsData | { active: [...] } |
StreamDoneData | Payload of the done event (full content + usage + ids) |
StreamErrorData | Payload of the error event — matches the REST error envelope |
GenUIMetaEvent | Payload of the genui_meta event |
Diagnostic Types
| Type | Used By | Description |
|---|
VerifyResult | theo.verify() | { healthy, authenticated, baseUrl, latencyMs, modelCount?, version?, error?, hint? } |
| Type | Used By | Description |
|---|
ImageRequest, ImageResponse | theo.images() | Image request/response |
VideoRequest | theo.video() | Video generation request |
CodeRequest, CodeResponse | theo.code() | Code request/response |
ResearchRequest | theo.research() | Research request |
DocumentRequest, DocumentResponse | theo.documents() | Document request/response |
TtsRequest | theo.tts() | TTS request |
SttResponse | theo.stt() | STT response |
AsyncJobResponse | theo.video(), theo.research() | Async job creation response |
JobStatus | theo.job(), theo.waitForJob() | Job polling response |
Resource Record Types
| Type | Used By | Description |
|---|
ConversationSummary | theo.conversations() | Compact conversation metadata |
ConversationDetail | theo.conversation(id) | Summary plus full message history |
ConversationMessage | ConversationDetail.messages[] | Individual message record |
SkillSummary | theo.skills(), theo.createSkill() | Skill listing shape |
SdkToolDefinition | theo.tools() | Tool definition — name, description, inputSchema, outputSchema?, permissionLevel, requiresApproval, skillId?, category? |
WorkflowRecord | theo.workflows(), theo.createWorkflow() | Workflow shape |
WorkflowRunRecord | theo.triggerWorkflow() | Workflow run shape |
SubmissionRecord | theo.submitSkill(), theo.submissions() | Skill marketplace submission |
SkillVersion | theo.skillVersions() | Version-history entry |
WebhookRecord, WebhookDelivery | Webhook methods | Webhook endpoint + delivery attempt |
HookRecord, HookExecution | Hook methods | Hook + execution history |
EventAck | theo.publishEvent() | Publish acknowledgement |
UsageReport | theo.usage() | Aggregated usage totals + per-mode / per-model breakdowns |
HealthResponse | theo.health() | System health response |
ModelInfo | theo.models() | Model registry entry |
Browser Session Types
| Type | Used By | Description |
|---|
BrowserRegion | BrowserCreateRequest.region | Datacenter region |
BrowserCreateRequest | theo.browser.create() | Start-session options |
BrowserSessionHandle, BrowserSessionSnapshot | theo.browser.create() / list() / get() | Session metadata |
BrowserLiveView | theo.browser.live() | Live-view URL + pages + version |
BrowserEndResult | theo.browser.end() | Duration + billed bytes |
Skill Authoring Types
| Type | Description |
|---|
SkillManifestInput | Input to defineSkill() |
SkillManifest | Validated output of defineSkill() |
SkillCategory | "productivity", "domain", "integration", "automation", "creative" |
SkillPermission | "read:conversations", "read:artifacts", "write:artifacts", etc. |
SkillTriggerType | "manual", "keyword", "event", "schedule" |
SkillToolInput | Tool definition within a skill manifest |
SkillTriggerInput | Trigger configuration |
E.V.I. Types
| Type | Description |
|---|
EviConfig | Configuration for theo.evi() |
CanvasVisibility, CanvasStatus | Canvas visibility + lifecycle |
CanvasRecord | Canvas row as returned by the API |
CreateCanvasInput, UpdateCanvasInput, PublishCanvasInput | Canvas mutation inputs |
CanvasCompileResult, CanvasTestResult, CanvasPublishResult | Compile / test / publish results |
TheoProjectConfig | Configuration for theo.config.ts |
TheoConfig | Client constructor options |
